Abnormality Cause Identification Using Residence-Time Data Linking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in accurately identifying the cause of abnormal irregularities in production facilities, particularly in associating process data from batch and continuous stages, which affects the accuracy of abnormality detection and cause identification.
Innovation Solution
An abnormal irregularity cause identifying device that acquires and preprocesses process data from sensors, using residence time to associate data between stages, and employs causal relation information and neural network models to calculate an abnormality degree, improving the accuracy of abnormality detection and cause identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If process data from batch and continuous stages are analyzed separately, then the analysis is simple, but the accuracy of abnormality cause identification deteriorates
Solution Approach 1:
The patent introduces an intermediary mechanism (preprocessing unit with residence time calculation) that mediates between batch stage data and continuous stage data. This intermediary calculates the residence time of processing targets and uses it to accurately associate process data across the two stages, enabling precise abnormality cause identification without excessive complexity
Solution Approach 2:
The patent segments the production facility into distinct batch stage and continuous stage, with dedicated processing units for each stage. The preprocessing unit then acts as a bridge that segments the data association task into manageable steps: reading batch data, reading continuous data, calculating residence time, and associating the data based on this time parameter
2Measurement precision
If residence time is used to associate process data between stages, then data association accuracy is improved, but calculation complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing the residence time of processing targets in the preprocessing unit before performing data association. This preliminary calculation of residence time serves as a ready-made key that simplifies the subsequent data matching process, improving association accuracy while managing complexity through advance preparation
3Measurement precision
If causal relation information is used for each sensor data, then cause identification accuracy is improved, but processing time increases
Solution Approach 1:
The patent applies partial action by focusing causal relation information application only on the associated process data that is relevant to the abnormality being diagnosed. Rather than processing all sensor data equally, the system selectively applies causal relations to the specific data points that have been associated through the residence time mechanism, improving efficiency while maintaining accuracy
Data Source
AI summary
An abnormal irregularity cause identifying device includes a process data acquisition unit that reads process data output by sensors included in a production facility performing a batch stage and a continuous stage, a preprocessing unit that associates a range of a complete timing of the batch stage with an output timing of process data of the process data in the continuous stage based on a residence time of the processing target in the production facility, an abnormality determination unit that calculates an abnormality degree by using process data in the batch stage and process data in the continuous stage associated with each other by the preprocessing unit, and a cause diagnosis unit that determines, for each of the process data output by the corresponding one of the plurality of sensors, whether the abnormality degree calculated by the abnormality determination unit satisfies a predetermined criterion.