State of health (SOH) monitoring and remaining useful life (RUL) prediction are the key to ensuring the safe use of lithium-ion batteries. However, the commonly used models are inefficient in predicting accuracy and do not have the ability to capture local regeneration of battery cells. In this paper, a temporal convolutional network (TCN) based SOH monitoring model framework of lithium-ion batteries is proposed. Causal convolution and dilated convolution techniques are used in the model to improve the ability of the model to capture local capacity regeneration, thus improving the overall prediction accuracy of the model. Residual connection and dropout technologies are used to improve the training speed of the model and avoid overfitting in deep network. The empirical mode decomposition (EMD) technology is used to denoise the offline data in RUL prediction, so as to avoid RUL prediction errors caused by local regeneration. The proposed model is verified on two kinds of datasets and the results show that it has the ability to capture local regeneration phenomena in Lithium-ion batteries. Compared with the commonly used models, it has higher accuracy and stronger robustness in SOH monitoring and RUL prediction.INDEX TERMS Lithium-ion battery, state of health, remaining useful life, local capacity regeneration, temporal convolutional network.

Vascular remodeling plays a key role in neural regeneration in the injured brain. Circulating endothelial progenitor cells (EPCs) are a mediator of the vascular remodeling process. Previous studies have found that progesterone treatment of traumatic brain injury (TBI) decreases cerebral edema and cellular apoptosis and inhibits inflammation, which in concert promote neuroprotective effects in young adult rats. However, whether progesterone treatment regulates circulating EPC level and fosters vascular remodeling after TBI have not been investigated. In this study, we hypothesize that progesterone treatment following TBI increases circulating EPC levels and promotes vascular remodeling in the injured brain in aged rats. Male Wistar 20-month-old rats were subjected to a moderate unilateral parietal cortical contusion injury and were treated with or without progesterone (n = 54/group). Progesterone was administered intraperitoneally at a dose of 16mg/kg at 1 h post-TBI and was subsequently injected subcutaneously daily for 14 days. Neurological functional tests and immnunostaining were performed. Circulating EPCs were measured by flow cytometry. Progesterone treatment significantly improved neurological outcome after TBI measured by the modified neurological severity score, Morris Water Maze and the long term potentiation in the hippocampus as well as increased the circulating EPC levels compared to TBI controls ( p < 0.05). Progesterone treatment also significantly increased CD34 and CD31 positive cell number and vessel density in the injured brain compared to TBI controls ( p < 0.05). These data indicate that progesterone treatment of TBI improves multiple neurological functional outcomes, increases the circulating EPC level, and facilitates vascular remodeling in the injured brain after TBI in aged rats.