Robust state of charge estimation of lithium-ion battery via mixture kernel mean p-power error loss LSTM with heap-based-optimizer

The state of charge(SOC)estimation of lithium-ion battery is an important function in the battery management system(BMS)of electric vehicles.The long short term memory(LSTM)model can be employed for SOC estimation,which is capable of estimating the future changing states of a nonlinear system.Since the BMS usually works under complicated operating conditions,i.e the real measurement data used for model training may be corrupted by non-Gaussian noise,and thus the performance of the original LSTM with the mean square error(MSE)loss may deteriorate.Therefore,a novel LSTM with mixture kernel mean p-power error(MKMPE)loss,called MKMPE-LSTM,is developed by using the MKMPE loss to replace the MSE as the learning criterion in LSTM framework,which can achieve robust SOC estimation under the measurement data contaminated with non-Gaussian noises(or outliers)because of the MKMPE containing the p-order moments of the error distribution.In addition,a meta-heuristic algorithm,called heap-based-optimizer(HBO),is employed to optimize the hyper-parameters(mainly including learning rate,number of hidden layer neuron and value of p in MKMPE)of the proposed MKMPE-LSTM model to further improve its flexibility and generalization performance,and a novel hybrid model(HBO-MKMPE-LSTM)is established for SOC estimation under non-Gaussian noise cases.Finally,several tests are performed under various cases through a benchmark to evaluate the performance of the proposed HBO-MKMPE-LSTM model,and the results demonstrate that the proposed hybrid method can provide a good robustness and accuracy under different non-Gaussian measurement noises,and the SOC estimation results in terms of mean square error(MSE),root MSE(RMSE),mean absolute relative error(MARE),and determination coefficient R2are less than 0.05%,3%,3%,and above 99.8%at 25℃,respectively.

Lithospheric structure and geodynamics at the northern margin of Tibetan plateau

A recent integrated geophysical survey has been completed along a transect from Baicheng, Xinjiang to Da Qaidam, Qinghai, China. In this study, wide-angle seismic reflection/refraction exploration with 10 shot points has been carried out to acquire the velocity structure of the crust and uppermost mantle. The earthquake focal mechanism solutions and terrestrial heat flow along the transect have also been obtained and analyzed. Based on the velocity structure of the crust and uppermost mantle along the transect, and combined with the focal mechanism solutions and terrestrial heat flow we develop a geodynamic model for the northern margin of the Tibetan plateau. This model reveals the detailed structure of the crust and uppermost mantle, determines the relationship of basin and range coupling, explores the deep dynamic setting for superposed basins, and establishes the northern boundary condition for Tibetan plateau research.

Adaptive Median Filtering Algorithm Based on Divide and Conquer and Its Application in CAPTCHA Recognition

As the first barrier to protect cyberspace,the CAPTCHA has made significant contributions to maintaining Internet security and preventing malicious attacks.By researching the CAPTCHA,we can find its vulnerability and improve the security of CAPTCHA.Recently,many studies have shown that improving the image preprocessing effect of the CAPTCHA,which can achieve a better recognition rate by the state-of-theart machine learning algorithms.There are many kinds of noise and distortion in the CAPTCHA images of this experiment.We propose an adaptive median filtering algorithm based on divide and conquer in this paper.Firstly,the filtering window data quickly sorted by the data correlation,which can greatly improve the filtering efficiency.Secondly,the size of the filtering window is adaptively adjusted according to the noise density.As demonstrated in the experimental results,the proposed scheme can achieve superior performance compared with the conventional median filter.The algorithm can not only effectively detect the noise and remove it,but also has a good effect in preservation details.Therefore,this algorithm can be one of the most strong tools for various CAPTCHA image recognition and related applications.

Roughness correction method for salinity remote sensing using combined active/passive observations

Roughness-induced emission from ocean surfaces is one of the main issues that affects the retrieval accuracy of sea surface salinity remote sensing.In previous studies,the correction of roughness effect mainly depended on wind speeds retrieved from scatterometers or those provided by other means,which necessitates a high requirement for accuracy and synchronicity of wind-speed measurements.The aim of this study is to develop a novel roughness correction model of ocean emissivity for the salinity retrieval application.The combined active/passive observations of normalized radar cross-sections(NRCSs)and emissivities from ocean surfaces given by the L-band Aquarius/SAC-D mission,and the auxiliary wind directions collocated from the National Centers for Environmental Prediction(NCEP)dataset are used for model development.The model is validated against the observations and the Aquarius standard algorithms of roughness-induced emissivity correction.Comparisons between model computations and measurements indicate that the model has better accuracy in computing wind-induced brightness temperature in the upwind/downwind directions or for the surfaces with smaller NRCSs,which can be better than 0.3 K.However,for crosswind directions and larger NRCSs,the model accuracy is relatively low.A model using HH-polarized NRCSs yields better accuracy than that using VV-polarized ones.For a fair comparison to the Aquarius standard algorithms using wind speeds retrieved from multi-source data,the maximum likelihood estimation is employed to produce results combining our model calculations and those using other sources.Numerical simulations show that combined results basically have higher accuracy than the standard algorithms.

Snap-through path in a bistable dielectric elastomer actuator

The dielectric elastomer(DE)has attracted significant attention due to its desired features,including large deformation,fast response,and high energy density.However,for a DE actuator(DEA)utilizing a snap-through deformation mode,most existing theoretical models fail to predict its deformation path.This paper develops a new finite element method(FEM)based on the three-parameter Gent-Gent model suitable for capturing strain-stiffening behaviors.The simulation results are verified by experiments,indicating that the FEM can accurately characterize the snap-through path of a DE.The method proposed in this paper provides theoretical guidance and inspiration for designing and applying DEs and bistable electroactive actuators.

A Meshless Collocation Method with Barycentric Lagrange Interpolation for Solving the Helmholtz Equation

In this paper,Chebyshev interpolation nodes and barycentric Lagrange interpolation basis function are used to deduce the scheme for solving the Helmholtz equation.First of all,the interpolation basis function is applied to treat the spatial variables and their partial derivatives,and the collocation method for solving the second order differential equations is established.Secondly,the differential matrix is used to simplify the given differential equations on a given test node.Finally,based on three kinds of test nodes,numerical experiments show that the present scheme can not only calculate the high wave numbers problems,but also calculate the variable wave numbers problems.In addition,the algorithm has the advantages of high calculation accuracy,good numerical stability and less time consuming.

Reliability Analysis of Repairable System with Multiple Closed-Loop Feedbacks Based on GO Method

In order to solve the problem of reliability modeling and the analysis of complex systems with multiple closed-loop feedbacks,a new reliability analysis method for repairable systems with multiple closed-loop feedbacks is proposed based on the goal-oriented(GO)methodology.Firstly,the basic theories and advantages of GO method are introduced.Secondly,a type-24B multiple closed-loop feedback structure operator is proposed through GO method with its operation formula given,which expands the types of GO method operators and the application scope of their reliability analysis.Finally,taking a certain type of diesel engine fuel supply system an example,the quantitative and qualitative analysis is carried out through GO method,Monte Carlo simulation as well as FTA respectively.The availability results verify the availability of the proposed type-24B operator in the reliability analysis of multiple closed-loop feedback systems.The qualitative analysis results indicate the accuracy and usability of the GO method as a qualitative analysis method.

中新世气候适宜期构造运动加速全球海洋碳循环

Global warming during the Miocene Climate Optimum(MCO,~17-14 million years ago)is associated with massive carbon emissions sourced from the flood basalt volcanism and ocean crustal production.However,the perturbation of tectonic carbon degassing on the interaction between climate change and carbon cycle remains unclear.Here,through time-evolutive phase analysis of new and published high-resolution benthic foraminiferal oxygen(δ^(18)O)and carbon(δ^(13)C)isotope records from the global ocean,we find that variations in the marine carbon cycle lead the climate-cryosphere system(δ^(13)Clead-δ^(18)O)on 405,000-year eccentricity timescales during the MCO.This is in contrast to the previously reported climate-lead-carbon(δ^(18)O-lead-δ^(13)C)scenario during most of the Oligo-Miocene(~34-6 million years ago).Further sensitivity analysis and model simulations suggest that the elevated atmospheric CO_(2) concentrations and the resulting greenhouse effect strengthened the low-latitude hydrological cycle during the MCO,accelerating the response of marine carbon cycle to eccentricity forcing.Tropical climate processes played a more important role in regulating carbon-cycle variations when Earth's climate was in a warm regime,as opposed to the dominant influence of polar ice-sheet dynamics during the PlioPleistocene(after~6 million years ago).

肿瘤微环境中的定量工程生物学

定量工程生物学在定量刻画肿瘤微环境方面起到了重要的作用,也推动了肿瘤免疫疗法的机制研究.然而在肿瘤免疫治疗的临床应用中,大部分病人对免疫治疗无响应.因此,免疫治疗的响应机制是研究肿瘤免疫疗法的重点和难点.其中,肿瘤微环境被认为是该研究领域的重要突破口之一.针对肿瘤微环境的定量测量与定量数据分析对肿瘤免疫疗法的机制研究产生积极而深远的影响.例如:利用定量生物学手段解析肿瘤微环境中的细胞种类、基因和蛋白的表达、各种细胞的空间位置、物理和化学因素、细胞外基质等,并建立这些因素与肿瘤免疫疗法效果之间的定量关系;运用工程生物学手段开发嵌合抗原受体T细胞、T细胞受体工程T细胞、树突状细胞疫苗等免疫疗法.本文将主要介绍定量测量方法在肿瘤微环境前沿研究领域内的应用,以及工程生物学在肿瘤的细胞免疫治疗中改造肿瘤微环境的应用.

Production of dissolved organic carbon in the South China Sea:A modeling study

The South China Sea(SCS)is the largest semi-enclosed marginal sea in the western Pacific.The alternation of East Asian monsoon causes a significant seasonal pattern of chlorophyll,primary productivity,and export flux of sinking particles.However,the source and sink of dissolved organic carbon(DOC)pools with different bioavailability are less studied.Here we evaluated the seasonal production of DOC in labile,semi-labile and refractory forms using a coupled physical-biogeochemical model.This study aims to understand the dynamics and budgets of organic matters in the SCS.Model results show that the production of labile,semi-labile and refractory DOC is highly correlated with the net primary productivity(NPP)which is higher in winter and lower in summer,reflecting a dependence of DOC on the NPP.The seasonal variation in Pearl River discharge dominates the DOC production in the northern coastal region.In the northeast,the Kuroshio intrusion associated frontal system is attributed to cause high winter production.The DOC production in the southwest is controlled by both winter mixing and summer upwelling.The production of refractory DOC with the least bioavailability favors carbon sequestration.Its annual mean production is 1.8±0.5 mg C m^(−2) d^(−1),equivalent to 26%of the export flux of particulate organic carbon at 1000 m.