Prediction and control of surface roughness for the milling of Al/SiC metal matrix composites based on neural networks

In recent years,there has been a significant increase in the utilization of Al/SiC particulate composite materials in engineering fields,and the demand for accurate machining of such composite materials has grown accordingly.In this paper,a feed-forward multi-layered artificial neural network(ANN)roughness prediction model,using the Levenberg-Marquardt backpropagation training algorithm,is proposed to investigate the mathematical relationship between cutting parameters and average surface roughness during milling Al/SiC particulate composite materials.Milling experiments were conducted on a computer numerical control(C N C)milling machine with polycrystalline diamond(PCD)tools to acquire data for training the ANN roughness prediction model.Four cutting parameters were considered in these experiments:cutting speed,depth of cut,feed rate,and volume fraction of SiC.These parameters were also used as inputs for the ANN roughness prediction model.The output of the model was the average surface roughness of the machined workpiece.A successfully trained ANN roughness prediction model could predict the corresponding average surface roughness based on given cutting parameters,with a 2.08%mea n relative error.Moreover,a roughness control model that could accurately determine the corresponding cutting parameters for a specific desired roughness with a 2.91%mean relative error was developed based on the ANN roughness prediction model.Finally,a more reliable and readable analysis of the influence of each parameter on roughness or the interaction between different parameters was conducted with the help of the ANN prediction model.

Scaling analysis of current influence on Hastelloy surface roughness in electro-polishing process

In this study, a series of Hastelloy tapes were electro-polished, and the dividing method was used to carry out a detailed investigation on the influence of polishing current(I) on root mean square(R_q) at various image scales(L). The electro-polishing is found to be effective mainly at L smaller than 10μm, where the R_q–I relationship could be fitted by an exponential decay function with a residual roughness value. An approximate model of electro-polishing process was established to interpret the exponential decay function. This study provides a quantified insight into the electro-polishing process, which could help to obtain more understanding of its mechanism.

Modeling the optimal compensation capacitance of a giant magnetostrictive ultrasonic transducer with a loosely-coupled contactless power transfer system

The giant magnetostrictive rotary ultrasonic processing system(GMUPS)with a loosely-coupled contactless power transfer(LCCPT)has emerged as a high-performance technique for the processing of hard and brittle materials,owing to its high power density.A capacitive compensation is required to achieve the highest energy efficiency of GMUPS to provide sufficient vibration amplitude when it works in the resonance state.In this study,an accurate model of the optimal compensation capacitance is derived from a new electromechanical equivalent circuit model of the GMUPS with LCCPT,which consists of an equivalent mechanical circuit and an electrical circuit.The phase lag angle between the mechanical and electrical circuits is established,taking into account the non-negligible loss in energy conversion of giant magnetostrictive material at ultrasonic frequency.The change of system impedance characteristics and the effectiveness of the system compensation method under load are analyzed.Both idle vibration experiments and machining tests are conducted to verify the developed model.The results show that the GMUPS with optimal compensation capacitance can achieve the maximum idle vibration amplitude and smallest cutting force.In addition,the effects of magnetic conductive material and driving voltages on the phase lag angle are also evaluated.