Active Clay Content Estimation Using Trained Machine Learning Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The measurement of active clay content in green sand is time-consuming, limiting the rate of the entire sand treatment cycle.
Innovation Solution
An active clay content estimation system using a trained model generated by machine learning, which takes information about mixed sand as input and estimates the active clay content, eliminating the need for real-time measurement during the sand treatment cycle.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional measurement techniques (absorptiometric analysis, washing method) are used to measure active clay content, then measurement accuracy is improved, but measurement time increases significantly
Solution Approach 1:
The patent creates a learned model that copies the relationship between sand properties and active clay content from training data. Instead of performing time-consuming physical measurements, the system uses the learned model to predict active clay content based on sand property measurements, achieving rapid estimation without sacrificing accuracy
Solution Approach 2:
The system performs preliminary action by collecting training data and constructing a learned model in advance. The model is trained using measurement data collected during the training phase, enabling rapid estimation during the actual sand treatment cycle without performing the full measurement process in real-time
2Measurement precision
If conventional measurement techniques are used, then active clay content can be determined accurately, but the sand treatment cycle rate decreases
Solution Approach 1:
The patent replaces the mechanical/chemical measurement system (absorptiometric analysis, washing methods) with an information processing system. The learned model processes sand property data to estimate active clay content, substituting physical measurement processes with computational estimation that does not slow down the sand treatment cycle
Solution Approach 2:
The learned model copies the relationship between sand properties and active clay content from training data, enabling rapid prediction during production without performing the actual measurement processes that would constrain the treatment cycle rate
Data Source
AI summary
This invention estimates an active clay content in mixed sand. A processor (51) of an information processing device (50) executes: an obtaining step of obtaining information concerning mixed sand with which green sand containing clay is mixed; and an estimating step of estimating an active clay content in the mixed sand in accordance with the obtained information concerning the mixed sand.