Drilling with a high-energy electron beam on a semiconductive ceramic substrate is emerging as an effective solution for creating high-aspect-ratio microholes. This method effortlessly surpasses band gaps and facilitates machining with continuous irradiation. However, the inherent brittleness and crystallinity of the semiconductive ceramic substrate hinder handling for quality analysis of the drilled substrate. From experimental drilling, the unique deformation history of the microhole with a high-energy electron beam hints at the potential for predictive modeling for non-destructive analysis of the microhole. In this study, we proposed a conditional generative adversarial network model for the non-destructive analysis of drilled microholes. We collected a limited number of images of hole inlets and cross-sectional holes for training and testing the network model. To effectively build the predictive model with our limited dataset, we introduced a generative adversarial network architecture with embedding a self-attention mechanism with multiple parallel heads. This architecture combines the advantages of the convolutional neural networks and the self-attention mechanism. The proposed architecture showed improvements in training loss and evaluation for image generation compared to the original convolutional neural network. The predictive precision for the inlet diameter, hole straightness, and drilled depth was enhanced by 11.6 %, 8.3 %, and 15 %, respectively. The maximum improvement in predictive accuracy for the inlet diameter, hole straightness, and drilled depth was 36.2 %, 22.98 %, and 58.6 %, respectively. These results indicate that the proposed model not only generated the geometrical profile of the cross-sectional hole but also accurately predicted geometrical dimensions.

Delamination is a prevalent issue in carbon fiber-reinforced plastic (CFRP) drilling, significantly compromising the mechanical properties of the material. Considering that delamination can impact the long-term durability of the final products, it is essential for operators to promptly identify it. This paper proposes a machined surface image generation model, called Sensor2Image, that employs time-series force sensor data as input and generates drilled-hole surface images as output. Sensor2Image first encodes the force sensor data into images using the Gramian angular field (GAF) method. Subsequently, it applies an image-to-image translation technique to generate the final machined surface images. The proposed model was trained and evaluated using experimental data gathered from drilling CFRP specimens under an industrial robot machining system. The results demonstrated the versatility of the proposed model for practical applications, regardless of the delamination factor. The proposed method offers significant advantages over existing methods through its intuitive visual representation approach. It facilitates the visual inspection of delamination while enabling surface quality analysis of the drilled hole and identification of defects or irregularities that may impact the mechanical properties of the material. The proposed approach can enhance the efficiency and reliability of industrial processes, particularly those involving complex delamination factors. It is a valuable tool for optimizing the CFRP drilling process and enhancing drilled-hole quality in a user-friendly manner.