Deep Neural Networks Based Approach for Battery Life Prediction

The Internet of Things(IoT)and related applications have witnessed enormous growth since its inception.The diversity of connecting devices and relevant applications have enabled the use of IoT devices in every domain.Although the applicability of these applications are predominant,battery life remains to be a major challenge for IoT devices,wherein unreliability and shortened life would make an IoT application completely useless.In this work,an optimized deep neural networks based model is used to predict the battery life of the IoT systems.The present study uses the Chicago Park Beach dataset collected from the publicly available data repository for the experimentation of the proposed methodology.The dataset is pre-processed using the attribute mean technique eliminating the missing values and then One-Hot encoding technique is implemented to convert it to numerical format.This processed data is normalized using the Standard Scaler technique.Moth Flame Optimization(MFO)Algorithm is then implemented for selecting the optimal features in the dataset.These optimal features are finally fed into the DNN model and the results generated are evaluated against the stateof-the-art models,which justify the superiority of the proposed MFO-DNN model.

Investigating explainable transfer learning for battery lifetime prediction under state transitions

Battery lifetime prediction at early cycles is crucial for researchers and manufacturers to examine product quality and promote technology development.Machine learning has been widely utilized to construct data-driven solutions for high-accuracy predictions.However,the internal mechanisms of batteries are sensitive to many factors,such as charging/discharging protocols,manufacturing/storage conditions,and usage patterns.These factors will induce state transitions,thereby decreasing the prediction accuracy of data-driven approaches.Transfer learning is a promising technique that overcomes this difficulty and achieves accurate predictions by jointly utilizing information from various sources.Hence,we develop two transfer learning methods,Bayesian Model Fusion and Weighted Orthogonal Matching Pursuit,to strategically combine prior knowledge with limited information from the target dataset to achieve superior prediction performance.From our results,our transfer learning methods reduce root-mean-squared error by 41%through adapting to the target domain.Furthermore,the transfer learning strategies identify the variations of impactful features across different sets of batteries and therefore disentangle the battery degradation mechanisms and the root cause of state transitions from the perspective of data mining.These findings suggest that the transfer learning strategies proposed in our work are capable of acquiring knowledge across multiple data sources for solving specialized issues.

Towards Long Lifetime Battery:AI-Based Manufacturing and Management

Technologies that accelerate the delivery of reliable battery-based energy storage will not only contribute to decarbonization such as transportation electrification,smart grid,but also strengthen the battery supply chain.As battery inevitably ages with time,losing its capacity to store charge and deliver it efficiently.This directly affects battery safety and efficiency,making related health management necessary.Recent advancements in automation science and engineering raised interest in AI-based solutions to prolong battery lifetime from both manufacturing and management perspectives.This paper aims at presenting a critical review of the state-of-the-art AI-based manufacturing and management strategies towards long lifetime battery.First,AI-based battery manufacturing and smart battery to benefit battery health are showcased.Then the most adopted AI solutions for battery life diagnostic including state-of-health estimation and ageing prediction are reviewed with a discussion of their advantages and drawbacks.Efforts through designing suitable AI solutions to enhance battery longevity are also presented.Finally,the main challenges involved and potential strategies in this field are suggested.This work will inform insights into the feasible,advanced AI for the health-conscious manufacturing,control and optimization of battery on different technology readiness levels.

Hybrid firefly algorithm-neural network for battery remaining useful life estimation

Accurately estimating the remaining useful life(RUL)of batteries is crucial for optimizing maintenance,preventing failures,and enhancing reliability,thereby saving costs and resources.This study introduces a hybrid approach for estimating the RUL of a battery based on the firefly algorithm–neural network(FA–NN)model,in which the FA is employed as an optimizer to fine-tune the network weights and hidden layer biases in the NN.The performance of the FA–NN is comprehensively compared against two hybrid models,namely the harmony search algorithm(HSA)–NN and cultural algorithm(CA)–NN,as well as a single model,namely the autoregressive integrated moving average(ARIMA).The comparative analysis is based mean absolute error(MAE)and root mean squared error(RMSE).Findings reveal that the FA–NN outperforms the HSA–NN,CA–NN,and ARIMA in both employed metrics,demonstrating su-perior predictive capabilities for estimating the RUL of a battery.Specifically,the FA–NN achieved a MAE of 2.5371 and a RMSE of 2.9488 compared with the HSA–NN with a MAE of 22.0583 and RMSE of 34.5154,the CA–NN with a MAE of 9.1189 and RMSE of 22.4646,and the ARIMA with a MAE of 494.6275 and RMSE of 584.3098.Additionally,the FA–NN exhibits significantly smaller maximum errors at 34.3737 compared with the HSA–NN at 490.3125,the CA–NN at 827.0163,and the ARIMA at 1.16e+03,further emphasizing its robust performance in minimizing prediction inaccuracies.This study offers important insights into battery health management,showing that the proposed method is a promising solution for precise RUL predictions.

Risk-based Two-stage Optimal Scheduling of Energy Storage System with Second-life Battery Units

With the growing adoption of Electrical Vehicles(EVs),it is expected that a large number of on-board Li-ion batteries will be retired from EVs in the near future.Retired batteries will typically retain 80%of their initial capacities and can be recycled as second life batteries(SLBs).Although the capital costs of SLBs are much cheaper,their operational reliability is an important concern since used batteries may suffer from a higher failure rate.This paper aggregates brand new batteries and SLBs together to improve power system’s operating performance with renewable energy resources.In the context of a day-ahead and intra-day dispatch framework,a two-stage coordinated optimal scheduling method is proposed.Specifically,the energy cost of brand-new batteries and SLBs is calculated based on detailed battery degradation model,and the reliability of batteries is modeled based on the Weibull distribution.Moreover,Conditional value at risk(CVaR)criterion is applied to evaluate the risk induced by intermittent renewable power output,load demand variation and SLBs failure probability.Simulation tests demonstrate the effectiveness of the proposed method.

Looping of Hybrid PV/Wind Turbine Power Plants by a Compressed Air Storage System and Creation of Artificial Wind to Ensure the Permanent Availability of Energy in the Tropical Zones

In general, the energy storage in facilities to intermittent sources is provided by a battery of accumulators. Having found that the duration of life of chemical accumulators is strongly shortened in the northern regions of Cameroon and that this has a considerable impact on the operating costs and the reliability of power plants to intermittent sources, this work proposes to find an alternative to these chemical accumulators rendered vulnerable by the high temperatures. It reviews all energy storage techniques and makes a choice （the CAES （compressed air energy storage）） based on thermal robustness. It proposes a new technique of restitution of the energy by producing an artificial wind from the compressed air. The feedback loop thus obtained by the compressor-tank-wind subsystem is studied from a series of manipulations and its efficiency is determined. To automate the operation of this system, a controller is required. The operating logic of the controller is provided in function of the precise states of the load, the tank and the natural sources.

Microstructural evolution in lithium plating process and its effect on the calendar storage life

The growing demand for electric vehicles highlights the need for energy storage solutions with higher densities,spotlighting Li metal anodes as potential successors to traditional Li-ion batteries(LIBs).Achieving longer calendar aging life for Li metal anodes is crucial for their practical use,given their propensity for corrosion due to a low redox potential,which leads to compromised cycling stability and significant capacity loss during storage.Recent research investigated that this susceptibility is mainly dependent on the surface area of Li metal anode and the properties of the solid electrolyte interphase(SEI),particularly its stability and growth rate.Our research adds to this understanding by demonstrating that the amount of Li plating is a key factor in its corrosion during open-circuit storage,as assessed across various electrolytes.We discovered that increasing the Li plating amount effectively reduces Coulombic efficiency(C.E.)loss during aging,due to a lower surface area-to-Li ratio.This implies that the choice of electrolyte for optimal storage life should consider the amount of Li plating,with higher capacities promoting better storage characteristics.

Universal organic anodes enable safe low-cost aqueous rechargeable batteries with long cycle life,high capacity, and fast kinetics

Future battery advances and economies of scale will help scrub CO2emissions from transportation and the grid.Economical energy storage lets battery-powered electric vehicles replace internal combustion engines in the transportation sector,which now accounts for the plurality of CO2emissions.For grid-scale applications,the benefits of adding storage are many and well documented[1–2].Beyond increased penetration of intermittent renewable energy generated from such as solar panels

GREENSKY:A fair energy-aware optimization model for UAVs in next-generation wireless networks

Unmanned Aerial Vehicles(UAVs)offer a strategic solution to address the increasing demand for cellular connectivity in rural,remote,and disaster-hit regions lacking traditional infrastructure.However,UAVs’limited onboard energy storage necessitates optimized,energy-efficient communication strategies and intelligent energy expenditure to maximize productivity.This work proposes a novel joint optimization model to coordinate charging operations across multiple UAVs functioning as aerial base stations.The model optimizes charging station assignments and trajectories to maximize UAV flight time and minimize overall energy expenditure.By leveraging both static ground base stations and mobile supercharging stations for opportunistic charging while considering battery chemistry constraints,the mixed integer linear programming approach reduces energy usage by 9.1%versus conventional greedy heuristics.The key results provide insights into separating charging strategies based on UAV mobility patterns,fully utilizing all available infrastructure through balanced distribution,and strategically leveraging existing base stations before deploying dedicated charging assets.Compared to myopic localized decisions,the globally optimized solution extends battery life and enhances productivity.Overall,this work marks a significant advance in UAV energy management by consolidating multiple improvements within a unified coordination framework focused on joint charging optimization across UAV fleets.The model lays a critical foundation for energy-efficient aerial network deployments to serve the connectivity needs of the future.

A multi-objective power flow optimization control strategy for a power split plug-in hybrid electric vehicle using game theory

Power flow optimization control,which governs the energy flow among engine,battery,and motor,plays a very important role in plug-in hybrid electric vehicles(PHEVs).Its performance directly affects the fuel economy of PHEVs.For the purpose of improving fuel economy,the electric system including battery and motor will be frequently scheduled,which would affect battery life.Therefore,a multi-objective optimization mechanism taking fuel economy and battery life into account is necessary,which is also a research focus in field of hybrid vehicles.Motivated by this issue,this paper proposes a multi-objective power flow optimization control strategy for a power split PHEV using game theory.Firstly,since the demand power of driver which is necessary for the power flow optimization control,cannot be known in advance,the demand power of driver can be modelled using a Markov chain to obtain predicted demand power.Secondly,based on the predicted demand power,the multi-objective optimization control problem is transformed into a game problem.A novel non-cooperative game model between engine and battery is established,and the benefit function with fuel economy and battery life as the optimization objective is proposed.Thirdly,under the premise of satisfying various constraints,the participants of the above game maximize their own benefit function to obtain the Nash equilibrium,which comprises of optimal power split scheme.Finally,the proposed strategy is verified compared with two baseline strategies,and results show that the proposed strategy can reduce equivalent fuel consumption by about 15%compared with baseline strategy 1,and achieve similar fuel economy while greatly extend battery life simultaneously compared with baseline strategy 2.

Overcharge to Remove Cathode Passivation Layer for Reviving Failed Li–O_(2)Batteries

Prolonging the lifetime of batteries is a long-term pursuit,and it is also one of the prerequisites for the practical application of batteries.However,this endeavor is challenging for high-energy Li–O_(2)batteries due to their poor charge efficiency and cathode passivation-induced by-products accumulation.Here,we demonstrated that overcharging Li–O_(2)batteries could facilitate the decomposition of accumulated residue products and revive the cathode;thus,the battery lifespan could be significantly extended.This long battery lifetime not only made full use of the Li anode but also enabled the battery to recycle in a safer way without the risk of firing and explosion.Furthermore,overcharge could be used in Li–O_(2)batteries with high mass loading,high rate,and large capacity.This overcharge strategy simplified the cathode regenerating procedures and realized system-level efficient use of battery components,thereby prolonging the life of Li–O_(2)batteries to meet the requirements of practical applications.