Entity

Time filter

Source Type


Zhao X.,University of Science and Technology Beijing | Zhao X.,Key Laboratory of Advanced Control of Iron and Steel Process | Zhang Z.,University of Science and Technology Beijing | Meng W.,Nanyang Technological University
2012 International Conference on Computational Problem-Solving, ICCP 2012 | Year: 2012

Wireless based data acquisition solutions are widely used in many fields like structure monitoring, transportation or environmental studies. This paper presents a General Packet Radio Service (GPRS) based remote data acquisition and forecasting system, which monitors the geological disasters along the natural gas pipeline under the ground. The field data terminal units (DTU) collect data from the sensors installed on the pipe, and transmit the data by GPRS module to the server in the control center. The server processes the data, broadcasts on the website, and forecasts abnormal variation in time. Three years' operation in site shows the system is effective and feasible. © 2012 IEEE. Source


Qun Y.,University of Science and Technology Beijing | Qun Y.,Key Laboratory of Advanced Control of Iron and Steel Process | Qing L.,University of Science and Technology Beijing | Zhang P.,University of Science and Technology Beijing | Yu D.,University of Science and Technology Beijing
26th Chinese Control and Decision Conference, CCDC 2014 | Year: 2014

Proton Exchange Membrane Fuel cell has many perfect characters and becomes one of the most important research subjects among domestic and international fuel cell fields. Heat transfer management is one of the key technologies for PEM fuel cell. This paper built a temperature model of PEM fuel cell based on fuzzy technology, which divided the fuzzy space evenly by established rules, got the number of fuzzy rules and rules application degree, identified the consequent parameters by least square method. This model is fit for multi-variables and has simple construction and high accuracy. Finally, simulation examples show the effectiveness of the modeling. © 2014 IEEE. Source


Wang L.,University of Science and Technology Beijing | Wang L.,Key Laboratory of Advanced Control of Iron and Steel Process | Guo H.,China Energy Conservation and Emission Reduction Co.
Chinese Control Conference, CCC | Year: 2014

Soft-sensors have been widely used for estimating product quality or other key variables. To achieve high estimation performance for soft-sensor design, it is important to select appropriate input or explanatory variables. This paper presents a new feature selection method applied to Soft-sensors. The proposed method, referred to as FCA-ARM (fuzzy clustering analysis-association rule mining). The measured variables were first clustered on the basis of the correlation by fuzzy clustering analysis, and each variable cluster was further evaluated by association rules mining, which can discover the important input variables that are related to the output variable based on the Apriori algorithm. By applying this method with the influence degree analysis, the overlap information can be effectively eliminated, and the important variables can be obtained as input variables. The usefulness of the proposed FCA-ARM feature selection method is demonstrated through an application to mechanical property forecasting in industrial hot rolling process. © 2014 TCCT, CAA. Source


Ling W.,University of Science and Technology Beijing | Ling W.,Key Laboratory of Advanced Control of Iron and Steel Process | Lu W.L.,University of Science and Technology Beijing | Lu W.L.,Key Laboratory of Advanced Control of Iron and Steel Process
Journal of Intelligent and Fuzzy Systems | Year: 2014

This paper presents a fuzzy rules extraction algorithm based on output-interval clustering and support vector regression. The approach is unlike most existing clustering algorithms for structure identification of fuzzy systems, where the focus is on combined input-output clustering. The output-interval clustering algorithm divides the output space into several partitions and each output partition is considered to be an interval; then, input data are projected into sub-clusters that are based on the input distribution constrained by the output intervals. Fuzzy rules are extracted from sub-clusters within each output interval. In order to have a more compact final system structure and better accuracy, local functions associated with each of the sub-clusters based on support vector regression are constructed. The fuzzy rule-based modeling scheme gradually adapts its structure and rules antecedent and consequent parameters from data. Its main purpose is continuous learning, and adaptation to unknown environments. To illustrate the effectiveness of the approach, the paper considers a 2-D nonlinear function approximation, chaotic time series prediction and an operation learning application of steel mechanical property forecasting. © 2014 - IOS Press and the authors. Source


Yu Y.,University of Science and Technology Beijing | Yu Y.,Key Laboratory of Advanced Control of Iron and Steel Process | Sun C.-Y.,University of Science and Technology Beijing | Sun C.-Y.,Key Laboratory of Advanced Control of Iron and Steel Process
2013 25th Chinese Control and Decision Conference, CCDC 2013 | Year: 2013

Robust attitude decentralized tracking control problem for a 3-DOF helicopter is investigated. The model of the 3-DOF helicopter is described as a MIMO strict-feedback form system with unknown parameters, bounded disturbances, nonlinear uncertain coupling effects and unknown input-delay. A new design method based on signal compensation technique and backstepping strategy is proposed. Based on the signal compensation method, at each backstepping design step, a robust controller consists of a nominal controller and a robust compensator. Robust practical tracking stability condition is derived in terms of linear matrix inequalities (LMIs). Experimental results demonstrate the effectiveness of the proposed control strategy. © 2013 IEEE. Source

Discover hidden collaborations