RESUMEN
In the present study, a physics-informed neural network model based on Bayesian hyperparameter optimization is proposed for the prediction of short crack growth paths. A large number of cyclic loadings at a lower amplitude were applied to an α titanium sample by an ultrasonic fatigue machine to ensure a sufficient amount of data for machine learning. The grain size, grain orientation and grain boundary direction on the path, as well as crack growth direction, were selected as feature data for training the prediction model. The optimizations of the size ratio and the angle operation were conducted to compare different data processing methods, respectively. After evaluation, eventually, a model for predicting crack growth path is obtained with a reliable performance of 10% tolerance on the path angle at each grain boundary. And the prediction effect of the proposed model is better than that of some classic machine learning models and slip trace analysis. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 1)'.
RESUMEN
Fiber-shaped supercapacitor (FSSC) is considered as a promising energy storage device for wearable electronics due to its high power density and outstanding safety. However, it is still a great challenge to simultaneously achieve high specific capacitance especially at rapid charging/discharging rate and long-term cycling stability of fiber electrode in FSSC for practical application. Here, a ternary poly(3,4-ethylenedioxythiophene):poly(styrenesulfonate)/reduced graphene oxide/polypyrrole (PEDOT:PSS/rGO/PPy) fiber electrode was constructed by in situ chemical polymerization of pyrrole on hydrothermally-assembled and acid-treated PEDOT:PSS/rGO (PG) hybrid hydrogel fiber. In this case, the porous PG hybrid fiber framework possesses combined advantages of highly-conductive PEDOT and flexible two-dimensional (2D) small-sized rGO sheets, which provides large surface area for the deposition of high-pseudocapacitance PPy, multiscale electrons/ions transport channels for the efficient utilization of active sites, and buffering layers to accommodate the structure change during electrochemical process. Attributed to the synergy, as-obtained ternary fiber electrode presents ultrahigh volumetric/areal specific capacitance (389 F cm-3 at 1 A cm-3 or 983 mF cm-2 at 2.5 mA cm-2) and outstanding rate performance (56 %, 1-20 A cm-3). In addition, 80 % preservation of initial capacitance after 8000 cycles for the corresponding FSSC also illustrates its greatly improved cycle stability compared with 64 % of binary PEDOT:PSS/PPy based counterpart. Accordingly, here proposed strategy promises a new opportunity to develop high-activity and durable electrode materials with potential applications in supercapacitor and beyond.
