温室环境神经网络建模

Modeling Greenhouse Environment with Artificial Neural Networks

温室环境的生产过程具有许多特点,时变性、非线性和不确定性,很难建立精确的数学模型；利用人工神经网络对温室环境温度进行建模；通过输入样本数据对神经网络模型进行训练,确定网络结构；实验结果表明,模型中的输入和输出时延不同,模型的精度也不相同；最后,确定了一种适用模型。

The process in production of the greenhouse environment has many characteristics, such as time variable, nonlinear and uncertain. Its very difficult to build an accurate mathematics model. So the greenhouse environment temperature model is built by using artificial neural networks method. The network models are trained by inputting specimen data. The experiments results demonstrated the network models with different input--output time delay parameters have different precision. Finally, the most accurate model is adopted.