Time filter

Source Type

Li B.,Hubei University of Arts and Science | Shi S.,Huazhong University of Science and Technology | Wang S.,DG HUST Manufacturing Engineering Institute
Advanced Materials Research | Year: 2013

A novel image recognition method based on chaotic-particle swarm-optimization-neural network algorithm was presented. The chaotic mapping mechanism and particle swarm algorithm were used to optimize the weight and threshold of BP neural network which was applied to the recognition of image. The simulation results show this new method can overcome the problems that BP neural network is easy to fall into local optimum and sensitive to the initial value, and has better recognition rate and stronger robustness. © (2013) Trans Tech Publications, Switzerland. Source

Lou Y.,Harbin Institute of Technology | Zhang Y.,Harbin Institute of Technology | Huang R.,Harbin Institute of Technology | Chen X.,Dong - A University | And 2 more authors.
IEEE Transactions on Automation Science and Engineering | Year: 2014

Optimal design is an inevitable step for parallel manipulators. The formulated optimal design problems are generally constrained, nonlinear, multimodal, and even without closed-form analytical expressions. Numerical optimization algorithms are thus applied to solve the problems. However, the optimization algorithms are usually chosen ad arbitrium. This paper aims to provide a guideline to choose algorithms for optimal design problems. Typical algorithms, the sequential quadratic programming (SQP) with multiple initial points, the controlled random search (CRS), the genetic algorithm (GA), the differential evolution (DE), and the particle swarm optimization (PSO), are investigated in detail for their convergence performances by using two canonical design examples, the Delta robot and the Gough-Stewart platform. It is shown that SQP with multiple initial points can be efficient for simple design problems, while DE and PSO perform effectively and steadily for all design problems. CRS can be used to generate good initial points since it exhibits excellent convergence evolution in the starting period. © 2004-2012 IEEE. Source

Cheng Y.,Huazhong University of Science and Technology | Cheng Y.,DG HUST Manufacturing Engineering Institute | Yang J.,Huazhong University of Science and Technology | Huang Q.,Huazhong University of Science and Technology
2011 International Conference on Consumer Electronics, Communications and Networks, CECNet 2011 - Proceedings | Year: 2011

The performance of motion control on a PMLSM is greatly affected by nonlinearities caused by thrust ripple. The approach of combinational iron-cored primary suggests a thrust ripple-free PMLSM. This paper investigates inductance parameter characteristics and thrust linear modeling of the PMLSM with combinational iron-cored primary. Inductance parameters are derived based on parameters of its armature modular, and symmetric and constant value characteristic of parameters is verified. Based on parameters property of the PMLSM, a thrust linear model is suggested. In comparison with a conventional PMLSM, the PMLSM resolves coupling of inductance parameters between d-axis and q-axis by Parks transformation, and a linear thrust model with a simple lumped parameter is achieved. The validation of the model is verified by simulation of finite-element method. The research predicts that a linear thrust model can be applied to implement a reliable, high efficiency and high performance control of PMLSM. © 2011 IEEE. Source

Li B.,Huazhong University of Science and Technology | Li B.,DG HUST Manufacturing Engineering Institute | Zhang G.-J.,Huazhong University of Science and Technology | Shi S.-X.,Huazhong University of Science and Technology
Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | Year: 2012

Based on the analysis of mold industry characteristics, the problems that uneven distribution of manufacturing resource and capacity seriously had impacted the development of mold industry were pointed out, and existing manufacturing model was difficult to obtain the balance of stability, quality, credit and other aspects in integration of service resource. Aiming at these problems, mould industry cloud manufacturing platform supporting industrial clusters cooperation was proposed. The content of platform was analyzed, and service object as well as application range of platform were illustrated.The system structure and key technologies of platform were discussed. The proposed platform was verified by examples, and it would play an exemplary role for the application of cloud manufacturing in other industries. Source

Chen Z.,Huazhong University of Science and Technology | Li H.,Huazhong University of Science and Technology | Huang Y.,Huazhong University of Science and Technology | Zhang Z.,DG HUST Manufacturing Engineering Institute
Applied Mechanics and Materials | Year: 2014

In the process of wire electrical discharge machining, the wire electrode inevitably suffers bending deformation due to wire tension, electrostatic force, electrodynamics force, etc., and the deflection would make an clearly negative impact upon the machining accuracy, productivity and stability. In this paper, first of all, a novel modeling and simulation method is proposed for quantitatively calculating the wire deflection. Secondly, the mainly impact factors and trend of wire deflection have been concluded. Moreover, the feasibility of the model is proved by comparing with other researchers models. Eventually, the practical approaches of reducing wire deflection and improving the machining accuracy have been proposed. © (2014) Trans Tech Publications, Switzerland. Source

Discover hidden collaborations