Aluminum Alloy Casting Mold Sensing for Real-Time Quality Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for predicting the production quality of aluminum alloy castings, particularly for complex structural parts, are inadequate as they rely on external indirect data and fail to accurately reflect quality changes, leading to low qualification rates and high reject rates.
Innovation Solution
Install sensors on the casting mold to collect direct process parameters such as temperature, pressure, and gas state data, and use an extreme gradient boosting algorithm to build a data mining-based prediction model that decouples the relationship between these parameters and casting quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If external indirect data (process parameters and equipment control parameters) are used for quality prediction, then the prediction system can be established, but the prediction accuracy is insufficient and cannot effectively reflect quality changes
Solution Approach 1:
The patent introduces internal direct data from sensors installed on the mold as an intermediary between the casting process and quality prediction. These sensors directly measure temperature, pressure, and other critical parameters within the mold cavity, providing more accurate and direct information about the actual casting process conditions compared to external indirect data.
Solution Approach 2:
The patent replaces the traditional mechanical approach of using external process parameters with a sensor-based measurement system that directly captures internal mold conditions. This substitution enables more precise quality prediction by directly measuring the actual state of the casting process rather than inferring from external parameters.
2Measurement precision
If sensors are installed on the mold to collect internal direct data, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The patent employs multi-functional sensors that can simultaneously measure multiple parameters (temperature, pressure, and other critical conditions) within the mold cavity. This multi-functionality reduces the total number of sensors needed while maintaining comprehensive monitoring capability, thereby limiting the increase in device complexity.
Solution Approach 2:
The patent focuses on measuring critical parameters that have the most significant impact on casting quality (temperature, pressure, etc.) rather than attempting to measure all possible parameters. This selective parameter monitoring approach simplifies the sensor installation while maintaining high prediction accuracy.
3Measurement precision
If comprehensive sensor monitoring is implemented, then the quality prediction accuracy improves, but the manufacturing cost increases
Solution Approach 1:
The patent selectively monitors only the critical parameters that have the most significant impact on casting quality (temperature, pressure, and key process conditions) rather than implementing comprehensive monitoring of all possible parameters. This targeted approach achieves high prediction accuracy while minimizing sensor costs and data processing requirements.
Data Source
AI summary
A data mining-based method for real-time production quality prediction of aluminum alloy casting, includes: (1) based on mold flow analysis results, installing sensors on a casting mold; wherein the sensors include at least one temperature sensor, at least one pressure sensor, at least one contact sensor, and a multi-functional gas sensor; (2) during casting production, real-time collecting temperatures, pressures, and contact times of the aluminum liquid at a plurality of locations of the casting mold, and pressure, composition, humidity, and temperature of gas in a mold cavity, by the installed sensors, for constructing an aluminum alloy casting process parameter set; and (3) inputting the process parameter set to a production quality prediction model; wherein the production quality prediction model is used to judge whether the production quality is qualified, which is obtained by mining a relationship between history casting process parameters and casting quality data.