WIRELESS TECHNOLOGY CONTRIBUTION FOR AVIATION SAFETY

Introduction

Wireless communication gaining traction in aerospace for flight

safety

Replaces wiring to reduce weight, improve resilience and modularity

Critical for air-ground communication, aircraft monitoring and

tracking

Key Wireless Technologies

5G for high performance aviation communication networks

Augmented reality provides enhanced visualization and awareness

for pilots

AeroMACS for airport ground-aircraft communications and

operations

WAIC to reduce wiring by enabling wireless avionics intra-

communications

IoT sensors for condition monitoring and predictive maintenance

SWIM for efficient air traffic data exchange and information sharing

Challenges

Managing interference with aircraft systems like radar altimeters

Ensuring security, reliability and low latency for safety systems

Dealing with radio interference from ground stations

Energy efficiency of battery-powered wireless nodes

Performance degradation from weather, atmospheric factors

Conclusion

Safety critical for aviation industry growth and success

Wireless technologies can enable improvements but have concerns

Further research needed for robust solutions suited to aviation

environments

Key considerations: interference, security, reliability, environment

tolerance

Key Highlights

Wireless has potential to enhance flight safety, reduce costs

Overcoming interference, latency, security risks is vital

A wireless technology tailored for aviation can enable next

generation systems

More research required to develop optimal wireless solutions for

aircraft

UNIVERSAL THEORETICAL WIRELESS SIGNAL PROPAGATION

PREDICTION MODELLING

Introduction

Wireless networks becoming ubiquitous with growing demand

Various methods used for modeling wireless signal propagation

Traditional empirical models include One Slope, Dual Slope, Hata

etc.

AI methods like ANN, ANFIS being explored for prediction accuracy

Literature Review

Obstacles affect indoor/outdoor signal propagation differently

Neural networks transform inputs like distance, obstacles to RSSI

output

ANFIS combines neural networks and fuzzy logic for function

approximation

Has learning capability of neural networks and knowledge base of

fuzzy logic

ANFIS architecture has 5 layers - input, 3 hidden, output

Premise and consequent parameters modified during training

PSO optimizes ANFIS parameters based on swarm intelligence

Objectives

Compare PSO trained LOG10D-ANFIS, LOG10D-ANFIS and ANFIS

Obtain RSSI using One Slope and Two Ray Ground Reflection models

Analyze performance using RMSE and graphical comparisons

Conclusion

AI methods like PSO-ANFIS useful for accurate wireless signal

prediction

Enhances modeling of complex real-world radio propagation

environments

More research needed on integrating AI with empirical models

Key Highlights

ANFIS combines strengths of neural networks and fuzzy logic

systems

PSO provides efficient training of ANFIS parameters

Comparative study analyzes different ANFIS frameworks for RSSI

modeling

AI and computational intelligence crucial for future wireless

networks

Students also viewed