Edge Computing for Passenger Boarding Bridge Docking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to automatically monitor operations areas, such as aircraft boarding gate areas, due to the need for high-bandwidth connectivity to centralized systems, which is often not available in remote locations.
Innovation Solution
A system comprising at least one camera and an edge computing device that processes image data to determine environmental states within operations areas, using machine learning models trained on data collected via low-bandwidth connections, and controls devices based on these determinations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If centralized systems are used for automated monitoring, then monitoring capability is improved, but connectivity requirement increases
Solution Approach 1:
The system segments the monitoring function by deploying edge computing devices at remote operations areas that can independently perform automated monitoring using machine learning models. These edge devices process image data locally and only transmit results or essential data to centralized systems, eliminating the need for continuous high-bandwidth connectivity while maintaining automated monitoring capabilities.
Solution Approach 2:
Edge computing devices serve as intermediaries between remote operations areas and centralized monitoring systems. These intermediaries perform local processing of image data using machine learning models, enabling automated monitoring at the edge while reducing the connectivity burden on the centralized system and the remote location.
2Measurement precision
If machine learning models are trained using centralized systems, then model accuracy is improved, but data transmission requirement increases
Solution Approach 1:
Machine learning models are pre-trained or pre-loaded onto edge computing devices before deployment to remote operations areas. This preliminary action enables the edge devices to perform accurate image processing and environmental state determination locally without needing to transmit large volumes of image data to centralized systems for processing.
Solution Approach 2:
The system creates copies of trained machine learning models and deploys them to edge computing devices at remote locations. These model copies enable local inference and processing, maintaining model accuracy while eliminating the need for continuous data transmission to centralized systems.
3Speed
If real-time processing is performed at centralized systems, then processing speed is improved, but connectivity requirement increases
Solution Approach 1:
The system segments the processing function by implementing real-time image processing and environmental state determination at edge computing devices located at remote operations areas. This segmentation enables local real-time processing without requiring continuous high-bandwidth connectivity to centralized systems, while centralized systems receive only essential data or results.
Data Source
AI summary
A system includes a non-transitory computer-readable medium having instructions stored thereon. The instructions, when executed by one or more processors, cause the one or more processors to acquire image data from one or more cameras, process the image data to determine whether a passenger boarding bridge is docked to an aircraft, determine whether an autolevel wheel of the passenger boarding bridge is in a stowed position or a deployed position where the autolevel wheel engages an exterior surface of the aircraft, and provide an alert in response to the passenger boarding bridge being docked to the aircraft and the autolevel wheel being in the stowed position.