CN-121989372-A - Material cutting parameter adjusting method, slicer, electronic device and computer readable storage medium

CN121989372ACN 121989372 ACN121989372 ACN 121989372ACN-121989372-A

Abstract

The invention provides a method for adjusting a material cutting parameter, a slicing machine, an electronic device and a computer readable storage medium, wherein the method for adjusting the material cutting parameter comprises the steps of acquiring the actual cutting parameter of a material in real time in the material cutting process, wherein the actual cutting parameter at least comprises cutting force, cutting time and a feeding position; and according to the theoretical cutting force parameter, proportional-integral-differential control is carried out on the cutting parameters of the materials in the subsequent cutting process so as to adjust the subsequent cutting force parameter to be within a preset parameter range in real time. The invention solves the problem of unstable surface quality of the cut silicon wafer caused by unstable output of cutting force of the diamond wire in the process of cutting the silicon wafer in the prior art.

Inventors

ZHANG AIXIN
LI LU
XING XU
ZHUANG XUSHENG

Assignees

高测(盐城)技术有限公司

Dates

Publication Date: 20260508
Application Date: 20241105

Claims (11)

1. The method for adjusting the material cutting parameters is characterized by comprising the following steps: In the material cutting process, acquiring actual cutting parameters of the material in real time, wherein the actual cutting parameters at least comprise cutting force, cutting time and feeding position; inputting the actual cutting parameters into a decision model for fitting to obtain theoretical cutting force parameters; And according to the theoretical cutting force parameters, proportional-integral-differential control is carried out on the cutting parameters of the materials in the subsequent cutting process so as to adjust the subsequent cutting force parameters to be within a preset parameter range in real time.
2. The method for adjusting a cutting parameter of a material according to claim 1, wherein performing proportional-integral-derivative control on the cutting parameter of the material in a subsequent cutting process according to the theoretical cutting force parameter comprises: acquiring an actual cutting force in the actual cutting parameters; calculating the difference value, increment and accumulated variation of the actual cutting force and the theoretical cutting force; And performing proportional-integral-derivative control according to the calculation result.
3. The method of claim 2, wherein calculating the difference, the increment, and the cumulative change between the actual cutting force and the theoretical cutting force comprises: e(t)=x t -E,t=1,2,...,k; Δe(t)=e t -e t-1 ; Wherein e (T) is the difference between the actual cutting force and the theoretical cutting force, Δe (T) is the increment of the actual cutting force and the theoretical cutting force, u (T) is the accumulated variation of the actual cutting force and the theoretical cutting force, K P is a proportionality coefficient for reflecting the speed of adjustment, T t is the residual accumulation time for reflecting the relation between the current value and the previous T i cycles, K i is an adjustment coefficient for indicating the adjustment force of the accumulated error, and T D is a differential time constant for reflecting the correction force after the abrupt change of the sensor value.
4. The method for adjusting a cutting parameter of a material according to claim 1, wherein inputting the obtained actual cutting parameter into a decision model to obtain a theoretical cutting force parameter comprises: Establishing a plurality of regression tree models, connecting the regression tree models in series, outputting target prediction results by each regression tree model, and outputting theoretical cutting force parameters according to each target prediction result.
5. The method for adjusting a cutting parameter of a material according to claim 1, wherein inputting the obtained actual cutting parameter into a decision model to obtain a theoretical cutting force parameter comprises: Establishing a strong learning expression: Wherein t represents the round and I (x ε R tj ) is an indicator function.
6. The method of claim 1, wherein inputting the obtained actual cutting parameters into a decision model comprises: And taking the actual feed position and the actual feed force data as input characteristics and the theoretical feed force as output characteristics, and carrying out regression tree model training.
7. The method of claim 6, wherein the performing regression tree model training comprises: calculating a training set minimum error MSE and a sample residual error; ε i ＝f(x i )-y i ,i=1,2...,m。
8. the method for adjusting a material cutting parameter according to claim 1, wherein, Before the actual cutting parameters are obtained, a test set and a training set of cutting data are obtained, and model training is carried out on the test set and the training set of the cutting data to obtain a regression tree model.
9. A microtome adapted to a method of adjusting a cutting parameter of a material according to any one of claims 1 to 8.
10. An electronic device, the electronic device comprising: The acquisition unit is used for acquiring a test set and a training set of the cutting data; The modeling unit is used for carrying out model training according to the training set and the testing set to obtain a regression tree model; and the cutting control unit is used for adjusting cutting parameters in real time according to the output result of the regression tree model and outputting the cutting parameters to the cutting equipment.
11. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored program, wherein the program, when run, controls a device in which the computer readable storage medium is located to perform the method for adjusting the material cutting parameter according to any one of claims 1 to 8.

Description

Material cutting parameter adjusting method, slicer, electronic device and computer readable storage medium Technical Field The invention relates to the technical field of cutting methods, in particular to a method for adjusting material cutting parameters, a slicing machine, an electronic device and a computer readable storage medium. Background At present, the consolidated diamond abrasive wire cutting technology has become the mainstream technology of photovoltaic silicon wafer cutting, and has the advantages of narrow kerf, good dicing quality, high cutting efficiency and the like. As photovoltaic cutting progresses to large-size, thin-line, fluctuations in diamond wire quality have more serious effects on cutting wire breakage or cutting quality. The abrasion cause of the diamond wire is complex, the abrasion cause has close relation with the cutting process, the cutting equipment, the cutting fluid and the manufacturing process of the steel wire, and a direct mathematical model is difficult to establish. Therefore, in the cutting process, due to the fact that silicon rods are different in size and the abrasion of the diamond wire in the repeated cutting process, the cutting force can fluctuate, even the risk of wire breakage occurs, and the cutting yield and the surface quality of a cut silicon wafer are reduced. Disclosure of Invention The invention mainly aims to provide a method for adjusting material cutting parameters, a slicing machine, an electronic device and a computer readable storage medium, so as to solve the problem of unstable surface quality of a cut silicon wafer caused by unstable output of cutting force of a diamond wire in the process of cutting the silicon wafer in the prior art. In order to achieve the above object, according to a first aspect of the present invention, there is provided a method for adjusting a cutting parameter of a material, including acquiring, in real time, an actual cutting parameter of the material during a cutting process of the material, the actual cutting parameter including at least a cutting force, a cutting time, and a feeding position, inputting the actual cutting parameter into a decision model to perform fitting to obtain a theoretical cutting force parameter, and performing proportional-integral-differential control on the cutting parameter of the material during a subsequent cutting process according to the theoretical cutting force parameter, so as to adjust the subsequent cutting force parameter to be within a predetermined parameter range in real time. Further, proportional integral differential control is carried out on cutting parameters of materials in a follow-up cutting process according to theoretical cutting force parameters, wherein the proportional integral differential control comprises the steps of obtaining actual cutting force in the actual cutting parameters, calculating a difference value, an increment and an accumulated variation of the actual cutting force and the theoretical cutting force, and carrying out proportional integral differential control according to a calculation result. Further, calculating the difference, increment and accumulated variation of the actual cutting force and the theoretical cutting force includes: e(t)=xt-E,t=1,2,...,k; Δe(t)=et-et-1; Wherein e (T) is the difference between the actual cutting force and the theoretical cutting force, Δe (T) is the increment of the actual cutting force and the theoretical cutting force, u (T) is the accumulated variation of the actual cutting force and the theoretical cutting force, K P is a proportionality coefficient for reflecting the speed of adjustment, T t is the residual accumulation time for reflecting the relation between the current value and the previous T i cycles, K i is an adjustment coefficient for indicating the adjustment force of the accumulated error, and T D is a differential time constant for reflecting the correction force after the abrupt change of the sensor value. Further, inputting the obtained actual cutting parameters into a decision model to obtain theoretical cutting force parameters, wherein the theoretical cutting force parameters comprise the steps of establishing a plurality of regression tree models, connecting the regression tree models in series, outputting target prediction results by each regression tree model, and outputting the theoretical cutting force parameters according to each target prediction result. Further, inputting the obtained actual cutting parameters into a decision model to obtain theoretical cutting force parameters, wherein the theoretical cutting force parameters comprise the steps of establishing a strong learning expression: Wherein t represents the round and I (x ε R tj) is an indicator function. Further, inputting the obtained actual cutting parameters into the decision model comprises the steps of taking the actual feeding position and the actual feeding force data as input characteristics and the theoret