Balancing the Imbalance: Advanced Anomaly Detection for Predictive Maintenance

Balancing the Imbalance: Advanced Anomaly Detection for Predictive Maintenance

Ch.Srivatsa Alivelu Mangatayi1    Vanam Pavan2

Sri Ratna3      G.Bharath4                S.Narasimha5

1  Assistant Professor, ACE Engineering College Hyderabad, India

2Student, ACE Engineering College Hyderabad, India 3Student, ACE Engineering College Hyderabad, India   4Student, ACE Engineering College Hyderabad, India

5Student, ACE Engineering College Hyderabad, India

Email : 1srivatsajava@gmail.com      2pavanvanam890@gmail.com

3srirathnatirunagari@gmail.com       4bharathgurram443@gmail.com

5 sangishettinarasimha@gmail.com

ABSTRACT:

Predictive maintenance is a crucial application in industrial systems, ensuring timely interventions to prevent failures and reduce downtime. However, the highly imbalanced nature of failure datasets poses a significant challenge to traditional machine learning models. This paper proposes an advanced anomaly detection framework utilizing synthetic data generation, oversampling techniques (SMOTE, ADASYN), and cost-sensitive learning to enhance failure detection accuracy. The system integrates Random Forest and XGBoost classifiers, optimized through hyperparameter tuning, to improve predictive maintenance efficiency. The proposed method demonstrates improved recall and precision, reducing false negatives while maintaining robustness in detecting rare failure events.