CN-122023059-A - Processing parameter determination method, apparatus, computer device, storage medium and computer program product

CN122023059ACN 122023059 ACN122023059 ACN 122023059ACN-122023059-A

Abstract

The present application relates to a processing parameter determination method, apparatus, computer device, storage medium and computer program product. The method comprises the steps of obtaining historical characteristic information of each of a plurality of historical processing objects and object characteristic information collected for the object to be processed, determining the difference degree between the historical characteristic information of the historical processing objects and the object characteristic information for each historical processing object, determining the historical processing parameters of the historical processing objects corresponding to the minimum difference degree as expected processing parameters for the object to be processed when the minimum difference degree in the difference degrees meets similar conditions, and determining the expected processing parameters of the object to be processed based on the object characteristic information when the minimum difference degree does not meet the similar conditions. By adopting the method, the accuracy can be improved.

Inventors

ZHANG JIALE
ZHANG QIUJUN
LIU HANYU
HU ZIYAN
OU CHANGXIN
Mo Weiguang

Assignees

珠海格力电器股份有限公司

Dates

Publication Date: 20260512
Application Date: 20251229

Claims (10)

1. A method of determining processing parameters, the method comprising: Acquiring the respective historical characteristic information of various historical processing objects and object characteristic information acquired for the object to be processed; determining, for each of the historical processing objects, a degree of difference between historical feature information of the historical processing object and the object feature information; when the minimum difference degree in the difference degrees meets the similar condition, determining the historical processing parameters of the historical processing object corresponding to the minimum difference degree as expected processing parameters for the object to be processed; And determining the expected processing parameters of the object to be processed based on the object characteristic information in the condition that the minimum difference degree does not meet the similar condition.
2. The method according to claim 1, wherein the method further comprises: acquiring respective history processing parameters of each history processing object, and constructing a training sample containing history characteristic information and the history processing parameters; Performing model training on the original model by using each training sample to obtain a processing parameter determination model; the determining the expected processing parameters of the object to be processed based on the object characteristic information comprises the following steps: Inputting the object characteristic information into the processing parameter determining model, and obtaining the expected processing parameter of the object to be processed based on the output of the processing parameter determining model.
3. The method of claim 2, wherein the determining the output of the model based on the process parameters results in the desired process parameters for the object to be processed, comprising: Determining the output of a model based on the processing parameters to obtain first expected processing parameters of the object to be processed; Determining the historical processing parameters of the historical processing object corresponding to the minimum difference degree as second expected processing parameters of the object to be processed; and determining the expected processing parameters of the object to be processed by combining the first expected processing parameters and the second expected processing parameters.
4. A method according to claim 3, wherein said determining the desired processing parameters of the object to be processed by combining the first desired processing parameters and the second desired processing parameters comprises: determining weights of the first desired processing parameter and the second desired processing parameter based on a difference between the minimum degree of difference and an upper limit of degree of difference characterizing the similar condition, wherein the weights of the second desired processing parameter are inversely related to the difference; and carrying out weighted statistics on the first expected processing parameter and the second expected processing parameter based on the weights to obtain the expected processing parameter of the object to be processed.
5. The method according to claim 1, wherein the method further comprises: performing information clustering on each piece of history characteristic information to obtain a plurality of processing object clusters, wherein each processing object cluster comprises at least one history processing object; determining an object cluster to be processed to which the history feature information belongs from the object clusters; The determining, for each of the historical processing objects, a degree of difference between the historical feature information of the historical processing object and the object feature information includes: And determining the degree of difference between the history feature information of the history processing object and the object feature information for each history processing object in the object cluster to be processed.
6. The method according to claim 2, wherein the method further comprises: Acquiring actual processing parameters of the object to be processed; And under the condition that the information difference between the actual processing parameter and the expected processing parameter is larger than an information difference threshold, constructing an incremental training sample containing the object characteristic information and the actual processing parameter, wherein the incremental training sample is used for performing incremental training on the processing information determination model.
7. A processing information determining apparatus, characterized by comprising: The characteristic information acquisition module is used for acquiring the respective historical characteristic information of various historical processing objects and object characteristic information acquired for the object to be processed; A difference determining module, configured to determine, for each of the historical processing objects, a difference between historical feature information of the historical processing object and the object feature information; a first expected processing parameter determining module, configured to determine, when a minimum difference degree in the difference degrees satisfies a similar condition, a historical processing parameter of a historical processing object corresponding to the minimum difference degree as an expected processing parameter for the object to be processed; And the second expected machining parameter determining module is used for determining the expected machining parameters of the object to be machined based on the object characteristic information in the case that the minimum difference degree does not meet the similar condition.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

Description

Processing parameter determination method, apparatus, computer device, storage medium and computer program product Technical Field The present application relates to the field of processing technology, and in particular, to a processing parameter determining method, apparatus, computer device, storage medium, and computer program product. Background Along with the rapid development of processing technology, accurate determination of processing parameters becomes a key link for improving product quality and production efficiency. In various processing scenes, the characteristic difference of different processing objects is obvious, and the traditional processing parameter determination mode usually depends on manual experience or a fixed process template. For example, in the conventional method, an operator needs to manually select processing parameters of similar cases as references by comparing visual features of an object to be processed and historical cases. However, the feature differences are difficult to comprehensively quantify by manual comparison, and the processing errors are easily caused by neglecting key parameters, so that the traditional processing parameter determining method has the problem of poor accuracy. Disclosure of Invention Based on this, it is necessary to provide a processing parameter determining method, apparatus, computer device, storage medium and computer program product for solving the technical problem that the conventional processing parameter determining method is poor in accuracy. In a first aspect, the present application provides a method of determining a processing parameter. The method comprises the following steps: Acquiring the respective historical characteristic information of various historical processing objects and object characteristic information acquired for the object to be processed; determining, for each of the historical processing objects, a degree of difference between historical feature information of the historical processing object and the object feature information; when the minimum difference degree in the difference degrees meets the similar condition, determining the historical processing parameters of the historical processing object corresponding to the minimum difference degree as expected processing parameters for the object to be processed; And determining the expected processing parameters of the object to be processed based on the object characteristic information in the condition that the minimum difference degree does not meet the similar condition. In one embodiment, the method further comprises: acquiring respective history processing parameters of each history processing object, and constructing a training sample containing history characteristic information and the history processing parameters; Performing model training on the original model by using each training sample to obtain a processing parameter determination model; the determining the expected processing parameters of the object to be processed based on the object characteristic information comprises the following steps: Inputting the object characteristic information into the processing parameter determining model, and obtaining the expected processing parameter of the object to be processed based on the output of the processing parameter determining model. In one embodiment, the determining the output of the model based on the processing parameters, to obtain the desired processing parameters of the object to be processed, includes: Determining the output of a model based on the processing parameters to obtain first expected processing parameters of the object to be processed; Determining the historical processing parameters of the historical processing object corresponding to the minimum difference degree as second expected processing parameters of the object to be processed; and determining the expected processing parameters of the object to be processed by combining the first expected processing parameters and the second expected processing parameters. In one embodiment, the determining the desired processing parameter of the object to be processed by combining the first desired processing parameter and the second desired processing parameter includes: determining weights of the first desired processing parameter and the second desired processing parameter based on a difference between the minimum degree of difference and an upper limit of degree of difference characterizing the similar condition, wherein the weights of the second desired processing parameter are inversely related to the difference; and carrying out weighted statistics on the first expected processing parameter and the second expected processing parameter based on the weights to obtain the expected processing parameter of the object to be processed. In one embodiment, the method further comprises: performing information clustering on each piece of history characteristic information to obtain a plural