Skip to main content

2023 | Book

Explainable Artificial Intelligence (XAI) in Manufacturing

Methodology, Tools, and Applications


About this book

This book provides a comprehensive overview of the latest developments in Explainable AI (XAI) and its applications in manufacturing. It covers the various methods, tools, and technologies that are being used to make AI more understandable and communicable for factory workers. With the increasing use of AI in manufacturing, there is a growing need to address the limitations of advanced AI methods that are difficult to understand or explain to those without a background in AI. This book addresses this need by providing a systematic review of the latest research and advancements in XAI specifically tailored for the manufacturing industry.

The book includes real-world case studies and examples to illustrate the practical applications of XAI in manufacturing. It is a valuable resource for researchers, engineers, and practitioners working in the field of AI and manufacturing.

Table of Contents

Chapter 1. Explainable Artificial Intelligence (XAI) in Manufacturing
This chapter begins by defining explainable artificial intelligence (XAI). A procedure for implementing XAI was also established. Then, through literature analysis, the application of XAI in various fields such as medicine, service, education, finance, medical treatment, manufacturing, food, and military is compared. Some representative cases in these fields are also reported. Subsequently, several applications of XAI in the field of manufacturing are reviewed, including explaining the classification process and results of factory jobs, explaining artificial neural network (ANN)-based cycle time prediction methods, comparing the effect of alloy composition using Shapely additive explanation value (SHAP) analysis, etc.
Tin-Chih Toly Chen
Chapter 2. Applications of XAI for Forecasting in the Manufacturing Domain
This chapter focuses on forecasting, which is an important function of manufacturing systems. Many operations and production activities such as cycle time forecasting, sales forecasting, unit cost reduction, predictive maintenance, yield learning, etc. are based on forecasting. This chapter takes job cycle time forecasting as an example. Artificial intelligence (AI) techniques have many applications in job cycle time prediction. Of these, artificial neural network (ANN) (or deep neural network, DNN) applications are most effective, but are difficult for factory workers to understand or communicate. To address this issue, existing explainable AI (XAI) techniques and tools for explaining the inference process and results of ANNs (or DNNs) are introduced. We first introduce XAI tools for visualizing operations in ANNs (or DNNs), such as ConvNetJS, TensorFlow, Seq2Seq, and MATLAB, and then mention XAI techniques for evaluating the impact, contribution, or importance of each input on the output, including partial derivatives, odd ratio, out-of-bag (OOB) predictor importance, recursive feature elimination (RFE), Shapely additive explanation value (SHAP). Subsequently, XAI techniques for approximating the relationship between the inputs and output of an ANN (or DNN), especially simpler machine learning techniques such as case-based reasoning (CBR), classification and regression trees (CART), random forest (RF), gradient boosting decision trees, eXtreme gradient boosting (XGBoost), and RF-based incremental interpretation are introduced. The application of each XAI technique is supplemented with simple examples and corresponding MATLAB codes, allowing readers to get started quickly.
Tin-Chih Toly Chen
Chapter 3. Applications of XAI for Decision Making in the Manufacturing Domain
This chapter discusses an important topic in factory management, that of improving the understandability of AI applications for group multi-criteria decision making in manufacturing systems. Due to its long-term and cross-functional impact, decision making may be more critical to the competitiveness and sustainability of manufacturing systems than production planning and control. This chapter uses the example of choosing the right smart and automation technologies for factories during the COVID-19 pandemic. This topic is of particular importance as many factories are forced to close or operate on a smaller scale (using a smaller workforce), thus pursuing further automation. Artificial intelligence and Industry 4.0 technologies have many applications in this area, most of which can also be applied for other decision-making purposes in manufacturing systems. First, a systematic procedure was established to guide the group multi-criteria decision-making process. Applications of AI and XAI to identify targets are first reviewed. Subsequently, the application of AI and XAI to selection factors and development of criteria is presented. Artificial intelligence techniques are widely used to derive criteria priorities. Therefore, it is particularly important to explain XAI techniques and tools for such AI applications. Aggregating the judgments of multiple decision makers is the next focus, followed by the introduction of AI and XAI applications to evaluate the overall performance of each alternative. Taking fuzzy ranking preference based on similarity to ideal solution (FTOPSIS) as an example, the application of XAI techniques and tools in explaining comparison results using FTOPSIS is illustrated. Another AI technology used for the same purpose is fuzzy VIKOR. XAI techniques and tools for interpreting fuzzy VIKOR are also presented. Finally, several metrics are proposed to evaluate the effectiveness of XAI techniques or tools for decision making in the manufacturing domain.
Tin-Chih Toly Chen
Chapter 4. Applications of XAI to Job Sequencing and Scheduling in Manufacturing
This chapter discusses a new application field of XAI in manufacturing—job sequencing and scheduling. It first breaks down job sequencing and scheduling into several steps and then mentions AI technologies applicable to some of these steps. It is worth noting that many AI applications focus on the preparation of inputs required for scheduling tasks, rather than the process of scheduling tasks, which is a distinctive feature of the field. Nonetheless, many AI techniques have already been explained in other fields or domains. These explanations can provide a reference for explaining the application of AI in job sequencing and scheduling. Therefore, some general XAI techniques and tools for job sequencing and scheduling are reviewed, including: referring to the classification of job scheduling problems; customizing scheduling rules; text description, pseudocode; decision trees, flowcharts. Furthermore, job sequencing and scheduling problems are often formulated as mathematical programming (optimization) models to be optimized. AI technologies can be applied to find the best solution for the model. Applications of genetic algorithm (GA) are of particular interest because such applications are most common in job scheduling. Furthermore, XAI techniques and tools for explaining GA can be easily extended to other evolutionary AI applications, such as artificial bee colony (ABC), ant colony optimization (ACO), and particle swarm optimization (PSO) in job scheduling. Applicable XAI techniques and tools include flowcharts, text description, chromosome maps, dynamic line charts, and bar charts with baseline. Some novel XAI techniques and tools for interpreting GAs are also introduced: decision tree-based interpretation and dynamic transition and contribution diagrams.
Tin-Chih Toly Chen
Explainable Artificial Intelligence (XAI) in Manufacturing
Tin-Chih Toly Chen
Copyright Year
Electronic ISBN
Print ISBN

Premium Partners