Multi-Parameter Self-Learning Model for Root Cause Failure Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for monitoring electrical signals in machine-driven systems are inadequate for early detection and analysis of incipient failure modes, particularly in 3-phase electrical machines, as they fail to effectively visualize and diagnose deviations from normal behavior.
Innovation Solution
A multi-parameter self-learning machine application model that uses multi-function sensors to measure and analyze voltages and currents, calculating time-varying variables and their derivatives to identify root cause failures by comparing normal behavior to pattern differences, with features like auto-refining segment width and statistical evaluation for enhanced alarm confidence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If current monitoring methods are used for electrical signals in machine-driven systems, then the system complexity is low, but the ability to detect and analyze incipient failure modes is inadequate
Solution Approach 1:
The monitoring system segments the electrical signals into multiple parameters (voltage, current, power factor, reactive power, impedance) and analyzes each parameter separately. This segmentation allows the system to detect specific failure modes by examining individual parameter deviations while maintaining manageable system complexity through modular analysis approaches.
Solution Approach 2:
The system transforms conventional single-dimension monitoring into multi-dimensional analysis by simultaneously monitoring multiple electrical parameters and their derivatives. This dimensional expansion enables early detection of incipient failures through pattern recognition across multiple parameter spaces, significantly improving reliability while the structured approach keeps complexity manageable.
2Reliability
If multi-parameter monitoring is implemented to improve failure detection, then the reliability increases, but the device complexity increases
Solution Approach 1:
The monitoring system is designed with multi-functionality to handle multiple electrical parameters (voltage, current, power factor, reactive power, impedance) using a unified analysis framework. This universal approach improves failure detection accuracy across different machine types and failure modes while avoiding the complexity of separate specialized systems for each parameter.
Solution Approach 2:
The system performs preliminary learning and normalization of electrical signal patterns during normal operation before failure occurs. This preliminary action establishes baseline behavior for each parameter, enabling the system to detect deviations indicating incipient failures. This approach improves detection accuracy while managing complexity through pre-computed reference patterns.
3Measurement precision
If detailed analysis of electrical signals is performed to identify root cause failures, then the measurement precision improves, but the loss of time increases due to complex calculations
Solution Approach 1:
The system performs preliminary calculations of electrical parameters and their derivatives during normal operation, storing normalized patterns and baseline values. When a failure or anomaly occurs, the system compares real-time measurements against pre-computed references, enabling rapid root cause identification with high precision without requiring time-consuming complex calculations at the moment of failure detection.
4Reliability
If continuous monitoring of voltages and currents is implemented, then the reliability of failure detection improves, but the use of energy increases
Solution Approach 1:
The system implements partial continuous monitoring by continuously tracking key electrical parameters (voltage, current) while computing derived parameters (power factor, reactive power, impedance) only when deviations from baseline patterns are detected. This approach maintains high reliability for failure detection while reducing energy consumption by avoiding constant full-scale analysis of all parameters.
Data Source
AI summary
A method for identifying root cause failure in a multi-parameter self learning machine application model is presented. At least one multi-function sensor having the capability to measure at least one of a voltage and current of the machine application model is provided. The method includes measuring voltages and currents of a multi-phase load with the multi-function sensors in a passive manor and calculating at least one of a time-varying variable KW, PF, kVAr, or Z out of the measured voltages and currents. The method further provides calculating a first, second or third order derivative of the time-varying variable and classifying segments of at least one of the time-varying variables depending on a state. Then, a step of choosing at least one of the variables and learning their normal behavior is undertaken. Finally, normal behavior is compared to a pattern difference and a root-cause meaning to the pattern difference is identified.