On-Board Method for Helicopters Turboshaft Engines Neuro-Fuzzy Fuel Consumption Control

The focus of this research is the advancement of a neuro-fuzzy control method for managing the fuel consumption of helicopters turboshaft engines. This method employs an adaptive neuro-fuzzy system that incorporates the Sugeno fuzzy inference system in the structure of a five-layer neural network for direct signal propagation. As a result, it enables real-time control of helicopters turboshaft engines fuel consumption with an impressive accuracy of 99.2 %. It has been proven that the hybrid method training the neural network in 105 times less epochs than the backpropagation algorithm. Utilizing the neuro-fuzzy method to regulate the fuel consumption of helicopters turboshaft engines results in a reduction in both first and second type errors, ranging from 1.34 to 5.17 times when compared to alternative neural network architectures. Increasing the outputs number of the ANFIS neuro-fuzzy network and expanding the base of fuzzy rules makes it possible to improve the decision-making logic and, as a result, expand the range of rule activity levels calculating. The prospect of further research is the introduction of the developed methods and algorithms into a modified closed onboard helicopters turboshaft engines automatic control system.