Finish-Machining Amount Prediction for Accurate Single-Pass Machining
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In finish machining processes, achieving high accuracy is challenging due to deviations in machine components from reference positions, which are often corrected manually, leading to inconsistencies and reduced precision.
Innovation Solution
A computer-implemented finish-machining amount prediction method and apparatus using machine learning to automatically predict machining amounts based on measurement results, incorporating a learning section that calculates rewards and updates value functions to determine optimal machining actions, improving accuracy and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual finish machining is performed based on measurement results and worker experience, then machining accuracy can be improved, but machining time increases and consistency decreases
Solution Approach 1:
The system enables automated self-service machining by using the measurement device to automatically measure component deviations, the prediction device to calculate required machining amounts based on measured data and machine characteristics, and the machining device to execute the machining process without manual intervention, thereby reducing machining time while maintaining accuracy
Solution Approach 2:
The patent replaces the manual mechanical decision-making process with an automated information processing system that uses measurement data, machine characteristic data, and prediction algorithms to determine machining amounts, eliminating the need for worker experience-based judgments and reducing machining time
2Ease of operation
If manual determination of machining amounts is performed based on worker experience, then flexibility can be maintained, but machining precision decreases due to human error
Solution Approach 1:
The system implements automated feedback by measuring the actual machining results with the measurement device, comparing them with target specifications, and using this feedback to adjust and optimize subsequent machining operations, thereby improving precision while maintaining operational flexibility through programmable parameters
Solution Approach 2:
The patent substitutes human judgment with an automated prediction device that processes measurement data and machine characteristics to determine optimal machining amounts, eliminating human error while maintaining flexibility through programmable machine characteristics and adjustable parameters
3Measurement precision
If finish machining is performed on each part independently based on its deviation, then local accuracy can be achieved, but overall component accuracy deteriorates due to inter-part influences
Solution Approach 1:
The patent merges the processing of multiple parts by the prediction device, which considers not only individual part deviations but also the characteristics and interactions of all parts to be machined, thereby determining coordinated machining amounts that achieve both local and overall accuracy simultaneously
Solution Approach 2:
The prediction device serves multiple functions by processing measurement data from various parts, analyzing machine characteristics, predicting machining amounts for each part, and coordinating the overall machining strategy to account for inter-part influences, thereby achieving comprehensive accuracy
4Manufacturing precision
If repeated measurements and adjustments are performed to achieve high accuracy, then machining precision can be improved, but productivity decreases
Solution Approach 1:
The system performs preliminary action by using the prediction device to calculate the optimal machining amounts before actual machining begins, based on pre-acquired machine characteristic data and measured component deviations, thereby achieving high accuracy in a single pass without repeated measurements and adjustments
Solution Approach 2:
The patent replaces iterative manual measurement and adjustment cycles with a single automated prediction and machining process, where the prediction device calculates precise machining amounts in advance based on measurement data and machine characteristics, eliminating the need for repeated operations and improving productivity
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
A machine learning device of a finish-machining amount prediction apparatus observes, as state variables expressing a current state of an environment, finish-machining amount data indicating finish-machining amounts of the respective parts of a component and accuracy data indicating the accuracy of the respective parts of a machine, to which the component is attached. Then, the machine learning device acquires determination data indicating propriety determination results of the accuracy of the respective parts of the machine, to which the component after being subjected to finish machining is attached. After that, the machine learning device learns the finish-machining amounts of the respective parts of the component in association with the accuracy data by using the state variables and the determination data.