Aiming at the problem of insufficient greenhouse temperature prediction accuracy,a combined prediction model of improved sparrow search algorithm(ISSA)optimized extreme learning machine(ELM)was proposed.Considering the local optimal problem of the SSA algorithm,PWLCM chaos is introduced to initialize the sparrow population to improve the diversity of the popu-lation;at the same time,the adaptive t distribution mutation is used to enhance the exploration and development capabilities of the algorithm.The extreme learning machine network is used as an optimization function of the Sparrow search algorithm,and the input layer and hidden layer connection weights and hidden layer thresholds of the extreme learning machine are iteratively optimized,and the optimal values obtained are reconstructed and the ELM model is established.ISSA-ELM model for greenhouse temperature prediction.The simulation results show that the constructed ISSA-ELM model has better accuracy and effect in predicting green-house temperature than ELM,PSO-ELM and GWO-ELM models.
万方数据