Stagewise Anomaly Detection for E-Transaxle Quality Monitoring Using Wavelet and STFT Features
Abstract
This paper presents two interpretable machine-learning frameworks for quality screening of e-transaxle assemblies in electric vehicles: a Stagewise Wavelet Isolation Forest (SWIF) framework and a short-time Fourier transform (STFT)-based diagnostic framework. High-dimensional vibration signals acquired from front and back accelerometers are analyzed across multiple operating stages to capture stage-dependent vibration behavior. In the SWIF framework, signals are decomposed using a five-level Daubechies-4 discrete wavelet transform, and blockwise mean-squared coefficients are extracted from the selected wavelet detail level to obtain compact multiscale features. In the STFT-based framework, dominant-frequency trends are extracted from time-frequency representations and summarized through regression coefficients with respect to instantaneous motor speed. Anomaly detection models are trained using accepted production units under the assumption that only a small fraction of accepted assemblies contain latent defects, and their performance is evaluated using road-tested units with validated quality outcomes. Experiments on production and road-tested e-transaxle units show that both approaches provide interpretable diagnostic information, while SWIF achieves the most favorable balance between defect detection and false-positive control. Compared with the STFT-based method and alternative anomaly detectors, SWIF combined with Isolation Forest yields lower anomaly rates within the Accept population while identifying high-risk units from the Reject population. The stagewise structure further localizes anomalous behavior to specific operating conditions, supporting root-cause analysis and targeted process improvement.
Related
- Hyperspectral Anomaly Detection via Group Sparse Low-Rank Tensor Factorization With Automatic Anomaly Grouping
- Real-time and adaptive anomaly detection algorithm for cyclostationary models
- Moment-Based Anomaly Detection in High-Dimensional Mixed Data
- Statistical Feature Augmentation for Anomaly Detection in Dynamic Graphs
- Spectral properties of the resistance Laplacian with applications to data clustering and anomaly detection
BibTeX
@misc{bisheh2026stagewise,
title = {{Stagewise Anomaly Detection for E-Transaxle Quality Monitoring Using Wavelet and STFT Features}},
author = {Mohammad N. Bisheh and Rajesh Gupta and Qian Wang and Mohammad Babakmehr and Colin Brady and Parinaz Farajiparvar and Saurabh Singh and Kamran Payanabar},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.22172},
eprint = {2609.22172},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.22172},
}
RIS
TY - UNPB
TI - Stagewise Anomaly Detection for E-Transaxle Quality Monitoring Using Wavelet and STFT Features
AU - Mohammad N. Bisheh
AU - Rajesh Gupta
AU - Qian Wang
AU - Mohammad Babakmehr
AU - Colin Brady
AU - Parinaz Farajiparvar
AU - Saurabh Singh
AU - Kamran Payanabar
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.22172
UR - https://arxiv.org/abs/2609.22172
AB - This paper presents two interpretable machine-learning frameworks for quality screening of e-transaxle assemblies in electric vehicles: a Stagewise Wavelet Isolation Forest (SWIF) framework and a short-time Fourier transform (STFT)-based diagnostic framework. High-dimensional vibration signals acquired from front and back accelerometers are analyzed across multiple operating stages to capture stage-dependent vibration behavior. In the SWIF framework, signals are decomposed using a five-level Daubechies-4 discrete wavelet transform, and blockwise mean-squared coefficients are extracted from the selected wavelet detail level to obtain compact multiscale features. In the STFT-based framework, dominant-frequency trends are extracted from time-frequency representations and summarized through regression coefficients with respect to instantaneous motor speed. Anomaly detection models are trained using accepted production units under the assumption that only a small fraction of accepted assemblies contain latent defects, and their performance is evaluated using road-tested units with validated quality outcomes. Experiments on production and road-tested e-transaxle units show that both approaches provide interpretable diagnostic information, while SWIF achieves the most favorable balance between defect detection and false-positive control. Compared with the STFT-based method and alternative anomaly detectors, SWIF combined with Isolation Forest yields lower anomaly rates within the Accept population while identifying high-risk units from the Reject population. The stagewise structure further localizes anomalous behavior to specific operating conditions, supporting root-cause analysis and targeted process improvement.
ER -