Computers & Electrical Engineering ( IF 4.0 ) Pub Date : 2021-06-12 , DOI: 10.1016/j.compeleceng.2021.107234 Arturo Mejia-Barron , Guillermo Tapia-Tinoco , Jose R. Razo-Hernandez , Martin Valtierra-Rodriguez , David Granados-Lieberman
Induction motors (IMs) are one of the most commonly used rotating machines in industry. In order to avoid downtimes and economical losses, development of condition monitoring systems is of paramount importance. Inter-turn short circuit (ITSC) faults are one of the most commonly occurring faults in IMs. In this regard, motor current signature analysis (MCSA) is a low cost and noninvasive technique, requiring only the current signal to perform the condition monitoring. Also, the development of tools that emulate IM faults, allow the design, calibration and validation of MCSA based techniques. In this work, a multilayer neural network-based model to reproduce the current signatures associated with ITSC fault conditions is presented. The model considers both five severities of ITSC faults and four torque levels. This model is also implemented on a power hardware in the loop scheme to provide a novel tool to test condition monitoring systems of IMs.
中文翻译:
基于神经网络的感应电机匝间短路故障 MCSA 模型及其功率硬件在环仿真
感应电机 (IM) 是工业中最常用的旋转机器之一。为了避免停机和经济损失,状态监测系统的开发至关重要。匝间短路 (ITSC) 故障是 IM 中最常见的故障之一。在这方面,电机电流特征分析 (MCSA) 是一种低成本和非侵入性技术,只需要电流信号来执行状态监测。此外,模拟 IM 故障的工具的开发允许设计、校准和验证基于 MCSA 的技术。在这项工作中,提出了一种基于多层神经网络的模型来重现与 ITSC 故障条件相关的电流特征。该模型同时考虑了 ITSC 故障的五个严重性和四个扭矩级别。