Open AccessPiggery Ammonia Concentration Prediction Method Based on CNN-GRU
Author(s) -
Kai Wang,
Chunhong Liu,
Qingling Duan
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1624/4/042055
Subject(s) - ammonia , mean squared error , convolutional neural network , environmental science , mean squared prediction error , computer science , statistics , mathematics , algorithm , artificial intelligence , chemistry , organic chemistry
The ammonia concentration in piggery has a great impact on the healthy growth of pigs and breeding environment. It is of great significance to control the ammonia concentration in piggery and ensure the healthy growth of pigs by timely mastering the ammonia concentration variation trend. In order to predict the ammonia concentration in piggery, a method based on CNN(Convolutional Neural Networks) and GRU(Gated Recurrent Unit) was proposed. Firstly, the environmental data in piggery and the meteorological data outside were collected, fused and preprocessed. Then, a piggery ammonia concentration prediction model combined with CNN and GRU was established. As a result, the ammonia concentration in piggery was predicted. The result shows that the proposed method has good prediction performance. The MSE (Mean Square Error), RMSE (Root Mean Square Error) and MAE (Mean Absolute Error) is 0.0637, 0.2524 and 0.1845, respectively. The proposed method can provide support for the early warning and regulation of piggery environment.