Deep learning is a significant branch of machine learning that involves training artificial neural networks with multiple layers to learn and make predictions from data. It has gained wide attention and popularity due to its remarkable success in various complex tasks, such as image and speech recognition, natural language processing, and game playing. Due to its ability to automatically learn complex patterns and representations from data, deep learning has great potential to enhance accuracy, efficiency, and the ability to identify complex fault patterns in fault diagnosis. Therefore, four deep learning-based network models, including convolutional neural network (CNN), deep belief network (DBN), stacked auto-encoder (SAE), and recurrent neural network (RNN), are introduced in this chapter. With cases of automotive transmission fault diagnosis and tool degradation assessment, this chapter gives detailed descriptions of how to apply deep neural networks (DNNs) for machinery fault diagnosis and equipment degradation assessment and the effectiveness has also been verified.
Deep Learning Based Machinery Fault Diagnosis
Intelligent Fault Diagnosis and Health Assessment for Complex Electro-Mechanical Systems ; Kapitel : 5 ; 273-370
11.09.2023
98 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Rotating machinery fault detection and diagnosis based on deep domain adaptation: A survey
Elsevier | 2023
|Construction of a deep sparse filtering network for rotating machinery fault diagnosis
SAGE Publications | 2022
|Machinery Fault Diagnosis of Packing Seal in Reciprocating Compressor
British Library Online Contents | 1996
|Fault fusion diagnosis of aero-engine based on deep learning
British Library Online Contents | 2018
|