Multivariate Kernel Density Estimation Performance in Detecting Abnormalities in Three-Phase Induction Motors With a Focus on Optimizing Kernel and Bandwidth

Abstract

In this study, we focus on the application of anomaly detection for three-phase induction motors using current data, a crucial aspect of predictive maintenance technologies transforming industrial operations. Induction motors play a pivotal role in converting electrical energy to mechanical energy across various industries. Detecting anomalies in these motors is essential for ensuring operational efficiency and minimizing downtime. Our approach involves analyzing the spectral characteristics of current data to identify abnormal motor states. Specifically, we leverage the distortion observed in the current spectrum as a key feature indicative of motor anomalies. To achieve this, we employ a multivariate kernel density estimation (MKDE) algorithm, which operates under unsupervised learning principles for anomaly detection. To determine the optimal threshold for anomaly detection, we utilize the Youden index, enhancing the reliability of our detection method. Furthermore, we fine-tune the model’s hyperparameters, including the kernel bandwidth, through experimentation with various selection rules. The final bandwidth is chosen based on an analysis of the feature distribution within the data. Implementing our proposed method offers significant benefits to industries by potentially reducing maintenance costs through timely anomaly detection in induction motors. Proactively replacing motor components when anomalies are detected can enhance overall motor performance and extend their operational lifespan. This approach underscores the critical role of advanced anomaly detection techniques in improving industrial efficiency and reliability.

Keywords

• Anomaly detection
• unsupervised learning
• frequency distortion
• damage detection
• multivariate kernel density estimation
• three-phase induction motor