Online Anomaly Detection in DC/DC Converters by Statistical Feature Estimation Using GPR and GA

DC/DC converters play an important role in electrical systems. The anomalous state of a dc/dc converter has a major impact on the operation of the back-end components and the entire electrical system. To effectively recognize an anomalous state, particularly for dc/dc converters with unknown circuit structures, an online anomaly detection method that involves statistical feature estimation using Gaussian process regression (GPR) and a genetic algorithm (GA) is proposed. In the proposed method, the normal output range is built upon the dc/dc normal output signal using GPR, and seven statistical features are considered as the detection indexes. In the detection process, the output signal of the dc/dc converter is acquired, and the corresponding extreme values of statistical features are calculated by using GA, which can effectively reduce the operation time and the calculation consumption. The working state of the dc/dc converter is distinguished according to these features. Simulation and hardware experimental results validate the practicability and effectiveness of the proposed method.