卫星初始速度阻尼智能控制器设计

针对卫星入轨后的初始速率阻尼问题,提出一种基于人脑中情绪学习模型的在线自主自适应控制器。该控制器模拟人脑对感官输入和情绪刺激的处理过程,自主选择适当的控制信号,完成控制任务。设计了基于PID控制和PWPF调制的人脑情绪学习模型智能控制器用以完成卫星初始速率阻尼控制。仿真结果表明,该智能控制器对于卫星转动惯量的不确定性具有较强的鲁棒性,在线学习能力使得智能控制器的性能明显优于PID控制器。     

Applying Brain Emotional Learning Based Intelligent Controller (Belbic) to Multiple‐Area Power Systems

Evolution of efficient power system control is very important. An effective power system simulation is useful for development as an evaluation of control performance. In this paper, a new, efficient simulation of multiple‐area power system control is proposed. We present the application of a Brain Emotional Learning Based Intelligent Controller (BELBIC) to regulate the frequency error for a two‐area interconnected power system. BELBIC is based on the emotional learning process in the Amygdala‐Orbitofrontal system of the mammalian brain. Simulation results of this controller and the PID controller for a two‐area power system in a matlab /simulink environment show that it develops the stability control performance and improves amplitude of oscillations and settling time up to 17% and 24%, respectively. Actually, the simulation shows that the proposed BELBIC model for the matlab /simulink environment works and gives acceptable results, without redesigning it for each separate system.     

Emotion on FPGA: Model driven approach

Implementation of intelligent and bio-inspired algorithms in industrial and real applications is arduous, time consuming and costly; in addition, many aspects of system from high level behavior of algorithm to energy consumption of targeted system must be considered simultaneously in the design process. Advancement of hardware platforms such as DSPs, FPGAs and ASICs in recent years has made it increasingly possible to implement computationally complex intelligent systems; on the other hand, however, the design and testing costs of these systems are high. Reusability and extendibility features of the developed models can decrease the total cost and time-to-market of an intelligent system. In this work, model driven development approach is utilized for implementation of emotional learning as a bio-inspired algorithm for embedded purposes. Recent studies show that emotion is a mechanism for fast decision making in human and other animals, and can be assumed as an expert system. Mathematical models have been developed for describing emotion in mammals from cognitive studies. Here brain emotional based learning intelligent controller (BELBIC), which is based on mammalian middle brain, is designed and implemented on FPGA and the obtained embedded emotional controller (E-BELBIC) is utilized for controlling real laboratorial overhead traveling crane in model-free and embedded manner. Short time-to-market, easy testing and error handling, separating concerns, improving reusability and extendibility of obtained models in similar applications are some benefits of the model driven development methodology.     

Deep brain emotional learning-based intelligent controller applied to an inverted pendulum system

Biologically inspired controllers demonstrate great success in several applications, mainly in situations that present disturbances and uncertainties in the dynamics of the system. In recent times, several works have appeared in the area of emotional learning which occurs in the human brain, thus allowing to the emergence of new theories and applications in control engineering. In control engineering, it is possible to highlight the BELBIC (Brain Emotional Learning-Based Intelligent Controller). However, the design and commissioning of this type of controller still represents a major challenge for researchers, since it is necessary to determine some characteristic signals to this system (stimuli), which can vary from application to application. This work presents a methodology for the construction of architectures for BELBIC stimulus signals, using as a basis the DRL (Deep Reinforcement Learning) techniques. The DRL allows extracting characteristic patterns from the dynamics of systems which, perhaps, may have high dimensionality and possibly nonlinear dynamics, as is the case of most problems involving real-world dynamic systems. The resulting controller model is validated by applying an inverted pendulum dynamic system in order to demonstrate a new approach to the architectures of the BELBIC that allows to achieve a greater generalization in its application, as well as providing a viable alternative to the traditional models in use.

     

A comparative study of various intelligent based controllers for speed control of IPMSM drives in the field-weakening region

Precise speed control of an Interior Permanent Magnet Synchronous Motor (IPMSM) drive becomes a complex issue due to the nonlinear nature of its developed torque. The system nonlinearity becomes severe when the IPMSM drive operates in the field weakening region. In order to achieve perfect control characteristics, the main purpose of this paper is to present a detailed comparison of various intelligent based controllers for flux weakening speed control of an IPMSM drive. In this paper, the Brain Emotional Learning Based Intelligent Controller (BELBIC), Genetic-Fuzzy Logic Based Controller (GFLBC), as well as genetic-PI based controller, are considered. BELBIC is a computational model of emotional processing mechanism in the brain. The effectiveness of the proposed BELBIC controller-based IPMSM drive is verified by simulation results at different operating conditions. Moreover, control regimes such as Maximum Torque Per Ampere (MTPA) control and flux weakening (FW) control as well as voltage and current constraints have been successfully applied. The results prove BELBIC’s perfect control characteristics, such as fast and smooth speed response, low maximum starting current, adaptability to speed and load changes and robustness to parameter variations, disturbance and sudden one-phase interruption.     

A novel design of high-sensitive fuzzy PID controller

A hybrid model is designed by combining the genetic algorithm (GA), radial basis function neural network (RBF-NN) and Sugeno fuzzy logic to determine the optimal parameters of a proportional-integral-derivative (PID) controller. Our approach used the rule base of the Sugeno fuzzy system and fuzzy PID controller of the automatic voltage regulator (AVR) to improve the system sensitive response. The rule base is developed by proposing a feature extraction for genetic neural fuzzy PID controller through integrating the GA with radial basis function neural network. The GNFPID controller is found to possess excellent features of easy implementation, stable convergence characteristic, good computational efficiency and high-quality solution. Our simulation provides high sensitive response (∼0.005 s) of an AVR system compared to the real-code genetic algorithm (RGA), a linear-quadratic regulator (LQR) method and GA. We assert that GNFPID is highly efficient and robust in improving the sensitive response of an AVR system.     

Implementation of genetic algorithm in an embedded microcontroller-based polarization control system

Implementation of genetic algorithm in a PIC32MX microcontroller-based polarization control system is proposed and demonstrated. The controller measures the signal intensity that is used to estimate the genetic value. This process is controlled by the genetic algorithm rather than referring to the Look-Up-Table as implemented in existing solutions. To reach optimum performance, the code is optimized by using the best genetic parameters so that the fastest execution time can be achieved. An ability of genetic algorithm to work efficiently in polarization control system possesses many advantages including easy code construction, low memory consumption and fast control speed. Genetic algorithm is intelligent enough to be used for endless polarization stabilization and in the worst case, able to stabilize the polarization changes in 300 μs. In the best case the response time can reach 17 μs.     

An automated signalized junction controller that learns strategies by temporal difference reinforcement learning

This paper shows how temporal difference learning can be used to build a signalized junction controller that will learn its own strategies through experience. Simulation tests detailed here show that the learned strategies can have high performance. This work builds upon previous work where a neural network based junction controller that can learn strategies from a human expert was developed (Box and Waterson, 2012). In the simulations presented, vehicles are assumed to be broadcasting their position over WiFi giving the junction controller rich information. The vehicle's position data are pre-processed to describe a simplified state. The state-space is classified into regions associated with junction control decisions using a neural network. This classification is the strategy and is parametrized by the weights of the neural network. The weights can be learned either through supervised learning with a human trainer or reinforcement learning by temporal difference (TD). Tests on a model of an isolated T junction show an average delay of 14.12 s and 14.36 s respectively for the human trained and TD trained networks. Tests on a model of a pair of closely spaced junctions show 17.44 s and 20.82 s respectively. Both methods of training produced strategies that were approximately equivalent in their equitable treatment of vehicles, defined here as the variance over the journey time distributions.     

Online tuning fuzzy PID controller using robust extended Kalman filter

Fuzzy PID controllers have been developed and applied to many fields for over a period of 30 years. However, there is no systematic method to design membership functions (MFs) for inputs and outputs of a fuzzy system. Then optimizing the MFs is considered as a system identification problem for a nonlinear dynamic system which makes control challenges. This paper presents a novel online method using a robust extended Kalman filter to optimize a Mamdani fuzzy PID controller. The robust extended Kalman filter (REKF) is used to adjust the controller parameters automatically during the operation process of any system applying the controller to minimize the control error. The fuzzy PID controller is tuned about the shape of MFs and rules to adapt with the working conditions and the control performance is improved significantly. The proposed method in this research is verified by its application to the force control problem of an electro-hydraulic actuator. Simulations and experimental results show that proposed method is effective for the online optimization of the fuzzy PID controller.     

On active acceleration control of vibration isolation systems

Active vibration isolation systems (VIS) have been widely used from the space shuttle applications to the ground vehicle suspensions. The main control objective is to achieve the minimum vibrations at the flotor for given vibrations at the stator. With respect to a fundamental limitation of using the PD type flotor acceleration controller, an I (integral) and II (double integral) type flotor acceleration controller is proposed in this paper. By incorporating the feedforward compensation of the umbilical dynamics, the proposed acceleration controller is able to experimentally push down the lowest isolation frequency from 1.4 Hz (when PID control is used) to 0.03 Hz with a sufficiently improved vibration isolation performance up to 10 Hz, with respect to a MIM (Microgravity Vibration Isolation Mount) system tested on the ground. A unique frequency selective filter (FSF) is also proposed, which experimentally suppresses a fixed-frequency umbilical resonant mode at 22.2 Hz with an attenuation of 20 dB.     

三自由度飞行器模型的神经网络PID控制

对于具有非线性、时变和强耦合特性的三自由度飞行器模型系统,采用常规PID控制方法难以获得满意的控制效果,因此,设计一种基于免疫遗传算法优化的RBF网络PID控制器来实现该系统的稳态控制.在控制系统中,RBF网络实现对被控对象的Jacobian矩阵信息辨识,并通过在线学习自适应地调整PID参数;免疫遗传算法用于RBF网络的初值参数优化,以确保获得理想的控制效果.仿真实验表明,这种方法的控制品质优于LQR控制,具有较好的适应能力、鲁棒性和较快的响应速度.     

Sugeno fuzzy PID tuning,by genetic-neutral for AVR in electrical power generation

We report a novel design method for determining the optimal proportional-integral-derivative (PID) controller parameters of an automatic voltage regulator (AVR) system, using a combined genetic algorithm (GA), radial basis function neural network (RBF-NN) and Sugeno fuzzy logic approaches. GA and a RBF-NN with a Sugeno fuzzy logic are proposed to design a PID controller for an AVR system (GNFPID). The problem for obtaining the optimal AVR and PID controller parameters is formulated as an optimization problem and RBF-NN tuned by GA is applied to solve the optimization problem. Whereas, optimal PID gains obtained by the proposed RBF tuning by genetic algorithm for various operating conditions are used to develop the rule base of the Sugeno fuzzy system and design fuzzy PID controller of the AVR system to improve the system's response (∼0.005 s). The proposed approach has superior features, including easy implementation, stable convergence characteristic, good computational efficiency and this algorithm effectively searches for a high-quality solution and improve the transient response of the AVR system (7E−06). Numerical simulation results demonstrate that this is faster and has much less computational cost as compared with the real-code genetic algorithm (RGA) and Sugeno fuzzy logic. The proposed method is indeed more efficient and robust in improving the step response of an AVR system.     

Forecasting of short-term traffic-flow based on improved neurofuzzy models via emotional temporal difference learning algorithm

Bounded rationally idea, rather that optimization idea, have result and better performance in decision making theory. Bounded rationality is the idea in decision making, rationality of individuals is limited by the information they have, the cognitive limitations of their minds, and the finite amount of time they have to make decisions. The emotional theory is an important topic presented in this field. The new methods in the direction of purposeful forecasting issues, which are based on cognitive limitations, are presented in this study. The presented algorithms in this study are emphasizes to rectify the learning the peak points, to increase the forecasting accuracy, to decrease the computational time and comply the multi-object forecasting in the algorithms. The structure of the proposed algorithms is based on approximation of its current estimate according to previously learned estimates. The short term traffic flow forecasting is a real benchmark that has been studied in this area. Traffic flow is a good measure of traffic activity. The time-series data used for fitting the proposed models are obtained from a two lane street I-494 in Minnesota City, USA. The research discuss the strong points of new method based on neurofuzzy and limbic system structure such as Locally Linear Neurofuzzy network (LLNF) and Brain Emotional Learning Based Intelligent Controller (BELBIC) models against classical and other intelligent methods such as Radial Basis Function (RBF), Takagi–Sugeno (T–S) neurofuzzy, and Multi-Layer Perceptron (MLP), and the effect of noise on the performance of the models is also considered. Finally, findings confirmed the significance of structural brain modeling beyond the classical artificial neural networks.     

Predicting Chaotic Time Series Using Neural and Neurofuzzy Models: A Comparative Study

The prediction accuracy and generalization ability of neural/neurofuzzy models for chaotic time series prediction highly depends on employed network model as well as learning algorithm. In this study, several neural and neurofuzzy models with different learning algorithms are examined for prediction of several benchmark chaotic systems and time series. The prediction performance of locally linear neurofuzzy models with recently developed Locally Linear Model Tree (LoLiMoT) learning algorithm is compared with that of Radial Basis Function (RBF) neural network with Orthogonal Least Squares (OLS) learning algorithm, MultiLayer Perceptron neural network with error back-propagation learning algorithm, and Adaptive Network based Fuzzy Inference System. Particularly, cross validation techniques based on the evaluation of error indices on multiple validation sets is utilized to optimize the number of neurons and to prevent over fitting in the incremental learning algorithms. To make a fair comparison between neural and neurofuzzy models, they are compared at their best structure based on their prediction accuracy, generalization, and computational complexity. The experiments are basically designed to analyze the generalization capability and accuracy of the learning techniques when dealing with limited number of training samples from deterministic chaotic time series, but the effect of noise on the performance of the techniques is also considered. Various chaotic systems and time series including Lorenz system, Mackey-Glass chaotic equation, Henon map, AE geomagnetic activity index, and sunspot numbers are examined as case studies. The obtained results indicate the superior performance of incremental learning algorithms and their respective networks, such as, OLS for RBF network and LoLiMoT for locally linear neurofuzzy model.     

基于PID神经元网络的智能车控制系统研究

研究了基于PID神经元网络的智能车多变量控制系统。智能车的转向控制与速度控制相互关联、相互影响、且都具有时变性,针对智能车在行驶时要求电机的动态响应速度要快、舵机的动态响应时间要短的特点,提出了将PID神经元网络（PIDNN）控制器及其算法应用到智能车的控制系统中来对传统PID控制进行改进。PIDNN控制系统不依赖智能车电机与舵机的数学模型,能够根据控制效果在线训练和学习,调整网络连接权重值,最终使系统的目标函数达到最小来实现智能车的精确控制。Matlab仿真测试表明,PIDNN控制系统的响应快,超调小、无静差,与传统PID控制算法相比,大大提高了智能车控制系统的性能。     

基于模糊RBF神经网络的PID及其应用

针对传统的PID控制器参数固定而导致在控制中效果差的问题,提出一种基于模糊RBF神经网络智能PID控制器的设计方法。该方法结合了模糊控制的推理能力强与神经网络学习能力强的特点,将模糊控制与RBF神经网络相结合以在线调整PID控制器参数,整定出一组适合于控制对象的kp, ki, kd参数。将算法运用到电机控制系统的PID参数寻优中,仿真结果表明基于此算法设计的PID控制器改善了电机控制系统的动态性能和稳定性。     

Bioreactor profile control by a nonlinear auto regressive moving average neuro and two degree of freedom PID controllers

This paper presents the use of nonlinear auto regressive moving average (NARMA) neuro controller for temperature control and two degree of freedom PID (2DOF-PID) for pH and dissolved oxygen (DO) of a biochemical reactor in comparison with the industry standard anti-windup PID (AWU-PID) controllers. The process model of yeast fermentation described in terms of temperature, pH and dissolved oxygen has been used in this study. Nonlinear auto regressive moving average (NARMA) neuro controller used for temperature control has been trained by Levenberg–Marquardt training algorithm. The 2DOF-PID controllers used for pH and dissolved oxygen have been tuned by MATLAB's auto tune feature along with manual tuning. Random training data with input varying from 0 to 100 l/h have been obtained by using NARMA graphical interface. The data samples used for training, validation and testing are 20,000, 10,000 and 10,000 respectively. Random profiles have been used for simulation. The NARMA neuro controller and the 2DOF-PID controllers have shown improvement in rise time, residual error and overshoot. The proposed controllers have been implemented on TMS320 Digital Signal Processing board using code composure studio. Arduino Mega board has been used for input/output interface.     

Fuzzy modeling and stable model predictive tracking control of large-scale power plants

This paper develops a stable model predictive tracking controller (SMPTC) for coordinated control of a large-scale power plant. First, a Takagi–Sugeno (TS) fuzzy model is established to approximate the behavior of the boiler–turbine coordinated control system (CCS) using fuzzy clustering and subspace identification (SID). Then, an SMPTC is designed based on the fuzzy model to track the power and pressure set-points while guaranteeing the input-to-state stability and the input constraints of the system. An output-based objective function is adopted for the proposed SMPTC so that the controller could be directly applicable for the data-driven model. Moreover, the effect of modeling mismatches and unknown plant variations has been overcome by the use of a disturbance term and steady-state target calculator (SSTC). Simulation results for a 600 MW power plant show that an off-set free tracking performance can be achieved over a wide range load variation.     

非线性动态系统神经模糊建模与内模/PID双重控制系统设计

非线性动态系统的内模控制要求建立精确的对象正模型和逆模型,这对于大多数实际对象是难以做到.提出了基于一类神经模糊模型的非线性动态系统建模方法,并在此基础上研究了基于神经模糊模型的非线性系统的内模控制设计.基于输入输出数据辨识的对象正模型和逆模型存在着模型失配问题,导致神经模糊内模控制范围变窄和控制鲁棒性降低,为了改善系统的性能,提出了神经模糊内模控制与PID控制结合的双重控制策略.对CSTR的反应物浓度控制研究表明,双重控制策略能有效地拓宽系统可控范围,改善系统性能.仿真结果证明该控制策略简单而有效.     

A learning method for multivariable PID control synthesis based on estimated plant Jacobian

Despite decades of research involving optimal control of multivariable systems, such controllers require accurate linear models of the plant dynamics. Real systems contain nonlinearities and high-order dynamics that may be difficult to model using conventional techniques. This paper presents a novel learning control (LC) method for PID controllers that doesn’t require explicit modeling of the plant dynamics. This method utilizes gradient descent techniques to iteratively reduce an error-related objective function. Simulations involving a hydrofoil catamaran show that the proposed PID-LC algorithm improves controller performance compared to LQR controllers derived from multivariable models.