A Flight Parameter-Based Aircraft Structural Load Monitoring Method Using a Genetic Algorithm Enhanced Extreme Learning Machine

High-precision operational flight loads are essential for monitoring fatigue of individual aircraft and usually determined by parameters. To tackle the nonlinear relationship between parameters more accurate prediction loads, artificial neural networks have been widely studied. However, there still two major problems, namely training strategy sensitivity analysis For first problem, gradient descent method is used, which time-consuming can easily converge to a local solution. solve this an extreme learning machine proposed determine weights based on Moore–Penrose generalized inverse. Moreover, genetic algorithm optimize input hidden layers. second mean impact value (MIV) measure parameters, neuron number in layer also optimized. Finally, measured dataset aircraft, load verified be effective efficient. In addition, comparison made with some well-known demonstrate advantages method.