Control System for Adjustable Abnormality Detection Timing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing factory automation control systems lack the ability to adjust the time required for detecting abnormalities in control objects, which can lead to inefficiencies and inaccuracies in diagnosing equipment issues.
Innovation Solution
A factory automation control system that includes determination means to adjust the time for detecting abnormalities by using parameters such as the number of dimensions for feature quantities and the k value for calculating deviations, allowing for a trade-off between detection time and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the period of time for acquiring degree of deviation is extended to improve abnormality detection accuracy, then measurement precision is improved, but productivity deteriorates due to increased detection time
Solution Approach 1:
The system dynamically adjusts the parameter k (number of data points for deviation calculation) based on the execution cycle time. When the execution cycle is long, a larger k is used to improve accuracy; when the execution cycle is short, a smaller k is used to ensure timely detection. This dynamic adaptation resolves the contradiction between detection accuracy and detection speed.
Solution Approach 2:
The invention changes the parameter k (number of dimensions for feature quantities) to adapt to different execution cycle requirements. By determining k based on the execution cycle time, the system optimizes the balance between using sufficient data for accurate deviation calculation and maintaining fast detection response.
2Measurement precision
If the number of feature quantities (k value) is increased to improve detection accuracy, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system dynamically determines the parameter k based on the execution cycle time rather than using a fixed value. This dynamic determination optimizes the number of feature quantities used in deviation calculation, achieving high accuracy when time permits while reducing computational complexity when execution cycle is constrained.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A control system for detecting an abnormality occurring in a control object is provided. The control system (1) includes: feature quantity creating means (174) that creates a feature quantity from data which is acquired from the control object based on a first parameter associated with elements defining the feature quantity; deviation acquiring means (144) that acquires a degree of deviation between the feature quantity created by the feature quantity creating means and a group of feature quantities stored by a storage means based on a second parameter associated with a range in the group of feature quantities; abnormality detecting means (162) that detects an abnormality occurring in the control object based on the degree of deviation acquired by the deviation acquiring means and a threshold value; and instruction means (170) that instructs the deviation acquiring means to start execution based on an execution cycle of the deviation acquiring means.