Abstract
Points cloud surface reconstruction method in reverse engineering was proposed, Radial basis function neural network (RBFNN) was designed, and simulated annealing arithmetic was adopted to adjust the network weights. MATLAB program was compiled, experiments on points cloud data have been done employing the program. All experiments have shown that the arithmetic can efficiently approach the surface with 10-4 mm error precision, also the learning speed is quick and reconstruction surface is smooth. Trainings have been done with other networks in comparison. The sum squared error is 4.6802×10-8mm using the algorithmic proposed in this paper, the one is 1.1014×10-6mm under the same parameters employing RBFNN only. Back-propagation learning algorithm network does not converge until 3500 iterative procedure, and exactness design RBFNN is time-consuming. The arithmetic can approach nonlinear function by arbitrary precision, and also keep the network from getting into partial minimum.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
