The electrochemo‐mechanical effects on the structural integrity of electrode materials during cycling is a non‐negligible factor that affects the cyclability and rate performance of all solid‐state batteries (ASSBs). Herein, combined with in situ electrochemical impedance spectroscopy (EIS), focused ion beam (FIB)–scanning electron microscope (SEM), and solid state nuclear magnetic resonance (ssNMR) techniques, the electrochemical performance and electrochemo‐mechanical behavior are compared of conventional polycrystalline NCM811 (LiNi0.8Co0.1Mn0.1O2), small‐size polycrystalline NCM811 and single‐crystal (S‐) NCM811 in Li10SnP2S12 based ASSBs during long charge–discharge cycles. The results show that the deteriorating performance of both large and small polycrystalline NCM811 originates from their inherent structural instability at >4.15 V, induced by the visible voids between the randomly oriented grains and microcracks due to the electrode pressing process and severe anisotropic volume change during cycling, rather than lithium ion transport in the primary particle. In contrast, S‐NCM811 with good microstructural integrity show remarkably high capacity (187 mAh g−1, 18 mA g−1), stable cyclability (100 cycles, retention of 64.5%), and exceptional rate capability (102 mAh g−1 at 180 mA g−1) in ASSBs even without surface modification. Moreover, 1 wt% LiNbO3@S‐NCM811 further demonstrates excellent initial discharge capacity and capacity retention. This work highlights the critical role of electrochemo‐mechanical integrity and offers an promising path towards mechanically‐reliable cathode materials for ASSBs.

No abstract

With the popularity of using deep learning-based models in various categorization problems and their proven robustness compared to conventional methods, a growing number of researchers have exploited such methods in environment sound classification tasks in recent years. However, the performances of existing models use auditory features like log-mel spectrogram (LM) and mel frequency cepstral coefficient (MFCC), or raw waveform to train deep neural networks for environment sound classification (ESC) are unsatisfactory. In this paper, we first propose two combined features to give a more comprehensive representation of environment sounds Then, a fourfour-layer convolutional neural network (CNN) is presented to improve the performance of ESC with the proposed aggregated features. Finally, the CNN trained with different features are fused using the Dempster–Shafer evidence theory to compose TSCNN-DS model. The experiment results indicate that our combined features with the four-layer CNN are appropriate for environment sound taxonomic problems and dramatically outperform other conventional methods. The proposed TSCNN-DS model achieves a classification accuracy of 97.2%, which is the highest taxonomic accuracy on UrbanSound8K datasets compared to existing models.