Automatic Fault Detection using Cause and Effect Rules for In-vehicle Networks

Kordes, Alexander; Wurm, Sebastian; Hozhabrpour, Hawzhin; Wismüller, Roland

doi:10.5220/0006792605370544

Cited by 2 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Studies on fault or anomaly detection for vehicle powertrains have been carried out by various approaches. They can be classified by rule-based methods [6][7][8][9][10][11][12], mathematical 2 of 21 model-based methods [13][14][15][16][17][18][19][20][21][22][23][24][25][26], and data-driven methods that use signal processing or machine learning [27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42][43].…”

Section: Introductionmentioning

confidence: 99%

“…Meyer proposed an inter-turn short circuit fault detection and fault degree identification method using moving horizon observer for the Toyota Prius traction motor [19]. In the case of using data-driven techniques, methods using frequency analysis [27,31,34,40], methods using frequency analysis and neural networks together [41], and methods using machine learning such as one-class SVM, Hidden Markov model, and Gaussian mixture model [28,33,36,42], etc., were proposed. Akin proposed a frequency analysis-based fault detection method used at the motor's zero speed [27].…”

Section: Introductionmentioning

confidence: 99%

“…Nair proposed a machine learning based fault detection method for battery sensors of HEV that used one-class support vector machine (SVM) and k-means clustering together [33]. Kordes detected faults of sensor data in a controller area network (CAN) bus using machine learning with the features by extracting features using cause and effect rules [36]. Jiang conducted fault diagnosis for an EV battery using variational mode decomposition and clustering [42].…”

Section: Introductionmentioning

confidence: 99%

“…In [6,22,26], the authors conducted studies to detect anomalies by examining vehicle data trends. In [10,36], the authors detected relatively simple anomalies through DTC signals or a tendency to increase/decrease between data. However, there is a limit to these applications to the verification of complicated control functions.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

Jeong

Cho

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

Transmission mounted electric drive type hybrid electric vehicles (HEVs) engage/disengage an engine clutch when EV↔HEV mode transitions occur. If this engine clutch is not adequately engaged or disengaged, driving power is not transmitted correctly. Therefore, it is required to verify whether engine clutch engagement/disengagement operates normally in the vehicle development process. This paper studied machine learning-based methods for detecting anomalies in the engine clutch engagement/disengagement process. We trained the various models based on multi-layer perceptron (MLP), long short-term memory (LSTM), convolutional neural network (CNN), and one-class support vector machine (one-class SVM) with the actual vehicle test data and compared their results. The test results showed the one-class SVM-based models have the highest anomaly detection performance. Additionally, we found that configuring the training architecture to determine normal/anomaly by data instance and conducting one-class classification is proper for detecting anomalies in the target data.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Jeong

Cho

et al. 2021

Applied Sciences

View full text Add to dashboard Cite

show abstract

Predictive Maintenance in the Automotive Sector: A Literature Review

Arena

Collotta

Luca

et al. 2021

MCA

View full text Add to dashboard Cite

With the rapid advancement of sensor and network technology, there has been a notable increase in the availability of condition-monitoring data such as vibration, temperature, pressure, voltage, and other electrical and mechanical parameters. With the introduction of big data, it is possible to prevent potential failures and estimate the remaining useful life of the equipment by developing advanced mathematical models and artificial intelligence (AI) techniques. These approaches allow taking maintenance actions quickly and appropriately. In this scenario, this paper presents a systematic literature review of statistical inference approaches, stochastic methods, and AI techniques for predictive maintenance in the automotive sector. It provides a summary on these approaches, their main results, challenges, and opportunities, and it supports new research works for vehicle predictive maintenance.

show abstract

Automatic Fault Detection using Cause and Effect Rules for In-vehicle Networks

Cited by 2 publications

References 6 publications

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

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

Predictive Maintenance in the Automotive Sector: A Literature Review

Contact Info

Product

Resources

About