Power Signal Wavelet Profiling for Predictive Failure Alerts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Equipment failures in electronic systems often occur without warning, leading to downtime, repair costs, and issues like misallocated energy accounting and unexpected equipment power off due to unclear connections to power feeds.
Innovation Solution
A power system that includes controllers with processors to receive power signals from monitored devices, perform discrete wavelet transforms (DWTs) on these signals, classify them into normal and atypical operational conditions, and generate alert signals when atypical conditions are met.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional monitoring methods are used, then equipment failure cannot be predicted, but implementing advanced signal processing increases system complexity
Solution Approach 1:
The patent extracts specific feature components from complex power signals using Discrete Wavelet Transform (DWT). The DWT decomposes the original signal into approximation coefficients (low-frequency trends) and detail coefficients (high-frequency variations), allowing the system to focus on specific diagnostic features rather than processing the entire complex signal, thus improving reliability while managing complexity.
Solution Approach 2:
The patent replaces traditional mechanical/electrical monitoring approaches with signal processing and machine learning algorithms. Instead of using complex hardware-based monitoring systems, the invention uses software-based DWT analysis combined with classification algorithms to predict equipment failures, reducing hardware complexity while maintaining or improving reliability.
2Measurement precision
If detailed power signal analysis is performed, then classification accuracy improves, but processing time increases
Solution Approach 1:
The patent extracts only the most diagnostically relevant features from power signals using DWT. By decomposing signals into approximation and detail coefficients at specific decomposition levels, the system identifies and analyzes only the critical frequency components that indicate equipment status, achieving high classification accuracy without processing unnecessary signal data, thus reducing processing time.
Solution Approach 2:
The patent performs preliminary signal decomposition and feature extraction using DWT before classification. By pre-processing signals to extract meaningful coefficients and store reference profiles for different equipment states, the system prepares data in advance for rapid classification, improving both accuracy and reducing real-time processing time.
3Reliability
If continuous monitoring of all devices is implemented, then failure detection capability improves, but energy consumption increases
Solution Approach 1:
The patent implements partial monitoring by focusing computational resources on analyzing only the most critical signal features rather than continuously processing entire signals at full resolution. The DWT decomposition allows the system to monitor at appropriate levels of detail - using approximation coefficients for overall trends and selectively analyzing detail coefficients only when anomalies are detected, reducing energy consumption while maintaining effective failure detection.
Solution Approach 2:
The monitoring system uses the existing power infrastructure and embedded controllers within devices to perform self-monitoring. The system leverages available power signal data without requiring additional dedicated monitoring hardware or excessive energy input, achieving reliable failure detection through intelligent analysis of routine operational signals.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A power system may receive power signals for one or more monitored devices, where a respective power signal includes at least one of a current or a voltage; perform discrete wavelet transforms (DWTs) of the power signals to generate DWT coefficients associated with the power signals; classify the power signals within two or more classes based on the DWT coefficients, where the two or more classes include one or more normal classes associated with one or more acceptable operational conditions and one or more atypical classes associated with one or more atypical operational conditions; and generate one or more alert signals based on the classified power signals when one or more alert conditions are met.