Glass Tempering Edge Quality Control With Self-Correcting Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The process of creating tempered glass is highly manual and requires constant monitoring and adjustment, leading to inefficiencies and defects in the glass tempering process.
Innovation Solution
A computing device integrates sensors throughout the glass tempering system to measure various aspects of the glass, applying machine learning models to detect defects and automatically adjust operation parameters to optimize the process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual monitoring and adjustment is used in glass tempering, then operators can make real-time decisions, but the process requires constant human intervention and is inefficient
Solution Approach 1:
The glass tempering system automatically monitors its own parameters (temperature, humidity, production speed) and adjusts operation parameters without human intervention. The system serves itself by using sensors and machine learning models to detect defects and autonomously optimize the tempering process, eliminating the need for constant manual monitoring while maintaining high productivity
Solution Approach 2:
Manual mechanical monitoring and adjustment by operators is replaced with an automated computational system. Sensors capture process data, machine learning models analyze the information to detect defects, and the system automatically adjusts operation parameters, substituting human mechanical intervention with an intelligent automated control system
2Measurement precision
If manual inspection is used to monitor glass quality, then defects can be detected, but the process is time-consuming and prone to human error
Solution Approach 1:
Manual visual inspection by operators is replaced with an automated optical inspection system. Sensors capture images of the glass throughout the tempering process, and machine learning models automatically analyze these images to detect defects with high precision. This automated system eliminates human error and operates continuously without fatigue, providing faster and more accurate defect detection
Solution Approach 2:
The inspection process becomes continuous rather than periodic. Sensors monitor glass quality throughout the entire tempering process, and the machine learning model continuously analyzes data to detect defects in real-time. This continuous monitoring eliminates the time loss associated with periodic manual inspections and ensures consistent detection accuracy throughout production
3Manufacturing precision
If frequent adjustments are made to operation parameters, then glass quality improves, but the complexity of controlling multiple parameters increases
Solution Approach 1:
The control system integrates multiple functions into a single unified platform. The machine learning model simultaneously analyzes multiple sensor inputs (temperature, humidity, production speed, glass appearance) and coordinates adjustments across multiple operation parameters. This multi-functional system manages the complexity of controlling numerous parameters while maintaining consistent glass quality through centralized intelligent control
Solution Approach 2:
The system implements closed-loop feedback control where sensors continuously monitor operation parameters and glass quality, the machine learning model analyzes this feedback data to detect defects, and the system automatically adjusts parameters based on the analysis. This feedback mechanism enables frequent precise adjustments while managing complexity through automated decision-making algorithms
4Loss of substance
If manual processes are used for glass tempering, then flexibility in handling different glass types is maintained, but waste increases due to lack of real-time optimization
Solution Approach 1:
The machine learning model dynamically adjusts operation parameters (temperature, humidity, production speed, tempering time) based on real-time sensor data and the specific characteristics of each glass batch. This parameter optimization minimizes defects and waste while maintaining the ability to adapt to different glass types, thicknesses, and compositions through automated parameter tuning rather than manual process changes
Data Source
AI summary
This disclosure is directed to techniques for utilizing various sensors and models to evaluate glass as it progresses through the tempering process in order to ensure that the tempered glass is of a proper quality. If, according to any of the various sensor measurements, the tempered glass is not of a proper quality, the system may automatically adjust one or more settings in any of the various components of the system in order to bring future panes of tempered glass back to having the proper quality. The system can measure for any number of glass characteristics or system characteristics, including edge quality, vertical flatness, haze, washing process variables, thermal imaging, distortion, blower information, production data, and furnace process data.