APP下载

基于改进深度信念网络的农业温室温度预测方法

2019-08-01周翔宇程勇王军

计算机应用 2019年4期

周翔宇 程勇 王军

摘 要:针对浅层神经网络面对温室复杂多变环境因子表征能力低、学习时间长的问题,提出一种基于改进深度信念网络并结合经验模态分解与门控循环单元的温室预测方法。首先,通过经验模态分解将温度环境因子进行信号分解,之后将分解出来的固有模态函数与残差信号进行不同程度的预测;然后,引入神经胶质改进深度信念网络,并将分解信号结合光照和二氧化碳进行多属性的特征提取;最后,将门控循环单元预测的信号分量相加获得最终的预测结果。仿真实验结果表明,与经验模态分解深度信念网络(EMD-DBN)和深度信念网络神经胶质链(DBN-g)相比,所提方法的预测误差分别降低了6.25%和5.36%,验证了其在强噪声、强耦合的温室时序环境下预测的有效性和可行性。

关键词: 循环神经网络;深度信念网络;门控循环单元;时间序列预测;神经胶质链

中图分类号:TP183

文献标志码:A

文章编号:1001-9081(2019)04-1053-06

Abstract: Concerning low representation ability and long learning time for complex and variable environmental factors in greenhouses, a prediction method based on improved Deep Belief Network (DBN) combined with Empirical Mode Decomposition (EMD) and Gated Recurrent Unit (GRU) was proposed. Firstly, the temperature environment factor was decomposed by EMD, and then the decomposed intrinsic mode function and residual signal were predicted at different degrees. Secondly, glia was introduced to improve DBN, and the decomposition signal was used to multi-attribute feature extraction combined with illumination and carbon dioxide. Finally, the signal components predicted by GRU were added together to obtain the final prediction result. The simulation results show that compared with empirical decomposition belief network (EMD-DBN) and glial DBN-glial chains (DBN-g), the prediction error of the proposed method is reduced by 6.25% and 5.36% respectively, thus verifying its effectiveness and feasibility of predictions in greenhouse time series environment with strong noise and coupling.

Key words: recurrent neural network; Deep Belief Network (DBN); Gated Recurrent Unit (GRU); time series prediction; glial chain

0 引言

溫度作为农作物赖以生存的重要因素,影响着农作物的生长、发育和形态建成,如何控制和管理温室温度成为设施农业的重要问题。温室大棚智能控制作为设施农业种植与生产过程中的关键环节,是提高生产效率、保障农作物品质的重要措施[1]。温室中影响农作物生长发育的环境变量都是时变量,其变化没有规律可循且难以进行预判,另外这些环境因素相互作用,难有适合的数学模型表述[2]。因此为了尽可能解决温室大滞后问题,实现智能温室控制,需要对环境变量进行精确地预测,建立类似专家逻辑思维、模拟人脑智力的智能控制系统。……

登录APP查看全文