Tool Lifetime Estimation Using Segmented Load Curves
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing tool lifetime estimation methods, such as those using machining information, face challenges in accurately predicting tool wear and maintenance timing, leading to potential production of defective products due to inadequate prediction accuracy.
Innovation Solution
An estimation model generation device that utilizes load curves indicating temporal or positional changes in the load applied to tools during machining, separating the load curve into first and second curves to generate an estimation model for predicting tool lifetime, with machine learning techniques applied to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machining information is used for tool lifetime estimation, then the estimation can be performed, but the prediction accuracy is insufficient leading to defective products
Solution Approach 1:
The load curve is segmented into multiple sections based on workpiece deformation stages. The estimation model separates the load curve into first load curves (during workpiece deformation) and second load curves (after deformation), extracting features from each segment to improve prediction accuracy and prevent defective products.
Solution Approach 2:
The invention changes the input parameters from general machining information to specific load curve parameters. By extracting features such as maximum load, average load, and load variations from segmented load curves, the model achieves more accurate tool lifetime prediction that directly impacts product quality.
2Measurement precision
If the load curve is used for estimation, then the sensitivity to tool wear improves, but the data processing complexity increases
Solution Approach 1:
The load curve data is segmented into meaningful sections corresponding to workpiece deformation stages. This segmentation simplifies feature extraction by focusing on specific phases (during and after deformation), improving tool wear detection sensitivity while managing data processing complexity through structured analysis.
Solution Approach 2:
The invention extracts key features from the load curve data, such as maximum load, average load, and load variations. By taking out only the essential parameters needed for tool wear detection rather than processing the entire raw data set, the model achieves high sensitivity while keeping processing complexity manageable.
Data Source
AI summary
Provided is an estimation model generation device configured to generate an estimation model for estimating a lifetime of a tool based on a load curve indicating temporal change or positional change of the load applied to the tool, the tool being used for repeatedly machining a plurality of workpieces in a plate-shape while applying the load to each of the plurality of workpieces, the estimation model generation device including: an information acquisition unit that acquires the load curve at a timing before the tool reaches the end of lifetime due to repeated machining using the tool; an estimation model generation unit that generates, based on load data and a tool lifetime, an estimation model for predicting the lifetime of the tool, the load data being obtained by separating the load curve into a first load curve and a second load curve.