Simulated response of NN based identification and predictive control of hydro plant

This paper studies the neural network nonlinear autoregressive with exogenous signal (NNARX) model identification of elastic and inelastic hydro power plant. A nonlinear relationship between the turbine deviated power and random gate position on random load variation and water disturbance is assessed. The identified elastic NNARX hydro plant model is simulated with predictive controller to track a given deviated power as a reference signal. The controller parameters are optimally determined by solving quadratic performance index using well known Levenberg–Marquardt and quasi-Newton algorithm. And it is demonstrated that the deviated power tracks its deviated power target signal accurately over wide rapid-variations in load and water disturbances.     

Adaptive intelligent hydro turbine speed identification with water and random load disturbances

In this paper, the hydro power plant model (with penstock-wall elasticity and compressible water column effect) is simulated at random load disturbance variation with output as turbine speed for random gate position as input. The multilayer perceptron neural network (i.e. NNARX) and fused neural network and fuzzy inference system (i.e. ANFIS) for identification of turbine speed as output variable are reported. Emphasis is put on obtaining a generalized model, using (i) NNARX model and (ii) ANFIS model with membership functions defined by subtractive clustering for plant model representation under different values of water time constant. The comparative performance study between the two approaches is also addressed. In the end of the paper, an application of adaptive noise cancellation based on ANFIS model to identify the turbine speed dynamics is also discussed.     

Nonlinear predictive control for a NNARX hydro plant model

A neural network (NN)-based nonlinear predictive control (NPC) is described for control of turbine power with variation in gate position. The studied plant includes the tunnel, surge tank and penstock effect dynamics. Multilayer perceptron neural network is chosen to represent a neural network nonlinear autoregressive with exogenous signal model of hydro power plant. With the said NN model configuration, quasi-Newton and Levenberg–Marquardt iterative optimization algorithms are applied in order to determine optimal predictive control parameters. The controlled response is simulated on different amplitude step function and trapezoidal shape reference signal. The study also discusses comparison with an approximate predictive control approach, being linearized around operating points. It is shown that NPC strategy gives impressive results in comparison to the approximated one.     

A comparison of linear and neural network ARX models applied to a prediction of the indoor temperature of a building

A neural network auto regressive with exogenous input (NNARX) model is used to predict the indoor temperature of a residential building. Firstly, the optimal regressor of a linear ARX model is identified by minimising Akaikes final prediction error (FPE). This regressor is then used as the input vector of a fully connected feedforward neural network with one hidden layer of ten units and one output unit. Results show that the NNARX model outperforms the linear model considerably: the sum of the squared error (SSE) is 15.0479 with the ARX model and 2.0632 with the NNARX model. The optimal network topology is subsequently determined by pruning the fully connected network according to the optimal brain surgeon (OBS) strategy. With this procedure near 73% of connections were removed and, as a result, the performance of the network has been improved: the SSE is equal to 0.9060.     

Nonlinear fuzzy model predictive iterative learning control for drum-type boiler–turbine system

Advanced control strategy is necessary to ensure high efficiency and high load-following capability in the operation of modern power plant. Model predictive control (MPC) has been widely used for controlling power plant. Nevertheless, MPC needs to further improve its learning ability especially as power plants are nonlinear under load-cycling operation. Iterative learning control (ILC) and MPC are both popular approaches in industrial process control and optimization. The integration of model-based ILC with a real-time feedback MPC constitutes the model predictive iterative learning control (MPILC). Considering power plant, this paper presents a nonlinear model predictive controller based on iterative learning control (NMPILC). The nonlinear power plant dynamic is described by a fuzzy model which contains local liner models. The resulting NMPILC is constituted based on this fuzzy model. Optimal performance is realized within both the time index and the iterative index. Convergence property has been proven under the fuzzy model. Deep analysis and simulations on a drum-type boiler–turbine system show the effectiveness of the fuzzy-model-based NMPILC     

具有尾缘襟翼风力机的恒功率反步法控制

尾缘襟翼风力机控制技术在大型风力机领域具有巨大的应用潜力.本文首先基于修正的叶素动量方法建立了具有可变尾缘襟翼的风力机气动模型.针对襟翼风力机的非线性模型,采用反步法设计了非线性控制器,保证系统的控制量和状态变量全局有界,并且风机的输出功率可以收敛到额定功率的一个小邻域内.此外,控制器设计过程中没有将实时风速信息纳入反馈系统,因而降低了工程实施的难度.最后针对12 m/s～15 m/s的阶跃风、基于四分量模型模拟的风载扰动、执行机构受到外部扰动以及总转动惯量具有10%不确定性的工况进行了仿真,仿真结果表明所设计的控制器能有效地稳定风力发电系统的输出功率,控制系统具有较强的鲁棒性.     

Zero-order TS fuzzy model to predict hydro turbine speed in closed loop operation

This paper addresses the development of new hydro plant model using a zero-order Takagi–Sugeno (TS) fuzzy approach. The control signal and turbine speed are identified as input–output variable of the plant. The said model is determined with two fuzzy sets using data generated from widely accepted second-order H-infinity and Padé transfer function (TF) plant model operating in closed loop through digital PID control.The parameters in fuzzy inference system are adaptively tuned using gradient-descent optimization technique. The performance of identified zero-order TS fuzzy model is demonstrated accurately and thus suitable for turbine speed dynamics study.     

Robust constrained predictive feedback linearization controller in a solar desalination plant collector field

This paper proposes a feedback linearization strategy for a solar collector field, which is a constrained non-linear processes. The benefits of input–output feedback linearization are improved by a filtered Smith predictor-based model predictive control algorithm with embedded variable constraint mapping to take advantage of: (i) linear control without losing the intrinsic non-linearities typical of thermal power plants; (ii) including input amplitude constraint handling capabilities due to control signal saturations induced, for example, by strong irradiance disturbances or plant start-up; and (iii) avoiding unstable or highly oscillatory responses caused by plant-model mismatch. Simulation studies are first presented to analyze robustness and constraint-mapping features, and real experimental tests of this technique in the AQUASOL desalination plant solar field have been included to demonstrate the advantages of its implementation, especially for reference tracking despite disturbances.     

An Investigation on Pruned NNARX Identification Model of Hydropower Plant

The aim of this paper is to determine an accurate nonlinear system model for identification of dynamics. A small hydropower plant connected as single machine infinite bus (SMIB) system is considered in the study. It is modeled by a neural network configured as a feedforward multilayer perceptron neural network (MLPNN). An investigation is conducted on various NN structures to determine the optimally pruned neural network nonlinear autoregressive with exogenous signal (NNARX) identification model. The structure selection is based on validation tests performed on these network models. The proposed structure identifies the model characteristics, which represent the dynamics of a power plant accurately. The results show an improved performance in identification of power plant dynamics by optimal brain surgeon (OBS) pruned network as compared to un-pruned (i.e., fully connected) network.     

Constrained predictive control for multivariable systems with application to power systems

Generalized predictive control (GPC) and dynamic performance predictive control (DPC) algorithms are introduced for industrial applications. Constraints on plant input rate, plant absolute input and plant absolute output can be implemented and are demonstrated on an application of these algorithms. A standard quadratic programming algorithm performs the calculation of the optimal control. A MATLAB/Simulink toolbox environment has been developed where controllers can be designed, linear and non-linear plant models can be embedded, discrete- and continuous-time loop parts can be mixed and simulation results can be managed and evaluated by graphical and statistical tools. This package utilises a graphical user interface. Finally, a case study design example is presented where a linear gas turbine model for power generation is examined with constrained GPC and DPC, and the advantages and drawbacks of the approach are the discussed. Copyright © 1999 John Wiley & Sons, Ltd.     

基于无差拍控制的超导磁储能系统

超导磁储能(SMES)系统具有功率密度高和功率指令响应快等特点,在平滑风力发电功率波动、提高电力系统稳定性等方面具有广阔的应用前景。针对当前SMES控制存在超调量大、控制精度不高等缺陷,将无差拍控制引入SMES的控制中。首先建立了SMES数学模型并介绍了无差拍控制的一般设计方法,然后根据SMES数学模型设计了SMES的无差拍控制策略,最后在MATLAB/SIMULINK中对所提控制策略进行了仿真。仿真结果表明,所提的控制方法具有跟踪无过冲、控制精度高和SMES变流器网侧电流谐波含量小等特点;将其应用于平滑双馈风机有功功率输出,有效平滑了双馈风机的功率波动,提高了双馈风机的并网能力。证明了该控制策略的有效性和优越性。     

Resilient distributed model-free adaptive predictive control for multiarea power systems under denial of service attack

This paper proposes a novel load frequency control (LFC) strategy for power systems based on distributed model-free adaptive predictive control. First, a power system dynamic model is established by the input and output signals of the power system. Then, a distributed model-free adaptive predictive control algorithm is established for the power system under denial-of-service attack by the established power system dynamic model, and a predictive compensation algorithm is designed to compensate the impact of DoS attack. Based on the designed distributed model-free adaptive predictive control algorithm, the frequency tracking error of the multiarea power system is bounded. The scheme is independent of the structure of the power system and does not need to measure any state signals of the power system, relying only on the input and output data of the power system. The results of simulations demonstrate the effectiveness and superiority of the design.     

含有有功损耗的DFIG风电场优化调度策略

优化风电调度可以最大限度地提高风电在限电条件下的利用率。论文对风力发电机组的基本理论进行了研究,分析了风力发电机组的功率控制和输出特性,分析了双馈感应电机(DFIG)具有良好的功率解耦控制和无功输出能力。通过对风力发电出力特性的研究,提出了风力发电优化调度的策略。计算结果表明,风电场总的有功功率和无功功率输出满足调度中心的要求,并且总的有功损耗和无功损耗最小。     

Asymptotic Tracking Control for Wind Turbines in Variable Speed Mode

This paper presents a variable speed control strategy for wind turbines in order to capture maximum wind power. Wind turbines are modeled as a two-mass drive-train system with generator torque control. Based on the obtained wind turbine model, variable speed control schemes are developed. Nonlinear tracking controllers are designed to achieve asymptotic tracking for a prescribed rotor speed reference signal so as to yield maximum wind power capture. Due to the difficulty of torsional angle measurement, an observer-based control scheme that uses only rotor speed information is further developed for global asymptotic output tracking. The effectiveness of the proposed control methods is illustrated by simulation results.      

Modelling of the whole process of a university campus CHP power plant and dynamic performance study

Combined heat and power (CHP) refers to a process/system designed to utilize the waste or residual heat from a power generation process. Thus, a CHP plant can produce both electricity and heat. The nature of such a combination makes the process more complex than any single power generation process or boiler heating system. The paper focuses on modelling study and analysis of energy efficiency of the University of Warwick micro-CHP power plant. In this CHP modelling study, a gas turbine module is built to provide driving power and methane is used as fuel gas. Heat recovery system and auxiliary boiler modules are developed for thermal power generation. All the sub-systems are validated by comparing the simulation results with the operating data collected from the CHP plant. The dynamic performance of the key CHP process outputs is studied with respect to the variation of the input syngas stream, including electricity generation, thermal power output and water output temperature. Simplified controllers are also applied to the gas engineheat recovery subsystem and auxiliary boiler. Simulation results with/without feedback control are both analyzed. The study has highlighted the key factors which influence the plant performance and suggested the strategy for potential energy efficiency improvement.     

Nonlinear modelling and adaptive predictive control of a solar power plant

This paper presents the application of a nonlinear controller, using a predictive control strategy, to the distributed collector field of a solar power plant at the Plataforma Solar de Almerı́a (Spain). The design procedure of the controller uses the mathematical input–output model of the plant to find a controller output, using a search strategy that minimizes the cost function for a given prediction horizon. From the basic physical relations that are valid for the heating process of the oil inside the piping different nonlinear models have been deduced for this plant. The parameters of these models are estimated on-line in order to compensate for time-varying effects and modelling errors. The controller has been used in connection with these models to form an adaptive control system and has been applied to the plant. The results of experiments that were carried out in 1998 are presented.     

A nonlinear state‐feedback state‐feedforward tracking control strategy for a boiler‐turbine unit

A boiler‐turbine unit is a primary module for coal‐fired power plants, and an effective automatic control system is needed for the boiler‐turbine unit to track the load changes with the drum water level kept within an acceptable range. The aim of this paper is to develop a nonlinear tracking controller for the Bell‐Åström boiler‐turbine unit. A Takagi‐Sugeno fuzzy control system is introduced for the nonlinear modeling of the Bell‐Åström boiler‐turbine unit. Based on the Takagi‐Sugeno fuzzy models, a nonlinear tracking controller is developed, and the proposed control law is comprised of a state‐feedforward term and a state‐feedback term. The stability of the closed‐loop control system is analyzed on the basis of Lyapunov stability theory via the linear matrix inequality approach and Schur complement. Moreover, model uncertainties are also considered, and it is proved that with the proposed control law the tracking error converges to zero. To assess the performance of the proposed nonlinear state‐feedback state‐feedforward control strategy, a nonlinear model predictive control strategy and a linear strategy are presented as comparisons. The effectiveness and the advantages of the proposed nonlinear state‐feedback state‐feedforward control strategy are demonstrated by simulations.     

变桨距风力发电机组恒功率反馈线性化控制

在额定风速以上时,为保证风电机组的安全稳定运行,需要降低风力机捕获风能,使风力机的转速及功率维持在额定值,基于微分几何反馈线性化方法,提出变桨距风力发电机组恒功率控制策略.建立了风力机的仿射非线性模型,采用微分几何反馈线性化变换实现全局精确线性化;根据新的线性化模型,以风力机转速为输出反馈变量,叶片桨距角为输入控制变量,设计桨距角控制器;在风速高于额定值时调节风力机维持在额定转速,从而实现额定风速以上的恒功率控制.仿真结果表明,所提控制策略能较好地解决变桨距风力发电机组额定风速以上的恒功率控制问题,控制方法具有较好的适应性和鲁棒性.     

Evaluate time delay from sensor's data by trend similarity search

Time delay estimation is a general issue in both signal processing and process control fields. Neither offline step impulse response-based methods nor least squares methods in control field estimate time delay directly from the real running data. Although the methods for signal processing directly evaluate the delay from signals, such as correlation calculation, coherence analysis and least mean square methods, they are mainly suitable for two signals only different at a time delay part and an attenuation factor. In this article, an estimation method is proposed which is directly based on the real running input and output data of a control plant. The input and output signals of a plant show raw monotony from each other in many cases. According to this feature, we estimate the delay by comparing the trend of two signals. Furthermore, it is extended to an adaptive method for estimating piecewise time-varying delay by sliding window and forgetting factor. The experiments on real plant show the good performances of our methods. The simulation experiments demonstrate that our basic method performs better than CCF or coherence analysis for the nonlinear plant and the adaptive one performs better than least mean square methods for the signals with transfer function except time delay.     

基于内模控制（IMC）的主汽温度控制系统设计

主蒸汽温度和再热蒸汽温度直接影响火电厂的热效率和汽轮机等设备运行的安全性。传统PID控制器的控制规律简单,但是不能根据控制过程中的不确定性变化做出相应调整。当被控对象参数实时变化时,控制器参数不能做出实时调整。这样会导致过程的品质指标变坏。针对超超临界机组过热蒸汽温度和再热蒸汽温度,提出了一种基于内模控制(Internal Model Control简称IMC)的PID控制策略,将PID控制、Smith预估控制、确定性及线性二次最优反馈控制和多种预测控制归纳于同一结构之下。以1000MW的电厂机组为对象开展了额定工况下和80%额定负荷下的过热气温和再热气温的PID-IMC控制器设计。