Model self-learning fused coating process parameter self-optimization system and method

By constructing directed data chains and mapping relationships, and combining reinforcement learning algorithms to optimize coating process parameters, the problem of insufficient correlation between detection results and historical data in existing technologies has been solved. This has achieved optimization of the stability and consistency of coating process parameters, and improved production efficiency and intelligent management.

CN122113654APending Publication Date: 2026-05-29GUANGZHOU ZHONGLIAN DINGXING TECH CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202610323541.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-17
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

In the current process of optimizing coating process parameters, there is a lack of data chain analysis on the correlation between test results and historical production data, which makes it difficult to guarantee the stability and reliability of the optimization results. In particular, when the process state or acquisition conditions drift, the optimization strategy is prone to deviate.

Method used

A directed data chain structure is constructed, and a unique mapping relationship is formed through process accessibility constraints and energy minimum path calculation. The deviation of the detection results is calculated by combining historical data distribution and dynamic operating condition correlation algorithms to generate a consistency index. Then, the process parameters are optimized under constraints through reinforcement learning algorithms to achieve adaptive parameter updates.

Benefits of technology

It improves the stability and consistency of coating process parameter optimization, significantly increases production efficiency, reduces reliance on manual adjustments, and has the ability to dynamically identify and self-correct abnormal operating conditions, thus realizing intelligent and highly reliable management of coating production.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to the field of coating parameter self-optimization, and discloses a coating process parameter self-optimization system and a coating process parameter self-optimization method fusing model self-learning. Comprising the following steps: collecting process parameters, production conditions, equipment power states and detection result data of multi-batch coating production in real time, and aligning and associating the data according to a process sequence to form a unique mapping relationship; reversely determining a corresponding process parameter node and working condition node set, and generating a consistency index; performing joint comparison on the consistency index and the corresponding data chain distribution, and outputting a corresponding working condition drift identifier; introducing the consistency index and the working condition drift identifier as constraint conditions into the parameter updating model, and outputting a constrained parameter updating result; a corresponding new round of detection result is written into the unique mapping relation, and the mapping relation and the reachable state space after incremental updating are generated. The method has the advantage of improving the stability of an optimization result.
Need to check novelty before this filing date? Find Prior Art