Cut tobacco drying process parameter selection method based on particle swarm optimization neural network

The invention discloses a cut tobacco drying process parameter selection method based on a particle swarm optimization neural network, and the method comprises the following steps: collecting cut tobacco drying process parameters to construct sample data, each sample comprising a group of cut tobacco drying process parameters and a cut tobacco quality probability corresponding to the group of process parameters; constructing a neural network, optimizing network parameters of the neural network by utilizing sample data, during optimization, initializing the network parameters into particle individuals, taking prediction errors of samples as individual fitness, optimizing the network parameters by adopting a particle swarm optimization algorithm, and taking the neural network with determined parameters as a process parameter selection model; and selecting cut tobacco drying process parameters by using the process parameter selection model. The method can quickly and accurately select the process parameters capa