Facility Abnormality Detection With On-Site Feedback Model Updates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine learning-based abnormality determination systems for facilities lack accuracy due to insufficient feedback mechanisms that fail to reflect real-world conditions, leading to potential misdetection and false negatives.
Innovation Solution
An abnormality determination device and method that updates its detection model based on on-site evaluation results, integrating these real-world corrections to enhance accuracy by comparing determination outcomes with on-site checks and updating the model to reflect the real state of the facilities, thereby improving accuracy and reducing the burden on the worker's burden.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If machine learning is used for abnormality detection without feedback mechanisms, then automation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent implements a feedback mechanism where on-site checking results are fed back to update the abnormality detection model. The determination unit compares automated detection results with on-site checking results, and when discrepancies occur, the learning unit updates the model using the correct labels from on-site checks. This closed-loop feedback system continuously improves measurement precision while maintaining automation.
2Measurement precision
If on-site checking is performed for all cases, then measurement precision is improved, but productivity deteriorates
Solution Approach 1:
The patent applies partial action by performing on-site checking only when necessary - specifically when the determination unit identifies a discrepancy between automated detection results and expected outcomes. Rather than checking all cases, the system selectively applies on-site verification only to problematic cases, thereby maintaining high productivity while still improving measurement precision through targeted feedback.
3Measurement precision
If the abnormality detection model is updated frequently, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent implements self-service through an automated update mechanism where the learning unit autonomously updates the abnormality detection model based on feedback from the determination unit. The system automatically compares results, identifies discrepancies, retrieves correct labels, and updates the model without requiring manual intervention or complex external management systems, thereby limiting the increase in device complexity.
Data Source
AI summary
An abnormality determination device include: a learning unit configured to provide an abnormality detection model for detecting an abnormality of a facility by machine learning using log data that represent operation performance of the facility; a determination unit configured to input data representing operation performance of a target facility and determine an abnormality of the target facility; and an output unit configured to output a determination result by the determination unit. If the determination result is different from an evaluation result of an on-site checking of the target facility, the learning unit is configured to update the abnormality detection model based on the evaluation result.