Method, device, equipment and storage medium for predicting removal amount of grinding material
A technology for grinding materials and prediction methods, applied in grinding/polishing equipment, measuring devices, metal processing equipment, etc., can solve problems such as intractability, reduce processing costs, improve processing efficiency, and be easy to deploy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0052] see figure 1 As shown, the present invention provides a flow chart of a grinding material removal prediction method, which specifically includes:
[0053] S10: Calibrate the acoustic emission sensor;
[0054] S20: fixing the acoustic emission sensor on the workpiece fixture;
[0055] S30: collecting the acoustic emission signal received by the acoustic emission sensor, measuring the material removal depth and converting it into a material removal amount;
[0056] S40: Process the collected acoustic emission signal by wavelet transform method and fast Fourier transform;
[0057] S50: extracting the characteristic value of the acoustic emission signal generated in the grinding process;
[0058] S60: Construct a nonlinear regression model of material removal amount according to the material removal amount and the eigenvalue, so as to realize online prediction of material removal amount and guide the subsequent grinding process.
[0059] Among them, S10: calibrate the a...
Embodiment 2
[0081] see figure 2 , which provides a flow chart of an integrated learning algorithm for predicting the removal amount of titanium alloy material removed by robotic abrasive belt grinding for the present invention.
[0082] Step S60 in the first embodiment constructs a nonlinear regression model of the material removal amount according to the material removal amount and the eigenvalue, so as to realize the online prediction of the material removal amount and guide the subsequent grinding process, specifically including: according to the The material removal amount and the eigenvalue construct the nonlinear regression model of the material removal amount based on integrated learning, wherein the integrated learning algorithm includes:
[0083] S61: Initialize weight distribution;
[0084] S62: Calculate the training set sample error value;
[0085] S63: Calculate the regression error rate of the base learner;
[0086] S64: Calculate the weight coefficient of the base learn...
Embodiment 3
[0109] see Figure three , the present invention provides a verification process for the prediction method of grinding material removal amount;
[0110] Based on an embodiment of a method for predicting the amount of grinding material removal, further, a verification process for the method for predicting the amount of grinding material removal is proposed. Specifically include:
[0111] S10: Calibrate the acoustic emission sensor;
[0112] S20: fixing the acoustic emission sensor on the workpiece fixture;
[0113] S30: collecting the acoustic emission signal received by the acoustic emission sensor, measuring the material removal depth and converting it into a material removal amount;
[0114] S40: Process the collected acoustic emission signal by using a wavelet transform method and a fast Fourier transform algorithm;
[0115] S50: extracting the characteristic value of the acoustic emission signal generated in the grinding process;
[0116] S60: Construct a nonlinear re...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


