Intelligent Data-Analytics for Condition Monitoring: Smart Grid Applications

Description

Intelligent Data-Analytics for Condition Monitoring: Smart Grid Applications looks at intelligent and meaningful uses of data required for an optimized, efficient engineering processes. In addition, the book provides application perspectives of various deep learning models for the condition monitoring of electrical equipment. With chapters discussing the fundamentals of machine learning and data analytics, the book is divided into two parts, including i) The application of intelligent data analytics in Solar PV fault diagnostics, transformer health monitoring and faults diagnostics, and induction motor faults and ii) Forecasting issues using data analytics which looks at global solar radiation forecasting, wind data forecasting, and more. This reference is useful for all engineers and researchers who need preliminary knowledge on data analytics fundamentals and the working methodologies and architecture of smart grid systems. Cover Title Copyright Contents Editors Biography Preface Part A Intelligent Data Analytics for Classifi cationin Smart Grid Chapter 1 - Advances in Machine Learning and Data Analytics 1 - Introduction 1.1 - Brief information of data base analysis 1.2 - Brief information of intelligent data analytics for business 1.3 - Brief information of intelligent data analytics for smart grid 1.4 - Brief information of intelligent data analytics for condition monitoring 2 - Data and it’s relation 3 - Data preprocessing (DPP) 3.1 - Feature extraction 3.2 - Most relevant features selection 4 - Data visualization and correlation representation (DVCR) 5 - Application area 6 - Softwares and techniques used for data analytics 7 - Sources of datasets for data analytics 8 - Conclusion References Chapter 2 - Intelligent Data Analytics for PV Fault Diagnosis Using Deep Convolutional Neural Network (ConvNet/CNN) 1 - Introduction 2 - Intelligent data analysis for photovoltaic module failures (PVMF) analysis 3 - PV image data set collection 4 - Proposed approach 5 - Deep convolutional neural network (ConvNet/CNN) 6 - Results and discussion 7 - Conclusion References Chapter 3 - Intelligent Data Analytics for Power Transformer Health Monitoring Using Modified Fuzzy Q Learning (MFQL) 1 - Introduction 2 - Data collection/source 2.1 - Dataset collection for the study 3 - Proposed approach and methodologies 3.1 - Feature vector formulation based on standard techniques 3.2 - Most influencing features selection 3.3 - Transformer health monitoring techniques 3.3.1 - Modify fuzzy Q learning (MFQL) based DGA interpretation 3.3.2 - Multilayer perceptron neural network (MLP-NN) 4 - Diagnosis performance analysis of standard techniques 4.1 - Performance analysis of standard techniques without AI 4.2 - Performance analysis of standard techniques with AI 4.2.1 - MLP-ANN based power transformer fault diagnosis 4.2.2 - MFQL based power transformer fault diagnosis 5 - Implementation of AI methods based on proposed most relevant input variables 5.1 - MLP-ANN based proposed approach implementation 5.2 - MFQL based proposed approach implementation 5.3 - Comparative analysis using AI based proposed approach 6 - Conclusions References Chapter 4 - Intelligent Data Analytics for 3-Phase Induction Motor Fault Diagnosis Using Gene Expression Programming (GEP) 1 - Introduction 2 - Brief information for IM condition monitoring innovations 3 - GEP methodology and data sources 3.1 - Database used for study 3.2 - Gene expression programming (GEP) 4 - External fault classifier based on GEP 4.1 - Dataset: training and testing 4.2 - The GEP approach 4.3 - GEP model formulation 5 - Results and discussion 6 - Conclusions References Chapter 5 - Intelligent Data Analytics for Power Quality Disturbance Diagnosis Using Extreme Learning Machine (ELM) 1 - Introduction 2 - Model formation and description 3 - Proposed approach 3.1 - Feature extraction using EMD technique 3.2 - Most relevant feature selection using WEKA based decision tree 3.3 - PQ diagnosis methods 3.3.1 - Extreme learning machine (ELM) overview 3.3.2 - Artificial neural network (ANN) overview 4 - Results and discussion 5 - Conclusion References Chapter 6 - Intelligent Data Analytics for Transmission Line Fault Diagnosis Using EEMD-Based Multiclass SVM and PSVM 1 - Introduction 2 - Methodology 2.1 - Proposed approach 2.2 - TL model formulation 2.3 - Feature extraction using EEMD 2.4 - Support vector machine (SVM) 2.5 - Proximal support vector machine (PSVM) 2.6 - SVM and PSVM based transmission line fault classification model formation 3 - Results and discussions 3.1 - SVM based transmission line fault classification 3.2 - PSVM based transmission line fault classification 3.3 - Comparative results analysis of SVM and PSVM based fault classification models 4 - Conclusion References Part B Intelligent Data Analytics for Forecastingin Smart Grid Chapter 7 - Intelligent Data Analytics for Global Solar Radiation Forecasting for Solar Power Production Using Deep Learnin... 1 - Introduction 2 - Data analysis for solar radiation forecasting and prediction (SRFP) 3 - Solar irradiance forecasting methods 4 - Study area and dataset collection used for study 5 - Structure of proposed model 5.1 - Deep learning neural network 5.2 - Performance evaluation measures 6 - Results and discussion 7 - Conclusion References Chapter 8 - Intelligent Data Analytics for Wind Speed Forecasting for Wind Power Production Using Long Short-Term Memory (L... 1 - Introduction 2 - Intelligent data analysis for WSFP 3 - Proposed framework formation 3.1 - Proposed approach formation 3.2 - Dataset collection for the study 3.3 - Feature extraction 3.4 - Most relevant feature selection 3.5 - Design of LSTM network 3.6 - Performance measure indices 4 - Case study: demonstration of results and discussion 5 - Conclusion References Chapter 9 - Intelligent Data Analytics for Time-Series Load Forecasting Using Fuzzy Reinforcement Learning (FRL) 1 - Introduction 2 - Intelligent data analytics for load forecasting 3 - Time-series load forecasting model 4 - Methodology 4.1 - Proposed approach 4.2 - Brief detail of FRL approach 4.3 - Data collection 5 - Case studies: performance evaluation 5.1 - Case study#1: month-ahead forecasting 5.2 - Case study#2: week-ahead forecasting 5.3 - Case study#3: day-ahead forecasting 5.4 - Case study#4: hour-ahead forecasting 6 - Conclusion and future work References Chapter 10 - Intelligent Data Analytics for Battery Health Forecasting Using Semi-Supervised and Unsupervised Extreme Learn... 1 - Introduction 2 - Methodology 2.1 - Data collection for study 2.2 - Proposed approach framework 2.2.1 - Formulation of HI extraction and optimization 2.2.1.1 - HI extraction 2.2.1.2 - HI optimization using Box-Cox transformation and its parameter identification 2.2.1.3 - HI performance evaluation 2.2.2 - RUL evaluation using multi-ELM 2.2.2.1 - RUL prediction 2.2.2.2 - Mathematical modeling of ELMs for RUL evaluation 2.2.2.2.1 - Mathematical modeling of SELM 2.2.2.2.2 - Mathematical modeling of SSELM 2.2.2.2.3 - Mathematical modeling of USELM 2.2.2.3 - RUL performance analysis 3 - Results and discussion 3.1 - HI extraction and optimization 3.1.1 - HI extraction 3.1.2 - HI optimization using Box-Cox transformation 3.1.3 - Transformed HI correlation analysis 3.1.4 - HI performance evaluation 3.2 - RUL estimation using ANN 4 - Conclusion Acknowledgment References Index Back cover