Fish pond oxygen consumption prediction method

Abstract

The invention provides a fishpond oxygen consumption prediction method. The fishpond oxygen consumption prediction method comprises the following steps: acquiring a water oxygen concentration acquisition sequence at a preset interval; De-noising the oxygen concentration sequence to generate a neural network training sample; Training a preset neural network according to the neural network trainingsample to obtain an input and output mapping matrix; Wherein the neural network satisfies the following formula: x (n + 1) = W1u (n + 1) + W2x (n) + W3y (n); Wherein x and y are input and output respectively, W1, W2 and W3 are conversion matrixes between the input state and the internal state of the neural network and between the output state and the next internal state respectively, and the inputand output mapping matrix can determine the output uniquely according to the input; And predicting the subsequent oxygen concentration according to the neural network. According to the method, the purpose of predicting the oxygen consumption of the fish pond is achieved by constructing the neural network, optimizing the training samples and training the neural network for predicting the oxygen consumption based on the training samples.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a method for predicting oxygen consumption in fish ponds. Background technique [0002] The construction of the neural network is based on the premise of the application of the neural network. In the past ten years, the biological neural network system that simulates the biological neural network has excellent performance in the fields of identification, decision and prediction. The biological neural network has better intelligence and adaptability by simulating the biological neural network, but usually the completely random connection of each neuron in the neural network leads to a high degree of coupling inside the neural network and insufficient dynamic characteristics, resulting in The adaptiveness of the neural network is difficult to improve and the output error is difficult to reduce. [0003] Of course, neural networks with poor adaptability and large errors are also diff...

AI Technical Summary

Problems solved by technology

The biological neural network has better intelligence and adaptability by simulating the biological neural network, but usually the completely random connection of each neuron in the neural network leads to a high degree of coupling inside the neural network and insufficient dynamic characteristics, resulting in The adaptability of the neural network is difficult to improve and the output error is difficult to reduce

[0003] Of course, neural networks with poor adaptability and large errors are also difficult to use in the field of data prediction, which limits their application in fields such as environmental protection, breeding, and risk prevention and control.

Images