Power Converters and AC Electrical Drives with Linear Neural Networks

The first book of its kind, Power Converters and AC Electrical Drives with Linear Neural Networks systematically explores the application of neural networks in the field of power electronics, with particular emphasis on the sensorless control of AC drives. It presents the classical theory based on space-vectors in identification, discusses control of electrical drives and power converters, and examines improvements that can be attained when using linear neural networks. The book integrates power electronics and electrical drives with artificial neural networks (ANN). Organized into four parts, it first deals with voltage source inverters and their control. It then covers AC electrical drive control, focusing on induction and permanent magnet synchronous motor drives. The third part examines theoretical aspects of linear neural networks, particularly the neural EXIN family. The fourth part highlights original applications in electrical drives and power quality, ranging from neural-based parameter estimation and sensorless control to distributed generation systems from renewable sources and active power filters. Simulation and experimental results are provided to validate the theories. Written by experts in the field, this state-of-the-art book requires basic knowledge of electrical machines and power electronics, as well as some familiarity with control systems, signal processing, linear algebra, and numerical analysis. Offering multiple paths through the material, the text is suitable for undergraduate and postgraduate students, theoreticians, practicing engineers, and researchers involved in applications of ANNs.

Review of Basic Concepts: Space-Vector AnalysisIntroductionSpace-Vector Definition3 ? 2 and 2 ? 3 TransformationsCoordinate TransformationInstantaneous Real and Imaginary PowersPart I Power ConvertersPulsewidth Modulation of Voltage Source InvertersFundamentals of Voltage Source InvertersOpen-Loop PWMClosed-Loop Control of VSIsList of SymbolsFurther ReadingsPower QualityNonlinear LoadsHarmonic Propagation on the Distribution NetworkPassive FiltersActive Power FiltersList of SymbolsPart II Electrical DrivesDynamic and Steady-State Models of the Induction MachineIntroductionDefinition of the Machine Space-Vector QuantitiesPhase Equations of the IMSpace-Vector Equations in the Stator Reference FrameSpace-Vector Equations in the Rotor Reference FrameSpace-Vector Equations in the Generalized Reference FrameMathematical Dynamic Model of the IM Taking into Account the Magnetic SaturationSteady-State Space-Vector Model of the IMExperimental Validation of the Space-Vector Model of the IMIM Model Including Slotting EffectsList of SymbolsControl Techniques of Induction Machine DrivesIntroduction on Induction Machine (IM) ControlScalar Control of IMsFOC of IMsDTC of IMList of SymbolsSensorless Control of Induction Machine DrivesIntroduction on Sensorless ControlModel-Based Sensorless ControlAnisotropy-Based Sensorless ControlModel-Based Sensorless TechniquesAnisotropy-Based Sensorless TechniquesConclusions on Sensorless Techniques for IM DrivesPermanent Magnet Synchronous Motor DrivesIntroductionSpace-Vector Model of Permanent Magnet Synchronous MotorsControl Strategies of PMSM DrivesSensorless Control of PMSM DrivesAppendix: Experimental Test SetupPart III Neural Based Orthogonal RegressionNeural-Based Orthogonal RegressionIntroduction: ADALINE and Least Squares ProblemsApproaches to the Linear RegressionMinor Component Analysis and the MCA EXIN NeuronMCA EXIN NeuronTLS EXIN NeuronGeneralization of Linear Least Squares ProblemsGeMCA EXIN NeuronGeTLS EXIN NeuronPart IV Selected ApplicationsLeast Square and Neural Identification of Electrical MachinesParameter Estimation of Induction Machines (IMs)Sensitivity of the Flux Model to Parameter VariationsExperimental Analysis of the Effects of Flux Model Detuning on the Control PerformanceMethods for the On-line Tracking of the Machine Parameter VariationsOn-line Estimation of the IM Parameters with the Ordinary Least Squares MethodConstrained Minimization for Parameter Estimation of IMs in Saturated and Unsaturated ConditionsParameter Estimation of an IM with the Total Least Squares MethodApplication of the RLS-Based Parameter Estimation to Flux Model Adaptation in FOC and DTC IM DrivesEstimation of the IM Parameters at StandstillList of SymbolsNeural-Enhanced Single-Phase DG Systems with APF CapabilityIntroductionGeneral Operating PrincipleADALINE Design CriteriaBuilding the Current ReferenceMultiresonant Current ControllerStability IssuesTest RigExperimental ResultsAPF Connection ProcedureNeural Sensorless Control of AC DrivesNN-Based Sensorless ControlBPN-Based MRAS Speed ObserverLS-Based MRAS Speed ObserverTLS EXIN Full-Order Luenberger Adaptive ObserverMCA EXIN + Reduced-Order ObserverAppendix A: Implemented Control SchemesAppendix B: Description of the Test SetupList of SymbolsIndexAll chapters include references.

Maurizio Cirrincione, PhD, is a full professor of control and signal processing at the University of Technology of Belfort, Montbeliard, France. His current research interests include neural networks, modeling and control, system identification, intelligent control, and electrical machines and drives. Marcello Pucci, PhD, is a senior researcher at the Institute of Intelligent Systems for Automation (ISSIA) section of Palermo of the National Research Council of Italy (CNR). His current research interests include electrical machines and drives, power converters, wind and photovoltaic generation systems, intelligent control, and neural networks applications. Gianpaolo Vitale is a senior researcher at the Institute of Intelligent Systems for Automation (ISSIA) section of Palermo of the National Research Council of Italy (CNR). He has been professor of power electronics and applied electronics at the University of Palermo, Italy. His current research interests include power electronics, generation from renewables, and related problems of electromagnetic compatibility.