Coating Process Parameter Adjustment for Drift-Resistant Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing feedback methods for coating processes fail to manage drifts in measuring instrument accuracy and precision, and are ineffective when environmental changes or material features differ from targeted specifications, leading to out-of-specification products.
Innovation Solution
A method that uses multiple mathematical prediction models trained on manufacturing history datasets to adjust coating process parameters in real-time, compensating for instrument drifts and environmental changes, allowing for simultaneous adjustment of multiple parameters and preventing local optimal traps.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If online feedback methods with continuous real-time monitoring are used, then manufacturing precision is improved, but device complexity increases due to numerous sensors and measuring devices
Solution Approach 1:
The patent segments the measurement system into distinct functional modules: optical property measurement devices (spectrometers, ellipsometers), process parameter sensors (temperature, pressure, flow), and data processing units. Each module independently measures specific parameters and feeds data to the control system, reducing overall system complexity while maintaining comprehensive monitoring capability
Solution Approach 2:
The patent introduces an intermediary data processing layer that receives data from multiple sensors and measuring devices, processes this information through algorithms, and generates control signals. This intermediary layer abstracts the complexity from the control system, allowing simple proportional adjustments based on measured deviations without requiring complex integration of all sensor data
2Measurement precision
If multiple sensors and measuring devices are deployed for real-time data collection, then measurement precision is improved, but loss of time increases due to data collection and processing delays
Solution Approach 1:
The patent implements continuous real-time measurement and control where optical property measurements, process parameter monitoring, and parameter adjustments occur continuously without interruption. The control system continuously receives measurement data, calculates deviations from target values, and adjusts process parameters in an unbroken feedback loop, eliminating delays between measurement and correction
Solution Approach 2:
The patent replaces complex mechanical data processing systems with electronic and optical measurement systems coupled with computational algorithms. Optical properties are measured using spectrometers and ellipsometers that provide immediate electronic signals, which are then processed by computers running control algorithms, eliminating the time delays associated with manual or mechanical measurement and calculation methods
3Manufacturing precision
If feedback loops continuously adjust process parameters, then manufacturing precision is improved, but productivity decreases due to disruption and lag times
Solution Approach 1:
The patent implements a feedback control system where process parameters are continuously measured, compared to target values, and adjusted automatically based on the deviations. The control system uses feedback from optical property measurements and process parameter sensors to make real-time adjustments to deposition conditions, maintaining precision while enabling continuous production without manual intervention or production stoppages
Solution Approach 2:
The control system performs self-adjustment of process parameters based on measured deviations, eliminating the need for operator intervention. The system automatically detects parameter drifts, calculates required corrections, and implements adjustments to deposition parameters, allowing the coating process to self-correct and maintain precision throughout continuous production without disrupting workflow
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
Method for adjusting at least two parameters of a coating process to manufacture a coated transparent substrate comprising a multi-layered coating according to a targeted value for at least one quality function for said coated transparent substrate. The method relies on a set of different mathematical prediction models in the training step, which, once trained, when they are used either sequentially, alternatively or in parallel, during the prediction step, allow to counteract or counterbalance drifts that may potentially occur from one of them. Outstanding advantages are that misbehaviours of current feedback methods may be prevented, that changes in the local atmosphere of deposit cells, and in turn in the chemistry of coated layers, which may occur from temperature and/or humidity variation, may be compensated, and that more than one coating process parameters may be adjusted at the same time.