Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Transfer Learning-based State of Charge Estimation for Lithium-Ion Battery at Varying Ambient Temperatures
50
0
0.0
(
0
)
Added by
Yan Qin
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Accurate and reliable state of charge (SoC) estimation becomes increasingly important to provide a stable and efficient environment for Lithium-ion batteries (LiBs) powered devices. Most data-driven SoC models are built for a fixed ambient temperature, which neglect the high sensitivity of LiBs to temperature and may cause severe prediction errors. Nevertheless, a systematic evaluation of the impact of temperature on SoC estimation and ways for a prompt adjustment of the estimation model to new temperatures using limited data have been hardly discussed. To solve these challenges, a novel SoC estimation method is proposed by exploiting temporal dynamics of measurements and transferring consistent estimation ability among different temperatures. First, temporal dynamics, which is presented by correlations between the past fluctuation and the future motion, is extracted using canonical variate analysis. Next, two models, including a reference SoC estimation model and an estimation ability monitoring model, are developed with temporal dynamics. The monitoring model provides a path to quantitatively evaluate the influences of temperature on SoC estimation ability. After that, once the inability of the reference SoC estimation model is detected, consistent temporal dynamics between temperatures are selected for transfer learning. Finally, the efficacy of the proposed method is verified through a benchmark. Our proposed method not only reduces prediction errors at fixed temperatures (e.g., reduced by 24.35% at -20{deg}C, 49.82% at 25{deg}C) but also improves prediction accuracies at new temperatures.
rate research
Read More
By informing accurate performance (e.g., capacity), health state management plays a significant role in safeguarding battery and its powered system. While most current approaches are primarily based on data-driven methods, lacking in-depth analysis of battery performance degradation mechanism may discount their performances. To fill in the research gap about data-driven battery performance degradation analysis, an invariant learning based method is proposed to investigate whether the battery performance degradation follows a fixed behavior. First, to unfold the hidden dynamics of cycling battery data, measurements are reconstructed in phase subspace. Next, a novel multi-stage division strategy is put forward to judge the existent of multiple degradation behaviors. Then the whole aging procedure is sequentially divided into several segments, among which cycling data with consistent degradation speed are assigned in the same stage. Simulations on a well-know benchmark verify the efficacy of the proposed multi-stages identification strategy. The proposed method not only enables insights into degradation mechanism from data perspective, but also will be helpful to related topics, such as stage of health.
Solid state battery technology has recently garnered considerable interest from companies including Toyota, BMW, Dyson, and others. The primary driver behind the commercialization of solid state batteries (SSBs) is to enable the use of lithium metal as the anode, as opposed to the currently used carbon anode, which would result in ~20% energy density improvement. However, no reported solid state battery to date meets all of the performance metrics of state of the art liquid electrolyte lithium ion batteries (LIBs) and indeed several solid state electrolyte (SSE) technologies may never reach parity with current LIBs. We begin with a review of state of the art LIBs, including their current performance characteristics, commercial trends in cost, and future possibilities. We then discuss current SSB research by focusing on three classes of solid state electrolytes: Sulfides, Polymers, and Oxides. We discuss recent and ongoing commercialization attempts in the SSB field. Finally, we conclude with our perspective and timeline for the future of commercial batteries.
Li-ion rechargeable batteries have enabled the wireless revolution transforming global communication. Future challenges, however, demands distributed energy supply at a level that is not feasible with the current energy-storage technology. New materials, capable of providing higher energy density are needed. Here we report a new class of lithium-ion batteries based on a graphene ink anode and a lithium iron phosphate cathode. By carefully balancing the cell composition and suppressing the initial irreversible capacity of the anode, we demonstrate an optimal battery performance in terms of specific capacity, i.e. 165 mAhg-1, estimated energy density of about 190 Whkg-1 and life, with a stable operation for over 80 charge-discharge cycles. We link these unique properties to the graphene nanoflake anode displaying crystalline order and high uptake of lithium at the edges, as well as to its structural and morphological optimization in relation to the overall battery composition. Our approach, compatible with any printing technologies, is cheap and scalable and opens up new opportunities for the development of high-capacity Li-ion batteries.
Reinforcement learning (RL) is well known for requiring large amounts of data in order for RL agents to learn to perform complex tasks. Recent progress in model-based RL allows agents to be much more data-efficient, as it enables them to learn behaviors of visual environments in imagination by leveraging an internal World Model of the environment. Improved sample efficiency can also be achieved by reusing knowledge from previously learned tasks, but transfer learning is still a challenging topic in RL. Parameter-based transfer learning is generally done using an all-or-nothing approach, where the networks parameters are either fully transferred or randomly initialized. In this work we present a simple alternative approach: fractional transfer learning. The idea is to transfer fractions of knowledge, opposed to discarding potentially useful knowledge as is commonly done with random initialization. Using the World Model-based Dreamer algorithm, we identify which type of components this approach is applicable to, and perform experiments in a new multi-source transfer learning setting. The results show that fractional transfer learning often leads to substantially improved performance and faster learning compared to learning from scratch and random initialization.
Upon insertion and extraction of lithium, materials important for electrochemical energy storage can undergo changes in thermal conductivity (${Lambda}$) and elastic modulus ($it M$). These changes are attributed to evolution of the intrinsic thermal carrier lifetime and interatomic bonding strength associated with structural transitions of electrode materials with varying degrees of reversibility. Using in situ time-domain thermoreflectance (TDTR) and picosecond acoustics, we systemically study $Lambda$ and $it M$ of conversion, intercalation and alloying electrode materials during cycling. The intercalation V$_{2}$O$_{5}$ and TiO$_{2}$ exhibit non-monotonic reversible ${Lambda}$ and $it M$ switching up to a factor of 1.8 (${Lambda}$) and 1.5 ($it M$) as a function of lithium content. The conversion Fe$_{2}$O$_{3}$ and NiO undergo irreversible decays in ${Lambda}$ and $it M$ upon the first lithiation. The alloying Sb shows the largest and partially reversible order of the magnitude switching in ${Lambda}$ between the delithiated (18 W m$^{-1}$ K$^{-1}$) and lithiated states (<1 W m$^{-1}$ K$^{-1}$). The irreversible ${Lambda}$ is attributed to structural degradation and pulverization resulting from substantial volume changes during cycling. These findings provide new understandings of the thermal and mechanical property evolution of electrode materials during cycling of importance for battery design, and also point to pathways for forming materials with thermally switchable properties.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
