Because of having many advantages, diamond is applied widely in many fields. But the existenceof body defects will debase the application quality. A set of defect recognized system is established based onthe compensatory fuzzy neural network of using wavelet and with fast algorithm in this paper. The energy-defect method to extract eigenvalue is used firstly, then defect classification is recognized by fuzzy neuralnetwork. The results of simulation show that the model established by making use of this algorithm has higherefficiency, and the possibility of wrap in local minimum value of the network during the training process issmaller, which can compare to approach the precision utmost steadily and classification recognize the defectprecision. The experiment result can verify this system have very high accurate rate to forecast the bodydefects and satisfy the demand of the engineering application, which provide the technique guarantee forfurther realizing the diamond synthesis quantity monitor system.
展开▼
