Intelligent Diagnosis and Prognosis of Industrial Networked Systems

In an era of intense competition where plant operating efficiencies must be maximized, downtime due to machinery failure has become more costly. To cut operating costs and increase revenues, industries have an urgent need to predict fault progression and remaining lifespan of industrial machines, processes, and systems. An engineer who mounts an acoustic sensor onto a spindle motor wants to know when the ball bearings will wear out without having to halt the ongoing milling processes. A scientist working on sensor networks wants to know which sensors are redundant and can be pruned off to save operational and computational overheads. These scenarios illustrate a need for new and unified perspectives in system analysis and design for engineering applications. Intelligent Diagnosis and Prognosis of Industrial Networked Systems proposes linear mathematical tool sets that can be applied to realistic engineering systems. The book offers an overview of the fundamentals of vectors, matrices, and linear systems theory required for intelligent diagnosis and prognosis of industrial networked systems. Building on this theory, it then develops automated mathematical machineries and formal decision software tools for real-world applications. The book includes portable tool sets for many industrial applications, including: Forecasting machine tool wear in industrial cutting machines Reduction of sensors and features for industrial fault detection and isolation (FDI) Identification of critical resonant modes in mechatronic systems for system design of R&D Probabilistic small-signal stability in large-scale interconnected power systems Discrete event command and control for military applications The book also proposes future directions for intelligent diagnosis and prognosis in energy-efficient manufacturing, life cycle assessment, and systems of systems architecture. Written in a concise and accessible style, it presents tools that are mathematically rigorous but not involved. Bridging academia, research, and industry, this reference supplies the know-how for engineers and managers making decisions about equipment maintenance, as well as researchers and students in the field.

IntroductionDiagnosis and PrognosisParametric-BasedNon-Parametric-BasedApplications in Industrial Networked SystemsModal Parametric Identification (MPI)Dominant Feature Identification (DFI)Probabilistic Small Signal Stability AssessmentDiscrete Event Command and Control Vectors, Matrices, and Linear SystemsFundamental ConceptsVectorsMatricesLinear SystemsIntroduction to Linear SystemsState-Space Representation of LTI SystemsLinearization of Non-Linear SystemsEigenvalue Decomposition and SensitivityEigenvalue and EigenvectorEigenvalue DecompositionGeneralized EigenvectorsEigenvalue Sensitivity to Non-Deterministic System ParametersEigenvalue Sensitivity to Link ParametersSingular Value Decomposition (SVD) and ApplicationsSingular Value Decomposition (SVD)Norms, Rank, and Condition NumberPseudo-InverseLeast Squares SolutionMinimum-Norm Solution Using SVDBoolean MatricesBinary RelationGraphsDiscrete-Event SystemsConclusion Modal Parametric Identification (MPI)IntroductionServo-Mechanical-Prototype Production CycleModal SummationPole-Zero ProductLumped PolynomialSystems Design ApproachModal Parametric Identification (MPI) AlgorithmNatural Frequencies fi and Damping Ratios ?i Reformulation Using Forsythe’s Orthogonal PolynomialsResidues RiError AnalysisIndustrial Application: Hard Disk Drive Servo SystemsResults and DiscussionsConclusion Dominant Feature Identification (DFI)IntroductionPrincipal Component Analysis (PCA)Approximation of Linear Transformation XApproximation in Range Space by Principal ComponentsDominant Feature Identification (DFI)Data CompressionSelection of Dominant FeaturesError AnalysisSimplified ComputationsTime Series Forecasting Using Force Signals and Static ModelsDetermining the Dominant FeaturesPrediction of Tool WearExperimental SetupEffects of Different Numbers of Retained Singular Values q and Dominant Features pComparison of Proposed Dominant Feature Identification (DFI) and Principal Feature Analysis (PFA)Time Series Forecasting Using Acoustic Emission Signals and Dynamic ModelsARMAX Model Based on DFIExperimental SetupComparison of Standard Non-Dynamic Prediction Models with Dynamic ARMAX ModelComparison of Proposed ARMAX Model using ELS with DFI, MRM using RLS with DFI, and MRM using RLS with Principal Feature Analysis (PFA)Effects of Different Numbers of Retained Singular Values and Features Selected Comparison of Tool Wear Prediction Using AE Measurements and Force MeasurementsDFI for Industrial Fault Detection and Isolation (FDI)Augmented Dominant Feature Identification (ADFI)Decentralized Dominant Feature Identification (DDFI)Fault Classification with Neural NetworksExperimental SetupFault Detection Using 120 FeaturesAugmented Dominant Feature Identification (ADFI) and NN for Fault DetectionDecentralized Dominant Feature Identification (DDFI) and NN for Fault DetectionConclusion Probabilistic Small Signal Stability AssessmentIntroductionPower System Modeling: Differential EquationsSynchronous MachinesExciter and Automatic Voltage Regulator (AVR)Speed Governor and Steam TurbineInteraction Between A Synchronous Machine and its Control SystemsPower System Modeling: Algebraic EquationsStator EquationsNetwork Admittance Matrix YNReduced Admittance Matrix YRState Matrix and Critical ModesEigenvalue Sensitivity MatrixSensitivity Analysis of the New England Power SystemStatistical FunctionsSingle Variate Normal PDF of aiMultivariate Normal PDFProbability CalculationsSmall Signal Stability RegionImpact of Induction Motor LoadComposite Load Model for Sensitivity AnalysisMotor Load Parameter Sensitivity AnalysisParametric Changes and Critical Modes MobilityEffect of the Number of IMs on Overall Sensitivity (with 30% IM load)Effect On Overall Sensitivity with Different Percentages of IM Load in the Composite LoadDiscussionConclusion Discrete Event Command and ControlIntroductionDiscrete Event C2 Structure For Distributed TeamsTask Sequencing Matrix (TSM) Resource Assignment Matrix (RAM)Programming Multiple MissionsConjunctive Rule-Based Discrete Event Controller (DEC)DEC State EquationDEC Output EquationsDEC as a Feedback ControllerFunctionality of the DECProperness and Fairness of the DEC Rule BaseDisjunctive Rule-Based Discrete Event Controller (DEC)DEC Simulation and ImplementationSimulation of Networked Team ExampleImplementation of Networked Team Example on Actual WSN Simulation of Multiple Military Missions Using FCSConclusion Future ChallengesEnergy-Efficient ManufacturingLife Cycle Assessment (LCA)System of Systems (SoS) ReferencesIndex

Chee Khiang Pang is an Assistant Professor in the Department of Electrical and Computer Engineering at National University of Singapore. Frank L. Lewis is a Professional Engineer and Head of Advanced Controls and Sensors Group at the Automation and Robotics Research Institute, The University of Texas at Arlington. Tong Heng Lee is Professor and cluster Head for the Department of Electrical and Computer Engineering at National University of Singapore. Zhao Yang Dong is Associate Professor for the Department of Electrical Engineering at The Hong Kong Polytechnic University.