CN-122024957-A - Copper plating thickness uniformity prediction method and device, electronic equipment and medium

CN122024957ACN 122024957 ACN122024957 ACN 122024957ACN-122024957-A

Abstract

The embodiment of the application provides a method and a device for predicting copper plating thickness uniformity, electronic equipment and a medium, and relates to the technical field of display screen manufacturing. The method comprises the steps of inputting copper plating design parameters of a circuit board to be produced into a pre-trained thickness prediction model, simulating a copper plating process flow of the circuit board to be produced based on the process design parameters and the structure design parameters by a simulation module in the thickness prediction model to obtain simulation thicknesses of all areas in the circuit board to be produced, inputting the simulation thicknesses into a correction network in the thickness prediction model, determining corrected copper plating thicknesses of all areas in the circuit board to be produced under the copper plating design parameters based on the copper plating design parameters and the simulation thicknesses by the correction network, outputting corrected copper plating thicknesses, and determining thickness uniformity results of the circuit board to be produced after copper plating by the copper plating design parameters based on the corrected copper plating thicknesses of all areas. Thereby rapidly and accurately obtaining the uniformity of the copper plating thickness of the circuit board to be produced.

Inventors

YANG JING
ZHAO YONGSHENG
ZHOU XIBO
ZHAO XINGXING

Assignees

京东方科技集团股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260123

Claims (10)

1. A method for predicting copper plating thickness uniformity, the method comprising: Inputting copper plating design parameters of a circuit board to be produced into a pre-trained thickness prediction model, wherein the thickness prediction model comprises a simulation module and a correction network, and the copper plating design parameters comprise process design parameters corresponding to a copper plating process flow and structural design parameters of all areas of the circuit board to be produced; The simulation module simulates a preset copper plating process flow of the circuit board to be produced based on the process design parameters and the structure design parameters to obtain simulation thicknesses of all areas in the circuit board to be produced, and inputs the simulation thicknesses into the correction network; The correction network determines corrected copper plating thickness of each region in the circuit board to be produced under the copper plating design parameters based on the copper plating design parameters and the simulation thickness, and outputs the corrected copper plating thickness; And determining thickness uniformity results after copper plating is carried out on the circuit board to be produced by adopting the copper plating design parameters based on the corrected copper plating thickness of each region of the circuit board to be produced.
2. The method of claim 1, wherein the training mode of the thickness prediction model comprises: Obtaining a plurality of training samples and thickness labels corresponding to each training sample, wherein each training sample comprises a sample copper plating design parameter of a sample circuit board, and the sample copper plating design parameter comprises a sample process design parameter corresponding to a copper plating process flow and a sample structure design parameter of each region of the sample circuit board; inputting each training sample into an initial thickness prediction model for the training sample; The simulation module in the initial thickness prediction model simulates a copper plating process flow of the sample circuit board, which is preset, based on the sample process design parameters and the sample structure design parameters to obtain sample simulation thicknesses of all areas in the sample circuit board, and inputs the sample simulation thicknesses into an initial correction network in the initial thickness prediction model; the initial correction network determines the copper plating thickness of each area in the sample circuit board after the sample correction under the sample copper plating design parameters based on the sample copper plating design parameters and the sample simulation thickness; and adjusting model parameters of the initial correction network according to the difference between the corrected copper plating thickness of the sample corresponding to each training sample and the thickness label corresponding to the training sample until the initial correction network meets convergence conditions, so as to obtain a trained thickness prediction model.
3. The method of claim 2, wherein the step of obtaining a plurality of training samples and thickness labels corresponding to each training sample comprises: carrying out data amplification on the real copper plating parameters in the production process of the circuit board to obtain a plurality of sample copper plating design parameters; inputting copper plating design parameters of each sample into the initial thickness prediction model, and obtaining sample simulation thickness output by a simulation module in the initial thickness prediction model; Determining a sample error corresponding to each sample simulation thickness based on a predetermined error distribution rule met by an output result of the simulation module; Aiming at each sample copper plating design parameter, determining a true value of copper plating thickness corresponding to the sample copper plating design parameter based on sample simulation thickness and sample error corresponding to the sample copper plating design parameter; and taking the copper plating design parameter of each sample as a training sample, and taking the true copper plating thickness value corresponding to the copper plating design parameter of the sample as a thickness label corresponding to the training sample.
4. The method of claim 3, wherein the step of data augmenting the actual copper plating parameters during the circuit board production process to obtain a plurality of sample copper plating design parameters comprises: And learning a joint distribution rule of real copper plating parameters in the production process of the circuit board by generating an countermeasure network, and carrying out data amplification on the real copper plating parameters according to the joint distribution rule to obtain a plurality of sample copper plating design parameters meeting preset amplification constraints.
5. A method according to claim 3, wherein prior to the step of determining a sample error for each sample simulation thickness based on a predetermined error distribution law satisfied by the output result of the simulation module, the method further comprises: Inputting each real copper plating parameter into an initial thickness prediction model, and obtaining a target simulation thickness corresponding to the real copper plating parameter output by a simulation module in the initial thickness prediction model; calculating a difference value between a true copper plating thickness value corresponding to each real copper plating parameter and a target simulation thickness; Inputting a difference value between a copper plating thickness true value corresponding to each real copper plating parameter and a target simulation thickness into an initial error prediction model so that the initial error prediction model carries out parameter optimization on kernel function parameters to obtain an error prediction model meeting an error distribution rule of the simulation module; The step of determining the sample error corresponding to each sample simulation thickness based on the error distribution rule satisfied by the predetermined output result of the simulation module comprises the following steps: And inputting each sample simulation thickness into the error prediction model, and obtaining a sample error corresponding to the sample simulation thickness output by the error prediction model.
6. The method according to any one of claims 1 to 5, wherein the step of determining a thickness uniformity result after copper plating of the circuit board to be produced using the copper plating design parameters based on the corrected copper plating thickness of each region of the circuit board to be produced comprises: and calculating the dispersion degree of the corrected copper plating thickness of each region based on the corrected copper plating thickness of each region of the circuit board to be produced, and obtaining the thickness uniformity result of the copper plating design parameters on the circuit board to be produced.
7. The method according to any one of claims 1 to 5, wherein after the step of determining a thickness uniformity result after copper plating the circuit board to be produced using the copper plating design parameters based on the corrected copper plating thickness of each region of the circuit board to be produced, the method further comprises: The copper plating design parameters are multiple, the thickness uniformity result comprises the thickness uniformity corresponding to each copper plating design parameter, the copper plating design parameter with optimal copper plating thickness uniformity is taken as a target copper plating design parameter, a circuit board is produced based on the structural design parameters included by the target copper plating design parameter, copper plating is carried out on the produced circuit board according to the process design parameters included by the target copper plating design parameter, or, And under the condition that the thickness uniformity result corresponding to the copper plating design parameter does not meet the preset uniformity requirement, determining a candidate copper plating design parameter meeting the parameter constraint condition corresponding to the copper plating design parameter by utilizing the copper plating design parameter, the thickness uniformity result and a preset optimizing algorithm, updating the copper plating design parameter of the circuit board to be produced into the candidate copper plating design parameter, returning to the step of inputting the copper plating design parameter of the circuit board to be produced into a pre-trained thickness prediction model until the thickness uniformity result corresponding to the obtained copper plating design parameter meets the preset uniformity requirement, taking the obtained copper plating design parameter as a target copper plating design parameter, producing the circuit board based on the structural design parameter included by the target copper plating design parameter, and carrying out copper plating on the produced circuit board according to the process design parameter included by the target copper plating design parameter.
8. A copper plating thickness uniformity prediction apparatus, characterized in that the apparatus comprises: The device comprises a parameter input module, a thickness prediction module, a correction network, a copper plating module and a copper plating module, wherein the parameter input module is used for inputting copper plating design parameters of a circuit board to be produced into a pre-trained thickness prediction model, and the thickness prediction model comprises a simulation module and the correction network; The simulation module is used for simulating a copper plating process flow of the circuit board to be produced, which is preset, based on the process design parameters and the structural design parameters, so as to obtain simulation thicknesses of all areas in the circuit board to be produced, and inputting the simulation thicknesses into the correction network; The correction module is used for determining corrected copper plating thickness of each region in the circuit board to be produced under the copper plating design parameters based on the copper plating design parameters and the simulation thickness by the correction network, and outputting the corrected copper plating thickness; And the prediction module is used for determining thickness uniformity results after copper plating is carried out on the circuit board to be produced by adopting the copper plating design parameters based on the corrected copper plating thickness of each region of the circuit board to be produced.
9. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus; a memory for storing a computer program; A processor for implementing the method of any of claims 1-7 when executing a program stored on a memory.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored therein a computer program which, when executed by a processor, implements the method of any of claims 1-7.

Description

Copper plating thickness uniformity prediction method and device, electronic equipment and medium Technical Field The application relates to the technical field of display screen manufacturing, in particular to a copper plating thickness uniformity prediction method, a copper plating thickness uniformity prediction device, electronic equipment and a copper plating thickness uniformity prediction medium. Background Copper plating is an important link in the manufacturing process of Mini LEDs (Light-emitting diodes), in which a copper layer is deposited on the surface of a micro-scale electrode by an electrochemical method to realize electrical interconnection and heat dissipation through the copper layer. Whether the copper plating thickness of each area of the circuit board is uniform directly influences the conductivity, the heat dissipation efficiency and the service life of a product, however, due to the high density structure and the microminiaturization characteristic of the Mini LED panel, the problems of uneven current distribution, uneven liquid medicine mass transfer and the like of different areas are easy to occur under the effect of an edge effect and a shielding effect in the copper plating process, so that the copper plating layers of different areas are different, and the uniformity of the copper plating thickness is influenced. Before the Mini LED is produced, the uniformity of the copper plating thickness of the Mini LED to be produced can be predicted, and the structure of the Mini LED can be adjusted according to the prediction result, so that the copper plating thickness of the produced Mini LED meets the uniformity requirement, and the quality of the produced Mini LED is improved. Disclosure of Invention The embodiment of the application aims to provide a method, a device, electronic equipment and a medium for predicting copper plating thickness uniformity, so as to predict copper plating thickness uniformity of a Mini LED to be produced. The specific technical scheme is as follows: in a first aspect, an embodiment of the present application provides a method for predicting uniformity of copper plating thickness, the method comprising: Inputting copper plating design parameters of a circuit board to be produced into a pre-trained thickness prediction model, wherein the thickness prediction model comprises a simulation module and a correction network, and the copper plating design parameters comprise process design parameters corresponding to a copper plating process flow and structural design parameters of all areas of the circuit board to be produced; The simulation module simulates a preset copper plating process flow of the circuit board to be produced based on the process design parameters and the structure design parameters to obtain simulation thicknesses of all areas in the circuit board to be produced, and inputs the simulation thicknesses into the correction network; The correction network determines corrected copper plating thickness of each region in the circuit board to be produced under the copper plating design parameters based on the copper plating design parameters and the simulation thickness, and outputs the corrected copper plating thickness; And determining thickness uniformity results after copper plating is carried out on the circuit board to be produced by adopting the copper plating design parameters based on the corrected copper plating thickness of each region of the circuit board to be produced. Optionally, the training mode of the thickness prediction model includes: Obtaining a plurality of training samples and thickness labels corresponding to each training sample, wherein each training sample comprises a sample copper plating design parameter of a sample circuit board, and the sample copper plating design parameter comprises a sample process design parameter corresponding to a copper plating process flow and a sample structure design parameter of each region of the sample circuit board; inputting each training sample into an initial thickness prediction model for the training sample; The simulation module in the initial thickness prediction model simulates a copper plating process flow of the sample circuit board, which is preset, based on the sample process design parameters and the sample structure design parameters to obtain sample simulation thicknesses of all areas in the sample circuit board, and inputs the sample simulation thicknesses into an initial correction network in the initial thickness prediction model; the initial correction network determines the copper plating thickness of each area in the sample circuit board after the sample correction under the sample copper plating design parameters based on the sample copper plating design parameters and the sample simulation thickness; and adjusting model parameters of the initial correction network according to the difference between the corrected copper plating thickness of the sample correspondi