Agricultural water conservancy scheduling method and system based on neural network technology

Abstract

The invention relates to the field of agricultural water resource scheduling, in particular to an agricultural water conservancy scheduling method and an agricultural water conservancy scheduling system based on a neural network technology. The method comprises the steps that a genetic algorithm is improved through a particle swarm algorithm, a plurality of monitoring sensors are arranged in an agricultural irrigation area, various environment data and various crop data of the area are monitored and processed, so that the initial weight and threshold value of a BP neural network are optimized,and a BP neural network prediction model of the improved genetic algorithm is established. The agricultural water conservancy resource scheduling method of the area is determined by outputting data predicted by the BP neural network model, and reasonable scheduling optimization and configuration of agricultural water conservancy resources are achieved. The model prediction output and the actual load value fitting degree are better, the prediction output stability is better, and large-amplitude fluctuation does not occur, that is, the agricultural water resource scheduling prediction method ismore reliable and more advantageous for agricultural water resource scheduling prediction.

Description

technical field [0001] The invention relates to the field of agricultural water resources dispatching, in particular to an agricultural water dispatching method and system based on neural network technology. Background technique [0002] Agriculture occupies a large proportion of the total water consumption of the national economy, and agricultural water plays a very important role in agricultural production. Therefore, estimating the water demand for agricultural development or predicting the future agricultural water consumption is of great importance for rational allocation and optimization. It is of great practical significance to dispatch limited water resources, improve the efficiency of water resource utilization, and promote the development of regional agricultural production. [0003] The prediction of agricultural water consumption is an important task for the rational planning and optimal allocation of water resources, and it is also the basic work for realizing t...

AI Technical Summary

Problems solved by technology

In the existing methods of dispatching agricultural water resources, especially in the vast rural areas, they basically belong to manual dispatching based on experience, and do not analyze and predict various agricultural data in local areas. Some scholars have proposed some mathematical models, mainly regional water balance method, neural network prediction method and gray theory method, each method has its own advantages and disadvantages

[0004] In the current methods for forecasting and dispatching agricultural water resources, all kinds of mathematical models are used to predict agricultural water consumption, but the principles of these models are relatively complicated and the operation is difficult. Relatively speaking, the BP neural network is not suitable for nonlinear loads. Data prediction has good fitting ability and is widely used, but BP neural network not only has a large amount of calculation and consumes a lot of time, but also has certain defects, such as: easy to fall into local minimum, slow convergence speed, initial weight, threshold Random assignment and network training shocks, etc. In the model of predicting agricultural water consumption using the neural network model improved by the genetic algorithm, because the crossover and mutation probability of the traditional genetic algorithm is constant, the group tends to stay in the local area during the training process. The optimal value, even if the prediction accuracy is improved, but there is insufficient local optimization ability, and it is easy to fall into defects such as early convergence; resulting in untimely and inaccurate agricultural water conservancy dispatching, etc.

Images