A neural network Smith predictive control strategy is proposed to deal with inpu t and feedback time delays in telerobot systems. The delay time is assumed to b e invariant and unknown. The proposed control structure...A neural network Smith predictive control strategy is proposed to deal with inpu t and feedback time delays in telerobot systems. The delay time is assumed to b e invariant and unknown. The proposed control structure consists of a slave syst em and a master controller. In the slave system, a recurrent neural network (RNN ) with on-line weight tuning algorithm is employed to approximate the dynamics of the time-delay-free nonlinear plant, which is used to linearize the slave s ystem. The master controller is a Smith predictor for the linearized slave syste m, which provides prediction and maintains the desirable tracking performance. S tability propriety is guaranteed based on the Lyapunov method. A simulation of a two-link robotic manipulator is provided to illustrate the effectiveness of th e proposed control strategy.展开更多
Back propagation is employed to forecast the current of a storm with various characteristics of storm surge; the technique is thus important in disaster forecasting. One of the most fuzzy types of information in the p...Back propagation is employed to forecast the current of a storm with various characteristics of storm surge; the technique is thus important in disaster forecasting. One of the most fuzzy types of information in the prediction of geological calamity is handled employing the information diffusion method. First, a single-step prediction model and neural network prediction model are employed to collect influential information used to predict the extreme tide level. Second, information is obtained using the information diffusion method, which improves the precision of risk recognition when there is insufficient information. Experiments demonstrate that the method proposed in this paper is simple and effective and provides better forecast results than other methods. Future work will focus on a more precise forecast model.展开更多
The resilient modulus(MR)of subgrade soils is usually used to characterize the stiffness of subgrade and is a crucial parameter in pavement design.In order to determine the resilient modulus of compacted subgrade soil...The resilient modulus(MR)of subgrade soils is usually used to characterize the stiffness of subgrade and is a crucial parameter in pavement design.In order to determine the resilient modulus of compacted subgrade soils quickly and accurately,an optimized artificial neural network(ANN)approach based on the multi-population genetic algorithm(MPGA)was proposed in this study.The MPGA overcomes the problems of the traditional ANN such as low efficiency,local optimum and over-fitting.The developed optimized ANN method consists of ten input variables,twenty-one hidden neurons,and one output variable.The physical properties(liquid limit,plastic limit,plasticity index,0.075 mm passing percentage,maximum dry density,optimum moisture content),state variables(degree of compaction,moisture content)and stress variables(confining pressure,deviatoric stress)of subgrade soils were selected as input variables.The MR was directly used as the output variable.Then,adopting a large amount of experimental data from existing literature,the developed optimized ANN method was compared with the existing representative estimation methods.The results show that the developed optimized ANN method has the advantages of fast speed,strong generalization ability and good accuracy in MR estimation.展开更多
In granule processing industries, acquisition of particle size and shape parameters is a common procedure, and volumetric measurement is of great importance in dealing with particle sizing and gradation. To eradicate ...In granule processing industries, acquisition of particle size and shape parameters is a common procedure, and volumetric measurement is of great importance in dealing with particle sizing and gradation. To eradicate the major drawbacks with manual gauge, this paper proposes an optical approach using Back Propagation （BP） neural network to estimate the particle volume based on the two-Dimensional （2D） image information. To achieve the better network efficiency and structure simplicity, Principal Component Analysis （PCA） is adopted to reduce the dimensions of network inputs To overcome the shortcomings of generic BP network for being slow to converge and vulnerable to being trapped in local minimum, Levenberg-Marquardt （LM） algorithm is applied to achieve a higher speed and a lower error rate. The real particle data is utilized in training and testing the presented network. The experimental result suggests that the proposed neural network is capable of estimating aggregate volume with satisfactory precision and superior to the generic BP network in terms of perforxnance capacity.展开更多
Cost estimation has its proven importance as one of essential factors for project success. The aim of this research is to predict the early project cost using neural network. Early project cost represents a key compon...Cost estimation has its proven importance as one of essential factors for project success. The aim of this research is to predict the early project cost using neural network. Early project cost represents a key component in business unit decisions. The most important factors influencing on the parametric cost estimation in construction building projects in Gaza Strip were defined and investigated. A questionnaire survey and relative index ranking technique were used to conclude the most important factors. Fourteen most effective factors were identified. One hundred and six case studies from real executed construction project in Gaza Strip were collected for training and testing the model. The cases were prepared to be used in cost estimate neural networks model. Eighty percent of case studies were used to train and test the model. The remaining 20% was used for model verification. The results revealed the ability to the model to predict cost estimate to an acceptable degree of accuracy. The minimum squares error with 0.005 in training stage and 0.021 in testing stage were recorded.展开更多
文摘A neural network Smith predictive control strategy is proposed to deal with inpu t and feedback time delays in telerobot systems. The delay time is assumed to b e invariant and unknown. The proposed control structure consists of a slave syst em and a master controller. In the slave system, a recurrent neural network (RNN ) with on-line weight tuning algorithm is employed to approximate the dynamics of the time-delay-free nonlinear plant, which is used to linearize the slave s ystem. The master controller is a Smith predictor for the linearized slave syste m, which provides prediction and maintains the desirable tracking performance. S tability propriety is guaranteed based on the Lyapunov method. A simulation of a two-link robotic manipulator is provided to illustrate the effectiveness of th e proposed control strategy.
基金Supported by the MISSION 908 (Nos. 908-02-03-07, SD-908-02-08)
文摘Back propagation is employed to forecast the current of a storm with various characteristics of storm surge; the technique is thus important in disaster forecasting. One of the most fuzzy types of information in the prediction of geological calamity is handled employing the information diffusion method. First, a single-step prediction model and neural network prediction model are employed to collect influential information used to predict the extreme tide level. Second, information is obtained using the information diffusion method, which improves the precision of risk recognition when there is insufficient information. Experiments demonstrate that the method proposed in this paper is simple and effective and provides better forecast results than other methods. Future work will focus on a more precise forecast model.
基金Project(51878078)supported by the National Natural Science Foundation of ChinaProject(2018-025)supported by the Training Program for High-level Technical Personnel in Transportation Industry,ChinaProject(CTKY-PTRC-2018-003)supported by the Design Theory,Method and Demonstration of Durability Asphalt Pavement Based on Heavy-duty Traffic Conditions in Shanghai Area,China。
文摘The resilient modulus(MR)of subgrade soils is usually used to characterize the stiffness of subgrade and is a crucial parameter in pavement design.In order to determine the resilient modulus of compacted subgrade soils quickly and accurately,an optimized artificial neural network(ANN)approach based on the multi-population genetic algorithm(MPGA)was proposed in this study.The MPGA overcomes the problems of the traditional ANN such as low efficiency,local optimum and over-fitting.The developed optimized ANN method consists of ten input variables,twenty-one hidden neurons,and one output variable.The physical properties(liquid limit,plastic limit,plasticity index,0.075 mm passing percentage,maximum dry density,optimum moisture content),state variables(degree of compaction,moisture content)and stress variables(confining pressure,deviatoric stress)of subgrade soils were selected as input variables.The MR was directly used as the output variable.Then,adopting a large amount of experimental data from existing literature,the developed optimized ANN method was compared with the existing representative estimation methods.The results show that the developed optimized ANN method has the advantages of fast speed,strong generalization ability and good accuracy in MR estimation.
基金Supported by Ningbo Natural Science Foundation (No. 2006A610016)Foundation of Ministry of Education for Returned Overseas Students & Scholars (SRF for ROCS, SEM. No. 2006699)
文摘In granule processing industries, acquisition of particle size and shape parameters is a common procedure, and volumetric measurement is of great importance in dealing with particle sizing and gradation. To eradicate the major drawbacks with manual gauge, this paper proposes an optical approach using Back Propagation （BP） neural network to estimate the particle volume based on the two-Dimensional （2D） image information. To achieve the better network efficiency and structure simplicity, Principal Component Analysis （PCA） is adopted to reduce the dimensions of network inputs To overcome the shortcomings of generic BP network for being slow to converge and vulnerable to being trapped in local minimum, Levenberg-Marquardt （LM） algorithm is applied to achieve a higher speed and a lower error rate. The real particle data is utilized in training and testing the presented network. The experimental result suggests that the proposed neural network is capable of estimating aggregate volume with satisfactory precision and superior to the generic BP network in terms of perforxnance capacity.
文摘Cost estimation has its proven importance as one of essential factors for project success. The aim of this research is to predict the early project cost using neural network. Early project cost represents a key component in business unit decisions. The most important factors influencing on the parametric cost estimation in construction building projects in Gaza Strip were defined and investigated. A questionnaire survey and relative index ranking technique were used to conclude the most important factors. Fourteen most effective factors were identified. One hundred and six case studies from real executed construction project in Gaza Strip were collected for training and testing the model. The cases were prepared to be used in cost estimate neural networks model. Eighty percent of case studies were used to train and test the model. The remaining 20% was used for model verification. The results revealed the ability to the model to predict cost estimate to an acceptable degree of accuracy. The minimum squares error with 0.005 in training stage and 0.021 in testing stage were recorded.
