Randomness is common in many real industrial processes, its modeling problem has always been an important research content in the field of industrial control. Probability density function(PDF) is an effective means to...
详细信息
Randomness is common in many real industrial processes, its modeling problem has always been an important research content in the field of industrial control. Probability density function(PDF) is an effective means to solve the problem of stochastic distributed system modeling This paper based on Bspline basis function sets up the model of output and input data. Due to the fact that there are often many constraints in the actual industrial process and high requirements for real-time and accuracy, this paper proposes to combine the PDF model with predictive control to achieve effective tracking of system output setpoints. Predictive control optimization is more complicated and computationally intensive, so the predictive functional control (PFC) strategy is adopted to reduce the degree of freedom of the optimization problem. Applying PFC based on PDF modeling to the molecular weight distribution (MWD) of the polymerization process, and compared with generalized predictive control (GPC) algorithm, the validity of the proposed method is verified.
A quantum internet is the holy grail of quantum information processing, enabling the deployment of a broad range of quantum technologies and protocols on a global scale. However, numerous challenges exist before the q...
详细信息
As an important research topic in computer vision, fine-grained classification which aims to recognition subordinate-level categories has attracted significant attention. We propose a novel region based ensemble learn...
详细信息
Short-term wind speed forecasting plays an important role in the daily power system operation. Therefore, this paper presents a novel model based on spiking neural network (SNN) used spike response model (SRM). Furthe...
详细信息
Short-term wind speed forecasting plays an important role in the daily power system operation. Therefore, this paper presents a novel model based on spiking neural network (SNN) used spike response model (SRM). Further, to achieve both smaller training errors and higher precision forecasting, the basic SpikeProp learning algorithm is improved by adaptively adjusting the learning rate and adding momentum items. Then, this paper selects the actual sampling data from a wind farm to verify the effectiveness and advantages of the proposed model.
In recent years,the rapid development of big data technology has also been favored by more and more *** data storage and calculation problems have also been *** the same time,outlier detection problems in mass data ha...
详细信息
In recent years,the rapid development of big data technology has also been favored by more and more *** data storage and calculation problems have also been *** the same time,outlier detection problems in mass data have also come along with ***,more research work has been devoted to the problem of outlier detection in big ***,the existing available methods have high computation time,the improved algorithm of outlier detection is presented,which has higher performance to detect *** this paper,an improved algorithm is *** SMK-means is a fusion algorithm which is achieved by Mini Batch K-means based on simulated annealing algorithm for anomalous detection of massive household electricity data,which can give the number of clusters and reduce the number of iterations and improve the accuracy of *** this paper,several experiments are performed to compare and analyze multiple performances of the *** analysis,we know that the proposed algorithm is superior to the existing algorithms.
Wind turbine spindle is the connecting part of impeller and *** has the function of transmitting torque and energy in the transmission chain of the *** needs to bear the bending moment and thrust of the wind wheel,so ...
详细信息
ISBN:
(纸本)9781509046584
Wind turbine spindle is the connecting part of impeller and *** has the function of transmitting torque and energy in the transmission chain of the *** needs to bear the bending moment and thrust of the wind wheel,so the failure rate of spindle is ***,the condition monitoring of the spindle is directly related to the stability of wind turbine and power *** spindle temperature model is established and used to predict by the nonlinear state estimate technology under the normal operating condition of the *** the spindle fails,the observation vector of the model input changes obviously,resulting in a significant change of the prediction *** order to improve the sensitivity and reliability of the spindle anomaly early warning,using the double moving window calculate the statistic properties of the residual sequence based on the Lewitt *** the residual mean or standard deviation exceeds the set fault alarm threshold,an alarm message will be *** the actual operating data of wind turbine spindles verify the validity of this method.
Indoor building environment for energy saving and human health has important significance and the main criterion for evaluating its quality is environmental *** experimental scheme for obtaining the mathematical model...
详细信息
ISBN:
(纸本)9781509046584
Indoor building environment for energy saving and human health has important significance and the main criterion for evaluating its quality is environmental *** experimental scheme for obtaining the mathematical model of the main parameters is designed by analyzing the parameters that affect the environmental *** scheme establishes a discrete bilinear model with parameters and control variables,and uses the the least squares method to obtain the model parameters based on the experimental *** simulation results show that the experimental scheme of this paper has strong universality and adaptability,and the model with the deviation of the real system is small,which can be used as the model basis for optimizing the control of the indoor building environment.
This paper provides a mixed attention network for remote sensing image classification whose idea comes from VQA methods. In this way, it could deal with more complex requests beyond just identifying what is in the pic...
详细信息
This paper provides a mixed attention network for remote sensing image classification whose idea comes from VQA methods. In this way, it could deal with more complex requests beyond just identifying what is in the picture. The HAN (Hierarchial Attention Network) consists of an attention model to detect details on one hand and a self-attention model to detect global information on the other hand. Through attention heat maps we could see division of work is really effective and the HAN has a great performance on NWPU-RESISC45 data set. Furthermore, we may add some other subnetworks to reinforce this ability in the future.
Taking an electrode-type electric boiler as the object, the factors influencing the thermal load of the electric boiler are analyzed. A prediction model for the thermal load is established with neural network, and the...
ISBN:
(纸本)9781538680988;9781538680971
Taking an electrode-type electric boiler as the object, the factors influencing the thermal load of the electric boiler are analyzed. A prediction model for the thermal load is established with neural network, and the model parameters are optimized by Gravitational Search Algorithm (GSA)to improve the convergence performance of its training process. The results show that, the neural network model can fit the nonlinear characteristics among input and output variables, and GSA significantly improves the training speed of the neural network model. The model can predict the electric boiler thermal load accurately under various conditions. It can also participate in peak regulation and frequency regulation of power grid combining with thermal power units, which can improve the operational flexibility of thermal power unit.
This paper applies ADRC algorithm to the inverted pendulum stabilization *** the extended state observer and control law can be nonlinear or linear,different combinations are designed to balance the pendulum's ***...
详细信息
ISBN:
(纸本)9781509046584
This paper applies ADRC algorithm to the inverted pendulum stabilization *** the extended state observer and control law can be nonlinear or linear,different combinations are designed to balance the pendulum's *** also offers a practical solution that the nonlinear parameters are tuned as the linear *** output response speed and control variable are compromised to determine the preferable *** showed that ADRC has good performance on stability,anti-interference and robustness.
暂无评论