Accuracy comparison and improvement for state of health estimation of lithium-ion battery based on random partial recharges and feature engineering

State of health(SOH)estimation of e-mobilities operated in real and dynamic conditions is essential and challenging.Most of existing estimations are based on a fixed constant current charging and discharging aging profiles,which overlooked the fact that the charging and discharging profiles are random and not complete in real application.This work investigates the influence of feature engineering on the accuracy of different machine learning(ML)-based SOH estimations acting on different recharging sub-profiles where a realistic battery mission profile is considered.Fifteen features were extracted from the battery partial recharging profiles,considering different factors such as starting voltage values,charge amount,and charging sliding windows.Then,features were selected based on a feature selection pipeline consisting of filtering and supervised ML-based subset selection.Multiple linear regression(MLR),Gaussian process regression(GPR),and support vector regression(SVR)were applied to estimate SOH,and root mean square error(RMSE)was used to evaluate and compare the estimation performance.The results showed that the feature selection pipeline can improve SOH estimation accuracy by 55.05%,2.57%,and 2.82%for MLR,GPR and SVR respectively.It was demonstrated that the estimation based on partial charging profiles with lower starting voltage,large charge,and large sliding window size is more likely to achieve higher accuracy.This work hopes to give some insights into the supervised ML-based feature engineering acting on random partial recharges on SOH estimation performance and tries to fill the gap of effective SOH estimation between theoretical study and real dynamic application.

The development of machine learning-based remaining useful life prediction for lithium-ion batteries

Lithium-ion batteries are the most widely used energy storage devices,for which the accurate prediction of the remaining useful life(RUL)is crucial to their reliable operation and accident prevention.This work thoroughly investigates the developmental trend of RUL prediction with machine learning(ML)algorithms based on the objective screening and statistics of related papers over the past decade to analyze the research core and find future improvement directions.The possibility of extending lithium-ion battery lifetime using RUL prediction results is also explored in this paper.The ten most used ML algorithms for RUL prediction are first identified in 380 relevant papers.Then the general flow of RUL prediction and an in-depth introduction to the four most used signal pre-processing techniques in RUL prediction are presented.The research core of common ML algorithms is given first time in a uniform format in chronological order.The algorithms are also compared from aspects of accuracy and characteristics comprehensively,and the novel and general improvement directions or opportunities including improvement in early prediction,local regeneration modeling,physical information fusion,generalized transfer learning,and hardware implementation are further outlooked.Finally,the methods of battery lifetime extension are summarized,and the feasibility of using RUL as an indicator for extending battery lifetime is outlooked.Battery lifetime can be extended by optimizing the charging profile serval times according to the accurate RUL prediction results online in the future.This paper aims to give inspiration to the future improvement of ML algorithms in battery RUL prediction and lifetime extension strategy.

Sorption equilibrium moisture and isosteric heat of Chinese wheat bran products added to rice to increase its dietary fibre content

More and more people concern about supplementing dietary food with wheat bran to increase fibre content,but there has been little study of the sorption isotherms and isosteric heats of wheat bran fibre products,which are important to the quality and storage durability of such commodities.This study collected equilibrium moisture content(EMC)and equilibrium relative humidity(ERH)data on six Chinese wheat bran products via the static gravimetric method and analysed their sorption isosteric heats.Results showed that all six wheat bran products had sigmoidal isotherms.The data were best fitted by polynomial,modified GAB,modified Oswin,and modified Halsey models.The relative safe moisture contents of the six wheat bran products were 12.20%–13.86%wet basis(w.b.).The heat of vaporization of wheat bran products approached the latent heat of pure water at around a moisture content(MC)of 22.5%and approximately 2450 kJ/kg.A process of extrusion and ultrafine grinding reduced the solid surface area and sorption isosteric heats of the monolayer,multilayer and condensed water regions in the wheat bran products.In the temperature range of 10–37℃,the EMC of sorption in monolayer,multilayer and condensed water regions decreased with increasing temperature.The milled rice to which 1%–3%200-mesh wheat bran product was added maintained its texture when made into cooked rice and its thermomechanical properties when made into rice dough.After processing by extrusion and ultrafine grinding,wheat bran products have a lower solid surface area and lower monolayer water content(Mm)and sorption isosteric heat values.Some 3%200-mesh wheat bran product can be added to cooked rice for increasing its fibre content and making it more nutritious.

Data-driven diagnosis of high temperature PEM fuel cells based on the electrochemical impedance spectroscopy: Robustness improvement and evaluation

Utilizing machine learning techniques for data-driven diagnosis of high temperature PEM fuel cells is beneficial and meaningful to the system durability. Nevertheless, ensuring the robustness of diagnosis remains a critical and challenging task in real application. To enhance the robustness of diagnosis and achieve a more thorough evaluation of diagnostic performance, a robust diagnostic procedure based on electrochemical impedance spectroscopy (EIS) and a new method for evaluation of the diagnosis robustness was proposed and investigated in this work. To improve the diagnosis robustness: (1) the degradation mechanism of different faults in the high temperature PEM fuel cell was first analyzed via the distribution of relaxation time of EIS to determine the equivalent circuit model (ECM) with better interpretability, simplicity and accuracy;(2) the feature extraction was implemented on the identified parameters of the ECM and extra attention was paid to distinguishing between the long-term normal degradation and other faults;(3) a Siamese Network was adopted to get features with higher robustness in a new embedding. The diagnosis was conducted using 6 classic classification algorithms—support vector machine (SVM), K-nearest neighbor (KNN), logistic regression (LR), decision tree (DT), random forest (RF), and Naive Bayes employing a dataset comprising a total of 1935 collected EIS. To evaluate the robustness of trained models: (1) different levels of errors were added to the features for performance evaluation;(2) a robustness coefficient (Roubust_C) was defined for a quantified and explicit evaluation of the diagnosis robustness. The diagnostic models employing the proposed feature extraction method can not only achieve the higher performance of around 100% but also higher robustness for diagnosis models. Despite the initial performance being similar, the KNN demonstrated a superior robustness after feature selection and re-embedding by triplet-loss method, which suggests the necessity of robustness evaluation for the machine learning models and the effectiveness of the defined robustness coefficient. This work hopes to give new insights to the robust diagnosis of high temperature PEM fuel cells and more comprehensive performance evaluation of the data-driven method for diagnostic application.

一种新型公猪信息素对无初情期记录的大龄后备母猪发情的影响实证

为了研究新型公猪信息素对大龄后备母猪发情的影响,选取526头255日龄左右无初情期记录的二元回交后备母猪,随机分为2组,试验组每天在鼻镜上喷新型公猪信息素4 mL,连喷21 d,21 d后还不发情的猪则并栏7 d应激,每天喷1次新型公猪信息素,每次4 mL;期间有发情表现的猪即可停止喷洒。对照组在相同条件下仅仅依靠人工查情,期间只要出现发情并且符合配种条件即可配种。分别统计每组的发情率,刺激-发情间隔。结果发现,在无初情期记录的大龄后备母猪.上每天喷4 mL新型公猪信息素,可显著提升后备母猪的发情比例(P<0.01),缩短刺激-发情的间隔(P<0.01)。由此得出,对大龄后备母猪使用新型公猪信息素28 d,可有效提升其发情率,缩短刺激-发情间隔。

Multiplexed intracellular detection based on dual-excitation/dualemission upconversion nanoprobes

Multiplexed intracellular detection is desirable in biomedical sciences for its higher eficiency and accuracy compared to the single-analyte detection.However,it is very challenging to construct nanoprobes that possess multiple fluorescent signals to recognize the different intracellular species synchronously.Herein,we proposed a novel dual-excitation/dual-emission upconversion strategy for multiplexed detection through the design of upconversion nanoparticles(UCNP)loaded with two dyes for sensitization and quenching of the upconversion luminescence(UCL),respectively.Based on the two independent energy transfer processes of near-infrared(NIR)dye IR845 to UCNP and UCNP to visible dye PAPS-Zn,CIO-and Zn2+were simultaneously detected with a limit of detection(LOD)of41.4 and 10.5 nM,respectively.By tilizing a purpose built 830/980 nm dual-laser confocal microscope,both intrinsic and exogenous CIO and Zn2+in live MCF-7 cells have been accurately quantified.Such dual-excitation/dual-emission ratiometric UCL detection mode enables not only monitoring multiple intracellular analytes but also eliminating the detection deviation caused by inhomogeneous probe distribution in cells.Through modulation of NIR dye and visible dye with other reactive groups,the nanoprobes can be extended to analyze various intraellular species,which provides a promising tool to study the biological activities in live cells and diagnose diseases.

A facile ＂ship-in-a-bottle＂ approach to construct nanorattles based on upconverting lanthanide-doped fluorides

Rattle structure is a topic of great interest in design and application of nano- materials due to the unique core@void@shell architecture and the integration of functions. Herein, we developed a novel ＂ship-in-a-bottle＂ method to fabricate upconverting （UC） luminescent nanorattles by incorporating lanthanide-doped fluorides into hollow mesoporous silica. The size of nanorattles and the filling amount of fluorides can be well controlled. In addition, the modification of silica shell （with phenylene and amine groups） and the variation of efficient UC fluorides （NaYF4：Yb, Er, NaLuF4：Yb, Er, NaGdF4：Yb, Er and LiYF4：Yb, Er） were readily achieved. The resulting nanorattles exhibited a high capacity and pH-dependent release of the anti-cancer drug doxorubicin （DOX）. Furthermore, we employed these nanorattles in proof-of-concept UC-monitoring drug release by utilizing the energy transfer process from UC fluorides to DOX, thus revealing the great potential of the nanorattles as efficient cancer theranostic agent.

Characterization of Kiwifruit Xyloglucan

Structural characteristics of xyloglucan are constant in the pericarp cell walls of kiwifruit （Actinidia deliciosa） throughout fruit enlargement and maturation. Most of the xyioglucan （XG） persists in the cell walls of ripe kiwifruit. XG from the pericarp tissues of 36-h ethylene-treated kiwifruit was extracted as hemicellulose Ⅱ （HC-Ⅱ） with 4.28 M KOH containing 0.02% NaBH4, and purified using iodine precipitation and subsequent anion-exchange chromatography. This purifying protocol increased XG purity from 50 mol% in HC-Ⅱ fraction to 62 mol% in the purified XG powder. The molar ratio of glucose： xylose： galactose： fucose in the purified XG was 10： 6.9： 2.1： 0.3. Gel permeation chromatography indicated that purified XG had an average molecular-mass of 161 KDa, a value that exceeds the 95 KDa Mr determined for total polymeric sugars. Sugar linkage analysis confirmed the lack of fucose in the kiwifruit XG, but a small amount of arabinoxylan and low Mr glucomannan remained associated with this fraction.

Modulator-directed assembly of hybrid composites based on metalorganic frameworks and upconversion nanoparticles

Hybrid composites made of metal-organic frameworks(MOFs)and lanthanide-doped upconversion nanoparticles(UCNPs)have attracted considerable interest for their synergistically enhanced functions in various applications such as chemical sensing,photocatalysis,anticounterfeiting and nanomedicine.However,precise assembly of MOF/UCNP hybrid composites with tunable morphologies remains a challenge due to the lack of effective synthetic methods and fundamental understanding of the growth mechanisms.Herein,we propose a modulator-directed assembly strategy to synthesize a series of ZIF-8@UCNP composites(ZIF-8=zeolitic imidazolate framework-8).The UCNPs densely paved on the surface of ZIF-8 microcrystals and endowed the composites with intense upconversion blue emission,which were verified by steady-state/transient photoluminescence(PL)spectroscopy and single-particle imaging.Ethylenediamine(EDA)was firstly used as a modulator to fine-tune the predominant MOF facets and realized distinct morphologies of the composites.By adjusting the concentration of EDA from 0 to 25 mmol/L,the morphology of the ZIF-8@UCNP composites was tuned from rhombic dodecahedron(RD)to truncated rhombic dodecahedron(TRD),cube with truncated edges(CTE),cube,and finally a unique form of interpenetration twins(IT).The nucleation and growth process of the ZIF-8@UCNP composites was monitored by time-dependent scanning electron microscopy(SEM)images and the formation mechanism was thoroughly revealed.Furthermore,we demonstrated that the strategy for assembly of morphology-controllable ZIF-8@UCNP composites was generally applicable to various UCNPs with different sizes and shapes.The proposed strategy is expected to open up new avenues for the controllable synthesis of MOF/UCNP composites toward diverse applications.

A rare case of visceral leishmaniasis misdiagnosed as systemic lupus erythematosus

Visceral leishmaniasis(VL)is an infectious disease caused by Leishmania donovani and transmitted by sandflies.It can be life-threatening if not treated.Common clinical features of VL include recurrent fever,pancytopenia,splenomegaly,and a variety of positive autoantibodies,which can lead to a misdiagnosis of systemic lupus erythematosus(SLE).We report the case of a 25-year-old woman with VL misdiagnosed as SLE to add to the existing literature on this subject.

Luminescent nano-bioprobes based on NIR dye/lanthanide nanoparticle composites

Near-infrared(NIR)light,which has ignorable tissue scattering/absorption,minimal photodamage,and no autofluorescence interference,is highly favorable for bioapplications.NIR dye and lanthanide-doped nanoparticle(LnNP),as representative NIR-excited luminescence probes,have attracted increasing interest due to their unique optical property and low biological toxicity.Design of luminescence probes based on NIR dye/LnNP nanocomposites cannot only integrate the advantages but also achieve additional functions via regulating internal energy transfer pathways.In this review,we focus on the most recent advances in the development of NIR dye/LnNP nanocomposites as potential bioprobes,which cover from their fundamental photophysics to bioapplications,including energy transfer mechanisms,interface engineering(involving binding interaction,distance,and aggregation as key factors),and their applications for dye-sensitized upconversion/downshifting luminescent bioimaging,detection of biomolecules,and NIR-triggered diagnosis and therapy.Some future prospects and efforts toward this active research field are also envisioned.