Environmental Prediction in Cold Chain Transportation of Agricultural Products Based on K-Means++ and LSTM Neural Network

Experiments have proven that traditional prediction research methods limitations in practice. Proposing countermeasures for environmental changes is the key to optimal control of cold chain environment and reducing lag effects. In this paper, a transportation method, combining k-means++ long short-term memory (LSTM) neural network, proposed according characteristics agricultural products. The model can predict trend next ten minutes, which allows vehicle managers issue instructions equipment advance. fusion process temperature humidity data measured by multiple sensors performed with algorithm, then fused are fed into an LSTM network based on time series. error paper very satisfactory, root-mean-square (RMSE), mean absolute (MAE), squared (MSE), percentage (MAPE) R-squared 0.5707, 0.2484, 0.3258, 0.0312 0.9660, respectively, prediction, RMSE, MAE, MSE, 1.6015, 1.1770, 2.5648, 0.2736 0.9702, prediction. Finally, back propagation (BP) compared order enhance reliability results. terms effect vehicles transporting products, has higher accuracy than existing models provide strategic support fine management regulation environment.