Sand nourishment is widely adopted as an effective soft approach to provide long-term coastal safety, protect the ecology environment, and promote tourism and recreation. With the increase in frequency and expenses in beach nourishment worldwide, an adequate prediction of morphology evolution is greatly desired for coastline management. Based on detailed monitoring data of the mega-nourishment Sand Engine, this article integrates a convolutional neural network (CNN) and long short-term memory (LSTM) to predict the nourishment morphology evolution. The historical surveyed data are transformed into sequence grids, which are input into the CNN to obtain the spatial features of beach nourishment. The CNN is constructed by performing the convolutional and pooling operation on the historical data, which can extract actual spatial features and reduce network complexity. The output of the CNN is input to LSTM to learn the temporal relationship to predict future nourishment terrain using past time-series features. Finally, the LSTM output is decoded by the fully connected layer to obtain the prediction result. The complex spatiotemporal correlations among the input data are identified through effective training of the proposed model. The major contribution of this article is to propose a data-driven model that combines CNN and LSTM for the morphology evolution prediction of beach nourishment, and validate the effectiveness of the proposed model by comparing with the performances of other popular methods in predicting the nourishment changes.@en

Lithium halide electrolytes with high ion conductivity and good cathode compatibility have shown great potential for solid-state batteries. Li₃YBr₆, with a conductivity of 0.39 mS/cm at room temperature, synthesized by mechanical milling (BM-Li₃YBr₆), which can be further increased by heat treatment. The annealing parameters are tailored to obtain pure Li₃YBr₆ (AN-Li₃YBr₆) with a higher conductivity of 3.31 mS/cm by annealing the BM-Li₃YBr₆ at 500 °C for 5 h. The higher conductivity of AN-Li₃YBr₆ compared to the previously-reported results is due to the lower activation energy. NMR and simulation results show that the lithium ion migration between Li-1 and Li-2 sites along the [001] direction is the major obstacle for lithium diffusion in AN-Li₃YBr₆. The K- and L₃-edge X-ray absorption near-edge structure (XANES) of Y for BM-Li₃YBr₆ and AN-Li₃YBr₆ showed that Y exists with similar local structures. The increased vibrations of AN-Li₃YBr₆ due to increased temperatures increase the rate of lithium jumping from one site to another, yielding higher lithium ion mobility. Lithium nuclear density maps prove that the mobile lithium on the 4g(Li) site is more sensitive to the varying temperatures. Both BM- and AN-Li₃YBr₆ are incompatible with Li, however, an annealing process can improve the electrochemical stability. Both the experimental and simulation results confirm the anode incompatibility between In and AN-Li₃YBr₆. To mitigate the cathode and anode incompatibility with AN-Li₃YBr₆, a LiNbO₃ coating layer and a Li_5.7PS_4.7Cl_1.3 buffer layer are introduced at the cathode side and anode side, respectively, to assemble all-solid-state batteries with improved capacity and cyclability.

@en

As the supporting unit of rotating machinery, bearing can ensure efficient operation of the equipment. Therefore, it is very important to monitor the status of bearings accurately. A bearing fault diagnosis mothed based on Multipoint Optimal Minimum Local Mean Entropy Deconvolution Adjusted (MOMLMEDA) and Long Short-Term Memory (LSTM) is proposed. MOMLMEDA is an improved algorithm based on Multipoint Optimal Minimum Entropy Deconvolution Adjusted (MOMEDA). By setting the local kurtosis mean as a new selection criterion, it can effectively avoid the interference of false kurtosis caused by noise and improve the accuracy of optimal kurtosis position. The optimal filter designed by optimal kurtosis position has periodic and amplitude characteristics, which are used as the fault feature in this paper. However, this feature has temporal characteristics and cannot be used as input of general neural network directly. LSTM is selected as the classification network in this paper. It can effectively avoid the influence of the temporal problem existing in feature vectors. Accurate diagnosis of bearing faults is realized by training classification neural network with samples. The overall recognition rate is up to 93.50%.@en

With the development of the materials genome philosophy and data mining methodologies, machine learning (ML) has been widely applied for discovering new materials in various systems including high-end steels with improved performance. Although recently, some attempts have been made to incorporate physical features in the ML process, its effects have not been demonstrated and systematically analysed nor experimentally validated with prototype alloys. To address this issue, a physical metallurgy (PM) -guided ML model was developed, wherein intermediate parameters were generated based on original inputs and PM principles, e.g., equilibrium volume fraction (V_f) and driving force (D_f) for precipitation, and these were added to the original dataset vectors as extra dimensions to participate in and guide the ML process. As a result, the ML process becomes more robust when dealing with small datasets by improving the data quality and enriching data information. Therefore, a new material design method is proposed combining PM-guided ML regression, ML classifier and a genetic algorithm (GA). The model was successfully applied to the design of advanced ultrahigh-strength stainless steels using only a small database extracted from the literature. The proposed prototype alloy with a leaner chemistry but better mechanical properties has been produced experimentally and an excellent agreement was obtained for the predicted optimal parameter settings and the final properties. In addition, the present work also clearly demonstrated that implementation of PM parameters can improve the design accuracy and efficiency by eliminating intermediate solutions not obeying PM principles in the ML process. Furthermore, various important factors influencing the generalizability of the ML model are discussed in detail.

@en

For planetary gear has the characteristics of small volume, light weight and large transmission ratio, it is widely used in high speed and high power mechanical system. Poor working conditions result in frequent failures of planetary gear. A method is proposed for diagnosing faults in planetary gear based on permutation entropy of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) Adaptive Neuro-fuzzy Inference System (ANFIS) in this paper. The original signal is decomposed into 6 intrinsic mode functions (IMF) and residual components by CEEMDAN. Since the IMF contains the main characteristic information of planetary gear faults, time complexity of IMFs are reflected by permutation entropies to quantify the fault features. The permutation entropies of each IMF component are defined as the input of ANFIS, and its parameters and membership functions are adaptively adjusted according to training samples. Finally, the fuzzy inference rules are determined, and the optimal ANFIS is obtained. The overall recognition rate of the test sample used for ANFIS is 90%, and the recognition rate of gear with one missing tooth is relatively high. The recognition rates of different fault gears based on the method can also achieve better results. Therefore, the proposed method can be applied to planetary gear fault diagnosis effectively.@en