论文部分内容阅读
提出了一种用于设备性能退化评估的PCA-CMAC(主成分分析小脑模型节点控制器)模型.该模型利用PCA进行特征提取,去除多个传感器信号特征的冗余信息,并且减少CMAC的输入维数;利用CMAC的局部泛化能力定量地评估设备的性能退化.给出了模型的实现过程,并将模型应用于钻削过程刀具状态的评估,试验结果证明该模型能基于刀具的正常状态,对刀具的磨损状态进行定量的评估.分析了CMAC中泛化参数g和量化参数r对评估结果的影响,g越大,CMAC的泛化能力越好,但各退化状态之间的区别越不明显;r越小,各退化状态之间越容易区分,但所需的权存储空间越大.2个参数的基本选择原则是CMAC的权存储空间应尽量小,与此同时,各退化状态之间应容易区分.
A model of PCA-CMAC (Principal Component Analysis (MCNA) node controller for device performance degradation assessment is proposed.) This model uses PCA to extract features, removes redundant information from multiple sensor signals, and reduces CMAC input Dimension, CMAC's local generalization ability is used to quantitatively evaluate the performance degradation of the equipment. The realization process of the model is given and the model is applied to the evaluation of the tool state during drilling. The test results show that the model can be based on the normal state of the tool , The wear state of the tool is quantitatively evaluated.The influence of the generalized parameter g and the quantitative parameter r on the evaluation results of the CMAC is analyzed.The larger the g is, the better the generalization ability of the CMAC is, but the difference between the degraded states Is not obvious; the smaller the r, the easier it is to distinguish between degraded states, but the larger the required storage space is. The basic choice principle of the two parameters is that CMAC's storage space should be as small as possible. At the same time, Should be easy to distinguish between.