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.

Acceptability of Immunization against COVID-19 by the Populations of the Kasenga State Health Area in the Uvira Health Zone, DR Congo

Introduction: COVID-19 was an emerging disease putting all public health systems in countries around the world in a state of emergency. To be able to prevent its spread and morbidity and mortality, several appropriate strategies were necessary, such as vaccination. The latter has been the subject of controversy. The objective of the present study is therefore to evaluate the factors associated with the acceptance of this vaccine within the population of the Kasenga State Health Area. A result which will shed light on future strategies to be put in place for possible new vaccines. Methodology: Is a prospective and analytical cross-sectional study conducted over a period of approximately 1 month from January 5 to February 5, 2024. A survey questionnaire in Kobotoolbox was useful for collecting data. STATA software was very important for us in analyzing the data collected. Results: Prevalence of vaccination against COVID-19 among the population of the Kasenga State Health Area is 37.5% (28.4 - 45.6). The study revealed that reluctance is observed among most of the population for different reasons, including, first and foremost, the deliberate aspect of not wanting to take the vaccine (46.6%) and rumors that this antigen is dangerous and harmful (32.9%). 72.5% of respondents believe that the COVID-19 vaccine is a fabrication, unhealthy and that the disease itself never existed. The study proved that there was a statistical relationship between age (p = 0.001) and adherence to vaccination. And the refusal of respondents to recommend the vaccine to loved ones was a factor associated with non-adherence to vaccination (OR = 7.901, 95% IC [3.028 - 20.615], p = 0.000). Conclusion: Vaccination against COVID-19 was not well accepted by the population of the study site. Raising public awareness and involving community leaders and political-administrative authorities, which has not been done well, would play an important role in the good perception of the disease, of the vaccine and therefore in its adherence.

End-cloud collaboration method enables accurate state of health and remaining useful life online estimation in lithium-ion batteries

Though the lithium-ion battery is universally applied,the reliability of lithium-ion batteries remains a challenge due to various physicochemical reactions,electrode material degradation,and even thermal runaway.Accurate estimation and prediction of battery health conditions are crucial for battery safety management.In this paper,an end-cloud collaboration method is proposed to approach the track of battery degradation process,integrating end-side empirical model with cloud-side data-driven model.Based on ensemble learning methods,the data-driven model is constructed by three base models to obtain cloud-side highly accurate results.The double exponential decay model is utilized as an empirical model to output highly real-time prediction results.With Kalman filter,the prediction results of end-side empirical model can be periodically updated by highly accurate results of cloud-side data-driven model to obtain highly accurate and real-time results.Subsequently,the whole framework can give an accurate prediction and tracking of battery degradation,with the mean absolute error maintained below 2%.And the execution time on the end side can reach 261μs.The proposed end-cloud collaboration method has the potential to approach highly accurate and highly real-time estimation for battery health conditions during battery full life cycle in architecture of cyber hierarchy and interactional network.

Estimation of state of health based on charging characteristics and back-propagation neural networks with improved atom search optimization algorithm

With the rapid development of new energy technologies, lithium batteries are widely used in the field of energy storage systems and electric vehicles. The accurate prediction for the state of health(SOH) has an important role in maintaining a safe and stable operation of lithium-ion batteries. To address the problems of uncertain battery discharge conditions and low SOH estimation accuracy in practical applications, this paper proposes a SOH estimation method based on constant-current battery charging section characteristics with a back-propagation neural network with an improved atom search optimization algorithm. A temperature characteristic, equal-time temperature variation(Dt_DT), is proposed by analyzing the temperature data of the battery charging section with the incremental capacity(IC) characteristics obtained from an IC analysis as an input to the data-driven prediction model. Testing and analysis of the proposed prediction model are carried out using publicly available datasets. Experimental results show that the maximum error of SOH estimation results for the proposed method in this paper is below 1.5%.

A Health State Prediction Model Based on Belief Rule Base and LSTM for Complex Systems

In industrial production and engineering operations,the health state of complex systems is critical,and predicting it can ensure normal operation.Complex systems have many monitoring indicators,complex coupling structures,non-linear and time-varying characteristics,so it is a challenge to establish a reliable prediction model.The belief rule base(BRB)can fuse observed data and expert knowledge to establish a nonlinear relationship between input and output and has well modeling capabilities.Since each indicator of the complex system can reflect the health state to some extent,the BRB is built based on the causal relationship between system indicators and the health state to achieve the prediction.A health state prediction model based on BRB and long short term memory for complex systems is proposed in this paper.Firstly,the LSTMis introduced to predict the trend of the indicators in the system.Secondly,the Density Peak Clustering(DPC)algorithmis used todetermine referential values of indicators for BRB,which effectively offset the lack of expert knowledge.Then,the predicted values and expert knowledge are fused to construct BRB to predict the health state of the systems by inference.Finally,the effectiveness of the model is verified by a case study of a certain vehicle hydraulic pump.

Estimating the State of Health for Lithium-ion Batteries:A Particle Swarm Optimization-Assisted Deep Domain Adaptation Approach

The state of health(SOH)is a critical factor in evaluating the performance of the lithium-ion batteries(LIBs).Due to various end-user behaviors,the LIBs exhibit different degradation modes,which makes it challenging to estimate the SOHs in a personalized way.In this article,we present a novel particle swarm optimization-assisted deep domain adaptation(PSO-DDA)method to estimate the SOH of LIBs in a personalized manner,where a new domain adaptation strategy is put forward to reduce cross-domain distribution discrepancy.The standard PSO algorithm is exploited to automatically adjust the chosen hyperparameters of developed DDA-based method.The proposed PSODDA method is validated by extensive experiments on two LIB datasets with different battery chemistry materials,ambient temperatures and charge-discharge configurations.Experimental results indicate that the proposed PSO-DDA method surpasses the convolutional neural network-based method and the standard DDA-based method.The Py Torch implementation of the proposed PSO-DDA method is available at https://github.com/mxt0607/PSO-DDA.

Boosting battery state of health estimation based on self-supervised learning

State of health(SoH) estimation plays a key role in smart battery health prognostic and management.However,poor generalization,lack of labeled data,and unused measurements during aging are still major challenges to accurate SoH estimation.Toward this end,this paper proposes a self-supervised learning framework to boost the performance of battery SoH estimation.Different from traditional data-driven methods which rely on a considerable training dataset obtained from numerous battery cells,the proposed method achieves accurate and robust estimations using limited labeled data.A filter-based data preprocessing technique,which enables the extraction of partial capacity-voltage curves under dynamic charging profiles,is applied at first.Unsupervised learning is then used to learn the aging characteristics from the unlabeled data through an auto-encoder-decoder.The learned network parameters are transferred to the downstream SoH estimation task and are fine-tuned with very few sparsely labeled data,which boosts the performance of the estimation framework.The proposed method has been validated under different battery chemistries,formats,operating conditions,and ambient.The estimation accuracy can be guaranteed by using only three labeled data from the initial 20% life cycles,with overall errors less than 1.14% and error distribution of all testing scenarios maintaining less than 4%,and robustness increases with aging.Comparisons with other pure supervised machine learning methods demonstrate the superiority of the proposed method.This simple and data-efficient estimation framework is promising in real-world applications under a variety of scenarios.

The Place of Human Resource Management in Lagos State Healthcare Delivery: A Statistical Overview

Background: Behind every great system is an organized team;this is especially true in the healthcare industry, where a dedicated human resources team can effectively recruit employees, train staff, and implement safety measures in the workplace. The importance of human resources in the healthcare industry cannot be overstated, with benefits ranging from providing an orderly and effectively run facility to equipping staff with the most accurate and up-to-date training. Proper human resources management is critical in providing high-quality health care. A refocus on human resources management in healthcare requires more research to develop new policies. Effective human resources management strategies are greatly needed to achieve better outcomes and access to health care worldwide. Methods: This study leveraged NOI Polls census data on Health Facility Assessment for Lagos State. One thousand two hundred fifty-six health care facilities were assessed in Lagos State;numbers of Health workers were documented alongside their area of specialization. Also, demographic characterizations of the facilities, such as LGA, Ownership type, Facility Level Care, and Category of the facility, were also documented. Descriptive statistics alongside cross tabulation was done to present the various area of specialization of the health workers. Multiple response analysis was done to understand the distribution of human resources across the health facilities. At the same time, Chi-square and correlation tests were conducted to test the independence of various categories recorded while understanding the relationships among selected specialties. Results: The study revealed that Nurses were the most common health specialist in the Lagos State health facilities. At the same time, Gynecologists and General surgeons are the two medical specialists mostly common in health facilities. Midwives are the second most common health specialist working full time, while Generalist medical doctors make up the top three health specialists working full time. Nurses and Midwives had the highest number in Lagos State, while Pulmonologists were currently the lowest human resource available in Lagos State health care system. It was also noted that health facility distribution across Lagos’s urban and rural areas was even. In contrast, distribution based on other factors such as ownership type, Facility level of care, and facility category was slightly skewed. Conclusion: The distribution of health workers in health facility across LGA in Lagos State depend on Ownership type, Facility level of care, and category of the facility.

基于迁移学习与GRU神经网络结合的锂电池SOH估计

为解决退役电池梯次利用过程中单体剩余使用寿命估计困难、测试流程复杂与能耗高等问题,提出迁移学习与GRU网络结合的锂离子电池健康状态估计方法;设计的基础模型结构为输入层+GRU层+全连接层+输出层;根据健康因子的得分,选择训练基础模型的数据集、划分电池相似度等级并制定对应的迁移学习策略。实验结果表明:与其他模型相比,分别使用数据集的前40%与前25%训练得到的基础模型与迁移学习模型,两者的精度分别最大提高42.48%与95.28%,而预测稳定性分别最大提高55.38%与93.55%。

基于等效电路模型和数据驱动模型融合的SOC和SOH联合估计方法

针对电池SOC与SOH估计结果相互影响,单独估计准确度不高的问题,该文提出了一种基于等效电路模型和数据驱动模型融合的SOC和SOH联合估计方法。通过构建考虑老化和SOC的电池二阶RC等效电路模型,采用带遗忘因子的递推最小二乘法,在不同SOC和SOH的情况下,对电池的参数进行在线辨识,实现电池参数在线辨识与电池SOC和SOH估计的耦合。以锂离子电池自SOC=20%到恒流充电阶段结束所需时间为输入,电池SOH值为输出,训练GPR模型,实现电池SOH估计。将输出的SOH估计值与电池的额定容量相乘,得到电池的实际容量,更新二阶RC状态空间方程,采用扩展卡尔曼滤波算法对电池进行SOC估计,实现电池SOH估计和SOC估计之间的联合。采用牛津大学电池退化数据集和NASA随机使用电池数据集进行算法验证,结果表明,所提联合估计方法能够在电池的生命周期内较准确地跟随锂离子电池SOC和SOH的真实值。

Challenges and opportunities for battery health estimation:Bridging laboratory research and real-world applications

Addressing climate change demands a significant shift away from fossil fuels,with sectors like electricity and transportation relying heavily on renewable energy.Integral to this transition are energy storage systems,notably lithium-ion batteries.Over time,these batteries degrade,affecting their efficiency and posing safety risks.Monitoring and predicting battery aging is essential,especially estimating its state of health(SOH).Various SOH estimation methods exist,from traditional model-based approaches to machine learning approaches.

A review of deep learning approach to predicting the state of health and state of charge of lithium-ion batteries

In the field of energy storage,it is very important to predict the state of charge and the state of health of lithium-ion batteries.In this paper,we review the current widely used equivalent circuit and electrochemical models for battery state predictions.The review demonstrates that machine learning and deep learning approaches can be used to construct fast and accurate data-driven models for the prediction of battery performance.The details,advantages,and limitations of these approaches are presented,compared,and summarized.Finally,future key challenges and opportunities are discussed.

基于双向长短期记忆网络含间接健康指标的锂电池SOH估计

快速准确地对锂离子电池进行全寿命周期的健康状态(SOH)估计有助于提高储能设备的安全可靠性。提出一种基于间接健康指标(IHI)和鲸鱼优化算法(WOA)优化的双向长短期记忆(BiLSTM)网络相结合的锂电池SOH估计模型,该模型考虑了未来状态对当前SOH的影响。首先,对锂电池恒流恒压(CC-CV)充放电过程进行分析,提取出多个随充放电循环动态变化的电压、电流、温度的时间特征作为IHI,并加入放电负载电压下降时间这一指标;然后,通过相关性分析,从各IHI中筛选出和容量关联度高的IHI作为输入特征;最后,建立基于WOA优化的BiLSTM网络的电池SOH估计模型,并利用美国国家航天航空局锂电池数据集对2个不同工况下的电池SOH进行估计。结果表明,所提方法可有效提高SOH的估计精度。

Linguistic Dynamic Modeling and Analysis of Psychological Health State Using Interval Type-2 Fuzzy Sets

The study of psychological health state is helpful to build appropriate models and take effective intervention strategies, and the results benefit the intervened released from psychological distress within the shortest possible time. In this paper, interval type-2 fuzzy sets and fuzzy comprehension evaluation are applied in the analysis of mental health status and crisis intervention. A closed-loop linguistic dynamic intervention model for psychological health state is built. Linguistic dynamic systems based on interval type-2 fuzzy sets are used to describe and analyze the evolutionary process of psychological health status.

Psychological and Physiological Health Benefits of a Structured Forest Therapy Program for Children and Adolescents with Mental Health Disorders

Mental health conditions in children and adolescents can be improved by slow mindful nature connection known as forest therapyor bathing.Forest therapy has recently received growing attention as an enabler of relaxation and preventive health care withdemonstrated clinical efficacy.However,it is not well-known that forest therapy also decreases mental health issues amongindividuals with mental health disorders.This study explored the psychological and physiological health benefits of structuredforest therapy programs for children and adolescents with mental health disorders.A one-group pre-test-posttest design wasemployed for our study participants.Twelve participants(aged 9–14 years)engaged in two one-hour guided standard sequenceforest therapy experiences.A Mindful Attention Awareness Scale(MAAS),Connectedness to Nature Scale(CNS),Profile ofMood States(POMS),place meanings(e.g.,functional,emotional,and cognitive attachment to the forest)questionnaire,andphysiological health assessment were administered to the participants.Our results showed that negative mood states weresignificantly reduced and that a positive mood state was significantly improved after the structured forest therapy programs.Also,mindfulness,nature connection,place meanings,and physiological health were significantly boosted after theinterventions.The results demonstrate substantial psychological and physiological health and well-being outcomes ofstructured forest therapy for similar individuals.

Depression among Health Care Workers in Khartoum State, Sudan, 2022

Introduction: Depression is a serious issue affecting healthcare workers and is a leading cause of disability for both genders. Furthermore, it is one of the leading causes of mortality and morbidity, responsible for 4.4 percent of global disability. An estimated 350 million people are currently living with depression worldwide. Objectives: to estimate the prevalence of depression among healthcare workers in Khartoum State in 2022 and determine the associated factors. Methods: A cross-sectional survey was conducted among healthcare workers in Khartoum State, Sudan, in 2022 using a self-administered electronic questionnaire. Depression was screened using the self-reporting questionnaire (PHQ-9). Descriptive statistics in the form of frequencies and percentages were used to display the data. Odds ratios (ORs) with a 95% confidence interval were estimated using bivariate and multivariate logistic regression analysis to determine associations between depression and related factors. Results: A total of 341 valid responses were received, with a mean age of 33.91. The overall prevalence of depression (PHQ-9 > 8) was 258 (75.6%). The prevalence was significantly associated with marital status (single and divorced), occupation (psychologist), and working department (Emergency Department), showing a p-value of Conclusion: Depression is a serious mental health disorder that affects all people, including healthcare workers, and is a growing problem in Sudan. To address this, healthcare organizations must implement policies and strategies to reduce inequality and protect healthcare workers. A multidisciplinary approach that includes mental health professionals, the Ministry of Health, and universities is needed to prioritize mental health issues and ensure quality care and the overall well-being of both healthcare workers and patients.

基于IMOCS-BP神经网络的锂离子电池SOH估计

锂离子电池随着循环充放电次数的增长,其健康状态SOH(state-of-health)会随之发生一定程度的衰减。针对以上问题,设计了一种基于改进的多目标布谷鸟搜索IMOCS(improved multi-objective Cuckoo search)-BP神经网络的锂离子电池健康状态估计方法,在避免算法陷入局部最优的同时自适应改变布谷鸟搜索CS(Cuckoo search)算法更新概率和搜索步长,解决CS算法收敛速度慢和求解精度低的问题。以IMOCS算法和BP神经网络结合,对节点空间范围进行全局搜索,降低权值和阈值的初值对BP神经网络的影响,实现参数优化。通过Matlab仿真,验证了基于IMOCS-BP神经网络的SOH估计算法误差低、性能强,实现了锂电池SOH的精准预测。

Perception of Adolescents on the Attitudes of Providers on Their Access and Use of Reproductive Health Services in Delta State, Nigeria

This paper examines the perception of adolescents on the attitudes of providers on their access and use of reproductive health services (ARHS) in Delta State, Nigeria, with a view of assessing the impact of providers’ attitude on the use of adolescents’ reproductive health services in Delta State. The study adopted a survey design to collect primary data using questionnaires and focus group discussions (FGDs) from adolescents in a sample of schools. A sample size of 1500 respondents was taken from 12 schools in six Local Government Areas in three Senatorial Districts in Delta State, Nigeria. The locations of the schools were such that six each were in rural and urban communities respectively. The result from the study was that unfriendly attitudes of providers which keep adolescents waiting, inadequate duration of consultations, judgmental attitudes of some providers, lack of satisfactory services provision and lack of confidentiality will put off adolescents from accessing and using adolescents’ reproductive health services irrespective of their sex, age, class, religion, residence, ethnic group, parents’ education or income levels. The paper concludes that medical personnel take all these issues very seriously when dealing with adolescents to enhance access and use adolescents’ reproductive health services in Delta State and indeed Nigeria.

Application Research of Music Therapy in Mental Health of Special Children

A healthy psychological state is the premise for children to carry out various activities.Previous surveys have shown that children with special needs are affected by their own obstacles and are more prone to psychological problems such as sensitivity,low self-esteem,and impulsiveness.Therefore,it is necessary to provide more sys-tematic mental health education support for special children.Mental health education programs are an efficient form of maintaining children’s mental health.However,in thefield of special education,the number of mental health education courses developed according to the physical and mental characteristics and developmental needs of special children is relatively small,and there are many difficulties in the implementation process.Autism dis-order(ASD)is a kind of pervasive developmental dysfunction that is relatively common and representative in clinical practice.In recent years,the number of autistic children has continued to surge,and has gradually expanded from a family problem to a serious social problem.At present,the evaluation of the effect of autism intervention mainly relies on various behavioral scales,which are subjective to a certain extent.At the same time,due to the unclear pathogenesis of autism,the treatment of autism cannot be predicated on the right medicine,and can only be intervened in various ways.The purpose of this paper is to explore the difference between the EEG signals of autistic children and typically developing control(TD)children through the analysis method of EEG signals,and based on the analysis of EEG signals from an objective point of view,to study whether the music therapy method of Chinese Zither playing training can effectively Improving the brain functional status of chil-dren with autism yields positive therapeutic outcomes.The experimental results show that the complexity of brain electrical signals of ASD children is much lower than that of TD children,and there is a significant difference in the brain functional state between the two.The music therapy method based on Chinese zither playing training can improve the brain function of autistic patients,and there is a positive therapeutic effect.And with the exten-sion of the training period,the effect may be more significant.Chinese zither playing training can provide a new direction for the intervention of autism.

基于EKF算法的纯电动汽车锂电池SOC与SOH联合估算

为提高对动力电池的荷电状态(state of charge, SOC)估算精度、动力电池的健康状态(state of health, SOH)对锂电池性能的影响,提出一种扩展卡尔曼滤波(extended kalman filtering, EKF)联合估算算法。根据现有的实验数据,分析锂电池特性,构建二阶RC等效电路模型,并进行参数辨识,搭建MATLAB仿真平台联合EKF算法进行SOC估算,将仿真结果与真实数据进行对比,结果表明,EKF联合估算SOC比EKF估算SOC误差精度约高1.2%,且抗干扰能力更强。