Fault diagnosis of electrohydraulic actuator based on multiple source signals: An experimental investigation

Wang, Yunlong; Miao, Jianguo; Wang, Jinglin; Yang, Fangfang; Tsui, Kwok‐Leung; Miao, Qiang

doi:10.1016/j.neucom.2020.05.102

Cited by 24 publications

(18 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the past period of time, the problem of fault diagnosis has been extensively studied in many literatures. [1][2][3][4][5][6][7][8][9][10] However, there is little research on incipient fault detection. The main reasons are that the fault evolution rate is relatively slow in the early stage, the fault symptoms are not obvious in the initial stage and hardly attract attentions, and the uncertainty of system modeling also affects fault detection to some extent.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Incipient fault prediction for nonlinear stochastic distribution systems

Zhang

Yao

2022

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

In order to avoid the occurrence of major accidents in the industrial production process, incipient fault prediction that can predict fault in advance has attracted more and more attentions. In this article, a generalized correntropy filtering‐based incipient fault prediction strategy is proposed, which is suitable for nonlinear stochastic distribution systems with simultaneous actuator and sensor faults and non‐Gaussian noise. Three filters are designed to predict the incipient fault of nonlinear stochastic distribution systems: the first one is used to predict the time when the incipient fault occurs, and the other two are used to estimate the evolution rate of sensor fault and actuator fault, respectively. When the residual signal exceeds the predetermined threshold, the fault is detected and the time of occurrence can be also estimated. Once the fault is detected, the designed filter can be used to estimate the evolution rate of the unknown fault. After estimating the time of fault appearance and its evolution rate, the change process of incipient fault can be predicted. Finally, an example of a chemical reaction process is given to illustrate the validity of the prediction scheme.

show abstract

Section: Introductionmentioning

confidence: 99%

“…In the past period of time, the problem of fault diagnosis has been extensively studied in many literatures 1‐10 . However, there is little research on incipient fault detection.…”

Section: Introductionmentioning

confidence: 99%

Incipient fault prediction for nonlinear stochastic distribution systems

Zhang

Yao

2022

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

show abstract

“…Chen et al 13 and Zhao et al 14 employed PCA to optimize the weight coefficients of neural networks and utilized improved neural networks to achieve abnormal parameter identification and unsupervised fault classification in the case of unlabeled data. To process the multi-source signals with information redundancy effectively, Wang et al 15 and Miao et al 16 conducted a series of experimental investigations and compared the processing results of various deep learning algorithms, which demonstrated the effectiveness of convolutional neural network in fault diagnosis of EHA. However, the above methods are mainly data-driven approaches.…”

Section: Introductionmentioning

confidence: 99%

An improved EKF based on excitation equivalent conversion for EHA multi-factor fault diagnosis

Chen

et al. 2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Electro-hydrostatic actuator (EHA), as an emerging power-by-wire (PBW) actuation mechanism with high energy efficiency and fast responsiveness, has been widely used in modern flight control systems. As a pivotal component, the fault diagnosis of EHA is necessary to ensure the reliability of the aircraft. Although researchers have proposed many effective fault diagnosis techniques at present, most of them can only deal with single-factor faults effectively. Recent studies on multi-state reliability and competing failure show that complicated systems such as EHA are more prone to multi-factor failures than single-factor failures. Therefore, an improved EKF based on excitation equivalent conversion is proposed in this paper to achieve the multi-factor fault diagnosis of EHA. First, the existing fault diagnosis methods for EHA and their limitations in multi-factor fault diagnosis are discussed. Then, multi-parameters estimation and observability, the key issues to achieve multi-factor fault diagnosis, are analyzed. Based on the structural characteristics and observability analysis of the second-order system, excitation equivalent conversion is introduced to establish additional available equation about the unknown state parameters to realize the multi-parameter estimation when system is unobservable. Finally, simulation and prototype test experiments have been performed, and the results demonstrate the efficacy of the proposed method, which outperforms that of the traditional single-factor failure analysis methods by comparison.

show abstract

“…Machine learning methods have achieved good performances for classification of rotating machinery. However, their architecture still lacks multi-layer nonlinear mapping ability, and as a result they cannot fully use previous information for classification, and existing methods need to exhibit better performances for the amount of data in complex conditions [ 11 , 12 , 13 , 14 ].…”

Section: Introductionmentioning

confidence: 99%

A Novel Hybrid Deep Learning Method for Fault Diagnosis of Rotating Machinery Based on Extended WDCNN and Long Short-Term Memory

Gao

Kim

2021

Sensors

View full text Add to dashboard Cite

Deep learning (DL) plays a very important role in the fault diagnosis of rotating machinery. To enhance the self-learning capacity and improve the intelligent diagnosis accuracy of DL for rotating machinery, a novel hybrid deep learning method (NHDLM) based on Extended Deep Convolutional Neural Networks with Wide First-layer Kernels (EWDCNN) and long short-term memory (LSTM) is proposed for complex environments. First, the EWDCNN method is presented by extending the convolution layer of WDCNN, which can further improve automatic feature extraction. The LSTM then changes the geometric architecture of the EWDCNN to produce a novel hybrid method (NHDLM), which further improves the performance for feature classification. Compared with CNN, WDCNN, and EWDCNN, the proposed NHDLM method has the greatest performance and identification accuracy for the fault diagnosis of rotating machinery.

show abstract

Fault diagnosis of electrohydraulic actuator based on multiple source signals: An experimental investigation

Cited by 24 publications

References 39 publications

Incipient fault prediction for nonlinear stochastic distribution systems

Incipient fault prediction for nonlinear stochastic distribution systems

An improved EKF based on excitation equivalent conversion for EHA multi-factor fault diagnosis

A Novel Hybrid Deep Learning Method for Fault Diagnosis of Rotating Machinery Based on Extended WDCNN and Long Short-Term Memory

Contact Info

Product

Resources

About