In this paper, variable-weights neural network is proposed to construct variable cycle engine’s analytical redundancy, when all control variables and environmental variables are changing simultaneously, also accompan...In this paper, variable-weights neural network is proposed to construct variable cycle engine’s analytical redundancy, when all control variables and environmental variables are changing simultaneously, also accompanied with the whole engine’s degradation. In another word,variable-weights neural network is proposed to solve a multi-variable, strongly nonlinear, dynamic and time-varying problem. By making weights a function of input, variable-weights neural network’s nonlinear expressive capability is increased dramatically at the same time of decreasing the number of parameters. Results demonstrate that although variable-weights neural network and other algorithms excel in different analytical redundancy tasks, due to the fact that variableweights neural network’s calculation time is less than one fifth of other algorithms, the calculation efficiency of variable-weights neural network is five times more than other algorithms. Variableweights neural network not only provides critical variable-weights thought that could be applied in almost all machine learning methods, but also blazes a new way to apply deep learning methods to aeroengines.展开更多
基金National Natural Science Foundation of China(Nos.51576097 and 51976089)Foundation Strengthening Project of the Military Science and Technology Commission,China(No.2017-JCJQ-ZD047-21)。
文摘In this paper, variable-weights neural network is proposed to construct variable cycle engine’s analytical redundancy, when all control variables and environmental variables are changing simultaneously, also accompanied with the whole engine’s degradation. In another word,variable-weights neural network is proposed to solve a multi-variable, strongly nonlinear, dynamic and time-varying problem. By making weights a function of input, variable-weights neural network’s nonlinear expressive capability is increased dramatically at the same time of decreasing the number of parameters. Results demonstrate that although variable-weights neural network and other algorithms excel in different analytical redundancy tasks, due to the fact that variableweights neural network’s calculation time is less than one fifth of other algorithms, the calculation efficiency of variable-weights neural network is five times more than other algorithms. Variableweights neural network not only provides critical variable-weights thought that could be applied in almost all machine learning methods, but also blazes a new way to apply deep learning methods to aeroengines.
