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.
A new nonlinear identification method of the platinum resistance sensor based on radial basis function neural network using a improved particle swarm optimization algorithm is proposed to settle its nonlinear problem. The particle swarm optimization algorithm is improved by introducing the shrinkage factor and the particle variation factor. The function of the particle fitness is achieved based on...
This paper presents an optimal radial basic function (RBF) neural network for fast restoration of distribution systems under different load levels. Basically, service restoration of distribution systems is a stressful and urgent task that must be performed by system operators. In this paper, a RBF network evolved by an enhanced differential evolution (EDE) algorithm is developed to achieve the fast...
Separable nonlinear least squares (SNLS) problem is a special class of nonlinear least squares (NLS) problems, whose objective function is a mixture of linear and nonlinear functions. It has many applications in many different areas, especially in Operations Research and Computer Sciences. They are difficult to solve with the infinite-norm metric. In this paper, we give a short note on the separable...
The comparative research on Particle Swarm Optimization (PSO) and the Serial -Niche Particle Swarm Optimization (SNPSO) to gain a optimal side-hulls's arrangement of trimaran. With stretched technology in object function, SNPSO improve the velocity of constringency and the efficiency of exploiture. Using the SNPSO in the arrangement of side-hulls, overcoming the disadvantage of losing the optimal...
This paper presents an approach using a high-performance feedback neural network optimizer based on a new idea of successive approximation, for the control of interconnected multi-reservoir systems. The main advantages of the proposed neural network optimizer over the existing neural network optimization models are that no dual variables, penalty parameters, or Lagrange multipliers are required. It...
The FastICA algorithm and the natural gradient algorithm is widely used in blind signal separation, as the two more popular algorithms in the areas of the ICA, because they can find implicit in the observation data in the independent component. However, they each have drawback, such as, online data processing and mass data(such as image data)processing tasks, we need that FastICA algorithm is faster...
In this paper, a one-layer recurrent neural network is presented for solving single-ration linear fractional programming problems subject to linear equality and box bound constraints. The convergence condition is derived to guarantee the solution optimality to the fractional programming problems if the design parameters in the neural network are larger than the derived lower bounds. Two numerical...
Oil-gas drilling cost is an important indicator which reflects the economic benefit of oilfield enterprise. Following taking the characteristics of oil-gas drilling cost which belongs to subsidiary of CNPC (China National Petroleum Corporation) into account, determinants concerning oil-gas drilling cost are identified. Bayesian Regularization Back Propagation Neural Network (BRBPNN) is proposed to...
Recently, a continuous-time k-winners-take-all (kWTA) network with a single state variable and a hard-limiting activation function and its discrete-time counterpart were developed. These kWTA networks have proven properties of finite-time global convergence and simple architectures. In this paper, the kWTA networks are applied for information retrieval, such as web search. The weights or scores of...
Independent Component Analysis (ICA) is a well-known technique for solving blind source separation (BSS) problem. However “classical” ICA algorithms seem not suited for non-negative sources. This paper proposes a gradient descent approach for solving the Non-Negative Independent Component Analysis problem (NNICA). NNICA original separation criterion contains the discontinuous sign function whose minimization...
Fuzzy particle swarm algorithm is a novel optimization method for solving real problems by using both the fuzzy rules and the characteristics of particle swarm algorithm. This paper solves the classical TSP by fuzzy particle swarm algorithm through series of typical instances. The computational results show the effectiveness and robustness of the algorithm in numerical simulation. It can find the...
This paper presents an online system identification method for a linear time-varying system whose parameters change with time. The method is based on an improved generalized ADAptive LINear Element (ADALINE) neural network. It is well known ADALINE is slow in convergence which is not appropriate for online application and identification of time varying system. To speed up convergence of learning and...
Rapid wind fluctuations make the systematic operation of electricity markets with high wind power penetration difficult. A novel dynamic pricing mechanism is presented, which uses a receding horizon principle to allow forecasts of wind power and demand to be incorporated as soon as they are available, and is shown to be capable of reducing dispatch costs on the hours timescale in volatile wind conditions...
In this paper, we investigate the identification of system dynamics of a completely resonant nonlinear wave system described by partial differential equation (PDE) via deterministic learning. Firstly, the wave system is firstly dis-cretized into a finite-dimensional dynamical system described by ordinary differential equation (ODE). Then, it is proved that the finite-dimensional dynamical system keeps...
Let f be functions with singularities at endpoints, and the smooth modulus. The present paper discuss the weighted approximation to functions with singularities and get the converse theorem as follows: w|Bn* (f, x) - f(x)| = O[[φ1-λ(x)/√n]s] → ω2φλ (f, t)w = O(ts)' which generalize the result of Vecchia-Mastroianni-Totik in [2].
A prediction scheme for sunspot series using a Recurrent Neural Network is proposed in this paper. The recurrent neural network adopted in this scheme is the Bilinear recurrent neural network (BRNN). Since the BRNN is based on the bilinear polynomial, BRNN has been successfully used in modeling highly nonlinear systems with time-series characteristics. Dynamic-BRNN (D-BRNN) further improves the convergence...
The neural network with learning and very strong non-linear processing ability, BP neural network used as the neural network model of parameter recognition for transient well test in this paper, the internal connection weights of neural network on representation of the model parameters. Static system by neural network identification method available well test interpretation parameters, BP neural network...
Process neural network (PNN) is a new neural network. This paper intends to improve the training speed of the discrete PNN with a Levenberg-Marquardt modified gradient training algorithm. The training steps and the algorithm are illustrated. Further, an experiment for the prediction of the humidity of sealed boxes is taken as a case study. This modified algorithm is employed in the case study where...
This paper proposed an artificial neural network (ANN) approach based on Lagrangian multiplier method (Lagrangian ANN) to solve the problem of economic load flow in a power system. Operational requirements and transmission losses are also taken care by the proposed approach. Power plant operating costs are represented by exponential cost functions. Simulation on a test example with six generating...
Neural networks can easily fall into a local extremum and have slow convergence rate. Quantum Genetic Algorithm (QGA) has features of small population size and fast convergence. Based on the investigation of QGA, we propose a novel neural network model, Radial Basis Function (RBF) networks optimized by Quantum Genetic Algorithm (QGA-RBF model). Then we investigate the performance of the proposed QGA-RBF...
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.