摘要
针对现有模拟电路系统PHM技术故障预测部分准确度不高和时效性不强的问题,提出了基于MCGCPSO优化改进的HMM状态退化识别模型。将小波包故障特征提取法与LDA特征降维法结合,确保了对特征信息非线性部分的充分提取,同时又避免了维度过高的问题;利用MCGCPSO优化改进后的HMM模型,提升了状态退化识别模型的分类准确度。最后将MCGCPSO-HMM与改进的灰色模型组合为一个新的电路故障预测模型,克服了单个预测方法性能不稳定的缺陷。通过仿真实验验证了MCGCPSO-HMM与改进的灰色模型组合具有更高的预测准确度。
In view of the problem existing in analog circuit system PHM technology support part ofprediction such as low accuracy and the immediate effect,this paper proposes a HMM degradationrecognition model based on optimizing and improving MCGCPSO. Combined fault feature extractionmethod of wavelet packet with LDA feature dimension reduction method,this paper ensures thenonlinear part feature information is fully extracted and avoids the problem of high dimension;theoptimized HMM model using MCGCPSO improves the classification accuracy degradation recognitionmodel on the basis of the principle of classification interval maximum,anda simulation is carried out.Finally,as the new a circuit fault prediction model,the combination of MCGCPSO-HMM and theimproved grey model can overcome the defect of single forecasting method performance is not stable. Itis verified by simulation experiments that the combination of MCGCPSO-HMM and the improved greymodel has higher predictive accuracy.
出处
《火力与指挥控制》
CSCD
北大核心
2018年第2期91-97,101,共8页
Fire Control & Command Control
基金
军队科研重点基金(KJ2012184)
陕西省自然科学基础研究计划资助项目(2014JM8344)
