Abnormality Cause Identification Using Multi-Sensor Process Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in accurately identifying the cause of abnormal irregularities in production facilities, affecting safety, stability, quality, and cost, as they struggle to associate and analyze process data from multiple sensors effectively.
Innovation Solution
An abnormal irregularity cause identifying device that acquires process data from sensors, calculates an abnormality degree, and uses causal relation information to determine the cause of irregularities, associating data based on management numbers and synchronizing time-series data for improved accuracy and detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If process data from multiple sensors are analyzed to identify abnormal irregularity causes, then the accuracy of cause identification is improved, but the complexity of data association and analysis increases
Solution Approach 1:
The patent segments the complex data analysis task by introducing a management number as a segmentation key. Process data from multiple sensors are divided and associated based on matching management numbers, which represent specific processing targets. This segmentation approach breaks down the complex multi-sensor data association into manageable units that can be independently analyzed and then combined, resolving the contradiction between comprehensive analysis and system complexity.
2Measurement precision
If data association based on management numbers is implemented, then the accuracy of abnormality detection is improved, but the complexity of data processing increases
Solution Approach 1:
The patent applies preliminary action by pre-associating process data with management numbers before abnormality detection. The management number is embedded in the data structure in advance, creating pre-grouped data sets that are ready for analysis. This preliminary organization eliminates the need for complex real-time association algorithms during detection, thereby improving detection accuracy while keeping processing complexity manageable.
3Reliability
If multiple sensors continuously output process data, then the comprehensiveness of monitoring is improved, but the difficulty of detecting and measuring abnormal patterns increases
Solution Approach 1:
The patent introduces the management number as an intermediary element that connects process data from multiple sensors. Instead of directly analyzing complex multi-sensor data patterns, the system uses the management number as a mediator to group and correlate data from different sensors. This intermediary approach simplifies pattern detection by providing a common reference framework, thereby maintaining comprehensive monitoring while reducing the difficulty of detecting abnormal patterns.
Data Source
AI summary
An abnormal irregularity cause identifying device includes a process data acquisition unit that reads, from a storage device storing process data and each associated with a management number of a processing target, the pieces of process data, an abnormality determination unit that continuously calculates an abnormality degree representing an extent of an irregularity of process data of the pieces of process data read by the process data acquisition unit, and a cause diagnosis unit that determines, for each of the pieces of process data and corresponding to the management number of the processing target, whether the abnormality degree calculated by the abnormality determination unit satisfies a predetermined criterion by using causal relation information defining a combination between a cause and the irregularity, which appears as an influence resulting from the cause, of the process data.