Die-Casting Quality Estimation Using Shot Time-Series Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies for product quality determination in injection molding and die-casting machines do not consider minute variations in operation states, such as injection speed and plunger position, leading to futile fabrication processing on defective products.
Innovation Solution
A product state estimation device that acquires and manipulates time series data from sensors to generate an estimation model using a neural network, considering both examination results and operation state data, enabling accurate quality estimation of products.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional quality determination methods are used that only check whether injection speed is between predetermined upper and lower limit waveforms, then the determination process is simple, but minute variations in operation state are not detected leading to reduced measurement precision
Solution Approach 1:
The patent transforms the quality determination approach by changing from simple waveform threshold comparison to comprehensive parameter analysis. Multiple parameters including injection speed, plunger position, and their temporal derivatives are analyzed together, allowing detection of minute variations that single-parameter threshold methods miss.
Solution Approach 2:
The patent replaces conventional mechanical quality control methods with machine learning-based estimation models. Neural networks and regression models process operational parameters to predict product quality, substituting physical measurement and inspection systems with computational intelligence that can detect subtle patterns.
2Measurement precision
If comprehensive time series data analysis with neural networks is implemented, then quality estimation accuracy is improved, but data processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary actions by pre-processing time series data during manufacturing operations. Data is collected, synchronized, and prepared in advance, allowing the estimation model to process information efficiently when quality determination is needed, reducing real-time computational burden.
Solution Approach 2:
The patent segments the quality estimation process into distinct functional modules: data acquisition, time series manipulation, model generation, and quality estimation. This segmentation allows parallel processing and optimization of each stage, reducing overall processing time while maintaining accuracy.
Data Source
AI summary
A product state estimation device includes: an examination result acquisition device that acquires an examination result related to a state of a product obtained through each shot by a die-casting machine; a time series data acquisition device that acquires time series data based on an output from a sensor that detects an operation state of the die-casting machine at each shot; a time series data manipulation device that performs manipulation that clips data of a predetermined time interval out of the time series data; an estimation model generation device that generates an estimation model by using a neural network with the examination result of the product and the manipulated time series data as learning data; and an estimation device that estimates information related to quality of the product based on the manipulated time series data obtained from a plurality of detection signals at each shot by using the estimation model.