An ELM Evaluation Model for Fighter Air Combat Effectiveness Against Gross Errors

A new air combat effectiveness evaluation model based on improved Extreme Learning Machine (ELM) is proposed to address the characteristics of two modern air combat modes: beyond visual range and close range. Firstly, an ELM based on M-estimation is introduced to resist the interference of gross errors in the sample data on ELM. Then, evaluate the combat effectiveness of fighter jets through the established model. Simulation shows that compared to ELM, the ELM method based on M estimation can achieve good accuracy after only 20 iterations and has strong resistance to gross errors, thus verifying its feasibility and effectiveness.