Integrating spatiotemperporal features into fault prediction using a multi-dimensional method

This study proposes a method to validate multidimensional fault prediction models. It integrates vibration and current data, analyzes spatiotemporal characteristics, and uses support vector machines and random forest algorithms to analyze fault characteristics. The short-time Fourier transform is us...

Full description

Saved in:
Bibliographic Details
Main Authors: Chun-Yi Lin, Yu-Chuan Tseng, Wu-Sung Yao
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123025019279
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849707515439218688
author Chun-Yi Lin
Yu-Chuan Tseng
Wu-Sung Yao
author_facet Chun-Yi Lin
Yu-Chuan Tseng
Wu-Sung Yao
author_sort Chun-Yi Lin
collection DOAJ
description This study proposes a method to validate multidimensional fault prediction models. It integrates vibration and current data, analyzes spatiotemporal characteristics, and uses support vector machines and random forest algorithms to analyze fault characteristics. The short-time Fourier transform is used to convert spatiotemporal data into the frequency domain for classification, and high-order features are extracted through convolutional networks. The model considers three spatial dimensions and three vibration measurement sources to form a nine-dimensional data structure, and a fault prediction algorithm based on these dimensions is established. The study evaluates the model using metrics such as accuracy, precision, recall, F1 score, and receiver operating characteristic area under curve (ROC-AUC), and visualizes performance through confusion matrices, ROC curves, and precision-recall curves. In order to further verify the significance of the model, the experiment is conducted on mercury induction motors of industrial water pumps, and an McNemar’s Chi-Square Test was used to statistically test the fault discrimination ability of the model under various conditions. Results show that this model achieves the stability and accuracy of the fault prediction under multi-dimensional data, effectively identifies abnormal conditions, and the technical support for smart monitoring and maintenance can be provided.
format Article
id doaj-art-73a2ab1af8bd4d4ca6faab3049e06989
institution DOAJ
issn 2590-1230
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-73a2ab1af8bd4d4ca6faab3049e069892025-08-20T03:15:54ZengElsevierResults in Engineering2590-12302025-09-012710585610.1016/j.rineng.2025.105856Integrating spatiotemperporal features into fault prediction using a multi-dimensional methodChun-Yi Lin0Yu-Chuan Tseng1Wu-Sung Yao2National Kaohsiung University of science and technology, Department of Mechatronics Engineering; No. 1, Daxue Rd., Yanchao Dist., Kaohsiung City 824005, TaiwanNational Kaohsiung University of science and technology, Department of Mechatronics Engineering; No. 1, Daxue Rd., Yanchao Dist., Kaohsiung City 824005, TaiwanCorresponding author.; National Kaohsiung University of science and technology, Department of Mechatronics Engineering; No. 1, Daxue Rd., Yanchao Dist., Kaohsiung City 824005, TaiwanThis study proposes a method to validate multidimensional fault prediction models. It integrates vibration and current data, analyzes spatiotemporal characteristics, and uses support vector machines and random forest algorithms to analyze fault characteristics. The short-time Fourier transform is used to convert spatiotemporal data into the frequency domain for classification, and high-order features are extracted through convolutional networks. The model considers three spatial dimensions and three vibration measurement sources to form a nine-dimensional data structure, and a fault prediction algorithm based on these dimensions is established. The study evaluates the model using metrics such as accuracy, precision, recall, F1 score, and receiver operating characteristic area under curve (ROC-AUC), and visualizes performance through confusion matrices, ROC curves, and precision-recall curves. In order to further verify the significance of the model, the experiment is conducted on mercury induction motors of industrial water pumps, and an McNemar’s Chi-Square Test was used to statistically test the fault discrimination ability of the model under various conditions. Results show that this model achieves the stability and accuracy of the fault prediction under multi-dimensional data, effectively identifies abnormal conditions, and the technical support for smart monitoring and maintenance can be provided.http://www.sciencedirect.com/science/article/pii/S2590123025019279Fault predictionSupport vector machineRandom forestShort-time Fourier transformConvolutional network
spellingShingle Chun-Yi Lin
Yu-Chuan Tseng
Wu-Sung Yao
Integrating spatiotemperporal features into fault prediction using a multi-dimensional method
Results in Engineering
Fault prediction
Support vector machine
Random forest
Short-time Fourier transform
Convolutional network
title Integrating spatiotemperporal features into fault prediction using a multi-dimensional method
title_full Integrating spatiotemperporal features into fault prediction using a multi-dimensional method
title_fullStr Integrating spatiotemperporal features into fault prediction using a multi-dimensional method
title_full_unstemmed Integrating spatiotemperporal features into fault prediction using a multi-dimensional method
title_short Integrating spatiotemperporal features into fault prediction using a multi-dimensional method
title_sort integrating spatiotemperporal features into fault prediction using a multi dimensional method
topic Fault prediction
Support vector machine
Random forest
Short-time Fourier transform
Convolutional network
url http://www.sciencedirect.com/science/article/pii/S2590123025019279
work_keys_str_mv AT chunyilin integratingspatiotemperporalfeaturesintofaultpredictionusingamultidimensionalmethod
AT yuchuantseng integratingspatiotemperporalfeaturesintofaultpredictionusingamultidimensionalmethod
AT wusungyao integratingspatiotemperporalfeaturesintofaultpredictionusingamultidimensionalmethod