Softcover reprint of the original 1st ed. 1996, XII, 201 pp. 92 figs.
Springer eBooks may be purchased by end-customers only and are sold without copy protection (DRM free). Instead, all eBooks include personalized watermarks. This means you can read the Springer eBooks across numerous devices such as Laptops, eReaders, and tablets.
You can pay for Springer eBooks with Visa, Mastercard, American Express or Paypal.
After the purchase you can directly download the eBook file or read it online in our Springer eBook Reader. Furthermore your eBook will be stored in your MySpringer account. So you can always re-download your eBooks.
Although the tenn quality does not have a precise and universally accepted definition, its meaning is generally well understood: quality is what makes the difference between success and failure in a competitive world. Given the importance of quality, there is a need for effective quality systems to ensure that the highest quality is achieved within given constraints on human, material or financial resources. This book discusses Intelligent Quality Systems, that is quality systems employing techniques from the field of Artificial Intelligence (AI). The book focuses on two popular AI techniques, expert or knowledge-based systems and neural networks. Expert systems encapsulate human expertise for solving difficult problems. Neural networks have the ability to learn problem solving from examples. The aim of the book is to illustrate applications of these techniques to the design and operation of effective quality systems. The book comprises 8 chapters. Chapter 1 provides an introduction to quality control and a general discussion of possible AI-based quality systems. Chapter 2 gives technical information on the key AI techniques of expert systems and neural networks. The use of these techniques, singly and in a combined hybrid fonn, to realise intelligent Statistical Process Control (SPC) systems for quality improvement is the subject of Chapters 3-5. Chapter 6 covers experimental design and the Taguchi method which is an effective technique for designing quality into a product or process. The application of expert systems and neural networks to facilitate experimental design is described in this chapter.
Content Level »Research
Keywords »artificial intelligence - control - design - expert system - intelligence - manufacturing - neural networks - problem solving - quality
1 Introduction.- 1.1 Quality Assurance Systems.- 1.2 Knowledge-Based Systems for Quality Control.- 1.3 Neural Networks for Quality Control.- 1.4 Integrating Expert Systems and Neural Networks for Quality Control.- 1.5 Summary.- References.- 2 Artificial Intelligence Tools.- 2.1 Expert Systems.- 2.1.1 Knowledge Representation.- 2.1.2 Elements of an Expert System.- 2.1.3 Expert System Shells and Tools.- 2.2 Neural Networks.- 2.2.1 Fundamentals of Neural Networks.- 2.2.2 Learning.- 2.2.3 Architecture of a Multi-Layer Perceptron (MLP).- 2.2.4 Architecture of a Learning Vector Quantisation (LVQ) Network.- 2.2.5 Architecture of an ART2 Network.- 2.3 Summary.- References.- 3 Statistical Process Control.- 3.1 Statistical Process Control (SPC) and Control Charting.- 3.2 XPC: An On-line Expert System for Statistical Process Control.- 3.2.1 Structure of XPC.- 3.2.2 Functions of XPC.- 3.2.3 Test Application and Discussion.- 3.3 Intelligent Advisors for Control Chart Selection.- 3.4 Summary.- References.- 4 Control Chart Pattern Recognition.- 4.1 Control Chart Patterns.- 4.2 A Knowledge-Based Control Chart Pattern Recognition System.- 4.2.1 On-line Pattern Recognition and Classification.- 4.2.2 Performance of the Recognition System.- 4.3 Using Neural Networks to Recognise Control Chart Patterns.- 4.3.1 Pattern Recognition Using a MLP Model.- 4.3.2 Recognising Control Chart Patterns Using LVQ Networks.- 4.3.3 Discussion.- 4.4 Composite Systems for Recognising Control Chart Patterns.- 4.4.1 Decision Making Module.- 4.4.2 Composite MLP System.- 4.4.3 Composite LVQ System.- 4.4.4 Hybrid Composite Systems.- 4.4.5 Discussion on Using Composite Systems.- 4.5 Summary.- References.- 5 Integrated Quality Control Systems.- 5.1 The Integration Process.- 5.1.1 Comparison of Expert Systems and Neural Networks.- 5.1.2 Combining Expert Systems and Neural Networks.- 5.2 An Example of Integrating an Expert System with Neural Networks for Quality Control.- 5.3 Summary.- References.- 6 Experimental Quality Design.- 6.1 Taguchi Experimental Design.- 6.1.1 Parameter Design.- 6.1.2 Knowledge-Based Systems for Taguchi Experimental Design.- 6.2 Neural Networks for the Design of Experiments.- 6.2.1 Training Data.- 6.2.2 Structure of the Network.- 6.2.3 Network Training and Results.- 6.3 Summary.- References.- 7 Inspection.- 7.1 Role of Inspection in Quality Control.- 7.1.1 Sampling.- 7.1.2 Sampling Plans.- 7.1.3 Knowledge-Based Systems for Selecting Sampling Plans.- 7.2 Automated Visual Inspection.- 7.3 Knowledge-Based Systems for Automated Visual Inspection.- 7.4 Neural Networks for Automated Visual Inspection.- 7.4.1 Training and Test Data Sets.- 7.4.2 Neural Network Details.- 7.4.3 Performance of the MLP Network.- 7.4.4 Other Classifiers.- 7.4.5 Composite Systems.- 7.5 Discussion.- 7.6 Summary.- References.- 8 Condition Monitoring and Fault Diagnosis.- 8.1 Condition Monitoring.- 8.1.1 Condition Monitoring Techniques.- 8.1.2 Implementation Stages of Condition Monitoring.- 8.1.3 Knowledge-Based Systems for Conditioning Monitoring.- 8.1.4 Neural Networks for Condition Monitoring.- 8.2 Diagnosis.- 8.2.1 Knowledge-Based Systems for Diagnosis.- 8.2.2 Neural Networks for Diagnosis.- 8.3 Discussion.- 8.4 Summary.- References.- Author Index.