https://orcid.org/0009-0000-2830-0695
Abstract
Aiming at the nonlinear and dynamic characteristics of data in automotive engine systems, a fault detection method based on canonical variate analysis combined with Bhattacharyya distance (CVA-BD) is proposed in this paper. First, CVA is utilized to calculate the state space of the system data. Second, a sliding window is introduced in the state space to quantify the difference in data distribution within the window using Bhattacharyya distance, thereby constructing a novel statistical indicator. Finally, the control limit for statistical indicator is determined to achieve process monitoring of automotive engine systems. CVA-BD effectively enhances the performance of process monitoring by capturing the sequential correlation of data through CVA and eliminating the nonlinear impact between samples using similarity measurement metrics. Simulation experiments are conducted using a numerical case and experimental data from turbocharged spark ignition (TCSI) engines. The simulation results further confirm that, compared with principal component analysis (PCA), dynamic principal component analysis (DPCA), canonical variable analysis (CVA), dissimilar canonical variable analysis (CVDA), auto-encoder (AE), and stacked auto-encoder (SAE) CVA-BD has demonstrated an improvement of at least 41%.
References
1.
Abboush
, M.
, Bamal
, D.
, Knieke
, C.
, and Rausch
, A.
, 2022
, “Intelligent Fault Detection and Classification Based on Hybrid Deep Learning Methods for Hardware-in-the-Loop Test of Automotive Software Systems
,” Sensors
, 22
(11
), p. 4066
.10.3390/s221140662.
Shang
, L.
, Liu
, J.
, and Zhang
, Y.
, 2017
, “Efficient Recursive Canonical Variate Analysis Approach for Monitoring Time-Varying Processes
,” J. Chemom.
, 31
(1
), p. e2858
.10.1002/cem.28583.
Fan
, S.
, Zhang
, X.
, and Song
, Z.
, 2022
, “Imbalanced Sample Selection With Deep Reinforcement Learning for Fault Diagnosis
,” IEEE Trans. Ind. Inform.
, 18
(4
), pp. 2518
–2527
.10.1109/TII.2021.31002844.
de Almeida
, V. E.
, de Sousa Fernandes
, D. D.
, Diniz
, P. H. G. D.
, de Araújo Gomes
, A.
, Véras
, G.
, Galvão
, R. K. H.
, and Araujo
, M. C. U.
, 2021
, “Scores Selection Via Fisher's Discriminant Power in PCA-LDA to Improve the Classification of Food Data
,” Food Chem.
, 363
, p. 130296
.10.1016/j.foodchem.2021.1302965.
Tang
, Y.
, Shang
, L.
, Zhang
, R.
, Li
, J.
, and Fu
, H.
, 2024
, “Hybrid Divergence Based on Mean Absolute Scaled Error for Incipient Fault Detection
,” Eng. Appl. Artif. Intell.
, 129
, p. 107662
.10.1016/j.engappai.2023.1076626.
Gao
, L.
, Li
, D.
, Liu
, X.
, and Liu
, G.
, 2022
, “Enhanced Chiller Faults Detection and Isolation Method Based on Independent Component Analysis and k-Nearest Neighbors Classifier
,” Build. Environ.
, 216
, p. 109010
.10.1016/j.buildenv.2022.1090107.
Ma
, X.
, Wu
, D.
, Gao
, S.
, Hou
, T.
, and Wang
, Y.
, 2023
, “Autocorrelation Feature Analysis for Dynamic Process Monitoring of Thermal Power Plants
,” IEEE Trans. Cybern.
, 53
(8
), pp. 5387
–5399
.10.1109/TCYB.2022.32288618.
Navarro-Acosta
, J. A.
, García-Calvillo
, I. D.
, and Reséndiz-Flores
, E. O.
, 2022
, “Fault Detection Based on Squirrel Search Algorithm and Support Vector Data Description for Industrial Processes
,” Soft Comput.
, 26
(24
), pp. 13639
–13650
.10.1007/s00500-022-07337-99.
Zhao
, Y. P.
, Xie
, Y. L.
, and Ye
, Z. F.
, 2021
, “A New Dynamic Radius SVDD for Fault Detection of Aircraft Engine
,” Eng. Appl. Artif. Intell.
, 100
, p. 104177
.10.1016/j.engappai.2021.10417710.
Sun
, H.
, Guo
, Y.
, and Zhao
, W.
, 2020
, “Fault Detection for Aircraft Turbofan Engine Using a Modified Moving Window KPCA
,” IEEE Access
, 8
, pp. 166541
–166552
.10.1109/ACCESS.2020.302277111.
Xi
, W.
, Li
, Z.
, Tian
, Z.
, and Duan
, Z.
, 2018
, “A Feature Extraction and Visualization Method for Fault Detection of Marine Diesel Engines
,” Measurement
, 116
, pp. 429
–437
.10.1016/j.measurement.2017.11.03512.
Chaudhuri
, A.
, Sadek
, C.
, Kakde
, D.
, Wang
, H.
, Hu
, W.
, Jiang
, H.
, Kong
, S.
, Liao
, Y.
, and Peredriy
, S.
, 2021
, “The Trace Kernel Bandwidth Criterion for Support Vector Data Description
,” Pattern Recogn.
, 111
, p. 107662
.10.1016/j.patcog.2020.10766213.
Zhang
, Q.
, Li
, P.
, Lang
, X.
, and Miao
, A.
, 2020
, “Improved Dynamic Kernel Principal Component Analysis for Fault Detection
,” Measurement
, 158
, p. 107738
.10.1016/j.measurement.2020.10773814.
Wu
, P.
, Lou
, S.
, Zhang
, X.
, He
, J.
, Liu
, Y.
, and Gao
, J.
, 2021
, “Data-Driven Fault Diagnosis Using Deep Canonical Variate Analysis and Fisher Discriminant Analysis
,” IEEE Trans. Ind. Inform.
, 17
(5
), pp. 3324
–3334
.10.1109/TII.2020.303017915.
Le Roux
, N.
, and Gardner-Lubbe
, S.
, 2024
, “A Two-Group Canonical Variate Analysis Biplot for an Optimal Display of Both Means and Cases
,” Adv. Data Anal. Classif.
, pp. 1
–28
.10.1007/s11634-024-00593-716.
Ma
, L.
, Li
, X.
, and Lei
, C.
, 2017
, “Process Monitoring of the Pneumatic Control Valve Using Canonical Variate Analysis
,” 2017 Chinese Automation Congress (CAC)
, Jinan, China, Oct. 20–22, pp. 2784
–2788
.10.1109/CAC.2017.824324917.
Odiowei
, P. E. P.
, and Cao
, Y.
, 2010
, “Nonlinear Dynamic Process Monitoring Using Canonical Variate Analysis and Kernel Density Estimations
,” IEEE Trans. Ind. Inform.
, 6
(1
), pp. 36
–45
.10.1109/TII.2009.203265418.
Dong
, J.
, Jiang
, L.
, Zhang
, C.
, and Peng
, K.
, 2022
, “A Novel Quality-Related Incipient Fault Detection Method Based on Canonical Variate Analysis and Kullback-Leibler Divergence for Large-Scale Industrial Processes
,” IEEE Trans. Instrum. Meas.
, 71
, pp. 1
–10
.10.1109/TIM.2022.319923919.
Bhattacharyya
, A.
, 1946
, “On a Measure of Divergence Between Two Multinomial Populations
,” Sankhyā: Indian J. Stat.
, 7
(4
), pp. 401
–406
.http://www.jstor.org/stable/2504788220.
Gupta
, S.
, Thakar
, U.
, and Tokekar
, S.
, 2022
, “Similarity Distance-Based Kernel Canonical Correlation Analysis for Multiview Data Representation
,” Proceedings of International Conference on Data Science and Applications
, Springer
, Kolkata, India
, Apr. 10–11, 2021, pp. 649
–660
.10.1007/978-981-16-5348-3_5221.
Gupta
, S.
, Thakar
, U.
, and Tokekar
, S.
, 2021
, “Canonical Correlation Analysis With Bhattacharya Similarity Distance for Multiview Data Representation
,” 2020 Proceedings of SocProS on Soft Computing for Problem Solving
, Springer
, Indore, India
, Dec. 18–20, pp. 505
–516
.10.1007/978-981-16-2712-5_4122.
Pilario
, K. E. S.
, and Cao
, Y.
, 2018
, “Canonical Variate Dissimilarity Analysis for Process Incipient Fault Detection
,” IEEE Trans. Ind. Inform.
, 14
(12
), pp. 5308
–5315
.10.1109/TII.2018.281082223.
Wu
, P.
, Ferrari
, R. M. G.
, Liu
, Y.
, and van Wingerden
, J.-W.
, 2021
, “Data-Driven Incipient Fault Detection Via Canonical Variate Dissimilarity and Mixed Kernel Principal Component Analysis
,” IEEE Trans. Ind. Inform.
, 17
(8
), pp. 5380
–5390
.10.1109/TII.2020.302990024.
Jang
, K.
, Hong
, S.
, Kim
, M.
, Na
, J.
, and Moon
, I.
, 2022
, “Adversarial Autoencoder Based Feature Learning for Fault Detection in Industrial Processes
,” IEEE Trans. Ind. Inform.
, 18
(2
), pp. 827
–834
.10.1109/TII.2021.307841425.
Qian
, J.
, Song
, Z.
, Yao
, Y.
, Zhu
, Z.
, and Zhang
, X.
, 2022
, “A Review on Autoencoder Based Representation Learning for Fault Detection and Diagnosis in Industrial Processes
,” Chemometr. Intell. Lab. Syst.
, 231
, p. 104711
.10.1016/j.chemolab.2022.10471126.
Yu
, W.
, and Zhao
, C.
, 2021
, “Low-Rank Characteristic and Temporal Correlation Analytics for Incipient Industrial Fault Detection With Missing Data
,” IEEE Trans. Ind. Inform.
, 17
(9
), pp. 6337
–6346
.10.1109/TII.2020.299097527.
Das
, R. S.
, 1965
, “An Application of Factor and Canonical Analysis to Multivariate 1
,” Br. J. Math. Stat. Psychol.
, 18
(1
), pp. 57
–69
.10.1111/j.2044-8317.1965.tb00693.x28.
Jiang
, Q.
, and Yan
, X.
, 2019
, “Learning Deep Correlated Representations for Nonlinear Process Monitoring
,” IEEE Trans. Ind. Inform.
, 15
(12
), pp. 6200
–6209
.10.1109/TII.2018.288604829.
Flores
, J. L.
, Calvo
, B.
, and Perez
, A.
, 2019
, “Supervised Non-Parametric Discretization Based on Kernel Density Estimation
,” Pattern Recogn. Lett.
, 128
, pp. 496
–504
.10.1016/j.patrec.2019.10.01630.
Weng
, H.
, Chen
, H.
, Wu
, L.
, Huang
, J.
, and Li
, Z.
, 2021
, “A Novel Pilot Protection Scheme for Transmission Lines Based on Current Distribution Histograms and Their Bhattacharyya Coefficient
,” Electr. Power Syst. Res.
, 194
, p. 107056
.10.1016/j.epsr.2021.10705631.
Tang
, J.
, Cheng
, J.
, Xiang
, D.
, and Hu
, C.
, 2022
, “Large-Difference-Scale Target Detection Using a Revised Bhattacharyya Distance in SAR Images
,” IEEE Geosci. Remote Sens. Lett.
, 19
, pp. 1
–5
.10.1109/LGRS.2022.316193132.
Kini
, K. R.
, and Madakyaru
, M.
, 2020
, “Improved Process Monitoring Strategy Using Kantorovich Distance-Independent Component Analysis: An Application to Tennessee Eastman Process
,” IEEE Access
, 8
, pp. 205863
–205877
.10.1109/ACCESS.2020.303773033.
Li
, N.
, Shi
, H.
, Song
, B.
, and Tao
, Y.
, 2020
, “Temporal-Spatial Neighborhood Enhanced Sparse Autoencoder for Nonlinear Dynamic Process Monitoring
,” Processes
, 8
(9
), p. 1079
.10.3390/pr809107934.
Han
, P.
, Ellefsen
, A. L.
, Li
, G.
, Holmeset
, F. T.
, and Zhang
, H.
, 2021
, “Fault Detection With LSTM-Based Variational Autoencoder for Maritime Components
,” IEEE Sens. J.
, 21
(19
), pp. 21903
–21912
.10.1109/JSEN.2021.310522635.
Yu
, F.
, Liu
, J.
, Liu
, D.
, Wang
, H.
, and Shang
, L.
, 2023
, “Feature Learning Based on Entropy Estimation Density Peak Clustering and Stacked Autoencoder for Industrial Process Monitoring
,” Can. J. Chem. Eng.
, 101
(7
), pp. 3998
–4015
.10.1002/cjce.2475036.
Shang
, L.
, Gu
, Y.
, Tang
, Y.
, Fu
, H.
, and Hua
, L.
, 2023
, “Recursive Ensemble Canonical Variate Analysis for Online Incipient Fault Detection in Dynamic Processes
,” Measurement
, 220
, p. 113411
.10.1016/j.measurement.2023.11341137.
Ng
, K. Y.
, Frisk
, E.
, Krysander
, M.
, and Eriksson
, L.
, 2020
, “A Realistic Simulation Testbed of a Turbocharged Spark-Ignited Engine System: A Platform for the Evaluation of Fault Diagnosis Algorithms and Strategies
,” IEEE Control Syst.
, 40
(2
), pp. 56
–83
.10.1109/MCS.2019.296179338.
Yu
, J.
, and Yan
, X.
, 2021
, “A New Deep Model Based on the Stacked Autoencoder With Intensified Iterative Learning Style for Industrial Fault Detection
,” Process Saf. Environ. Prot.
, 153
, pp. 47
–59
.10.1016/j.psep.2021.07.00239.
Zhang
, Z.
, 2019
, “Linear Canonical Wigner Distribution Based Noisy LFM Signals Detection Through the Output SNR Improvement Analysis
,” IEEE Trans. Signal Process.
, 67
(21
), pp. 5527
–5542
.10.1109/TSP.2019.294107140.
Han
, X.
, Jiang
, J.
, Xu
, A.
, Huang
, X.
, Pei
, C.
, and Sun
, Y.
, 2021
, “Fault Detection of Pneumatic Control Valves Based on Canonical Variate Analysis
,” IEEE Sens. J.
, 21
(12
), pp. 13603
–13615
.10.1109/JSEN.2021.3070035
