Innovative AI-Enhanced Ice Detection System Using Graphene-Based Sensors for Enhanced Aviation Safety and Efficiency

Area of Science:

• Aerospace Engineering
• Artificial Intelligence
• Materials Science

Background:

• Aircraft surface ice formation presents significant safety hazards.
• Existing ice detection systems lack real-time accuracy.
• Predictive maintenance is crucial for aviation safety.

Purpose of the Study:

• To develop and evaluate a smart ice control system leveraging machine learning.
• To improve the accuracy and real-time prediction of ice formation on aircraft.
• To optimize deicing processes and enhance flight safety.

Main Methods:

• Utilized a suite of machine learning models: Logistic Regression, Support Vector Machine, Random Forest, K-Means Clustering, and Multilayer Perceptron.
• Integrated various sensors for detecting temperature anomalies indicative of ice formation.
• Trained and tested models for predicting and identifying ice formation patterns.

Main Results:

• The developed smart system accurately predicts ice formation in real time.
• The system optimizes deicing operations, leading to reduced power consumption.
• Experimental results confirm enhanced safety through improved ice detection.

Conclusions:

• Machine learning-driven systems offer a robust solution for real-time ice detection.
• This technology has the potential to significantly improve aviation safety.
• The system is applicable to other industries needing predictive maintenance for ice-related issues.