机械制造与自动化
機械製造與自動化
궤계제조여자동화
Machine Building & Automation
2015年
5期
155-158
,共4页
电力电子电路%故障预测%特征性能参数%粒子群非齐次灰色模型
電力電子電路%故障預測%特徵性能參數%粒子群非齊次灰色模型
전력전자전로%고장예측%특정성능삼수%입자군비제차회색모형
power electronic circuits%fault prediction%characteristic parameter%particle swarm optimization non-homogenous grey model
针对现有电力电子电路故障预测技术的不足,提出了将电路特征性能参数和粒子群非齐次灰色模型PSO-NGM( particle swarm optimization non-homogenous grey model)模型结合,对电力电子电路进行故障预测。以 Buck-Boost电路为例,选择电路输出电压作为监测信号,提取输出电压平均值和纹波值作为电路特征性能参数,并利用 PSO-NGM预测模型实现故障预测。实验结果表明,利用 PSO-NGM 对电路输出平均电压和输出纹波电压的预测相对误差很小,能够跟踪故障特征性能参数的变化趋势,有效实现电力电子电路故障预测。
針對現有電力電子電路故障預測技術的不足,提齣瞭將電路特徵性能參數和粒子群非齊次灰色模型PSO-NGM( particle swarm optimization non-homogenous grey model)模型結閤,對電力電子電路進行故障預測。以 Buck-Boost電路為例,選擇電路輸齣電壓作為鑑測信號,提取輸齣電壓平均值和紋波值作為電路特徵性能參數,併利用 PSO-NGM預測模型實現故障預測。實驗結果錶明,利用 PSO-NGM 對電路輸齣平均電壓和輸齣紋波電壓的預測相對誤差很小,能夠跟蹤故障特徵性能參數的變化趨勢,有效實現電力電子電路故障預測。
침대현유전력전자전로고장예측기술적불족,제출료장전로특정성능삼수화입자군비제차회색모형PSO-NGM( particle swarm optimization non-homogenous grey model)모형결합,대전력전자전로진행고장예측。이 Buck-Boost전로위례,선택전로수출전압작위감측신호,제취수출전압평균치화문파치작위전로특정성능삼수,병이용 PSO-NGM예측모형실현고장예측。실험결과표명,이용 PSO-NGM 대전로수출평균전압화수출문파전압적예측상대오차흔소,능구근종고장특정성능삼수적변화추세,유효실현전력전자전로고장예측。
Aiming at the issue existing in the fault prediction technique of power electronic circuits, this paper proposes that the char-acteristic parameter data is used with the particle swarm optimization non-homogenous grey model( PSO-NGM) to predict the power electronic circuits failure. The Buck-Boost converter circuit is taken as an example to predict its failure,The output voltage is selected as monitoring signal and the average voltage and ripple voltage are extracted as characteristic parameters, then the PSO-NGM algo-rithm is used to predict Buck-Boost converter circuit. The experimental results show that using the PSO-NGM algorithm to predict the average voltage and ripple voltage, its error is smal er. The new method can be used to trace the characteristic parameter trend and predic the failure of power electronic circuits effectively.