Utility Pole Hazardous Event Localization via AI Fiber Optic Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current distributed fiber optic sensing systems are unable to effectively classify and localize hazardous events, such as impacts on utility poles, which are critical for timely service restoration and safety, especially in rural areas where manual localization is time-consuming and inefficient.
Innovation Solution
The integration of distributed fiber optic sensing with machine learning algorithms and AI engines to analyze vibration data from telecommunication fiber optic cables, enabling real-time identification and localization of hazardous events on utility poles with high accuracy (>90%) by employing a 'hammer test' for data collection and processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual localization methods are used for utility pole hazardous events, then system complexity is reduced, but response time and productivity deteriorate significantly
Solution Approach 1:
The patent replaces manual mechanical localization methods with an automated optical sensing system. DFOS technology uses laser pulses traveling through fiber optic cables to detect vibrations and strains caused by hazardous events, automatically identifying pole locations and event positions without human intervention, thereby dramatically improving response time while accepting increased system complexity
Solution Approach 2:
The system enables self-service localization by allowing the fiber optic cable itself to act as the sensing element. The cable detects vibrations and strains along its length and automatically provides location information, eliminating the need for external manual inspection equipment or personnel while achieving rapid event localization
2Measurement precision
If distributed fiber optic sensing is deployed without AI analysis, then device complexity is lower, but measurement precision and event localization accuracy deteriorate
Solution Approach 1:
The patent introduces an AI engine as an intermediary between the DFOS data collection system and the event localization output. The AI engine processes raw vibration and strain data, patterns event signatures, and determines precise pole and event locations, thereby achieving high measurement precision while managing the complexity through specialized algorithmic processing
Solution Approach 2:
The system transforms physical parameters (vibration frequency, strain magnitude, temporal patterns) detected by the DFOS system into actionable localization information through AI analysis. By changing and analyzing multiple parameters simultaneously, the system achieves precise event localization that would be impossible with single-parameter detection
3Loss of information
If comprehensive DFOS data collection is implemented, then information completeness improves, but data processing time and computational requirements increase
Solution Approach 1:
The patent implements preliminary action by pre-processing and filtering DFOS data as it is collected, using AI algorithms to immediately identify and flag potential hazardous events rather than analyzing all data comprehensively after collection. This approach maintains information completeness for confirmed events while reducing processing time by avoiding unnecessary analysis of normal conditions
Solution Approach 2:
The system applies partial action by focusing computational resources only on segments of the fiber optic cable where anomalies are detected, rather than processing the entire cable length uniformly. This selective analysis maintains complete information for affected areas while significantly reducing overall data processing time and computational requirements
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
This approach allows for rapid and accurate detection and localization of hazardous events on utility poles, ensuring quick service restoration and enhancing safety by automatically identifying affected poles and triggering alarms for dispatch, outperforming existing systems in accuracy and efficiency.
Implementation Method 1
sensing various physical parameters including temperature, vibration, strain
Implementation Method 2
sensing various physical parameters including temperature, vibration, strain
Data Source
AI summary
Distributed fiber optic sensing (DFOS) and artificial intelligence (AI) systems and methods for performing utility pole hazardous event localization that advantageously identify a utility pole that has undergone a hazardous event such as being struck by an automobile or other detectable impact. Systems and methods according to aspects of the present disclosure employ machine learning methodologies to uniquely identify an affected utility pole from a plurality of poles. Our systems and methods collect data using DFOS techniques in telecommunication fiber optic cable and use an AI engine to analyze the data collected for the event identification. The AI engine recognizes different vibration patterns when an event happens and advantageously localizes the event to a specific pole and location on the pole with high accuracy. The AI engine enables analyses of events in real-time with greater than 90% accuracy.