Battery Discharge Research Articles

Reinforcement Learning for EV Fleet Smart Charging with On-Site Renewable Energy Sources

In 2020, the transportation sector was the second largest source of carbon emissions in the UK and in Newcastle upon Tyne, responsible for about 33% of total emissions. To support the UK’s target of reaching net zero emissions by 2050, electric vehicles (EVs) are pivotal in advancing carbon-neutral road transportation. Optimal EV charging requires a better understanding of the unpredictable output from on-site renewable energy sources (ORES). This paper proposes an integrated EV fleet charging schedule with a proximal policy optimization method based on a framework for deep reinforcement learning. For the design of the reinforcement learning environment, mathematical models of wind and solar power generation are created. In addition, the multivariate Gaussian distributions derived from historical weather and EV fleet charging data are utilized to simulate weather and charging demand uncertainty in order to create large datasets for training the model. The optimization problem is expressed as a Markov decision process (MDP) with operational constraints. For training artificial neural networks (ANNs) through successive transition simulations, a proximal policy optimization (PPO) approach is devised. The optimization approach is deployed and evaluated on a real-world scenario comprised of council EV fleet charging data from Leicester, UK. The results show that due to the design of the rewards function and system limitations, the charging action is biased towards the time of day when renewable energy output is maximum (midday). The charging decision by reinforcement learning improves the utilization of renewable energy by 2–4% compared to the random charging policy and the priority charging policy. This study contributes to the reduction in battery charging and discharging, electricity sold to the grid to create benefits and the reduction in carbon emissions.

Simultaneous measurement of temperature and refractive index based on fiber optic Fabry-Pérot cavity in batteries

Abstract A Fabry-Pérot (FP) sensor for simultaneous measurement of refractive index and temperature of an all-fiber synchronous liquid based on the Vernier effect is proposed, special application for internal monitoring of lithium-ion battery electrolytes. The theoretical model of high sensitivity cascade Fabry-Pérot interferometer (PFPI) is established, the sensitivity amplification mechanism of PFPI is analyzed in detail, the perfect matching scheme for measuring the refractive index of the electrolyte inside the battery is designed according to the matching conditions of the optical path, and the corresponding sensors for simultaneous measurement of the temperature and the refractive index are fabricated. The experimental results show that the sensor has a maximum refractive index sensitivity of 15391.5033 nm/RIU, a good linear fit, and can effectively monitor the refractive index change of the electrolyte by 10-4 orders of magnitude during normal charging and discharging of lithium-ion batteries. Compared to traditional epoxy adhesive bonded or laser processed FP sensors, this all-fibre optic structure not only improves temperature and corrosion resistance, but also significantly reduces temperature cross-sensitivity. Its small size and excellent resistance to high temperature and corrosion ensure the sensor's excellent response and broad application prospects in monitoring the refractive index of the electrolyte in 18650 lithium-ion batteries, which provides effective technical support for monitoring the health status of batteries and detecting early safety issues.

Ab Initio Simulation of Raman Fingerprints of Sulfur/Carbon Copolymer Cathodes During Discharge of Li-S Batteries.

Sulfur/carbon copolymers have emerged as promising alternatives for conventional crystalline sulfur cathodes for lithium-sulfur batteries. Among these, sulfur--n--1,3--diisopropenylbenzene (S/DIB) copolymers, which present a 3D network of DIB molecules interconnected via sulfur chains, have particularly shown a good performance and, therefore, have been under intensive experimental and theoretical investigations. However, their structural complexity and flexibility have hindered a clear understanding of their structural evolution during redox reactions at an atomistic level. Here, by performing state-of-the-art ab initiomolecular dynamics-based Raman spectroscopy simulations, we investigate the spectral fingerprints of S/DIB copolymers arising from local structures during consecutive reactions with lithium. We discuss Raman spectral changes in particular frequency ranges which are common in S/DIB copolymers having shortand those consisting of longer sulfur chains. We also highlight those spectroscopic fingerprints specific to local S/DIB structures containing only short or long sulfur chains. This could help distinguish them experimentally during discharge. Our theoretically predicted results are in a good agreement with experimental Raman measurements on cells at different discharge stages. This work representsan attempt to compute Raman fingerprints ofcopolymer cathodes during battery operationincluding quantum-chemical and finite-temperature effects, and provides a guideline for Raman spectral changes of arbitrary electrodes during discharge.

All‐Climate Thermal Management Performance of Power Batteries Based on Double‐Layer Flexible Phase Change Materials

AbstractThermal management systems for power batteries based on phase change materials (PCM) are limited by low heat transfer efficiency, leakage issues, and high rigidity, and most of them cannot meet the needs of all‐climate thermal management. A double‐layer flexible phase change material (FPCM) sleeve structure for all‐climate thermal management is proposed in this study for the first time. Innovations in both material and design have enhanced the adaptability of the thermal management system. The outer layer FPCM achieves high thermal conductivity (4.23 W m−1 K−1) and electrical conductivity (0.95 S m−1), the inner layer FPCM achieves insulation (22.76 MΩ) and flexibility, the thermal contact resistance (TCR) between the double‐layer sleeve structure and the battery are measured to be only 0.15 °C W−1, significantly improved thermal management performance. Experimental results show that at 30 °C ambient temperature, 5 C discharge, the system reduces the maximum temperature by 14.5 °C, from 61.4 to 46.9 °C, compared to natural convection. Additionally, during heating, the system achieves heating rates of 7.0, 8.3, and 8.7 °C min−1 at −20, −10, and 0 °C, respectively, extending battery discharge duration by 32.5%, 65.9%, and 33.6%.

УПРАВЛІННЯ ГІБРИДНОЮ СИСТЕМОЮ ЕЛЕКТРОЖИВЛЕННЯ ТВАРИННИЦЬКОЇ ФЕРМИ З ВІДНОВЛЮВАЛЬНИМИ ДЖЕРЕЛАМИ ТА ЕЛЕКТРОТРАНСПОРТОМ

The article considers the improvement of the control with using the generation of renewable energy sources forecast for a grid-connected a hybrid power supply system of a livestock farm with electric transport and a gas generator. The task is to form a graph of the state of charge of the main battery with a limitation of the depth of discharge with the maximum use of renewable sources energy. The calculation method of the state of charge of a battery and power consumption graph when working with the grid and in autonomous mode has been improved, with the definition of recommendations for charging electric transport. A mechanism has been developed for correcting the power consumption based on the deviation of the battery charge state relative to the specified value, with the correction disabled to implement the function of eliminating the export of excess energy to the grid or gas generator. This ensures the limitation of the gas generator power within certain limits and helps to limit the influence of generation and load deviations relative to the forecast on the battery discharge depth. The structure of the energy processes model in the system for the daily operation cycle has been developed. In the process of modeling, the deviation of renewable energy generation up to 20% and 10% was studied simultane-ously with a 10% increase in load.

Iron bed accelerator for discharging cylindrical NCA battery in salt solution

This study examines the iron bed accelerator for discharging cylindrical NCA batteries in salt solution. The use of Li-ion batteries has increased due to the rise of e-mobility in computers, cell phones, and electric vehicles. Recycling Li-ion batteries for raw material in lithium-ion battery production is increasingly important as the revolution unfolds. When disposing of, transporting, and recycling the battery, it is important to crush it to separate the black mass, plastic, and metal components. However, there is a potential explosion risk due to the remaining voltage in the battery. In recycling, the discharge step is significant. The research aimed to test a new method for discharging cylinder batteries using saltwater and an iron bed. Higher NaCl content increases pH and lowers electrochemical potential for water electrolysis. This unique combination enables the battery to discharge at a high rate. In 6 hours, the battery discharged in a 20 wt.% salt solution with 99.6% efficiency. The battery discharge efficiency decreased when exposed to 25 wt% and 30 wt% salt solutions, attributed to reduced water electrolysis intensity. According to the results of various experiments, it has been observed that as the temperature of the salt solution rises, there is a slight increase in the rate of battery discharge; however, no significant difference has been observed. This article talks about how batteries are discharged. It shows the electrochemical reaction using the Eh-pH diagram for Fe-Na-Cl. It also has a schematic diagram that shows the process and a chemical analysis of the precipitate that forms during the discharge test.

Constructing dilute Mg-1.0In binary alloy: A pathway to enhanced anode performance in Mg-air battery

Magnesium anode is a critical material in Mg-air battery; however, the contradiction between mitigating self-corrosion and promoting activation poses a significant obstacle to the rapid advancement of primary magnesium batteries. Herein, this issue is addressed by constructing a dilute Mg-1.0In binary alloy with 1 wt% indium as the anode material. The equiaxed dendrites and moderate indium concentration gradient in the as-cast anode facilitate the formation of a protective surface film, leading to a low corrosion rate of 0.20 mm y−1 and enhancing the stability prior to discharge. Moreover, during the battery discharge process, this unique microstructure enables the redeposition of metallic indium and indium hydroxide, thereby dramatically accelerating the shedding of oxidation products and suppressing side hydrogen evolution reaction. The Mg-1.0In anode in a Mg-air battery delivers a discharge capacity of 1587 mA h g−1 and an average voltage of 1.46 V at 10 mA cm−2, outperforming most of previously reported magnesium anodes and the control samples with various indium contents. This work would inspire the achievement of superior Mg-air battery performance through the use of binary magnesium anode system in as-cast state, as opposed to a more complex and time-consuming multi-component anode design involving heat treatment and plastic deformation.

A novel bionic lotus leaf channel liquid cooling plate for enhanced thermal management of lithium-ion batteries

Battery Thermal Management Systems (BTMS) are pivotal in safeguarding the safety, efficiency, and lifespan of electric vehicles. In this study, we propose a bionic lotus leaf (BLL) channel liquid-cooled plate to mitigate temperature accumulation issues observed during lithium-ion battery (LIB) discharge. The primary objective is to enhance heat dissipation and achieve uniform temperature distribution within LIBs. We investigated the impact of different interior configurations and mass flow rates on individual lithium-ion battery (LIB) temperatures using single-variable analysis. Our findings indicate that higher inlet mass flow rates effectively lower the temperature increase in individual LIBs, albeit at the cost of inducing a significant pressure drop.The optimal parameter combination is determined through orthogonal analysis. Specifically, the channel angle (α) and inlet mass flow rate (M) are found to significantly influence the maximum temperature (Tmax) of LIBs. The number of channels (N) is optimized to enhance temperature distribution and reduce maximum temperature variation (ΔTmax) within LIBs. Furthermore, adjusting the channel width (D) substantially mitigated pressure drop (ΔP) in the BLL channel liquid cooling plate, thereby improving hydraulic pump efficiency. The identified optimal combination (M = 1.0 g s-1, N = 4, D = 2.5 mm, α = 90°) ensures that Tmax remains below 29.732 °C even during a 5C discharge, a critical requirement. Compared to a traditional serpentine channel with equivalent heat transfer area and inlet mass flow, the optimized BLL channel showed a decrease in Tmax by 0.776 °C, ΔTmax reduction by 2.445 °C, and ΔP reduced to only 43.44 % of that in the serpentine channel. The BLL channel proposed in this research can serve as a valuable reference for BTMS.

Design and experimental verification of propulsion system for a Mars quadcopter

Due to the Mars rotorcraft can conduct extensive surface exploration of Mars and carry sampler for collecting samples on the Martian surface, it is gradually becoming the mainstream exploration devices for Mars missions. In response to the thin atmosphere on Mars, with the flight duration and sample-carrying capacity of the quadcopter as constraints, we design the propulsion system parameters for the Mars quadcopter with the function of sampling on the Martian surface. A method for evaluating rotor performance indicators, including mass and Mach number at the tip of the blade, is proposed. Based on the evaluation index and the steady RANS method for predicting the lift and drag characteristics of the rotor, an appropriate rotor diameter for the Mars quadrotor is selected. The method combining NSGA-II and two-dimensional steady RANS is employed to optimize the airfoil of the Mars quadcopter blade under the condition of a chord length of 40 mm, a Mach number of 0.43, an angle of attack of 20°, and a Reynolds number based on chord of 6080. Experimental verification for the lift-to-drag characteristics of the single rotor is conducted in an environment simulating the atmospheric density on the Martian surface. The results show that the blade after optimization can generate a thrust of 5.95 N and consume power of 164.9 W, at the rotational speed of 3650 r/min. Based on the test bench with the function of sliding up and down for testing aerodynamic performance of quadcopter, the temperature of the motor and battery discharge characteristics of the Mars quadcopter are conducted. The results of the test show that the quadrotor can provide a thrust-to-weight ratio of 1.66 for the Mars quadcopter while meeting the design requirement of 3 min.

Optimization of thermal management performance of direct-cooled power battery based on backpropagation neural network and deep reinforcement learning

The batteries of new energy vehicles generate a large amount of heat when discharged at large multiplication rates, which can cause safety hazards if the heat is not eliminated in time. In this paper, a Swiss roll-type cooling belt is used to improve the thermal performance of lithium-ion battery packs. This paper selects six key parameters as optimization parameters, including the structure of Swiss roll-type cooling belt, coolant type, inlet coolant mass flow rate, inlet coolant gas volume fraction, battery discharge rate, and ambient temperature. Use neural network fitting and deep reinforcement learning to optimize these six parameters in order to achieve optimized cooling performance. The results show that after the cold plate has been structurally optimised and the inlet parameters have been optimised by deep reinforcement learning, the thermal performance has been significantly improved. Not only does the cold plate inlet require less mass flow, but the battery pack also performs better in terms of temperature difference.

Optimal control algorithms for Gabon’s Smart Grid: Enhancing efficiency and sustainability

The adoption of smart grid technologies offers Gabon several opportunities to enhance energy efficiency and sustainability. This study investigates the use of optimum control algorithms to increase grid stability and enhance the utilization of renewable energy sources. Mathematical models and simulations are used to assess genetic algorithms in light of Gabon's unique energy situation. Systems known as electrical smart grids supply electricity to users directly from power plants in an effort to reduce costs, cut down on blackouts, and improve energy efficiency. Smart grids, or SGs, are well-known pieces of equipment because of their amazing capabilities, which include bi-directional communication, stability, power failure detection, and interconnectivity with appliances for monitoring. Many modern data and security management systems, including modeling, monitoring, optimization, and/or artificial intelligence, lead to SGs. Energy was once cheap, easily managed, and dependent only on fundamental elements. Demand has significantly increased as a result of the current circumstances, which has also increased Gabon's electricity expenses, the likelihood of a contingency, and the complexity of the electrical network. In Gabon, smart grids have shown to be the most practical and clever way to lessen these problems in recent years. An electrical network with information technology integrated is called a smart grid. According to this study, using genetic algorithms in a smart grid could lower Gabon's overall electricity prices. In order to meet demand, the proposed approach makes use of off-grid battery banks and renewable energy sources. The goal of GA optimization is the short-term time averaged power cost; factors that affect this include grid energy to satisfy load, battery discharge, and other factors. MATLAB software is used to solve the optimization problem over a 24-hour period of renewable input, real-time energy pricing, and load. The results are presented.

Optimizing Charge and Discharge of Lithium-Ion Batteries by Deploying PID Controller with Coupled Electro-Thermal-Aging Dynamic

Optimizing Charge and Discharge of Lithium-Ion Batteries by Deploying PID Controller with Coupled Electro-Thermal-Aging Dynamic

Optimal design and control strategy for enhanced battery thermal management

The Battery Thermal Management System (BTMS) plays a crucial role in the safety and performance of new energy vehicles. This study proposes an innovative cooling structure design that ingeniously combines the advantages of air cooling, water cooling, and Phase Change Materials (PCMs) to enhance the cooling efficiency of the battery system. Through numerical simulations, the effectiveness of this cooling system was validated and further supported by experimental evidence confirming the accuracy of the simulation results. Subsequently, this research utilized the Response Surface Methodology (RSM) to optimize key parameters of the cooling structure, including the fin height, gap length, and PCM thickness, with their optimal values determined to be 5.20 mm, 17.69 mm, and 3.38 mm, respectively. This parameter optimization work provides precise guidance for the design of battery thermal management systems, contributing to enhanced heat dissipation performance. To further enhance the intelligence of battery thermal management, this study introduced a novel neural network model based on Temporal Convolutional Networks (TCN) and Bidirectional Long Short-Term Memory (BiLSTM) with Multi-Head Attention (MHA). This model is capable of predicting temperature changes during the battery discharge process in real-time with high accuracy. Based on the prediction results, this research designed an efficient control strategy that, compared to a scenario without a control strategy, demonstrated a reduction in energy consumption by 20.87 %, a decrease in maximum temperature by 2.52 K, and a reduction in the maximum temperature difference by 0.05 K. These results not only prove the effectiveness of the control strategy but also provide a new direction for the optimization of battery thermal management systems.

Energy management strategy of integrated adaptive fuzzy power system in fuel cell vehicles

Fuel cell vehicles are a reliable solution to address energy shortages. However, when the road conditions are complex, the system distributes power unevenly between fuel cells and lithium batteries, and cannot effectively absorb the energy generated by braking. In response to this issue, an adaptive control strategy is adopted to allocate the required power of the car to two types of batteries in real time. Fuzzy logic is used to continuously optimize the relevant parameters of the controller based on the vehicle state, and a multi-island genetic algorithm is used to optimize the control strategy, enhancing the global search ability of the control strategy and increasing the vehicle’s ability to absorb and reuse the energy generated by braking. The experiment findings denote that the optimized control strategy increases the remaining capacity of lithium batteries by an average of 1.67%, increases energy recovery by an average of 135 W, increases the overall energy recovery rate by an average of 2.8%, and reduces vehicle fuel consumption by an average of 0.24 L/100 Km. It can be concluded that the optimized adaptive fuzzy control strategy can reduce the probability of over-charging and discharging of lithium batteries and improve the battery life. Meanwhile, the optimized strategy can improve the energy reuse rate, reduce vehicle fuel consumption, lower usage costs. The optimized strategy provides a reference for subsequent research on energy management of fuel cell vehicles.

Sulfur/reduced graphite oxide and dual-anion solid polymer‒electrolyte integrated structure for high-loading practical all-solid-state lithium–sulfur batteries

The demand for high-capacity batteries with long cycle life and safety has been increasing owing to the expanding mid-to-large battery market. Li–S batteries are suitable energy-storage devices because of their reversibility, high theoretical capacity, and inexpensive construction materials. However, their performance is limited by various factors, including the shuttle effect and dendrite growth at the anode. Here, an integrated electrode for use in all-solid-state (ASS) Li–S batteries was formed via hot pressing. In detail, S particles dispersed in a functionalized reduced graphite oxide (rGO) cathode with a binder-less polymer electrolyte (PE) and a dual-anion ionic liquid-containing cross-linked poly(ethylene oxide)–Li bis(fluoromethanesulfonyl)imide–N-butyl-N-methylpyrrolidinium bis(trifluoromethanesulfonyl) imide-based solid polymer electrolyte (SPE, PEO–LiFSI0.1(Pyr14TFSI)0.4) were hot-pressed into an integrated electrode, which serves as both the cathode and electrolyte. The resulting S/rGO-based solid-state Li–S batteries exhibited more stable performance than Li–S batteries using liquid electrolytes did, indicating that the dual-anion SPE layer effectively suppressed dendritic Li formation and the shuttle effect with high ionic conductivity. At 0.1 C, the battery discharge capacities were 957 and 576 mAh g−1 in the first cycle and after 100 cycles, respectively. At 1 C, the reversible capacity was 590 and 417 mAh g−1 in the first cycle and after 100 cycles, respectively (capacity retention = 71%). Therefore, the proposed S/rGO/PE//LiFSI0.1(Pyr14TFSI)0.4-integrated electrodes are beneficial for ASS Li–S batteries.

Battery temperature estimation at wide C-rates using the LSTM model based on polarization characteristics

Data-driven based approaches have achieved significant results in estimating battery temperature. Nevertheless, the present challenge emanates from the dearth of theoretical guidance governing the training strategy of the model, leading to an inefficient training process and constrained accuracy, especially under specific conditions. In this paper, a Long Short-Term Memory (LSTM) neural network based on polarization characteristics is proposed to estimate the battery discharge temperature. Firstly, the LSTM temperature estimation model is established and the hyperparameters are optimized by Genetic Algorithm (GA). The results show that the accuracy of the traditional model is less satisfactory, with the Maximum Error (ME) of 3.79 °C. Subsequently, the voltage and polarization heat production characteristics of the battery are analyzed under various discharge conditions. It is found that the heat production of the battery is smaller at 0–1.5C, and the heat production characteristics are similar at medium-rate, but the change of heat production is significant when C-rate exceeds 3C. Finally, a LSTM temperature estimation model based on polarization characteristics is proposed, which divides the datasets according to heat production characteristics. Further, a strategy for predicting temperatures in later stages based on limited data from the current condition is also proposed, this mothed combines with the transfer learning method to rapidly develop models for different high-rate conditions. The ME of the model on the test set is 1.1 °C, and the training time is reduced by 32.93 s. The results show that the LSTM temperature estimation model based on polarization characteristics has higher accuracy and training efficiency than the traditional LSTM temperature estimation model.

Optimizing the economic dispatch of weakly-connected mini-grids under uncertainty using joint chance constraints

AbstractIn this paper, we deal with a renewable-powered mini-grid, connected to an unreliable main grid, in a Joint Chance Constrained (JCC) programming setting. In several rural areas in Africa with low energy access rates, grid-connected mini-grid system operators contend with four different types of uncertainties: forecasting errors of solar power and load; frequency and outages duration from the main-grid. These uncertainties pose new challenges to the classical power system’s operation tasks. Three alternatives to the JCC problem are presented. In particular, we present an Individual Chance Constraint (ICC), Expected-Value Model (EVM) and a so called regular model that ignores outages and forecasting uncertainties. The JCC model has the capability to guarantee a high probability of meeting the local demand throughout an outage event by keeping appropriate reserves for Diesel generation and battery discharge. In contrast, the easier to handle ICC model guarantees such probability only individually for different time steps, resulting in a much less robust dispatch. The even simpler EVM focuses solely on average values of random variables. We illustrate the four models through a comparison of outcomes attained from a real mini-grid in Lake Victoria, Tanzania. The results show the dispatch modifications for battery and Diesel reserve planning, with the JCC model providing the most robust results, albeit with a small increase in costs.

The application of Co3S4@NCNT/NCHS with excellent bifunctional catalytic activity in aqueous and flexible Zn-air batteries

In this work, we prepared a hybrid structure Co3S4@NCNT/NCHS using SiO2 nanospheres as a template. The structure is supported by hollow carbon spheres (NCHS), which are coated by Co3S4 nanoparticles and cross-linked N-doped carbon nanotubes. The combination of Co3S4 with N-doped carbon material significantly improves the electrocatalytic activity. In addition, the presence of N-doped carbon nanotubes induces more defects, which can regulate the electronic configuration of the material and improve its electrical conductivity. Therefore, Co3S4@NCNT/NCHS has good catalytic performance. At 10 mA cm−2, the OER overpotential of Co3S4@NCNT/NCHS is only 230 mV, which is lower than that of the commercial catalyst RuO2, and the ORR half-wave potential can reach 0.80 V. In the battery discharge test, Co3S4@NCNT/NCHS based ZABs can discharge continuously for 71.5 h, the specific capacity of 790.12 mA h g−1, power density of 113.09 m W cm−2, better than Pt/C+RuO2 battery. When the current density is 3 mA cm−2, ZABs assembled with Co3S4@NCNT/NCHS as catalyst can maintain a voltage gap of 0.62 V to 0.63 V within 300 h without significant change. When the current density is increased to 5 mA cm−2, ZABs based on Co3S4@NCNT/NCHS can be stably cycled for 300 h at a voltage gap between 0.80 V and 0.82 V.

Passivation of the positive electrode during the discharge of Li-O2 and O2-assisted Li-CO2 batteries: A comparative study

The effect of passivation of the positive electrode by solid products under discharge is assessed for the first time as one of the factors determining the discharge characteristics of Li-O2 (LOB) and oxygen-assisted Li-CO2 (LCOB) batteries. In order to estimate the passivation, the electrode surface coverage θ by the reaction product (Li2O2 or Li2CO3) is determined on the basis of a decrease in the double-layer capacitance value in the course of the discharge. It is shown that for a given amount of electricity, the electrode surface coverage by Li2CO3 in LCOB is 1.5–2 times that of the coverage by Li2O2 under discharge in LOB. Furthermore, for each of the batteries, achievement of the maximum discharge capacity does not result in the full electrode surface blocking by the discharge products. LCOB manifests higher discharge characteristics than LOB under the kinetic reaction control (in the 100–500 mA g−1 current density range), owing to the accelerated conversion of intermediates and slower solid reaction product deposition on a larger electrode surface area. As the current density increases from 500 to 2000 mA g−1, the discharge capacity of LOB and LCOB decreases, which is mainly due to the effect of diffusion limitations. Moreover, while in the case of LOB the parameter θ decreases, in the case of LCOB it is practically independent of the current density in the studied range. The latter effect may be due to increased passivating properties of Li2CO3 deposits formed under high current density. The results of the work allow considering θ as a new criterion for estimation of the discharge depth and for predicting the characteristics of LCOB and LOB.

Energy management optimization of hybrid electric vehicles based on deep learning model predictive control

In this paper, the hybrid electric vehicle (HEV) energy management optimization method is proposed based on deep learning (DL) model predictive control. Through empirical research combined with the questionnaire survey, this article not only provides a new perspective and practical basis but also improves the efficiency and accuracy of the model by improving the relevant algorithms. The study first analyzes the importance of HEV energy management and reviews the existing literature. Then, the optimization method of HEV energy management based on the deep learning model is introduced in detail, including the composition of energy management for hybrid electric vehicles, the structure and working principle of the deep learning model, especially the backpropagation neural network (BPNN) and the convolutional neural network (CNN), and the steps of application of deep learning in energy management. In the experimental part, questionnaire data from 1,500 consumers were used to design the HEV energy management optimization scheme, and consumers’ attitudes and preferences towards HEV energy optimization were discussed. The experimental results show that the proposed model can predict HEV energy consumption under different road conditions (urban roads, highways, mountain areas, suburban areas, and construction sites), and the difference between the average predicted energy consumption and the actual energy consumption is between 0.1KWH and 0.3KWH, showing high prediction accuracy. In addition, the deep learning-based energy management strategy outperforms traditional control strategies in terms of fuel consumption (6.2 L/100 km), battery charge and discharge times (814), battery life, and CO2 emissions, significantly improving the efficiency of HEV energy. These results demonstrate the great potential and practical application value of deep learning models in the optimization of energy management of HEVs, helping to drive the development of more sustainable and efficient transportation systems.