基于集中供热时延的温度预测模型及仿真
|
摘要
供热预测对实现供热节能有重要意义,然而由于供热系统具有非线性、复杂性和大时滞性等特点,预测存在一定难度,为了解决供热预测中的时延建模、求解和温度预测问题,基于供热系统的传热物理规律建立优化模型,提出最小二乘意义上的时延求解剪枝算法,并进行温度预测。将供热系统的时延考虑在内的模型符合热传递的物理规律,剪枝降低了时延求解的计算复杂度。通过仿真实验对比与分析证明,与梯度下降最小二乘回归、支持向量机、最小二乘支持向量机和BP神经网络等模型相比,本模型具有较低的平均相对误差和均方误差,且模型简单,计算便捷。
Heating prediction is essential for energy saving. However, it is difficult to some extent because the central heating system(CHS) is nonlinear with large-scaled delay and other characteristics.Based on physical laws of the CHS, a novel model combining pruning algorithm with the least mean square is proposed to solve the problem of delay and predict the temperature. The model with the delay taking into consideration conforms to the law of thermal transmission. The pruning algorithm lowers the computational complexity. Simulations using gradient descent least squared regression(LSR), support vector machine(SVM), least-squared support vector machine(LS-SVM) and BP neural network are put forward to evaluate the model and the results show that the model has low average relative error and mean squared error; and the model is simple and easy to calculate.
Heating prediction is essential for energy saving. However, it is difficult to some extent because the central heating system(CHS) is nonlinear with large-scaled delay and other characteristics.Based on physical laws of the CHS, a novel model combining pruning algorithm with the least mean square is proposed to solve the problem of delay and predict the temperature. The model with the delay taking into consideration conforms to the law of thermal transmission. The pruning algorithm lowers the computational complexity. Simulations using gradient descent least squared regression(LSR), support vector machine(SVM), least-squared support vector machine(LS-SVM) and BP neural network are put forward to evaluate the model and the results show that the model has low average relative error and mean squared error; and the model is simple and easy to calculate.
引文
[1]贺平,孙刚.供热工程[M].4版.北京:中国建筑工业出版社,2009.Ping He,Gang Sun.Heating Engineering[M].4th edition.Beijing:China Architecture&Building Press,2009.
[2]刘满平.供热工程[M].北京:中国建材工业出版社,2013.Manping Liu.Heating Engineering[M].Beijing:China Architecture&Building Press,2013.
[3]Bass M S,Batukhtin A G.An Integrated Approach for Optimizing the Operation of Modern Heat Supply Systems[J].Thermal Engineering(S0040-6015),2011,58(8):678-679.
[4]文翰.基于最小二乘法的热负荷预测的研究与应用[D].大连海事大学,2014:12-17.Wen Han.The research and application of heating load forecast based on the least square method[D].Dalian Maritime University,2014:12-17.
[5]李琦,李梅.PSO优化在供热网络控制中的应用研究[J].计算机仿真,2013,30(12):294-297.Li Qi,Mei Li.Study and Application of PSO in Heating Network Control[J].Computer Simulation,2013,30(12):294-297.
[6]高丙坤,李阳,许明子.优化粒子群算法在组合供热负荷预测中的应用[J].信息与电子工程,2012,9(5):655-659.Gao Bingkun,Li Yang,Xu Mingzi.Application of particle swarm optimization algorithm in the heating load combination forecasting[J].Information and Electronic Engineering,2012,9(5):655-659.
[7]张永明,陈烈,齐维贵.基于支持向量区间回归的供热负荷概率预报[J].吉林大学学报(工学版),2010,40(6):1693-1697.Zhang Yongming,Chen Lie,Qi Weigui.Probabilistic prediction approach of heat load based on support vector interval regression[J].Journal of Jilin University(Enginering and Technology Edition),2010,40(6):1693-1697.
[8]王美萍,田琦,张佼.模糊耦合神经网络的系统供热预测研究[J].太原理工大学学报,2015,45(4):485-489.Wang Meiping,Tian Qi,Zhang Jiao.Research on Heat Forecasting Based on Fuzy Neural Network[J].Journal of Taiyuan University of Technology,2015,45(4):485-489.
[9]崔高健,凡东生,曲永利.基于Elman型神经网络集中供热负荷预测模型的研究[J].建筑节能,2011(3):9-11.Cui Gaojian,Fan Dongsheng,Qu Yongli.Load Predication Model of District Heating System Based on Elman Neural Network[J].Building Energy Efficiency,2011(3):9-11.
[10]谢慕君,冯敬芳,姜长泓.集中供热二次网回水温度的预测和控制研究[J].控制工程,2015,22(2):291-295.Xie Mujun,Feng Jingfang,Jiang Changhong.Research of Secondary Network Backwater Temperature Forecast and Control for Centralized Heat-supply System[J].Control Engineering of China,2015,22(2):291-295.
[11]冯敬芳,谢慕君,步伟明,等.基于神经网络集中供热二次回水温度预测研究[J].计算机仿真,2014,31(3):351-354.Feng Jingfang,Xie Mujun,Bu Weiming,et al.Research on Secondary Network Backwater Temperature Forecast for Centralized Heat-Supply System Based on Neural Network[J].Computer Simulation,2014,31(3):351-354.
[12]刘兰斌,江亿,付林,等.供暖末端通断调节系统仿真模型介绍[J].建筑科学,2010,26(10):310-317.Liu Lanbin,Jiang Yi,Fu Lin,et al.An introduction to the system simulation models of on-off control in the end of heating system[J].Building Science,2010,26(10):310-317.
[13]Chang C C,Lin C J.LIBSVM:A library for support vector machines[J].ACM Transactions on Intelligent Systems&Technology(S2157-6904),2011,2(3):389-396.
[14]Suykens J A K,Vandewalle J.Least Squares Support Vector Machine Classifiers[J].Neural Processing Letters(S1370-4621),1999,9(3):293-300.
[15]Ding S,Chang X H,Wu Q H.A Study on Approximation Performances of Improved BP Neural Networks Based on LM Algorithms[J].Applied Mechanics&Materials(S 1662-7482),2013(411/412/413/414):1935-1938.
[2]刘满平.供热工程[M].北京:中国建材工业出版社,2013.Manping Liu.Heating Engineering[M].Beijing:China Architecture&Building Press,2013.
[3]Bass M S,Batukhtin A G.An Integrated Approach for Optimizing the Operation of Modern Heat Supply Systems[J].Thermal Engineering(S0040-6015),2011,58(8):678-679.
[4]文翰.基于最小二乘法的热负荷预测的研究与应用[D].大连海事大学,2014:12-17.Wen Han.The research and application of heating load forecast based on the least square method[D].Dalian Maritime University,2014:12-17.
[5]李琦,李梅.PSO优化在供热网络控制中的应用研究[J].计算机仿真,2013,30(12):294-297.Li Qi,Mei Li.Study and Application of PSO in Heating Network Control[J].Computer Simulation,2013,30(12):294-297.
[6]高丙坤,李阳,许明子.优化粒子群算法在组合供热负荷预测中的应用[J].信息与电子工程,2012,9(5):655-659.Gao Bingkun,Li Yang,Xu Mingzi.Application of particle swarm optimization algorithm in the heating load combination forecasting[J].Information and Electronic Engineering,2012,9(5):655-659.
[7]张永明,陈烈,齐维贵.基于支持向量区间回归的供热负荷概率预报[J].吉林大学学报(工学版),2010,40(6):1693-1697.Zhang Yongming,Chen Lie,Qi Weigui.Probabilistic prediction approach of heat load based on support vector interval regression[J].Journal of Jilin University(Enginering and Technology Edition),2010,40(6):1693-1697.
[8]王美萍,田琦,张佼.模糊耦合神经网络的系统供热预测研究[J].太原理工大学学报,2015,45(4):485-489.Wang Meiping,Tian Qi,Zhang Jiao.Research on Heat Forecasting Based on Fuzy Neural Network[J].Journal of Taiyuan University of Technology,2015,45(4):485-489.
[9]崔高健,凡东生,曲永利.基于Elman型神经网络集中供热负荷预测模型的研究[J].建筑节能,2011(3):9-11.Cui Gaojian,Fan Dongsheng,Qu Yongli.Load Predication Model of District Heating System Based on Elman Neural Network[J].Building Energy Efficiency,2011(3):9-11.
[10]谢慕君,冯敬芳,姜长泓.集中供热二次网回水温度的预测和控制研究[J].控制工程,2015,22(2):291-295.Xie Mujun,Feng Jingfang,Jiang Changhong.Research of Secondary Network Backwater Temperature Forecast and Control for Centralized Heat-supply System[J].Control Engineering of China,2015,22(2):291-295.
[11]冯敬芳,谢慕君,步伟明,等.基于神经网络集中供热二次回水温度预测研究[J].计算机仿真,2014,31(3):351-354.Feng Jingfang,Xie Mujun,Bu Weiming,et al.Research on Secondary Network Backwater Temperature Forecast for Centralized Heat-Supply System Based on Neural Network[J].Computer Simulation,2014,31(3):351-354.
[12]刘兰斌,江亿,付林,等.供暖末端通断调节系统仿真模型介绍[J].建筑科学,2010,26(10):310-317.Liu Lanbin,Jiang Yi,Fu Lin,et al.An introduction to the system simulation models of on-off control in the end of heating system[J].Building Science,2010,26(10):310-317.
[13]Chang C C,Lin C J.LIBSVM:A library for support vector machines[J].ACM Transactions on Intelligent Systems&Technology(S2157-6904),2011,2(3):389-396.
[14]Suykens J A K,Vandewalle J.Least Squares Support Vector Machine Classifiers[J].Neural Processing Letters(S1370-4621),1999,9(3):293-300.
[15]Ding S,Chang X H,Wu Q H.A Study on Approximation Performances of Improved BP Neural Networks Based on LM Algorithms[J].Applied Mechanics&Materials(S 1662-7482),2013(411/412/413/414):1935-1938.