Artificial Intelligence in Manufacturing
Enabling Intelligent, Flexible and Cost-Effective Production Through AI
- Open Access
- 2024
- Open Access
- Book
- Editor
- John Soldatos
- Publisher
- Springer Nature Switzerland
About this book
This open access book presents a rich set of innovative solutions for artificial intelligence (AI) in manufacturing. The various chapters of the book provide a broad coverage of AI systems for state of the art flexible production lines including both cyber-physical production systems (Industry 4.0) and emerging trustworthy and human-centered manufacturing systems (Industry 5.0). From a technology perspective, the book addresses a wide range of AI paradigms such as deep learning, reinforcement learning, active learning, agent-based systems, explainable AI, industrial robots, and AI-based digital twins. Emphasis is put on system architectures and technologies that foster human-AI collaboration based on trusted interactions between workers and AI systems. From a manufacturing applications perspective, the book illustrates the deployment of these AI paradigms in a variety of use cases spanning production planning, quality control, anomaly detection, metrology, workers’ training, supply chain management, as well as various production optimization scenarios.
This is an open access book.
Advertisement
Table of Contents
-
Architectures and Knowledge Modelling for AI in Manufacturing
-
Frontmatter
-
Reference Architecture for AI-Based Industry 5.0 Applications
- Open Access
Download PDF-versionThe chapter discusses the evolution from Industry 4.0 to Industry 5.0, emphasizing the need for human-centric and sustainable industrial processes. It introduces a reference architecture for AI-based Industry 5.0 applications, focusing on cybersecurity, human-robot collaboration, and safety domains. The architecture includes functionalities such as secure data collection, data provenance, risk assessment, and AI cyber-defense strategies. It also presents blueprints for developing Industry 5.0 solutions compliant with European AI regulations, highlighting the importance of trustworthy and explainable AI systems. The chapter concludes by noting the lack of existing standards for Industry 5.0 systems and the need for comprehensive architectural models to guide the development of trustworthy AI applications.AI Generated
This summary of the content was generated with the help of AI.
AbstractIndustry 5.0 (I5.0) is a novel paradigm for the development and deployment of industrial applications based on Cyber-Physical Systems (CPS). It evolves Industry 4.0 in directions that exploit trustworthy human–AI interactions in human-in-the-loop scenarios. Despite the rising popularity of I5.0, there is still a lack of reference architectures (RAs) that outline the building blocks of I5.0 applications, along with the structuring principles for effectively integrating them in industrial systems. This chapter introduces a reference model for industrial applications that addresses critical elements and requirements of the I5.0, including human–robot collaboration, cybersecurity, safety, and trust. The model enhances state-of-the-art I4.0 Industrial Internet of Things (IIoT) architectures with human-centered I5.0 features and functionalities. Based on this model, the present chapter introduces a set of blueprints that could ease the development, deployment, and operation of I5.0 applications. These blueprints address technical integration, trustworthy operations, as well as the ever-important compliance to applicable regulations such as General Data Protection Regulation (GDPR) and the emerging AI Act. -
Designing a Marketplace to Exchange AI Models for Industry 5.0
- Open Access
Download PDF-versionThe chapter delves into the creation of a marketplace for exchanging AI models specifically designed for Industry 5.0 and smart manufacturing. It introduces a high-level architecture that includes user-friendly interfaces, trusted transactions, and secure ownership management using blockchain technology. The marketplace supports a wide range of AI models and ensures interoperability through standardized formats like ONNX and PMML. Additionally, it emphasizes the importance of metadata management and ontology for effective model description and retrieval. The knowlEdge Marketplace aims to facilitate intelligent production by offering a platform where AI solutions can be traded securely and efficiently, addressing the unique needs of the manufacturing sector.AI Generated
This summary of the content was generated with the help of AI.
AbstractNowadays, the market for AI services is continuously growing and it is expected to exceed 5 trillion euros in the next 5 years. However, the sharing of knowledge is primarily achieved by the sharing of published AI-related papers. The sharing of the trained AI/ML models is still in its infancy stage and in some domains it does not even exist. In this chapter, a marketplace for exchanging AI models related to smart manufacturing and Industry 5.0 domains is introduced. The proposed AI Marketplace consists of a semantic-based repository that manages the AI models, a blockchain-based framework that adds the business logic and web-based user interfaces that enable models’ exploration and sharing, and transactions among the stakeholders. The purpose of this chapter is to present the implementation details of this AI Model Marketplace by highlighting the key concepts and technologies used along with the main supported functionalities. By using such a marketplace, the manufacturing companies are able to capitalize in a large variety of AI models to solve various problems enabling intelligent, flexible, and cost-effective production. -
Human-AI Interaction for Semantic Knowledge Enrichment of AI Model Output
- Open Access
Download PDF-versionThis chapter delves into the integration of human-AI interaction for enhancing AI model outputs in the manufacturing sector. It introduces the concept of domain knowledge fusion, where domain experts collaborate with AI systems to provide contextual knowledge and feedback. This process involves inspecting AI model outputs, correcting inaccuracies, and retraining models to improve predictive performance. The chapter also highlights the use of ontology enrichment systems and intuitive interfaces to facilitate this collaboration. Additionally, it discusses the challenges and future research directions in scaling human-AI collaboration in manufacturing settings. By emphasizing the iterative improvement of AI models through human feedback, this chapter offers a unique perspective on enhancing AI effectiveness in manufacturing processes.AI Generated
This summary of the content was generated with the help of AI.
AbstractModern manufacturing requires developing a framework of AI solutions that capture and process data from various sources including from human-AI collaboration. This chapter tries to describe the concept of domain knowledge fusion in human-AI collaboration for manufacturing. Human interaction with AI is enabled in such a way that the domain expert not only inspects the output of the AI model but also injects engineered knowledge in order to retrain AI models for iterative improvement. Domain knowledge fusion is a technique that involves combining knowledge from multiple domains or sources to produce a more complete solution by augmenting learned knowledge, i.e., the knowledge generated by the AI model with engineered knowledge, i.e., the knowledge provided by the domain expert. The concept developed in this chapter demonstrates how the domain expert interacts with AI systems to observe and decide the veracity of the learned knowledge with respect to the given context. It enables humans to collaborate with AI systems through intuitive interfaces that help domain experts in interpreting insights, validating the findings, and applying domain knowledge to gain a deeper understanding of the data. -
Examining the Adoption of Knowledge Graphs in the Manufacturing Industry: A Comprehensive Review
- Open Access
Download PDF-versionThe chapter delves into the transformative potential of Knowledge Graphs (KGs) in the manufacturing industry, focusing on their role in Industry 4.0 and the anticipated Industry 5.0. It examines how KGs facilitate the integration of human decision-making with AI-generated insights, thereby improving processes such as knowledge management, predictive maintenance, and supply chain optimization. The study reviews the current usage scenarios and challenges, identifying key research questions and providing insights into the most active research communities and domains. It also highlights the prevalence of RDF and LPG as KG types and discusses the knowledge-driven and data-driven approaches to KG creation. The chapter concludes by emphasizing the need for standardized procedures and best practices to fully harness the power of KGs in manufacturing.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe integration of Knowledge Graphs (KGs) in the manufacturing industry can significantly enhance the efficiency and flexibility of production lines and improve product quality. By integrating and contextualizing information about devices, equipment, production resources, location, usage, and related data, KGs can be a powerful operational tool. Moreover, KGs can contribute to the intelligence of manufacturing processes by providing insights into the complex and competitive manufacturing landscape. This research work presents a comprehensive analysis of the current trends utilizing KG in the manufacturing sector. We provide an overview of the state of the art in KG applications in manufacturing and highlight the critical issues that need to be addressed to enable a successful implementation. Our research aims to contribute to advancing KG technology in manufacturing and realizing its full potential to enhance manufacturing operations and competitiveness. -
Leveraging Semantic Representations via Knowledge Graph Embeddings
- Open Access
Download PDF-versionThis chapter delves into the significance of knowledge graphs (KGs) in data-driven domains like healthcare, finance, and manufacturing. It introduces the concept of KG embeddings, which transform KG elements into numerical representations, enabling applications like recommendation systems and question answering. The author discusses various embedding formalisms, including tensor decomposition models, geometric models, and deep learning models. The chapter also explores the challenges and benefits of using KG embeddings in the manufacturing domain, particularly highlighting the need for dynamic embedding methods to capture evolving relationships. The Navi approach is introduced as a promising solution for real-time and structure-preserving dynamic KG embeddings. The chapter concludes by emphasizing the potential of KGs and KG embeddings to optimize processes and enhance productivity in the manufacturing sector.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe representation and exploitation of semantics has been gaining popularity in recent research, as exemplified by the uptake of large language models in the field of Natural Language Processing (NLP) and knowledge graphs (KGs) in the Semantic Web. Although KGs are already employed in manufacturing to integrate and standardize domain knowledge, the generation and application of corresponding KG embeddings as lean feature representations of graph elements have yet to be extensively explored in this domain. Existing KGs in manufacturing often focus on top-level domain knowledge and thus ignore domain dynamics, or they lack interconnectedness, i.e., nodes primarily represent non-contextual data values with single adjacent edges, such as sensor measurements. Consequently, context-dependent KG embedding algorithms are either restricted to non-dynamic use cases or cannot be applied at all due to the given KG characteristics. Therefore, this work provides an overview of state-of-the-art KG embedding methods and their functionalities, identifying the lack of dynamic embedding formalisms and application scenarios as the key obstacles that hinder their implementation in manufacturing. Accordingly, we introduce an approach for dynamizing existing KG embeddings based on local embedding reconstructions. Furthermore, we address the utilization of KG embeddings in the Horizon2020 project Teaming.AI (www.teamingai-project.eu.) focusing on their respective benefits. -
Architecture of a Software Platform for Affordable Artificial Intelligence in Manufacturing
- Open Access
Download PDF-versionThis chapter delves into the architecture of a software platform, KITT4SME, designed to make AI accessible and affordable for manufacturing SMEs. It highlights the challenges and opportunities of AI adoption in small and mid-sized enterprises, and introduces the KITT4SME platform as a solution to democratize AI technologies. The platform is built on a modular, cloud-based architecture that supports the integration of AI components and services. It also leverages open-source technologies like FIWARE to ensure interoperability, security, and scalability. The chapter discusses the functionalities and components of the platform, including data gathering, processing, and visualization, as well as the use of AI models for decision-making and performance optimization. A real-world use case in the injection molding industry is presented to illustrate the practical application of the platform. The chapter concludes by emphasizing the potential of the KITT4SME platform to enhance the competitiveness of European SMEs in the manufacturing sector.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe fourth industrial revolution has driven companies of all sizes to embrace digitalization, recognizing the potential of AI technologies for data analysis and real-time decision-making. However, the adoption of AI by manufacturing SMEs faces challenges related to cost, accessibility, and the need for expertise. To address these challenges, this chapter introduces a groundbreaking platform developed as part of the EU H2020 KITT4SME project. The platform aims to democratize the adoption of AI tools by leveraging the “as-a-service” model, making them affordable and readily available for SMEs. It follows a five-step workflow (diagnose–compose–sense–intervene–evolve) to provide tailor-made AI solutions to SMEs. The distinctive functionality of the platform allows for the composition of AI components from a marketplace into a customized service offering for companies, filling a gap in existing AI platforms. The KITT4SME platform has been successfully applied in four use cases within the project and to 18 external demonstrators via Open Calls. This chapter presents one of the internal use cases to showcase the capabilities and benefits of the KITT4SME platform. -
Multisided Business Model for Platform Offering AI Services
- Open Access
Download PDF-versionThe chapter introduces the concept of multisided business models for platform-based AI services, highlighting the essential role of platforms in minimizing transaction costs and leveraging network effects. It focuses on the KITT4SME project, a Horizon 2020 initiative aimed at European SMEs, and uses the Platform Design Toolkit (PDT) to develop a robust business model. The PDT methodology is detailed, including steps for mapping ecosystems, portraying entity roles, analyzing value exchanges, and designing core relationships. The case study showcases how the PDT can be applied to create a sustainable and scalable AI platform, offering insights into revenue models and the challenges of balancing network effects. The chapter concludes with a call for further quantitative assessment of the business model's sustainability, emphasizing the need for setting up a minimum viable platform (MVP) to validate design assumptions.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe development of B2B platforms has led to the diffusion of business models (BMs) based on the concept of sharing economy. In recent years, multisided platform BMs have become an important way of creating and capturing value even though the phenomenon remains undertheorized (Zhao et al., Long Range Planning 53(4):101892, 2020). Multisided platforms (MSPs) are present in an increasing number of sectors due to the development of the Internet, digital technologies, and artificial intelligence (AI). The manufacturing sector has not been untouched by this trend; however, it still struggles to establish value drivers to support small- and medium-sized enterprises (SMEs) in the change. The objective of the proposed study is to present an ecosystem for the SME manufacturing sector, which will be based on the selected MSP offering AI services. An initial BM for the AI platform as a service will be design, and a revenue model will be proposed within it. The selected case allowed the use of a methodological approach (PDT – Platform Design Toolkit) to the design of an MSP business model based on a qualitative analysis of the dynamics governing the platform ecosystem. The originality of the research stems from the reliance on data obtained from the implementation of the KITT4SME project (H2020, GA 952119). The study results indicate that it is crucial to properly identify the needs of the platform’s stakeholders, and then precisely define the values and the mechanisms for exchanging them through MSP. -
Self-Reconfiguration for Smart Manufacturing Based on Artificial Intelligence: A Review and Case Study
- Open Access
Download PDF-versionThe chapter delves into the concept of self-reconfiguration in smart manufacturing, discussing its importance in adapting to dynamic market demands. It traces the evolution from flexible manufacturing systems to reconfigurable and self-reconfigurable systems, emphasizing the role of AI in enhancing responsiveness and efficiency. The text also presents a case study on the GAMHE 5.0 pilot line, demonstrating the integration of AI-based visual inspection, AutoML for process optimization, and fuzzy logic for system reconfiguration. These approaches showcase the potential of AI in achieving real-time adaptability and improved performance in manufacturing processes.AI Generated
This summary of the content was generated with the help of AI.
AbstractSelf-reconfiguration in manufacturing systems refers to the ability to autonomously execute changes in the production process to deal with variations in demand and production requirements while ensuring a high responsiveness level. Some advantages of these systems are their improved efficiency, flexibility, adaptability, and cost-effectiveness. Different approaches can be used for designing self-reconfigurable manufacturing systems, including computer simulation, data-driven methods, and artificial intelligence-based methods. To assess an artificial intelligence-based solution focused on self-reconfiguration of manufacturing enterprises, a pilot line was selected for implementing an automated machine learning method for finding and setting optimal parametrizations and a fuzzy system-inspired reconfigurator for improving the performance of the pilot line. Additionally, a deep learning segmentation model was integrated into the pilot line as part of a visual inspection module, enabling a more efficient management of the production line workflow. The results obtained demonstrate the potential of self-reconfigurable manufacturing systems to improve the efficiency and effectiveness of production processes.
-
-
Multi-agent Systems and AI-Based Digital Twins for Manufacturing Applications
-
Frontmatter
-
Digital-Twin-Enabled Framework for Training and Deploying AI Agents for Production Scheduling
- Open Access
Download PDF-versionThe chapter introduces a Digital-Twin-Enabled framework for training and deploying AI agents for production scheduling, addressing the complex nature of production scheduling problems. It discusses the use of Digital Twins and Asset Administration Shells to enhance real-time decision-making and adaptability in dynamic manufacturing environments. The framework includes a Multi-Agent System that uses AI scheduling agents to generate efficient schedules. The chapter also highlights the development of mathematical optimization models, data-driven optimization approaches, and deep reinforcement learning agents for dynamic scheduling problems. It concludes with a case study that demonstrates the implementation of the proposed framework in the bicycle industry.AI Generated
This summary of the content was generated with the help of AI.
AbstractDigital manufacturing tools aim to provide intelligent solutions that will help manufacturing industry adapt to the volatile work environment. Modern technologies such as artificial intelligence (AI) and digital twins (DT) are primarily exploited in a way to simulate and select efficient solutions from a broad range of alternative decisions. This work aims to couple DT and AI technologies in a framework where training, testing, and deployment of AI agents is made more efficient in production scheduling applications. A set of different AI agents were developed, utilizing key optimization technologies such as mathematical programming, deep learning, heuristic algorithms, and deep reinforcement learning are developed to address hard production schedule optimization problems. DT is the pilar technology, which is used to simulate accurately the production environment and allow the agents to reach higher efficiency. On top of that, Asset Administration Shell (AAS) technology, being the pilar components of Industry 4.0 (I4.0), was used for transferring data in a standardized format in order to provide interoperability within the multi-agent system (MAS) and compatibility with the rest of I4.0 ecosystem. The system validation was provided in the manufacturing system of the bicycle industry by improving the business performance. -
A Manufacturing Digital Twin Framework
- Open Access
Download PDF-versionThe chapter delves into the transformative potential of digital twin (DT) technology in the manufacturing industry. It defines DTs, their types, and usages, highlighting their role in optimizing processes and increasing productivity. The knowlEdge Digital Twin Framework is introduced, detailing its components and alignment with ISO 23247 standards. A case study on a dairy company demonstrates the practical application of DTs for process improvement and scheduling optimization. The chapter concludes by emphasizing the future potential of DT technology in revolutionizing the manufacturing sector.AI Generated
This summary of the content was generated with the help of AI.
AbstractDigital twin technology has become a driving force in the transformation of the manufacturing industry, playing a crucial role in optimizing processes, increasing productivity, and enhancing product quality. A digital twin (DT) is a digital representation of a physical entity or process, modeled to improve decision-making in a safe and cost-efficient environment. Digital twins (DTs) cover a range of problems in different domains at different phases in the lifecycle of a product or process. DTs have gained momentum due to their seamless integration with technologies such as IoT, machine learning algorithms, and analytics solutions. DTs can have different scopes in the manufacturing domain, including process level, system level, asset level, and component level. This work presents the knowlEdge Digital Twin Framework (DTF), a toolkit that comprises a set of tools to create specific instances of DTs in the manufacturing process. This chapter explains how the DTF relates to other standards, such as ISO 23247. This chapter also presents the implementation done for a dairy company. -
Reinforcement Learning-Based Approaches in Manufacturing Environments
- Open Access
Download PDF-versionThis chapter delves into the integration of reinforcement learning (RL) in manufacturing environments, highlighting the significant role of Industry 4.0 principles and the digital twin concept. It discusses the challenges and solutions in optimizing path trajectories for CNC machines and robotic manipulation of complex materials using advanced RL techniques. The chapter also explores the use of deep learning in RL algorithms, showcasing their effectiveness in addressing high-dimensional spaces and enhancing the performance of robotic systems. Practical examples and case studies are presented to illustrate the potential of RL in improving manufacturing processes and productivity.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe application of reinforcement learning often faces limitations due to the exploration phase, which can be costly and risky in various contexts. This is particularly evident in manufacturing industries, where the training phase of a reinforcement learning agent is constrained, resulting in suboptimal performance of developed strategies. To address this challenge, digital environments are typically created, allowing agents to freely explore the consequences of their actions in a controlled setting. Strategies developed in these digital environments can then be tested in real scenarios, and secondary training can be conducted using hybrid data that combines digital and real-world experiences.In this chapter, we provide an introduction to reinforcement learning and showcase its application in two different manufacturing scenarios. Specifically, we focus on the woodworking and textile sectors, which are part of ongoing research activities within two distinct European Research Projects. We demonstrate how reinforcement learning is implemented in a digital context, with the ultimate goal of deploying these strategies in real systems. -
A Participatory Modelling Approach to Agents in Industry Using AAS
- Open Access
Download PDF-versionThe chapter introduces a participatory modelling approach for agents in industry using Asset Administration Shell (AAS). It highlights the challenges of traditional standardization processes and proposes a bottom-up methodology to develop high-quality, reusable AAS models. The methodology is divided into four phases: design, define, align, and deploy, with a focus on agent modelling. The authors also present an online repository for sharing and visualizing AAS models, facilitating collaboration and reducing duplication of work. The chapter emphasizes the importance of community-driven standards and provides practical tools to enhance interoperability and standardization in industrial settings.AI Generated
This summary of the content was generated with the help of AI.
AbstractTo develop interoperable and flexible systems, Industry 4.0 solutions need available models and standardization. There is not just a need for physical but also digital asset descriptions, which can be reused in different cases. Particularly, with newer complex system integration, there is an increase in implementations of agent-based solutions. Although the meta-language Asset Administration Shell aims to help with integration, it is still not mature enough and lacks sufficient methods and tooling. To support the aim for interoperability, we present three tools: an updated generic agent model, a methodology for AAS model creation, and a platform for model visualization and distribution. -
I4.0 Holonic Multi-agent Testbed Enabling Shared Production
- Open Access
Download PDF-versionThe chapter delves into the application of Multi-Agent Systems (MAS) in modern manufacturing environments, emphasizing the holonic MAS approach to enable shared production. It discusses the challenges of adaptability, agility, and responsiveness in manufacturing, highlighting the need for decentralized, distributed, and networked manufacturing systems. The text introduces Cloud Manufacturing and Production Level 4 as solutions for highly diversified and reconfigurable supply chains. It then focuses on the holonic MAS architecture, its control structures, and the use of cyber-physical production modules (CPPMs) to encapsulate production functionalities. The chapter also explores the use of Asset Administration Shells (AAS) and Gaia-X for data exchange and data sovereignty. The holonic MAS is implemented in a demonstrator testbed at SmartFactory KL, showcasing its ability to handle dynamic optimization and decision-making processes. The text concludes by discussing the limitations and future extensions of the MAS, emphasizing the need for more complex planning systems and factory-wide monitoring.AI Generated
This summary of the content was generated with the help of AI.
AbstractThis chapter aims at presenting the system architecture of a distributed production testbed embedded in an interoperable Shared Production network. The goal of the modular architecture is to enable flexible, resilient and distributed production. The presented approach illustrates how Multi-Agent Systems (MAS) can be incorporated in the manufacturing domain for distributed components on different hierarchy layers based on a holonic approach. The concept is validated on the real-world demonstrator testbed of the SmartFactoryKL. Furthermore, the MAS is combined with Industry 4.0 technologies such as the Asset Administration Shell and OPC UA. -
A Multi-intelligent Agent Solution in the Automotive Component–Manufacturing Industry
- Open Access
Download PDF-versionThe chapter delves into the challenges and variabilities in the automotive component manufacturing industry, highlighting the need for a more integrated and data-driven approach. It introduces the Multi-intelligent Agent Solution (MAS4AI), a framework that leverages AI to optimize production processes. The MAS4AI system is designed to interact seamlessly with various data sources and agents, improving communication and coordination across different manufacturing stages. The implementation of MAS4AI at Fersa Bearings is used as a case study, demonstrating how the system enhances production control, quality, and efficiency. The chapter also discusses the data architecture and agent-based Asset Administration Shell (AAS) approach, providing a comprehensive overview of how AI can be effectively integrated into manufacturing environments.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe manufacturing industry is an ecosystem full of changes and variations where production conditions are never the same. As an example, the raw materials received from suppliers differ from one another, though within tolerances. And similar variations appear in all areas of manufacturing, such as tool wearing, the statuses of production machines, and even operator decisions.Improvements to production must factor in technical considerations and economic ones. Several points of view must be included to determine the best solution. Even when applying artificial intelligence (AI) in the manufacturing process, the situation should be similar: Several agents with different goals should interact to determine the most holistic solution.This paper presents the ontology, semantics, and architecture that facilitates multiagent interaction. The Reference Architecture Model Industry 4.0, or RAMI 4.0 (RAMI4.0 – 2018 – DE (plattform-i40.de)), has been selected as the basis for this approach.Given that most of the time, the operator’s decision is based on intuition and experience, not based on data analysis, this paper also analyses which data architecture will permit the data analysis of raw materials, finished products, tooling characteristics and statuses, machine parameters, and external conditions, to minimize the influence of intuition and personal bias on decision-making in manufacturing. -
Integrating Knowledge into Conversational Agents for Worker Upskilling
- Open Access
Download PDF-versionThe chapter delves into the integration of knowledge into conversational agents for worker upskilling, addressing the challenges posed by the current labor market. It reviews existing conversational agents and resources, such as O*NET and ESCO, and proposes a solution that leverages these resources to enhance the capabilities of conversational agents. The proposed solution aims to provide workers with reliable information about their jobs and potential growth paths, while also addressing technical and privacy challenges. The chapter concludes by highlighting the potential benefits and impacts of these technologies on workers, organizations, and the labor market as a whole.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe labor market is a key part of an economy. Several existing online platforms allow the upload of resumes and the search for a job. One of their limitations, however, is that obtaining the best opportunity can be hard because certain jobs need some experiences, abilities, and features that an applicant might not know. The recent diffusion and employment of conversational agents definitely have proven to benefit this kind of issue. For example, ChatGPT has shown impressive outcomes in different domains and for a variety of tasks. It has weaknesses, although, related to the veracity of the responses it generates, which might deceive the user interacting with it. The usage of external domain knowledge is the direction we suggest in this chapter. Several lexical databases and taxonomies have already been collected and designed by different organizations. We illustrate a list of such resources and provide a solution that integrates conversational agents with relevant information extracted from one of such resources showing the benefits and the impact that our proposal can generate. -
Advancing Networked Production Through Decentralised Technical Intelligence
- Open Access
Download PDF-versionThe chapter delves into the transformative potential of Decentralised Technical Intelligence (DTI) for networked production, highlighting the integration of human and machine intelligence to enhance operational efficiency and flexibility. It presents a detailed roadmap for implementing DTI, including building blocks such as universal transparency, cooperative innovation, and sustainable operations. The text also underscores the need for a business-centric approach to ensure the economic viability and real-world applicability of these technological advancements. By exploring real-world case studies and discussing the challenges and opportunities of DTI, the chapter offers a compelling vision for the future of manufacturing, emphasising the shift towards more decentralised, agile, and resilient production networks.AI Generated
This summary of the content was generated with the help of AI.
AbstractIn today’s competitive landscape, networked production plays a crucial role in enabling companies to create value and remain competitive. By integrating advanced logistics and supply chain processes, companies optimise resources through cooperation and dynamic arrangements. However, managing the emerging complexity requires a new and intelligent approach. Decentralised Technical Intelligence (DTI) is a response to this challenge. It refers to the distributed and autonomous intelligence embedded in interconnected systems, devices, and agents—involving both humans and machines. By combining the strengths of humans and artificial intelligence (AI), DTI creates a coordinated environment that enhances the overall system intelligence. This collaboration leads to greater autonomy and enables multiple DTI agents to operate independently within a decentralised network. To achieve advanced networked production with DTI, a roadmap will be established, encompassing building blocks that focus on transparency, cooperation, sustainability, seamless integration and intelligent network control. All building blocks are linked to a vision, value promise and development pathway. As networked production evolves, it gives rise to new business models and demands new skills and expertise. By following this roadmap, DTI unlocks its potential for advancement, creating value and fostering competitiveness.
-
-
Trusted, Explainable and Human-CenteredAI Systems
-
Frontmatter
-
Wearable Sensor-Based Human Activity Recognition for Worker Safety in Manufacturing Line
- Open Access
Download PDF-versionThis chapter delves into the transformative role of wearable sensor-based human activity recognition (HAR) in enhancing worker safety and optimizing productivity within manufacturing environments. By leveraging advanced sensor technologies and machine learning algorithms, the chapter explores how real-time monitoring of workers’ activities can identify safety hazards and improve operational efficiency. The use case at the SmartFactory Testbed demonstrates the practical application of HAR, showcasing how accurate activity recognition can prevent collisions between workers and robots. The chapter also introduces innovative deep learning techniques such as adversarial learning and contrastive learning to enhance the accuracy and generalization of activity recognition models. Additionally, it discusses the ethical considerations and challenges associated with wearable sensor systems, providing a holistic view of the potential and limitations of HAR in manufacturing settings. By presenting real-world applications and cutting-edge research, this chapter offers valuable insights into the future of smart manufacturing and the role of wearable sensors in promoting worker well-being and operational excellence.AI Generated
This summary of the content was generated with the help of AI.
AbstractImproving worker safety and productivity is of paramount importance in the manufacturing industry, driving the adoption of advanced sensing and control systems. This concern is particularly relevant within the framework of Industry 5.0. In this context, wearable sensors offer a promising solution by enabling continuous and unobtrusive monitoring of workers’ activities in the manufacturing line. This book chapter focuses on wearable sensor-based human activity recognition and its role in promoting worker safety in manufacturing environments. Specifically, we present a case study on wearable sensor-based worker activity recognition in a manufacturing line with a mobile robot. As wearable sensors comprise various sensor types, we investigate and compare sensor data fusion approaches using neural network models to effectively handle the multimodal sensor data. In addition, we introduce several deep learning-based techniques to improve the performance of human activity recognition. By harnessing wearable sensors for human activity recognition, this book chapter provides valuable insights into improving worker safety on the manufacturing line, aligning with the principles of the Industry 5.0 paradigm. The chapter sheds light on the potential of wearable sensor technologies and offers avenues for future research in this field. -
Object Detection for Human–Robot Interaction and Worker Assistance Systems
- Open Access
Download PDF-versionThe chapter delves into the transformative potential of object detection technology in industrial environments, emphasizing its role in enhancing human–robot interaction and worker assistance systems. It discusses the integration of advanced algorithms and sensor fusion techniques to improve safety, streamline workflows, and optimize processes. The text explores real-world applications, such as automated logistics and quality inspection, and introduces innovative approaches like context-based object detection for small object detection in assembly scenarios. Additionally, it highlights the advantages of synthetic data generation and continual learning techniques for enhancing object detection models. The chapter concludes by summarizing key findings and emphasizing the substantial benefits of object detection in industrial settings, making it a valuable resource for professionals seeking to understand and implement these technologies.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe primary goal of this research is to describe the scenarios, challenges, and complexities associated with object detection in industrial environments and to provide clues on how to tackle them. While object detection in production lines offers significant advantages, it also poses notable difficulties. This chapter delves into the common scenarios and specific challenges encountered in industrial object detection and proposes targeted solutions for various use cases. For example, synthetic data play a pivotal role in overcoming labeling challenges, particularly when it comes to small objects. By harnessing synthetic data, we can efficiently track and debug object detection results, ensuring faster identification and resolution of many data labeling issues. Synthetic data facilitate effective tracking and debugging of object detection results, streamlining the overall workflow. Furthermore, we explore the application of object detection in head-worn devices, utilizing the human point of view (POV) as a valuable perspective. This approach not only enhances human assistance systems but also enhances safety in specific use cases. Through this research endeavor, our aim is to contribute to the advancement of the whole process of object detection methods in complex industrial environments. -
Boosting AutoML and XAI in Manufacturing: AI Model Generation Framework
- Open Access
Download PDF-versionThe AI Model Generation (AMG) framework is introduced as a solution for non-experts in AI to create supervised models automatically. The framework includes submodules for data retrieval, pre-processing, cost computation, hyperparameter tuning, training, inference, and explainability. It supports various data types and deployment scenarios, ensuring models are interoperable and containerized for seamless integration into manufacturing environments. The chapter also discusses the challenges of AI adoption in manufacturing and how the AMG framework addresses these through user-centered tools and partnerships with experts. The framework is part of the European project knowlEdge, aiming to enhance AI-powered manufacturing services across the edge-to-cloud continuum.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe adoption of AI in manufacturing enables numerous benefits that can significantly impact productivity, efficiency, and decision-making processes. AI algorithms can optimize production schedules, inventory management, and supply chain operations by analyzing historical data and producing demand forecasts. In spite of these benefits, some challenges such as integration, lack of data infrastructure and expertise, and resistance to change need to be addressed for the industry to successfully adopt AI. To overcome these issues, we introduce the AI Model Generation framework (AMG), able to automatically generate AI models that adjust to the user’s needs. More precisely, the model development process involves the execution of a whole chain of sub-processes, including data loading, automated data pre-processing, cost computation, automatic model hyperparameter tuning, training, inference, explainability generation, standardization, and containerization. We expect our approach to aid non-expert users into more effectively producing machine and deep learning algorithms and hyperparameter settings that are appropriate to solve their problems without sacrificing privacy and relying on third-party services and infrastructure as few as possible. -
Anomaly Detection in Manufacturing
- Open Access
Download PDF-versionThe chapter delves into the critical role of anomaly detection in manufacturing, discussing various statistical methods and the advanced approach of deep learning, particularly autoencoders. A case study from the EU project knowlEdge illustrates the practical application of autoencoders in detecting anomalies during the blow molding process of fuel tanks. The chapter also emphasizes the importance of human expertise in refining these models, ensuring accurate and efficient anomaly detection. By combining theoretical insights with real-world examples, this chapter offers valuable guidance for enhancing quality control and safety in manufacturing processes.AI Generated
This summary of the content was generated with the help of AI.
AbstractThis chapter provides an introduction to common methods of anomaly detection, which is an important aspect of quality control in manufacturing. We give an overview of widely used statistical methods for detecting anomalies based on k-means, decision trees, and Support Vector Machines. In addition, we examine the more recent deep learning technique of autoencoders. We conclude our chapter with a case study from the EU project knowlEdge, where an autoencoder was utilized in order to detect anomalies in a manufacturing process of fuel tanks. Throughout the chapter, we emphasize the importance of humans-in-the-loop and provide an example of how AI can be used to improve manufacturing processes. -
Towards Industry 5.0 by Incorporation of Trustworthy and Human-Centric Approaches
- Open Access
Download PDF-versionThe chapter discusses the evolution from Industry 4.0 to Industry 5.0, emphasizing the role of AI in creating sustainable, human-centric, and resilient industries. It introduces the TAI-PRM framework, which combines risk management principles with trustworthy AI requirements. The framework is designed to help management units and developers incorporate trustworthy requirements into the AI life cycle, ensuring compliance with current regulations. The chapter also highlights the importance of human-centric AI and the challenges of managing ethical considerations in AI development. It provides a detailed overview of the TAI-PRM framework, including its goals, components, and implementation strategies. Additionally, the chapter discusses the use of Failure Mode and Effects Analysis (FMEA) for risk assessment and the importance of considering ethical risks in AI asset management. The TAI-PRM framework is presented as a tool for performing and evaluating approaches for trustworthy AI, offering a structured approach to handling risks in AI assets. The chapter concludes by emphasizing the need for further efforts to address the challenges of AI risk management and the importance of considering the human factor in these processes.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe industrial sector has been a major adopter of new technologies for decades, driving economic and societal progress. The path by which industry embraces new techniques has a significant impact on the environment and society and thus must be guided by principles of sustainability and trustworthiness. In this chapter, we explore the current paradigm in which Industry 4.0 is evolving towards Industry 5.0, where artificial intelligence (AI) and other advance technologies are being used to build services from a sustainable, human-centric, and resilient perspective. We examine how AI can be applied in industry while respecting trustworthy principles and collect information to define how well these principles are adopted. Furthermore, it is presented a perspective on the industry’s approach towards adopting trustworthy AI (TAI), and we propose steps to foster its adoption in an appropriate manner. We also examine the challenges and risks associated with the adoption of AI in industry and propose strategies to mitigate them. This chapter intends to serve researchers, practitioners, and policymakers interested in the intersection of AI, industry, and sustainability. It provides an overview of the latest developments in this field and offers practical guidance for those seeking to promote the adoption of TAI. -
Human in the AI Loop via xAI and Active Learning for Visual Inspection
- Open Access
Download PDF-versionThe chapter discusses the evolution of manufacturing through Industry 5.0, emphasizing human-centric approaches and the integration of AI to enhance visual inspection processes. It introduces active learning and explainable AI paradigms, highlighting their potential to improve machine learning models and human-machine collaboration. The authors present a vision for an AI-first human-centric visual inspection solution and detail experiments and results from the EU H2020 STAR project, showcasing the practical applications of these techniques. The chapter also explores the challenges and future directions in this field, including the development of human-digital twins and defenses against adversarial attacks in AI-driven systems.AI Generated
This summary of the content was generated with the help of AI.
AbstractIndustrial revolutions have historically disrupted manufacturing by introducing automation into production. Increasing automation reshapes the role of the human worker. Advances in robotics and artificial intelligence open new frontiers of human-machine collaboration. Such collaboration can be realized considering two sub-fields of artificial intelligence: active learning and explainable artificial intelligence. Active learning aims to devise strategies that help obtain data that allows machine learning algorithms to learn better. On the other hand, explainable artificial intelligence aims to make the machine learning models intelligible to the human person. The present work first describes Industry 5.0, human-machine collaboration, and state-of-the-art regarding quality inspection, emphasizing visual inspection. Then it outlines how human-machine collaboration could be realized and enhanced in visual inspection. Finally, some of the results obtained in the EU H2020 STAR project regarding visual inspection are shared, considering artificial intelligence, human-digital twins, and cybersecurity. -
Multi-Stakeholder Perspective on Human-AI Collaboration in Industry 5.0
- Open Access
Download PDF-versionThe chapter delves into the transformative potential of AI in smart manufacturing, highlighting its ability to optimize machinery maintenance, detect defects, and enhance operator safety. It presents three use cases illustrating AI's role in quality inspection, parameter optimization, and ergonomic risk assessment. The authors emphasize the importance of mutual trust and effective communication between human operators and AI systems. They also discuss the critical success factors and quality characteristics identified through stakeholder interviews, offering valuable insights into the design and implementation of AI-based platforms in Industry 5.0.AI Generated
This summary of the content was generated with the help of AI.
AbstractAI has gained significant traction in manufacturing, offering tremendous potential for enhancing production efficiency, cost reduction, and safety improvements. Consequently, developing AI-based software platforms that facilitate collaboration between human operators and AI services is crucial. However, integrating the different stakeholder perspectives into a common framework is a complex process that requires careful consideration. Our research has focused on identifying the individual relevance of varying quality characteristics per stakeholder toward such a software platform. Therefore, this work proposes an overview on the vital success factors related to human-AI teaming that can be used to measure fulfillment. -
Holistic Production Overview: Using XAI for Production Optimization
- Open Access
Download PDF-versionThe chapter 'Holistic Production Overview: Using XAI for Production Optimization' delves into the intricate challenges of managing large-scale manufacturing lines, focusing on a Ford use case. It explores the application of explainable AI (XAI) to tackle the complexities of engine production, where various engine types and components introduce significant variability and potential bottlenecks. The use of AI models to predict and optimize production is emphasized, with a particular focus on the integration of explainability tools to enhance transparency and decision-making. The chapter also discusses the development of hybrid models and graph machine learning approaches, showcasing how these advanced techniques can provide actionable insights and improve overall production efficiency. By addressing real-world challenges and providing practical solutions, the chapter offers a compelling case study for the implementation of XAI in manufacturing environments.AI Generated
This summary of the content was generated with the help of AI.
AbstractThis chapter introduces the work performed in XMANAI to address the need of explainability in manufacturing AI systems applied to optimize production lines. The XMANAI platform is designed to meet the needs of manufacturing factories, offering them a unified framework to leverage their data and extract valuable insights. Within the project, the Ford use case is focused on forecasting production in a dynamically changing manufacturing line, serving as a practical illustration of the platform capabilities. This chapter focuses on the application of explainability using Hybrid Models and Heterogeneous Graph Machine Learning (ML) techniques. Hybrid Models combine traditional AI models with eXplainable AI (XAI) tools and Heterogeneous Graph ML techniques using Graph Attention (GAT) layers to extract explainability in complex manufacturing scenarios where data that can be represented as a graph. To understand explainability applied to the Ford use case, this chapter describes the initial needs of the scenario, the infrastructure behind the use case and the results obtained, showcasing the effectiveness of this approach, where models are trained in the XMANAI platform. Specifically, a description is given on the results of production forecasting in an engine assembly plant while providing interpretable explanations when deviations from expected are predicted. -
XAI for Product Demand Planning: Models, Experiences, and Lessons Learnt
- Open Access
Download PDF-versionThe chapter delves into Whirlpool's use of XAI for sales demand forecasting within the H2020 XMANAI project. It discusses the challenges and solutions encountered in making AI systems explainable and trustworthy for business users. Key topics include the development of explainability tools, the importance of user engagement, and the evaluation of the XMANAI platform's impact on business operations. The chapter offers insights into the practical application of XAI, highlighting its potential to improve decision-making and operational efficiency.AI Generated
This summary of the content was generated with the help of AI.
AbstractToday, Explainable AI is gaining more and more traction due to its inherent added value to allow all involved stakeholders to understand why/how a decision has been made by an AI system. In this context, the problem of Product Demand Forecasting as faced by Whirlpool has been elaborated and tackled through an Explainable AI approach. The Explainable AI solution has been designed and delivered in the H2020 XMANAI project and is presented in detail in this chapter. The core XMANAI Platform has been used by data scientists to experiment with the data and configure Explainable AI pipelines, while a dedicated manufacturing application is addressed to business users that need to view and gain insights into product demand forecasts. The overall Explainable AI approach has been evaluated by the end users in Whirlpool. This chapter presents experiences and lessons learnt from this evaluation. -
Process and Product Quality Optimization with Explainable Artificial Intelligence
- Open Access
Download PDF-versionThe chapter delves into the transformative potential of Explainable Artificial Intelligence (XAI) in modern factories, focusing on its applications in process and product quality optimization. It begins with an introduction to XAI, highlighting its ability to enhance operator decision-making by providing transparent and understandable explanations for AI model outputs. The chapter then explores various applications of XAI, such as feature importance analysis, failure analysis, and predictive maintenance, demonstrating how it can improve product performance and process efficiency. The practical implementation of XAI is showcased through a case study involving CNH Industrial, where XAI is used to optimize maintenance processes in a tractor manufacturing plant. The chapter provides a detailed technical implementation of XAI, including data processing, model training, and explainability requirements. It also discusses the development of a web app and an augmented reality application to facilitate operator interaction with XAI systems. The chapter concludes with an evaluation of the XAI platform, highlighting its benefits and areas for future optimization. Throughout, the chapter emphasizes the importance of human-machine collaboration and the role of XAI in driving efficiency and productivity in manufacturing environments.AI Generated
This summary of the content was generated with the help of AI.
AbstractIn today’s rapidly evolving technological landscape, businesses across various industries face a critical challenge: maintaining and enhancing the quality of both their processes and the products they deliver. Traditionally, this task has been tackled through manual analysis, statistical methods, and domain expertise. However, with the advent of artificial intelligence (AI) and machine learning, new opportunities have emerged to revolutionize quality optimization. This chapter explores the process and product quality optimization in a real industrial use case with the help of explainable artificial intelligence (XAI) techniques. While AI algorithms have proven their effectiveness in improving quality, one of the longstanding barriers to their widespread adoption has been the lack of interpretability and transparency in their decision-making processes. XAI addresses this concern by enabling human stakeholders to understand and trust the outcomes of AI models, thereby empowering them to make informed decisions and take effective actions. -
Toward Explainable Metrology 4.0: Utilizing Explainable AI to Predict the Pointwise Accuracy of Laser Scanning Devices in Industrial Manufacturing
- Open Access
Download PDF-versionThe chapter 'Toward Explainable Metrology 4.0' delves into the integration of Explainable AI (XAI) to enhance the predictive accuracy and transparency of laser scanning devices in industrial manufacturing. It discusses the challenges faced in current metrological practices, such as variability in measurement errors due to surface texture, incident angles, and sensor distances. The proposed methodology leverages XAI to model the differential accuracy of laser scanning devices under various scanning configurations and surface orientations. This approach not only predicts point-wise measurement errors but also provides explanations for the model's predictions, enabling metrologists to understand and trust the AI-driven measurement process. The chapter outlines the methodology, experimental setup, and results, showcasing the superior performance of the PointNet-based model in predicting measurement errors. It also highlights the use of SHAP (SHapley Additive exPlanations) to interpret the model's decisions, offering insights into the key factors affecting measurement accuracy. The study concludes with a discussion on the practical implications and future perspectives of XAI in metrology, emphasizing its potential to revolutionize the field by enhancing accuracy, efficiency, and transparency in measurement processes.AI Generated
This summary of the content was generated with the help of AI.
AbstractThe field of metrology, which focuses on the scientific study of measurement, is grappling with a significant challenge: predicting the measurement accuracy of sophisticated 3D scanning devices. These devices, though transformative for industries like manufacturing, construction, and archeology, often generate complex point cloud data that traditional machine learning models struggle to manage effectively. To address this problem, we proposed a PointNet-based model, designed inherently to navigate point cloud data complexities, thereby improving the accuracy of prediction for scanning devices’ measurement accuracy. Our model not only achieved superior performance in terms of mean absolute error (MAE) across all three axes (X, Y, Z) but also provided a visually intuitive means to understand errors through 3D deviation maps. These maps quantify and visualize the predicted and actual deviations, which enhance the model’s explainability as well. This level of explainability offers a transparent tool to stakeholders, assisting them in understanding the model’s decision-making process and ensuring its trustworthy deployment. Therefore, our proposed model offers significant value by elevating the level of precision, reliability, and explainability in any field that utilizes 3D scanning technology. It promises to mitigate costly measurement errors, enhance manufacturing precision, improve architectural designs, and preserve archeological artifacts with greater accuracy.
-
- Title
- Artificial Intelligence in Manufacturing
- Editor
-
John Soldatos
- Copyright Year
- 2024
- Publisher
- Springer Nature Switzerland
- Electronic ISBN
- 978-3-031-46452-2
- Print ISBN
- 978-3-031-46451-5
- DOI
- https://doi.org/10.1007/978-3-031-46452-2
PDF files of this book don't fully comply with PDF/UA standards, but do feature limited screen reader support, described non-text content (images, graphs), bookmarks for easy navigation and searchable, selectable text. Users of assistive technologies may experience difficulty navigating or interpreting content in this document. We recognize the importance of accessibility, and we welcome queries about accessibility for any of our products. If you have a question or an access need, please get in touch with us at accessibilitysupport@springernature.com