共查询到20条相似文献，搜索用时 187 毫秒
1.
A new paradigm called self-recurrent neural network (SRNN) is proposed. Two SRNNs are utilized in a control system, one as an emulator and the other as a controller. To guarantee convergence and for faster learning, an approach using adaptive learning rate is developed by Lyapunov function. Finally, the neural network control algorithm is developed for on-line control of structural seismic response in real time. Simulation-results have shown that it can effectively control structural seismic response and make it consist with the desired response. © 1998 John Wiley & Sons, Ltd. 相似文献
2.
Prediction of effective porosity from seismic attributes using locally linear model tree algorithm 
下载免费PDF全文
下载免费PDF全文 Ahmad Ashtari Talkhestani 《Geophysical Prospecting》2015,63(3):680-693
In this study, a locally linear model tree algorithm was used to optimize a neuro‐fuzzy model for prediction of effective porosity from seismic attributes in one of Iranian oil fields located southwest of Iran. Valid identification of effective porosity distribution in fractured carbonate reservoirs is extremely essential for reservoir characterization. These high‐accuracy predictions facilitate efficient exploration and management of oil and gas resources. The multi‐attribute stepwise linear regression method was used to select five out of 26 seismic attributes one by one. These attributes introduced into the neuro‐fuzzy model to predict effective porosity. The neuro‐fuzzy model with seven locally linear models resulted in the lowest validation error. Moreover, a blind test was carried out at the location of two wells that were used neither in training nor validation. The results obtained from the validation and blind test of the model confirmed the ability of the proposed algorithm in predicting the effective porosity. In the end, the performance of this neuro‐fuzzy model was compared with two regular neural networks of a multi‐layer perceptron and a radial basis function, and the results show that a locally linear neuro‐fuzzy model trained by a locally linear model tree algorithm resulted in more accurate porosity prediction than standard neural networks, particularly in the case where irregularities increase in the data set. The production data have been also used to verify the reliability of the porosity model. The porosity sections through the two wells demonstrate that the porosity model conforms to the production rate of wells. Comparison of the locally linear neuro‐fuzzy model performance on different wells indicates that there is a distinct discrepancy in the performance of this model compared with the other techniques. This discrepancy in the performance is a function of the correlation between the model inputs and output. In the case where the strength of the relationship between seismic attributes and effective porosity decreases, the neuro‐fuzzy model results in more accurate prediction than regular neural networks, whereas the neuro‐fuzzy model has a close performance to neural networks if there is a strong relationship between seismic attributes and effective porosity. The effective porosity map, presented as the output of the method, shows a high‐porosity area in the centre of zone 2 of the Ilam reservoir. Furthermore, there is an extensive high‐porosity area in zone 4 of Sarvak that extends from the centre to the east of the reservoir. 相似文献
3.
Vibration mitigation using smart, reliable and cost‐effective mechanisms that requires small activation power is the primary objective of this paper. A semi‐active controller‐based neural network for base‐isolation structure equipped with a magnetorheological (MR) damper is presented and evaluated. An inverse neural network model (INV‐MR) is constructed to replicate the inverse dynamics of the MR damper. Next, linear quadratic Gaussian (LQG) controller is designed to produce the optimal control force. Thereafter, the LQG controller and the INV‐MR models are linked to control the structure. The coupled LQG and INV‐MR system was used to train a semi‐active neuro‐controller, designated as SA‐NC, which produces the necessary control voltage that actuates the MR damper. To evaluate the proposed method, the SA‐NC is compared to passive lead–rubber bearing isolation systems (LRBs). Results revealed that the SA‐NC was quite effective in seismic response reduction for wide range of motions from moderate to severe seismic events compared to the passive systems. In addition, the semi‐active MR damper enjoys many desirable features, such as its inherent stability, practicality and small power requirements. The effectiveness of the SA‐NC is illustrated and verified using simulated response of a six‐degree‐of‐freedom model of a base‐isolated building excited by several historical earthquake records. Copyright © 2006 John Wiley & Sons, Ltd. 相似文献
4.
Applying active control systems to civil engineering structures subjected to dynamic loading has received increasing interest. This study proposes an active pulse control model, termed unsupervised fuzzy neural network structural active pulse controller (UFN‐SAP controller), for controlling civil engineering structures under dynamic loading. The proposed controller combines an unsupervised neural network classification (UNC) model, an unsupervised fuzzy neural network (UFN) reasoning model, and an active pulse control strategy. The UFN‐SAP controller minimizes structural cumulative responses during earthquakes by applying active pulse control forces determined via the UFN model based on the clusters, classified through the UNC model, with their corresponding control forces. Herein, we assume that the effect of the pulses on structure is delayed until just before the next sampling time so that the control force can be calculated in time, and applied. The UFN‐SAP controller also averts the difficulty of obtaining system parameters for a real structure for the algorithm to allow active structural control. Illustrative examples reveal significant reductions in cumulative structural responses, proving the feasibility of applying the adaptive unsupervised neural network with the fuzzy classification approach to control civil engineering structures under dynamic loading. Copyright © 2001 John Wiley & Sons, Ltd. 相似文献
5.
Accurate forecasting of hydrological time‐series is a quite important issue for a wise and sustainable use of water resources. In this study, an adaptive neuro‐fuzzy inference system (ANFIS) approach is used to construct a time‐series forecasting system. In particular, the applicability of an ANFIS to the forecasting of the time‐series is investigated. To illustrate the applicability and capability of an ANFIS, the River Great Menderes, located in western Turkey, is chosen as a case study area. The advantage of this method is that it uses the input–output data sets. A total of 5844 daily data sets collected from 1985 to 2000 are used for the time‐series forecasting. Models having various input structures were constructed and the best structure was investigated. In addition, four various training/testing data sets were built by cross‐validation methods and the best data set was obtained. The performance of the ANFIS models in training and testing sets was compared with observations and also evaluated. In order to get an accurate and reliable comparison, the best‐fit model structure was also trained and tested by artificial neural networks and traditional time‐series analysis techniques and the results compared. The results indicate that the ANFIS can be applied successfully and provide high accuracy and reliability for time‐series modelling. Copyright © 2007 John Wiley & Sons, Ltd. 相似文献
6.
Various types of neural networks have been proposed in previous papers for applications in hydrological events. However, most of these applied neural networks are classified as static neural networks, which are based on batch processes that update action only after the whole training data set has been presented. The time variate characteristics in hydrological processes have not been modelled well. In this paper, we present an alternative approach using an artificial neural network, termed real‐time recurrent learning (RTRL) for stream‐flow forecasting. To define the properties of the RTRL algorithm, we first compare the predictive ability of RTRL with least‐square estimated autoregressive integrated moving average models on several synthetic time‐series. Our results demonstrate that the RTRL network has a learning capacity with high efficiency and is an adequate model for time‐series prediction. We also investigated the RTRL network by using the rainfall–runoff data of the Da‐Chia River in Taiwan. The results show that RTRL can be applied with high accuracy to the study of real‐time stream‐flow forecasting networks. Copyright © 2002 John Wiley & Sons, Ltd. 相似文献
7.
A computational algorithm for maximizing the control efficiency in actively controlling the elastic structural responses during earthquake is proposed. Study of optimal linear control using a single degree of freedom shows that applying active control is very effective in reducing the structural displacement and velocity responses for long‐period structures, but at the same time it has an adverse effect in increasing the absolute acceleration response. The extent of this adverse effect reduces the effectiveness of the control system, and therefore it poses a limit on the maximum control force in order to provide maximum control efficiency. In view of this shortcoming, maximum control energy dissipation is used to define the most effective optimal linear control law. Less displacement and velocity response are expected as larger control force is applied, but there is always a limit that maximum control energy can be dissipated. This study shows that this limit depends on the structural characteristics as well as the input ground motion, and a general trend is that the maximum control energy decreases as damping increases. Finally, application of the proposed algorithm on a six‐storey hospital building is presented to show the effectiveness of using optimal linear control on a multi‐degree‐of‐freedom system from the control energy perspectives. Copyright © 2001 John Wiley & Sons, Ltd. 相似文献
8.
The discrete‐time variable structure control method for seismically excited linear structures with time delay in control is investigated in this paper. The control system with time delay is first discretized and transformed into standard discrete form which contains no time delay in terms of the time delay being integer and non‐integer times of sampling period, respectively. Then the discrete switching surface is determined using ideal quasi‐sliding mode and discrete controller is designed using the discrete approach‐law reaching condition. The deduced controller and switching surface contain not only the current step of state feedback but also linear combination of some former steps of controls. Numerical simulations are illustrated to verify the feasibility and robustness of the proposed control method. Since time‐delay effect is incorporated in the mathematical model for the structural control system throughout the derivation of the proposed algorithm, system performance and dynamic stability are guaranteed. Copyright © 2002 John Wiley & Sons, Ltd. 相似文献
9.
This paper evaluates the feasibility of using an artificial neural network (ANN) methodology for estimating the groundwater levels in some piezometers placed in an aquifer in north‐western Iran. This aquifer is multilayer and has a high groundwater level in urban areas. Spatiotemporal groundwater level simulation in a multilayer aquifer is regarded as difficult in hydrogeology due to the complexity of the different aquifer materials. In the present research the performance of different neural networks for groundwater level forecasting is examined in order to identify an optimal ANN architecture that can simulate the piezometers water levels. Six different types of network architectures and training algorithms are investigated and compared in terms of model prediction efficiency and accuracy. The results of different experiments show that accurate predictions can be achieved with a standard feedforward neural network trained usung the Levenberg–Marquardt algorithm. The structure and spatial regressions of the ANN parameters (weights and biases) are then used for spatiotemporal model presentation. The efficiency of the spatio‐temporal ANN (STANN) model is compared with two hybrid neural‐geostatistics (NG) and multivariate time series‐geostatistics (TSG) models. It is found in this study that the ANNs provide the most accurate predictions in comparison with the other models. Based on the nonlinear intrinsic ANN approach, the developed STANN model gives acceptable results for the Tabriz multilayer aquifer. Copyright © 2008 John Wiley & Sons, Ltd. 相似文献
10.
作为深度学习方法的一种,长短时记忆神经网络(LSTM)是一种信号处理的重要方法.本文基于实际观测地电场数据来合成训练集,对特定结构的长短时记忆神经网络进行训练,将训练所得网络对测试集数据进行测试后,将网络应用至实际观测数据.结果显示,经过训练的网络很好地学到了训练集样本的特征,对测试集数据的信噪比压制了约20 dB,并过滤了人为添加的特定频率的干扰成分,对实际观测数据处理后得到明显的日变、半日变以及半月变、月变、半年变、年变等潮汐响应,表明长短时记忆神经网络可以有效应用于地电场数据处理研究. 相似文献
11.
A new inelastic structural control algorithm is proposed by incorporating the force analogy method (FAM) with the predictive instantaneous optimal control (PIOC) algorithm. While PIOC is very effective in compensating for the time delay for elastic structures, the FAM is highly efficient in performing the inelastic analysis. Unlike conventional inelastic analysis methods of changing stiffness, the FAM analyzes structures by varying the structural displacement field, and therefore the state transition matrix needs to be computed only once. This greatly simplifies the computation and makes inelastic analysis readily applicable to the PIOC algorithm. The proposed algorithm compensates for the time delay that happens in practical control systems by predicting the inelastic structural response over a period that equals the magnitude of the time delay. A one‐story frame with both strain‐hardening and strain‐softening inelastic characteristics is analyzed using this algorithm. Results show that the proposed control algorithm is feasibile for any inelastic structures. While the control efficiency deteriorates with the increase in magnitude of the time delay, the PIOC maintains acceptable performance within a wide range of time delay magnitudes. Finally, a computer model of a six‐story moment‐resisting steel frame is analyzed to show that PIOC has good control results for real inelastic structures. Copyright © 2003 John Wiley & Sons, Ltd. 相似文献
12.
The classical performance index optimization control algorithm is considered in order to check the real optimality of the control procedure; the basic steps for the optimal algorithm are reviewed, and the equation for the optimal control force derived. It is shown that the optimality conditions cannot be met with regard to the performance index, unless one is concerned with simple free oscillations. It is proved that in this case on one side the optimal control turns out to be of the linear closed‐loop type, yielding explicit optimal control coefficients, and on the other side that no solution can exist of the optimal problem for a generic forcing function. It is concluded that one is forced to calibrate the control force for free oscillations, and that the reliability of the index procedure mainly rests on some implicit expectation that linear control can be calibrated in the absence of the external disturbance and that it works under forced oscillations as well. Furthermore, the problem of delayed active control, with reference to a s.d.o.f. system controlled by a closed‐loop linear algorithm and under the action of a dynamic forcing function is investigated. In particular, the effects produced on the response of the structure by the introduction in the control law of assessed critical values of time delay are analysed and the comparison is proposed between the numerical results that one gets by adopting two different procedures (on one hand the above‐mentioned optimal linear control law and on the other hand the constrained minimization of the structural response norm) to compensate for time lag occurring in the actuation of the active control servomechanisms. Copyright © 2000 John Wiley & Sons, Ltd. 相似文献
13.
A semi‐active fuzzy control strategy for seismic response reduction using a magnetorheological (MR) damper is presented. When a control method based on fuzzy set theory for a structure with a MR damper is used for vibration reduction of a structure, it has an inherent robustness, and easiness to treat the uncertainties of input data from the ground motion and structural vibration sensors, and the ability to handle the non‐linear behavior of the structure because there is no longer the need for an exact mathematical model of the structure. For a clipped‐optimal control algorithm, the command voltage of a MR damper is set at either zero or the maximum level. However, a semi‐active fuzzy control system has benefit to produce the required voltage to be input to the damper so that a desirable damper force can be produced and thus decrease the control force to reduce the structural response. Moreover, the proposed control strategy is fail‐safe in that the bounded‐input, bounded‐output stability of the controlled structure is guaranteed. The results of the numerical simulations show that the proposed semi‐active control system consisting of a fuzzy controller and a MR damper can be beneficial in reducing seismic responses of structures. Copyright © 2004 John Wiley & Sons, Ltd. 相似文献
14.
A neural network is employed to select earthquake waves in a time history approach for structural dynamics. The neural network is a preferable alternative to an expert system because knowledge can easily be renewed. It involves a back propagation model having three layers (one input, one hidden and one output layer) and is used to avoid inappropriate earthquake input prior to practical numerical computations. Knowledge to categorize the earthquake waves is acquired through network training with earthquake response spectra and structural responses. The trained network is tested by categorizing the responses of three types of unknown structures caused by 50 previously recorded earthquakes. Comparisons are made with analogous data from the traditional site dominant period method. Results demonstrate that, unlike the latter method, a neural network is generally more successful as the number of training patterns increases. 相似文献
15.
In this paper an approach is developed for establishing optimal maintenance (repair) strategies of structures in seismic zones. The approach is based on expected future costs and the main decision variable is a damage threshold for repair given an acceptable reliability level. It is considered that structural damage accumulates over a number of earthquakes until a threshold is reached or exceeded, after which the structure is repaired so that there is no remaining damage. A Markov model is implemented for such a process of damage accumulation during future earthquakes. An algorithm is proposed for computing non‐linear structural response to earthquakes using a damage function model. This algorithm is used to evaluate transition probabilities between damage states based on simulations of future earthquakes of given intensities. Expressions are derived for evaluating expected life‐cycle damage costs and structural reliability as a function of time and of the damage threshold for repair. As an application, a single‐degree‐of‐freedom structural system is studied. In addition, the paper addresses the case of instrumented structures where information from earthquake response records is available. Such information is incorporated into the formulation for maintenance strategies by means of a Bayesian approach for updating the probability distribution of structural damage and of non‐linear behaviour parameters so that predictions about costs and reliability are improved. Copyright © 2002 John Wiley & Sons, Ltd. 相似文献
16.
Forecasting river flow is important to water resources management and planning. In this study, an artificial neural network (ANN) model was successfully developed to forecast river flow in Apalachicola River. The model used a feed‐forward, back‐propagation network structure with an optimized conjugated training algorithm. Using long‐term observations of rainfall and river flow during 1939–2000, the ANN model was satisfactorily trained and verified. Model predictions of river flow match well with the observations. The correlation coefficients between forecasting and observation for daily, monthly, quarterly and yearly flow forecasting are 0·98, 0·95, 0·91 and 0·83, respectively. Results of the forecasted flow rates from the ANN model were compared with those from a traditional autoregressive integrated moving average (ARIMA) forecasting model. Results indicate that the ANN model provides better accuracy in forecasting river flow than does the ARIMA model. Copyright © 2004 John Wiley & Sons, Ltd. 相似文献
17.
Nonlinear inversion of electrical resistivity imaging using pruning Bayesian neural networks 总被引：1，自引：0，他引：1
Conventional artificial neural networks used to solve electrical resistivity imaging (ERI) inversion problem suffer from overfitting and local minima. To solve these problems, we propose to use a pruning Bayesian neural network (PBNN) nonlinear inversion method and a sample design method based on the K-medoids clustering algorithm. In the sample design method, the training samples of the neural network are designed according to the prior information provided by the K-medoids clustering results; thus, the training process of the neural network is well guided. The proposed PBNN, based on Bayesian regularization, is used to select the hidden layer structure by assessing the effect of each hidden neuron to the inversion results. Then, the hyperparameter α k , which is based on the generalized mean, is chosen to guide the pruning process according to the prior distribution of the training samples under the small-sample condition. The proposed algorithm is more efficient than other common adaptive regularization methods in geophysics. The inversion of synthetic data and field data suggests that the proposed method suppresses the noise in the neural network training stage and enhances the generalization. The inversion results with the proposed method are better than those of the BPNN, RBFNN, and RRBFNN inversion methods as well as the conventional least squares inversion. 相似文献
18.
A method to generate an efficient control law for a neural-network controller is presented to reduce the dynamic response of buildings exposed to earthquake-induced ground excitations. The proposed training scheme for the neural-network controller does not rely on the emulation of the structure to be controlled. The approach used for this work is based on a force-matching procedure, and it directly utilizes the dynamic data characterizing the structure response to generate an efficient training signal. The proposed controller has a feedback structure, utilizing a limited set of response quantities. A shear building actuated at its top by a tuned-mass damper is utilized to demonstrate the effectiveness of the controller. For training purposes, an ensemble of synthetically generated ground-motion time histories, with appropriate site spectrum characteristics, have been used. The performance of the trained controller is then evaluated for two different historic ground-acceleration records that do not belong to the training set of time histories. The numerical simulations show the control effectiveness of the proposed scheme with modest control requirements. Copyright © 1999 John Wiley & Sons Ltd. 相似文献
19.
A temporal artificial neural network‐based model is developed and applied for long‐lead rainfall forecasting. Tapped delay lines and recurrent connections are two different components that are used along with a static multilayer perceptron network to design a time‐delay recurrent neural network. The proposed model is, in fact, a combination of time‐delay and recurrent neural networks. The model is applied in three case studies of the Northwest, West, and Southwest basins of Iran. In addition, an autoregressive moving average with exogenous inputs (ARMAX) model is used as a baseline in order to be compared with the time‐delay recurrent neural networks developed in this study. Large‐scale climate signals, such as sea‐level pressure, that affect the rainfall of the study area are used as the predictors in the models, as well as the persistence between rainfall data. The results of winter‐spring rainfall forecasts are discussed thoroughly. It is demonstrated that in all cases the proposed neural network results in better forecasts in comparison with the statistical ARMAX model. Moreover, it is found that in two of three case studies the time‐delay recurrent neural networks perform better than either recurrent or time‐delay neural networks. The results demonstrate that the proposed method can significantly improve the long‐lead forecast by utilizing a non‐linear relationship between climatic predictors and rainfall in a region. Copyright © 2007 John Wiley & Sons, Ltd. 相似文献
20.
Experimental study of identification and control of structures using neural network. Part 2: control
Experimental verifications of a recently developed active structural control method using neural networks are presented in this paper. The experiments were performed on the earthquake simulator at the University of Illinois at Urbana—Champaign. The test specimen was a 1/4 scale model of a three-storey building. The control system consisted of a tendon/pulley system controlled by a single hydraulic actuator at the base. The control mechanism was implemented through four active pre-tensioned tendons connected to the hydraulic actuator at the first floor. The structure modelling and system identification has been presented in a companion paper. (Earthquake Engng. Struct. Dyn. 28 , 995–1018 (1999)). This paper presents the controller design and implementation. Three controllers were developed and designed: two neurocontrollers, one with a single sensor feedback and the other with three sensor feedback, and one optimal controller with acceleration feedback. The experimental design of the neurocontrollers is accomplished in three steps: system identification, multiple emulator neural networks training and finally the neurocontrollers training with the aid of multiple emulator neural networks. The effectiveness of both neurocontrollers are demonstrated from experimental results. The robustness and the relative stability are presented and discussed. The experimental results of the optimal controller performance is presented and assessed. Comparison between the optimal controller and neurocontrollers is presented and discussed. Copyright © 1999 John Wiley & Sons, Ltd. 相似文献