Cause Estimation Using Common-Cause Event Likelihoods
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cause estimation methods for events in social infrastructure systems, such as power generation facilities and industrial machines, suffer from decreased precision when multiple events occur due to a common cause, as they assume independent occurrences.
Innovation Solution
A cause estimation device and method that calculates the likelihood of events occurring due to a common cause, rewrites frequency information in a cause table to account for simultaneous events, and estimates the cause of occurrence based on the rewritten table and likelihood.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a plurality of events are assumed to occur independently for cause estimation, then the estimation process is simple, but the estimation precision decreases when events occur due to a common cause
Solution Approach 1:
The patent applies dynamics by making the event occurrence assumption flexible rather than fixed. The system dynamically adjusts between independent occurrence assumption and common cause assumption based on the actual event pattern observed. When multiple events occur simultaneously, the system switches to common cause assumption, thereby adapting the estimation model to the situation to maintain high precision without unnecessary complexity in normal cases.
Solution Approach 2:
The patent changes the fundamental parameter of event occurrence assumption from static (always independent) to variable (independent or common cause based on conditions). By introducing a conditional parameter that determines whether events are independent or share a common cause, the system achieves higher estimation precision while managing complexity through conditional logic rather than constant complex processing.
2Measurement precision
If the frequency in the cause table is not rewritten to account for common causes, then the cause table remains simple, but the cause estimation accuracy decreases when multiple events occur simultaneously
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing rewritten frequency information in the cause table that accounts for common cause relationships. During event analysis, the system directly uses these pre-prepared frequency values rather than performing complex real-time calculations, thereby achieving accurate cause estimation while keeping the processing mechanism relatively simple through advance preparation.
Solution Approach 2:
The cause table is made dynamic by incorporating frequency rewriting that adapts to different event occurrence patterns. The frequency values are adjusted based on whether events are determined to share a common cause, allowing the table to reflect the actual statistical relationships under different conditions and thereby improve estimation accuracy without requiring a completely complex structure.
Data Source
AI summary
A cause estimation device includes: an acquisition unit that acquires a measurement value of a target apparatus; a likelihood calculation unit that calculates, in a case where it is assumed that events occur due to a common cause, a likelihood of an occurrence of each of the events based on the measurement value; a table storage unit that stores a cause table in which a cause of occurrence of the event and a frequency of the cause of occurrence are associated with each other for each of the plurality of events; and an estimation unit that rewrites the frequency registered in the cause table into a frequency in the case where it is assumed that the plurality of events occur due to the common cause, and estimates the cause of occurrence based on the rewritten cause table and the likelihood.