Sensor Causal Diagnosis for Production Irregularity Root Causes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to accurately identify the cause of abnormal irregularities in production facilities, which can impact safety, stability, and quality, leading to inefficiencies and increased costs.
Innovation Solution
An abnormality cause identifying device that utilizes process data acquisition, abnormality determination, and causal relation information to detect and diagnose the cause of irregularities by analyzing sensor data with techniques like autoencoders and machine learning algorithms, considering positive and negative divergence directions, and using knowledge bases for causal relations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional abnormality detection methods are used, then the system can detect abnormalities, but the accuracy of identifying the specific cause of abnormal irregularities is insufficient
Solution Approach 1:
The patent introduces causal relation information as an intermediary element that mediates between process data and abnormality causes. This causal relation information serves as a bridge that connects observed process data with potential causes, enabling more accurate cause identification by providing contextual relationships rather than relying solely on direct correlation analysis.
Solution Approach 2:
The patent adds a new dimension of analysis by incorporating causal relation information that defines hierarchical relationships along time series. This transforms the analysis from a single-dimensional correlation approach to a multi-dimensional framework that considers temporal hierarchy and causal relationships, thereby improving identification accuracy without losing critical causal information.
2Reliability
If multiple process data from multiple sensors are analyzed, then the detection coverage improves, but the complexity of analysis increases
Solution Approach 1:
The patent segments the complex analysis task by processing data from each sensor independently to determine abnormality degrees, then integrating results through causal relation information. This segmentation approach maintains high detection reliability by comprehensively analyzing multiple sensors while reducing overall complexity by breaking down the analysis into manageable per-sensor units that can be processed separately.
3Measurement precision
If the abnormality degree criterion is set strictly, then false positives are reduced, but the number of detected abnormalities decreases
Solution Approach 1:
The patent changes the evaluation parameter from simple abnormality degree threshold checking to a composite assessment that incorporates causal relation information. By transforming the determination criterion to consider hierarchical causal relationships, the system maintains high precision in abnormality determination while improving detection throughput by providing more comprehensive diagnostic information that reduces unnecessary follow-up investigations.
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 determines, for each of the pieces of 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 by using causal relation information defining a combination of a causal relation between a cause and the irregularity, which appears as an influence resulting from the cause, of the process data output by each of the plurality of sensors in a hierarchical manner along time series.