This paper discusses the effect of basketweave microstructure on the very high cycle fatigue behavior of TC21 titanium alloy. Ultrasonic fatigue tests at 20 kHz are done on a very high cycle fatigue (VHCF) property of the alloys with 60 μm and 40 μm basketweave size, respectively. Results show that the alloys illustrate step-wise S-N characteristics over the 10⁵–10⁹ cycle regimes and that fatigue fracture in both of the alloys occur beyond the conventional fatigue limit of 10⁷ cycles. Subsurface crack initiation occurs at low stress amplitude. A fine granular area (FGA) is observed along the α lamella at the subsurface crack initiation site. The mechanism for the subsurface crack initiation is revealed using layer-by-layer-polishing, due to the micro-voids that are introduced at the granular α phase. The colony of α lamella is due to the local stress concentrated between them under the cyclic load. The stress intensity factor range at the FGA front is regarded as the threshold value controlling the internal crack propagation. Furthermore, the effect of the baseketweave size on the very high cycle fatigue limits of the TC21 titanium alloy is evaluated based on the Murakami model, which is consistent with the experimental results. The fatigue life of TC21 titanium alloy is well predicted using the energy-based crack nucleation life model.

The very high cycle fatigue (VHCF) property of TC21 titanium alloy blunt-notched specimens were investigated by using an ultrasonic fatigue test machine with a frequency of 20 kHz. S–N of blunt-notched specimens illustrated a continuous decrease characteristic with a horizontal line over the 10⁵–10⁹ cycle regimes. However, the fatigue life showed a large scatter for blunt-notched specimens. Blunt-notch significantly reduced the fatigue property in the high cycle and very high cycle regimes compared with that of smooth specimens. The crack initiation modes for blunt-notched specimens in the very high cycle regime can be divided into three types: (i) surface initiation, (ii) subsurface with flat facet, and (iii) subsurface with “facet + fine granular area”. The crack initiation mechanism of blunt-notched specimens is discussed in view of the interaction of notch stress gradient distribution and heterogeneous microstructure. Furthermore, the fatigue limit model based on the theory of critical distance (TCD) was modified for the very high cycle regime, and the scatter of the fatigue property of the blunt-notched specimens were well predicted by using this model.

Cavitation damage has not been well predicted because of its complex relationship of many mechanical and microstructural factors. An artificial neural network approach of the back-propagation network was used to predict cavitation damage of stainless steels, 316L and 420, in terms of the significant influence of cavitation time, roughness, and residual stress on cavitation damage. Mean depth of erosion was used to quantitatively describe cavitation damage of 316L and 420. Prediction accuracy was improved by analyzing the effects of the number and type of input nodes, the number of nodes in the hidden layer, and different activation functions on prediction accuracy. The best performance was in the model with the input nodes of cavitation time and roughness, eleven nodes in the hidden layer, and the activation function of logsig.

Unmanned aerial vehicles (UAVs) can enhance data collection for ground sensing nodes (SNs). Given the modest battery capacity of UAVs and the limited communication range of SNs, it is crucial to conceive efficient trajectory coordination for UAVs. However, existing studies simply decouple the joint trajectory planning policy of multiple UAVs into independent local policies, preventing their cooperation and hence limits the performance. Inspired by the observation that sharing messages among agents can promote their cooperation, we investigate the communication-assisted decentralized trajectory planning policy of multi-UAV wireless networks. Our goal is to minimize the overall energy consumption of UAVs and the average age of information of all SNs. To harness the encoded messages for learning a sophisticated policy, we conceive a communication-assisted distributed training and execution framework, and propose a communication-aided decentralized trajectory control algorithm. Our simulation results show that the proposed algorithm substantially outperforms the state-of-the-art deep reinforcement learning based methods, at a modest communication overhead.