A hybrid deep learning model for robust prediction of the dimensional accuracy in precision milling of thin-walled structural components

The use of artificial intelligence to process sensor data and predict the dimensional accuracy of machined parts is of great interest to the manufacturing community and can facilitate the intelligent production of many key engineering components.In this study,we develop a predictive model of the dimensional accuracy for precision milling of thin-walled structural components.The aim is to classify three typical features of a structural component—squares,slots,and holes—into various categories based on their dimensional errors(i.e.,“high precision,”“pass,”and“unqualified”).Two different types of classification schemes have been considered in this study:those that perform feature extraction by using the convolutional neural networks and those based on an explicit feature extraction procedure.The classification accuracy of the popular machine learning methods has been evaluated in comparison with the proposed deep learning model.Based on the experimental data collected during the milling experiments,the proposed model proved to be capable of predicting dimensional accuracy using cutting parameters(i.e.,“static features”)and cutting-force data(i.e.,“dynamic features”).The average classification accuracy obtained using the proposed deep learning model was 9.55%higher than the best machine learning algorithm considered in this paper.Moreover,the robustness of the hybrid model has been studied by considering the white Gaussian and coherent noises.Hence,the proposed hybrid model provides an efficient way of fusing different sources of process data and can be adopted for prediction of the machining quality in noisy environments.

Precision Milling of Integrated Turbine Based on a Non-Contact On-Machine Measurement System

The machining accuracy of the curved surfaces of integrated turbine blades directly determines the performance and service life of the turbojet engine system.In this paper,a non-contact on-machine measurement system is developed for precision milling of integrated turbines to reduce the impact of workpiece deformation,overcutting,tool chatter,and material work hardening.Milling with the on-machine measurement system obtained high-quality integrated turbine surfaces.The geometric accuracy error(PV)is below 3μm,and the surface roughness(Ra)is less than 2μm.The processed integrated turbine blade can achieve the accuracy requirements in the design and manufacturing and can be practically applied to the entire turbojet engine.

Focused ion beam built-up on scanning electron microscopy with increased milling precision

In this work,a focused ion beam(FIB)-scanning electron microscopy(SEM) dual beam system was successfully built by integrating a FIB column and a graphics generator onto a SEM.Real-time observation can be realized by SEM during the process of FIB milling.All kinds of graphics at nanoscale regime,such as lines,characters,and pictures,were achieved under the control of graphics generator.Moreover,the FIB milling line width can be reduced nearly 27% by the introduction of simultaneous electron beam,and a line width as small as 10 nm was achieved.The numerical analysis indicates that the significant improvement on line width is induced by the Coulomb interaction between the electrons and ions.