论文部分内容阅读
介绍了农用地膜的光降解技术,阐述了实现地膜可控降解的原理。在此基础上,结合实际应用,采用反向传播(BP)神经网络模型指导可控降解地膜的配方设计,建立了基于光敏剂用量和气候条件关系的BP神经网络预测模型。结果表明:BP网络很快就达到设定的精度要求而收敛,且预测值与真实值之间的平均误差为9.6%,对可控降解地膜配方的设计具有重要的指导意义。
The photodegradation technology of agricultural film was introduced and the principle of controllable degradation of plastic film was expounded. On this basis, combined with the practical application, BP neural network model was used to guide the formulation design of controllable degradable plastic film, and a BP neural network prediction model based on the relationship between photosensitizer dosage and climatic conditions was established. The results show that the BP network converges quickly to meet the set accuracy requirements, and the average error between the predicted and the true values is 9.6%, which is of great guiding significance for the design of the controllable degradable mulching film.