Intelligent detection modeling method for blanking quality of alloy plate

Abstract

The invention relates to an intelligent detection modeling method for blanking quality of an alloy plate, which comprises the following steps: firstly, synchronously monitoring an acoustic emission signal in an alloy blanking process by acoustic emission, and denoising the acoustic emission signal through HHT (Hilbert Huang Transformation); then extracting characteristic parameters in the blanking process: maximum peak values of ringing count, energy, effective value voltage RMS, average signal level ASL and the like; detecting the section of the blanking part by an optical method, recording parameters such as width values of a bright area and a tearing area of the section of the blanking part and height values of a fillet area and burrs, and normalizing characteristic parameters and parameters of the section of the blanking part; using normalized characteristic parameters as input of an artificial neural network, using normalized blanking part section parameters as output to train an artificial neural network model, verification shows that the accuracy of the artificial neural network model reaches 98% or above, and the method can be used in the field of blanking quality detection. The modeling method has the advantages of high detection efficiency and high accuracy.

Description

Technical field [0001] The present invention belongs to the field of alloy sheet mass detection, and specifically, the present invention relates to a smart detection modeling method of alloy sheet punching quality. Background technique [0002] During the pressing process of the auto parts, the unreasonable punching process and damaged molds cause the emergence of punching defects, and the punching may cause flaws such as burrs, wear, thin, cracking. Since the equipment may be very long from the time of failure to discover the fault and from the production failure, it may not be able to prevent the manufacture of defective products, and timely detect the quality of the defect on the punching parts and the safety of automotive driving. [0003] In response to this situation, in recent years, it has developed a predictive maintenance. For predictive repairs, advanced non-destructive testing technology can be used to detect defects, but this non-destructive test is a device that is ...

AI Technical Summary

Problems solved by technology

[0002] In the blanking process of auto parts, unreasonable blanking process and damaged molds lead to the appearance of blanking parts defects, which may cause defects such as burrs, wear, thinning, and cracking of the sheet

Since the time from the failure of the equipment to the discovery of the failure and the elimination of the failure from the production failure may be very long, it is impossible to prevent the manufacture of defective products, and timely detection of defects is crucial to the quality of blanking parts and the safety of automobile driving

[0003] In response to this situation, predictive maintenance has been developed in recent years. For predictive maintenance, advanced non-destructive testing technology can be used to detect device defects, but this kind of non-destructive testing is aimed at processed devices and cannot achieve real-time detection; Establishing a real-time intelligent detection model for the punching quality of alloy sheets is a technical problem that needs to be solved urgently

Images