Dynamic modeling of a SOFC/MGT hybrid power system based on modified OIF Elman neural network

Solid oxide fuel cell (SOFC) integrated into micro gas turbine (MGT) cycle is a promising power‐generation technology. This article proposes a modified output–input feedback (OIF) Elman neural network model to describe the nonlinear temperature and power dynamic properties of the SOFC/MGT hybrid system. A physics‐based mathematical model of a 220 kW SOFC/MGT hybrid power system is used to generate the data required for the training and prediction of the modified OIF Elman neural network identification model. Compared with the conventional Elman neural network, the simulation results show that the modified OIF Elman identification model can follow the temperature and power response of the SOFC/MGT hybrid system with higher prediction accuracy and faster convergent speed. Copyright © 2010 John Wiley & Sons, Ltd.     

Thermal modeling of a solid oxide fuel cell and micro gas turbine hybrid power system based on modified LS-SVM

For a solid oxide fuel cell (SOFC) integrated into a micro gas turbine (MGT) hybrid power system, SOFC operating temperature and turbine inlet temperature are the key parameters, which affect the performance of the hybrid system. Thus, a least squares support vector machine (LS-SVM) identification model based on an improved particle swarm optimization (PSO) algorithm is proposed to describe the nonlinear temperature dynamic properties of the SOFC/MGT hybrid system in this paper. During the process of modeling, an improved PSO algorithm is employed to optimize the parameters of the LS-SVM. In order to obtain the training and prediction data to identify the modified LS-SVM model, a SOFC/MGT physical model is established via Simulink toolbox of MATLAB6.5. Compared to the conventional BP neural network and the standard LS-SVM, the simulation results show that the modified LS-SVM model can efficiently reflect the temperature response of the SOFC/MGT hybrid system.     

Optimization of a solid oxide fuel cell and micro gas turbine hybrid system

For a solid oxide fuel cell (SOFC) and micro gas turbine (MGT) hybrid system, optimal control of load changes requires optimal dynamic scheduling of set points for the system's controllers. Thus, this paper proposes an improved iterative particle swarm optimization (PSO) algorithm to optimize the operating parameters under various loads. This method combines the iteration method and the PSO algorithm together, which can execute the discrete PSO iteratively until the control profile would converge to an optimal one. In MATLAB environment, the simulation results show that the SOFC/MGT hybrid model with the optimized parameters can effectively track the output power with high efficiency. Hence, the improved iterative PSO algorithm can be helpful for system analysis, optimization design, and real‐time control of the SOFC/MGT hybrid system. Copyright © 2011 John Wiley & Sons, Ltd.     

基于对角递归神经网络整定的PID解耦单元机组负荷控制系统

针对火电厂单元机组具有多变量强耦合、非线性及参数时变的受控对象，提出了基于对角递归神经网络整定的PID解耦控制方法，其主要特点是能够提供一个对角递归神经网络来辩识系统模型，进而对PID控制器参数进行整定，实现多变量解耦控制。通过对火电机组负荷控制系统的设计和仿真研究，表明系统达到了动态近似解耦、静态完全解耦和无静差跟踪，并具有响应速度快，鲁棒性好等特点。图5参6     

Multi-loop control strategy of a solid oxide fuel cell and micro gas turbine hybrid system

Solid oxide fuel cell and micro gas turbine (SOFC/MGT) hybrid system is a promising distributed power technology. In order to ensure the system safe operation as well as long lifetime of the fuel cell, an effective control manner is expected to regulate the temperature and fuel utilization at the desired level, and track the desired power output. Thus, a multi-loop control strategy for the hybrid system is investigated in this paper. A mathematical model for the SOFC/MGT hybrid system is built firstly. Based on the mathematical model, control cycles are introduced and their design is discussed. Part load operation condition is employed to investigate the control strategies for the system. The dynamic modeling and control implementation are realized in the MATLAB/SIMULINK environment, and the simulation results show that it is feasible to build the multi-loop control methods for the SOFC/MGT hybrid system with regard to load disturbances.     

Performance analysis for the part-load operation of a solid oxide fuel cell–micro gas turbine hybrid system

In this paper, the performance evaluation of a solid oxide fuel cell (SOFC)–micro gas turbine (MGT) hybrid power generation system under the part-load operation was studied numerically. The present analysis code includes distributed parameters model of the cell stack module. The conversions of chemical species for electrochemical process and fuel reformation process are considered. Besides the temperature distributions of the working fluids and each solid part of cell module by accounting heat generation and heat transfers, are taken into calculation. Including all of them, comprehensive energy balance in the cell stack module is calculated. The variable MGT rotational speed operation scheme is adopted for the part-load operation. It will be made evident that the power generation efficiency of the hybrid system decreases together with the power output. The major reason for the performance degradation is the operating temperature reduction in the SOFC module, which is caused by decreasing the fuel supply and the heat generation in the cells. This reduction is also connected to the air flow rate supplement. The variable MGT rotational speed control requires flexible air flow regulations to maintain the SOFC operating temperature. It will lead to high efficient operation of the hybrid system.     

Nonlinear model predictive control of SOFC based on a Hammerstein model

To protect solid oxide fuel cell (SOFC) stack and meet the voltage demand of DC type loads, two control loops are designed for controlling fuel utilization and output voltage, respectively. A Hammerstein model of the SOFC is first presented for developing effective control strategies, in which the nonlinear static part is approximated by a radial basis function neural network (RBFNN) and the linear dynamic part is modeled by an autoregressive with exogenous input (ARX) model. As we know, the output voltage of the SOFC changes with load variations. After a primary control loop is designed to keep the fuel utilization as a steady-state constant, a nonlinear model predictive control (MPC) based on the Hammerstein model is developed to control the output voltage of the SOFC. The performance of the MPC controller is compared with that of the PI controller developed in [Y.H. Li, S.S. Choi, S. Rajakaruna, An analysis of the control and operation of a solid oxide fuel-cell power plant in an isolated system, IEEE Trans. Energy Convers. 20 (2) (2005) 381–387]. Simulation results demonstrate the potential of the proposed Hammerstein model for application to the control of the SOFC, while the excellence of the nonlinear MPC controller for voltage control of the SOFC is proved.     

基于BP神经网络和GA-PID的超超临界锅炉系统解耦控制研究

直流锅炉运行中,给水调节和燃料调节十分重要,但其各变量之间存在强耦合关系。本文针对1 000 MW超超临界机组直流锅炉中燃料和给水协调控制对象参数多变、强耦合的特点,提出了一种改进权值调整的BP神经网络分散解耦智能方法,实现系统解耦,然后采用遗传算法PID(GA-PID)控制方法对解耦后近似独立的两组对象进行控制。仿真结果表明:BP神经网络分散解耦算法具有很强的非线性映射能力和自适应解耦能力,GA-PID具有良好的控制效果,所设计的系统具有较强的鲁棒性,解耦控制方案能够达到理想的效果。     

Predictive control of SOFC based on a GA-RBF neural network model

Transients in a load have a significant impact on the performance and durability of a solid oxide fuel cell (SOFC) system. One of the main reasons is that the fuel utilization changes drastically due to the load change. Therefore, in order to guarantee the fuel utilization to operate within a safe range, a nonlinear model predictive control (MPC) method is proposed to control the stack terminal voltage as a proper constant in this paper. The nonlinear predictive controller is based on an improved radial basis function (RBF) neural network identification model. During the process of modeling, the genetic algorithm (GA) is used to optimize the parameters of RBF neural networks. And then a nonlinear predictive control algorithm is applied to track the voltage of the SOFC. Compared with the constant fuel utilization control method, the simulation results show that the nonlinear predictive control algorithm based on the GA-RBF model performs much better.     

采用神经网络改善式循环柴油机的供氧控制

在氧气反馈调节的基础上,不依赖系统模型,借助神经网络的构成前馈控制器,以反馈输出引导网络权值及输出的调整,使网络逐步学成前馈补偿功能,并最在控制中占据主导地位,实现对负荷扰动的补偿。仿真结果表明,采用这一复合控制系统能有效地改善氧气控制的动态特性。     

Parameter optimization study on SOFC‐MGT hybrid power system

This paper mainly studied the solid oxide fuel cell (SOFC)–micro gas turbine (MGT) hybrid power system. The key parameters that greatly influence the overall system performance have been studied and optimized. The thermodynamic potential of improving the hybrid system performance by integrating SOFC with the advanced thermal cycle system is analyzed. The optimization rules of main parameters of SOFC‐MGT hybrid power system with the turbine inlet temperature (TIT) of MGT as a constraint condition are revealed. The research results show that TIT is a key parameter that limits the electrical efficiency of hybrid power system. With the increase of the cell number, both the power generation efficiency of the hybrid cycle power system and TIT increase. Regarding the hybrid system with the fixed cell number, in order to get a higher electrical efficiency, the operating temperature of SOFC should be enhanced as far as possible. However, the higher operating temperature will result in the higher TIT. Increasing of fuel utilization factor is an effective measure to improve the performance of hybrid system. At the same time, TIT increases slightly. Both the electrical efficiency of hybrid power system and TIT reduce with the increase of the ratio of steam to carbon. The achievements obtained from this paper will provide valuable information for further study on SOFC‐MGT hybrid power system with high efficiency. Copyright © 2010 John Wiley & Sons, Ltd.     

Optimal dual-model controller of solid oxide fuel cell output voltage using imitation distributed deep reinforcement learning

Solid oxide fuel cell (SOFC) is disadvantaged by significant nonlinearity, which makes it difficult to control output voltage of SOFC and satisfy the constraints of fuel utilization simultaneously. In order to solve this problem, a dual-model control framework (DMCF) is proposed. In particular, there are two controllers deployed under this framework, with an PID controller and a supplementary dynamic controller to track the SOFC output voltage. The supplementary dynamic controller is conducive to the stabilization of tracking by adapting to the uncertainties, considering the constraint on fuel utilization. In addition, an imitation distributed deep deterministic policy gradient (ID3PG) algorithm, which integrates imitation learning and distributed deep reinforcement learning to enhance the robustness and adaptive capacity of this framework, is proposed for the supplementary dynamic controller. The simulation results obtained in this work have demonstrated that the proposed framework is effective in imposing control on SOFC output voltage and preventing constraint violations of fuel utilization.     

Development of solid oxide fuel cell and battery hybrid power generation system

Solid oxide fuel cell hybrid generation system is the best scheme for the load tracking of off-grid monitoring stations. But there are still potential problems that need to be addressed: preventing fuel starvation and ensuring thermal safety while meeting load tracking in hybrid power generation system. In order to solve these problems, a feasible hybrid power generation system structure scheme is proposed which combined SOFC subsystem and Li-ion battery subsystem. Then a model of the hybrid power generation system is built based on the proposed system structure. On this basis, an adaptive controller, include the adaptive energy management algorithm and current feedforward gas supply strategy, is applied to manage the power-sharing in this hybrid system as well as keep the system operating within the safety constraints. The constraints, including maintaining the bus voltage at the desired level, keeping SOFC operating temperature in safety, and mitigating fuel starvation are explicitly considered. The stability of the proposed energy management algorithm is analyzed. Finally, the developed control algorithm is applied to the hybrid power generation system model, the operation result proves the feasibility of the designed controller strategy for hybrid generation system and effectively prevent fuel starvation and ensure thermal safety.     

Fuzzy neural control of a hybrid fuel cell/battery distributed power generation system

An innovative control strategy is proposed of hybrid distributed generation (HDG) systems, including solid oxide fuel cell (SOFC) as the main energy source and battery energy storage as the auxiliary power source. The overall configuration of the HDG system is given, and dynamic models for the SOFC power plant, battery bank and its power electronic interfacing are briefly described, and controller design methodologies for the power conditioning units and fuel cell to control the power flow from the hybrid power plant to the utility grid are presented. To distribute the power between power sources, the fuzzy switching controller has been developed. Then, a Lyapunov based-neuro fuzzy algorithm is presented for designing the controllers of fuel cell power plant, DC/DC and DC/AC converters; to regulate the input fuel flow and meet a desirable output power demand. Simulation results are given to show the overall system performance including load-following and power management of the system.     

基于BP神经网络的温度控制系统

文中介绍了基于BP(Back Pmpagation)的神经网络气化炉温度控制系统。对BP神经网络控制算法作了详细的介绍，运用模糊逻辑控制概念赋予隐层含义，并决定其节点数，同时用高斯核函数作为节点激励函数，并做了仿真研究，叙述了系统的硬件与软件构成，试验表明所设计的系统操作方便、安全可靠，所选择的控制算法适应性强，控制效果良好。     

Enhancement of grid-connected photovoltaic system using ANFIS-GA under different circumstances

In recent years, many different techniques are applied in order to draw maximum power from photovoltaic (PV) modules for changing solar irradiance and temperature conditions. Generally, the output power generation of the PV system depends on the intermittent solar insolation, cell temperature, efficiency of the PV panel and its output voltage level. Consequently, it is essential to track the generated power of the PV system and utilize the collected solar energy optimally. The aim of this paper is to simulate and control a grid-connected PV source by using an adaptive neuro-fuzzy inference system (ANFIS) and genetic algorithm (GA) controller. The data are optimized by GA and then, these optimum values are used in network training. The simulation results indicate that the ANFIS-GA controller can meet the need of load easily with less fluctuation around the maximum power point (MPP) and can increase the convergence speed to achieve the MPP rather than the conventional method. Moreover, to control both line voltage and current, a grid side P/Q controller has been applied. A dynamic modeling, control and simulation study of the PV system is performed with the Matlab/Simulink program.     

固体氧化物燃料电池的神经模糊控制策略研究

固体氧化物燃料电池(Solid Oxide Fuel Cell,SOFC)具有多输入多输出、强耦合的特点,为了使其输出电压稳定设计了高效控制器,采用神经模糊控制方法对其输出电压进行控制。通过机理分析和实验数据拟合方法分别建立SOFC的机理模型和神经网络模型,在此基础上采用模糊控制策略对SOFC的输出电压进行控制,并应用神经模糊控制方法进一步提高了控制精度。通过MATLAB/Simulink仿真实验发现,SOFC神经网络模型得到的预测电压与实际电压之间的误差小于0.008 V,较其机理模型更加准确,所提出的控制策略能有效控制SOFC的输出电压。     

基于相似日理论和LIBSVM软件中SVR算法的光伏发电系统输出功率预测方法

由于光伏发电具有间歇性、波动性的特点,因此准确预测并网型光伏发电系统的输出功率对电网调度,以及电网的安全稳定和经济高效运行具有重要意义.提出了一种基于相似日理论和LIBSVM软件中支持向量机回归(SVR)算法的光伏发电系统输出功率预测方法.通过实例进行仿真验算,并与同样采用相似日理论的反向传播(BP)神经网络算法、径向...     

Application of neural network for the modeling and control of evaporative condenser cooling load

Artificial neural network (ANN), in comparison with PID controllers which have broad applications in the highly complex HVAC systems, has recently received more attention. The present paper includes thermodynamic modeling of an evaporative condenser under steady state and transient state conditions for establishing control of thermal capacity, using Artificial neural network. To train the system under dynamic condition, predictive neural network, capable of understanding dynamic behavior and predicting the preset output is used. The principle operation of such neural networks is based on the reduction of gradients of errors existing between the predicted output and the actual output of the system. To control the system thermal capacity, neural controller based on training received from the reduction of gradients between the output controller and the ideal output, is used. Results obtained during present investigation indicate that artificial neural network controller is suitable substitute for PID controllers for thermal systems.     

基于BP神经网络的解耦方法在直流锅炉控制系统中的应用

分析了直流锅炉运行时各变量之间的耦合关系;针对直流锅炉参数多变、强耦合的特点,提出了一种改进的误差反向传播算法(BP)神经网络分散解耦方法,对直流锅炉汽温-压力控制系统进行解耦,然后采用基于BP神经网络的PID控制方法对解耦后的2个近似独立的单输入单输出系统进行控制.仿真实验结果表明:BP神经网络分散解耦控制算法具有很强的自学习功能和自适应解耦能力,能取得良好的控制效果.