A Comparative Study of Deep Neural Network-Aided Canonical Correlation Analysis-Based Process Monitoring and Fault Detection Methods

Chen, Zhiwen; Liang, Ketian; Ding, Steven X.; Yang, Chao; Peng, Tao; Yuan, Xiaofeng

doi:10.1109/tnnls.2021.3072491

Cited by 35 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are three steps in the complete motor fault diagnosis process: fault detection, classification, and severity prediction. Among all the motor fault diagnosis methods, deep learning models are usually unable to build an end-to-end model due to the difficulty involved in obtaining training data and their poor anti-noise ability, so artificial features are required [16][17][18]. However, deep learning models have a strong representation ability and can be used as a part of a diagnosis method for feature preprocessing and other operations.…”

Section: Preliminariesmentioning

confidence: 99%

Multi-Condition PMSM Fault Diagnosis Based on Convolutional Neural Network Phase Tracker

et al. 2022

Self Cite

View full text Add to dashboard Cite

In many industrial systems, symmetry is the key to ensuring efficiency and reliability. For example, in electric vehicles, the driving system often requires high symmetry. As widely used motors, permanent magnet synchronous motors (PMSMs) are often used in highly symmetrical structures as the driving devices. Consequently, maintaining the symmetry of the system relies on the normal and stable operation of the PMSM, and it is necessary to diagnose faults in the PMSM in a timely manner. In PMSM fault diagnosis methods, frequency domain features of the stator current are extensively used. However, these features change with the switching of motor operating conditions, leading to difficulty of diagnosis in multiple operating conditions. Therefore, a fault diagnosis method based on a convolutional neural network (CNN) phase tracker is proposed in this paper. Through phase tracking and angular domain resampling, the fundamental frequency of stator currents in different operating conditions are aligned, so as to fix the distribution of frequency domain features and solve the problem of features changing with operating conditions. Experimental results show that the proposed method can resample the stator current signals with a small error, detect faults in a relatively short time with high accuracy, and diagnose fault type and severity level under multiple operating conditions.

show abstract

Section: Preliminariesmentioning

confidence: 99%

Multi-Condition PMSM Fault Diagnosis Based on Convolutional Neural Network Phase Tracker

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…where Ã = A + I, D = j Ãi j and W (k) ∈ R d×d is the trainable weight matrix. H (k) ∈ R n×n is the node embedding, which can be calculated after k steps of the GCN (k ∈ [2,6]). The node embedding H (k−1) are calculated from previous step, and the input initial node embedding (iteration k = 1) H (0) is the node features on the graph, i.e., H (0) = F .…”

Section: Spatial-based Convolution Treatment By Every Snapshotmentioning

confidence: 99%

Spatial-temporal associations representation and application for process monitoring using graph convolution neural network

Ren¹,

Yang²,

Liang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Industrial process data reflects the dynamic changes of operation conditions, which mainly refer to the irregular changes in the dynamic associations between different variables in different time. And this related associations knowledge for process monitoring is often implicit in these dynamic monitoring data which always have richer operation condition information and have not been paid enough attention in current research. To this end, a new process monitoring method based on spatial-based graph convolution neural network (SGCN) is proposed to describe the characteristics of the dynamic associations which can be used to represent the operation status over time. Spatia-temporal graphs are firstly defined, which can be used to represent the characteristics of node attributes (dynamic edge features) dynamically changing with time. Then, the associations between monitoring variables at a certain time can be considered as the node attributes to define a snapshot of the static graph network at the certain time. Finally, the snapshot containing graph structure and node attributes is used as model inputs which are processed to implement graph classification by spatial-based convolution graph neural network with aggregate and readout steps. The feasibility and applicability of this proposed method are demonstrated by our experimental results of benchmark and practical case application.

show abstract

“…Wu et al [ 23 ] proposed locality preserving randomized canonical correlation analysis (LPRCCA) by mapping raw data to a randomized low‐dimensional feature space through random Fourier feature mapping for real‐time nonlinear process monitoring. Chen et al [ 24 ] introduced four deep neural network (DNN) models which are suitable to combine with CCA, and analyzed the characteristics and differences of CCA assisted by each DNN model. Zheng et al [ 25 ] proposed fault detection models using CCA and just‐in‐time learning (JITL) to process scalar signals of high‐speed train gears, named CCA‐JITL.…”

Section: Introductionmentioning

confidence: 99%

A fault detection method based on sparse dynamic canonical correlation analysis

Hu,

Wu,

Pan

et al. 2023

Can J Chem Eng

View full text Add to dashboard Cite

Fault detection based on canonical correlation analysis (CCA) has received increased attention due to its efficiency in exploring the relationship between input and output. However, traditional CCA may generate redundant features in both the input and output projections while maximizing the correlations. In this paper, sparse dynamic canonical correlation analysis (SDCCA) is developed for dealing with the fault detection of dynamic processes. Through posing sparsity in the extraction of features, the interpretability of canonical variates is enhanced attributed to the sparsity of canonical weights. Based on the SDCCA model, the monitoring metric is established for fault detection. Moreover, the upper control limit (UCL) based on monitoring metrics is determined by the kernel density estimation (KDE) method to avoid the violation of the Gaussian assumption. The superiority of the proposed SDCCA‐based fault detection method is illustrated through a comparative study of the Tennessee Eastman process benchmark.

show abstract

A Comparative Study of Deep Neural Network-Aided Canonical Correlation Analysis-Based Process Monitoring and Fault Detection Methods

Cited by 35 publications

References 33 publications

Multi-Condition PMSM Fault Diagnosis Based on Convolutional Neural Network Phase Tracker

Multi-Condition PMSM Fault Diagnosis Based on Convolutional Neural Network Phase Tracker

Spatial-temporal associations representation and application for process monitoring using graph convolution neural network

A fault detection method based on sparse dynamic canonical correlation analysis

Contact Info

Product

Resources

About