Alloy grade identification method based on artificial neural network

Abstract

The invention discloses an alloy grade identification method based on an artificial neural network. The method comprises the steps of (1) establishment of the artificial neural network in which the proper artificial neural network which includes the type and layer number of the neural network, the number of neurons in each layer, a transfer function and a training function is established according to the size of a grade library; (2) training of the artificial neural network in which sample input includes contents of key elements, sample output includes identification codes of grades, and the trained artificial network is stored and kept standby; and (3) simulation of the artificial neural network in which actual measurement data of detected samples is input to the trained neural network, integers are taken from the output data of the neural network proximately, the taken values represent the identification codes of grades of the detected samples, and the grades of the detected samples are reported according to the identification codes of the grades.

Description

technical field [0001] The invention relates to the field of alloy detection, in particular to an alloy grade identification method based on an artificial neural network. Background technique [0002] Brand identification refers to comparing the measured element content information of the tested sample with the element content range information of several brands in the brand library, and inferring related information such as the brand name of the test object. Brand identification is a new function gradually derived with the development of the alloy testing industry, which greatly facilitates the identification and classification of alloys. [0003] There are few types of existing brand identification methods, which are generally divided into the following categories: (1) Determine whether the detected object is the brand according to whether the measured element content value is within the content range specified by the brand. The disadvantage of this method is that if a cer...

AI Technical Summary

Problems solved by technology

[0005] In view of the above deficiencies, the present invention provides an alloy grade recognition method based on an artificial neural network, which introduces the artificial neural network into the grade recognition problem, utilizes the powerful learning ability and fault tolerance of the artificial neural network, and puts aside the complicated analysis process. The identification problem of alloy grades is converted into a black box problem, and the accurate identification of alloy grades can be realized with the help of the powerful computing power of the computer

Images