Anomaly Detection of Servomotors Subject to Highly Accelerated Limit Testing

Abstract

Companies utilize highly accelerated limit testing (HALT) to ensure efficient product development by accelerating loading conditions in the qualification process. The aim of qualitative accelerated testing such as HALT is to properly identify early behavioral anomalies. To this end, this study utilizes machine learning techniques for detecting anomalies in servomotors in electronic products subjected to HALT. A case study was conducted using a programmable robot kit with 12 servomotors. HALT comprises five types of stress: thermal conditioning (cold and heat), rapid thermal change, vibration, and combined stresses. The anomalous behavior of a servomotor can be identified using a k-nearest neighbor algorithm and verified by inspection using the loading conditions and electrical responses. In addition, anomalous behaviors among servomotors and a control board are assessed using a Gaussian graph model approach. Changes in the Gaussian graph are assessed as anomaly scores using Kullback–Leibler divergence. The anomaly score increased earlier than the operating limit defined by inspection, i.e., the deviation from the initial position of the shaft. The machine learning algorithm successfully identified the failure precursor of the unit. The proposed approach of HALT with the machine learning algorithm supports prognostic health management of servomotors.