Production Line Anomaly Detection With Dummy Status Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing anomaly determination methods in production management systems face challenges in accurately determining anomalies when input data exceeds or falls outside the allowable range, or when data is missing, leading to difficulties in performing anomaly determination processing.
Innovation Solution
The proposed method generates dummy operating status data based on planned production quantities and operation timepoints from adjacent processes, allowing for anomaly determination processing to continue even with data loss, by predicting a dummy operation timepoint using first and third operating status data when second data is missing, and vice versa.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If guard processing is performed to bring input data closer to the allowable range, then data accuracy is improved, but anomaly determination cannot be performed when no input data is input
Solution Approach 1:
The system performs preliminary actions by obtaining operating status data from multiple sources (first, second, and third production devices) before anomaly determination is needed. When data loss occurs at any stage, dummy data has already been prepared or can be quickly generated, ensuring anomaly determination can proceed without interruption.
Solution Approach 2:
Dummy operating status data acts as an intermediary element that bridges the gap when actual operating status data is lost or unavailable. The dummy data allows the anomaly determination process to continue by providing placeholder values that maintain the data flow and processing continuity.
2Measurement precision
If data is obtained from multiple production devices, then anomaly determination accuracy is improved, but data loss may occur during network transmission
Solution Approach 1:
The system prepares dummy operating status data in advance as a cushion against potential data loss during network transmission. When actual data fails to arrive, the dummy data serves as a pre-prepared backup that prevents processing interruption and maintains anomaly determination accuracy.
Solution Approach 2:
The system applies different data quality strategies to different data sources. For each production device, the system attempts to obtain actual operating status data, but has dummy data ready as a local fallback specific to each data source, ensuring that data loss in one location does not compromise overall anomaly determination.
3Reliability
If dummy operating status data is generated when data is lost, then anomaly determination can continue, but processing complexity increases
Solution Approach 1:
The system extracts and separates the dummy data generation function from the main anomaly determination process. By isolating the dummy data creation logic, the system can generate dummy data only when necessary (when actual data is lost) without adding continuous complexity to the normal processing flow.
Solution Approach 2:
The system performs self-service by automatically detecting data loss conditions and generating dummy operating status data without external intervention. The anomaly determination device monitors its own data inputs and autonomously decides when to use dummy data, simplifying the overall control structure.
Data Source
AI summary
An anomaly determination method, in a production management system that manages a production line including first, second, and third production devices, includes: obtaining, from among first, second, and third operating status data of the first, second, and third production devices, respectively, at least the first and third operating status data; when it is determined that the second operating status data was not obtained, predicting a dummy operation timepoint corresponding to a planned production quantity of the second production device, and generating dummy operating status data including the planned production quantity and the dummy operation timepoint; performing anomaly determination processing on production processes as a whole based on the first and third operating status data and the dummy operating status data; and outputting determination result information representing a result of the anomaly determination processing to display the determination result information on a display device included in the production management system.