English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

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%.

Prediction of Manufacturing Quality of Holes Based on a BP Neural Network