An improved ensemble fusion autoencoder model for fault diagnosis from imbalanced and incomplete data

Abstract Skewed distribution and incompleteness of monitored data might cause feature submergence and information loss, rendering the fault diagnosis from imbalanced and incomplete data commonly existing in industrial systems is still an intractable problem. Therefore, in order to improve the accuracy of fault diagnosis from imbalanced and incomplete data, this paper proposes a fusion autoencoder (FAE) network and an ensemble diagnosis scheme. A designed multi-level denoising strategy and a variable-scale resampling strategy are adopted as compensation for information loss and skewed distribution. The multiple FAE networks are constructed by combining the advantages of improved sparse autoencoder (SAE) with denoising autoencoder (DAE) to enhance the adaptability. Different hyper parameters are configured for each FAE to ameliorate the diagnostic flexibility, and Bagging strategy is employed to integrate each network into a complete FAE fault diagnosis model. Furthermore, evaluation criteria are suggested and the application range of the model is tested. Finally, different experiments are conducted to verify the effectiveness and practicability of the proposed method.

[1]  Liang Chen,et al.  Deep Fault Recognizer: An Integrated Model to Denoise and Extract Features for Fault Diagnosis in Rotating Machinery , 2016, Applied Sciences.

[2]  Zhiqiang Ge,et al.  Distributed parallel deep learning of Hierarchical Extreme Learning Machine for multimode quality prediction with big process data , 2019, Eng. Appl. Artif. Intell..

[3]  Zhiqiang Ge,et al.  K-means Bayes algorithm for imbalanced fault classification and big data application , 2019, Journal of Process Control.

[4]  Chunhui Zhao,et al.  A Fine-Grained Adversarial Network Method for Cross-Domain Industrial Fault Diagnosis , 2020, IEEE Transactions on Automation Science and Engineering.

[5]  Chunhui Zhao,et al.  Robust Monitoring and Fault Isolation of Nonlinear Industrial Processes Using Denoising Autoencoder and Elastic Net , 2020, IEEE Transactions on Control Systems Technology.

[6]  Xiao He,et al.  Remaining useful life estimation for micro switches of railway vehicles , 2019 .

[7]  Jian-Guo Wang,et al.  Stacked autoencoder for operation prediction of coke dry quenching process , 2019, Control Engineering Practice.

[8]  Guo Xie,et al.  Adaptive Transition Probability Matrix-Based Parallel IMM Algorithm , 2019, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[9]  Cong Wang,et al.  Construction of hierarchical diagnosis network based on deep learning and its application in the fault pattern recognition of rolling element bearings , 2016 .

[10]  Huaqing Wang,et al.  A New Method for Weak Fault Feature Extraction Based on Improved MED , 2018 .

[11]  Amir Hussain,et al.  Applications of Deep Learning and Reinforcement Learning to Biological Data , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[12]  Chunhui Zhao,et al.  Fault Subspace Selection Approach Combined With Analysis of Relative Changes for Reconstruction Modeling and Multifault Diagnosis , 2016, IEEE Transactions on Control Systems Technology.

[13]  Hongyang Li,et al.  Design of data-injection attacks for cyber-physical systems based on Kullback-Leibler divergence , 2019, Neurocomputing.

[14]  Changyin Sun,et al.  Support vector machine-based optimized decision threshold adjustment strategy for classifying imbalanced data , 2015, Knowl. Based Syst..

[15]  Xin Li,et al.  Estimating the Probability Density Function of Remaining Useful Life for Wiener Degradation Process with Uncertain Parameters , 2019, International Journal of Control, Automation and Systems.

[16]  Haidong Shao,et al.  An enhancement deep feature fusion method for rotating machinery fault diagnosis , 2017, Knowl. Based Syst..

[17]  Youmin Zhang,et al.  Deep model integrated with data correlation analysis for multiple intermittent faults diagnosis. , 2019, ISA transactions.

[18]  Xiaofeng Wang,et al.  Networked Strong Tracking Filtering with Multiple Packet Dropouts: Algorithms and Applications , 2014, IEEE Transactions on Industrial Electronics.

[19]  Wei Guo,et al.  A hybrid intelligent multi-fault detection method for rotating machinery based on RSGWPT, KPCA and Twin SVM. , 2017, ISA transactions.

[20]  Yan-Fu Li,et al.  A SVM framework for fault detection of the braking system in a high speed train , 2017, Mechanical Systems and Signal Processing.

[21]  Changqing Shen,et al.  Stacked Sparse Autoencoder-Based Deep Network for Fault Diagnosis of Rotating Machinery , 2017, IEEE Access.

[22]  Wentao Mao,et al.  Online sequential prediction of bearings imbalanced fault diagnosis by extreme learning machine , 2017 .

[23]  Jiangtao Wen,et al.  Intelligent Bearing Fault Diagnosis Method Combining Compressed Data Acquisition and Deep Learning , 2018, IEEE Transactions on Instrumentation and Measurement.

[24]  Chunhui Zhao,et al.  Online Fault Diagnosis for Industrial Processes With Bayesian Network-Based Probabilistic Ensemble Learning Strategy , 2019, IEEE Transactions on Automation Science and Engineering.

[25]  Ming Zhao,et al.  A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox , 2017 .

[26]  Jing Yang,et al.  An improved deep network for intelligent diagnosis of machinery faults with similar features , 2019, IEEJ Transactions on Electrical and Electronic Engineering.

[27]  Zhiqiang Ge,et al.  Scalable learning and probabilistic analytics of industrial big data based on parameter server: Framework, methods and applications , 2019, Journal of Process Control.

[28]  Fang Wang,et al.  Prediction of NOX emission for coal-fired boilers based on deep belief network , 2018, Control Engineering Practice.

[29]  Alessandro Beghi,et al.  Data-driven Fault Detection and Diagnosis for HVAC water chillers , 2016 .

[30]  Peng Li,et al.  Parallel processing algorithm for railway signal fault diagnosis data based on cloud computing , 2018, Future Gener. Comput. Syst..

[31]  Chunhui Zhao,et al.  Statistical analysis based online sensor failure detection for continuous glucose monitoring in type I diabetes , 2015 .

[32]  Dongying Han,et al.  Stochastic resonance in a time-delayed feedback tristable system and its application in fault diagnosis , 2018, Journal of Sound and Vibration.

[33]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[34]  Chunhui Zhao,et al.  Enhanced Random Forest With Concurrent Analysis of Static and Dynamic Nodes for Industrial Fault Classification , 2020, IEEE Transactions on Industrial Informatics.