Logo image
Machine Learning-Based Multi-Sensor Feature Fusion Framework for Predictive Maintenance of Industrial Mechanical Gearboxes
Conference proceeding - Paper   Peer reviewed   ACCEPTED MANUSCRIPT

Machine Learning-Based Multi-Sensor Feature Fusion Framework for Predictive Maintenance of Industrial Mechanical Gearboxes

Echezona Clifford Okeke, Emmanuel Okang Edim, Celestine Iwendi and Vandana Sharma
CI2A 2027 (Kota Yogyakarta, Indonesia, 19/03/2027–21/03/2027)
09/2026

Abstract

Predictive Maintenance Gearbox Fault Diagnosis Feature Fusion, Random Forest Support Vector Machine XGBoost Condition Monitoring Machine Learning
In the realm of manufacturing, industrial gearboxes play a vital function in systems and machinery, and any unforeseen breakdown or malfunction can result in costly downtime and diminished productivity. This paper proposes a Multi-Sensor Feature Fusion Framework for Predictive Maintenance of Industrial Mechanical Gearboxes via Vibration Signal Analysis based on machine learning. An overlapping sliding-window approach was used to segment the vibration data obtained from four accelerometer sensor signals, both in the healthy and broken tooth operating conditions. From each sensor, statistical and frequency domain features were extracted and feature-level fusion was performed to provide a single feature representation. Three supervised machine learning algorithms namely, Random Forest (RF), Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) were trained and evaluated under the same experimental conditions. The following accuracy, precision, recall, F1-score, receiver operating characteristic (ROC) analysis, confusion matrix, and training time are used to evaluate the performance of models. The results of the experiments have shown that the proposed framework can well differentiate the healthy condition and faulty conditions of the gearbox.
pdf
Machine Learning-Based Multi-Sensor Feature Fusion Framework for Predictive Maintenance of Industrial Mechanical Gearboxes1.43 MB
Accepted Restricted Access CC BY V4.0  — This license enables reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator.
url
CI2A 2027View
Event page

Metrics

1 Record Views

Details

Logo image

Usage Policy