A Study on the Anomaly Detection of Engine Clutch Engagement/Disengagement Using Machine Learning for Transmission Mounted Electric Drive Type Hybrid Electric Vehicles

Ji, Yonghyeok; Jeong, Seong‐Yong; Cho, Yeongjin; Seo, Hanbyul; Bang, Jae-Sung; Kim, Jihwan; Lee, Hyeongcheol

doi:10.3390/app112110187

Cited by 6 publications

(2 citation statements)

References 67 publications

(102 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Even without labelled data, anomaly detection algorithms can be used to detect abnormal behaviour associated with the clutch system. The algorithms learn the usual operating features of the clutches then flag abnormal sensory data profiles, this ultimate enables the algorithm to detect unexpected malfunctions of the clutch [5].…”

Section: Anomaly Detectionmentioning

confidence: 99%

Deep learning based fault detection of automobile dry clutch system using spectrogram plots

Sai S,

Sridharan,

Chakrapani

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

In this research study, a novel approach that leverages the power of transfer learning (a famous deep learning technique) is proposed to diagnose multiple types of clutch faults including, worn release fingers, fractured pressure plates, deteriorated pressure plates, loss of friction material and distorted tangential strips using spectrogram plots. To train and validate the diagnostic system, vibration readings were taken from a specially designed test rig with the help of piezoelectric accelerometer while the clutch system was operated under different load conditions of 0 (no load), 5 and 10 kg This procedure of data collection was then repeated to acquire the vibration data for all of the fault conditions by replacing the good with fault components individually. These vibration signals were further processed and transformed into spectrogram plots that serves as the input data for the deep learning models considered. Fine-tuning techniques were applied on pretrained networks to maximise the prediction accuracy of the models to effectively determine and diagnose faults in the clutch system. For this study 12 pre-trained networks were chosen namely, Xception, InceptionResNet, DenseNet, AlexNet, VGG16, GoogLeNet, VGG19, ResNet101, ResNet50, InceptionV3, MobileNetV2 and ShuffleNet. To optimize the performance of deep learning models, a systematic adjustment of hyperparameters such as the train-test split ratio, learning rate, optimizer and batch size for each network model was carried out. Through careful experimentation and analysis, significant improvements in fault classification accuracy were achieved thereby enhancing the reliability and effectiveness of the diagnostic system. From the results it was noted that 100% classification accuracy was displayed by AlexNet (for the no load condition and the 10kg load condition) and GoogLeNet (for 5 kg load condition) with extremely low computation times.

show abstract

Section: Anomaly Detectionmentioning

confidence: 99%

Deep learning based fault detection of automobile dry clutch system using spectrogram plots

Sai S,

Sridharan,

Chakrapani

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…A machine learning based approach, having a unique advantage to solve complex problems which have no certain explicit laws, lends itself as a suitable method to explore the underlying process-structure-property relationships governing the RSW. ML techniques have been leveraged to develop optimized systems and effective decision making in many engineering and manufacturing fields [7][8][9][10]. Recently, ML algorithms have been employed to address the key issues associated with materials joining, such as the weld nugget prediction based on infrared images using convolutional neural network [11], weld penetration detection from multisource sensing images using ensembled neural network models [12], defect-welding process correlation establishment using decision tree and Bayesian neural network [13], process-property relationship for Al-steel ultrasonic welds using feed forward neural network [14], weld quality monitoring by analyzing in situ signals using multi-layer perception and support vector regression [15], and autonomous nondestructive evaluation of weld quality using convolutional neural network [16,17], etc.…”

Section: Introductionmentioning

confidence: 99%

A New Perspective of Post-Weld Baking Effect on Al-Steel Resistance Spot Weld Properties through Machine Learning and Finite Element Modeling

Zhang

Wang

Chen

et al. 2022

JMMP

View full text Add to dashboard Cite

The root cause of post-weld baking on the mechanical performance of Al-steel dissimilar resistance spot welds (RSWs) has been determined by machine learning (ML) and finite element modeling (FEM) in this study. A deep neural network (DNN) model was constructed to associate the spot weld performance with the joint attributes, stacking materials, and other conditions, using a comprehensive experimental dataset. The DNN model positively identified that the post-weld baking reduces the joint performance, and the extent of degradation depends on the thickness of stacking materials. A three-dimensional finite element (FE) model was then used to investigate the root cause and the mechanism of the baking effect. It revealed that the formation of high thermal stresses during baking, from the mismatch of thermal expansion between steel and Al alloy, causes damage and cracking of the brittle intermetallic compound (IMC) formed at the interface of the weld nugget during welding. This in turn reduces the joint performance by promoting undesirable interfacial fracture when the welds were subjected to externally applied loads. The FEM model further revealed that increase in structural stiffness, because of increase in steel sheet thickness, reduces the thermal stresses at the interface caused by the thermal expansion mismatch and consequently lessens the detrimental effect of post-weld baking on the joint performance.

show abstract

Enhanced fault detection in automobile clutch system using CATboost with feature fusion method

Sai,

Chakrapani,

Annamalai

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

Automobile clutch systems represent pivotal components within vehicles that facilitate smooth gear shifting, optimal engine operation, and efficient power transmission. Ensuring the integrity of clutch systems is paramount for maintaining vehicle performance and safety standards. Consequently, developing robust fault detection methodologies is imperative for promptly identifying potential issues. This study investigates the application of a CATboost classifier with feature fusion to analyse vibrational signals from clutch systems. Vibrational signals, collected via specialized sensors across various clutch conditions, serve as the primary dataset for fault detection analysis. A comprehensive feature fusion approach, combining statistical, histogram, and Autoregressive Moving Average (ARMA) features, aims to enhance fault detection accuracy. By integrating these feature sets, the study gains insights into clutch system behavior under varying operational circumstances. The classifier successfully identifies five distinct faults: worn release fingers, fractured pressure plates, deteriorated pressure plates, loss of friction material, and distorted tangential strips. Each fault presents unique challenges, emphasizing the significance of accurate detection mechanisms. Results underscore the remarkable performance of the CATboost classifier, achieving 100% accuracy when combining ARMA and statistical features. Impressive accuracy rates of 98.889% and 97.50% are observed with alternative feature combinations. Five other machine learning models (Decision Stump, Hoeffding Tree, REP Tree, SVM, and Random Forest) were also trained on the best feature combination set and compared to CATboost, illustrating its superiority. These findings substantiate the efficacy of feature fusion in augmenting fault detection capabilities within automobile clutch systems. The study's outcomes highlight the potential for improving vehicle maintenance practices, reducing downtime, and enhancing overall automotive safety through advanced fault detection techniques. Future research could explore real-time implementation of these methods in vehicle diagnostics systems.

show abstract

A Study on the Anomaly Detection of Engine Clutch Engagement/Disengagement Using Machine Learning for Transmission Mounted Electric Drive Type Hybrid Electric Vehicles

Cited by 6 publications

References 67 publications

Deep learning based fault detection of automobile dry clutch system using spectrogram plots

Deep learning based fault detection of automobile dry clutch system using spectrogram plots

A New Perspective of Post-Weld Baking Effect on Al-Steel Resistance Spot Weld Properties through Machine Learning and Finite Element Modeling

Enhanced fault detection in automobile clutch system using CATboost with feature fusion method

Contact Info

Product

Resources

About