Bookstore

This book gives a complete presentatin of the basic essentials of machinery prognostics and prognosis oriented maintenance management, and takes a look at the cutting-edge discipline of intelligent failure prognosis technologies for condition-based maintenance.* Presents an introduction to advanced maintenance systems, and discusses the key technologies for advanced maintenance by providing readers with up-to-date technologies* Offers practical case studies on performance evaluation and fault diagnosis technology, fault prognosis and remaining useful life prediction and maintenance scheduling, enhancing the understanding of these technologies* Pulls togeter recent developments and varying methods into one volume, complemented by practical examples to provide a complete reference

Machinery Prognostics and Prognosis Oriented Maintenance Management

About the Author xiPreface xiiiAcknowledgements xv1 Introduction 11.1 Historical Perspective 11.2 Diagnostic and Prognostic System Requirements 21.3 Need for Prognostics and Sustainability-Based Maintenance Management 31.4 Technical Challenges in Prognosis and Sustainability-Based Maintenance Decision-Making 41.5 Data Processing, Prognostics, and Decision-Making 71.6 Sustainability-Based Maintenance Management 91.7 Future of Prognostics-Based Maintenance 11References 122 Data Processing 132.1 Probability Distributions 132.1.1 Uniform Distribution 142.1.2 Normal Distribution 162.1.3 Binomial Distribution 182.1.4 Geometric Distribution 192.1.5 Hyper-Geometric Distribution 212.1.6 Poisson Distribution 222.1.7 Chi-Squared Distributions 242.2 Statistics on Unordered Data 252.2.1 Treelets Analysis 262.2.2 Clustering Analysis 282.3 Statistics on Ordered Data 322.4 Technologies for Incomplete Data 33References 343 Signal Processing 373.1 Introduction 373.2 Signal Pre-Processing 383.2.1 Digital Filtering 383.2.2 Outlier Detecting 393.2.3 Signal Detrending 413.3 Techniques for Signal Processing 423.3.1 Time-Domain Analysis 423.3.2 Spectrum Analysis 443.3.3 Continuous Wavelet Transform 463.3.4 Discrete Wavelet Transform 493.3.5 Wavelet Packet Transforms 513.3.6 Empirical Mode Decomposition 513.3.7 Improved Empirical Mode Decomposition 573.4 Real-Time Image Feature Extraction 673.4.1 Image Capture System 673.4.2 Image Feature Extraction 683.5 Fusion or Integration Technologies 723.5.1 Dempster-Shafer Inference 723.5.2 Fuzzy Integral Fusion 733.6 Statistical Pattern Recognition and Data Mining 743.6.1 Bayesian Decision Theory 743.6.2 Artificial Neural Networks 763.6.3 Support Vector Machine 793.7 Advanced Technology for Feature Extraction 853.7.1 Group Technology 873.7.2 Improved Algorithm of Group Technology 883.7.3 Numerical Simulation of Improved Group Algorithm 903.7.4 Group Technology for Feature Extraction 913.7.5 Application 92References 964 Health Monitoring and Prognosis 1014.1 Health Monitoring as a Concept 1014.2 Degradation Indices 1014.3 Real-Time Monitoring 1064.3.1 Data Acquisition 1064.3.2 Data Processing Techniques 1154.3.3 Example 1204.4 Failure Prognosis 1264.4.1 Classification and Clustering 1294.4.2 Mathematical Model of the Classification Method 1304.4.3 Mathematical Model of the Fuzzy C-Means Method 1304.4.4 Theory of Ant Colony Clustering Algorithm 1334.4.5 Improved Ant Colony Clustering Algorithm 1344.4.6 Intelligent Fault Diagnosis Method 1384.5 Physics-Based Prognosis Models 1414.5.1 Model-Based Methods for Systems 1424.6 Data-Driven Prognosis Models 1444.7 Hybrid Prognosis Models 147References 1495 Prediction of Remaining Useful Life 1535.1 Formulation of Problem 1535.2 Methodology of Probabilistic Prediction 1545.2.1 Theory of Weibull Distribution 1555.2.2 Bayesian Theorem 1575.3 Dynamic Life Prediction Using Time Series 1605.3.1 General Introduction 1605.3.2 Prediction Models 1625.3.3 Applications 1735.4 Remaining Life Prediction by the Crack-Growth Criterion 176References 1816 Maintenance Planning and Scheduling 1836.1 Strategic Planning in Maintenance 1836.1.1 Definition of Maintenance 1836.1.2 Maintenance Strategy Planning 1886.2 Maintenance Scheduling 1966.2.1 Fundamentals of Maintenance Scheduling 1966.2.2 Problem Formulation 2026.2.3 Models for Maintenance Scheduling 2036.3 Scheduling Techniques 2076.3.1 Maintenance Timing Decision-Making Method Based on MOCLPSO 2076.3.2 Grouping Methods for Maintenance 2146.3.3 Maintenance Scheduling Based on a Tabu Search 2226.3.4 Dynamic Scheduling of Maintenance Measure 2236.3.5 Case Study 2296.4 Heuristic Methodology for Multi-unit System Maintenance Scheduling 2316.4.1 Models or Multi-Unit System Maintenance Decision 2326.4.2 Heuristic Maintenance Scheduling Algorithm 2336.4.3 Case Study 2346.4.4 Conclusions and Discussions 237References 2377 Prognosis Incorporating Maintenance Decision-Making 2417.1 The Changing Role of Maintenance 2417.2 Development of Maintenance 2437.3 Maintenance Effects Modeling 2447.3.1 Reliability Estimation 2457.3.2 Modeling the Improvement of Reliability after Maintenance 2477.4 Modeling of Optimization Objective - Maintenance Cost 2517.5 Prognosis-Oriented Maintenance Decision-Making 2537.5.1 Reliability Estimation and Prediction 2537.5.2 Case Study 2547.5.3 Maintenance Scheduling Based on Reliability Estimation and Prediction by Prognostic Methodology 2607.5.4 Case Description 2657.6 Maintenance Decision-Making Considering Energy Consumption 2697.6.1 Energy Consumption Modeling 2697.6.2 Implementation 2737.6.3 Verification and Conclusions 279References 2848 Case Studies 2878.1 Improved Hilbert-Huang Transform Based Weak Signal Detection Methodology and Its Application to Incipient Fault Diagnosis and ECG Signal Analysis 2878.1.1 Incipient Fault Diagnosis Using Improved HHT 2878.1.2 HHT in Low SNR Scenario 2908.1.3 Summary 2938.2 Ant Colony Clustering Analysis Based Intelligent Fault Diagnosis Method and Its Application to Rotating Machinery 2938.2.1 Description of Experiment and Data 2938.2.2 Model Training for Fault Diagnosis 2948.2.3 Fault Recognition 2988.2.4 Summary 3008.3 BP Neural Networks Based Prognostic Methodology and Its Application 3008.3.1 Experimental Test Conditions 3018.3.2 BP Network Model Training 3028.3.3 BP Network Real-Time Prognostics 3048.3.4 Error Analysis for Prediction 3058.3.5 PDF Curve for Life Prediction 3058.3.6 Summary 3078.4 A Dynamic Multi-Scale Markov Model Based Methodology for Remaining Life Prediction 3078.4.1 Introduction 3078.4.2 Methods of Signal Processing and Performance Assessment 3088.4.3 Markov-Based Model for Remaining Life Prediction 3098.4.4 Experiment and Validation 3158.4.5 Summary 3218.5 A Group Technology Based Methodology for Maintenance Scheduling for a Hybrid Shop 3228.5.1 Introduction 3228.5.2 Production System Modeling 3228.5.3 Clustering-Based Grouping Method 3238.5.4 Application 3238.5.5 Summary 327References 328Index 331