Data Intensive Industrial Asset Management: IoT-based Algorithms and Implementation

✍ Scribed by Farhad Balali, Jessie Nouri, Adel Nasiri, Tian Zhao

• Publisher: Springer
• Tongue: English
• Leaves: 247
• Category: Library

✦ Synopsis

This book presents a step by step Asset Health Management Optimization Approach Using Internet of Things (IoT). The authors provide a comprehensive study which includes the descriptive, diagnostic, predictive, and prescriptive analysis in detail. The presentation focuses on the challenges of the parameter selection, statistical data analysis, predictive algorithms, big data storage and selection, data pattern recognition, machine learning techniques, asset failure distribution estimation, reliability and availability enhancement, condition based maintenance policy, failure detection, data driven optimization algorithm, and a multi-objective optimization approach, all of which can significantly enhance the reliability and availability of the system.

✦ Table of Contents

Preface
Contents
List of Figures
List of Tables
Author Biography
Chapter 1: Internet of Things (IoT): Principles and Framework
1.1 Internet of Things (IoT)
1.2 Smart Systems vs. Smart Connected Systems
1.2.1 Smart Connected System Main Layers
1.3 Dataflow in the Wisdom Pyramid
1.3.1 Smart Connected Systems Components and Technologies
1.4 Selection of Smart Devices
1.5 Centralized and Decentralized IoT Structures
1.6 Business Models´ Perspective
1.7 Concluding Remarks
References
Chapter 2: Industrial Asset Management and Maintenance Policies
2.1 Asset Management (AM)
2.2 Maintenance Strategies
2.3 Remaining Useful Lifetime (RUL)
2.4 IoT-Based Asset Management
2.5 General Key Performance Indicators
2.6 Concluding Remarks
References
Chapter 3: Asset Aging Through Degradation Mechanism
3.1 Asset Degradation
3.2 Challenges of Classical Models
3.3 Prognosis and Health Management (PHM)
3.4 Degradation Process
3.5 Remaining Useful Life (RUL)
3.6 Concluding Remarks
References
Chapter 4: Predictive Degradation Models
4.1 Degradation Models
4.2 Applications of the Degradation Models
4.3 General Path Degradation Models
4.4 Non-destructive Degradation Models
4.5 Non-destructive Degradation Predictive Models
4.6 Destructive Degradation Models
4.7 Destructive Degradation Predictive Models
4.8 Concluding Remarks
References
Chapter 5: IoT Platform: Smart Devices, Gateways, and Communication Networks
5.1 Smart Devices
5.2 Device Security
5.3 Smart Gateway
5.4 Communication Types
5.5 Network Service
5.6 Data Network Security
5.7 Concluding Remarks
References
Chapter 6: Data Features
6.1 Data Analysis
6.1.1 Qualitative and Quantitative Analysis
6.1.2 Parametric and Nonparametric Analysis
6.2 Data Requirement
6.3 Data Type
6.4 Data Process
6.4.1 Data Collection
6.4.2 Data Preparation
6.4.2.1 Data Fusion
6.4.2.2 Data Cleansing
6.4.2.3 Data Wrangling
6.4.2.4 Data Scraping
6.4.2.5 Data Filtration
6.4.2.6 Data Mapping
6.5 Data Visualization
6.6 Data Acquisition
6.7 Data Lake
6.8 Dark Data
6.9 Big Data
6.10 Time-Series Data
6.11 Data Mining
6.12 Concluding Remarks
References
Chapter 7: Data Analytics
7.1 Data Analytics
7.2 Analytics Value
7.3 Descriptive Analytics
7.4 Diagnostic Analytics
7.5 Predictive Analytics
7.6 Prescriptive Analytics
7.7 Concluding Remarks
References
Chapter 8: Machine Learning Principles
8.1 Introduction
8.2 Machine Learning Algorithms
8.2.1 Linear Regression
8.2.1.1 Linear Regression Assumptions
8.2.2 Logistic Regression
8.2.2.1 Logistic Regression Assumption
8.2.3 Decision Tree
8.2.4 Support Vector Machine
8.2.5 Naïve Bayes
8.2.6 Artificial Neural Network
8.2.7 Deep Neural Network
8.2.8 Convolution Neural Network
8.3 Machine Learning Algorithms Evaluation
8.4 Ensembles
8.5 Regression Example
8.6 Classification Example
8.7 Machine Learning as a Service (MLaaS)
8.8 Concluding Remarks
References
Chapter 9: Implementation Tools of IoT Systems
9.1 Introduction
9.1.1 IoT Platforms
9.1.2 Requirements of IoT Applications
9.1.3 Cloud-Based IoT Platform
9.2 Azure IoT Platform
9.2.1 IoT Devices and Gateways
9.2.2 Storage
9.2.3 Data Analysis
9.2.4 User Interface
9.3 Experiences with Azure
9.3.1 Data Set
9.3.2 Azure Setup
9.3.3 Resource Groups
9.3.4 IoT Hub and Storage
9.3.5 Stream Analytics
9.3.6 Azure Functions
9.3.7 Azure Machine Learning
9.3.8 Power BI
9.3.9 Experiment Observations
9.4 Conclusion
References
Appendix A: Regression Example
Linear Regression Matlab Code
Linear Interaction Regression Model
Linear Stepwise Regression Model
Decision Tress
Bagged Decision Tree
Linear SVM
Appendix B: Classification Example
Fine Tree
Bagged Tree
Fine KNN
Weighted KNN
Logistic Regression
Linear SVM
Quadratic SVM
Cubic SVM
Index