摘要：
The input and output characteristic of thermocouple vacuum gauge exhibits high nonlinearity, which comes from the gauges' inherent physical peculiarities and causes big error in measurement results. There is a need to make compensation of the nonlinearity for accurate measurement. In this article, a least squares support vector machine (LS-SVM) model is developed to function as a compensator with which to accomplish this task. Particle swarm optimization (PSO) algorithm is introduced to search optimal parameters combination of the LS-SVM model. Based on the real sensor measurements obtained from a solar water heater plant, experiments were performed to investigate the compensation accuracy with developed LS-SVM compensator model and higher compensation accuracy results were obtained.
作者机构：
[Wang L.-H.] College of Economics and Management, University of South China, Hengyang 421001, China;[Tang Y.-G.; Gao S.; Qu X.] College of Electrical Engineering, University of South China, Hengyang 421001, China
通讯机构：
[Qu, X.] C;College of Electrical Engineering, , Hengyang 421001, China
会议名称：
2nd International Conference on Materials Science and Manufacturing, ICMSM 2013
会议时间：
29 March 2013 through 31 March 2013
会议地点：
中国湖南张家界
关键词：
Blast furnace;Hot metal silicon content;Least squares support vector machine;Particle swarm optimization;Prediction model
作者机构：
[Luo, Qiang; Kuang, Zhonghua; Li, Lanjun; Gao, Song] Univ South China, Sch Elect Engn, Hengyang 421001, Peoples R China.
会议名称：
2013 25th Chinese Control and Decision Conference (CCDC)
会议时间：
May 2013
会议地点：
Guiyang, China
会议论文集名称：
2013 25th Chinese Control and Decision Conference (CCDC)
关键词：
Tobacco feeding by air;ARM;Closed-loop control;human machine interface
摘要：
In tobacco industry, the air for feeding tobacco and the air for dusting are supported simultaneously to save energy and reduce emission. Feeding speed is vital to the quality of the production. The paper puts forward a control system based on Advanced RISC Machines(ARM), touch panel and PLC. It describes the component structure of control system, control principle and the design of hardware and software in detail. Testing results showed that the built system is running well in the cigarette maker and demonstrated excellent performance like fast and accurate response and strong robustness. Air speed during feeding is controlled precisely with deviation less than +/- 1 m/s. The system satisfied all standards of design requirement. Effective tobacco feeding will increase production safety and decrease energy and tobacco consumption.
摘要：
A method for compensating nonlinear characteristic of thermocouple vacuum gauge is proposed. Least squares support vector machine (LS-SVM) is adopt as compensation model, of which parameters are optimized using particle swarm optimization (PSO) algorithm. Experimental results using data obtained on-site show that the proposed approach effectively compensates the nonlinearity characteristic, and the accuracy of this method is higher than those obtained by SVM model.
摘要：
A simulation system for instrument cluster based on the CANoe from Vector company is developed and used for real-time cluster test and fault analysis. Test results show that the operation condition of cluster can be simulated and the fault data from CAN bus can be collected, replayed and analyzed using this system.
作者机构：
[喻寿益] College of Information Science and Engineering, Central South University, Changsha 410083, China;[高嵩; 唐耀庚] School of Electrical Engineering, University of South China, Hengyang 421001, China;[李兰君] College of Information Science and Engineering, Central South University, Changsha 410083, China, School of Electrical Engineering, University of South China, Hengyang 421001, China
通讯机构：
[Li, L.-J.] C;College of Information Science and Engineering, , Changsha 410083, China
期刊：
INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTATION TECHNOLOGY AND AUTOMATION, VOL 1, PROCEEDINGS,2008年:1008-1011
通讯作者：
Li Lanjun
作者机构：
[Li Lanjun; Yu Shouyi] Cent S Univ, Coll Informat Sci & Engn, Changsha 410083, Peoples R China.;[Li Lanjun; Gao Song; Tang Yaogeng] Univ South China, Sch Elect Engn, Hengyang 421001, Hunan, Peoples R China.
通讯机构：
[Li Lanjun] C;Cent S Univ, Coll Informat Sci & Engn, Changsha 410083, Peoples R China.
会议名称：
International Conference on Intelligent Computation Technology and Automation(2008 智能计算技术与自动化国际会议 ICICTA 2008)
会议时间：
2008-10-20
会议地点：
长沙
会议论文集名称：
International Conference on Intelligent Computation Technology and Automation(2008 智能计算技术与自动化国际会议 ICICTA 2008)论文集
摘要：
Nuclear pulse is directly related to the radiation intensity but influenced by statistical fluctuation. Because most available rate-meters have complex structure of circuits, we introduce a chip-microcomputer-based nuclear count rate measuring system which is easily incorporated into isotope gauges for measurement on level, density, thickness, etc. To make continuous measurement of the count rate, the time period is divided equally into a lot of intervals. The sample frequency is increased by making the interval smaller. The box car averaging and self-adapting weighted algorithm for continuous count rate measurement are explained in details. Simulations show that both methods can substantially decrease the statistical fluctuation by appropriately choosing the number of data used for on-line measurement and the weighted algorithm gives minimum variance. In a word, the measuring system is a fast rate meter with simple construction and high accuracy.
