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.
This paper proposes a neural network (NN) based noise prediction model for electric machines, applied to the case of synchronous reluctance motors (SynRMs). The natural frequencies of various vibration modes for a SynRM stator with generalized tooth geometry and slot numbers have been obtained using structural FEA based computations and then used to build a NN based surrogate model. The accuracy of...
This paper presents the results of Internal Model Control (IMC) for InnoSAT attitude control based on Neural Network (NN). IMC is composed of an inverse model connected in series with the plant and a forward model connected in parallel with the plant. The controller is achieved by estimating the plant and then finding its inverse model of the InnoSAT plant using the NN. The control signal error is...
In this study, a new artificial neuron network model called the meta-controlled Boltzmann machine is introduced. The meta-controlled Boltzmann machine model includes the McCulloch-Pitts model, the Hop field network, and also the Boltzmann machine. The proposed method are applied both diffusion processes and simulated annealing. The convergence proof of the proposed method is shows in this paper. Meta-controlled...
In this paper, based on the noise signal, BBD ball mill material detection method and mill pulverizing system optimization control are presented. The noise of ball mill is decomposed using wavelet packet. The eigenvectors reflecting coal level of mill can be obtained from wavelet packet parameters. Through neural network training, the statistical model of coal level and ball mill eigenvectors is established...
It is of great significance how to identify car licence rapidly and accurately in the modern urban traffic management system. Hopfield NN is a feedback network with association function. It can figure out the weight of network according to some rules and update every nerve cell's state constantly in curse of the network evolvement. This paper presents a method identifying noise of vehicle license...
In this paper, a novel active noise control (ANC) scheme based on neural networks is presented for nonlinear ANC systems without the identification of secondary path by introducing virtual primary noises. The ANC system is analyzed in the form of discrete-time state equations. The proposed controller employs neural networks to attenuate the noises. The proposed scheme does not require the dynamical...
Tracking agile aircraft under high accelerations generally demands sophisticated models for determining trajectories with desirable dynamics and accuracy. Often this raises complexity of the estimation algorithm as it gives rise to more elaborated methods for both taking model nonlinearities into account and handling a greater number of state variables that describe the model. The approach of this...
For an aircraft flying in atmosphere a BP neural network controller based on the active control technology is designed. The design goal is to reject the influence of a rotary gust disturbance to the normal overload of the aircraft. In order to improve the dynamic response of such aircraft, the active control technology which will act on the longitudinal control is proposed. The designed controller...
This paper proposed a method in order to noise effect reduction in a AC voltage reference source. The AC voltage reference source is implemented on MEMS technology. It uses capacitive MEMS technology. The reference is based on the characteristic AC current-voltage curve MEMS component. The multilayer neural network is used. In this simulation, we have assumed the MEMS component is stable. We have...
Flow regeneration noise is a main reason effect on attenuation performance of mufflers, at present no sophisticated software or tool is found to predict effectively flow regeneration noises from mufflers. Prediction of flow regeneration noise from a muffler element of simple expansion chamber is realized using Bp neural network, and comparison of prediction with experiment is carried out. Results...
Aiming at some problems such as ldquoover-fitrdquo with ANN modeling, a new type of combined neural network and corresponding optimal modeling method are proposed in this paper. By this method, expectation error (namely, possible minimum error) is firstly estimated according to data quality; then, optimize network structure and choose optimal training result according to the difference between actual...
This paper proposed a new direct nonlinear controller design method based on virtual reference(VR) and support vector machine(SVM), which allows to directly design nonlinear controller on the base of input/output data with no need of a model of the plant. Firstly, the relation between virtual reference feedback tuning(VRFT) and internal model control(IMC) was analyzed. Then, the structure and design...
FECG (Fetal ECG) signal contains potentially precise information that could assist clinicians in making more appropriate and timely decisions during pregnancy and labour. The extraction and detection of the FECG signal from composite abdominal signals with powerful and advance methodologies is becoming a very important requirement in fetal monitoring. The purpose of this paper is to model the developed...
The main objective of this work is to develop a new method for the blind separation of the noised image. A nonlinear neural network and independent component analysis (ICA) algorithm are combined. The neural network filter is used to remove the noise and ICA algorithm is used for the blind separation of the mixed image. But the effect of pre-filter is different from the post-filter. By comparing the...
The back propagation training algorithm, used to train non-linear feed forward multi-layer artificial neural networks, is capable of estimating the error present in the data presented to a network. While of no use during the training of a network, such information can be useful after training to permit the input data to be itself adjusted to better fit the internal model of a trained neural network...
There are many practical situations in which the chaotic signal appears in the observation in a random manner so that there are intermittent failures in the observation mechanism at certain times. Using weights and network output of neural network as state equation and observation equation to obtain the linear state transition equation, and the chaotic time-series prediction results represented by...
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.