Skip to main content

Open Access 2023 | Open Access | Book

Cover of the book

Flexible Automation and Intelligent Manufacturing: The Human-Data-Technology Nexus

Proceedings of FAIM 2022, June 19–23, 2022, Detroit, Michigan, USA


About this book

This is an open access book. It gathers the first volume of the proceedings of the 31st edition of the International Conference on Flexible Automation and Intelligent Manufacturing, FAIM 2022, held on June 19 – 23, 2022, in Detroit, Michigan, USA. Covering four thematic areas including Manufacturing Processes, Machine Tools, Manufacturing Systems, and Enabling Technologies, it reports on advanced manufacturing processes, and innovative materials for 3D printing, applications of machine learning, artificial intelligence and mixed reality in various production sectors, as well as important issues in human-robot collaboration, including methods for improving safety. Contributions also cover strategies to improve quality control, supply chain management and training in the manufacturing industry, and methods supporting circular supply chain and sustainable manufacturing. All in all, this book provides academicians, engineers and professionals with extensive information on both scientific and industrial advances in the converging fields of manufacturing, production, and automation.

Table of Contents


Open Access

Correction to: Development Process for Information Security Concepts in IIoT-Based Manufacturing

The book has been inadvertently published with the incorrect affiliation of all the authors in Chapter 31, which has now been corrected. The book and the chapter have been updated with the change.

Julian Koch, Kolja Eggers, Jan-Erik Rath, Thorsten Schüppstuhl

Manufacturing Processes


Open Access

Die-Less Forming of Fiber-Reinforced Plastic Composites

Fiber-reinforced plastics (FRP) are increasingly popular in light weight applications such as aircraft manufacturing. However, most production processes of thin-walled FRP parts to date involve the use of expensive forming tools. This especially hinders cost-effective production of small series as well as individual parts and prototypes. In this paper, we develop new possible alternatives of highly automated and die-less production processes based on a short review of current approaches on flexible thin-walled FRP production. All proposed processes involve robot guided standard tools, similar to incremental sheet metal forming, for local forming of the base materials. These include woven glass fiber fabrics which are locally impregnated with thermoset resin and cured using UV-light, woven commingled yarns made out of glass fibers and thermoplastic fibers which are locally heated and pressed, as well as pre-consolidated thermoplastic organo sheets which require selective heating for forming. General applicability of the processes is investigated and validated in practical experiments.

Jan-Erik Rath, Robert Graupner, Thorsten Schüppstuhl

Open Access

Assessment of High Porosity Lattice Structures for Lightweight Applications

Additive manufacturing (AM) methods have a growing application in different fields such as aeronautical, automotive, biomedical, and there is a huge interest towards the extension of their use. In this paper, lattice structures for AM are analysed with regards to stiffness and printability in order to verify the suitability for applications where the main requirement of efficiency in terms of stiffness has to be balanced with other needs such as weight saving, ease of manufacturing and recycling of the material. At this aim, lattice structures with high porosity unit cells and large cell size made of a recyclable material were considered with a geometrical configuration allowing 3D printing without any supports. The lattice structures considered were based on body-centred cubic (BCC) and face centred cubic (FCC) unit cell combined with cubic cell. Finally, a multi-morphology lattice structure obtained by mixing different unit cells is also proposed. The lattice structures were modelled and structurally analysed by means of finite element method (FEM), manufactured with a Fusion deposition modelling (FDM) printer and evaluated in relation to printability and dimensional accuracy. The results show that the proposed structure with mixed cells is potentially advantageous in terms of weight saving in relation to the mechanical properties.

Rita Ambu, Michele Calì

Machine Tools


Open Access

Development of a Sensor Integrated Machining Vice Towards a Non-invasive Milling Monitoring System

The future of manufacturing processes is the fully autonomous operation of machine tools. The reliable autonomous operation of machine tools calls for the integration of inline quality control systems that will be able to assess in real time the process status and ensure that the machine tool, process and workpiece are complying with the manufacturing tolerances and requirements. Sensor integrated tooling for machining processes can significantly contribute towards this goal as they can facilitate monitoring close to the actual process. However, most of the solutions proposed so far are highly expensive or very complex to integrate and operate in an industrial environment. To this end, this paper proposes an approach for a sensor integrated vise using low-cost industrial sensors that can easily be integrated in existing machine tools in a non-invasive fashion. The development and dynamic analysis of the system is presented, along with an experimental verification against a lab-scale, high accuracy sensing setup

Panagiotis Stavropoulos, Dimitris Manitaras, Christos Papaioannou, Thanassis Souflas, Harry Bikas

Open Access

Effect of Ultrasonic Burnishing Parameters on Burnished-Surface Quality of Stainless Steel After Heat Treatment

Ultrasonic burnishing induces beneficial compressive stresses and high surface quality in components with contact as a functional requirement. It was observed in previous work that some burnishing parameters can hinder burnishability of stainless steels. In this research tangential misalignment angles (TMA) for burnishing were varied considering as-supplied and heat-treated stainless steel. Properties such as surface hardness and surface roughness were measured after burnishing process. Electron Backscatter Diffraction was performed to characterize microstructure using Matlab (MTEX) to calculate average grain areas. By changing burnishing parameters, i.e., shaft rotational speed and burnishing tool diameter, it was observed that burnishing was less successful. Nevertheless, significant improvement in burnished surface quality was observed after heat-treatment process. In addition, grain size characterization revealed mean grain area reduction from 26 µm2 for unburnished to 11 µm2 and 3 µm2 for burnished and heat-treated samples respectively. Most importantly this work reveals the enhanced possibility of burnishing stainless steels after heat-treatment with varying tangential misalignment angles.

Rizwan Ullah, Eric Fangnon, Juha Huuki

Open Access

High Precision Fabrication of an Innovative Fiber-Optic Displacement Sensor

This study presents the high precision fabrication technique, employed to manufacture a 3D conical grating, used as the reflector element, for a fiber-optic displacement sensor. To get high performance in terms of the surface quality, as well as a dimensional precision, the surface of the reflector must be a polished-mirror surface. To do so, a high precision turning machine along with aluminum alloy were the technical choices made. Two prototypes with different geometric dimensions, have been fabricated using the same machining strategy. Single crystal diamond tool was chosen, to obtain high surface roughness. The followed machining procedure was divided into two main parts; the first part achieves several cuts, to get the desired dimensions, and the last cut is deduced to get the desired nanometric roughness. Good results have been obtained, which validates the followed machining procedure.

Zeina Elrawashdeh, Philippe Revel, Christine Prelle, Frédéric Lamarque

Open Access

3D Printing of Hydrogel-Based Seed Planter for In-Space Seed Nursery

Interest in manufacturing parts using 3D printing became popular across academic and industrial sectors because of its improved reliability and accessibility. With the necessity of self-sustentation, growing plant in space is one of the most popular topics. Carboxymethyl cellulose (CMC) is one of the best candidates for sprouting substrate with 3D printing fabrication as it is non-toxic, biodegradable, and suitable for extrusion-based 3D printing. Soybeans were placed into the designed and printed CMC gel with different orientations. Without visible light, soybeans with hilum facing side had the highest water absorption average comparing those facing up or down. Hydrogel weight dominated the water absorption efficiency. These findings signified that bean orientation affects the sprouting process. This study demonstrates the substrate geometry and seed orientation impacts on germination of soybeans, proposed guidelines for optimizing the sprouting process for high-level edible plants and promoting innovated in-space seed nursery approach.

Yanhua Huang, Li Yu, Liangkui Jiang, Xiaolei Shi, Hantang Qin

Open Access

Modelling and Simulation of Automated Hydraulic Press Brake

In this study, a reconfigurable hydraulic press brake was designed using Solidworks and simulated on a hydraulic Automation Studio Fluidsim. The designed press brake comprises of the frame balance, conveyor rollers and support, belt, chuck, six hydraulic cylinders assembled with bolts and nuts. The buckling force was determined analytically and compared with the Finite Element Analysis (FEA) simulation to prevent distortion of length and section. The Von mises stress theory was used to determine the stress, resultant load and displacement. The results obtained from the FEA simulation were compared with the mechanical properties of the hydraulic press brake. The maximum stress induced is significantly lower than the tensile strength of the hydraulic press brake. Hence, the stress induced due to bending cannot cause the cast alloy to yield. Also, the buckling force significantly exceeds the resultant force giving no chances for buckling. The designed hydraulic press brake is flexible enough to control using hydraulic cylinders and enhances sufficient strength and rigidity during clamping and loading conditions.

Ilesanmi Daniyan, Khumbulani Mpofu, Bankole Oladapo, Rufus Ajetomobi

Open Access

Assessment of Reconfigurable Vibrating Screen Technology for the Mining Industries

Vibrating screens are very vital in the mineral processing industries for the beneficiation (separation) of mineral particles into different sizes. The breaking down of vibrating screens due to unforeseen contingencies have reduced the productivity of these machines thereby reducing the competitiveness, availability and reliability of these machines for the set production target made by the company. Also since human wants are insatiable, fluctuation in the mineral concentrates demands has been an inevitable scenario, thus, reducing the efficiency of the mineral beneficiation industries. During peak mineral concentrates demand, most of these industries do not have an option than to purchase another beneficiation screen in order to meet up with the continuously increasing production demand. A solution called the Reconfigurable Vibrating Screen (RVS) that can cover the gaps created by machine breakdown, and ensure that the variations in quantity of mineral concentrates needed by customers are met. In this paper, a state of configurations achieved by RVS as compared to the existing conventional vibrating screens was made. In addition to this, a market assessment of the proposed RVS and other existing screening technologies was performed. The index parameters used for this analysis are capacity, reliability, efficiency, versatility and cost. From the comparative analysis, it was observed that there are high advantages for using RVS for beneficiation operations in the mineral beneficiation in place of existing vibrating screens.

Boitumelo Ramatsetse, Khumbulani Mpofu, Ilesanmi Daniyan, Olasumbo Makinde

Manufacturing Systems


Open Access

Deep Anomaly Detection for Endoscopic Inspection of Cast Iron Parts

Detecting anomalies in image data plays a key role in automated industrial quality control. For this purpose, machine learning methods have proven useful for image processing tasks. However, supervised machine learning methods are highly dependent on the data with which they have been trained. In industrial environments data of defective samples are rare. In addition, the available data are often biased towards specific types, shapes, sizes, and locations of defects. On the contrary, one-class classification (OCC) methods can solely be trained with normal data which are usually easy to obtain in large quantities. In this work we evaluate the applicability of advanced OCC methods for an industrial inspection task. Convolutional Autoencoders and Generative Adversarial Networks are applied and compared with Convolutional Neural Networks. As an industrial use case we investigate the endoscopic inspection of cast iron parts. For the use case a dataset was created. Results show that both GAN and autoencoder-based OCC methods are suitable for detecting defective images in our industrial use case and perform on par with supervised learning methods when few data are available.

Ole Schmedemann, Maximilian Miotke, Falko Kähler, Thorsten Schüppstuhl

Open Access

Classification and Detection of Malicious Attacks in Industrial IoT Devices via Machine Learning

The term “the Industrial Internet of Things” has become increasingly more pervasive in the context of manufacturing as digitization has become a business priority for many manufacturers. IIoT refers to a network of interconnected industrial devices, resulting in systems that can monitor, collect, exchange, analyze, and deliver valuable data and new insights. These insights can then help drive smarter, and faster business decisions for manufacturers. However, these benefits have come at the cost of creating a new attack vector for the malicious agents that aim at stealing manufacturing trade secrets, blueprints, or designs. As a result, cybersecurity concerns have become more relevant across the field of manufacturing. One of the main tracks of research in this field deals with developing effective cyber-security mechanisms and frameworks that can identify, classify, and detect malicious attacks in industrial IoT devices. In this paper, we have developed and implemented a classification and detection framework for addressing cyber-security concerns in industrial IoT which takes advantage of various machine learning algorithms. The results prove the satisfactory performance and robustness of the approach in classifying and detecting the attacks.

Mohammad Shahin, F Chen, Hamed Bouzary, Ali Hosseinzadeh, Rasoul Rashidifar

Open Access

Implementation of a Novel Fully Convolutional Network Approach to Detect and Classify Cyber-Attacks on IoT Devices in Smart Manufacturing Systems

In recent years, Internet of things (IoT) devices have been widely implemented and industrially improved in manufacturing settings to monitor, collect, analyze, and deliver data. Nevertheless, this evolution has increased the risk of cyberattacks, significantly. Consequently, developing effective intrusion detection systems based on deep learning algorithms has proven to become a dependable intelligence tool to protect Industrial IoT devices against cyber-attacks. In the current study, for the first time, two different classifications and detection long short-term memory (LSTM) architectures were fine-tuned and implemented to investigate cyber-security enhancement on a benchmark Industrial IoT dataset (BoT-IoT) which takes advantage of several deep learning algorithms. Furthermore, the combinations of LSTM with FCN and CNN demonstrated how these two models can be used to accurately detect cyber security threats. A detailed analysis of the performance of the proposed models is provided. Augmenting the LSTM with FCN achieves state-of-the-art performance in detecting cybersecurity threats.

Mohammad Shahin, FFrank Chen, Hamed Bouzary, Ali Hosseinzadeh, Rasoul Rashidifar

Open Access

Application of ARIMA-LSTM for Manufacturing Decarbonization Using 4IR Concepts

Increasing climate change concerns call for the manufacturing sector to decarbonize its process by introducing a mitigation strategy. Energy efficiency concepts within the manufacturing process value chain are proportional to the emission reductions, prompting decision makers to require predictive tools to execute decarbonization solutions. Accurate forecasting requires techniques with a strong capability for predicting automotive component manufacturing energy consumption and carbon emission data. In this paper we introduce a hybrid autoregressive moving average (ARIMA)-long short-term memory network (LSTM) model for energy consumption forecasting and prediction of carbon emission within the manufacturing facility using the 4IR concept. The method could capture linear features (ARIMA) and LSTM captures the long dependencies in the data from the nonlinear time series data patterns, Root means square error (RMSE) is used for data analysis comparing the performance of ARIMA which is 448.89 as a single model with ARIMA-LSTM hybrid model as actual (trained) and predicted (test) 59.52 and 58.41 respectively. The results depicted RMSE values of ARIMA-LSTM being extremely smaller than ARIMA, which proves that hybrid ARIMA-LSTM is more suitable for prediction than ARIMA.

Olukorede Tijani Adenuga, Khumbulani Mpofu, Ragosebo Kgaugelo Modise

Open Access

Online Path Planning in a Multi-agent-Controlled Manufacturing System

In recent years the manufacturing sectors are migrating from mass production to mass customization. To be able to achieve mass customization, manufacturing systems are expected to be more flexible to accommodate the different customizations. The industries which are using the traditional and dedicated manufacturing systems are expensive to realize this transition. One promising approach to achieve flexibility in their production is called Plug & Produce concept which can be realized using multi-agent-based controllers. In multi-agent systems, parts and resources are usually distributed logically, and they communicate with each other and act as autonomous agents to achieve the manufacturing goals. During the manufacturing process, an agent representing a robot can request a path for transportation from one location to another location. To address this transportation facility, this paper presents the result of a futuristic approach for an online path planning algorithm directly implemented as an agent in a multi-agent system. Here, the agent systems can generate collision-free paths automatically and autonomously. The parts and resources can be configured with a multi-agent system in the manufacturing process with minimal human intervention and production downtime, thereby achieving the customization and flexibility in the production process needed.

Sudha Ramasamy, Mattias Bennulf, Xiaoxiao Zhang, Samuel Hammar, Fredrik Danielsson

Open Access

Assessing Visual Identification Challenges for Unmarked and Similar Aircraft Components

Highest demands for complete traceability and quality control of each component, require thorough identification of each produced, replaced, and (dis-)assembled aircraft component. As many production and MRO-processes for modern aircraft remain to be carried out manually, this poses a great challenge. Many small components either do not feature a Part Number or in MRO-processes their Part Number is occluded or not readable due to dirt and wear. Considering unmarked components with a high resemblance to one another and few characteristics, e.g. standard parts such as bushings and pipes, manual identification is an error-prone task. Avoiding errors through digitalized procedures has the potential to significantly reduce error rates and costs for a typical manual dual control. However, automated identification of components has to overcome the high classification complexity that originates in the manifold of aircraft components and is additionally increased by individualistic MRO modifications for specific aircraft. This work presents a methodological approach to reveal possible challenges for identification procedures and gives special focus to the assessment of similarities between components. Two similarity metrics are introduced that are calculated either through feature-based analysis or through 3D-shape similarity assessment. The methodology is demonstrated with two to this date unsolved Use-Cases that represent different challenges of visual identification systems for similar and unmarked components.

Daniel Schoepflin, Johann Gierecker, Thorsten Schüppstuhl

Open Access

Projecting Product-Aware Cues as Assembly Intentions for Human-Robot Collaboration

Collaborative environments between humans and robots are often characterized by simultaneous tasks carried out in close proximity. Recognizing robot intent in such circumstances can be crucial for operator safety and cannot be determined from robot motion alone. Projecting robot intentions on the product or the part the operator is collaborating on has the advantage that it is in the operator’s field of view and has the operator’s undivided attention. However, intention projection methods in literature use manual techniques for this purpose which can be prohibitively time consuming and unscalable to different part geometries. This problem is only more relevant in today’s manufacturing scenario that is characterized by part variety and volume. To this end, this study proposes (oriented) bounding boxes as a generalizable information construct for projecting assembly intentions that is capable of coping with different part geometries. The approach makes use of a digital thread framework for on-demand, run-time computation and retrieval of these bounding boxes from product CAD models and does so automatically without human intervention. A case-study with a real diesel engine assembly informs appreciable results and preliminary observations are discussed before presenting future directions for research.

Joe David, Eric Coatanéa, Andrei Lobov

Open Access

Online Quality Inspection Approach for Submerged Arc Welding (SAW) by Utilizing IR-RGB Multimodal Monitoring and Deep Learning

Online, Image-based monitoring of arc welding requires direct visual contact with the seam or the melt pool. During SAW, these regions are covered with flux, making it difficult to correlate temperature and spatial related features with the weld quality. In this study, by using a dual-camera setup, IR and RGB images depicting the irradiated flux during fillet welding of S335 structural steel beams are captured and utilized to develop a Deep Learning model capable of assessing the quality of the seam, according to four classes namely “no weld”, “good weld”, “porosity” and “undercut/overlap”, as they’ve emerged from visual offline inspection. The results proved that the camera-based monitoring could be a feasible online solution for defect classification in SAW with exceptional performance especially when a dual-modality setup is utilized. However, they’ve also pointed out that such a monitoring setup does not grand any real-world advantage when it comes to the classification of relatively large, defective seam regions.

Panagiotis Stavropoulos, Alexios Papacharalampopoulos, Kyriakos Sabatakakis

Open Access

Detachable, Low-Cost Tool Holder for Grippers in Human-Robot Interaction

To hand over more than just pick & place tasks to an industrial collaborative robotic arm with a two-jaw gripper, the gripper must first be removed, and a new tool mounted. This tool change requires either human assistance or an expensive tool changer. The tools applied to the end-effector are often highly expensive and software system interfaces between different tools and robots are seldom available. Therefore, a holder was developed that allows the robot to pick up and operate a tool, such as an electric screwdriver, without having to demount the two-jaw gripper. Instead, the gripper’s functionality is used to activate and deactivate the tool fixed to the holder. This paper presents the state-of-the-art of the underlying problem as well as the development process including simulations, the patented design, and the low-cost production of the tool holder. This detachable, low-cost tool holder enables a flexibilization of human-robot processes in manufacturing.

Christina Schmidbauer, Hans Küffner-McCauley, Sebastian Schlund, Marcus Ophoven, Christian Clemenz

Open Access

Intelligent Robotic Arm Path Planning (IRAP2) Framework to Improve Work Safety in Human-Robot Collaboration (HRC) Workspace Using Deep Deterministic Policy Gradient (DDPG) Algorithm

Industrial robots are widely used in manufacturing systems. The places that humans share with robots are called human-robot collaboration (HRC) workspaces. To ensure the safety in HRC workspaces, a collision-avoidance system is required. In this paper, we regard the collision-avoidance as a problem during the robot action trajectory design and propose an intelligent robotic arm path planning (IRAP2) framework. The IRAP2 framework is based on the deep deterministic policy gradient (DDPG) algorithm because the path planning is a typical continuous control problem in a dynamic environment, and DDPG is well suited for such problems. To test the IRAP2 framework, we have studied a HRC workspace in which the robot size is larger than humans. At first, we have applied a physics engine to build a virtual HRC workspace including digital models of a robot and a human. Using this virtual HRC workspace as the environment model, we further trained an agent model using the DDPG algorithm. The trained model can optimize the motion path of the robot to avoid collision with the human.

Xiangqian Wu, Li Yi, Matthias Klar, Marco Hussong, Moritz Glatt, Jan C. Aurich

Open Access

A Conceptual Framework of a Digital-Twin for a Circular Meat Supply Chain

Every year more than 900 million tonnes of food is wasted, contributing to almost 10% of total greenhouse gas emissions. Reducing food waste has been identified as essential to tackle the current climate crisis, and links to several UN’s sustainable development goals. This is especially critical for energy and resource-intensive food products like meat, whose consumption is predicted to reach an historical maximum by 2030. Whilst wastage occurs at all stages of the supply chain, tractable data about the journey of food from production to consumer remains largely hidden or unrecorded. Powered by the latest advances in sensing like smart food packaging and digital technologies such as Big Data and IoT, Digital Twins offer a valuable opportunity to monitor and control meat products and processes across the whole supply chain, enabling food waste to be reduced and by-products reintegrated into the supply chain. This paper proposes a new framework for a Digital Twin that integrates key technological enablers across different areas of the meat supply chain towards with the goal of a “zero-waste”, circular meat supply chain.

M. R. Valero, B. J. Hicks, A. Nassehi

Open Access

A Mathematical Model for Cloud-Based Scheduling Using Heavy Traffic Limit Theorem in Queuing Process

Cloud manufacturing (CMfg) is a service-oriented manufacturing paradigm that distributes resources in an on-demand business model. In the cloud manufacturing environment, scheduling is considered as an effective tool for satisfying customer requirements which has attracted attention from researchers. In this case, quality of service (QoS) in the scheduling plays a vital role in assessing the impacts of the distributed resources in operation on the performance of scheduling functions. In this paper, a queuing system is employed to model the scheduling problem with multiple servers and then scheduling in cloud manufacturing is classified based on various QoS requirements. Moreover, a set of heavy traffic limit theorems is introduced as a new approach to solving this scheduling problem in which different heavy traffic limits are provided for each of QoS-based scheduling classes. Finally, the number of operational resources in the scheduling is determined by considering the results obtained in the numerical analysis of the heavy traffic limit with different queue disciplines. The results show that different numbers of active machines in various QoS requirements classes play a vital role in that the required QoS metrics such as the expected waiting time and the expected completion time which are critical performance indicators of the cloud’s service are intimately related.

Rasoul Rashidifar, F. Frank Chen, Hamed Bouzary, Mohammad Shahin

Open Access

Approach for Evaluating Changeable Production Systems in a Battery Module Production Use Case

Volatile markets continue to complicate manufacturing companies’ production system design, leading to efficiency losses due to imperfect system setups. In such a market environment, a perfect system setup cannot be achieved. Therefore, changeable production systems that cope with immanent uncertainty gain interest in research and industry. For several decades, changeable production systems have been in the research and development stage. The advantages and disadvantages are well investigated. So far, however, they have gained only limited acceptance in industry. One of the reasons is the difficult evaluation of the benefits. Existing investment calculation methods either neglect many effects of changeability, such as easier adaptation to unpredictable events, or are too complex and therefore too time-consuming to become standard. Thus, a practical evaluation method is needed that considers these changeability aspects. This paper deviates the industry requirements regarding an evaluation method based on an industry survey and develops a practical approach for an evaluation method for a changeable production system considering monetary and non-monetary aspects. The approach is characterized by a calculation that is as accurate as possible considering the existing input factors. The method shows that changeable production systems excel in environments with frequent need for adaptation. The approach is applied to a battery module assembly in the ARENA2036 research campus.

Christian Fries, Patricia Hölscher, Oliver Brützel, Gisela Lanza, Thomas Bauernhansl

Open Access

Cost-Minimal Selection of Material Supply Strategies in Matrix Production Systems

Companies are facing changing market demands, high variance, and volatile quantities. Resilient production systems are needed to meet these challenges. The matrix production is such a system. It offers degrees of freedom in terms of operation sequence flexibility and work distribution flexibility through redundantly used resources. For the material supply this is a challenge in planning. The material must be supplied in a cost-efficient manner and without shortages.To increase planning quality, a method for selecting the least expensive material supply strategy is developed. Depending on consumption, constraints of space, and supply framework conditions, different strategies are advantageous for each material. The developed method requires three steps.First, required data for step 2 and step 3 is collected. In step 2, standardized process blocks combine to describe a company-specific material supply strategy. The approach is company-independent and added by cost functions to the process blocks. Through the cost functions applied to the process blocks the costs of a supply strategy is achieved. As material can be supplied in alternative ways, multiple expected costs for supplying arise. As only one supply strategy needs to be selected, step 3 is necessary. It uses the branch-and-cut algorithm on the mathematical description of the logistic selection problem to find the cost-minimal configuration of supply strategies. As the problem is in the context of matrix production, several conditions and requirements need to be included in the selection process.The result is the assignment of a material supply strategy to each material while minimizing the costs.

Daniel Ranke, Thomas Bauernhansl

Open Access

Assessment of Ergonomics Risk Experienced by Welding Workers in a Rail Component Manufacturing Organization

The various types of welding workstation designs used in a rail component manufacturing system environment have drawn the attention of industrial engineers to the safety and efficiency of the workers during welding operations. Welding operations are carried out using several posture configurations, which have a negative physical ergonomic impact on the workers, especially in manual welding processes. This empirical research investigates the ergonomics conditions of welding workplaces with the aim of ascertaining the disorders that may be associated with working posture during welding operations among the South African population. Twenty-seven (27) welders were randomly selected, and data was collected using a structured questionnaire. The majority (67 percent of the welders) stated that they experience discomfort and pain whilst they carry out their task, which contradicts ergonomic guidelines for working posture. Forty-eight percent of the welding workers were frequently physically tired. Sixty-three (63) percent agree that they perform repetitive tasks, and a majority of 78% of welding workers reported neck discomfort as a result of tilting their neck posture for a longer period during welding operations. It was deduced that the correlation among risk factors associated with workstation design, repetitive tasks, contribute to the awkward posture adopted whilst welding, that, if retained for a long duration, could lead to musculoskeletal injuries, poor quality of work, and reduced productivity. Based on these results, in order to increase productivity, it was proposed to redesign the welding workstations and to prioritize interventional ergonomic programme to minimize the MSDs problems.

Khumbuzile Nedohe, Khumbulani Mpofu, Olasumbo Makinde

Open Access

A Survey of Smart Manufacturing for High-Mix Low-Volume Production in Defense and Aerospace Industries

Defense and aerospace industries usually possess unique high-mix low-volume production characteristics. This uniqueness generally calls for prohibitive production costs and long production lead-time. One of the major trends in advanced, smart manufacturing is to be more responsive and better readiness while ensuring the same or higher production quality and lower cost. This study reviews the state-of-the-art manufacturing technologies to solve these issues and previews two levels of flexibility, i.e., system and process, that could potentially reduce the costs while increasing the production volume in such a scenario. The main contribution of the work includes an assessment of the current solutions for HMLV scenarios, especially within the defense of aerospace sectors, and a survey of the current and potential future practices focusing on smart production process planning and flexible assembly plan driven by emerging techniques.

Tanjida Tahmina, Mauro Garcia, Zhaohui Geng, Bopaya Bidanda

Open Access

Feasibility Analysis of Safety Training in Human-Robot Collaboration Scenario: Virtual Reality Use Case

Design and modification of human-robot collaboration workspace requires analysis of the safety of systems. Generally, the safety analysis process of a system commences with conducting a risk assessment. There exists a number international standards for design robotics work cells and collaborative shared workspaces. These guidelines expound on principles and measures to identify hazards and reduce risks. Measures of risk reductions include eliminating hazards by design, safeguarding, and providing supplementary protective measures such as user training. This study analyzed the technical feasibility and industrial readiness of Virtual Reality (VR) technology for safety training in manufacturing sector. The test case of a VR-based safety training application is defined in the human-robot collaboration pilot-line of diesel engines. The Analytic Hierarchy Process method was utilized for conducting a quantitative analysis of the survey with ten experts. The participants performed the importance rating with respect to two hierarchy level criteria. Regarding the evaluation of safety training methods in a human-robot collaboration environment, two alternatives of traditional and Virtual Reality -based training are compared. The results indicates that the VR-based training is valued over the traditional method, with a scored proportion of approximately 65 percent over 35 percent.

Morteza Dianatfar, Saeid Heshmatisafa, Jyrki Latokartano, Minna Lanz

Enabling Technologies


Open Access

Energy Efficiency for Manufacturing Using PV, FSC, and Battery-Super Capacitor Design to Enhance Sustainable Clean Energy Load Demand

Energy efficiency (EE) are recognized globally as a critical solution towards reduction of energy consumption, while the management of global carbon dioxide emission complement climate change. EE initiatives drive is a key factor towards climate change mitigation with variable renewable technologies. The paper aimed to design and simulate photovoltaic (PV), fuel cell stack (FCS) systems, and battery-super capacitor energy storage to enhance sustainable clean energy load demand and provide significant decarbonization potentials. An integration of high volume of data in real-time was obtained and energy mix fraction towards low carbon emission mitigation pathway strategy for grid linked renewables electricity generation was proposed as a solution for the future transport manufacturing energy supplement in South Africa. The interrelationship between energy efficiency and energy intensity variables are envisaged to result in approximately 87.6% of global electricity grid production; electricity energy demand under analysis can reduce the CO2 emissions by 0.098 metric tons and CO2 savings by 99.587 per metric tons. The scope serves as a fundamental guideline for future studies in the future transport manufacturing with provision of clean energy and sufficient capacity to supply the demand for customers within the manufacturing.

Olukorede Tijani Adenuga, Khumbulani Mpofu, Thobelani Mathenjwa

Open Access

The Impact of Learning Factories on Teaching Lean Principles in an Assembly Environment

Learning factories are realistic manufacturing environments built for education; many universities have recently introduced learning factories in engineering programs to tackle real industrial problems; however, statistical studies on its effectiveness are still scarce. This paper presents a statistical study on the impact of learning factories on the students’ learning process, when teaching the lean manufacturing concepts in an assembly environment. The analysis is carried out through the Lean Manufacturing Lab at KTH, a learning factory supporting the traditional educational activities. In the lab, the students assemble a product on an assembly line; during three rounds, they identify problems on the line, apply the appropriate lean tools to overcome the problems, and try to achieve a higher productivity. The study is based on the analysis of the times recorded during the sessions of the lab. A questionnaire submitted to the students after the course evaluates the level of knowledge of lean production principles that the students achieved. The results are twofold: the improvement of the assembly times through the implementation of the lean tools and the positive effect of a hands-on experience on the students’ understanding of the lean principles, highlighted by the answers to the questionnaire. The main contributions are that applying the lean tools on an assembly line improves the productivity even with inexperienced operators, implementing a learning factory is effective in enhancing the learning process, and, lastly, that a first-hand experience applying the lean tools in a real assembly environment is an added value to the students’ education.

Fabio Marco Monetti, Eleonora Boffa, Andrea de Giorgio, Antonio Maffei

Open Access

Generation of Synthetic AI Training Data for Robotic Grasp-Candidate Identification and Evaluation in Intralogistics Bin-Picking Scenarios

Robotic bin picking remains a main challenge for the wide enablement of industrial robotic tasks. While AI-enabled picking approaches are encouraging they repeatedly face the problem of data availability. The scope of this paper is to present a method that combines analytical grasp research with the field of synthetic data creation to generate individual training data for use-cases in intralogistics transportation scenarios. Special attention is given to systematic grasp finding for new objects and unknown geometries in transportation bins and to match the generated data to a real two-finger parallel gripper. The presented approach includes a grasping simulation in Pybullet to investigate the general tangibility of objects under uncertainty and combines these findings with a previously reported virtual scene generator in Blender, which generates AI-images of fully packed transport boxes, including depth maps and necessary annotations. This paper, therefore, contributes a synthesizing and cross-topic approach that combines different facets of bin-picking research such as geometric analysis, determination of tangibility of objects, grasping under uncertainty, finding grasps in dynamic and restricted bin-environments, and automation of synthetic data generation. The approach is utilized to generate synthetic grasp training data and to train a grasp-generating convolutional neural network (GG-CNN) and demonstrated on real-world objects.

Dirk Holst, Daniel Schoepflin, Thorsten Schüppstuhl

Open Access

Objectifying Machine Setup and Parameter Selection in Expert Knowledge Dependent Industries Using Invertible Neural Networks

The textile industry is one of the oldest and largest industries in the world. The fields of application for textile products are diverse. Although the technologies for manufacturing textiles are extensively researched, the industry is still highly dependent on expert knowledge. To date, manual process- and machine adjustments and quality control are the norms rather than the exception. Heat setting is used in the process chain to dissolve or selectively introduce tensions from the weaving or knitting process and to prepare the products for digital printing. The correct setting of the machine depends on a large number of different materials-, processes- & environmental parameters. For each product, the machine has to be set up again by an experienced textile engineer. To ease the training for new workers and shorten the machine setting process, this study aims to use machine learning to facilitate and objectify the setting of the heat-setting process. Machine parameters are generated using an invertible neural network (INN) based on pre-defined target parameters. The results can be used to identify trends in machine settings and respond accordingly. Thus, a reduction of machine setting time could be realized.

Kai Müller, Andrés Posada-Moreno, Lukas Pelzer, Thomas Gries

Open Access

Integration of Machining Process Digital Twin in Early Design Stages of a Portable Robotic Machining Cell

Industrial robots have been getting a more important role in manufacturing processes during the last decades, due to the flexibility they can provide in terms of reachability, size of working envelope and workfloor footprint. An especially interesting application are material removal processes and specifically machining. Use of robots in machining has opened new pathways for the development of flexible, portable robotic cells for several use cases. However, the peculiarity of such cells compared to traditional machine tools calls for novel approaches in their design and dynamic analysis. To this end, this work proposes an approach that integrates the digital twin of the machining process to set the boundary conditions for the design and dynamic analysis of the robotic cell. Physics-based modelling of milling is coupled with a Multi-Body Simulation of the robotic arm to define the inputs for the design of the cell. The design and dynamic analysis of the robotic cell is performed in a commercial FEA package, taking into account the requirements of the machining process.

Panagiotis Stavropoulos, Dimitris Manitaras, Harry Bikas, Thanassis Souflas

Open Access

Development Process for Information Security Concepts in IIoT-Based Manufacturing

Digital technologies are increasingly utilized by manufacturers to make processes more transparent, efficient and networked. Novel utilization elicits the challenge of preventing deployed information technology from compromising processual security. The digital enabling of formerly analog operation technology, the extensive use of information technology connectivity like MQTT, TCP/IP, Wi-Fi, and the deployment of IoT edge computing platforms create an application scenario for the Industrial Internet of Things (IIoT), which also introduces the associated vulnerabilities, which have been extensively exploited in the past. This paper introduces a development process for information security concepts designed for production scenarios based on the IIoT. This concept is then applied using an illustrative use case from aircraft production. The main contents of the development process include: Formulation of reasonable assumptions, system modelling, threat analysis including risk assessment, recommendation of countermeasures, reassessment after incorporating countermeasures. Specifically, a Data Flow Diagram as the model is developed, and a “risk first” variation of the STRIDE methodology is applied to identify threats and prioritize them. The aforementioned state-of-the-art methodologies are adjusted to our cyber-physical use case in the IIoT. The resulting concept aims to enable manufacturing processes to be digitized as sought. The adjustments to the methodologies are independent from our use case and may be suitable to a broad field of scenarios in the IIoT.

Julian Koch, Kolja Eggers, Jan-Erik Rath, Thorsten Schüppstuhl

Open Access

Augmented Virtuality Input Demonstration Refinement Improving Hybrid Manipulation Learning for Bin Picking

Beyond conventional automated tasks, autonomous robot capabilities aside human cognitive skills are gaining importance in industrial applications. Although machine learning is a major enabler of autonomous robots, system adaptation remains challenging and time-consuming. The objective of this research work is to propose and evaluate an augmented virtuality-based input demonstration refinement method improving hybrid manipulation learning for industrial bin picking. To this end, deep reinforcement and imitation learning are combined to shorten required adaptation timespans to new components and changing scenarios. The method covers initial learning and dataset tuning during ramp-up as well as fault intervention and dataset refinement. For evaluation standard industrial components and systems serve within a real-world experimental bin picking setup utilizing an articulated robot. As part of the quantitative evaluation, the method is benchmarked against conventional learning methods. As a result, required annotation efforts for successful object grasping are reduced. Thereby, final grasping success rates are increased. Implementation samples are available on:

Andreas Blank, Lukas Zikeli, Sebastian Reitelshöfer, Engin Karlidag, Jörg Franke

Open Access

Manufacturing Process Optimization via Digital Twins: Definitions and Limitations

Manufacturing process real-time optimization has been one of the main digital twins’ operations. It is of utmost importance to the processes, since it enables the feedback of a digital twin towards the real world. However, it is quite difficult to be implemented, since it requires modelling of the process, adaptivity of both the model and the process, real-time communication and link to other functionalities. Under the framework of formalizing such activities, the current work attempts to categorize the types of manufacturing process real-time optimization and show their limitations. For the sake of simplicity, generic process models are adopted and then the requirements for the process control are given, driving the aforementioned definitions. Specific numerical examples are used to illustrate the definitions, while the latter presented herein span all categories of real-time optimization as well as all manufacturing performance indicators. Finally, both mathematically and physics-wise, the limitations are discussed.

Alexios Papacharalampopoulos, Panagiotis Stavropoulos

Open Access

The Circular Economy Competence of the Manufacturing Sector — A Case Study

Circular economy refers to the intention to overcome the problems in the current production and consumption model. The current model is based on continuous growth and an increasing efficient resource utilization among the industry. Within the circular economy, an organizations are expected to minimize material and energy use, and by design and action reduce the environmental deterioration without restricting economic growth or social and technical progress. This development has been undertaken in many industries, especially in consumer-related businesses, many examples are well documented. However, there are only few studies available concerning the current circular economy activities in the manufacturing industry or their potential. The main goal of this paper is to identify and validate the circular economy readiness between communication and actual action in the circular economy business in manufacturing companies in a regional context. The results of this study will show the capabilities of the manufacturing industry to do business in regional circular economy activities. Two conclusions can be made. Firstly, the results of regional circular economy activities bring valuable information for academics, policymakers, and manufacturing companies. Secondly, the regional baseline of the circular economy can help highlight the current situation and identify the business areas which the next actions should be targeted at.

Nillo Adlin, Minna Lanz, Mika Lohtander

Open Access

A Framework for Manufacturing System Reconfiguration Based on Artificial Intelligence and Digital Twin

The application of digital twins and artificial intelligence to manufacturing has shown potential in improving system resilience, responsiveness, and productivity. Traditional digital twin approaches are generally applied to single, static systems to enhance a specific process. This paper proposes a framework that applies digital twins and artificial intelligence to manufacturing system reconfiguration, i.e., the layout, process parameters, and operation time of multiple assets, to enable system decision making based on varying demands from the customer or market. A digital twin environment has been developed to simulate the manufacturing process with multiple industrial robots performing various tasks. A data pipeline is built in the digital twin with an API (application programming interface) to enable the integration of artificial intelligence. Artificial intelligence methods are used to optimise the digital twin environment and improve system decision-making. Finally, a multi-agent program approach shows the communication and negotiation status between different agents to determine the optimal configuration for a manufacturing system to solve varying problems. Compared with previous research, this framework combines distributed intelligence, artificial intelligence for decision making, and production line optimisation that can be widely applied in modern reactive manufacturing applications.

Fan Mo, Jack C. Chaplin, David Sanderson, Hamood Ur Rehman, Fabio Marco Monetti, Antonio Maffei, Svetan Ratchev

Open Access

AI-Based Engineering and Production Drawing Information Extraction

The production of small batches to single parts has been increasing for many years and it burdens manufacturers with higher cost pressure. A significant proportion of the costs and processing time arise from indirect efforts such as understanding the manufacturing features of engineering drawings and the process planning based on the features. For this reason, the goal is to automate these indirect efforts. The basis for the process planning is information defined in the design department. The state of the art for information transfer between design and work preparation is the use of digital models enriched with additional information (e.g. STEP AP242). Until today, however, the use of 2D manufacturing drawings is widespread. In addition, a lot of knowledge is stored in old, already manufactured components that are only documented in 2D drawings. This paper provides an AI(Artificial Intelligence)-based methodology for extracting information from the 2D engineering and manufacturing drawings. Hereby, it combines and compiles object detection and text recognition methods to interpret the document systematically. Recognition rates for 2D drawings up to 70% are realized.

Christoph Haar, Hangbeom Kim, Lukas Koberg

Open Access

Generation of an Intermediate Workpiece for Planning of Machining Operations

Digital twins in manufacturing plays a key factor for the digital transformation. A necessary component of any digital twin in manufacturing is a geometric model of a workpiece as it is processed through steps. DT requires solid 3d models, machining features, and information regarding machines, tools, and its constraints such as initial setup, machining direction, etc. The objective of this paper is to generate alternate feature interpretations to identify geometric constraints, machine and tool requirements, and stock materials to generate flexible manufacturing plans that fit a defined criterion. In this study we propose using the IMPlanner system to retrieve a 3d model from a CAD software, read its geometric features and convert them into possible machining features. This information along with information from the database of stock materials, tools, machines, and tolerances, the system generates several feature interpretations, thus offering a more flexible manufacturing plan.

Dušan Šormaz, Anibal Careaga Campos, Jaikumar Arumugam

Open Access

Automating the Generation of MBD-Driven Assembly Work Instruction Documentation for Aircraft Components

The classical approach to the creation of assembly work instructions for high value, complex products is time-consuming and prone to error. It requires a process engineer to write the work instructions step-by-step and manually insert specific technical information, using an encompassing document of manufacturing parameters or life cycle management software. The latter offers synchronisation to design changes through updateable parameters, however major design modifications still require significant manual work to modify the text contents and structure of the work instructions. This leaves the work instruction documentation vulnerable to human error, as well as making the process time-consuming to fully synchronise. A methodology was therefore developed to resolve these issues, utilising JavaScript and VBA for Office to create a simple interface for rapid content generation for work instructions including text, MBD extracted parameters, images and formatting. The overall methodology speeds up the creation of assembly work instructions and reduces errors by implementing automatic insertion of parameters from an MBD model. The implementation and effectiveness of the suggested approach is demonstrated on a case study for the assembly of the joined wing configuration of the RACER helicopter, the latest generation of compound helicopters of Airbus Helicopter.

Aikaterini R. Papadaki, Konstantinos Bacharoudis, David Bainbridge, Nick Burbage, Alison Turner, David Sanderson, Atanas A. Popov, Svetan M. Ratchev

Open Access

Hyperspectral Imaging for Non-destructive Testing of Composite Materials and Defect Classification

Carbon fiber composite materials are intensively used in many manufacturing domains such as aerospace, aviation, marine, automation and civil industries due to their excellent strength, corrosion resistance, and lightweight properties. However, their increased use requires a conscious awareness of their entire life cycle and not only of their manufacturing. Therefore, to reduce waste and increase sustainability, reparation, reuse, or recycling are recommended in case of defects and wear. This can be largely improved with reliable and efficient non-destructive defect detection techniques; those are able to identify damages automatically for quality control inspection, supporting the definition of the best circular economy options. Hyperspectral imaging techniques provide unique features for detecting physical and chemical alterations of any material and, in this study, it is proposed to identify the constitutive material and classify local defects of composite specimens. A Middle Wave Infrared Hyperspectral Imaging (MWIR-HSI) system, able to capture spectral signatures of the specimen surfaces in a range of wavelengths between 2.6757 and 5.5056 µm, has been used. The resulting signatures feed a deep neural network with three convolutional layers that filter the input and isolate data-driven features of high significance. A complete experimental case study is presented to validate the methodology, leading to an average classification accuracy of 93.72%. This opens new potential opportunities to enable sustainable life cycle strategies for carbon fiber composite materials.

Trunal Patil, Claudia Pagano, Roberto Marani, Tiziana D’Orazio, Giacomo Copani, Irene Fassi
Flexible Automation and Intelligent Manufacturing: The Human-Data-Technology Nexus
Kyoung-Yun Kim
Leslie Monplaisir
Jeremy Rickli
Copyright Year
Electronic ISBN
Print ISBN

Premium Partners