This paper proposes a Fuzzy Neural Network (FNN) model, which uses a propagation algorithm. A logical operation is defined by a set of weights which are independent of inputs. The realization of the basic And,Or and N...This paper proposes a Fuzzy Neural Network (FNN) model, which uses a propagation algorithm. A logical operation is defined by a set of weights which are independent of inputs. The realization of the basic And,Or and Negation fuzzy logical operations is shown by the fuzzy neuron. A example in fault diagnosis is put forward and the result witnesses some effectiveness of the new FNN model.展开更多
In order to design an effective hydraulic motor speed control system, Matlab_Simiulink and AMESim co-simulation technology is adopted to establish more accurate model and reflect the actual system. The neural...In order to design an effective hydraulic motor speed control system, Matlab_Simiulink and AMESim co-simulation technology is adopted to establish more accurate model and reflect the actual system. The neural network proportion-integration-differentiation （PID） control parameters on-line adjustment is utilized to improve system accuracy, celerity and stability. Simulation results indicate that with the control system proposed in this paper, the system deviation is reduced, therefore accuracy is improved; response speed for step signal and sinusoidal signal gets faster, thus acceleration is rapidly improved; and the system can be restored to the control value in case of interfering, so stability is improved.展开更多
A rough set based corner classification neural network, the Rough-CC4, is presented to solve document classification problems such as document representation of different document sizes, document feature selection and...A rough set based corner classification neural network, the Rough-CC4, is presented to solve document classification problems such as document representation of different document sizes, document feature selection and document feature encoding. In the Rough-CC4, the documents are described by the equivalent classes of the approximate words. By this method, the dimensions representing the documents can be reduced, which can solve the precision problems caused by the different document sizes and also blur the differences caused by the approximate words. In the Rough-CC4, a binary encoding method is introduced, through which the importance of documents relative to each equivalent class is encoded. By this encoding method, the precision of the Rough-CC4 is improved greatly and the space complexity of the Rough-CC4 is reduced. The Rough-CC4 can be used in automatic classification of documents.展开更多
In the incremental sheet forming （ISF） process, springback is a very important factor that affects the quality of parts. Predicting and controlling springback accurately is essential for the design of the toolpath f...In the incremental sheet forming （ISF） process, springback is a very important factor that affects the quality of parts. Predicting and controlling springback accurately is essential for the design of the toolpath for ISF. A three-dimensional elasto-plastic finite element model （FEM） was developed to simulate the process and the simulated results were compared with those from the experiment. The springback angle was found to be in accordance with the experimental result, proving the FEM to be effective. A coupled artificial neural networks （ANN） and finite element method technique was developed to simulate and predict springback responses to changes in the processing parameters. A particle swarm optimization （PSO） algorithm was used to optimize the weights and thresholds of the neural network model. The neural network was trained using available FEM simulation data. The results showed that a more accurate prediction of s!oringback can be acquired using the FEM-PSONN model.展开更多
An artificial neural network model was developed to predict the oxidation of refractory gold concentrate （RGC） by ozone and ferric ions. The concentration of ozone and ferric ions, pulp density, oxygen amount, leach...An artificial neural network model was developed to predict the oxidation of refractory gold concentrate （RGC） by ozone and ferric ions. The concentration of ozone and ferric ions, pulp density, oxygen amount, leaching time and temperature were employed as inputs to the network; the output of the network was the percentage of the ferric extraction iron from RGC. The multilayered feed-forward networks were trained by 33 sets of input-output patterns using a back propagation algorithm; a three-layer network with 8 neurons in the hidden layer gave optimal results. The model gave good predictions of high correlation coefficient （R2=0.966）. The predictions by ANN are more accurate when compared with conventional multivariate regression analysis （MVRA）. In addition, calculation with ANN model indicates that temperature is the predominant parameter and ozone concentration is the lesser influential parameter in the pre-oxidation process of refractory gold ore. The ANN neural network model accurately estimates the ferric extraction during pretreatment process of RGC in gold smelter plants and can be used to optimize the process parameters.展开更多
In view of the characteristics of soft soil deep foundation pit for the construction and geotechnical characteristics of the special medium,it is difficult to calculate theoreti- cally accurately structural deformatio...In view of the characteristics of soft soil deep foundation pit for the construction and geotechnical characteristics of the special medium,it is difficult to calculate theoreti- cally accurately structural deformation of the foundation pit,so in the course of excavation on the construction of the information is particularly important.The analysis and compari- son of several popular non-linear forecasting methods,combined with the actual projects, set up a grey theoretical prediction model,time series forecasting model,improved neural network model to predict deformation of the foundation pit.The results show that the use of neural network to predict with high accuracy solution,it is the foundation deformation prediction effective way in underground works with good prospects.展开更多
Based on the statistical data from 1975 to 1997, we forecast the growth rate of coal consuming and the quantity in coming decade with the BP neuron network in the article.
The adaptive learning and prediction of a highly nonlinear and time-varying bioreactor benchmark process is studied using Neur-On-Line, a graphical tool kit for developing and deploying neural networks in the G2 real ...The adaptive learning and prediction of a highly nonlinear and time-varying bioreactor benchmark process is studied using Neur-On-Line, a graphical tool kit for developing and deploying neural networks in the G2 real time intelligent environment,and a new modified Broyden, Fletcher, Goldfarb, and Shanno （BFGS） quasi-Newton algorithm. The modified BFGS algorithm for the adaptive learning of back propagation （BP） neural networks is developed and embedded into NeurOn-Line by introducing a new search method of learning rate to the full memory BFGS algorithm. Simulation results show that the adaptive learning and prediction neural network system can quicklv track the time-varving and nonlinear behavior of the bioreactor.展开更多
The effect of extrusion parameters on the extrusion load for AZ31 magnesium alloy was investigated with the support of numerical methods.With this regard,the process temperature,extrusion ratio,friction factor and pun...The effect of extrusion parameters on the extrusion load for AZ31 magnesium alloy was investigated with the support of numerical methods.With this regard,the process temperature,extrusion ratio,friction factor and punch velocity were selected as main parameters for the experiments.Besides,the experimental results were analyzed by using the finite element method(FEM)and artificial neural network(ANN)method to build a numerical model for predicting the forming load.All the experimental and numerical results were compared to each other and it was concluded from the results that the effect of friction factor on the extrusion load is more dominant at lower extrusion temperature for all given extrusion ratios and punch velocities.Besides this,higher extrusion ratios require higher process temperatures to obtain the lower extrusion load.Also,it was observed that the increase in the extrusion speed causes a significant increase in the forming load for all extrusion ratios and extrusion temperatures.展开更多
This paper presents a new designed miniature six DOF （degree of freedom） force/torque sensor. This sensor is fully integrated with a micro DSP （digital signal processor）, so all the signal conditioning, A/D, decou...This paper presents a new designed miniature six DOF （degree of freedom） force/torque sensor. This sensor is fully integrated with a micro DSP （digital signal processor）, so all the signal conditioning, A/D, decoupling, digital-signals serial output are performed in the sensor. Some experimental results are presented to demonstrate the capability of the proposed design. Finally, a neural network was used for decoupling the interacting signals, compared with the conventional method using the inverse matrix, this new method is more accurate.展开更多
文摘This paper proposes a Fuzzy Neural Network (FNN) model, which uses a propagation algorithm. A logical operation is defined by a set of weights which are independent of inputs. The realization of the basic And,Or and Negation fuzzy logical operations is shown by the fuzzy neuron. A example in fault diagnosis is put forward and the result witnesses some effectiveness of the new FNN model.
文摘In order to design an effective hydraulic motor speed control system, Matlab_Simiulink and AMESim co-simulation technology is adopted to establish more accurate model and reflect the actual system. The neural network proportion-integration-differentiation （PID） control parameters on-line adjustment is utilized to improve system accuracy, celerity and stability. Simulation results indicate that with the control system proposed in this paper, the system deviation is reduced, therefore accuracy is improved; response speed for step signal and sinusoidal signal gets faster, thus acceleration is rapidly improved; and the system can be restored to the control value in case of interfering, so stability is improved.
基金The National Natural Science Foundation of China(No.60503020,60373066,60403016,60425206),the Natural Science Foundation of Jiangsu Higher Education Institutions ( No.04KJB520096),the Doctoral Foundation of Nanjing University of Posts and Telecommunication (No.0302).
文摘A rough set based corner classification neural network, the Rough-CC4, is presented to solve document classification problems such as document representation of different document sizes, document feature selection and document feature encoding. In the Rough-CC4, the documents are described by the equivalent classes of the approximate words. By this method, the dimensions representing the documents can be reduced, which can solve the precision problems caused by the different document sizes and also blur the differences caused by the approximate words. In the Rough-CC4, a binary encoding method is introduced, through which the importance of documents relative to each equivalent class is encoded. By this encoding method, the precision of the Rough-CC4 is improved greatly and the space complexity of the Rough-CC4 is reduced. The Rough-CC4 can be used in automatic classification of documents.
基金Project(50175034) supported by the National Natural Science Foundation of China
文摘In the incremental sheet forming （ISF） process, springback is a very important factor that affects the quality of parts. Predicting and controlling springback accurately is essential for the design of the toolpath for ISF. A three-dimensional elasto-plastic finite element model （FEM） was developed to simulate the process and the simulated results were compared with those from the experiment. The springback angle was found to be in accordance with the experimental result, proving the FEM to be effective. A coupled artificial neural networks （ANN） and finite element method technique was developed to simulate and predict springback responses to changes in the processing parameters. A particle swarm optimization （PSO） algorithm was used to optimize the weights and thresholds of the neural network model. The neural network was trained using available FEM simulation data. The results showed that a more accurate prediction of s!oringback can be acquired using the FEM-PSONN model.
基金Project (2006AA06Z132) supported by High-tech Research and Development Program of ChinaProject (B604) supported by Leading Academic Discipline Project of Shanghai
文摘An artificial neural network model was developed to predict the oxidation of refractory gold concentrate （RGC） by ozone and ferric ions. The concentration of ozone and ferric ions, pulp density, oxygen amount, leaching time and temperature were employed as inputs to the network; the output of the network was the percentage of the ferric extraction iron from RGC. The multilayered feed-forward networks were trained by 33 sets of input-output patterns using a back propagation algorithm; a three-layer network with 8 neurons in the hidden layer gave optimal results. The model gave good predictions of high correlation coefficient （R2=0.966）. The predictions by ANN are more accurate when compared with conventional multivariate regression analysis （MVRA）. In addition, calculation with ANN model indicates that temperature is the predominant parameter and ozone concentration is the lesser influential parameter in the pre-oxidation process of refractory gold ore. The ANN neural network model accurately estimates the ferric extraction during pretreatment process of RGC in gold smelter plants and can be used to optimize the process parameters.
基金the Educational Department of Liaoning Province Through Scientific Research Project(20060051)National Natural Science Foundation of China(50604009)Universities Excellent Talents Support Plan to Train Foundation of Liaoning(RC-04-13)
文摘In view of the characteristics of soft soil deep foundation pit for the construction and geotechnical characteristics of the special medium,it is difficult to calculate theoreti- cally accurately structural deformation of the foundation pit,so in the course of excavation on the construction of the information is particularly important.The analysis and compari- son of several popular non-linear forecasting methods,combined with the actual projects, set up a grey theoretical prediction model,time series forecasting model,improved neural network model to predict deformation of the foundation pit.The results show that the use of neural network to predict with high accuracy solution,it is the foundation deformation prediction effective way in underground works with good prospects.
文摘Based on the statistical data from 1975 to 1997, we forecast the growth rate of coal consuming and the quantity in coming decade with the BP neuron network in the article.
文摘The adaptive learning and prediction of a highly nonlinear and time-varying bioreactor benchmark process is studied using Neur-On-Line, a graphical tool kit for developing and deploying neural networks in the G2 real time intelligent environment,and a new modified Broyden, Fletcher, Goldfarb, and Shanno （BFGS） quasi-Newton algorithm. The modified BFGS algorithm for the adaptive learning of back propagation （BP） neural networks is developed and embedded into NeurOn-Line by introducing a new search method of learning rate to the full memory BFGS algorithm. Simulation results show that the adaptive learning and prediction neural network system can quicklv track the time-varving and nonlinear behavior of the bioreactor.
文摘The effect of extrusion parameters on the extrusion load for AZ31 magnesium alloy was investigated with the support of numerical methods.With this regard,the process temperature,extrusion ratio,friction factor and punch velocity were selected as main parameters for the experiments.Besides,the experimental results were analyzed by using the finite element method(FEM)and artificial neural network(ANN)method to build a numerical model for predicting the forming load.All the experimental and numerical results were compared to each other and it was concluded from the results that the effect of friction factor on the extrusion load is more dominant at lower extrusion temperature for all given extrusion ratios and punch velocities.Besides this,higher extrusion ratios require higher process temperatures to obtain the lower extrusion load.Also,it was observed that the increase in the extrusion speed causes a significant increase in the forming load for all extrusion ratios and extrusion temperatures.
基金Supported by the National Natural Science Foundation of China （ No. 60275032 ） and the Supported bv the High Technology Research and Development Programme of China （ No. 2003AA404220）.
文摘This paper presents a new designed miniature six DOF （degree of freedom） force/torque sensor. This sensor is fully integrated with a micro DSP （digital signal processor）, so all the signal conditioning, A/D, decoupling, digital-signals serial output are performed in the sensor. Some experimental results are presented to demonstrate the capability of the proposed design. Finally, a neural network was used for decoupling the interacting signals, compared with the conventional method using the inverse matrix, this new method is more accurate.
