摘要
针对航空发动机气路系统健康状态评估建模中有效故障数据贫乏的问题,文中基于置信规则库(BRB)理论,融合监测信息与专家知识建立了航空发动机气路系统健康状态评估模型。首先,为了减小BRB模型的复杂度,考虑相关性对特征量进行选择;将特征量作为BRB模型输入,建立BRB健康状态评估模型;最后,利用带有投影操作的约束协方差矩阵P-CMA-ES算法对模型进行参数优化,提高了模型的评估精度。通过对某型航空发动机气路系统进行健康状态评估仿真分析,验证了所提模型的有效性和准确性。
Aiming at the problem that the valid fault data of the aero-engine gas path system is few,a health state estimation model based on Belief Rule Base(BRB)for aero-engine gas path system by fusing monitoring information and expert knowledge is proposed in this paper.First of all,the correlation selection of the features is carried out in order to reduce the complexity of the BRB model.Taking the features as the inputs,the health state estimation model based on BRB is established.Finally,in order to improve the estimation accuracy of the model,the parameters of the model are optimized using the Projection Covariance Matrix Adaption Evolution Strategy(P-CMA-ES).The validity and accuracy of the proposed model are verified by an example of health state estimation of a certain type of aero-engine gas path system.
作者
尹晓静
张宇
彭寿鑫
史广旭
YIN Xiaojing;ZHANG Yu;PENG Shouxin;SHI Guangxu(School of Mechatronic Engineering, Changchun University of Technology, Changchun 130012, China)
出处
《长春工业大学学报》
CAS
2022年第1期10-18,共9页
Journal of Changchun University of Technology
基金
国家自然科学基金项目(61803044,61973046)
吉林省科技厅项目(20200403036SF)。
关键词
航空发动机气路系统
置信规则库
健康状态评估
自适应进化策略
aero-engine gas path system
Belief Rule Base(BRB)
state estimation
Projection Covariance Matrix Adaption Evolution Strategy(P-CMA-ES)
