Font Size: a A A

Analysis Of Deformation In Machining And Parameter Optimization Technology For Long Guide Rail

Posted on:2016-05-15Degree:MasterType:Thesis
Country:ChinaCandidate:L G LiFull Text:PDF
GTID:2272330476954811Subject:Mechanical engineering
Abstract/Summary:PDF Full Text Request
Aviation aluminum-alloy has many excellent properties such as low density and high strength. It serves as thin-wall structure and overall frame, which are widely used in aerospace manufacturing. However, during manufacturing, the components are prone to deformation or even scrapped in the worst cases due to their low stiffness and high surface accuracy requirement. As a result, controlling the deformation has become a vital issue in domestic aviation industry. In order to reduce the deformation, research on the parameter optimization of the machining process of components is needed.Thin-walled guide rail is the key component of aerospace launch. However,the guide rail is prone to deformation in machining especially milling slot feature. In order to reduce the machining deformation of thin-walled guide rail slot, this paper put forward the optimization technology of milling process parameters based on improved QPSO.1. The real size three-dimensional milling cutting tool and guide rail model is constructed and a finite element model is established to simulate the milling process of the slot feature using force-thermal coupling technology. A real experiment is then conducted and the real deformation data of guide rail are collected via three-dimensional coordinate measuring instrument to validate the model.2. The maximum accuracy and the minimum complexity of network are considered as training objectives, and finite element simulation data are used as training samples to train the improved four layers neural network prediction model, and the test samples are used to validate the prediction accuracy and generalization ability of the neural network model.3. Finally, quantum-behaved particle swarm optimization(QPSO) based on improved optimal strategy jumping out of the local extremum is presented, and used for combinatorial optimization of milling process parameters, which embodied as the minimized machining deformation of the guide rail slot. The results demonstrate the superiority of the improved QPSO and obtain the optimized machining parameters, which has a great significance towards real production of such parts.
Keywords/Search Tags:Thin-walled guide rail slot, milling process parameters optimization, deformation control, neural network model, improved QPSO
PDF Full Text Request
Related items