Artificial Intelligence -Based Condition Monitoring Techniques for Powertrains in Electric Vehicles
Bibliographic record
Abstract
With the rapid development and wide application of electric vehicles (EVs), condition monitoring and fault diagnosis of EV motors have become key tasks to ensure the reliability and safety of EVs. The aim of this study is to propose an integrated approach to achieve accurate monitoring of electric vehicle motor status and timely diagnosis of faults. This research utilizes a variety of data-driven methods including few-shot learning and graph neural networks to improve the reliability and efficiency of these systems. The first segment explores the use of AI in fault detection and diagnosis (FDD), particularly in Permanent Magnet Synchronous Motors (PMSMs). By employing a hybrid few-shot learning network that amalgamates model-driven and data-driven methods, the research addresses the limitations in acquiring sufficient quality data for fault diagnosis. It particularly focuses on detecting Voltage Source Inverter (VSI) open-circuit faults, enhancing diagnostic certainty through attention-based vision transformer models. The second part delves into vibration analysis, a vital aspect of motor condition monitoring. It introduces an attention-based spatial-spectral graph convolutional network (ASSGCN) aimed at reducing the number of required sensors while maintaining accurate vibration signal reconstruction. The model investigates the spectral features and spatial configurations of the vibration signals, predicting them at different sensor sampling points effectively. Lastly, the research presents a spatial-spectral-based inductive graph neural network specifically designed to tackle the challenges of high evaluation accuracy with fewer vibration sensors. This algorithm aggregates and extracts features of sensor graph signals and employs convolutional networks for reconstructing vibration signals at virtual sensor points. Collectively, these approaches contribute to the reduction of operational costs, enhancement of system reliability, and improvement of fault diagnostic accuracy. Experimental verifications have been carried out on a 21 kW IPMSM testing rig equipped with Brüel & Kjær's vibration sensing technology, confirming the efficacy of the proposed methods. These techniques pave the way for more efficient, reliable, and cost-effective condition monitoring and fault detection in electric motor systems across various applications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".