Quality management in industrial production is a key measure of success. Often it decides technical and/or commercial viability. In many cases, a large amount of data is collected at every stage of the production process. The editors assert that this data can be used for stage and process-wide decision making by applying intelligent data processing techniques, such as neural networks, particle swarm optimization, genetic algorithms, fuzzy sets, ant colony optimization, bee colony optimization, simulated annealing, tabu search, swarm intelligence, and differential evolution. The editors feel that this field warrants the attention of a wider body of production engineers and researchers. They have produced this excellent collection, covering topics from literature surveys, industrial practices, theories, and case studies. The volume contains 15 chapters, each devoted to a facet of the field.

The first chapter, authored by the editors, presents an excellent literature review and background for the topic, and highlights the progress in management of product quality from traditional statistical processes (SPC) to an increasing use of intelligent computational techniques. This survey covers applications and lists more than 80 useful references. The next two chapters, by Kahraman et al., show how control charts can be used to implement process controls using fuzzy set theory. The authors illustrate techniques with numerical examples and substantiate assertions by providing ample references. This is followed by a discussion on the use of control charts based on exponentially weighted moving average (EWMA), in a chapter by Aslan et al. Chapter 4 shows with a numerical study how these charts have been used to control a large ensemble of individually controlled and repaired machines (called Jidoka production system (JPS)). Predestined EWMA statistical processes using fuzzy sets and meta-heuristics generate signals for different (pre-identified) events, such as an out-of-control machine/repair event.

The next four chapters of the book focus on theoretical aspects of intelligent processes, attempting to achieve Six Sigma quality control. Chapter 5, by Parchami and Sadeghpour-Gildeh, discusses, with appropriate examples, process capability indices (PCI) and their computation using random samples in terms of fuzzy set theory definitions of the upper and lower specification limit in a Six Sigma quality control process. In chapter 6, Garg develops a composite index (RAM-Index) for the reliability, availability, and maintainability (RAM) of the production process. He examines fuzzy set theory and evolutionary algorithms, such as genetics algorithms, particle swarm optimization, the artificial bee colony algorithm, and the cuckoo search algorithm, to present a methodology. In chapter 7, Kahraman et al. present, with six numerical illustrations, a design method for single and double acceptance sampling plans, using a mathematical model based on fuzzy set theory (often acceptance sampling is used as an alternative to costly 100 percent sampling). This is followed by a literature review, “The Role of Computational Intelligence in Experimental Design,” covering fundamentals and available intelligent computational techniques for experimental design, including optimization methods, heuristics, fuzzy techniques, and artificial intelligence.

The next four chapters discuss popular quality control methodologies and their possible usage with intelligent computational processes. In chapter 9, Kulcsár et al. discuss PDCA (plan-do-check-act), and DMAIC (define-opportunities, measure-performance, analyze-opportunity, improve-performance, and control-performance), and point out that these methodologies require data collection and analysis at every stage of production, which can be modeled as a multivariate multistage optimization problem being solved through data mining-based knowledge discovery. The authors formally present their approach, called CRISP-DM (short for cross-industry standard process for data mining), and illustrate it with an example based on the Phillips loop reactor process. This is followed by a tutorial and literature review on “Failure Mode and Effects Analysis Under Uncertainty,” in chapter 10, by Asan and Soyer. In chapter 11, Jiang et al. first discuss four basic aspects of a QFD, that is, functional relationships in QFD, the relative weight of each customer requirement, importance weights of engineering characteristics, and the target value of each engineering parameter. Subsequently, they present a group-decision methodology based on a fuzzy analytic process based on extent analysis, chaos-based fuzzy regression, and genetic algorithms. Fogal, in chapter 12, discusses “Process Improvement Using Intelligent Six Sigma,” with a focus on required performance measures. He uses as an example an artificial neural network (ANN) with multiple feedback loops in a production control process when using Six Sigma methodology.

The remaining chapters focus on analytical techniques. In chapter 13, Tang et al. discuss “Taguchi Method Using Intelligence Techniques.” The authors assert that Taguchi methods combine engineering and statistical methods to achieve improved efficiency, cost, and quality, while retaining simplicity, in a discussion on intelligent control for automated guided vehicles using fuzzy rule sets along with ANN. In the next chapter, Potena et al. discuss “Software Architecture Quality of Service Analysis Based on Optimization Models,” with a focus on the mathematical foundation of quality of service tradeoffs, including its dependencies on static and dynamic aspects of the software architecture, and automation of architectural decisions using optimization models. The last chapter presents a literature review and discussion on “Key-Driver Analysis with Extended Back-Propagation Neural Network Based Importance-Performance Analysis (BPNN-IPA),” supported by an example of BPNN-IPA.

This collection should interest people who want a comprehensive overview or are starting research in this area.