Visual Sensor Abnormality Cause Estimation via Environmental Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing visual sensor abnormality detection systems struggle to quickly identify the cause of abnormalities in production systems, particularly when issues arise from changes in the ambient environment, making it difficult to restore production devices to a normal state efficiently.
Innovation Solution
A visual sensor abnormality cause estimation system that acquires environment information and estimates the strength of correlation between abnormalities and potential cause items using machine learning algorithms, displaying the results to facilitate quick identification of the most likely cause.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional abnormality detection methods are used, then abnormalities in visual sensors can be detected, but the specific cause of abnormalities cannot be quickly identified, especially when caused by ambient environment changes
Solution Approach 1:
The system performs preliminary actions by acquiring environment information (temperature, humidity, vibration, etc.) continuously before abnormalities occur and storing it as baseline data. When an abnormality is detected, the system compares current environment information with the pre-acquired baseline to quickly identify cause items, eliminating the need for time-consuming round-robin checking during actual troubleshooting
Solution Approach 2:
The system introduces environment information (temperature, humidity, vibration, illumination, etc.) as an intermediary variable that mediates between the visual sensor abnormality and its cause. By measuring these environmental parameters and calculating their correlation with the abnormality, the system can identify the specific cause item without directly observing the complex failure mode
2Reliability
If round-robin method is used to check presumed causes, then all possible causes can be investigated, but it takes considerable time for the production device to return to normal state
Solution Approach 1:
The system replaces the mechanical round-robin checking process with an information processing system that automatically calculates correlation strengths between environment information and abnormalities. Instead of manually checking each presumed cause in sequence, the system uses automated correlation analysis to rank cause items by likelihood, enabling rapid identification of the primary cause without sacrificing investigative thoroughness
3Reliability
If visual sensor abnormalities are monitored continuously, then sensor state can be tracked, but causal dependency between specific events and abnormalities cannot be determined when abnormalities occur after short delay
Solution Approach 1:
The system implements feedback by continuously acquiring environment information, detecting abnormalities, calculating correlation strengths, and identifying cause items. This closed-loop feedback mechanism ensures that even when abnormalities occur with short delays after triggering events, the system can trace back through the recorded environment information to establish causal relationships based on correlation analysis
Data Source
AI summary
A camera abnormality cause estimation system for estimating the causes of abnormalities in a camera in a production system in which the camera controls a robot. The production system includes a robot, a camera that detects visual information of the robot or the surrounding thereof, and a controller that controls the robot based on an image signal obtained by the camera. The camera abnormality cause estimation system estimates the causes of abnormalities in the camera and includes an environment information acquisition unit that acquires environment information of the camera, and an abnormality cause estimation unit that estimates a probability that each of a plurality of predetermined abnormality cause items is the cause of an abnormality in the camera for the respective abnormality cause items using the environment information acquired by the environment information acquisition means and displays the estimated probability on a display unit for the respective abnormality cause items.