Deep Learning-Based State-of-Health Estimation of Proton-Exchange Membrane Fuel Cells under Dynamic Operation Conditions.

Proton-exchange membrane fuel cells (PEMFCs) play a crucial role in the transition to sustainable energy systems. Accurately estimating the state of health (SOH) of PEMFCs under dynamic operating conditions is essential for ensuring their reliability and longevity. This study designed dynamic operating conditions for fuel cells and conducted durability tests using both crack-free fuel cells and fuel cells with uniform cracks. Utilizing deep learning methods, we estimated the SOH of PEMFCs under dynamic operating conditions and investigated the performance of long short-term memory networks (LSTM), gated recurrent units (GRU), temporal convolutional networks (TCN), and transformer models for SOH estimation tasks. We also explored the impact of different sampling intervals and training set proportions on the predictive performance of these models. The results indicated that shorter sampling intervals and higher training set proportions significantly improve prediction accuracy. The study also highlighted the challenges posed by the presence of cracks. Cracks cause more frequent and intense voltage fluctuations, making it more difficult for the models to accurately capture the dynamic behavior of PEMFCs, thereby increasing prediction errors. However, under crack-free conditions, due to more stable voltage output, all models showed improved predictive performance. Finally, this study underscores the effectiveness of deep learning models in estimating the SOH of PEMFCs and provides insights into optimizing sampling and training strategies to enhance prediction accuracy. The findings make a significant contribution to the development of more reliable and efficient PEMFC systems for sustainable energy applications.

Enhancing Lithium-Ion Battery Health Predictions by Hybrid-Grained Graph Modeling.

Predicting the health status of lithium-ion batteries is crucial for ensuring safety. The prediction process typically requires inputting multiple time series, which exhibit temporal dependencies. Existing methods for health status prediction fail to uncover both coarse-grained and fine-grained temporal dependencies between these series. Coarse-grained analysis often overlooks minor fluctuations in the data, while fine-grained analysis can be overly complex and prone to overfitting, negatively impacting the accuracy of battery health predictions. To address these issues, this study developed a Hybrid-grained Evolving Aware Graph (HEAG) model for enhanced prediction of lithium-ion battery health. In this approach, the Fine-grained Dependency Graph (FDG) helps us model the dependencies between different sequences at individual time points, and the Coarse-grained Dependency Graph (CDG) is used for capturing the patterns and magnitudes of changes across time series. The effectiveness of the proposed method was evaluated using two datasets. Experimental results demonstrate that our approach outperforms all baseline methods, and the efficacy of each component within the HEAG model is validated through the ablation study.

Electrochemical Circuit Model Based State of Health Prognostics for Evaluation of Reusability of Lithium-Ion Batteries from Electric Vehicle.

For the purpose of predicting the state of health of already used lithium-ion batteries from 85 kWh electric vehicles, a simplified equivalent circuit model is utilized to estimate the electrochemical time constant from constant current discharge profiles. The grading process among as-obtained LIB cells is classified into three level types according to the remaining capacity and direct current resistance. Theoretically, the logarithmic equation describing cycling behavior is derived and utilized in the prediction of the state of health of the used cells. After the selection of the electrochemical time constant obtained from the best-fitting results in constant current discharge data, the suitable cycle number until the 20th cycle was selected for the prediction of the state of health after the 250th cycling data, which revealed that a narrow error range below 5% was for high and medium battery grades. Also, this error range became abruptly wider in lowest grade batteries, indicating that our proposed model for cycling behavior was highly useful in the prediction of the future state of health of the used batteries.

Are electric vehicle batteries being underused? A review of current practices and sources of circularity.

The increasing demand for Lithium-ion batteries for Electric Vehicle calls for the adoption of sustainable practices and a switch towards a circular economy-based system to ensure that the electrification of transportation does not come at a high environmental cost. While driving patterns have not changed much over the years, the current Electric Vehicle market is evolving towards models with higher battery capacities. In addition, these batteries are considered to reach the End of Life at 70-80% State of Health, regardless of their capacity and application requirements. These issues may cause an underuse of the batteries and, therefore, hinder the sustainability of the Electric Vehicle. The goal of this study is to review and compare the circular processes available around Electric Vehicle batteries. The review highlights the importance of prioritizing the first-life of the battery onboard, starting with reducing the nominal capacity of the models. In cases where the battery is in risk of reaching the End of Life with additional value, Vehicle to Grid is encouraged over the deployment of second-life applications, which are being strongly promoted through institutional fundings in Europe. As a result of the identified research gaps, the methodological framework for the estimation of a functional End of Life is proposed, which constitutes a valuable tool for sustainable decision-making and allows to identify a more accurate End of Life, rather than considering the fixed threshold assumed in the literature.

[Features of the state of health, including physical development, of adolescent girls living in the middle and high mountains of the Kyrgyz Republic].

Adolescent girls aged 15-18 are in an active process of growth and development, as evidenced by the dynamics of changes in height and weight indicators. Low values of average growth indicators were determined among girls in Batken, on average 2 cm less than the average indicators of girls in Bishkek, however, the statistical analysis performed did not confirm the reliability of these differences. In 84.3% of the surveyed adolescent girls living in Naryn, iron deficiency anemia was detected. Kidney and urinary tract diseases (31.4%) took the first place in the structure of diseases among girls in Batken. Diffuse enlargement of the thyroid gland was found in 13% of women living in highlands. Inflammatory diseases of the genitourinary system are two or more times more common among girls in the middle and high mountains than in Bishkek: vulvitis in 8.7-11.4% of cases against 4.1% of cases, urogenital diseases in 6.5-17.4 versus 3.9 respectively. This indicates the need to introduce specific preventive programs for girls living in the middle and high mountains.

A Review on the Prediction of Health State and Serving Life of Lithium-Ion Batteries.

The monitoring and prediction of the health status and the end of life of batteries during the actual operation plays a key role in the battery safety management. However, although many related studies have achieved exciting results, there are few systematic and comprehensive reviews on these prediction methods. In this paper, the current prediction models of remaining useful life of lithium-ion batteries are divided into mechanism-based models, semi-empirical models and data-driven models. Their advantages, technical obstacles, improvement methods and prediction performance are summarized, and the latest research results are shown by comparison. We highlight that the fusion models of convolution neural network, long short term memory network and so on, which have great practical application prospects because of their outstanding computing efficiency and strong modeling ability. Finally, we look forward to the future work in simplifying the model and improving its interpretability.

State of Health Prediction of Lithium-Ion Battery Based on Deep Dilated Convolution.

A battery's charging data include the timing information with respect to the charge. However, the existing State of Health (SOH) prediction methods rarely consider this information. This paper proposes a dilated convolution-based SOH prediction model to verify the influence of charging timing information on SOH prediction results. The model uses holes to fill in the standard convolutional kernel in order to expand the receptive field without adding parameters, thereby obtaining a wider range of charging timing information. Experimental data from six batteries of the same battery type were used to verify the model's effectiveness under different experimental conditions. The proposed method is able to accurately predict the battery SOH value in any range of voltage input through cross-validation, and the SDE (standard deviation of the error) is at least 0.28% lower than other methods. In addition, the influence of the position and length of the range of input voltage on the model's prediction ability is studied as well. The results of our analysis show that the proposed method is robust to different sampling positions and different sampling lengths of input data, which solves the problem of the original data being difficult to obtain due to the uncertainty of charging-discharging behaviour in actual operation.

A Learning-Based Vehicle-Cloud Collaboration Approach for Joint Estimation of State-of-Energy and State-of-Health.

The state-of-energy (SOE) and state-of-health (SOH) are two crucial quotas in the battery management systems, whose accurate estimation is facing challenges by electric vehicles' (EVs) complexity and changeable external environment. Although the machine learning algorithm can significantly improve the accuracy of battery estimation, it cannot be performed on the vehicle control unit as it requires a large amount of data and computing power. This paper proposes a joint SOE and SOH prediction algorithm, which combines long short-term memory (LSTM), Bi-directional LSTM (Bi-LSTM), and convolutional neural networks (CNNs) for EVs based on vehicle-cloud collaboration. Firstly, the indicator of battery performance degradation is extracted for SOH prediction according to the historical data; the Bayesian optimization approach is applied to the SOH prediction combined with Bi-LSTM. Then, the CNN-LSTM is implemented to provide direct and nonlinear mapping models for SOE. These direct mapping models avoid parameter identification and updating, which are applicable in cases with complex operating conditions. Finally, the SOH correction in SOE estimation achieves the joint estimation with different time scales. With the validation of the National Aeronautics and Space Administration battery data set, as well as the established battery platform, the error of the proposed method is kept within 3%. The proposed vehicle-cloud approach performs high-precision joint estimation of battery SOE and SOH. It can not only use the battery historical data of the cloud platform to predict the SOH but also correct the SOE according to the predicted value of the SOH. The feasibility of vehicle-cloud collaboration is promising in future battery management systems.

A Data-Driven Approach to State of Health Estimation and Prediction for a Lithium-Ion Battery Pack of Electric Buses Based on Real-World Data.

In the era of big data, using big data to realize the online estimation of battery SOH has become possible. Traditional solutions based on theoretical models cannot take into account driving behavior and complicated environmental factors. In this paper, an approximate SOH degradation model based on real operating data and environmental temperature data of electric vehicles (EVs) collected with a big data platform is proposed. Firstly, the health indicators are extracted from the historical operating data, and the equivalent capacity at 25 °C is obtained based on the capacity-temperature empirical formula and the capacity offset. Then, the attenuation rate during each charging and discharging process is calculated by combining the operating data and the environmental temperature. Finally, the long short-term memory (LSTM) neural network is used to learn the degradation trend of the battery and predict the future decline trend. The test results show that the proposed method has better performance.

A Review of Mechanical and Chemical Sensors for Automotive Li-Ion Battery Systems.

The electrification of passenger cars is one of the most effective approaches to reduce noxious emissions in urban areas and, if the electricity is produced using renewable sources, to mitigate the global warming. This profound change of paradigm in the transport sector requires the use of Li-ion battery packages as energy storage systems to substitute conventional fossil fuels. An automotive battery package is a complex system that has to respect several constraints: high energy and power densities, long calendar and cycle lives, electrical and thermal safety, crash-worthiness, and recyclability. To comply with all these requirements, battery systems integrate a battery management system (BMS) connected to an complex network of electric and thermal sensors. On the other hand, since Li-ion cells can suffer from degradation phenomena with consequent generation of gaseous emissions or determine dimensional changes of the cell packaging, chemical and mechanical sensors should be integrated in modern automotive battery packages to guarantee the safe operation of the system. Mechanical and chemical sensors for automotive batteries require further developments to reach the requested robustness and reliability; in this review, an overview of the current state of art on such sensors will be proposed.

Estimation of Online State of Charge and State of Health Based on Neural Network Model Banks Using Lithium Batteries.

Lithium batteries are secondary batteries used as power sources in various applications, such as electric vehicles, portable devices, and energy storage devices. However, because explosions frequently occur during their operation, improving battery safety by developing battery management systems with excellent reliability and efficiency has become a recent research focus. The performance of the battery management system varies depending on the estimated accuracy of the state of charge (SOC) and state of health (SOH). Therefore, we propose a SOH and SOC estimation method for lithium-ion batteries in this study. The proposed method includes four neural network models-one is used to estimate the SOH, and the other three are configured as normal, caution, and fault neural network model banks for estimating the SOC. The experimental results demonstrate that the proposed method using the long short-term memory model outperforms its counterparts.

State-of-Health Prediction Using Transfer Learning and a Multi-Feature Fusion Model.

Existing data-driven technology for prediction of state of health (SOH) has insufficient feature extraction capability and limited application scope. To deal with this challenge, this paper proposes a battery SOH prediction model based on multi-feature fusion. The model is based on a convolutional neural network (CNN) and a long short-term memory network (LSTM). The CNN can learn the cycle features in the battery data, the LSTM can learn the aging features of the battery over time, and regression prediction can be made through the full-connection layer (FC). In addition, for the aging differences caused by different battery operating conditions, this paper introduces transfer learning (TL) to improve the prediction effect. Across cycle data of the same battery under 12 different charging conditions, the fusion model in this paper shows higher prediction accuracy than with either LSTM and CNN in isolation, reducing RMSPE by 0.21% and 0.19%, respectively.

Optimal Energy-Storage Configuration for Microgrids Based on SOH Estimation and Deep Q-Network.

Energy storage is an important adjustment method to improve the economy and reliability of a power system. Due to the complexity of the coupling relationship of elements such as the power source, load, and energy storage in the microgrid, there are problems of insufficient performance in terms of economic operation and efficient dispatching. In view of this, this paper proposes an energy storage configuration optimization model based on reinforcement learning and battery state of health assessment. Firstly, a quantitative assessment of battery health life loss based on deep learning was performed. Secondly, on the basis of considering comprehensive energy complementarity, a two-layer optimal configuration model was designed to optimize the capacity configuration and dispatch operation. Finally, the feasibility of the proposed method in microgrid energy storage planning and operation was verified by experimentation. By integrating reinforcement learning and traditional optimization methods, the proposed method did not rely on the accurate prediction of the power supply and load and can make decisions based only on the real-time information of the microgrid. In this paper, the advantages and disadvantages of the proposed method and existing methods were analyzed, and the results show that the proposed method can effectively improve the performance of dynamic planning for energy storage in microgrids.

[MONITORING OF OFFICIAL REQUIREMENTS TO THE STATE OF HEALTH OF CITIZENS OF MILITARY AGE WITH DISEASES OF THE NERVOUS SYSTEM].

the article provides an analysis of changes in official requirements for the state of health of young men with diseases of the nervous system (Regulations on military medical examination as amended from 1995, 2003, 2013). Columns I and II of articles 21-28 of the Schedule of Diseases of this Provision are considered from the point of view of the category of fitness for military service on conscription. A set of measures is proposed to reduce the consequences of changing the requirements for the functional state of the nervous system of the health of future conscripted servicemen.

Acoustic Emission Detection and Analysis Method for Health Status of Lithium Ion Batteries.

The health detection of lithium ion batteries plays an important role in improving the safety and reliability of lithium ion batteries. When lithium ion batteries are in operation, the generation of bubbles, the expansion of electrodes, and the formation of electrode cracks will produce stress waves, which can be collected and analyzed by acoustic emission technology. By building an acoustic emission measurement platform of lithium ion batteries and setting up a cycle experiment of lithium ion batteries, the stress wave signals of lithium ion batteries were analyzed, and two kinds of stress wave signals which could characterize the health of lithium ion batteries were obtained: a continuous acoustic emission signal and a pulse type acoustic emission signal. The experimental results showed that during the discharge process, the amplitude of the continuous acoustic emission signal decreased with the increase of the cycle times of batteries, which could be used to characterize performance degradation; there were more pulse type acoustic emission signals in the first cycle of batteries, less in the small number of cycles, and slowly increased in the large number of cycles, which was in line with the bathtub curve and could be used for aging monitoring. The research on the health of lithium ion batteries by acoustic emission technology provides a new idea and method for detecting the health lithium ion batteries.

[Health-related quality of life in patients consuming benzodiazepine]. / Calidad de vida relacionada con la salud en pacientes consumidores de benzodiacepinas.

OBJECTIVE: To describe the health-related quality of life (HRQoL) in benzodiazepine users and to verify whether there is an association with the characteristics of the treatment, its effectiveness, and the sociodemographic variables. DESIGN: Descriptive cross-sectional study. LOCATION: Family medicine consultations. PARTICIPANTS: Four hundred and fifty 2patients over 18 years of age consuming benzodiazepines or similar drugs. MAIN MEASUREMENTS: HRQoL was assessed using the EuroQol5-D questionnaire. Other variables: symptoms of anxiety or insomnia, sociodemographic variables and characteristics of the treatment. RESULTS: The mean score in health status was 62.80 (95% CI: 60.69-64.86), lower in people without studies (59.27±21.97 SD; P=.004) and lower social category (60.02±21.27 SD; P<.001). Regarding the social rate (EQ index), a mean score of 0.6025 (95% CI: 0.5659-0.6391) was obtained, higher in people with higher education (0.6577±0.3574 SD; P=.001), plus social category (0.7286±0.3381 SD; P<.001) and age less than 65 years (0.6603±0.3426 SD; P<.001). The variables that were associated with the value of the EQ index by means of multiple regression were absence of anxiety/insomnia, belonging to higher social classes, age less than 65 years and less consumption of anxiolytics/hypnotics. CONCLUSIONS: Patients who use benzodiazepines show, despite treatment, a moderate HRQL, lower than that obtained in the general population or in primary care patients. The situation is more favorable in the youngest, in those who do not present anxiety/insomnia, in those belonging to higher social classes and when the consumption of drugs is lower.

Health Status of French Young Patients with Inborn Errors of Metabolism with Lifelong Restricted Diet.

OBJECTIVE: To describe the health status of young patients affected by inborn errors of metabolism that require adherence to a restricted diet (IEMRDs) and to describe and compare their self- and proxy (parent)-reported quality of life (QoL) with reference values. STUDY DESIGN: A cross-sectional study was conducted in 2015-2017 in patients affected by IEMRDs (except phenylketonuria) younger than 18 years. Data collection was based on medical records, clinical examinations, parents' and children's interviews, and self-reported questionnaires. Measurements included clinical and healthcare data, child and family environment data, and self- and proxy (parent)-reported QoL. RESULTS: Of the 633 eligible participants, 578 were recruited (50.3% boys; mean age: 8.7 years); their anthropometric status did not differ from the general population. Approximately one-half of them had at least 1 complication of the disease. Their self-reported global QoL did not differ from that of the general population. However, relations with friends and leisure activities QoL domains were negatively impacted, whereas relations with medical staff, relations with parents, and self-esteem QoL domains were positively impacted. Their proxy (parent)-reported QoL was negatively impacted. CONCLUSIONS: Young patients affected by IEMRDs present a high rate of clinical complications. Although their proxy (parent)-reported QoL was negatively impacted, their self-reported QoL was variably impacted (both positively and negatively). These results may inform counseling for those who care for affected patients and their families.

EUROPEAN STANDARDS FOR ASSESSING THE HEALTH OF A PERSON WHO PROBABLY SUSTAINED MISTREATMENT DURING DETENTION OR CUSTODY.

OBJECTIVE: The aim: The purpose of this paper is to identify and characterize the standards for assessing the health status of a person who is likely to have been mistreated during detention or custody. PATIENTS AND METHODS: Materials and methods: The provisions of international regulations, as well as the case law of the European Court of Human Rights (hereinafter - ECHR, Court) were studied in the preparation of the paper. A set of general scientific and special methods of cognition was used, in particular, the comparative-legal method, the system-structural method, the generalization method, the method of analysis and synthesis, and others. CONCLUSION: Conclusions: Medical examinations and forensic examinations of persons detained or incarcerated and alleging torture or mistreatment are appropriate provided that they comply with European standards set out in the case law of the ECHR and the recommendations of international organizations, which whereas will ensure the effectiveness of formal investigations of such facts.

Placental dysfunction: health status, nutritional status and mineral profile of a mother-child pair.

OBJECTIVE: The aim: the analysis of the PD, pregnancy, the labor, the research on peculiarities of the development and health status of breast-fed children, who are born to mothers with PD, by means of analyzing the mother-child pair's nutritional status and mineral homeostasis. PATIENTS AND METHODS: Materials and methods: At the 1 stage, an analysis of the PD frequency, the pregnancy, the labor was conducted during 5 years. At the 2 stage, 188 mother-child pairs were examined: 84.04% women had PD and 15.96% didn't have it. The research included the analysis of the anamnestic data, maternal nutritional status, general clinical study, assessment of the physical, psychomotor level of the child's development, study of the elemental profile. RESULTS: Results: High frequency of complications in pregnancy and labor was observed in cases when women had PD, due to the imbalance in the "mother-placenta-fetus" system. The results' analysis showed an increased level of Zn (1.437%), K (10.147%), and Ca (83.900%) in hair; an increased level of K (82.818%), Cr (0.274%), and Na (3.611%) in breast milk of women with PD. Children born to mothers with PD had a significantly increased level of Cr (0.92%), S (0.578%) and P (0.169%), Na (0.107%), Ca (56.041%), and Zn (7.149%). CONCLUSION: Conclusions: PD has a negative impact on the pregnancy and labor and may be one of the factors causing the mineral imbalance of breast-fed infant.

[The Self-Evaluation of Health and Psycho-Emotional Status of the Young Families and Population of Adolescent Youth Age].

The purpose of the study was to investigate characteristics of health and psycho-emotional status according to self-assessment in young families and contingents of adolescence, residing in the Irkutsk oblast, in the second decade of XXI century. METHODS: The study implemented technology of self-assessment of the level of individual health according five-point scale in groups of adolescents, students, and the families. The methodology also considered presence of chronic diseases, manifestations of painful symptoms, rate of cases of diseases during the year, number of visits to physician, causes of disease, treatment costs. The prompt diagnosis was implemented regarding psycho-emotional stress on the basis of method of O. S. Kopina et al. (2004). In families and among students, the degree of satisfaction with various aspects of life was rated. RESULTS: The number of persons among adult family member, who rated their health status as satisfactory, was higher than among adolescents and youths by 2.0 and 1.5 times (χ2 = 11.2, p = 0.02). The highest frequency of self-assessment of health as "bad" and "very poor" was among students. Teenage-girls and student-girls were statistically significantly more likely than young boys to note morphofunctional disorders on the part of various organs and systems. In adolescent groups, 2.3% of boys and 10.9% of girls; in the groups of students - 8.9% of boys and 12.8% of girls reported pathology of reproductive system. The main reasons of visiting patients for medical care are: respiratory and digestive diseases, allergic and neurological diseases. Students and family adult members also suffered of circulatory system diseases. The family adult members experienced high level of psychoemotional stress more frequently than adolescents by 3.4 times, students - 2.9 times (χ2 = 31.3; p < 0.001), which corresponded to lower indicators of satisfaction of the family adult members with living conditions. FINDINGS: The high frequency of morphofunctional disorders, neurotic and psychosomatic manifestations among examined individuals indicate significant prevalence of autonomic nervous system dysfunctions and latent pathological processes.