Claims:1. A method of managing an electric vehicle battery includes determining a management condition associated with the electric vehicle battery's state of charge (SOC), collecting SOC information from an electric vehicle terminal, and determining if the SOC information meets the predetermined SOC management condition. The method also includes performing battery management based on the determination result.
2. Claim 1, wherein the predetermining comprises any of the following elements: The management condition is determined by presenting the user equipment with at least one SOC option, receiving a selection of the at least one SOC option from the user equipment, and determining a SOC management condition for the chosen SOC option.
3. According to claim 2, the user’s driving behavior and battery management pattern are used to decide at least one SOC choice.
4. In claim 3, the battery management pattern is identified based on a previous SOC management history.
5. The technique of claim 1, wherein the management condition is within the SOC's permissible range.
, Description:The current invention offers particular systems, techniques, and algorithms based on AI expert system technology (EVs) to determine preferable routes of travel for electric cars.
DISCUSSION OF THE PRIOR ART:
Several projects have been launched to make electric vehicles (EVs) more readily available for a wide range of transportation needs to combat the rising dependence on fossil fuels. Considerations include the development and deployment of electric vehicle (EV) automobile drive trains and EV-specific battery and charging technologies, as well as the influence that greater usage of EVs will have on power production and distribution. The management of EV traffic flow on roads and highways is an additional factor to consider to maintain acceptable levels of automobile transportation performance as the use of EVs grows.
It's predicted that in 2025, the number of people driving electric vehicles (EVs) will surpass 3700,000 globally, including 575,000 people in the United States. Nissan LEAF and Chevrolet Volt are commercially available electric vehicles. Reducing pollution from fossil fuel vehicles is one of the main objectives of EV initiatives. You'll save money, help the environment, and have a more enjoyable driving experience with EVs.

Reduced operational range is the price to be paid for these benefits. EVs driven only by batteries have a claimed range of up to 100 miles, according to reports. For a battery range of roughly 10 miles, plug-in hybrid electric cars may switch to a regular internal combustion engine. A 50-mile battery range is standard for extended-range electric cars, incorporating a generator powered by an internal combustion engine. Consider T. Denton's "Electric and Hybrid Vehicles" from Routledge, which was published in 2016.
"Range anxiety" is a term that refers to the worry about having a restricted driving range. Drivers are worried that they won't have enough fuel to go to their final destination or even to and from work every day.
Currently, lithium-ion batteries are the most popular choice for electric vehicles (EVs). Many consumer electronic gadgets use lithium-ion batteries, such as mobile phones, laptop computers, and tablets. System control technology that assures safe operation and mechanical design is required for automobile application because of the harsh environment. Heating and cooling systems must be designed with the required temperature ranges in mind. Check out the source above as well as, for example, T Horiba's "Lithium-Ion Battery Systems," IEEE Proceeding, June 2014, pages 939-950.

Recharging or replacing the car batteries will be necessary to increase the driving range of EVs. It's a complex issue with many variables, and there are several different approaches to pricing. The majority of electric vehicles (EVs) are recharged at home. In addition, businesses may provide charging stations for their staff and/or customers. Another option being studied and, in some instances, adopted is the installation of public charging stations along highways. The most common charging technique is AC charging. Chargers may be single-phase AC, three-phase AC, or greater power DC. Low-power single-phase AC systems have a 100-km range charging time of 6-8 hours. Three-phase AC systems with more power may charge in the same amount of time (20-30 minutes). As little as 10 minutes is possible with high-power DC systems. The IEC has standardized a variety of charging cable designs (International Electrotechnical Commission). A good place to start is T. Denton's book "Electric and Hybrid Vehicles," published by Routledge in 2016.
Electric vehicle battery charging might also make use of Wireless Power Transfer (WPT) (WPT). Static WPT, which is used while the vehicle is parked, and dynamic WPT, used on highways when the car is moving, are both options. There is no need for wiring between the car and WPT's charging system since it uses magnetic induction. The main coil of a fixed or roadside vehicle is connected to the secondary coil of a stationary or moving vehicle to perform charging. In addition, N. Shinohara, "Wireless Power Transfer through Radio Waves," John Wiley and Sons, 2014, and V. Prasanth, et al. "Green Energy based Inductive Self-Healing Highways of the Future," IEEE Transportation and Electrification Conference and Expo (ITEC), 2016 are cited in the study.
Autonomous vehicles, often known as driverless automobiles, are a significant advancement in vehicular mobility. Autonomous or self-driving vehicles can sense their surroundings and navigate with little or no human input. To sense the road, barriers, traffic control signals, signs, and other vehicles may have to share the road with a driverless automobile. Even though autonomous cars are just now being deployed, experts expect their use will increase shortly. To avoid more problematic roads or congestion that might offer tough or more demanding sensory challenges for the car, drivers of EV autonomous vehicles may have to make specific considerations while planning their travel itineraries. Routes that are suitable for cars with drivers may not be suitable for cars without drivers. Driverless cars may also use the present invention's systems and techniques, as long as the databases and navigation algorithms used in the vehicles are acceptable for driverless ones.
Improved systems and methods to manage the charging of electric vehicles have led to various technological suggestions for the allocation and placement of charging stations, integration with navigation systems, the use of Wireless Power Transfer (WPT), and mathematical modeling of system operation design and use. Examples of prior art systems and techniques that aim to meet some of these requirements, in addition to those listed above, include the following:
Electric Vehicle Charging Station Allocation: Optimization Model and Application to a Dense Urban Network, IEEE Intelligent Transportation Systems Magazine, Fall 2014, p. 1 (in French). For example, in the metropolitan region of Lyon, France, maximizing the placement of electric car charging stations is an important issue. As inputs to an integer linear optimization algorithm for the position of charging stations, the model incorporates trip OD miles, vehicle energy consumption, and routing tools with elevation information parameters.
IEEE Transactions on Vehicular Technology, 2015, Jyun-Yan Yang et al., "Electric Vehicle Navigation System Based on Power Consumption." To address the increased complexity of navigation systems, the authors claim in this study to present an electric vehicle navigation system (EVNS) with an architecture based on autonomous computation and a hierarchical structure. While on the road, the electric car transmits traffic data to the traffic information center (TIC) or makes a navigation request. The TIC analyses and arranges traffic routes based on the data collected. A proposed path is sent to the electric car, and it acts as a navigation tool. Navigation systems give traffic data, such as the current state of charge (SOC), traffic flow, average speed, journey duration, and the route taken by the vehicle in question.
"Optimal Routing of Electric Vehicles in Networks with Charging Nodes: A Dynamic Programming Approach," 2014 IEEE Electronic Vehicle Conference, Sepideh Pourazarm et al. This study claims to attempt to reduce the overall time taken for cars to reach their destinations by taking into account travel time as well as time spent recharging at nodes while using a dynamic programming method.
Green Energy-based Inductive Self-Healing Highways of the Future by Venugopal Prasanth et al., IEEE Transportation Electrification Conference and Expo (ITEC), 2016. Using Inductive Power Transfer (IPT) to recharge electric cars is the subject of this study. The usage of renewable energy sources such as solar and wind is also explored.
Plug-in Hybrid Electric Vehicle Supervisory Control Strategy Based on Energy Demand Prediction and Route Preview, F. Tianheng et al., IEEE Transactions on Vehicle Technology, May 2015, pp. 1691-1700 5. According to the authors, a supervisory control technique for plug-in hybrid electric cars based on energy demand prediction and route preview is reportedly presented in this study. The energy demand of the vehicle is predicted using a neural network, and an adaptive equivalent consumption reduction technique is utilized to efficiently divide energy between the engine and the motor to obtain the best possible torque split...
A strategy to employ an onboard navigation system for electric and hybrid vehicle energy management was disclosed in US Patent 6,487,477 by J T Woestman et al. on November 26, 2002. It was assigned to Ford Global Technologies, Inc. This invention claims to incorporate a navigation system onboard an electric vehicle (EV) or a hybrid electric vehicle to enable energy management (HEV). The car's position is constantly tracked, driver demand expectations are identified, and vehicle accommodations are provided. For example, it's possible to customize the system to incorporate data on traffic patterns and weather and date and time, altitude, and speed restrictions for drivers. According to the manufacturer, discrete control rules, fuzzy logic, and neural networks are among the possible configurations for the vehicle's accommodations.
Patent 9,103,686 in the United States To guide battery-operated vehicles to reconditioning stations, B. Pettersson devised a method and guidance unit. On August 11, 2015, LEICA GEOSYSTEMS AG was assigned. To guide a mobile transportation device to one of several reconditioning stations, this Patent claims methods and apparatus for locating the battery, determining the battery's condition, forecasting the transportation device's consumption, and assessing the mobility of the transportation device. The method and apparatus are then assigned to the particular reconditioning station. When using a search algorithm to allocate transportation means to reconditioning stations and batteries, the algorithm optimises both the assignment and the route based on existing and predicted information on many elements of the transportation means, stations, and batteries.
Along with "search engine," the Patent #686 also states: "For optimization, some situations and aspects may be included by using abstracted mathematical models of the underlaying physical or logical background, which can be included in lookup tables, statistical or projected data. They may be global, overall models of resource behaviour or subsystem models, such as a single battery or engine in a transportation vehicle. These models can be global, overall models of resource behaviour. A knowledgeable worker is familiar with a variety of modelling methodologies, such as physical models, differential equations, Fuzzy-Logic models, logical models, statistics models, forecasting models, and so on." See the '686 Patent, pp. 47-58 for further information.
"Communication and control about power supplier for wireless electric vehicle electrical energy transmission," R. A. Hyde et al., U.S. Pat. No. 9,199,548, Owner—Elwha LLC, as of December 1, 2015. An electric vehicle wireless electrical energy charger is described in this Patent as a computationally implemented system and method for electronically assessing electricity provider detail information associated with the provision of electrical energy to one or more electric vehicles wireless electrical energy chargers configured for wirelessly charging the one or more electric vehicles.
US Patent No. 9,333,873, "Electric vehicle management system," by K. Mori and colleagues On May 10, 2016, Mitsubishi Electric Corporation was designated as the Assignee. An electric motor vehicle management system with a portable terminal owned by a user and installed in an electric motor vehicle is described in this Patent. The portable terminal transmits vehicle condition information of the electric motor vehicle, including position information of the portable terminal, to an energy management system (EMS) installed in a customer. An EMS charging and discharging plan creation unit uses vehicle condition information to produce an electric motor vehicle battery charging and discharging plans. According to the battery charging-and-discharging strategy at least one of charging and discharging the electric vehicle battery is performed by a charging and discharging device.
9,335,179 United States Patent Electric car data systems to permit charging station access, by A. Penilla et al. The date is Tuesday, May 10, 2016. An electric vehicle with a rechargeable battery is described in this Patent as having an interfacing cloud system. There is also a wireless communication system connected to the onboard computer in the electric car. The onboard computer is set up to monitor the battery's charge level and show it on the electric car's dashboard display screen. With the use of global positioning system (GPS) technology, the electric car can pinpoint its exact location. The cloud system is set up to keep track of an electric vehicle's user account and to store data related to that account. The data contains the user's input about charge settings. The electric vehicle's onboard computer may communicate with the cloud by using a wireless communication network to connect the cloud system. Depending on the geolocation of the electric car and the received data about the battery charge level of the electric vehicle and the user's charging settings, the cloud system is programmed to provide one or more alternatives of charging stations to the electric vehicle. The charging stations offered as alternatives are situated along a route that can be reached before the electric car's battery is completely depleted.
While the present invention is described herein by example using embodiments and illustrative drawings, those skilled in the art will recognize that the invention is not limited to the images of drawing or drawings described and are not intended to represent the various scale components. Further, some features that may form a part of the invention may not be illustrated in specific figures for ease of illustration. Such omissions do not limit the embodiments outlined in any way. It should be understood that the drawings and detailed descriptions are not intended to limit the invention to the particular form disclosed. Still, on the contrary, the story is to cover all modifications, equivalents, and alternatives falling within the scope of the present invention as defined by the appended claims. As used throughout
In this description, the word "may" is used in a permissive sense (i.e., meaning having the potential to) rather than the mandatory reason (i.e., meaning must).
Further, the words "a" or "an" mean "at least one," and the word "plurality" means "one or more" unless otherwise mentioned. Furthermore, the terminology and phraseology used herein are solely for descriptive purposes and should not be construed as limiting in scope. Language such as "including," "comprising," "having," "containing," or "involving," and variations thereof, is intended to be broad and encompass the subject matter listed after that, equivalents, and additional subject matter not recited, and is not intended to exclude other additives, components, integers or steps. Likewise, the term "comprising" is considered synonymous with the words "including" or "containing" for applicable legal purposes. Any discussion of documents, materials, devices, articles, and the like are included in the specification solely to provide a context for the present invention. It is not suggested or represented that any or all of these matters form part of the prior art base or were common general knowledge in the field relevant to the present invention.
In this disclosure, whenever a composition or an element or a group of elements is preceded with the transitional phrase "comprising," it is understood that we also contemplate the same design, component or group of elements with transitional words "consisting of," "consisting," "selected from the group of consisting of, "including," or "is" preceding the recitation of the composition, element or group of elements and vice versa.
The present invention is described from various embodiments concerning the accompanying drawings, wherein reference numerals used in the accompanying drawing correspond to the like elements throughout the description. However, this invention may be embodied in many different forms and should not be construed as limited to the embodiment set forth herein. Instead, the image is provided so that this disclosure will be thorough and complete and fully convey the invention's scope to those skilled in the art. The following detailed description provides numeric values and ranges for various aspects of the implementations described. These values and ranges are treated as examples only and are not intended to limit the claims' scope. Also, several materials are identified as suitable for various facets of the implementations. These materials are to be treated as exemplary and are not intended to limit the invention's scope.
SUMMARY OF THE PRESENT INVENTION:
Electric cars and grid-scale energy storage are only two of the many uses for batteries in our low-carbon future. It's still a significant struggle to get the most life and efficiency out of these gadgets. There is a definite possibility for more intelligent control of battery systems now that battery performance/lifetime, diagnostic procedures, and machine learning methodologies have advanced recently. Nowadays, physics-based modelling techniques predominate over empirical connections when it comes to these types of systems. Physics-based models offer several benefits, such as the ability to estimate anode potentials for rapid charging methods, but real-world implementation issues are beginning to show themselves. To do this, you'll have to take apart a lot of the cell, which will amplify any intrinsic cell-to-cell variance you could find when the battery wears down.
Thanks to diagnostic tools, many scientific research have used a mix of spectroscopic, physical, and electrochemical methodologies to increase our present knowledge of battery performance. However, low-cost onboard approaches that now use voltage, current, and temperature measurements are becoming more important for real-world and in-operando deployment of diagnostic procedures. Electrochemical insights into the system may be gained by analysing them in a variety of ways. Additionally, new data formats like stress and strain can enhance onboard diagnostics' capabilities beyond these measurements. Additionally, methodologies like EIS and hence DRT analysis are becoming more affordable. To be successful, the fusion of diverse data kinds must be done with adequate regard for well-designed data recording and curation.
ML-based techniques have increased interest because of the abundance of data and lack of assurance in forecasting actual battery performance in the real world. Several of these techniques have shown substantial promise in well-controlled lab circumstances in linking important aspects of batteries' charge/discharge profiles with capacity loss. Although these technologies are becoming more widely used, data production is still a problem. Consequently, hybrid and surrogate models have been developed, which use multi-physics and multiple scale models' predictive capability while still being computationally cheap. By combining these models with ANNs, we may get quicker model predictions while maintaining high order physics, optimizing crucial features like rapid charging procedures in a closed-loop fashion. The merging of diverse data kinds with techniques such as k-mean closest neighbours and SVMs will likely boost accuracy and open up new application areas as this variety of diagnostics continues to evolve.
Models, data, and machine learning (ML) and Artificial intelligence(AI) techniques are the building blocks of battery digital twins because they allow for intimate interaction between the physical and digital counterparts of the same thing. Because of these factors, the potential for longer-lasting battery systems is unlocked by combining numerous data sets with hybrid models. However, with this new developing profession come multidisciplinary difficulties around data curation, data sharing, and the security of these systems.
Battery scientists and engineers now have more digital and networked instruments at their disposal. This is a game-changer for battery systems in the future, allowing them to operate in new ways. Even though this article covers some of the most up-to-date thinking on several aspects of the integrated digital world, much work remains to be done. There are different online attempts to develop community, where tools such as online webinars, Twitter, and Slack for exchanging ideas and solving issues are major facilitators
Battery digital twins will play an important part in future battery technology developments across many applications. However, there are still considerable obstacles, and hence possibilities, to be overcome. To summarise. The following are only a few examples:
• Wider usage in academia and industry of transparent and standardized testing/data processing techniques for parameterization and diagnostics.
• Standards-based, transferable techniques for database administration and data storage.
• Multi-scale physics models encapsulating nano-scale impacts on macroscopic metrics are being developed to construct surrogate models to help with high quality digital data production.
• It's time to create hybrid models that combine physics with data to be more accurate in the actual world.
• Lifetime estimate using a combination of data/hybrid models based on deeper electrochemical understanding and novel sensing techniques.
• ML and AI techniques, data preprocessing, and data selection for successful curation are all essential.
• Cyber-physical systems with low latency that allow for real-time adaptation in control.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENT AND FURTHER OPTIONAL FEATURES OF THE INVENTION:
A more particular description will be rendered by referencing specific embodiments illustrated in the appended drawings to clarify various aspects of some example embodiments of the present invention. It is appreciated that these drawings depict only illustrated embodiments of the story and are therefore not considered limiting its scope. The design will be described and explained with additional specificity and detail through the accompanying drawings.
So that the advantages of the present invention will be readily understood, a detailed description of the story is discussed below in conjunction with the appended drawings, which, however, should not be considered to limit the scope of the invention to the accompanying drawing.
Further, another user interface can also be used with the relevant modification to provide the results above with the same modules, its principal, and protocols for the present invention.
It is to be understood that the above description is intended to be illustrative and not restrictive. For example, the above-discussed embodiments may be used in combination with each other. Many other embodiments will be apparent to those of skill in the art upon reviewing the above description.
The benefits and advantages which the present invention may provide have been described above about specific embodiments. These benefits and advantages and any elements or limitations that may cause them to occur or become more pronounced are not construed as critical, required, or essential features of any or all of the embodiments.
While the present invention has been described concerning particular embodiments, it should be understood that the images are illustrative and that the invention's scope is not limited to these embodiments. Many variations, modifications, additions, and improvements to the embodiments described above are possible. It is contemplated that these variations, changes, additions, and improvements fall within the invention's scope.
Real-world applications suffer from diminished prediction accuracy when physics-based techniques are used because of the intrinsic unpredictability of cells. This is an issue that must be addressed. Computers can now learn from data and enhance their performance without human programming thanks to machine learning, which makes them excellent for coping with battery fluctuation. There have long been data-driven methods in the battery industry that use techniques like artificial neural networks (ANN). Still, it wasn't until recently that improved processing power and an availability of data combined to stimulate a renewed interest in these approaches. As well as ANNs and SVM, other methods such as random forests and KF-based approaches have been used to predict states such as SOC, SOH, and RUL, and they have been effectively summarised by Ng et al. and Li et al. in their respective studies.
Utilizing differential voltage data for LFP-Gr cells cycled under rapid charging patterns, Severson et al. showed how a simple linear regression model could predict RUL with a 9.1% accuracy using the first 100 cycles using a basic data-driven methodology RUL estimation in batteries. Several other researchers, such as Li et al., have shown a linear relationship between the SOH of cells and particular peak positions in the ICA spectra. Partial charge curves may be used to estimate SOH by monitoring selected peaks, reducing the gap between lab-based research and real-world implementation. However, caution should be used when estimating RUL with linear models since battery capacity fading might accelerate under high usage circumstances. Fermin-Cueto et al. addressed this issue by demonstrating how a Bacon-Watts model and an SVM might be used to identify knee-points when deterioration rates rise.
RUL estimate using voltage and capacity data is quite promising; nevertheless, it is possible to combine these basic regression techniques with deeper electrochemical insights, models that capture additional deterioration mechanisms, and data types that are more diversified to synthesize them. According to Hu et al., a data-driven method to RUL estimate using five battery charging variables was presented. Feature weights were determined by combining a k-nearest neighbors approach with a particle swarm optimization with the following parameters: beginning charge voltage, constant current charge capacity, constant voltage charge capacity, and final charge voltage and current. The use of k-means closest neighbors, in particular, demonstrates the future possibility of synthesizing various diagnostic data sources for more accurate RUL assessment.
When used in conjunction with a closed-loop optimization approach, these RUL estimation methods become even more potent. For example, Attia et al. [58] employed an elastic net regression-trained linear model to forecast the ultimate battery lifespan of LFP-Gr batteries based on the first 100 cycles of charging. It was possible to greatly minimize the number of trials required by combining this machine learning-driven RUL estimate with a Bayesian and closed-loop optimization technique. This reduced the time it took to study 244 various charging strategies from 500 days to 16 days, demonstrating the potential of ML to speed up the creation of improved battery functionality.

Other writers have recommended using EIS spectra as a SOH indication in addition to differential voltage measurements as an RUL indicator. For example, Zhang et al. demonstrated that reliable RUL predictions might be accomplished by integrating the whole EIS spectrum with Gaussian process regression and an autonomous relevance decision approach. Two frequencies were found: 17 Hz and 2 Hz. While this was considered a signal for deteriorating interfacial qualities, it is unclear why these frequencies would be such an effective predictor for deterioration. When dealing with real-world challenges, the quality of the EIS data is also a vital factor to consider. A Bayesian framework was used to reformulate the key EIS criteria, and metrics were created to measure how well the data complies with the restrictions of its derivation, notably linearity, time-invariance, and causation. EIS and hence DRT measurements will be more trustworthy as a result of this, which will allow for real-world application in noisy environments with poor measuring circumstances.
Researchers are suggesting a whole-system approach to recording crucial data from material production all the way through automotive applications, in addition to simply vehicle-level data logging. For example, Yang et al. proposed the cyber hierarchy and interactional network (CHAIN) framework, which proposes uploading key physical and electrochemical parameters of a cell during manufacturing to a cloud-based server to perform closed-loop optimization for full battery system lifespan management. Using the CHAIN architecture, a large, complicated system may be broken into smaller, more manageable pieces. The following is an example of multi-scale mapping: When researchers can avoid time-consuming trials by using digital models across the lifetime and length-scale points, they may boost resource efficiency, shorten development timeframes and improve flexibility.
To construct a succession of required models that can be swiftly trained, sensor data is wirelessly and seamlessly uploaded to servers, where they can be conveniently accessible for manufacturing, design, and optimization advice. It is possible to quickly upgrade current assets and provide insights into future goods because of the real-time nature of this data recording.
Using various estimating techniques from cloud-based servers, an end-to-end strategy collecting states from materials, cell production, automotive usage, and second life applications may be accomplished, allowing for a closed-loop cycle to be applied back to raw materials. It is possible to upload and exchange data from each step of the cycle on the cloud servers for data analysis to give insights across stages. Assessing various recycled battery materials' quality, for example, may influence both their first and second lives, as well as their future performance.
Computation will occur in three places: on-board end applications, at the edge, and in the cloud. This future smart system will be multi-scale in nature. It will become more difficult to deploy these frameworks while optimizing data flows over the network and providing adequate data security.

Battery digital twins play a transformational function in the multi-scale design and intelligent management system of battery systems as a multidisciplinary physical system. We can continually update the suggested complicated physical battery digital system with new information from physics data, both known and unknown. As a result of the emergence of essential Cloud computing technologies, such as virtualization and service-oriented architectures, improved digital twins and the resulting energy effect will become a reality sooner rather than later.
This might lead to more accurate performance modeling, but several difficulties need to be addressed first. Other researchers, such as Yang et al. and Rasheed et al., have shed light on some of the issues with digital twins. Multi-physics models are needed, as are nano/micro scale characterizations, future communication networks with low latency, the significance of good data preprocessing leading to computationally efficient algorithms, and better data security for wide adoption of these techniques.
As a result, battery lifespan estimates and control have shifted from a purely empirical approach to one that relies on models. As computing capacity has improved, data-driven and machine-learning (ML) techniques have experienced a comeback, but real-world applicability issues persist. A suggested combined hybrid model/data strategy is shown in Figure 1 and utilizes real-time data gathering from an IoT-enabled device to create a digital battery twin.