Sparse Autoencoder-based Multi-head Deep Neural Networks for Machinery Fault Diagnostics with Detection of Novelties

作     者：Zhe Yang Dejan Gjorgjevikj Jianyu Long Yanyang Zi Shaohui Zhang Chuan Li Zhe Yang;Dejan Gjorgjevikj;Jianyu Long;Yanyang Zi;Shaohui Zhang;Chuan Li

作者机构：School of Mechanical EngineeringDongguan University of TechnologyDongguan 523808China School of Mechanical EngineeringXi’an Jiaotong UniversityXi’an 710049China Faculty of Computer Science and EngineeringSs.Cyril and Methodius UniversitySkopjeMacedonia 

出 版 物：《Chinese Journal of Mechanical Engineering》 (中国机械工程学报（英文版）)

年 卷 期：2021年第34卷第3期

页      面：146-157页

核心收录：

学科分类：08[工学] 081104[工学-模式识别与智能系统] 0817[工学-化学工程与技术] 0807[工学-动力工程及工程热物理] 0802[工学-机械工程] 0811[工学-控制科学与工程] 080201[工学-机械制造及其自动化] 0801[工学-力学（可授工学、理学学位）] 

基　　金：Supported by National Natural Science Foundation of China(Grant Nos.52005103,71801046,51775112,51975121) Guangdong Province Basic and Applied Basic Research Foundation of China(Grant No.2019B1515120095) Intelligent Manufacturing PHM Innovation Team Program(Grant Nos.2018KCXTD029,TDYB2019010) MoST International Cooperation Program(6-14). 

主　　题：Deep learning Fault diagnostics Novelty detection Multi-head deep neural network Sparse autoencoder 

摘      要：Supervised fault diagnosis typically assumes that all the types of machinery failures are known.However,in practice unknown types of defect,i.e.,novelties,may occur,whose detection is a challenging task.In this paper,a novel fault diagnostic method is developed for both diagnostics and detection of novelties.To this end,a sparse autoencoder-based multi-head Deep Neural Network(DNN)is presented to jointly learn a shared encoding representation for both unsupervised reconstruction and supervised classification of the monitoring data.The detection of novelties is based on the reconstruction error.Moreover,the computational burden is reduced by directly training the multi-head DNN with rectified linear unit activation function,instead of performing the pre-training and fine-tuning phases required for classical DNNs.The addressed method is applied to a benchmark bearing case study and to experimental data acquired from a delta 3D printer.The results show that its performance is satisfactory both in detection of novelties and fault diagnosis,outperforming other state-of-the-art methods.This research proposes a novel fault diagnostics method which can not only diagnose the known type of defect,but also detect unknown types of defects.