欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
基于变量预测模型的分类识别（Variable predictive model-based class discriminate,VPMCD）方法是一种新的分类识别方法,但模型类型的选择存在主观性。为了解决VPMCD方法应用于机械故障诊断过程中的模型选择问题,结合遗传算法的全局优化能力,提出了基于GA-VPMCD（Genetic algorithm and variable predictive model based class discriminate）智能诊断方法。首先通过样本训练建立多个弱VPM（Variable predictive model）,然后采用遗传算法优化各个弱VPM的权值,得到最优权值矩阵,最后用最优权值矩阵加权融合测试样本的弱VPM特征变量预测值,得到最佳特征变量预测值,并以误差平方和最小为辨别函数分类识别故障类型。通过GA-VPMCD方法在滚动轴承故障智能诊断中的应用实验验证了基于GA-VPMCD的故障智能诊断方法能有效地提高诊断精度和诊断系统的鲁棒性。
英文摘要：
Variable predictive model based class discriminate （VPMCD） is a new class discriminate approach, however, the choice of model type exists subjectivity. Combining the global optimization performance of genetic algorithm （GA）, a method of fault intelligent diagnosis based on GA and VPMCD is presented to solve the problem of selecting model type in the course of machinery fault diagnosis by using VPMCD. Firstly, multiple weak Variable predictive models （VPMs） can be established through samples training. Secondly, after GA is used to optimize the weights matrix of each weak VPM, the optimal weights matrix is obtained. Lastly, optimal weights matrix is exploited to get optimal feature variables predictions by weight fusion for the values, which are predicted by the weak VPMs for the test samples, and fault types are identified according to the minimum error square sum as discrimination function simultaneously. It is demonstrated from the diagnosis experiment of roller bearings that the proposed method of intelligent diagnosis based on GA and VPMCD can improve the accuracy rate and robustness of diagnosis system.
同期刊论文项目
同项目期刊论文
Rolling bearing fault diagnosis based on multi-scale fuzzy entropy and variable predictive model-bas
Normalized complex Teager energy operator demodulation method and its application to fault diagnosis
Generalized empirical mode decomposition and its applications to rolling element bearing fault diagn
期刊信息
位置：