CN-122024944-A - Thermoplastic thickness prediction method and device based on industrial Internet and electronic equipment

CN122024944ACN 122024944 ACN122024944 ACN 122024944ACN-122024944-A

Abstract

The embodiment of the application provides a thermoplastic thickness prediction method and device based on industrial Internet and electronic equipment, and relates to the technical field of thermoplastic. The method comprises the steps of dividing a material to be thermoplastic into a plurality of first grid cells, constructing a graph structure of the material to be thermoplastic according to the position relation among the plurality of first grid cells, wherein nodes of the graph structure are used for representing the corresponding first grid cells, edges of the graph structure are used for representing the position relation among the two corresponding first grid cells, acquiring first temperature distribution of thermoplastic equipment, determining second temperature distribution corresponding to each first grid cell based on the first temperature distribution, updating node characteristics of the plurality of nodes in the graph structure based on the second temperature distribution, obtaining an updated graph structure, and predicting thermoplastic thickness corresponding to the plurality of first grid cells according to the updated graph structure to obtain a thermoplastic thickness prediction result of the material to be thermoplastic. High-precision prediction of the thickness of the product is realized, and the quality and the production efficiency of the product are improved.

Inventors

WANG LIN
FENG XINGZHI
CHEN LUCHENG
YANG JIAN
LU XIAOPING
WANG CHAO
LI LEI

Assignees

卡奥斯工业智能研究院(青岛)有限公司
卡奥斯物联科技股份有限公司

Dates

Publication Date: 20260512
Application Date: 20251225

Claims (12)

1. A thermoplastic thickness prediction method based on the industrial internet, the method comprising: Dividing a material to be thermoplastic into a plurality of first grid cells, and constructing a graph structure of the material to be thermoplastic according to the position relation among the plurality of first grid cells, wherein nodes of the graph structure are used for representing the corresponding first grid cells, and edges of the graph structure are used for representing the position relation among the two corresponding first grid cells; acquiring a first temperature distribution of a thermoplastic device, wherein the thermoplastic device is used for processing the material to be thermoplastic; determining a second temperature distribution corresponding to each first grid unit based on the first temperature distribution; And based on the second temperature distribution, updating node characteristics of a plurality of nodes in the graph structure to obtain an updated graph structure, and predicting thermoplastic thicknesses corresponding to a plurality of first grid units according to the updated graph structure to obtain a thermoplastic thickness prediction result of the material to be thermoplastic.
2. The method of claim 1, wherein the determining a second temperature profile corresponding to each of the first grid cells based on the first temperature profile comprises: Performing temperature zone division processing on the thermoplastic equipment to obtain a plurality of second grid cells corresponding to the thermoplastic equipment; And determining a heat conduction mapping relation between the plurality of second grid cells and the first grid cells, and determining a second temperature distribution corresponding to each first grid cell according to the mapping relation and the first temperature distribution.
3. The method according to claim 1, wherein constructing the graph structure of the material to be thermoplastic according to the positional relationship among the plurality of first grid cells includes: Determining a plurality of adjacent first grid cells adjacent to any one first grid cell according to the position relation among the plurality of first grid cells; Determining a grid distance between the first grid cell and any of the plurality of adjacent first grid cells, the grid distance being used to indicate a distance between a grid center point of the first grid cell and the adjacent first grid cell grid center point; determining a plurality of edge weights of the first grid unit and the plurality of adjacent first grid units according to the grid distance and the material parameters of the material to be thermoplastic; And taking any one of the first grid cells as a node of the graph structure, and taking the plurality of edge weights as edges of the graph structure to obtain the graph structure of the material to be thermoplastic.
4. The method of claim 1, wherein after said building the patterned structure of the material to be thermoplastic, the method further comprises: acquiring technological parameters of the material to be thermoplastic, wherein the technological parameters comprise adsorption pressure, adsorption time and heating time in the thermoplastic treatment process; Determining material parameters of the material to be thermoplastic; and determining initial node characteristics of the first grid cells according to the material parameters and the process parameters of the first grid cells.
5. The method of claim 4, wherein updating the node characteristics of the plurality of nodes in the graph structure based on the second temperature distribution to obtain an updated graph structure comprises: determining a heat flow value and an attention coefficient of any one first grid cell and the adjacent first grid cell in the graph structure based on the graph structure; and updating the node characteristics of a plurality of nodes in the graph structure according to the heat flow value, the attention coefficient, the initial node characteristics and the second temperature distribution to obtain an updated graph structure.
6. The method of claim 1, wherein predicting thermoplastic thicknesses corresponding to a plurality of the first grid cells based on the updated graph structure comprises: The updated graph structure is used as input data of a thermoplastic thickness prediction model, and the thermoplastic thickness prediction model is controlled to carry out iterative processing, wherein the thermoplastic thickness prediction model is obtained by training according to historical thermoplastic production data and field expert experience based on a machine learning method; determining a total loss function of the thermoplastic thickness prediction model, the total loss function comprising a first loss function of the thermoplastic thickness prediction model and a second loss function of a physical constraint; And when the total loss function is determined to be converged, controlling the thermoplastic thickness prediction model to stop iterative processing, and outputting predicted thicknesses corresponding to a plurality of first grid cells.
7. The method of claim 6, wherein said determining a total loss function of said thermoplastic thickness predictive model comprises: obtaining the thermoplastic thickness prediction result output by the thermoplastic thickness prediction model and the actual thickness of the material to be thermoplastic after thermoplastic treatment; determining an absolute value of a difference between the actual thickness and the predicted result; judging whether the absolute value of the difference value is smaller than an error threshold value or not; determining that the first loss function converges when the absolute value of the difference is smaller than an error threshold; determining that the first loss function is non-converging if the absolute value of the difference is not less than the error threshold; determining a second loss function of the thermoplastic thickness prediction model, where the first loss function indicates convergence, the second loss function being used to indicate a physical law constraint; a total loss function of the thermoplastic thickness prediction model is determined based on the first loss function and the second loss function.
8. The method of claim 7, wherein the method further comprises: if the actual thickness is larger than the target thickness, carrying out up-regulating treatment on the adsorption pressure and/or the adsorption duration and/or the heating duration; And if the actual thickness is not greater than the target thickness, performing down-regulating treatment on the adsorption pressure and/or the adsorption duration and/or the heating duration.
9. An industrial internet-based thermoplastic thickness prediction apparatus, the apparatus comprising: The processing module is used for dividing the material to be thermoplastic into a plurality of first grid cells and constructing a graph structure of the material to be thermoplastic according to the position relation among the plurality of first grid cells, wherein nodes of the graph structure are used for representing the corresponding first grid cells, and edges of the graph structure are used for representing the position relation among the two corresponding first grid cells; the acquisition module is used for acquiring a first temperature distribution of thermoplastic equipment, and the thermoplastic equipment is used for processing the material to be thermoplastic; A determining module, configured to determine a second temperature distribution corresponding to each first grid cell based on the first temperature distribution; The processing module is further configured to update node characteristics of a plurality of nodes in the graph structure based on the second temperature distribution, obtain an updated graph structure, and predict thermoplastic thicknesses corresponding to the plurality of first grid units according to the updated graph structure, so as to obtain a thermoplastic thickness prediction result of the material to be thermoplastic.
10. An electronic device comprising a processor and a memory communicatively coupled to the processor; The memory stores computer-executable instructions; The processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1 to 8.
11. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1to 8.
12. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1 to 8.

Description

Thermoplastic thickness prediction method and device based on industrial Internet and electronic equipment Technical Field The present application relates to the field of thermoplastic technologies, and in particular, to a thermoplastic thickness prediction method and apparatus based on industrial internet, and an electronic device. Background Thermoplastic processing is a common material molding process and is widely applied to processing thermoplastic materials such as plastics, rubber and the like. Thermoplastic processing mainly utilizes the property of thermoplastic materials that soften when heated to a certain temperature and harden when cooled. By controlling the heating and cooling process, the material can be thermoformed into a desired shape. Currently, thermoplastic processing techniques are used by securing thermoplastic sheets over a mold. Subsequently, the plate material is heated to a softened state by a heating device. The mold is then moved toward the sheet to form a sealed cavity. And the air in the cavity is pumped out by the vacuum pump, and the plate is tightly attached to the surface of the die by means of atmospheric pressure, so that the forming process is completed. After forming, the plate is shaped in the cooling process. And finally, smoothly demolding the molded plastic piece from the mold by using compressed air. Although thermoplastic processing has the advantages of high efficiency and low cost, in the vacuum plastic sucking molding process, the thickness of the final product is uneven due to the uneven temperature distribution of the heating plate or the characteristics of the material, and the quality of the product is affected. For products with new shapes, the prior art relies on manual parameter adjustment, resulting in low production efficiency. Disclosure of Invention The application provides a thermoplastic thickness prediction method and device based on industrial Internet and electronic equipment, which are used for solving the technical defects of low product quality and low production efficiency caused by uneven thickness of thermoplastic products and dependence on manual parameter adjustment in the prior thermoplastic technology. In a first aspect, the present application provides a thermoplastic thickness prediction method based on the industrial internet, applied to thermoplastic equipment, comprising: Dividing a material to be thermoplastic into a plurality of first grid cells, and constructing a graph structure of the material to be thermoplastic according to the position relation among the plurality of first grid cells, wherein nodes of the graph structure are used for representing the corresponding first grid cells, and edges of the graph structure are used for representing the position relation among the two corresponding first grid cells; acquiring a first temperature distribution of a thermoplastic device, wherein the thermoplastic device is used for processing the material to be thermoplastic; determining a second temperature distribution corresponding to each first grid unit based on the first temperature distribution; And based on the second temperature distribution, updating node characteristics of a plurality of nodes in the graph structure to obtain an updated graph structure, and predicting thermoplastic thicknesses corresponding to a plurality of first grid units according to the updated graph structure to obtain a thermoplastic thickness prediction result of the material to be thermoplastic. Optionally, the determining, based on the first temperature distribution, a second temperature distribution corresponding to each first grid unit includes: Performing temperature zone division processing on the thermoplastic equipment to obtain a plurality of second grid cells corresponding to the thermoplastic equipment; And determining a heat conduction mapping relation between the plurality of second grid cells and the first grid cells, and determining a second temperature distribution corresponding to each first grid cell according to the mapping relation and the first temperature distribution. Optionally, the constructing the graph structure of the material to be thermoplastic according to the positional relationship among the plurality of first grid cells includes: Determining a plurality of adjacent first grid cells adjacent to any one first grid cell according to the position relation among the plurality of first grid cells; Determining a grid distance between the first grid cell and any of the plurality of adjacent first grid cells, the grid distance being used to indicate a distance between a grid center point of the first grid cell and the adjacent first grid cell grid center point; determining a plurality of edge weights of the first grid unit and the plurality of adjacent first grid units according to the grid distance and the material parameters of the material to be thermoplastic; And taking any one of the first grid cells as a node of the gr