神经网络预测及电力主变室多参数优化控制
|
摘要
针对变压器室通风散热这类多变量、非线性和时变的复杂控制系统,采用神经网络作为优化反馈控制器求解优化反馈解;利用预测控制的滚动优化具有克服室外温度干扰和不确定性影响的优势,通过滚动优化算法训练神经网络模型,同时对控制系统中负荷电流变化也采用神经网络进行预测,以实现被控对象的实时预测;利用该方法对变压器室通风散热系统进行理论分析和仿真,仿真结果表明系统具有较强的鲁棒性;最后应用于变压器室智能通风散热系统实际工程中,获得较好降温的效果。
Transformer room ventilation is a multivariable,nonlinear and time-varying control system,a neural network served as the optimal feedback controller,which was trained with optimization algorithm based on the method of the rolling optimization of predictive control to compensate for disturbances and uncertain plant nonlinearities.The controller can approximate the optimal feedback solution for nonlinear-time-varying systems without the complexities of computation.Additional neural networks were used to predict load current parameters to realize the real-time predication of the dynamic behavior.An optimal control system was designed to control ventilation and heat dissipation system of the transformer chamber,which aimed at implement the theoretical analysis and simulation,Simulation results show that the system has strong robustness.Finally,applied to the ventilation and heat dissipation intelligent system of the main transformer chamber in practical engineering,which has got better effect.
Transformer room ventilation is a multivariable,nonlinear and time-varying control system,a neural network served as the optimal feedback controller,which was trained with optimization algorithm based on the method of the rolling optimization of predictive control to compensate for disturbances and uncertain plant nonlinearities.The controller can approximate the optimal feedback solution for nonlinear-time-varying systems without the complexities of computation.Additional neural networks were used to predict load current parameters to realize the real-time predication of the dynamic behavior.An optimal control system was designed to control ventilation and heat dissipation system of the transformer chamber,which aimed at implement the theoretical analysis and simulation,Simulation results show that the system has strong robustness.Finally,applied to the ventilation and heat dissipation intelligent system of the main transformer chamber in practical engineering,which has got better effect.
引文
[1]张靖波,牛彭涛.110kV全室内变电站主变压器自然通风方案探讨[J].电源技术与应用,2012,(10):196-197.
[2]Ryder S A,He Q,Si J,et al.Prediction of top-oil temperature for transformers using neural networks[J].IEEE Transactions on Power Delivery,2001,16(4):825-826.
[3]任旭明.变压器室散热的研究[J].变压器,2003,40(5):15-16.
[4]张国仲,李晶,振玉民,等.干式变压器气候和环境试验[J].变压器,2005,42(7):1-3.
[5]陈君.变电站室内变压器通风系统改造措施[J].北京电力高等专科学校学报(自然科学版),2012,29(2):209-209.
[6]Cherchi E,Guevara C A.A Monte Carlo experiment to analyze the curse of dimensionality in estimating random coefficients models with a full variance-covariance matrix[J].Transportation Research.Part B,Methodological,2012,46B(2):321-332.
[7]刘高原,马丽.热轧带钢层流冷却控制系统研究与实现[J].计算机测量与控制,2012,20(8):2111-2113.
[8]王娟,刘明治.蚁群算法滚动优化的LS-SVM预测控制研究[J].控制与决策,2009,24(7):1087-1091.
[9]Li Z,Ierapetritou M G.Rolling horizon based planning and scheduling integration with production capacity consideration[J].Chemical Engineering Science,2010,65(22):5887-5900.
[10]李伟,何鹏举,杨恒,等.基于粗糙集和改进遗传算法优化BP神经网络的算法研究[J].西北工业大学报,2012,30(4):601-606.
[11]郭伟,倪家健,李涛,等.基于时域的分数阶PID预测函数励磁控制器[J].仪器仪表学报,2011,32(11):2461-2467.
[12]薛振宇,房大中,袁世强,等.基于泛函灵敏度方法的PSS参数优化设计[J].华南理工大学学报(自然科学版),2011,39(8):140-145.
[2]Ryder S A,He Q,Si J,et al.Prediction of top-oil temperature for transformers using neural networks[J].IEEE Transactions on Power Delivery,2001,16(4):825-826.
[3]任旭明.变压器室散热的研究[J].变压器,2003,40(5):15-16.
[4]张国仲,李晶,振玉民,等.干式变压器气候和环境试验[J].变压器,2005,42(7):1-3.
[5]陈君.变电站室内变压器通风系统改造措施[J].北京电力高等专科学校学报(自然科学版),2012,29(2):209-209.
[6]Cherchi E,Guevara C A.A Monte Carlo experiment to analyze the curse of dimensionality in estimating random coefficients models with a full variance-covariance matrix[J].Transportation Research.Part B,Methodological,2012,46B(2):321-332.
[7]刘高原,马丽.热轧带钢层流冷却控制系统研究与实现[J].计算机测量与控制,2012,20(8):2111-2113.
[8]王娟,刘明治.蚁群算法滚动优化的LS-SVM预测控制研究[J].控制与决策,2009,24(7):1087-1091.
[9]Li Z,Ierapetritou M G.Rolling horizon based planning and scheduling integration with production capacity consideration[J].Chemical Engineering Science,2010,65(22):5887-5900.
[10]李伟,何鹏举,杨恒,等.基于粗糙集和改进遗传算法优化BP神经网络的算法研究[J].西北工业大学报,2012,30(4):601-606.
[11]郭伟,倪家健,李涛,等.基于时域的分数阶PID预测函数励磁控制器[J].仪器仪表学报,2011,32(11):2461-2467.
[12]薛振宇,房大中,袁世强,等.基于泛函灵敏度方法的PSS参数优化设计[J].华南理工大学学报(自然科学版),2011,39(8):140-145.