Entity

Time filter

Source Type


Gao J.,Capital University of Economics and Business | Zhao B.,University of Science and Technology Beijing | Zhao B.,Key Laboratory of Advanced Control for Iron and Steel Process
Proceedings - 2011 IEEE International Workshop on Open-Source Software for Scientific Computation, OSSC-2011 | Year: 2011

Nowadays, decision tree is widely used as one of the most powerful tools in data mining. However, to construct an optimization decision tree is a complete NP problem. So a new method about how to construct decision tree, which is based on association rule mining, is proposed in this paper. Firstly, approximate exact rule with high reliability is defined. Secondly new attributes are generated from the approximate exact rule. And then its evaluation method is discussed in detail. Thirdly, the decision tree is constructed with both the new generated attributes and its original data. Finally, after comprehensive analysis, experimental results show that this new method has higher accuracy than any other old method. © 2011 IEEE. Source


Zhao B.,University of Science and Technology Beijing | Zhao B.,Key Laboratory of Advanced Control for Iron and Steel Process | Qi Y.,Communication University of China
Proceedings - 2011 IEEE International Workshop on Open-Source Software for Scientific Computation, OSSC-2011 | Year: 2011

Radial basis function (RBF) network is one of the significant neural networks. It has been used successfully in various fields. But in RBF network approximation algorithm, the initial value of the network weights, Gauss function center vector and broad-based vector is not easy to determine, and when these parameter choice is undeserved, RBF network approximation precision will decline and even the serious consequences of network spread will be produced. By using genetic algorithm in this paper, which can better realize RBF network parameter optimization, thereby increasing the accuracy of approximation. Scilab is open source software and has good simulation capabilities. Experiments using Scilab shows that the optimization method of genetic neural network is feasible and results are satisfied. © 2011 IEEE. Source


Sun Q.,University of Science and Technology Beijing | Sun Q.,Key Laboratory of Advanced Control for Iron and Steel Process | Wang Y.,Post University
Proceedings of the 29th Chinese Control Conference, CCC'10 | Year: 2010

In order to overcome the drawbacks in the sliding-mode controller and the cloud controller, a novel intelligent sliding-mode controller is studied, which combines the two controllers for the first time. A sliding-mode controller based on cloud models, which consists of an equivalent controller and a cloud controller, is proposed for nonlinear systems with system uncertainties and external disturbances. The cloud controller, with the sliding-mode function as its input, is used to replace the discontinuous switch control part to alleviate the chattering phenomenon effectively. The stability of close-loop control system is guaranteed using Lyapunov stability theory. Finallythe designed sliding-mode controller is used to control the Genesion chaos system, and the simulation results demonstrated the feasibility and robustness of the method. Source


Jing P.,University of Science and Technology Beijing | Tong C.,University of Science and Technology Beijing | Tong C.,Key Laboratory of Advanced Control for Iron and Steel Process | Hu C.,University of Science and Technology Beijing
IET Conference Publications | Year: 2012

Considering the dynamic characteristics of the deformation zone, a new model of combined shape and thickness system in rolling process was proposed, regarding bending force and gauge as the main factors. Taking various kinds of secondary causes, perturbation and disturbance into consideration, robust control methods were brought in. A mathematic model was proposed based on field data, then static decoupler and robust controller were developed with benefit of robust control toolbox in MATLAB. Simulation results show the effectiveness of tracing and decoupling and robustness for parameter perturbation. Source


Qingwen H.,University of Science and Technology Beijing | Qingwen H.,Key Laboratory of Advanced Control for Iron and Steel Process | Xianzhong C.,University of Science and Technology Beijing | Xianzhong C.,Key Laboratory of Advanced Control for Iron and Steel Process | Ping C.,University of Science and Technology Beijing
Chinese Control Conference, CCC | Year: 2015

A method of spatio-temporal data association processing based on FMCW radar in blast furnace was proposed in this paper. First, model-categories of basic stock-line profile through mining information of process of production are established. Next, predicting measured value on the basis of historical observations and associating with model category of basic stock-line shape-changing using grey relation algorithm, which acquires the expected distribution values. Finally, Welch FFT and peak-searching method of FT continuous spectrum are researched in the calculation of center distance. Simulation results indicate that the proposed method reduces the average rate of outliers from 13% to 4%, and the matching rate of fitting stock-line associating with prior model class library increases from 68% to 87%, compared with traditional interpolation fitting of direct measurement, which guides the operation of blast furnace charging reasonably. © 2015 Technical Committee on Control Theory, Chinese Association of Automation. Source

Discover hidden collaborations