Machine Fault Recognition Through Parameter Correlation Corridors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods fail to effectively recognize fault states in machines or processes due to the inability to accurately detect deviations in parameter correlations, leading to inefficiencies and potential damage.
Innovation Solution
An apparatus and method that detect actual values of process parameters, define target correlations, and recognize fault states by determining if actual correlations lie outside predefined corridors, using mean values and standard deviations to identify deviations in parameter pairs or groups.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current methods are used to detect parameter deviations, then detection simplicity is maintained, but fault recognition accuracy deteriorates
Solution Approach 1:
The system predefines target correlations and corridors for parameter relationships before actual operation. This preliminary setup includes establishing mean values and standard deviations for parameter pairs, creating reference frameworks that enable accurate fault detection during runtime without requiring complex real-time analysis
Solution Approach 2:
The patent introduces corridors as intermediary reference ranges between actual parameter values and target correlations. These corridors act as mediators that simplify comparison by providing acceptable deviation ranges, making fault detection more accurate without requiring overly complex analysis methods
2Reliability
If parameter correlations are monitored in real-time, then fault detection timeliness is improved, but computational load increases
Solution Approach 1:
The system segments parameter monitoring into multiple independent pairs or groups, each with its own predefined target correlation and corridor. This segmentation allows parallel processing of simpler comparisons rather than requiring complex holistic analysis, improving detection timeliness while managing computational load through divided tasks
Solution Approach 2:
The patent transforms the monitoring approach by changing from absolute parameter value monitoring to relative correlation monitoring. By focusing on relationships between parameters rather than individual values, the system achieves timely fault detection with reduced computational requirements, as correlation deviations are often more sensitive and easier to detect
3Reliability
If multiple parameter pairs are analyzed, then fault detection completeness is improved, but system complexity increases
Solution Approach 1:
The system divides parameter monitoring into multiple independent pairs or groups, each analyzed separately with its own target correlation and corridor. This segmentation enables comprehensive fault detection across all parameters while maintaining manageable complexity through modular, independent analysis units that can be processed in parallel
Data Source
AI summary
A method and apparatus (100) for recognizing a fault state of a machine (102) or of a process is disclosed. The apparatus (100) is configured to detect actual values of parameters of the process at the machine (102) for carrying out the process. The parameters include at least one controllable process parameter (204) of the process, at least one non-controllable process parameter (206) of the process or at least one control parameter (202) for controlling the or another controllable process parameter (204) in the process. The apparatus (100) is configured to predefine a target correlation for actual values of at least two of the parameters, to determine an actual correlation depending on the actual values of the at least two of the parameters, and to recognize a fault state of the machine (102) or of the process depending on the actual correlation and the target correlation.