Aircraft Cabin Experience Network With Modular Data Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Commercial aircraft onboard networks face computational limitations in processing sensor data for tasks like facial recognition, motion detection, and sensor fusion, due to limited processing power and interface constraints, making it difficult to integrate additional sensors and systems without high costs and certification challenges.
Innovation Solution
A Sensor Processing Unit (SPU) is introduced, resembling a Network Attached Storage device, with six parallel multi-core computers that offload computational tasks from the network server, enabling real-time processing of sensor data for applications such as facial recognition, sensor fusion, and data logging, while maintaining compatibility with existing aircraft wiring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If additional sensors and processing capabilities are integrated into the aircraft, then sensor fusion capability and processing power are improved, but device complexity and certification requirements increase
Solution Approach 1:
The patent divides the aircraft's computational system into separate functional units: existing federated computers handle traditional avionics tasks, while new onboard sensors and processing units are added as independent modules. This segmentation allows each component to be certified and integrated separately, reducing overall system complexity while maintaining enhanced processing capabilities for sensor fusion and facial recognition.
Solution Approach 2:
The patent implements universal interface standards and communication protocols that allow different sensor types and processing units to interoperate through common interfaces. This multi-functionality enables the system to handle various sensor inputs (cameras, LIDAR, acoustic sensors) and processing tasks (facial recognition, motion detection, sensor fusion) through a unified architecture, reducing the need for specialized dedicated systems.
2Adaptability or versatility
If more sensors are integrated into the aircraft, then sensor fusion capability is improved, but interface ports and wiring requirements increase
Solution Approach 1:
The patent employs universal interface standards and communication bus architectures that allow multiple sensor types to connect through standardized ports. This approach enables diverse sensors (visual, acoustic, LIDAR) to be integrated without requiring unique wiring harnesses for each sensor type, thereby increasing adaptability while controlling wiring complexity.
Solution Approach 2:
The patent introduces intermediary processing units and communication buses that act as mediators between multiple sensors and the central avionics system. These intermediaries aggregate sensor data and manage communication protocols, reducing the direct wiring requirements between each sensor and the main system while maintaining versatile sensor integration capability.
3Power
If sensor data is processed off-board, then processing power requirements are reduced, but communication bandwidth limits are exceeded
Solution Approach 1:
The patent extracts and performs computationally intensive processing tasks (facial recognition, sensor fusion, motion analysis) locally on-board using dedicated processing units and federated computers. This extraction of processing functions from potential off-board systems eliminates the need to transmit large volumes of raw sensor data through limited bandwidth communication channels, as only processed results need to be communicated.
4Reliability
If federated sensor systems are used, then functional dedication is improved, but expandability and integration ease are reduced
Solution Approach 1:
The patent segments the sensor system into independent functional modules where each federated sensor unit maintains its dedicated function for reliability, while the modular architecture allows easy addition and integration of new sensor types. Each module can be certified and validated independently, preserving functional reliability while enabling system expandability through standardized interfaces.
Data Source
Figure 1A
Figure 1B
Figure 2A
AI summary
A computer-implemented method of processing raw sensor data in an Aviation Internet of Things (AloT) system is provided. The computer-implemented method comprises obtaining, by a network interface of a sensor processing unit (SPU), raw sensor data from one or more systems of a vehicle; providing, by the network interface, the raw sensor data to one or more processing units of the SPU; performing, by the one or more processing units, one or more processing tasks on the raw sensor data to produce processed data; and providing, by the network interface, the processed data to the one or more systems.