In order to improve the manufacturing quality of holes (Φ3–Φ8 mm) and to optimize the hole drilling process in T300 carbon fiber-reinforced plastic (CFRP) and 7050-T7 Al alloy stacks, a prediction model of multiple objective parameter optimization was proposed based on a back propagation (BP) neural network algorithm. Four parameters of feed rate, spindle speed, drilling diameter, and cushion plate were taken as the input layer parameters to study the manufacturing quality of holes in four stack types: CFRP/Al, Al/CFRP, Al/CFRP/Al, and CFRP/Al/CFRP. Delamination and tearing defects often appear in the drilling process; thus, a certain degree of defects in CFRP was selected as the output parameter, in an effort to build a prediction model of drilling quality. After the neural network model of the optimized hole-making process of an 8–14–1 three-layer topology was corrected by 170 steps, the error was reduced to 0.00016882, the regression fitting was 0.99978, and the fitting error of training samples was 10⁻²~10⁻⁵. The prediction model of the number of defective holes provided basically similar results to the experimental data. This indicates that the prediction model based on a BP neural network has good prediction ability. Based on the prediction of parameters, verification tests were performed, and the number of defective holes in CFRP was reduced while the manufacturing quality of the holes was improved significantly; the qualified rate of manufactured holes reached 97%.

This research studies an effective polishing process to elevate the surface precision and homogeneity by improving the polishing trajectory of magnetic brush. The moment of magnetic brush is a key influence factor on finishing characteristics, but in conventional plane magnetic abrasive Polishing process, the movements of magnetic brush is relatively simple. In this paper a polishing process using the complex polishing trajectory of magnetic brush has been modified and studied by use of newly designed experiment device. The linear movement of workpiece, the rotation and revolution or movement in XY coordinate plane of magnetic brush can be realized by this device. In comparison with conventional method, variation regularity about surface roughness and the material removal are been studied. According to experimental results for polishing trajectory of magnetic brush, finishing characteristics was clarified. The results show that studies on polishing trajectory of magnetic brush are more valuable and the experimental researches are consistent with theoretical analysis. In addition, the accuracy of plane magnetic abrasive finishing can be elevated in terms of the reasonable planning for polishing trajectory of magnetic brush.

Based on the mechanism of magnetic abrasive finishing, the 7075 aluminum alloy (Al7075) was used in the experimental study. In order to improve wall surface quality and to remove the edge burrs of the hole, a novel magnetic abrasive finishing process was proposed. First, the radial magnetizing pole for the inner surface finishing process was confirmed. The evaluation of magnet spinning speed, abrasive mesh, and abrasive filling amount on the diameter deviation of the hole and surface roughness of the inner wall was studied. According to the characteristics of magnetic abrasive finishing process, Taguchi’s method was used to carry out the test. Through the analysis of variance, the best process parameters were determined and verified. The inner surface roughness was further decreased and the surface morphology was more uniform after finishing process. Second, the edge burr removal process of the hole exit was also studied, and the geometry of the burrs was measured before and after the magnetic abrasive finishing process. The results show that the burrs were significantly removed and the burr removal efficiency was improved by 33.3% compared with the conventional magnetic abrasive finishing process. Finally, the improved magnetic abrasive finishing process is an effective method in improving finishing quality of the Al7075 holes.