Detection and control of layer width in fused plus wire arc additive manufacturing

Abstract

Fused plus wire arc additive manufacturing is a low cost and high efficiency manufacturing technology for large scale metal parts. Aiming at the difficulty and low accuracy of component size information acquisition under strong arc light, this paper designs a laser bandpass composite filter system based on the intensity of the spectral characteristics. The component size features are extracted by image processing algorithms such as edge detection, threshold division, and line fitting. Through the adaptive control of the forming speed, the deposition width deviation is automatically corrected. The results show that under strong arc light, the feature size accuracy monitoring reaches 91.79%, and the clear image of deposition layer can be obtained effectively. This method can realize the effective forming with the deposition width of 5.5–10 mm and can accurately change the deposition layer width on demand. The dynamic control value error of the deposition feature size is less than 0.4 mm, that is, the control system can effectively ensure the component surface accuracy.

SE-CBAM-YOLOv7: An Improved Lightweight Attention Mechanism-Based YOLOv7 for Real-Time Detection of Small Aircraft Targets in Microsatellite Remote Sensing Imaging

“…YOLOv7 incorporates the SPPCSPC (Spatial Pyramid Pooling and Connected Spatial Pyramid Convolution) module. SPPCSPC was initially presented in YOLOv5 [18], extracts image features, and enhances target detection performance. This module combines the Spatial Pyramid Pooling (SPP) and Channel Pyramid Convolution (CSPC) techniques.…”