Finish-Machining Amount Prediction for Accurate Single-Pass Machining

Resolve Bottlenecks,
Find Innovative Solutions
Generate 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

VSEngineering 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

Engineering Contradiction:
Improvemachining accuracyVSAvoidmachining time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

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

Inventive Principle:
Principle #25Self-service

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

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

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

Engineering Contradiction:
Improveoperational flexibilityVSAvoidmachining precision
Core Design Contradiction:
Ease of operationVSManufacturing precision

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

Inventive Principle:
Principle #23Feedback

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

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

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

Engineering Contradiction:
Improvelocal measurement accuracyVSAvoidoverall component accuracy
Core Design Contradiction:
Measurement precisionVSManufacturing precision

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

Inventive Principle:
Principle #5Merging (Combining)

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

Inventive Principle:
Principle #6Universality (Multi-functionality)

4Manufacturing precision

If repeated measurements and adjustments are performed to achieve high accuracy, then machining precision can be improved, but productivity decreases

Engineering Contradiction:
Improvemachining precisionVSAvoidmachining speed
Core Design Contradiction:
Manufacturing precisionVSProductivity

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

Inventive Principle:
Principle #10Preliminary action

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

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP3372342B1Finish-machining amount prediction apparatus and method
Publication Date: 2021.08.25 FANUC LTD
  • EP3372342B1 patent drawingFigure 1~2
  • EP3372342B1 patent drawingFigure 3
  • EP3372342B1 patent drawingFigure 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.