AI-Based Series Arcing Detection in Hybrid-Electric Propulsion Buses
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Hybrid-electric and electric propulsion systems in aircraft often suffer from series arcing, which causes overheating, component damage, and performance issues, and is difficult to diagnose due to its intermittent nature.
Innovation Solution
A hybrid-electric propulsion system that includes a thermal engine, electric motor, battery, battery management unit, electrical distribution bus, artificial intelligence model, and a monitoring system controller. The AI model predicts operational parameters using electric motor data and determines the presence of series arcing by comparing actual and predicted parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional monitoring methods are used to detect series arcing, then the system structure remains simple, but the detection precision and reliability are insufficient due to the intermittent nature of arcing
Solution Approach 1:
The monitoring system segments the detection process into multiple independent modules: voltage signal acquisition module, current signal acquisition module, AI model module, and determination module. Each module performs a specific function, allowing the complex detection task to be divided into manageable parts that can be implemented and maintained separately while achieving high detection precision through coordinated operation
Solution Approach 2:
An AI model serves as an intermediary between the raw voltage and current signals and the final arcing determination. The AI model processes the input signals, identifies patterns indicative of series arcing, and outputs a determination result. This intermediary layer enables accurate detection of intermittent arcing events without requiring direct complex signal analysis in the monitoring logic
2Reliability
If AI models are used to predict operational parameters for detecting series arcing, then the detection reliability improves, but the computational power and processing time increase
Solution Approach 1:
The AI model processes only the specific voltage and current signals relevant to series arcing detection rather than analyzing all possible operational parameters. This partial action approach focuses computational resources on the critical signals needed for reliable arcing detection, avoiding unnecessary computational overhead from processing unrelated system parameters
Solution Approach 2:
The AI model is trained offline in advance with historical data to learn the patterns of series arcing. During actual operation, the trained model quickly processes real-time signals without requiring extensive real-time computation. This preliminary training action transfers computational burden from runtime to setup time, improving detection reliability while minimizing ongoing computational power requirements
Data Source
AI summary
A hybrid-electric propulsion system is provided that includes a thermal engine, an electric motor, a battery, a battery management unit (BMU), an electrical distribution bus, an artificial intelligence (AI) model, and a monitoring system (MS) controller. The electrical distribution bus electrically connects the electric motor and the BMU. The MS controller is in communication with the AI model, the electric motor, the BMU, and a memory storing instructions. The instructions when executed cause the MS controller to: receive a first operational parameter from the BMU unit; control the AI model to produce a predicted first operational parameter utilizing at least one electric motor operating parameter; and determine the presence of series arcing within the electrical distribution bus using the first operational parameter and the predicted first operational parameter.