CAJ | 학술논문

针对电力电子电路故障诊断时故障模式间存在交叉数据的模式识别问题,在量子计算和人工神经网络结合的基础上,提出了一种基于量子神经网络的故障诊断方法,并以双桥12相脉波整流电路为例进行故障诊断.实验结果表明:量子神经网络有一种固有的模糊性,它能将不确定性数据合理地分配到各故障模式中,从而使网络具有高性能、更好的鲁棒性和省时的特点,且能正确地识别大部分的样本故障模式,成功地完成电力电子电路的故障诊断.
침대전력전자전로고장진단시고장모식간존재교차수거적모식식별문제,재양자계산화인공신경망락결합적기출상,제출료일충기우양자신경망락적고장진단방법,병이쌍교12상맥파정류전로위례진행고장진단.실험결과표명:양자신경망락유일충고유적모호성,타능장불학정성수거합리지분배도각고장모식중,종이사망락구유고성능、경호적로봉성화성시적특점,차능정학지식별대부분적양본고장모식,성공지완성전력전자전로적고장진단.
In this paper, a method for fault diagnosis based on quantum neural network is presented on combination of quantum computation and artificial neural network, which aims at the pattern recognition problems of cross-data in fault modes, during the power electronic circuits fault diagnosis. By taking the Twin-bridge 12 phase pulse wave rectifier circuit as an example, the results show that quantum neural network has the characteristic of inherent ambiguity, which can assign the uncertainty data to each fault mode reasonably, making the network with the features of high capacity, better robust and timesaving. Meanwhile it can identify the majority of the sample fault modes correctly, and has accomplished the fault diagnosis of power electronic circuits successfully.