Process Data Cause Diagnosis for Production Irregularities
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies for identifying the cause of abnormal irregularities in production facilities lack accuracy and efficiency, impacting safety, stability, quality, and cost.
Innovation Solution
An abnormal irregularity cause identifying device that acquires process data from sensors, calculates an abnormality degree, and uses causal relation information to diagnose the cause of irregularities, with the option to weight data based on type and magnitude, providing accurate likelihoods and possible causes for user recognition and action.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional abnormality cause identification methods are used, then the identification process can be performed, but the accuracy of identifying the cause is insufficient
Solution Approach 1:
The patent segments the cause identification process into multiple independent evaluation dimensions: abnormality degree calculation, criterion satisfaction assessment, and causal relation matching. Each dimension is evaluated separately and then integrated to determine the final cause accuracy, improving overall identification precision through systematic decomposition of the diagnostic process.
Solution Approach 2:
The patent introduces multiple adjustable parameters including abnormality degree thresholds, criterion satisfaction levels, and causal relation weights. By dynamically changing these parameters based on process data characteristics and abnormality patterns, the system adapts to different diagnostic scenarios and improves identification accuracy across varying operational conditions.
2Measurement precision
If multiple types of process data are analyzed to improve identification accuracy, then the accuracy of cause identification improves, but the complexity of the system increases
Solution Approach 1:
The patent divides multiple types of process data into distinct evaluation modules, each handling specific data types (e.g., temperature data, pressure data, flow data). Each module independently calculates abnormality degrees and criterion satisfaction for its designated data type, then results are aggregated. This segmentation allows comprehensive multi-parameter analysis while maintaining manageable system complexity through modular architecture.
Solution Approach 2:
The patent implements a universal evaluation framework that processes multiple types of process data through a common causal relation information structure. The same causal relation database and evaluation logic are applied across different data types, allowing the system to handle diverse sensors and parameters without requiring separate complex analysis paths for each data type.
3Measurement precision
If weighting coefficients are applied to different process data types to improve accuracy, then the precision of cause identification improves, but the complexity of calculation increases
Solution Approach 1:
The patent introduces weighting coefficients as adjustable parameters that reflect the relative importance and reliability of different process data types. These weights are applied systematically to abnormality degrees and criterion satisfaction scores from various sensors. The calculation complexity is managed by using standardized weighting formulas and pre-defined weight values based on process knowledge, transforming a potentially complex optimization problem into a manageable parameter adjustment task.
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, the pieces of process data, an abnormality determination unit that 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 obtains accuracy of a cause of the irregularity based on a proportion of process data having the abnormality degree calculated by the abnormality determination unit satisfying a predetermined criterion to the plurality of types of pieces of process data, by using causal relation information defining a combination between the cause and the irregularity, which appears as an influence resulting from the cause, of each of the plurality of types of pieces of process data.