Cover Image

Transfer Learning for Rotary Machine Fault Diagnosis and Prognosis /

Transfer Learning for Rotary Machine Fault Diagnosis and Prognosis introduces the theory and latest applications of transfer learning on rotary machine fault diagnosis and prognosis. Transfer learning-based rotary machine fault diagnosis is a relatively new subject, and this innovative book synthesi...

Full description

Bibliographic Details
Main Author: Yan, Ruqiang
Corporate Author: ScienceDirect (Online service)
Format: eBook
Language:English
Published: Amsterdam, Netherlands ; Oxford, United Kingdom ; Cambridge MA : Elsevier, [2024]
Subjects:
Transfer learning (Machine learning)
Fault location (Engineering) > Data processing.
Machinery.
Apprentissage par transfert (Intelligence artificielle)
Détection de défaut (Ingénierie) > Informatique.
Machines.
machinery.
Fault location (Engineering) > Data processing
Machinery
Electronic books.
Online Access:Connect to the full text of this electronic book
Table of Contents:
  • Front Cover
  • Transfer Learning for Rotary Machine Fault Diagnosis and Prognosis
  • Transfer Learning for Rotary Machine Fault Diagnosis and Prognosis
  • Copyright
  • Contents
  • Author biography
  • Preface
  • One
  • Introduction of machine fault diagnosis and prognosis
  • 1.1 Background of machine fault diagnosis and prognosis
  • 1.2 Machine fault diagnosis and prognosis technology with artificial intelligence
  • 1.2.1 Fault diagnosis of rotating machinery based on new generation AI technology
  • 1.2.2 RUL prediction of rotating machinery based on new generation AI technology
  • 1.3 Machine fault diagnosis and prognosis technology with transfer learning
  • 1.3.1 Research on rotating machinery fault diagnosis based on transfer learning
  • 1.3.2 Research on rotating machinery RUL prediction based on transfer learning
  • 1.4 Current problems and potential solutions
  • References
  • Two
  • Foundations on transfer learning in machine fault diagnosis and prognosis
  • 2.1 From machine learning to transfer learning
  • 2.2 Model structure of transfer learning
  • 2.2.1 Parameter-based knowledge transfer
  • 2.2.2 Instance-based knowledge transfer
  • 2.2.3 Feature-based knowledge transfer
  • 2.2.4 Relevance-based knowledge transfer
  • 2.3 The necessity of transfer learning
  • 2.4 Negative transfer
  • 2.5 Transfer components of machine fault diagnosis and prognosis models
  • 2.6 Transfer fields of machine fault diagnosis and prognosis models
  • 2.6.1 Transfer tasks across channels
  • 2.6.2 Transfer between multiple machines
  • 2.7 Transfer orders of machine fault diagnosis and prognosis models
  • References
  • Three
  • Fault diagnosis models based on feature/sample transfer components
  • 3.1 Machine fault diagnosis based on improved least squares support vector machines
  • 3.1.1 Least squares support vector machine
  • 3.1.2 Multitask LSSVM
  • 3.1.3 The NMPT framework for GFD
  • 3.1.4 Complete process of the NMPT model for gear fault diagnosis
  • 3.1.5 Experiment and discussion
  • 3.2 Machine fault diagnosis model based on hybrid transfer strategy
  • 3.2.1 Overall framework of hybrid transfer strategy
  • 3.2.2 Multidomain feature extraction
  • 3.2.3 Signed rank and chi-square test-based similarity estimation
  • 3.2.4 Hybrid transfer-based gear fault diagnosis
  • 3.2.4.1 Low-quality source domains: The fast TrAdaBoost algorithm
  • 3.2.4.2 High-quality source domains: The PMT algorithm
  • 3.2.5 Experimentation and performance analysis
  • References
  • Four
  • Fault diagnosis models based on cross time field transfer
  • 4.1 Introduction
  • 4.2 Machine fault diagnosis model based on dimensionality reduction projection
  • 4.2.1 Basic assumptions
  • 4.2.2 Dimensionality reduction projection
  • 4.2.3 Building projection model
  • 4.3 Machine fault diagnosis model based on locally weighted enhanced maximum interval projection