A novel hybrid machine learning algorithm for detection in smart cities. (April 2022)

• Record Type: Journal Article
• Authors: Jiang, Jiahui; Han, Shuangxu
• Is Part Of: Computers & electrical engineering. Volume 99(2022)
• Publication Date: 2022-04
• Subjects: Smart grid and motors -- Fault detection -- Broken rotor bar -- Sigma point method; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.107787
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Develop a novel hybrid method for the state estimation. Learning-based broken rotor bar (BRB) detection of the induction motors (IMs) in smart grids. Machine learning-based malfunctioning detection in the system. Abstract: This article tries to develop a novel hybrid method for the state estimation as well as the broken rotor bar (BRB) detection of the induction motors (IMs) in smart grids. This is so significant to survive the IM from harsh damages and avoid malfunctioning in the system. The suggested method is constructed based on the Kalman filter as a successful machine learning and sigma point which have shown superior performance over the other well-known methods in the area. In order to enhance its efficiency, sigma points would make a transformation which can make the model more stable and precise. The experimental results on a test IM reveal the high accuracy and stable performance of the proposed model. Three varied scenarios are simulated to show the quality and appropriate performance of the proposed intelligent method at different loading situations. The simulation results validate the high quality and promising performance of the proposed model. Graphical abstract: Image, graphical abstract