Automatic Re-Feeding Decision System for Monocrystal Pulling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In the production of monocrystal pulling-up, the manual operation required for re-feeder declining is time-consuming and inefficient, lacking adequate safety and fool-proof protection, and automatic control of the declining process is not fully realized.
Innovation Solution
An automatic decision-making method for re-feeding is implemented using deep learning to process and analyze data from re-feeding nodes, establishing models for critical feeding quality, crystal position, and sensor weight, enabling real-time monitoring and control of the re-feeding process to determine reasonable parameters and detect abnormalities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual operation is used to control the re-feeder declining, then the operator can directly control the process, but it is time-consuming and inefficient
Solution Approach 1:
The system enables self-service by having the re-feeder automatically decline based on real-time monitoring of crystal position and feeding quality parameters. The control system autonomously decides when declining is needed and executes the action without manual intervention, allowing the system to serve itself in the re-feeding process.
Solution Approach 2:
The patent implements feedback mechanisms by continuously monitoring crystal position, feeding quality, and sensor weight data during the re-feeding process. This real-time feedback information is fed back to the control system, which automatically adjusts the re-feeder declining operation based on the actual process state, ensuring efficient and safe automated control.
2Reliability
If manual operation is used for re-feeder declining, then the operator has direct control, but safety and fool-proof protection are insufficient
Solution Approach 1:
The system continuously monitors multiple parameters including crystal position, feeding quality, and sensor weight during the re-feeding process. This real-time feedback enables the control system to detect abnormal conditions and automatically prevent unsafe operations, providing reliable safety protection without requiring manual intervention.
Solution Approach 2:
The patent establishes critical thresholds for feeding quality, crystal position, and sensor weight before the re-feeding process begins. These pre-set safety margins act as a cushion against abnormal conditions, allowing the automated system to prevent unsafe operations before they occur, thereby ensuring reliability and fool-proof protection.
3Productivity
If automatic control is implemented for re-feeding, then efficiency is improved, but system complexity increases
Solution Approach 1:
The control system is designed to automatically monitor and control the re-feeding process without requiring complex external intervention. The system self-regulates by processing its own sensor data and autonomously executing declining operations when conditions require it, simplifying the overall system architecture while maintaining high efficiency.
Data Source
AI summary
The present disclosure relates to automatic decision-making for re-feeding. Multi-dimensional data cleaning is performed and dimensional data warehouse is established by processing, filtering and converting basic source data of re-feeding nodes in a re-feeding process for monocrystal pulling-up into data sets easily identified and marked and establishing respective models based thereon. Basic source data of a current re-feeding nodes are obtained and converted into process parameters. The process parameters are compared with respective models in the dimensional data warehouse to obtain a first determination result. Data analysis is performed on the first determination result to determine whether an abnormality occurs in the current re-feeding process to obtain a second determination result. Decision is made automatically based on the second determination result.