Agentic AI For High-Accuracy Electric Motor Predictive Maintenance In Noisy Environments

Read full text Summarise with VIRAT
Authors: Animireddy Anusha, Ganta Akhila, Artham  Divya, Budidhi Abhilash, Bakkathatla Ramya, Gunda Manikanta
Cited by: 0
References: 13

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Industrial electric motors are the backbone of modern manufacturing, necessitating highreliability maintenance strategies to prevent costly downtime.While acoustic monitoring offers a non-intrusive alternative to traditional vibration or temperature analysis, conventional handcrafted features such as Mel Frequency Cepstral Coefficients (MFCCs) and Spectral Centroids often struggle to capture the complex temporal-spectral dependencies of real-world industrial settings.These "shallow" features are frequently compromised by environmental noise and fluctuations in machine load, leading to poor generalization across diverse fault types like gearbox anomalies or fan imbalances.To overcome these limitations, this study proposes a novel diagnostic framework leveraging Waveformbased Language Model (WavLM) transformer embeddings.Unlike classical methods, WavLM extracts rich, context-aware representations from raw audio, providing superior noise tolerance and structural depth.These high-dimensional embeddings were evaluated across multiple classifiers, including Categorical Boosting (CatBoost) and Decision Trees (DTC).Experimental results demonstrate that the proposed Histogram-Based Gradient Boosting (HistGB) classifier achieves a state-of-the-art accuracy of 95%, significantly outperforming traditional machine learning pipelines.To facilitate industrial adoption, a graphical user interface (GUI) was developed to streamline data processing and real-time fault prediction.This research offers a scalable, high-precision solution for predictive maintenance, proving that self-supervised audio representations can dramatically enhance diagnostic robustness in noisy industrial ecosystems.

Fields of Study & Subjects

Machine Fault Diagnosis Techniques Music and Audio Processing Fault Detection and Control Systems

Publication details

Journal / source
International journal of engineering science and advanced technology.
Volume
26
Issue
3
Pages
414–422
Publication date
1 March 2026
Language
EN