This paper proposes a robust control scheme based on the sequential convex programming and learning-based model for nonlinear system subjected to additive uncertainties.For the problem of system nonlinearty and unknow...This paper proposes a robust control scheme based on the sequential convex programming and learning-based model for nonlinear system subjected to additive uncertainties.For the problem of system nonlinearty and unknown uncertainties,we study the tube-based model predictive control scheme that makes use of feedforward neural network.Based on the characteristics of the bounded limit of the average cost function while time approaching infinity,a min-max optimization problem(referred to as min-max OP)is formulated to design the controller.The feasibility of this optimization problem and the practical stability of the controlled system are ensured.To demonstrate the efficacy of the proposed approach,a numerical simulation on a double-tank system is conducted.The results of the simulation serve as verification of the effectualness of the proposed scheme.展开更多
A nonlinear model predictive control problem based on pseudo-linear neural network (PNN) is discussed, in which the second order on-line optimization method is adopted. The recursive computation of Jacobian matrix is ...A nonlinear model predictive control problem based on pseudo-linear neural network (PNN) is discussed, in which the second order on-line optimization method is adopted. The recursive computation of Jacobian matrix is investigated. The stability of the closed loop model predictive control system is analyzed based on Lyapunov theory to obtain the sufficient condition for the asymptotical stability of the neural predictive control system. A simulation was carried out for an exothermic first-order reaction in a continuous stirred tank reactor.It is demonstrated that the proposed control strategy is applicable to some of nonlinear systems.展开更多
Injection of water to enhance oil production is commonplace, and improvements in understanding the process are economically important. This study examines predictive models of the injection-to-production ratio. First...Injection of water to enhance oil production is commonplace, and improvements in understanding the process are economically important. This study examines predictive models of the injection-to-production ratio. Firstly, the error between the fitting and actual injection-production ratio is calculated with such methods as the injection-production ratio and water-oil ratio method, the material balance method, the multiple regression method, the gray theory GM (1,1) model and the back-propogation (BP) neural network method by computer applications in this paper. The relative average errors calculated are respectively 1.67%, 1.08%, 19.2%, 1.38% and 0.88%. Secondly, the reasons for the errors from different prediction methods are analyzed theoretically, indicating that the prediction precision of the BP neural network method is high, and that it has a better self-adaptability, so that it can reflect the internal relationship between the injection-production ratio and the influencing factors. Therefore, the BP neural network method is suitable to the prediction of injection-production ratio.展开更多
Since chemical processes are highly non-linear and multiscale,it is vital to deeply mine the multiscale coupling relationships embedded in the massive process data for the prediction and anomaly tracing of crucial pro...Since chemical processes are highly non-linear and multiscale,it is vital to deeply mine the multiscale coupling relationships embedded in the massive process data for the prediction and anomaly tracing of crucial process parameters and production indicators.While the integrated method of adaptive signal decomposition combined with time series models could effectively predict process variables,it does have limitations in capturing the high-frequency detail of the operation state when applied to complex chemical processes.In light of this,a novel Multiscale Multi-radius Multi-step Convolutional Neural Network(Msrt Net)is proposed for mining spatiotemporal multiscale information.First,the industrial data from the Fluid Catalytic Cracking(FCC)process decomposition using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)extract the multi-energy scale information of the feature subset.Then,convolution kernels with varying stride and padding structures are established to decouple the long-period operation process information encapsulated within the multi-energy scale data.Finally,a reconciliation network is trained to reconstruct the multiscale prediction results and obtain the final output.Msrt Net is initially assessed for its capability to untangle the spatiotemporal multiscale relationships among variables in the Tennessee Eastman Process(TEP).Subsequently,the performance of Msrt Net is evaluated in predicting product yield for a 2.80×10^(6) t/a FCC unit,taking diesel and gasoline yield as examples.In conclusion,Msrt Net can decouple and effectively extract spatiotemporal multiscale information from chemical process data and achieve a approximately reduction of 30%in prediction error compared to other time-series models.Furthermore,its robustness and transferability underscore its promising potential for broader applications.展开更多
Temporal land use/land cover (LULC) change information provides a variety of applications for informed management of land resources. The aim of this study was to detect and predict LULC changes in the Arasbaran region...Temporal land use/land cover (LULC) change information provides a variety of applications for informed management of land resources. The aim of this study was to detect and predict LULC changes in the Arasbaran region using an integrated Multi-Layer Perceptron Neural Network and Markov Chain analysis. At the first step, multi-temporal Landsat images (1990, 2002 and 2014) were processed using ancillary data and were classified into seven LULC categories of high density forest, low-density forest, agriculture, grassland, barren land, water and urban area. Next, LULC changes were detected for three time profiles, 1990–2002, 2002–2014 and 1990–2014. A 2014 LULC map of the study area was further simulated (for model performance evaluation) applying 1990 and 2002 map layers. In addition, a collection of spatial variables was also used for modeling LULC change processes as driving forces. The actual and simulated 2014 LULC change maps were cross-tabulated and compared to ensure model simulation success and the results indicated an overall accuracy and kappa coefficient of 97.79% and 0.992, respectively. Having the model properly validated, LULC change was predicted up to the year 2025. The results demonstrated that 992 and 1592 ha of high and lowdensity forests were degraded during 1990–2014,respectively, while 422 ha were added to the extent of residential areas with a growth rate of 17.58 ha per year. The developed model predicted a considerable degradation trend for the forest categories through 2025, accounting for 489 and 531 ha of loss for high and low-density forests, respectively. By way of contrast, residential area and farmland categories will increase up to 211 and 427 ha, respectively. The integrated prediction model and customary area data can be used for practical management efforts by simulating vegetation dynamics and future LULC change trajectories.展开更多
The measure of uncertainty is adopted as a measure of information. The measures of fuzziness are known as fuzzy information measures. The measure of a quantity of fuzzy information gained from a fuzzy set or fuzzy sys...The measure of uncertainty is adopted as a measure of information. The measures of fuzziness are known as fuzzy information measures. The measure of a quantity of fuzzy information gained from a fuzzy set or fuzzy system is known as fuzzy entropy. Fuzzy entropy has been focused and studied by many researchers in various fields. In this paper, firstly, the axiomatic definition of fuzzy entropy is discussed. Then, neural networks model of fuzzy entropy is proposed, based on the computing capability of neural networks. In the end, two examples are discussed to show the efficiency of the model.展开更多
Based on the comparison of several methods of time series predicting, this paper points out that it is necessary to use dynamic neural network in modeling of complex production process. Because self feedback and mutua...Based on the comparison of several methods of time series predicting, this paper points out that it is necessary to use dynamic neural network in modeling of complex production process. Because self feedback and mutual feedback are adopted among nodes at the same layer in Elman network, it has stronger ability of dynamic approximation, and can describe any non linear dynamic system. After the structure and mathematical description being given, dynamic back propagation (BP) algorithm of training weights of Elman neural network is deduced. At last, the network is used to predict ash content of black amber in jigging production process. The results show that this neural network is powerful in predicting and suitable for modeling, predicting, and controling of complex production process.展开更多
Based on the basic principles of BP artificial neural network model and the fundamental law of water and sediment yield in a river basin, a BP neural network model is developed by using observed data, with rainfall co...Based on the basic principles of BP artificial neural network model and the fundamental law of water and sediment yield in a river basin, a BP neural network model is developed by using observed data, with rainfall conditions serving as affecting factors. The model has satisfactory performance of learning and generalization and can be also used to assess the influence of human activities on water and sediment yield in a river basin. The model is applied to compute the runoff and sediment transmission at Xingshan, Bixi and Shunlixia stations. Comparison between the results from the model and the observed data shows that the model is basically reasonable and reliable.展开更多
文摘This paper proposes a robust control scheme based on the sequential convex programming and learning-based model for nonlinear system subjected to additive uncertainties.For the problem of system nonlinearty and unknown uncertainties,we study the tube-based model predictive control scheme that makes use of feedforward neural network.Based on the characteristics of the bounded limit of the average cost function while time approaching infinity,a min-max optimization problem(referred to as min-max OP)is formulated to design the controller.The feasibility of this optimization problem and the practical stability of the controlled system are ensured.To demonstrate the efficacy of the proposed approach,a numerical simulation on a double-tank system is conducted.The results of the simulation serve as verification of the effectualness of the proposed scheme.
文摘A nonlinear model predictive control problem based on pseudo-linear neural network (PNN) is discussed, in which the second order on-line optimization method is adopted. The recursive computation of Jacobian matrix is investigated. The stability of the closed loop model predictive control system is analyzed based on Lyapunov theory to obtain the sufficient condition for the asymptotical stability of the neural predictive control system. A simulation was carried out for an exothermic first-order reaction in a continuous stirred tank reactor.It is demonstrated that the proposed control strategy is applicable to some of nonlinear systems.
文摘Injection of water to enhance oil production is commonplace, and improvements in understanding the process are economically important. This study examines predictive models of the injection-to-production ratio. Firstly, the error between the fitting and actual injection-production ratio is calculated with such methods as the injection-production ratio and water-oil ratio method, the material balance method, the multiple regression method, the gray theory GM (1,1) model and the back-propogation (BP) neural network method by computer applications in this paper. The relative average errors calculated are respectively 1.67%, 1.08%, 19.2%, 1.38% and 0.88%. Secondly, the reasons for the errors from different prediction methods are analyzed theoretically, indicating that the prediction precision of the BP neural network method is high, and that it has a better self-adaptability, so that it can reflect the internal relationship between the injection-production ratio and the influencing factors. Therefore, the BP neural network method is suitable to the prediction of injection-production ratio.
文摘Since chemical processes are highly non-linear and multiscale,it is vital to deeply mine the multiscale coupling relationships embedded in the massive process data for the prediction and anomaly tracing of crucial process parameters and production indicators.While the integrated method of adaptive signal decomposition combined with time series models could effectively predict process variables,it does have limitations in capturing the high-frequency detail of the operation state when applied to complex chemical processes.In light of this,a novel Multiscale Multi-radius Multi-step Convolutional Neural Network(Msrt Net)is proposed for mining spatiotemporal multiscale information.First,the industrial data from the Fluid Catalytic Cracking(FCC)process decomposition using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)extract the multi-energy scale information of the feature subset.Then,convolution kernels with varying stride and padding structures are established to decouple the long-period operation process information encapsulated within the multi-energy scale data.Finally,a reconciliation network is trained to reconstruct the multiscale prediction results and obtain the final output.Msrt Net is initially assessed for its capability to untangle the spatiotemporal multiscale relationships among variables in the Tennessee Eastman Process(TEP).Subsequently,the performance of Msrt Net is evaluated in predicting product yield for a 2.80×10^(6) t/a FCC unit,taking diesel and gasoline yield as examples.In conclusion,Msrt Net can decouple and effectively extract spatiotemporal multiscale information from chemical process data and achieve a approximately reduction of 30%in prediction error compared to other time-series models.Furthermore,its robustness and transferability underscore its promising potential for broader applications.
文摘Temporal land use/land cover (LULC) change information provides a variety of applications for informed management of land resources. The aim of this study was to detect and predict LULC changes in the Arasbaran region using an integrated Multi-Layer Perceptron Neural Network and Markov Chain analysis. At the first step, multi-temporal Landsat images (1990, 2002 and 2014) were processed using ancillary data and were classified into seven LULC categories of high density forest, low-density forest, agriculture, grassland, barren land, water and urban area. Next, LULC changes were detected for three time profiles, 1990–2002, 2002–2014 and 1990–2014. A 2014 LULC map of the study area was further simulated (for model performance evaluation) applying 1990 and 2002 map layers. In addition, a collection of spatial variables was also used for modeling LULC change processes as driving forces. The actual and simulated 2014 LULC change maps were cross-tabulated and compared to ensure model simulation success and the results indicated an overall accuracy and kappa coefficient of 97.79% and 0.992, respectively. Having the model properly validated, LULC change was predicted up to the year 2025. The results demonstrated that 992 and 1592 ha of high and lowdensity forests were degraded during 1990–2014,respectively, while 422 ha were added to the extent of residential areas with a growth rate of 17.58 ha per year. The developed model predicted a considerable degradation trend for the forest categories through 2025, accounting for 489 and 531 ha of loss for high and low-density forests, respectively. By way of contrast, residential area and farmland categories will increase up to 211 and 427 ha, respectively. The integrated prediction model and customary area data can be used for practical management efforts by simulating vegetation dynamics and future LULC change trajectories.
基金Supported by the National Natural Science Foundation of China(60074014)
文摘The measure of uncertainty is adopted as a measure of information. The measures of fuzziness are known as fuzzy information measures. The measure of a quantity of fuzzy information gained from a fuzzy set or fuzzy system is known as fuzzy entropy. Fuzzy entropy has been focused and studied by many researchers in various fields. In this paper, firstly, the axiomatic definition of fuzzy entropy is discussed. Then, neural networks model of fuzzy entropy is proposed, based on the computing capability of neural networks. In the end, two examples are discussed to show the efficiency of the model.
文摘Based on the comparison of several methods of time series predicting, this paper points out that it is necessary to use dynamic neural network in modeling of complex production process. Because self feedback and mutual feedback are adopted among nodes at the same layer in Elman network, it has stronger ability of dynamic approximation, and can describe any non linear dynamic system. After the structure and mathematical description being given, dynamic back propagation (BP) algorithm of training weights of Elman neural network is deduced. At last, the network is used to predict ash content of black amber in jigging production process. The results show that this neural network is powerful in predicting and suitable for modeling, predicting, and controling of complex production process.
文摘Based on the basic principles of BP artificial neural network model and the fundamental law of water and sediment yield in a river basin, a BP neural network model is developed by using observed data, with rainfall conditions serving as affecting factors. The model has satisfactory performance of learning and generalization and can be also used to assess the influence of human activities on water and sediment yield in a river basin. The model is applied to compute the runoff and sediment transmission at Xingshan, Bixi and Shunlixia stations. Comparison between the results from the model and the observed data shows that the model is basically reasonable and reliable.
