The inverse problem of electrical resistivity surveys (ERS) is difficult because of its nonlinear and ill-posed nature. For this task, traditional linear inversion methods still face challenges such as sub-optimal approximation and initial model selection. Inspired by the remarkable non-linear mapping ability of deep learning approaches, in this paper we propose to build the mapping from apparent resistivity data (input) to resistivity model (output) directly by convolutional neural networks (CNNs). However, the vertically varying characteristic of patterns in the apparent resistivity data may cause ambiguity when using CNNs with the weight sharing and effective receptive field properties. To address the potential issue, we supply an additional tier feature map to CNNs to help it get aware of the relationship between input and output. Based on the prevalent U-Net architecture, we design our network (ERSInvNet) which can be trained endto-end and reach real-time inference during testing. We further introduce depth weighting function and smooth constraint into loss function to improve inversion accuracy for the deep region and suppress false anomalies. Four groups of experiments are considered to demonstrate the feasibility and efficiency of the proposed methods. According to the comprehensive qualitative analysis and quantitative comparison, ERSInvNet with tier feature map, smooth constraints and depth weighting function together achieve the best performance.
In response to the potential environment pollution and energy waste caused by the increasing spent lithium iron phosphate batteries (LFPs), many recycling methods have been developed. Among previous studies, the physical recycling method has attracted numerous attention due to its uncomplicated process and high efficiency. This work provides a regeneration mechanism of that the organic carbon layer is in situ coated on the surface of LiFePO 4 particles by the decomposition of binder so that improves the conductivity and rate capability. When serving as cathode material for lithium ion battery, the 3 h-regenerated lithium iron phosphate battery delivers an excellent electrochemical performance which shows a discharge specific capacity of 151.55 mAh g −1 at 0.2C and delivers a discharge capacity of 120.44 mAh g −1 even at 10C compared with pristine spent LFPs. It delivers a discharge capacity of 124.35 mAh g −1 in first cycle and maintains 103.12 mAh g −1 with a high capacity retention rate of 82.93% after 2000 cycles at 0.5C through 18,650 battery testing. Meaningfully, a facile and sustainable regeneration process has been demonstrated to re-synthesize LiFePO 4 from spent LFPs by our study which can be reused as cathode materials for lithium-ion batteries, indicating an economical and facile method to recycle spent LiFePO 4 materials in large scale.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.