Deep-learning approach for predicting laser-beam absorptance in full-penetration laser keyhole welding.

Laser-beam absorptance in a keyhole is generally calculated using either a ray-tracing method or electrodynamic simulation, both physics-based. As such, the entire computation must be repeated when the keyhole geometry changes. In this study, a data-based deep-learning model for predicting laser-beam absorptance in full-penetration laser keyhole welding is proposed. The model uses a set of keyhole top- and bottom-aperture as inputs. From these, an artificial intelligence (AI) model is trained to predict the laser-energy absorptance value. For the training dataset, various keyhole geometries (i.e., top- and bottom-aperture shapes) are hypothetically created, upon which the ray-tracing model is employed to compute the corresponding absorptance values. An image classification model, ResNet, is employed as a learning recognizer of features to predict absorptance. For image regression, several modifications are applied to the structure. Five model depths are tested, and the optimal AI architecture is used to predict the absorptance with an R2 accuracy of 99.76% within 1.66 s for 740 keyhole shapes. Using this model, several keyhole parameters affecting the keyhole absorptance are identified.

Fabrication of a compound infrared microlens array with ultrashort focal length using femtosecond laser-assisted wet etching and dual-beam pulsed laser deposition.

We present the design, fabrication, and characterization of a compound infrared microlens array having an ultrashort focal length and a hyperbolic profile that comprises a PDMS microlens array and a GRIN lens. A concave microlens mold was first fabricated on a fused silica substrate using femtosecond laser irradiation followed by a wet etching process, and a standard replication process was employed to fabricate a PDMS convex lens array. To shorten the focal length further and cut off the visible spectrum of light, a graded DLC/silicon coating, which functioned as a GRIN lens and a visible light cut-off filter, was additionally deposited using dual-beam pulsed laser deposition. The lenslet diameter was 6 µm and the graded coating reduced the focal length from 4.5 to 2.9 µm.

Highly Flexible and Efficient All-Polymer Solar Cells with High-Viscosity Processing Polymer Additive toward Potential of Stretchable Devices.

Considering the potential applications of all-polymer solar cells (all-PSCs) as wearable power generators, there is an urgent need to develop photoactive layers that possess intrinsic mechanical endurance, while maintaining a high power-conversion efficiency (PCE).Herein a strategy is demonstrated to simultaneously control the intercalation behavior and nanocrystallite size in the polymer-polymer blend by using a newly developed, high-viscosity polymeric additive, poly(dimethylsiloxane-co-methyl phenethylsiloxane) (PDPS), into the TQ-F:N2200 all-PSC matrix. A mechanically robust 10wt% PDPS blend film with a great toughness was obtained. Our results provide a feasible route for producing high-performance ductile all-PSCs, which can potentially be used to realize stretchable all-PSCs as a linchpin of next-generation electronics.