Journal of Aircraft · 1995 · 27 citations · 8 references
ComputingAerospace EngineeringComputer ScienceArtificial IntelligenceFlight MechanicsMachine LearningAircraft InstrumentationFault DetectionFlight SimulationHealth Monitoring SystemsNeural NetworksAircraft Network TopologyFlight Test EngineeringFlight TestingInstrumentation System DesignMachine Learning For Fault DetectionNetwork Topology EstimationNeural Network Modeling
During flight test programs, instrumented parameters degrade from wear and tear, and data from multiple flights are lost due to undetected instrumentation faults. The study proposes using artificial neural networks to estimate flight test data, aiming to reduce cost and wasted test flights. The authors used a simulation program to identify suitable network topologies and then verified the concept with actual flight test data from a business jet. The results show that while a single network cannot predict all suspect parameters, a collection of smaller networks can accurately estimate each parameter, and both simulation and real flight data confirm that these networks can detect instrumentation degradation.
During a flight test program, certain instrumented parameters are subject to degradation due to wear and tear. Over the course of a flight test program, data from several flights will be lost due to undetected instrumentation faults. The application of artificial neural networks as flight test data estimators has been proposed with the intention of reducing the aforementioned cost and wasted test flights. Several network topologies have been studied. A simulation program has been used to identify the appropriate network topology for this task. It is shown that a single network is not capable of predicting all of the correct values of the suspect parameters based solely on the information received from the reliable instruments. However, it is shown that a collection of smaller networks can succeed in this task, with each network predicting one suspect parameter. Limited training and test results based on simulation-generated data are presented. Actual flight test data from a typical business jet have been used to verify this concept and these results are presented as well. It is demonstrated that in most cases these networks are capable of predicting the measured parameter outputs with sufficient accuracy to enable identification of instrumentation system degradation.
8