Sensor Fusion for Underground Conduit Void Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Buried pipe and conduit systems deteriorate over time, leading to inaccurate structural integrity assessments, resulting in costly misallocation of repair resources and potential safety hazards due to incorrect identification of critical infrastructure needs.
Innovation Solution
A robotic transporter with a radar transmitter/receiver unit and secondary sensors, such as cameras and laser profilers, is used to gather data from underground conduits, employing sensor fusion algorithms like Bayesian networks to enhance data reliability and distinguish between true and false void detections.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple sensors are used to assess buried structures, then measurement precision and reliability are improved, but device complexity increases
Solution Approach 1:
The patent combines multiple sensor types (radar, cameras, laser profilers, accelerometers, gyroscopes) into a single integrated inspection system mounted on a robotic crawler. This merging of sensors allows simultaneous data collection from multiple sources, improving measurement precision while managing device complexity through integrated hardware and software architecture.
Solution Approach 2:
The inspection system is designed with multi-functional sensors that can detect various conditions (structural defects, voids, deformations) using different sensing modalities. The sensor fusion framework processes data from all sensors through a common algorithmic structure, making the system universally applicable to different buried structure assessment scenarios while maintaining manageable complexity.
2Reliability
If sensor fusion algorithms are employed to distinguish true and false void detections, then reliability is improved, but loss of time in data processing increases
Solution Approach 1:
The sensor fusion framework performs preliminary data processing and correlation during the inspection operation itself, rather than waiting for post-processing. The system continuously fuses sensor data in real-time, establishing baseline correlations between different sensor readings that can quickly identify true voids versus false positives, reducing overall processing time while maintaining high reliability.
Solution Approach 2:
The system uses feedback from multiple sensor sources to continuously refine void detection accuracy. When one sensor detects a potential void, the framework cross-validates with other sensor data streams, providing immediate feedback that confirms or refutes the detection. This feedback mechanism improves reliability while keeping processing time manageable through efficient algorithms.
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 method provides accurate and reliable condition assessments of underground conduits, reducing costly misallocations and enhancing safety by distinguishing between actual defects and false indications, thereby optimizing infrastructure maintenance and repair efforts.
Implementation Method 1
a radar transmitter/receiver unit capable of transmitting a pulsed signal toward the inner wall of the conduit
Data Source
AI summary
A method of surveying the condition of an underground conduit by positioning a propelled carriage assembly within the underground conduit. The carriage assembly includes (i) at least one transmitter/receiver unit capable of transmitting a pulsed signal toward at least a portion of an inner wall of the conduit, and (ii) a secondary sensor positioned on the carriage assembly. The data derived from the pulsed signal at a given lateral location within an underground conduit is read as is a secondary sensor condition derived from secondary sensor data taken at the given lateral location. Then it is determined whether the secondary sensor condition indicates a basis for a false void detection by the data derived from the pulsed signal and if the basis for false void detection exists, providing an indication of such basis.