Feature Engineering and Artificial Intelligence-Supported Approaches Used for Electric Powertrain Fault Diagnosis: A Review

Zhang, Xiaotian; Hu, Yihua; Deng, Jiamei; Xu, Hui; Wen, Huiqing

doi:10.1109/access.2022.3157820

Cited by 23 publications

(7 citation statements)

References 184 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Modified sample entropy was used for real-time multifault diagnosis of early battery failure [130]. In [131], feature engineering techniques and artificial intelligence (AI) algorithms (including machine learning, neural networks, and deep learning) in condition monitoring and problem detection approaches were extensively summarized. Fault diagnosis algorithms are reviewed in Table 8.…”

Section: Mode-l and Non-model-based Fault Diagnosis And State Of Safe...mentioning

confidence: 99%

Overview of Model- and Non-Model-Based Online Battery Management Systems for Electric Vehicle Applications: A Comprehensive Review of Experimental and Simulation Studies

et al. 2022

View full text Add to dashboard Cite

The online battery management system (BMS) is very critical for the safe and reliable operation of electric vehicles (EVs) and renewable energy storage applications. The primary responsibility of BMS is data assembly, state monitoring, state management, state safety, charging control, thermal management, and information management. The algorithm and control development for smooth and cost-effective functioning of online BMS is challenging research. The complexity, stability, cost, robustness, computational cost, and accuracy of BMS for Li-ion batteries (LiBs) can be enhanced through the development of algorithms. The model-based and non-model-based data-driven methods are the most suitable for developing algorithms and control for online BMS than other methods present in the literatures. The performance analysis of algorithms under different current, thermal, and load conditions have been investigated. The objective of this review is to advance the experimental design and control for online BMS. The comprehensive overview of present techniques, core issues, technical challenges, emerging trends, and future research opportunities for next-generation BMS is covered in this paper with experimental and simulation analysis.

show abstract

Section: Mode-l and Non-model-based Fault Diagnosis And State Of Safe...mentioning

confidence: 99%

Overview of Model- and Non-Model-Based Online Battery Management Systems for Electric Vehicle Applications: A Comprehensive Review of Experimental and Simulation Studies

et al. 2022

View full text Add to dashboard Cite

show abstract

“…However, BSS necessitates a baseline signal, posing a limitation for complex VS situations [ 17 ]. To proficiently analyze non-stationary signals, innovative signal-processing methods, such as the short time Fourier transform (STFT), have been utilized [ 18 , 19 ].…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis of a Multistage Centrifugal Pump Using Explanatory Ratio Linear Discriminant Analysis

Ullah,

Ahmad,

Kim

2024

Sensors

View full text Add to dashboard Cite

This study introduces an innovative approach for fault diagnosis of a multistage centrifugal pump (MCP) using explanatory ratio (ER) linear discriminant analysis (LDA). Initially, the method addresses the challenge of background noise and interference in vibration signals by identifying a fault-sensitive frequency band (FSFB). From the FSFB, raw hybrid statistical features are extracted in time, frequency, and time–frequency domains, forming a comprehensive feature pool. Recognizing that not all features adequately represent MCP conditions and can reduce classification accuracy, we propose a novel ER-LDA method. ER-LDA evaluates feature importance by calculating the explanatory ratio between interclass distance and intraclass scatteredness, facilitating the selection of discriminative features through LDA. This fusion of ER-based feature assessment and LDA yields the novel ER-LDA technique. The resulting selective feature set is then passed into a k-nearest neighbor (K-NN) algorithm for condition classification, distinguishing between normal, mechanical seal hole, mechanical seal scratch, and impeller defect states of the MCP. The proposed technique surpasses current cutting-edge techniques in fault classification.

show abstract

“…These relays have many benefits compared over electromagnetic ones in terms of accuracy, response speed, and reliability [27]. The most effective methods used to protect motors are techniques based on artificial intelligence due to their high reliability and low cost [28]. According to the type of signal used in the analyses, phase loss detection algorithms can be broadly classified into three categories: voltage, current, and combinations of them.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Protection Scheme Against Single-Phasing Fault for Three-Phase Induction Motor

Dawood,

Ismeil,

Hussein

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The loss of one phase of a three-phase Induction Motor (IM) is one of the main causes of motor failure due to overheating. Several protection devices protect IM against this fault, but the majority of conventional devices lack a thorough classification of this type of fault. So, this paper introduces a highefficiency protection scheme to detect and classify in detail 15 types of faults that can occur due to a phase loss of a three-phase IM. These faults are classified according to the defective phase, fault location either from the power source or beyond the relay point, and motor action modes (standstill mode, transient mode, and steady state mode). One of the advantages of the presented protection method is that it is suitable for many motors because the inputs to the proposed scheme are the per-unit values of both RMS line-line voltages and line currents. The proposed scheme has been validated and tested using MATLAB Simulink under normal conditions and different faults for phase loss, during and after disconnecting the motor, and after pushing the restart button. The simulation results show that the proposed scheme behaves with high efficiency and it is able to detect and classify correctly the phase loss faults for three-phase IM within 1.5 cycles (30 ms) of the fault inception. Thus, the proposed scheme can be used as a simple and reliable scheme in the protection system of a 3-phase IM to detect and classify the different types of phase loss faults.

show abstract

Feature Engineering and Artificial Intelligence-Supported Approaches Used for Electric Powertrain Fault Diagnosis: A Review

Cited by 23 publications

References 184 publications

Overview of Model- and Non-Model-Based Online Battery Management Systems for Electric Vehicle Applications: A Comprehensive Review of Experimental and Simulation Studies

Overview of Model- and Non-Model-Based Online Battery Management Systems for Electric Vehicle Applications: A Comprehensive Review of Experimental and Simulation Studies

Fault Diagnosis of a Multistage Centrifugal Pump Using Explanatory Ratio Linear Discriminant Analysis

An Efficient Protection Scheme Against Single-Phasing Fault for Three-Phase Induction Motor

Contact Info

Product

Resources

About