Catenary Icing Detection via Infrared Imaging and Deep Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting catenary icing in rail transit systems rely on manual judgment and video surveillance, which are inefficient due to limited human resources and are prone to errors from environmental light and background interference, making it challenging to accurately identify snow and thin ice.
Innovation Solution
A catenary icing detection method using infrared imaging and meteorological monitoring, which involves obtaining real-time infrared and visible light images, synchronizing meteorological data, and employing a deep learning model like MobileNetV3 for automatic identification of icing states, minimizing interference from environmental light and enabling non-contact measurement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual judgment based on weather conditions and video surveillance is used, then detection can be performed with simple equipment, but detection range and efficiency are limited due to human resources
Solution Approach 1:
The patent replaces manual visual inspection with an automated system combining infrared imaging sensors, visible light cameras, and deep learning algorithms. The infrared imaging sensor captures thermal radiation from the catenary, while the visible light camera provides complementary visual data. The deep learning model automatically analyzes these images to identify icing conditions, eliminating the need for manual judgment and significantly improving detection efficiency and coverage area.
2Measurement precision
If edge feature extraction algorithms are used for video surveillance, then automatic identification can be achieved, but accurate identification of snow and thin ice remains challenging due to environmental light and background interference
Solution Approach 1:
The patent introduces infrared imaging as an intermediary detection method that is not affected by visible light conditions. The infrared imaging sensor detects thermal radiation from the catenary surface, providing information about temperature and material properties that are independent of environmental lighting. This intermediary thermal data serves as a reliable basis for identifying snow and thin ice, overcoming the limitations of visible light-based methods.
Solution Approach 2:
The patent combines multiple detection modalities (infrared imaging, visible light imaging, and meteorological data) into a composite detection system. By fusing data from different sources with complementary characteristics, the system achieves more accurate and reliable identification of icing conditions than any single method could provide alone, effectively compensating for the weaknesses of individual detection approaches.
3Object-affected harmful factors
If infrared imaging is used to detect the target, then target brightness is improved and interference from environmental light is reduced, but additional equipment and data processing are required
Solution Approach 1:
The patent designs the detection system to perform multiple functions using integrated components. The dual imaging system (infrared and visible light) serves both independent detection purposes and complementary roles, where each sensor type can operate independently or in combination with the other. This multi-functionality justifies the additional equipment by providing robust detection capability across varying environmental conditions.
Solution Approach 2:
The patent merges infrared imaging data with visible light imaging data and meteorological monitoring data into a unified detection framework. By combining these data streams through data fusion techniques, the system creates a comprehensive view of the catenary condition that leverages the strengths of each data source while compensating for their individual limitations, making the additional equipment worthwhile.
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 allows for real-time, automatic identification of dry, wet, and icy states of catenary surfaces, improving detection reliability and reducing manpower requirements, while being minimally affected by visible light, enabling simultaneous detection of various states and providing real-time viewing and recording of current conditions.
Implementation Method 1
the infrared imaging sensor provides real-time images of the target
Implementation Method 2
obtain an infrared image and a visible light image in real time of a target catenary through a camera device
Implementation Method 3
the meteorological monitoring unit synchronously obtains meteorological data such as temperature, humidity, rainfall, snowfall, and wind speed
Implementation Method 4
through the deep learning model, the states of water accumulation, snow accumulation and icing of the target are automatically identified
Data Source
AI summary
The disclosure provides a catenary icing detection method based on infrared imaging and meteorological monitoring. In the disclosure, infrared illumination is used to detect the target, real-time images of the target are obtained through an infrared imaging sensor, and meteorological data are synchronously obtained through a meteorological monitoring unit, and normalized fusion processing is performed; the data are stored in a front-end edge computing unit, and through the deep learning model, the states of water accumulation, snow accumulation and icing of the target are automatically identified, and then sent to a background system through a transmission unit.