Affiliations: [a] National Engineering Laboratory of Speech and Language Information Processing, China | [b] University of Science and Technology of China, Hefei, Anhui, China
Correspondence:
[*]
Corresponding author: Enhong Chen, University of Science and Technology of China, Hefei, Anhui, China. E-mail: [email protected].
Abstract: Stored-grain temperature is the most important factor in grain storage. According to the measured data, the temperature in the grain pile can be effectively predicted, which can find problems in advance, reduce grain loss and increase grain quality. Long Short-Term memory (LSTM) can perform better in longer sequences than ordinary RNN. This paper is applied to the analysis of big data of grain storage and the early warning of grain storage temperature. In this paper, the selected LSTM is optimized and the early warning model of grain situation is established, and the analysis steps of the early warning model are given. In order to verify the availability of the improved LSTM network structure, RNN and three variants were used to predict the grain temperature under the same conditions, the prediction effect of the improved CLSTM is better.
Keywords: LSTM, grain storage temperature, CLSTM, temperature prediction
