Quality Determination Device for Changed Portions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing quality determination devices do not efficiently handle changes in the design or processes applied to a target object, leading to inefficiencies and potential inaccuracies in quality assessment when compared to previous determination models.
Innovation Solution
A determination device and method that utilize sensor data to identify changed portions of a target object, employing a learned determination model to assign labels and accept user inputs for quality determination, thereby distinguishing between unchanged and changed portions to optimize quality assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a determination model learned from training data is used to automatically determine quality of all target portions, then productivity is improved, but measurement precision deteriorates when the target object includes changed portions
Solution Approach 1:
The patent applies different determination approaches to different portions of the target object based on their characteristics. Changed portions are handled with manual determination while unchanged portions use automatic determination, optimizing both accuracy and efficiency for each region.
Solution Approach 2:
The patent segments the target object into changed portions and unchanged portions, applying different quality determination methods to each segment. This segmentation allows the system to maintain high accuracy for changed portions while preserving automated efficiency for unchanged portions.
2Measurement precision
If manual determination is performed for all target portions, then measurement precision is improved, but productivity deteriorates
Solution Approach 1:
The patent applies manual determination only partially - specifically to changed portions of the target object - rather than to all portions. This partial application of manual determination maintains accuracy where needed while preserving automated processing for the majority of unchanged portions, thus improving productivity compared to full manual determination.
3Adaptability or versatility
If the determination model is updated to accommodate design or process changes, then adaptability is improved, but device complexity increases
Solution Approach 1:
The patent performs preliminary identification of changed portions before quality determination. By detecting and flagging changed portions in advance, the system can apply appropriate determination methods without requiring complex real-time model updates, thus maintaining adaptability while controlling system complexity.
Data Source
AI summary
A determination device that determines quality of target portion based on sensor data obtained by a sensor measuring the target object, includes one or more processors configured to acquire sensor data representing the target portion, acquire information indicating a changed portion, determine whether the target portion includes the changed portion based on acquired information, determine a first label of the target portion represented in the sensor data by using a determination model learned from a training dataset based on training target portions, the first label representing target portion as one of good, defect, and a defect candidate, accept a second label of the target portion input via a user interface when the target portion includes the changed portion or when the first label of the target portion is determined as the defect candidate, and perform quality determination of the target portion based on the first label and/or the second label.