以某2×350 MW火电机组为研究对象,采用改进灰狼算法(improved grey wolf algorithm,IGWO)为辨识方法,将石灰石浆液pH值与净烟气SO_(2)浓度作为模型输出,通过构建决策树,选取相关度较高变量作为输入变量,建立传递函数模型。对厂级SI...以某2×350 MW火电机组为研究对象,采用改进灰狼算法(improved grey wolf algorithm,IGWO)为辨识方法,将石灰石浆液pH值与净烟气SO_(2)浓度作为模型输出,通过构建决策树,选取相关度较高变量作为输入变量,建立传递函数模型。对厂级SIS系统数据进行零初始化、粗大值以及平滑处理,使用IGWO完成不同工况下火电厂湿法脱硫系统传递函数参数的辨识。结果表明,使用IGWO辨识所得不同工况模型输出误差较小,较为符合实际工况,为后续湿法脱硫系统控制研究提供了保障。展开更多
The temperature-humidity models of wood drying were developed based on Time-delay neural network and the identification structures of Time-delay neural network were given. The controlling model and the schedule model,...The temperature-humidity models of wood drying were developed based on Time-delay neural network and the identification structures of Time-delay neural network were given. The controlling model and the schedule model, which revealed the relation between controlling signal and temperature-humidity and the relation between wood moisture content and temperature-humidity of wood drying, were separately presented. The models were simulated by using the measured data of the experimental drying kiln. The numerical simulation results showed that the modeling method was feasible, and the models were effective.展开更多
The identification problem of Hammerstein model with extension to the multi input multi output (MIMO) case is studied. The proposed identification method uses a hybrid neural network (HNN) which consists of a mult...The identification problem of Hammerstein model with extension to the multi input multi output (MIMO) case is studied. The proposed identification method uses a hybrid neural network (HNN) which consists of a multi layer feed forward neural network (MFNN) in cascade with a linear neural network (LNN). A unified back propagation (BP) algorithm is proposed to estimate the weights and the biases of the MFNN and the LNN simultaneously. Numerical examples are provided to show the efficiency of the proposed method.展开更多
Aim Using animals as object of experiment to acquire various patterns of low cerebral blood pressure and reduced blood capacity in cerebral tissues of astronauts due to the load of acceleration. Methods The isotope ...Aim Using animals as object of experiment to acquire various patterns of low cerebral blood pressure and reduced blood capacity in cerebral tissues of astronauts due to the load of acceleration. Methods The isotope tracking technique was applied to mark the blood and record the dynamic curves of cerebral blood flow changes under various accelerations, and the relevant mathematical model was set up using the method of system recognition. Also the method of factor analyzing was used to select two out of the data collected by eight sensors as two factors. Results One of the two factors reflects the various patterns in the astronaut's upper body, the other for the lower body. Parameters of rise time, delay time and steady value reflect the results under different acceleration. Conclusion Whether for the upper body or the lower body, blood flow changes can be considered as a second order system model. This method provides a new technique and method of doing research on astronaut's endurance of acceleration and selecting astronauts.展开更多
This paper investigates the problem of the model validation in identifying discrete-time-nonlinear dynamic systems by using neural networks with a single hidden layer.Based on the estimation theory,a synthetic error-i...This paper investigates the problem of the model validation in identifying discrete-time-nonlinear dynamic systems by using neural networks with a single hidden layer.Based on the estimation theory,a synthetic error-index(SEI)criterion for the neural network models has been developed.By using the powerful training algorithm of recursive prediction error (RPE),two simulated non-linear systems are studied,and the results show that the synthetic error-index criterion can be used to verify the dynamic neural network models.Furthermore,the proposed technique is much simple in calculation than that of the effective correlation tests.Finally,some problems required by further study are discussed.展开更多
In the last two decades, the damage detection for civil engineering structures has been widely treated as a modal analysis problem and most of the currently available vibration-based system identification approaches a...In the last two decades, the damage detection for civil engineering structures has been widely treated as a modal analysis problem and most of the currently available vibration-based system identification approaches are based on modal parameters, namely the natural frequencies, mode shapes and damping ratios, and/or their derivations, which are suitable for linear systems. Nonlinearity is generic in engineering structures. For example, the initiation and development of cracks in civil engineering structures as typical structural damages are nonlinear process. One of the major challenges in damage detection, early warning and damage prognosis is to obtain reasonably accurate identification of nonlinear performance such as hysteresis which is the direct indicator of damage initiation and development under dynamic excitations. In this study, a general data-based identification approach for hysteretic performance in form of nonlinear restoring force using structural dynamic responses and complete and incomplete excitation measurement time series was proposed and validated with a 4-story frame structure equipped with smart devices of magneto-theological (MR) damper to simulate nonlinear performance. Firstly, as an optimization method, the least-squares technique was employed to identify the system matrices of an equivalent linear system of the nonlinear structure model basing on the exci- tation force and the corresponding vibration measurements with impact test when complete and incomplete excitations; and secondly, the nonlinear restoring force of the structure was identified and compared with the test measurements fi- nally. Results show that the proposed data-based approach is capable of identifying the nonlinear behavior of engineering structures and can be employed to evaluate the damage initiation and development of different structure under dynamic loads.展开更多
This paper creates a LM (Levenberg-Marquardt) algorithm model which is appropriate to solve the problem about weights value of feedforward neural network. On the base of this model, we provide two applications in the ...This paper creates a LM (Levenberg-Marquardt) algorithm model which is appropriate to solve the problem about weights value of feedforward neural network. On the base of this model, we provide two applications in the oilfield production. Firstly, we simulated the functional relationships between the petrophysical and electrical properties of the rock by neural networks model, and studied oil saturation. Under the precision of data is confirmed, this method can reduce the number of experiments. Secondly, we simulated the relationships between investment and income by the neural networks model, and studied invest saturation point and income growth rate. It is very significant to guide the investment decision. The research result shows that the model is suitable for the modeling and identification of nonlinear systems due to the great fit characteristic of neural network and very fast convergence speed of LM algorithm.展开更多
The identification of Wiener systems has been an active research topic for years. A Wiener system is a series connection of a linear dynamic system followed by a static nonlinearity. The difficulty in obtaining a repr...The identification of Wiener systems has been an active research topic for years. A Wiener system is a series connection of a linear dynamic system followed by a static nonlinearity. The difficulty in obtaining a representation of the Wiener model is the need to estimate the nonlinear function from the input and output data, without the intermediate signal availability. This paper presents a methodology for the nonlinear system identification of a Wiener type model, using methods for subspaces and polynomials of Chebyshev. The subspace methods used are MOESP (multivariable output-error state space) and N4SID (numerical algorithms for subspace state space system identification). A simulated example is presented to compare the performance of these algorithms.展开更多
The paper concerns a research into dynamic properties of the steel suspension bridge across Opolska Street in Krakow, Poland. Parameter identification was carried out with the application of the nonlinear system ident...The paper concerns a research into dynamic properties of the steel suspension bridge across Opolska Street in Krakow, Poland. Parameter identification was carried out with the application of the nonlinear system identification method on the basis of system responses to exploitational excitation resulting from pedestrian traffic. In order to verify obtained results, on the basis of the geometrical and material properties of the considered system, the FEM (finite elements model) was created. Created FEM model was updated through the comparison with the model determined by the use of experimental modal analysis method and then applied to analytical evaluation of the considered suspension bridge natural frequencies.展开更多
文摘以某2×350 MW火电机组为研究对象,采用改进灰狼算法(improved grey wolf algorithm,IGWO)为辨识方法,将石灰石浆液pH值与净烟气SO_(2)浓度作为模型输出,通过构建决策树,选取相关度较高变量作为输入变量,建立传递函数模型。对厂级SIS系统数据进行零初始化、粗大值以及平滑处理,使用IGWO完成不同工况下火电厂湿法脱硫系统传递函数参数的辨识。结果表明,使用IGWO辨识所得不同工况模型输出误差较小,较为符合实际工况,为后续湿法脱硫系统控制研究提供了保障。
基金This study was supported by the Key Program of Ministry of Education of China (01066)
文摘The temperature-humidity models of wood drying were developed based on Time-delay neural network and the identification structures of Time-delay neural network were given. The controlling model and the schedule model, which revealed the relation between controlling signal and temperature-humidity and the relation between wood moisture content and temperature-humidity of wood drying, were separately presented. The models were simulated by using the measured data of the experimental drying kiln. The numerical simulation results showed that the modeling method was feasible, and the models were effective.
文摘The identification problem of Hammerstein model with extension to the multi input multi output (MIMO) case is studied. The proposed identification method uses a hybrid neural network (HNN) which consists of a multi layer feed forward neural network (MFNN) in cascade with a linear neural network (LNN). A unified back propagation (BP) algorithm is proposed to estimate the weights and the biases of the MFNN and the LNN simultaneously. Numerical examples are provided to show the efficiency of the proposed method.
文摘Aim Using animals as object of experiment to acquire various patterns of low cerebral blood pressure and reduced blood capacity in cerebral tissues of astronauts due to the load of acceleration. Methods The isotope tracking technique was applied to mark the blood and record the dynamic curves of cerebral blood flow changes under various accelerations, and the relevant mathematical model was set up using the method of system recognition. Also the method of factor analyzing was used to select two out of the data collected by eight sensors as two factors. Results One of the two factors reflects the various patterns in the astronaut's upper body, the other for the lower body. Parameters of rise time, delay time and steady value reflect the results under different acceleration. Conclusion Whether for the upper body or the lower body, blood flow changes can be considered as a second order system model. This method provides a new technique and method of doing research on astronaut's endurance of acceleration and selecting astronauts.
文摘This paper investigates the problem of the model validation in identifying discrete-time-nonlinear dynamic systems by using neural networks with a single hidden layer.Based on the estimation theory,a synthetic error-index(SEI)criterion for the neural network models has been developed.By using the powerful training algorithm of recursive prediction error (RPE),two simulated non-linear systems are studied,and the results show that the synthetic error-index criterion can be used to verify the dynamic neural network models.Furthermore,the proposed technique is much simple in calculation than that of the effective correlation tests.Finally,some problems required by further study are discussed.
基金The authors gratefully acknowledge the support provided through the National Natural Science Foundation of China (NSFC) under grant No. 50608031the Hunan Provincial Natural Science Foundation of China under grant No.08JJ1009the Key Project of Chinese Ministry of Education (No. 108102)
文摘In the last two decades, the damage detection for civil engineering structures has been widely treated as a modal analysis problem and most of the currently available vibration-based system identification approaches are based on modal parameters, namely the natural frequencies, mode shapes and damping ratios, and/or their derivations, which are suitable for linear systems. Nonlinearity is generic in engineering structures. For example, the initiation and development of cracks in civil engineering structures as typical structural damages are nonlinear process. One of the major challenges in damage detection, early warning and damage prognosis is to obtain reasonably accurate identification of nonlinear performance such as hysteresis which is the direct indicator of damage initiation and development under dynamic excitations. In this study, a general data-based identification approach for hysteretic performance in form of nonlinear restoring force using structural dynamic responses and complete and incomplete excitation measurement time series was proposed and validated with a 4-story frame structure equipped with smart devices of magneto-theological (MR) damper to simulate nonlinear performance. Firstly, as an optimization method, the least-squares technique was employed to identify the system matrices of an equivalent linear system of the nonlinear structure model basing on the exci- tation force and the corresponding vibration measurements with impact test when complete and incomplete excitations; and secondly, the nonlinear restoring force of the structure was identified and compared with the test measurements fi- nally. Results show that the proposed data-based approach is capable of identifying the nonlinear behavior of engineering structures and can be employed to evaluate the damage initiation and development of different structure under dynamic loads.
文摘This paper creates a LM (Levenberg-Marquardt) algorithm model which is appropriate to solve the problem about weights value of feedforward neural network. On the base of this model, we provide two applications in the oilfield production. Firstly, we simulated the functional relationships between the petrophysical and electrical properties of the rock by neural networks model, and studied oil saturation. Under the precision of data is confirmed, this method can reduce the number of experiments. Secondly, we simulated the relationships between investment and income by the neural networks model, and studied invest saturation point and income growth rate. It is very significant to guide the investment decision. The research result shows that the model is suitable for the modeling and identification of nonlinear systems due to the great fit characteristic of neural network and very fast convergence speed of LM algorithm.
文摘The identification of Wiener systems has been an active research topic for years. A Wiener system is a series connection of a linear dynamic system followed by a static nonlinearity. The difficulty in obtaining a representation of the Wiener model is the need to estimate the nonlinear function from the input and output data, without the intermediate signal availability. This paper presents a methodology for the nonlinear system identification of a Wiener type model, using methods for subspaces and polynomials of Chebyshev. The subspace methods used are MOESP (multivariable output-error state space) and N4SID (numerical algorithms for subspace state space system identification). A simulated example is presented to compare the performance of these algorithms.
文摘The paper concerns a research into dynamic properties of the steel suspension bridge across Opolska Street in Krakow, Poland. Parameter identification was carried out with the application of the nonlinear system identification method on the basis of system responses to exploitational excitation resulting from pedestrian traffic. In order to verify obtained results, on the basis of the geometrical and material properties of the considered system, the FEM (finite elements model) was created. Created FEM model was updated through the comparison with the model determined by the use of experimental modal analysis method and then applied to analytical evaluation of the considered suspension bridge natural frequencies.