Abnormality Detection System for Real-Time Production Delay Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing abnormality detection systems in production systems cannot detect abnormalities in real-time, as they only visualize the relationship between production steps after all steps have been completed, making it impossible to identify issues as they occur.
Innovation Solution
An abnormality detection system that includes a processor to store log data from production devices, calculate temporal relationships between devices, and display alarms when a reference time has elapsed, allowing for real-time detection and visualization of production delays or issues.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system displays the relationship between production steps after all steps have been completed, then the visualization of production relationships is achieved, but real-time abnormality detection is not possible
Solution Approach 1:
The system performs preliminary actions by storing log data from each production device as it is generated during the production process, rather than waiting for all steps to complete. The calculating unit continuously computes temporal relationships between devices based on stored log data, enabling real-time abnormality detection before the entire production process finishes.
Solution Approach 2:
The system implements feedback by continuously monitoring the temporal relationships between production devices and comparing them against expected values. When deviations are detected, the system provides immediate feedback through abnormality notifications, allowing for real-time adjustments and interventions in the production process.
2Productivity
If log data from multiple production devices is continuously monitored and temporal relationships are calculated in real-time, then real-time abnormality detection is enabled, but the system complexity increases
Solution Approach 1:
The system segments the monitoring task by assigning each production device its own log data storage and processing responsibilities. The calculating unit divides the temporal relationship calculation into discrete comparisons between adjacent devices in the production sequence, making the complex monitoring task manageable and scalable.
Solution Approach 2:
The calculating unit serves multiple functions: it stores log data, calculates temporal relationships, compares results against expected values, and generates abnormality notifications. This multi-functional approach consolidates what could be separate complex systems into a single integrated unit, reducing overall system complexity while maintaining real-time detection capabilities.
Data Source
AI summary
An abnormality detection system includes a processor configured to execute a process. The process includes: storing log data in a storage in which at least a production device number is associated with the event date and time; referring to the log data stored in the storage and calculating a temporal relationship between a first device and a second device that subsequently performs a process after the first device from among a plurality of production devices; detecting elapse of a reference time that is obtained from both the latest log data from among the pieces of log data related to the first device stored in the storage and the temporal relationship calculated at the calculating and that new log data related to the second device is not newly stored in the storage; and displaying an alarm when detection is obtained at the detecting.