模糊辨识方法在蓄电池建模中的应用

针对光伏系统中蓄电池建模十分困难的问题,基于T—S模糊模型,提出一种模糊建模方法。该方法采用三角形隶属函数计算给定样本的隶属度,利用稳态卡尔曼滤波器辨识模糊模型的结论参数,并把辨识模型的仿真结果与系统实验测量数据相对比,以检验模糊模型的可靠性。实验结果表明,这种新的蓄电池建模方法具有很高的精度,为高度复杂的非线性电化学过程的模型化提供了一条新途经。     

基于T-S模型的质子交换膜燃料电池控制建模

对PEMFC非线性复杂被控对象,提出了一种在线辨识模糊预测算法,用模糊聚类和线性辨识方法在线建立PEMFC控制系统的T—S模糊预测模型,仿真实验结果表明了该模糊辨识建模方法具有建模简单、模型精度高等优点,亦证明了该算法的有效性和优越性。研究结果对质子交换膜燃料电池控制系统的建模和控制具有一定的实用价值。     

基于自适应竞争聚类的多输人多输出热工过程模糊辨识

针对多输入多输出（MIM0）热工过程的非线性、强耦合、变工况及参数时变等特点,提出了一种基于系统输入输出数据和模糊自适应竞争聚类的模型辨识新方法．该方法首先依据系统的各个典型运行工况,使用模糊自适应竞争聚类对输入输出数据进行聚类划分,并对T—S模糊模型进行结构辨识,以确定系统的模型结构和参数;然后采用最小二乘递推算法对模型后件参数进行辨识,同时对结构辨识参数进行精确修正．将所提出的模型辨识方法用于锅炉一汽轮机非线性系统的模型辨识,仿真结果验证了该方法的有效性．     

基于ANFIS网络水电机组控制系统建模

利用模糊神经网络ANFIS较强的非线性逼近能力建立辨识模型，对水电机组控制系统输入、输出特性进行了辨识。辨识采用离线训练ANFIS网络和在线辨识相结合的方法，模型能很好地辨识系统输入、输出特性，为研究智能水轮发电机组控制策略提供了有效的建模方法。     

采用径向基函数神经网络的热工过程在线辨识方法

基于M-RAN算法的RBF神经网络是一种动态神经网络,适合于过程的在线建模。对M-RAN算法的删除策略进行了改进,不仅删除那些连续对网络输出贡献较小的隐层单元,同时还将相似的隐层单元合并,使网络结构更加紧凑。将基于这种算法的RBF神经网络用于电厂非性线模型热工过程的在线辨识,仿真研究表明了这种建模方法的有效性,且所得模型精度高,计算量小,可直接应用于基于模型的控制算法。图4表1参18     

电渣重熔过程熔速控制模型的建立

采用递推的带遗忘因子的最小二乘方法,以现场测得的熔炼电流为输入,实际熔化率为模型输出,对电渣重熔过程进行辨识,得到了精度较高的系统时变模型,并证明了模型的可靠性。通过与电渣炉机理建模的结果进行对比,证明了辨识模型的优越性。基于此模型建立的先进控制方法已经成功运用于邢台冶金轧辊集团电渣炉车间,效果良好。     

风力机系统的神经网络模型辨识

应用人工神经网络的建模方法,采用多层感知器的模型结构,利用自适应学习速率的BP学习算法,辨识出风力机系统的功能模型,并把辨识模型的仿真结果与系统实验测量数据相对比,开展了与经典系统辨识方法的比较研究,以检验神经网络模型的可靠性.实验结果表明,这种新的风力机系统建模方法具有很高的精度.     

风力机系统的神经网络模型辨识

应用人工神经网络的建模方法，采用多层感知器的模型结构，利用自适应学习速率的ＢＰ学习算法，辨识出风力机系统的功能模型，并把辨识模型的仿真结果与系统实验测量数据相对比，开展了与经典系统辨识方法的比较研究，以检验神经网络模型的可靠性。实验结果表明，这种新的风力机系统建模方法具有很高的精度。     

应用模糊辨识方法对DMFC电堆的温度特性建模

从甲醇燃料电池（DMFC）电堆实际应用的角度出发,利用模糊技术对DMFC电堆非线性系统进行模型辨识和预测。以阴阳极燃料的流速为的输入量,电堆的工作温度为输出量,利用1000组实验数据作为样本,建立了不同燃料流速下电堆工作温度的动态响应模型。仿真结果证明采用模糊辨识建模的方法是有效的,建立的模型精度较高,从而为设计DMFC电堆实时控制系统奠定了基础。     

水轮机引水系统精细化模型参数辨识研究

由于传统的水轮机调速建模在引水系统部分无法较为准确地辨识参数,针对水力损失函数复杂的模型机理结构,通过黑箱辨识与曲线拟合的方法,搭建了水力损失函数精细化模型。通过改进型的粒子群算法对模型参数进行辨识,改善了粒子群算法收敛性与容易陷入局部最优等问题并用算例验证了模型与方法的有效性。     

Multi-objective exergy-based optimization of a continuous photobioreactor applied to produce hydrogen using a novel combination of soft computing techniques

This work was aimed at proposing a flexible and reliable framework based on combination of three soft computing techniques, i.e., artificial neural network, genetic algorithm, and fuzzy systems for multi-objective exergetic optimization of continuous photobiohydrogen production process from syngas by Rhodospirillum rubrum bacterium. To this end, artificial neural network (ANN) coupled with fuzzy clustering method (FCM) to model exergetic outputs on the basis of input variables. The outputs of modeling system were then fed into a novel optimization approach developed by hybridizing additive linear interdependent fuzzy multi-objective optimization (ALIFMO) and the elitist non-dominated sorting genetic algorithm (NSGA-II). The optimization was carried out to minimize the normalized exergy destruction and maximize the rational and process exergetic efficiencies, simultaneously. The solutions of the proposed approach were also compared with conventional fuzzy multi-objective optimization procedure with independent objectives. Overall, the modeling system predicted the exergetic parameters of photobioreactor with a coefficient of determination higher than 0.90. Furthermore, the optimization approach suggested syngas flow rate of 13.35 mL/min and agitation speed of 383.34 rpm as the best operational condition by considering the preferences of process exergy efficiency, rational exergy efficiency, and normalized exergy destruction, respectively. This condition could yield the normalized exergy destruction of 1.56, process exergetic efficiency of 21.66%, and rational exergetic efficiency of 85.65%. The obtained results showed the superiority of the proposed approach over the conventional fuzzy method in optimizing the complex biofuel production systems.     

Neural network-based self-organizing fuzzy controller for transientstability of multimachine power systems

An efficient self-organizing neural fuzzy controller (SONFC) is designed to improve the transient stability of multimachine power systems. First, an artificial neural network (ANN)-based model is introduced for fuzzy logic control. The characteristic rules and their membership functions of fuzzy systems are represented as the processing nodes in the ANN model. With the excellent learning capability inherent in the ANN, the traditional heuristic fuzzy control rules and input/output fuzzy membership functions can be optimally tuned from training examples by the backpropagation learning algorithm. Considerable rule-matching times of the inference engine in the traditional fuzzy system can be saved. To illustrate the performance and usefulness of the SONFC, comparative studies with a bang-bang controller are performed on the 34-generator Taipower system with rather encouraging results     

Artificial intelligence for the modeling and control of combustion processes: a review

Artificial intelligence (AI) systems are widely accepted as a technology offering an alternative way to tackle complex and ill-defined problems. They can learn from examples, are fault tolerant in the sense that they are able to handle noisy and incomplete data, are able to deal with non-linear problems, and once trained can perform prediction and generalization at high speed. They have been used in diverse applications in control, robotics, pattern recognition, forecasting, medicine, power systems, manufacturing, optimization, signal processing, and social/psychological sciences. They are particularly useful in system modeling such as in implementing complex mappings and system identification. AI systems comprise areas like, expert systems, artificial neural networks, genetic algorithms, fuzzy logic and various hybrid systems, which combine two or more techniques. The major objective of this paper is to illustrate how AI techniques might play an important role in modeling and prediction of the performance and control of combustion process. The paper outlines an understanding of how AI systems operate by way of presenting a number of problems in the different disciplines of combustion engineering. The various applications of AI are presented in a thematic rather than a chronological or any other order. Problems presented include two main areas: combustion systems and internal combustion (IC) engines. Combustion systems include boilers, furnaces and incinerators modeling and emissions prediction, whereas, IC engines include diesel and spark ignition engines and gas engines modeling and control. Results presented in this paper, are testimony to the potential of AI as a design tool in many areas of combustion engineering.     

An exergetically-sustainable operational condition of a photo-biohydrogen production system optimized using conventional and innovative fuzzy techniques

The aim of the present study was to perform an exergy-based multi-objective fuzzy optimization of a continuous photobioreactor applied for biohydrogen production from syngas via the water-gas shift reaction by Rhodospirillum rubrum. For this purpose, the conventional and innovative fuzzy optimization techniques coupled with multilayer perceptron (MLP) neural model to optimize the main exergetic performance parameters of the photobioreactor. The MLP neural model was applied to correlate three dependent variables (rational and process exergy efficiencies and normalized exergy destruction) with two independent variables (syngas flow rate and agitation speed). The developed MLP model was then interfaced with three different multi-objective fuzzy optimization systems with independent, interdependent, and locally modified interdependent objectives. The optimization process was aimed at maximizing the rational exergy and process efficiencies, while minimizing the normalized exergy destruction, simultaneously. Generally, the innovative locally modified interdependent objectives fuzzy system showed a better optimization capabilities compared with the other two fuzzy systems. Accordingly, the optimal syngas photo-fermentation for biohydrogen production in the continuous bioreactor corresponded to the agitation speed of 383.34 rpm and syngas flow rate of 13.35 mL/min in order to achieve the normalized exergy destruction of 1.56, rational exergy efficiency of 85.65%, and process exergy efficiency of 21.66%.     

Generation Cost Assessment of an Isolated Power System With a Fuzzy Wind Power Generation Model

This paper presents a fuzzy set based modeling of wind power generation. The wind power generation has been solved by the proposed fuzzy generation for an island in Taiwan. The cost effectiveness of wind power generation is then evaluated by calculating the avoided generation cost of diesel generators. The load survey study has been performed to find the typical daily load patterns of various customer classes. With the typical load patterns and total energy consumption by each customer class, the load composition and daily power profile of the isolated power system are therefore derived. The wind power generation of eight wind turbines and the corresponding avoided generation cost is estimated by the fuzzy generation model according to the hourly wind speed. The power generation and the corresponding cost of diesel generators required to meet the system power demand with wind power generation have therefore been obtained. It is found that the wind power generation can economically and effectively substitute the generation cost of the diesel power plant and provide the partial power supply capability for the net peak load demand.     

Robust fault tolerant control of DFIG wind energy systems with unknown inputs

This paper proposes a Fuzzy Dedicated Observers (FDOS) method using a Nonlinear Unknown Input Fuzzy Observer (UIFO) with a Fuzzy Scheduler Fault Tolerant Control (FSFTC) algorithm for fuzzy Takagi-Sugeno (TS) systems subject to sensor faults, parametric uncertainties, and time varying unknown inputs. FDOS provide residuals for detection and isolation of sensor faults which can affect a TS model. The TS fuzzy model is adopted for fuzzy modeling of the uncertain nonlinear system and establishing fuzzy state observers. The concept of Parallel Distributed Compensation (PDC) is employed to design FSFTC and fuzzy observers from the TS fuzzy models. TS fuzzy systems are classified into three families based on the input matrices and a FSFTC synthesis procedure is given for each family. In each family, sufficient conditions are derived for robust stabilization, in the sense of Taylor series stability and Lyapunov method, for the TS fuzzy system with parametric uncertainties, sensor faults, and unknown inputs. The sufficient conditions are formulated in the format of Linear Matrix Inequalities (LMIs). The effectiveness of the proposed controller design methodology is finally demonstrated through a wind energy system with Doubly Fed Induction Generators (DFIG) to illustrate the effectiveness of the proposed method.     

Fuzzy thermoeconomic optimization of energy-transforming systems

We have developed a new approach for thermoeconomic analysis of energy-transforming systems based on the sequential uncertainty account to make decisions that simultaneously meet thermodynamic and economic goals. Thermoeconomic optimization has been considered as a fuzzy non-linear programming problem in which local criteria: maximum energy (exergy) efficiency and minimum total cost rate as well as different constraints in an ill-structured situation can be represented by fuzzy sets. The trade-off or the Pareto domain, where the value of a thermodynamic criterion cannot be improved without the value of economic criterion being worsened, has been considered as a first step of optimization strategy. The Bellman–Zadeh model, as the intersection of all fuzzy criteria and constraints, has been used for a final decision-making. Case studies of fuzzy thermoeconomic analysis application have been presented.     

Coolant circuit modeling and temperature fuzzy control of proton exchange membrane fuel cells

Effective temperature management is necessary for the safe and efficient operation of proton exchange membrane fuel cells (PEMFC). Generally circulating coolant can be applied in removing the excess heat of the PEMFC whose electrical power exceeds 5 kW. So a coolant circuit modeling method and a temperature fuzzy control strategy are presented in the paper in order to keep the PEMFC within the ideal operation temperature range. Firstly, a coolant circuit mathematical model is developed, which includes a PEMFC thermal model, a water reservoir model, a water pump model, a bypass valve model, a heat exchanger model and a PEMFC electrochemical model. Secondly, the incremental fuzzy control with integrator technique is designed according to the established model and control experience rule. And the PEMFC temperature and circulating coolant inlet temperature are controlled by regulating the circulating coolant flux and bypass valve factor respectively. Finally, the established model and fuzzy controllers are simulated and analyzed in Matlab software, and the simulation results demonstrate that the incremental fuzzy controller with integrator can effectively control the PEMFC temperature and the inlet coolant temperature within their objective working ranges respectively. In addition, the modeling and control process are very concise, and they can be easily applied in various power classes PEMFC temperature control in real-time.     

Expert diagnosis of polymer electrolyte fuel cells

Diagnosing faulty conditions of engineering systems is a highly desirable process within control structures, such that control systems may operate effectively and degrading operational states may be mitigated. The goal herein is to enhance lifetime performance and extend system availability. Difficulty arises in developing a mathematical model which can describe all working and failure modes of complex systems. However the expert's knowledge of correct and faulty operation is powerful for detecting degradation, and such knowledge can be represented through fuzzy logic. This paper presents a diagnostic system based on fuzzy logic and expert knowledge, attained from experts and experimental findings. The diagnosis is applied specifically to degradation modes in a polymer electrolyte fuel cell. The defined rules produced for the fuzzy logic model connect observed operational modes and symptoms to component degradation. The diagnosis is then tested against common automotive stress conditions to assess functionality.