Cracking Mechanism and Inhibition Strategies of Polycrystalline NCM Electrode Particles.

Developing a high-energy-density cathode material (LiNiCoMnO, NCM) for lithium-ion batteries is crucial to the electric vehicle and energy storage industries. However, the continuous insertion/extraction of Li generates diffusion-induced stress, causing NCM particles to crack or even pulverize, leading to battery capacity loss and limiting its wider commercial application. Current experimental studies are primarily postmortem examinations, and it is difficult to capture the particle cracking evolution.

Effective Plug-Ins for Reducing Inference-Latency of Spiking Convolutional Neural Networks During Inference Phase.

Convolutional Neural Networks (CNNs) are effective and mature in the field of classification, while Spiking Neural Networks (SNNs) are energy-saving for their sparsity of data flow and event-driven working mechanism. Previous work demonstrated that CNNs can be converted into equivalent Spiking Convolutional Neural Networks (SCNNs) without obvious accuracy loss, including different functional layers such as Convolutional (Conv), Fully Connected (FC), Avg-pooling, Max-pooling, and Batch-Normalization (BN) layers. To reduce inference-latency, existing researches mainly concentrated on the normalization of weights to increase the firing rate of neurons.