运用灰色理论中的关联度分析方法，计算待检磨粒与标准磨粒的关联度，从而检测出磨粒的类型．这种方法在实现上，以神经网络的方式进行，形成了一个有效的磨位识别诊断系统． The gray relational analysis method was used to calculate the degree of association between the test abrasive particles and the standard abrasive particles to detect the type of abrasive particles. This method is implemented in the way of neural network, forming an effective grinding position recognition diagnosis system.