Grain pile humidity and condensation prediction method based on depth time sequence

Abstract

The invention discloses a grain pile humidity and condensation prediction method based on a depth time sequence, and the method comprises the following steps: S1, collecting the initial data of a grain pile, and carrying out the normalization processing, and obtaining target data; s2, constructing first sequence sample points based on the target data in continuous time, and selecting a deep learning model of a time sequence through Bayesian optimization; s3, obtaining an extreme point of an expected improvement value of the first sequence sample point through a Gaussian process based on a deep learning model of the time sequence; and S4, taking the maximum value point as a second sequence sample point, repeating the steps S2-S3, and predicting the local humidity of the grain pile and judging whether the grain pile is dewed or not based on the deep learning model of the Bayesian optimization time sequence. According to the invention, the humidity of different positions of the grain pile at different storage times can be predicted, and a new thought is provided for finding the local high-humidity position of the grain pile, judging whether the local part of the grain pile is dewed or not, and taking measures such as ventilation and moisture dissipation.

Description

technical field [0001] The invention belongs to the field of grain storage, in particular to a method for predicting the humidity and condensation of grain piles based on depth time series. Background technique [0002] Condensation in the grain pile is due to the temperature difference in different positions of the grain pile, which leads to the microcirculation of the air in the pores of the grain pile. When the humidity increases, if the temperature difference is large, condensation will occur, which will cause the local moisture in the grain pile to increase, and then mildew, resulting in the loss of stored grain. When the seasons alternate, the temperature outside the warehouse and the upper space of the grain pile suddenly rises and falls suddenly. Since grain is a poor conductor of heat, there will be temperature differences between the surface and interior of the grain pile, and the sunny side and the backside of the grain pile, forming a temperature gradient. Make ...

AI Technical Summary

Problems solved by technology

And if you can't get the samples of the dew condensation part, you can't know that the dew condensation has taken place, and the determination of the moisture content of the grain samples needs a lot of manpower and material resources. Therefore, there is an urgent need

Images