Dendrobium candidum growth environment prediction method

The present invention relates to a dendrobium candidum growth environment prediction method. The method comprises the steps of a growth environment prediction model and an improved BP neural network.The growth environment prediction model comprises normalizing the obtained parameters, so that the neural network has good fitting effect on the samples; and the improved BP neural network comprises that a primary fuzzy controller processes an input error signal e(n) and a secondary fuzzy controller processes the input error change rate (as shown in the specification). The beneficial effects of the method provided by the present invention are that: the present invention provides an improved BP neural network algorithm for plant growth environment prediction, and the improved BP neural networkovercomes the defect of a slow convergence rate of the traditional BP neural network and changes the step length, so that the adaptive variable step length is implemented by using the fuzzy control according to the growth envi