The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Wind power generation has the characteristics of intermittency and uncertainty. It is significant to predict intervals of short-term wind power precisely for optimizing the grid power system operation scheduling and reserve capacity. The paper proposed a simple short-term wind power intervals prediction model based on artificial bee colony-neural network (ABC-NN). A new criterion was developed in...
In this note, an adaptive control scheme is developed for the time-delayed nonlinear Markovian jump systems. The explosion of complexity in traditional backstepping design is avoided by utilizing dynamic surface control. Filters are constructed to provide the proper auxiliary signals. Neural networks are employed to estimate the unknown continuous functions. A novel Lyapunov function is proposed,...
To solve the currently existing problems of time consuming and low flexibility in warfare simulation experiment, an intelligent control method based on neural network is advanced, imitating human's thinking process of decision. Firstly, the main general idea and framework of the intelligent control are introduced. Secondly, the structure and training algorithm of three layered feedforward neural network,...
It is difficult to establish an accurate model of technical energy consumption due to the problem of too many parameters and high interference in the process of aluminum electrolysis. An improved UKFNN algorithm named Square Root Unscented Kalman Neural Networks (SRUKFNN) is proposed to establish the technical energy consumption model of aluminum electrolysis in this paper. In the model, square root...
This paper addresses the problem of coordinated formation control for multiple surface vessels, a distributed adaptive coordinated formation control strategy based on virtual leader is present. Firstly, with the passivity-based techniques, a guided system which gives out desired trajectory signal for follower vessels is designed. Then, considering the uncertainty in mathematical mode of the vessel,...
Fractional order PID, which involve integration and differentiation of non-integer order, is increasingly being used in the fields of control system, robotics, signal processing and circuit theory. Based on neural network, this paper introduce a new approach for design fractional order PID controller. A self-learning PID controller with five dimension parameters is realized by using parameter turning...
In this paper a novel feature extraction algorithm is proposed which uses Genetic Algorithm (GA) inorder to optimize the output node from Trained artificial neural network (ANN). Basically this algorithm does not change the training process and nor does modify the results. It only extract the relevant features and discard the redundant feature. The weights between the input node to hidden node and...
This paper deals with application of deep learning neural network for power system fault diagnosis. Deep learning is a more effective approach than traditional neural network to solve problems including availability of data, better local optimum, and diffusion of gradients. In the paper, data is extracted from power system dispatching department and preprocessed before training in the deep learning...
A Hammerstein Model based on neural networks is proposed for piezoelectric actuators (PEA) hysteresis dynamics. An elementary hysteresis operator is constructed to describe the hysteresis information, which is used with a Neural Network to represent the static nonlinear part of the PEA. An Autoregressive Model with Exogenous Input model is used to model the rate-dependent properties of the actuator...
In this thesis, the Super-Twisting control algorithm is used to analyze the nonlinear control system based on U model. The non-affine nonlinear systems are described, and the 1-order and n-order nonlinear system is designed. The neural network approximation of the nonlinear function is performed by Super-Twisting control algorithm. The convergence of Super-Twisting algorithm is proved by the appropriate...
This paper investigates the synchronization problem for a class of delayed neural networks with Markovian switching parameters by using adaptive control scheme. A new delayed neural networks model with Markovian switching parameters and adaptive coupling strengths is established. By utilizing adaptive scheme, M-matrix approach and Lyapunov theory, sufficient criteria for a class of delayed neural...
Real time evaluation of rivers water quality has great significance for maintenances and protection of water resources. In the case of Huaihe River, we took advantages of LVQ (Learning Vector Quantization, LVQ) to classify the water qualities. Comparing with BP neural network and RBF neural network. LVQ neural network has the advantages of simple structure, self-learning, self-organization, and nonlinear...
A novel model of coagulant dosing control is proposed based on a fuzzy logic approach. The actual process data of a water treatment plant are first classified by using fuzzy c-means clustering method to obtain the class center. In combination with k-nearest neighbor algorithm, the premise parameter of Takagi-Sugeno fuzzy model can be generated. Then, the recursive least square method is used to determine...
This paper investigates the adaptive group consensus of multiple robotic manipulator systems in task space under directed acyclic graph topology. Two adaptive control strategies are proposed based on parameters linearity method and neural network method, respectively. The criteria for solving group consensus problems are established by using Lyapunov approach. It is shown that, under some reasonable...
Based on the sequential batch reactor (SBR) simulation model of the wastewater treatment process for a secondary fiber paper mill that we have developed, two control strategies, a neural network (BP-PID controller) and a fuzzy logic system (Fuzzy-PID controller), were separately combined with PID to control the dissolved oxygen (DO) concentration in the SBR process of paper mill. Two cases, without...
This paper considers the tracking fault-tolerant controller design problem for a class of nonlinear systems with unknown functions and actuator dead-zone. Based on dynamic surface control scheme and neural network approximated technique, some assumptions on nonlinear functions are removed. Also, the structure of controller is simple without the problem of ‘explosion of complexity’. Simultaneously,...
For the ultralow altitude airdrop decline stage, many factors such as actuator nonlinearity, the uncertain atmospheric disturbances and model unknown nonlinearity affect the precision of trajectory tracking, A robust adaptive neural network dynamic surface control method is proposed. The ultra-low altitude airdrop longitudinal dynamics with actuator input nonlinearity is established, the neural network...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.