Entity

Time filter

Source Type

Harbin, China

Harbin University of Science and Technology is a university in Harbin, China. Previously known as Harbin University of Science . It is colloquially known as Hakeda , as opposed to Hagongda, which is Harbin Institute of Technology. Wikipedia.


Sun J.,Harbin University of Science and Technology
Neurocomputing | Year: 2012

In this paper, a neural classifier based on the newly developed local coupled feedforward neural network, which may improve the convergence of BP learning significantly, is developed. A binary threshold unit is used as the output node of the classifier. A general error gradient of the output node is defined for the BP training of the classifier. And a hidden node selection scheme is developed for the local coupled feedforward neural network. In addition, we derive a result on the "universal approximation" property of the local coupled feedforward neural network with an arbitrary group of window functions, which can cover the region of training samples. Simulation results show that the general error gradient and the hidden node selection scheme work well. © 2011 Elsevier B.V. Source


Ying X.,Harbin University of Science and Technology
IEEE Transactions on Magnetics | Year: 2010

In this paper, the influences of broken bars located at different relative positions in an induction motor are presented. In this investigation, a finite-element model of the squirrel-cage induction motor is developed. Both thermal and electromagnetic analysis of the induction motor operating in conditions of healthy and broken bars fault are carried out, and operating performance and thermal fields with two broken rotor bars located at different relative positions are studied. The accuracy of simulation is verified by experimental results derived from a prototype. From the results, some valuable ideas can be proposed to the broken bars' fault diagnosis. © 2010 IEEE. Source


Yongmei J.,Harbin University of Science and Technology
Advances in Information Sciences and Service Sciences | Year: 2012

As the connection of micro-electronics and powerful engineering equipment, Electro-Hydraulic proportional controller has been important part of integration of mechanics and electrics. It's the core of Electro-Hydraulic proportional controller system and has a tremendous impact on it. The prevalence of domestic proportional controller poor reliability, short life and other issues, therefore, this paper developed a new type of electro-hydraulic proportion controller with a graphics user interface based on Qt. After experiment, it shows the controller has some advantages as follows, low power consumption, high repeatability precision and low temperature drift. And the graphics user interface is friendly with stable performance. Source


Sun J.,Harbin University of Science and Technology
Neural Networks | Year: 2010

In this paper, the local coupled feedforward neural network is presented. Its connection structure is same as that of Multilayer Perceptron with one hidden layer. In the local coupled feedforward neural network, each hidden node is assigned an address in an input space, and each input activates only the hidden nodes near it. For each input, only the activated hidden nodes take part in forward and backward propagation processes. Theoretical analysis and simulation results show that this neural network owns the "universal approximation" property and can solve the learning problem of feedforward neural networks. In addition, its characteristic of local coupling makes knowledge accumulation possible. © 2009 Elsevier Ltd. All rights reserved. Source


Sun J.,Harbin University of Science and Technology
Neural Networks | Year: 2010

In this paper, a new neural belief network, which has considered backward inferences and the influence of the belief sources on belief propagations, is developed. In this new neural network, a link record set is built for every conclusion node for handling the multiple conditions of inference rules, and a route record set is built for every active node and every active link for handling the dependency of belief propagations on the belief sources. In addition, a temporary node is added for every evidence node. The assignment of the temporary nodes releases the evidence nodes from the role as belief sources and allows belief propagations in them. As a result, the new neural belief network can handle both definite evidences and indefinite evidences, and the evidences may come from observations or the prior knowledge of experts. The inference processes of the new neural belief network are based on available evidences and if...then rules. Therefore, it can solve the problems of Bayesian networks caused by the prior knowledge reliance and may be an alternative technique to the popular Bayesian networks. © 2009 Elsevier Ltd. All rights reserved. Source

Discover hidden collaborations