Wu D.,Hunan University |
Wu D.,Sany Intelligent Control Equipment Co. |
Jin M.,Hunan University
Zhongguo Jixie Gongcheng/China Mechanical Engineering | Year: 2011
According to poor performance of the traditional method in large dataset and strong noise environment, the various kinds of fault class and atrocious work conditions of hydraulic pumps, a novel state recognition method called fault-tolerant adaptive SVM (FTASVM) was proposed herein. It achieved a fast classification by: (1)importing fault-tolerant; (2)selecting the binary SVMs which can divide one class from all other classes; (3)selecting the binary SVMs with the fewest average number of support vectors (SVs); (4)To improve the adaptability of multi-fault diagnosis, an incremental learning algorithm was imported to train the model. In order to verify the superiority of FTASVM , it was applied to the fault diagnosis of hydraulic pump of concrete pump truck. Experiments demonstrate FTASVM can speed up the test phase remarkably and remain the high accuracy of classification.
Xia M.X.,Changsha University |
Luo S.F.,Sany Intelligent Control Equipment Co. |
Peng G.F.,Changsha University
Materials Science and Technology (United Kingdom) | Year: 2015
Titanium dioxide nanostructures have been synthesised by annealing the Pd loaded titanium foil at 680°C under the atmosphere of Ar or Ar-H2 gas mixture. The microstructure and production of titanium dioxide are found to depend critically on the concentration of Pd catalyst and the Ar-H2 atmosphere. The catalyst of Pd and the introduction of 5%H2 gas are the key factor for the formation of the long (about 100 mm in the average) and smooth titanium dioxide nanowires at low temperature. Scanning electron microscope and X-ray diffraction show that they are all rutile phase. The further result shows that the titanium dioxide nanowires possess good crystallinity and high surface photovoltage response. © 2015 Institute of Materials, Minerals and Mining.
Yuan D.,Hunan International Business Vocational College |
Li X.,Central South University |
Zhu N.,Sany Intelligent Control Equipment Co.
Journal of Computational Information Systems | Year: 2014
In oil production, we use petroleum perforating bullet to make perforation from which oil outflow. How to predict the depth of perforation to reduce the cost of testing is a research focus. In this paper, we train BP neural network based on training data, and predict the depth of perforation in this model. In order to get better result, we proposed a way named EDAD (Estimate Distribution with Angle and Distance) to judge the quality of training data. According to the quantity of each EDAD of input data, we can add several pivotal samples to get the more accurate result. 1553-9105/Copyright © 2014 Binary Information Press.
Song Y.,Tsinghua University |
Hu J.,Tsinghua University |
Yang X.,University of Science and Technology Beijing |
Fu J.,Sany Intelligent Control Equipment Co. |
Xie X.,Sany Intelligent Control Equipment Co.
ICSPS 2010 - Proceedings of the 2010 2nd International Conference on Signal Processing Systems | Year: 2010
The sampling storage method which used in the current data stream could not respond data tendency effectively. For the problem, this paper presents a new processing method based on curve fitting. A weighted least-square principle is used to fit the cached stream data and better model description is obtained. Then the fitting results are analyzed by clustering algorithm, which serves as a classifier for polynomial fitting parameters. According to the clustering result, the appropriate window size will be given to fit the periodic stream data. Comparing the function solutions with the actual data, the different methods are adopted to store data according to the comparison result. The experimental results indicate that the proposed method has better fitting accuracy and compression ratio, could meet the requirement of data stream processing. And the data tendency could be responded effectively by the fitting results. © 2010 IEEE.
Yang D.,Sany Intelligent Control Equipment Co. |
Chen X.,Sany Intelligent Control Equipment Co. |
Xiong J.,Sany Intelligent Control Equipment Co.
Zhongguo Jixie Gongcheng/China Mechanical Engineering | Year: 2014
According to the poor performance of the traditional data network resources sharing capability and data load ability, and combined with the increasing number of intelligent parts of construction machinery and the demand of data complexity, based on the high reliability of CAN and the good performance of the throughput capacity and resource sharing ability of industrial ethernet, a novel network construction was proposed herein, the basic idea was double nets shunt. Experiments demonstrate it can ensure the low packet loss, and well meet multi-unit and communication requirements needed in industrial scene.