Fault Detection and Fault Tolerant Control for Anti-lock Braking Systems )ABS) Speed Sensors by Using Neural Networks

Abdulkareem, Ayad; Humod, Abdulrahim Thiab; Ahmed, Oday A.

doi:10.30684/etj.2022.135106.1259

Cited by 3 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first one is a higher fault detection accuracy since, beside kNN fault detection, it performs fault detection confirmation through residual signal generation, and the second one is fault effect accommodation or fault tolerance. While, compared to [8], based on the kNN decision signal, it avoids false detection alarms. It utilizes the kNN decision signal to stop signal construction that employs faulty signals.…”

Section: Discussionmentioning

confidence: 99%

“…Researchers have proposed several data-driven approaches based on machine learning and deep learning to solve fault detection and isolation problems. The development of the ABS speed sensor fault detection method has been presented by [8], where a two-separated model based on neural networks serves analytical redundancy purposes by being utilized to construct an alternative signal for each of the ABS speed sensors. These constructed signals are then utilized in FD-FTC operation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid Fault Detection and Fault Tolerant Control Based on kNN and NN Approaches for ABS Speed Sensors

2023

IJCCCE

View full text Add to dashboard Cite

To perform fault tolerance for Anti-lock Braking System (ABS), This paper proposes a hybrid Fault Detection and Fault Tolerant Control (FD-FTC) for ABS speed sensors. It utilizes a Fault Detection (FD) unit and a Data Construction (DC) unit. The first one, the FD unit, is based on a kNN classifier model with 99.9% fault detection accuracy to perform three tasks: early fault detection, fault location diagnosis, and excluding faulty signals from being utilized in further processes. On the other hand, the second one, the DC Unit, is based on two separate neural network models. These models have an MSE of 2.01139e-1 and a R2 of 999880 for the first model and an MSE of 1.12486e-0 and 0.999586 for the second model. They are employed to provide an estimated alternative signal for the ABS speed sensors. These estimated signals are employed to perform two tasks: confirming fault detection declared by the FD model and compensating for the excluded faulty signal to fulfill fault accommodation. Both methods are trained and tested with MATLAB and Simulink. Results demonstrate that the proposed hybrid method has the ability to accurately detect and tolerate sensor faults and fulfill its design purpose, especially during emergency braking. Index Terms— Anti-lock Braking System, Fault Tolerant Control, k-Nearest Neighbour, Neural Networks, Speed Sensor Fault.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Hybrid Fault Detection and Fault Tolerant Control Based on kNN and NN Approaches for ABS Speed Sensors

2023

IJCCCE

View full text Add to dashboard Cite

show abstract

“…Furthermore, vibration analysis is often used to locate defects in rotating machinery and mini-UAVs. Many vibration signal analysis techniques have previously been applied to diagnose rotating machine defects [2,3,4]. Previous studies frequently employed offline condition monitoring and imbalance classification techniques, resulting in extended-time decisions.…”

Section: Introductionmentioning

confidence: 99%

Investigation of Frequency-Domain-Based Vibration Signal Analysis for UAV Unbalance Fault Classification

Al-Haddad¹,

Jaber²,

Neranon³

et al. 2023

ETJ

View full text Add to dashboard Cite

Research on Hardware-in-the-Loop Automated Testing for integrated by-wire hydraulic brake system

Chen,

Li,

Wang

et al. 2023

2023 5th International Academic Exchange Conference on Science and Technology Innovation (IAECST)

View full text Add to dashboard Cite

Fault Detection and Fault Tolerant Control for Anti-lock Braking Systems )ABS) Speed Sensors by Using Neural Networks

Cited by 3 publications

References 21 publications

A Hybrid Fault Detection and Fault Tolerant Control Based on kNN and NN Approaches for ABS Speed Sensors

A Hybrid Fault Detection and Fault Tolerant Control Based on kNN and NN Approaches for ABS Speed Sensors

Investigation of Frequency-Domain-Based Vibration Signal Analysis for UAV Unbalance Fault Classification

Research on Hardware-in-the-Loop Automated Testing for integrated by-wire hydraulic brake system

Contact Info

Product

Resources

About