Remote Optical Power Quality Disturbance Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies lack a non-invasive method to detect and classify power quality disturbances on electrical power grids, as existing systems require invasive hardware and cannot utilize optical sensing for remote detection and classification.
Innovation Solution
A remote optical sensing system that uses an optical source connected to the same power grid as a load, recording voltage and frequency changes to classify power quality disturbances through machine learning, specifically by extracting intensity and frequency responses and applying cross-covariance to identify features matching known classes of disturbances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If invasive electronic detection devices are inserted into power grid infrastructure to detect power quality disturbances, then detection capability is improved, but system complexity and intrusion into existing infrastructure increase
Solution Approach 1:
The patent replaces invasive electronic detection devices with optical cameras that use optical modulation techniques to remotely sense power quality disturbances. The system captures video of a light source connected to the power grid and extracts vibration signatures through optical sensing, eliminating the need to insert electronic hardware into the power infrastructure while maintaining disturbance detection capability
Solution Approach 2:
The patent introduces a light source as an intermediary element that connects the power grid to the detection system. The light source converts electrical power quality disturbances into optical signals that can be captured by the camera, serving as a non-invasive mediator between the power grid and the detection apparatus
2Ease of operation
If optical cameras are used for remote sensing of power quality disturbances, then non-invasive detection is achieved, but the ability to classify detected disturbances is lost
Solution Approach 1:
The patent implements a feedback loop where the optical camera captures video signals, the system extracts vibration signatures, compares them against a database of known disturbance patterns, and classifies the detected power quality disturbance. This feedback mechanism restores classification capability to the optical sensing system by continuously learning from and comparing against known disturbance characteristics
Solution Approach 2:
The patent performs preliminary action by pre-processing the video signals to extract vibration signatures before classification. The system prepares the raw optical data by filtering and transforming it into characteristic vibration patterns that can be efficiently compared and classified against known disturbance types
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables the non-invasive detection and classification of power quality disturbances, allowing for remote monitoring and utilization tracking of loads, which can be applied in the Internet of Things (IoT) for improved power grid management.
Implementation Method 1
Passive, remote-sensing, optical cameras have been recently shown to extract vibration signatures using optical modulation techniques
Data Source
AI summary
An optically detected power quality disturbance caused by a remote load is classified as belonging to a class of known classes of power quality disturbances. Features associated with different power quality disturbances that belong to a plurality of different known classes of power quality disturbances are learned. Cross-covariance is applied to the optically detected power quality disturbance and the different power quality disturbances that belong to the different known classes of power quality disturbances to recognize features of the optically detected power quality disturbance that at least partially match the learned features. The class of power quality disturbances among the plurality of classes of different known power quality disturbances to which the optically detected power quality disturbance belongs is determined based on the recognized features.