Powering electric vehicles

Abstract

A power supply system utilizes a hybrid architecture to extend the range of traction batteries with low cycle life, high energy density chemistries for use in rechargeable batteries.

Description

[0001] Cross-references to related applications

[0002] This application claims priority to U.S. Application 63 / 089,990, filed October 9, 2020, and U.S. Application 63 / 161,822, filed March 16, 2021, which are incorporated herein by reference in their entirety. Technical Field

[0003] The present invention generally relates to systems, methods, and computer programs for supplying power to electric vehicles, and more specifically, to systems, methods, and computer programs for operating power supply systems for electric vehicles via high-energy-density batteries configured to extend the range of traction batteries.

[0004] The present invention also relates to a method, system, and computer program product for intelligently determining the output power levels obtained from the individual batteries of a hybrid architecture to achieve mileage or distance targets, while maintaining or maximizing the advantages offered by the hybrid architecture, including ensuring safety, maximizing battery life, and maximizing battery capacity in electric vehicles. Background Technology

[0005] The power supply systems used in electric vehicles typically employ a single battery pack or multiple battery packs connected in series. These batteries are usually rechargeable and are typically lithium-ion batteries.

[0006] Lithium-ion batteries are widely used in electric vehicles and as storage devices for green energy (without environmental pollution) due to their high output voltage, good cycle performance, low self-discharge rate, fast charging and discharging, and high charging efficiency.

[0007] Traditional battery parameter updates rely on the Battery Management System (BMS). The main functions of the BMS include: monitoring data points such as battery voltage, current, and temperature; estimating battery SOC (State of Charge), SOH (State of Health), SOE (State of Energy), SOP (State of Operation), and RM (Remaining Range); performing operational diagnostics; protecting battery health; and performing battery balancing management and battery thermal management.

[0008] To more accurately measure battery parameters, conventional technical solutions typically pre-store OCV (Open Circuit Voltage)-SOC curves to check the estimated battery SOC. A BMS (Battery Management System) can upload some data to a cloud backup, allowing manufacturers or after-sales personnel to retrieve data for fault analysis and battery history information.

[0009] Maintaining precise SOC balance and balancing battery characteristics between battery cells and battery packs / modules is typically difficult. Old and new batteries, batteries of different capacities, or battery packs with different characteristics cannot be used together; a failure in one cell or pack can cause the entire battery system to fail. These problems reduce efficiency and range, and significantly increase the production and selection costs of battery systems.

[0010] Another common problem in the development of battery technology involves the trade-off between energy density, the number of battery cycles available during the battery's lifespan, and battery performance. Currently, there is no known technology that provides a battery solution or energy storage solution with favorable energy density, high performance, and a large number of cycles (the number of times a battery can be charged and discharged during its lifespan). Attached Figure Description

[0011] To facilitate identification of any particular element or action discussed, one or more of the most effective numbers in the reference numerals refer to the figure number in which the element is first introduced. Certain novel characteristics of the power supply system, considered to be features, are outlined in the appended claims. However, the power supply system itself, as well as preferred modes of use, other non-limiting purposes, and advantages thereof, will be best understood by referring to the following detailed description of illustrative embodiments, in conjunction with the accompanying drawings:

[0012] Figure 1 A block diagram depicts a power supply system that can implement the illustrative embodiments.

[0013] Figure 2 A block diagram depicts a computer system that can implement illustrative embodiments.

[0014] Figure 3 A sketch depicting an electric vehicle according to an illustrative embodiment.

[0015] Figure 4A A diagram depicting an illustrative embodiment.

[0016] Figure 4B Another diagram depicting an illustrative embodiment.

[0017] Figure 5A A sketch depicting a power supply system according to an illustrative embodiment.

[0018] Figure 5B A graph depicting the charge and discharge curves according to an illustrative embodiment.

[0019] Figure 6 Another sketch depicting a power supply system according to an illustrative embodiment.

[0020] Figure 7Another block diagram depicting a power supply system and vehicle chassis according to an illustrative embodiment.

[0021] Figure 8 A block diagram depicting a power supply system according to an illustrative embodiment.

[0022] Figure 9 A flowchart depicts an example process for operating a power supply system that can implement illustrative embodiments.

[0023] Figure 10 A block diagram depicts a network that can implement the illustrative embodiments of the data processing system.

[0024] Figure 11 A block diagram depicts a data processing system that can implement illustrative embodiments.

[0025] Figure 12 The configuration for intelligent power output recommendations is described according to an illustrative embodiment.

[0026] Figure 13 A block diagram depicting an example configuration for training a machine learning model according to an illustrative embodiment.

[0027] Figure 14 A flowchart depicting an example process according to an illustrative embodiment.

[0028] Figure 15 A block diagram depicting an example priority order of attributes according to an illustrative embodiment. Detailed Implementation

[0029] The illustrative embodiments acknowledge that currently available solutions do not fully address or provide adequate solutions to the problems discussed above. Electric vehicles typically rely on a single battery to power them. This limits the vehicle's range to chemistry that only meets cycle life, durability, and mileage requirements, often meaning that the chemistry must be limited. Many chemistry can have higher energy densities than conventional chemistry used in electric vehicle batteries (e.g., two to three times the energy density of conventional chemistry), but with insufficient cycle life. Considering the need for range extension in electric vehicles, these chemistry can be utilized, when properly managed, to significantly extend the range beyond conventional capabilities.

[0030] The illustrative embodiments recognize that most conventional cells in a rechargeable battery are connected in parallel, thereby eliminating the control of input and output currents through the battery. The illustrative embodiments also recognize that when individual cells of the rechargeable battery fail, it is difficult to maintain battery integrity and performance because battery termination is accelerated due to the inability to detect and / or mitigate the failure in a timely manner. Furthermore, in some configurations, when one cell fails, the entire battery may become unusable. The illustrative embodiments further recognize that conventional batteries do not utilize high-energy-density chemistry due to high cycle life requirements.

[0031] For clarity of description, and without implying any limitation thereof, some example configurations are used to describe illustrative embodiments. According to the present invention, those skilled in the art will be able to conceive of many changes, adaptations, and modifications to the described configurations for achieving the described objectives, and to contemplate such changes, adaptations, and modifications within the scope of the illustrative embodiments.

[0032] Furthermore, simplified diagrams of the system are used in the accompanying drawings and illustrative embodiments. In a real computing environment, additional structures or components not shown or described herein, or structures or components different from those shown but used for similar functions as described herein, may exist without departing from the scope of the illustrative embodiments.

[0033] Furthermore, illustrative embodiments with respect to specific actual or hypothetical components are described merely as examples. The steps described by the various illustrative embodiments can be adapted for use in power supply systems for electric vehicles, which utilize various components that can be used or reused to provide the described operations, and such adaptation is contemplated within the scope of the illustrative embodiments.

[0034] These illustrative embodiments are described merely as examples of certain types of steps, applications, processors, problems, and data processing environments. Any particular manifestation of these and other similar techniques is not intended to limit the invention. Any suitable manifestation of these and other similar techniques may be chosen within the scope of the illustrative embodiments.

[0035] The examples in this invention are for illustrative purposes only and are not intended to limit the scope of the illustrative embodiments. Any advantages listed herein are merely examples and are not intended to be limited to the illustrative embodiments. Specific illustrative embodiments may achieve additional or different advantages. Furthermore, a particular illustrative embodiment may have some, all, or none of the advantages described above.

[0036] The illustrative embodiments described herein relate to a power supply system 100 for an electric vehicle. Power supply system 100 ( Figure 1The battery systems disclosed herein are configured to include low-cycle-life, high-energy-density chemistry in a hybrid architecture to realize the benefits of such chemistry (including a significant increase in range) while protecting the architecture from the adverse effects of the chemistry, preventing reliance on the chemistry in other ways in the automotive field. The battery systems disclosed herein may be referred to as “hybrid” systems because they comprise multiple chemistry compounds working together. Alternatively, to distinguish them from “hybrid” vehicles that use both electric and internal combustion power sources, the battery systems, vehicles, and related systems and components disclosed herein may be referred to as “range-extending multi-chemistry battery systems.”

[0037] The power supply system 100 disclosed herein may include a traction battery 102 (including, for example, lithium iron phosphate (LFP)) and a hybrid range extender battery 124. The hybrid range extender battery 124 includes one or more high-energy-density hybrid modules 112 having one or more hybrid chemistry and being controllable to provide power to charge the traction battery 102 and / or power the electric vehicle. One or more embodiments recognize that problems in rechargeable battery manufacturing necessitate providing electric vehicles with batteries having high energy density, which increases the range of electric vehicles capable of long-distance driving beyond conventional mileage, while taking into account the correspondingly low cycle life introduced by said high energy density.

[0038] One or more embodiments include one or more processors 106 (or processor 120, computer processor 206) that are contained in or outside the vehicle-mounted or external computer system 126 (or computer system 200). Figure 2 The traction battery can monitor and determine the limits of discharge and charge. The inverter can manage the power flow, and the hybrid module controller can manage its own charging / discharging via a DC / DC converter. In one or more embodiments, the vehicle 302 ( Figure 3 The vehicle is configured as an electric vehicle (EV). In one or more embodiments, vehicle 302 is configured as a plug-in hybrid electric vehicle (PHEV). The term electric vehicle is used hereinafter for all vehicles, such as motorized vehicles, rail vehicles, ships, and aircraft, which are configured to use rechargeable batteries as their primary energy source to power their drive system or have an all-electric powertrain.

[0039] Furthermore, as used herein, a sensor can be a sensor device that is: a system, device, software, hardware, executable instruction set, interface, software application, transducer, and / or the aforementioned combinations of one or more sensors for indicating, responding to, detecting, and / or measuring physical properties and generating data about the physical properties.

[0040] In addition, battery energy density is often used as a measure of the proportion of energy contained in a battery cell to its volume.

[0041] Furthermore, as used herein, a high energy density module generally refers to a module having battery cells with an energy density of about 1000 Wh / L or greater (e.g., an energy density of 1100 Wh / L or 1200 Wh / L). Those skilled in the art will recognize that, Figure 4B As shown, conventional battery chemistry with automotive performance levels has a cell energy density below or significantly below 1000 Wh / L (e.g., between approximately 350 Wh / L and 500 Wh / L) measured at the cell level. Using high-energy-density chemistry in the hybrid range extender battery 124 can ensure that it provides two or three times more energy than, for example, the energy provided by the traction battery 102.

[0042] In one or more embodiments, the power supply system 100 includes a traction battery 102 having one or more traction modules 122, a hybrid range extender battery 124 having one or more high-energy-density hybrid modules 112, and a partition between the traction battery 102 and the hybrid range extender battery 124.

[0043] Each module can be a battery pack. Those skilled in the art will understand that other types of battery devices can be used to provide power in the embodiments described herein, and therefore, statements regarding certain configurations are not intended to be limiting. Figure 1The battery management system (BMS) 104 discussed herein can use, for example, the onboard computer system 126 to control the relay 108 and report operational limitations. It can also request power from one or more hybrid modules to meet the vehicle's needs. The hybrid module controller of the hybrid range extender battery 124 can control its contribution to the high-voltage DC bus based on its own internal objectives (such as objectives defined by one or more preset or dynamically determined rules), state of energy, observed state of energy of the traction battery, and driving behavior, without centralized coordination from the BMS. Therefore, the power supply system 100 can operate in a more efficient and energy-saving mode to increase the operating range of the vehicle 302 or prevent module degradation caused by a single faulty battery cell. For example, during a journey, one or more embodiments described herein include the onboard computer system 126, which estimates the power requirements for navigation to the destination and determines whether the vehicle 302 can safely reach its destination using the stored energy available for operation. If the computer system 126 determines that the vehicle cannot reach the intended destination, the hybrid range extender battery 124 can be used to charge the traction battery 102 to provide sufficient power for the journey.

[0044] In one or more embodiments, the high energy density mixing module 112 is configured to have a single chemical, while in one or more other embodiments, the high energy density mixing module 112 is configured to have multiple chemicals (e.g., three chemicals for daily, weekly, and monthly use).

[0045] In an illustrative embodiment, the traction battery 102 includes a single traction module 122 or multiple traction modules 122 connected in series. In another illustrative embodiment, the hybrid range extender battery 124 has multiple high-energy-density hybrid modules 112 connected in parallel with each other and also in parallel with the traction battery 102, allowing each high-energy-density hybrid module 112 to manage its contribution to charging the traction battery 102 or powering the vehicle 302, wherein a hybrid module controller 118 for each high-energy-density hybrid module 112 includes a bidirectional DC-DC converter. More generally, the negative terminal is connected, and the positive output of the bidirectional DC-DC converter is also connected.

[0046] In one or more embodiments, the batteries that can be used in the hybrid range extender battery 124 described herein to provide power to the vehicle 302 or to charge the traction battery 102 include batteries with battery cells 114 having a cell energy density greater than 1000 Wh / L.

[0047] Battery systems in electric vehicles are typically traction batteries, consisting of hundreds of battery cells packaged together. These systems are rated at voltages such as 300V to 400V, supply currents up to approximately 300A (e.g., 200 to 300A), and any mismanagement can lead to a major disaster. Therefore, a battery management system (BMS) is essential for the safe operation of high-voltage batteries in electric vehicles. A BMS can be configured to monitor the battery's condition and prevent overcharging and discharging that could reduce battery life, capacity, or even cause explosions. For example, the BMS checks the voltage and stops charging when the required voltage is reached. When irregular patterns in the power flow are detected, the BMS can shut down the battery and issue an alarm. Furthermore, the BMS can be configured to relay information about battery conditions to the energy and power management system. Additionally, the BMS can regulate the temperature of the battery cells and the overall health of the battery, ensuring its safety and reliability under all conditions.

[0048] One feature of a Battery Management System (BMS) is its ability to estimate the state of charge (SOC) of the battery pack. This is desirable, or in some cases, crucial, for efficiently maintaining the SOC to ensure that the battery voltage is not too high or too low. For example, in some situations, a battery should not be charged beyond 100% or discharged to 0%, as this will reduce the capacity of the battery cells. A BMS can provide precise information about the battery's voltage and temperature, as well as indications of usable energy and remaining battery charge.

[0049] In some embodiments, the State of Charge (SOC) can be estimated. Furthermore, in coulomb-counting processing, the currents flowing into and out of the battery are integrated to produce a relative value of its charge. However, in conventional systems, it can often be difficult to accurately determine the SOC and other characteristics of individual batteries connected in parallel.

[0050] Therefore, the illustrative embodiments recognize that conventional BMS cannot accurately measure the individual characteristics of battery cells in a battery pack. Conventional solutions attempt to obtain estimates, but there is no method to control the current of a battery cell to measure the corresponding characteristic parameters of the battery cell, such as voltage.

[0051] Return to Figure 1The traction battery 102 may include one or more traction modules 122 configured to power the vehicle 302. The hybrid range extender battery 124 is designed to be modular, having one or more types of chemistry different from that of the traction battery 102, to provide varying power requirements to the vehicle as needed. As a specific example, the traction battery may have an LFP chemical, and the hybrid range extender battery 124 may have a Gr (graphite) or Gr+SS (graphite + solid) chemical. Regardless of the specific chemistry used, the hybrid range extender battery 124 may be designed to have one or more high-energy-density hybrid modules 112 or packages configured with corresponding DC-DC converters to function as independent batteries. The charging and discharging rates of the battery cells 114 can be adjusted by being able to independently control the high-energy-density hybrid modules 112 and independently measure the health or state of their individual battery cells 114. In an embodiment, the battery cells 114 of the high-energy-density hybrid module 112 are arranged in series. By using a balancing device 128 (such as a bleeder resistor) connected in parallel with each battery cell 114, the charging or discharging rate of the battery cell 114 can be controlled; that is, the bleeder resistor for the battery cell is turned on to discharge the charge stored in that battery cell. In an illustrative embodiment, the bleeder resistor can be enabled to generate an additional discharge current of up to several hundred (200) mA, thereby fine-tuning the charging / discharging current of the battery cell and allowing the battery cells in the string to be brought to a common state. Furthermore, one or more sensors 116 are used to measure voltage and determine how long the bleeder resistor should remain enabled to achieve a balanced state among all battery cells in the battery cell string.

[0052] The rate at which a battery discharges relative to its maximum capacity is its C-rate. For example, a 1C rate means that the discharge current will discharge the entire battery in one hour. Typically, vehicles require a 4C peak and a 1C average. By utilizing bidirectional DC-DC converters to individually control the high-energy-density hybrid modules 112, rates of C / 5 (i.e., 0.2C) or lower can be achieved. This prevents malfunctions associated with high-energy-density chemistry due to overcharging and discharging. More specifically, the traction battery 102 can follow the load demands of the vehicle and provide peak current. The high-energy-density hybrid modules 112 can use their bidirectional DC-DC converters to discharge the traction battery and the vehicle's HV bus to which the powertrain is connected. In an illustrative embodiment with five high-energy-density hybrid modules 112, each hybrid module contributes C / 5, and their combined contribution is 1C. If the vehicle requires 4C, the traction battery is discharged at 3C. If the vehicle requires 1C, the traction battery 102 is at rest (0C). If the vehicle requires -1C (regenerative braking), the traction battery is recharged at 2C. In an embodiment, each high-energy-density hybrid module 112 also has a hybrid module controller 118 operatively coupled to measure the health or state of the battery cells 114. For example, the hybrid module controller 118 may be configured to measure the voltage, current, temperature, SOC (state of charge), and SOH (state of health) of all battery cells in the respective high-energy-density hybrid module 112. The hybrid module controller 118 also has DC-DC converter control to allow for the management of isolation and current and to limit their contribution to absorb energy and supply power to the main bus / high-voltage DC bus of the power supply system 100. The system may also have a BMS 104 configured to primarily communicate with the traction battery 102. In the event of a failure of the traction battery 102, one or more of the high-energy-density hybrid modules 112 may act as a replacement (e.g., a temporary replacement) for the traction battery 102 by directly powering the drive unit 110. In many configurations, one or more processors (processor 120, processor 106, or the processor of computer system 126) are used to enable one or more processes or operations described herein. Relay 108 is controlled to operably couple the drive unit 110 of the vehicle to power from the power supply system 100. The drive unit 110 may be collectively referred to as a device external to the power supply system 100, such as a propulsion motor, inverter, HVAC (heating, ventilation, and air conditioning) system, etc.

[0053] After describing the power supply system 100, reference will now be made to... Figure 2 , Figure 2A block diagram of a computer system 200 that may be employed according to at least some of the illustrative embodiments described herein is shown. Although various embodiments may be described with respect to this example computer system 200, it may become apparent to those skilled in the art, after reading this description, how to implement the invention using other computer systems and / or architectures.

[0054] In the example embodiments described herein, computer system 200 is formed. Figure 1 Part of or independent of computer system 126 Figure 1 The computer system 126. Furthermore, at least some components of the power supply system 100 can be formed. Figure 2 Computer system 200 or included Figure 2 The computer system 200 includes at least one computer processor 206. Processors 106 and 120 of the power supply system 100 may be or form part of the computer processor 206, or may be independent of the computer processor 206. The computer processor 206 may include, for example, a central processing unit (CPU), multiple processing units, an application-specific integrated circuit (“ASIC”), a field-programmable gate array (“FPGA”), etc. The computer processor 206 may be connected to a communication infrastructure (e.g., a network) 202 (e.g., a communication bus, network). In the illustrative embodiments herein, the computer processor 206 includes a CPU for controlling the operation of the power supply system 100, including controlling the state of the bidirectional DC-DC converter between the high-energy-density hybrid module 112 and the traction battery 102 or drive unit 110 of the electric vehicle 302.

[0055] Display interface 208 (or other output interface) can forward text, video graphics, and other data related to the power supply system 100 from communication infrastructure (e.g., network) 202 or from a frame buffer (not shown) for display on display unit 214, which may be the display of electric vehicle 302. For example, display interface 208 may include a video card with a graphics processing unit, or it may provide an interface to an operator for controlling the power supply system 100.

[0056] The computer system 200 may also include an input unit 210 that can be used by an operator of the computer system 200 in conjunction with the display unit 214 to send information to the computer processor 206. The input unit 210 may include a keyboard and / or a touchscreen monitor. In one example, the display unit 214, the input unit 210, and the computer processor 206 may collectively form a user interface.

[0057] One or more computer-implemented steps for operating the power supply system 100 can be stored on a non-transitory storage device in the form of computer-readable program instructions. To execute the process, the computer processor 206 loads the appropriate instructions stored on the storage device into memory and then executes the loaded instructions.

[0058] Computer system 200 may further include main memory 204 and secondary storage 218, whereby main memory 204 may be random access memory (“RAM”). Secondary storage 218 may include, for example, hard disk drive 220 and / or removable storage drive 222 (e.g., floppy disk drive, magnetic tape drive, optical disk drive, and flash memory drive, etc.). Removable storage drive 222 reads from and / or writes to removable storage unit 226 in a known manner. Removable storage unit 226 may be, for example, a floppy disk, magnetic tape, optical disk, and flash memory device, and may be written to and read from by removable storage drive 222. Removable storage unit 226 may include a non-transitory computer-readable storage medium for storing computer-executable software instructions and / or data.

[0059] In a further illustrative embodiment, secondary storage 218 may include other computer-readable media for storing a computer-executable program or other instructions to be loaded into computer system 200. Such an arrangement may include: removable storage unit 228 and interface 224 (e.g., program cartridge and cartridge interface); removable memory chip (e.g., erasable programmable read-only memory (“EPROM” or programmable read-only memory (“PROM”)) and associated memory socket; and other removable storage units 228 and interfaces 224 that allow software and data to be transferred from removable storage unit 228 to other parts of computer system 200.

[0060] Computer system 200 may also include a communication interface 212 that enables the transfer of software and data between computer system 200 and external devices. Such an interface may include a modem, a network interface (e.g., an Ethernet card or an IEEE 802.11 wireless LAN interface), or a communication port (e.g., a USB port). Ports), PCMCIA (Personal Computer Memory Card International Association) interface, and (Bluetooth), etc. Software and data transmitted via communication interface 212 may be in the form of signals, which may be electronic, electromagnetic, optical, or other types of signals that can be sent and / or received by communication interface 212. Signals may be provided to communication interface 212 via communication path 216 (e.g., a channel). Communication path 216 carries signals and may be implemented using wired or cable, fiber optic, telephone line, cellular link, or radio frequency (“RF”) link, etc. Communication interface 212 may be used to transmit software or data or other information between computer system 200 and a remote server or cloud-based storage (not shown).

[0061] One or more computer programs or computer control logic may be stored in main memory 204 and / or secondary memory 218. Computer programs may also be received via communication interface 212. The computer programs include computer-executable instructions that, when executed by computer processor 206, cause computer system 200 to perform the methods described below. Therefore, the computer programs can control computer system 200 and other components of power supply system 100.

[0062] In another embodiment, the software may be stored in a non-transitory computer-readable storage medium and loaded into main memory 204 and / or secondary storage 218 using a removable storage drive 222, a hard disk drive 220, and / or a communication interface 212. When the control logic (software) is executed by the computer processor 206, the control logic (software) causes the computer system 200, and more generally the power supply system 100, to perform some or all of the methods described herein.

[0063] Finally, in another example, hardware components such as ASICs and FPGAs can be used to perform the functions described herein. Given this description, it will be apparent to those skilled in the art (one or more) of the relevant fields that implementing such a hardware arrangement to perform the functions described herein is feasible.

[0064] Figure 4A A graph is shown according to an illustrative embodiment. This graph shows a driving day percentage axis 402 and a daily driving distance axis 404 as disclosed herein in the example embodiment. By measuring a user's driving habits, it can be seen that a considerable percentage of driving days are spent driving relatively short distances, and thus utilizing the traction battery 102 as shown by the traction battery portion 406 of the graph. On the other hand, the hybrid range extender portion 408 is used for a relatively much shorter amount of time. Then, as... Figure 4B As shown, range extenders with chemicals providing energy densities of 1000 Wh / L or greater can offer a good trade-off between density and cycle life. This can be achieved by determining the percentage of cycles falling outside of daily use and selecting appropriate chemicals capable of sustaining those numerous cycles. Figure 4A Illustrative embodiments.

[0065] Figure 4B The graph includes an energy density axis 410 and a cycle life axis 412. As used herein, a battery's "cycle life" refers to the number of times a battery can be depleted to 100% depth of discharge (DoD) while still retaining at least 80% of its original charge. Thus, for example, a battery with a cycle life of 100 cycles will retain 80% of its original charge after being charged and fully depleted 100 times.

[0066] The traction battery chemical can be selected from traction battery chemical region 414 to provide a cycle life of approximately 3,000 cycles (e.g., at least 2,500 or 3,000 cycles). In conventional battery chemistry, this cycle life typically provides a corresponding cell energy density of approximately 400 Wh / L. To accommodate predetermined mileage requirements for non-traction applications, a range-extender battery chemical can be selected from illustrative hybrid range extender battery chemical region 418 (e.g., between 1,000 and 1,200 Wh / L). This typically provides a corresponding cycle life of approximately 200 cycles (e.g., between 200 and 350 cycles) or less. Depending on the energy requirements of the vehicle, other chemicals 416 can optionally be used in appropriate packages for medium-range requirements and independent control.

[0067] More generally, the embodiments disclosed herein can utilize multiple battery chemistry compounds in a power supply system, each with different desired cycle life and / or cell energy density. This allows for the use of battery chemistry compounds and arrangements conventionally considered unsuitable for electric vehicles and similar devices. For example, conventional systems often assume that a higher cycle life is required even with higher energy density consumption. In contrast, the embodiments disclosed herein can utilize higher density chemistry compounds even where the associated batteries may have relatively low cycle life, because the cell of a range extender or mid-range battery may not undergo charge / discharge cycles as frequently as conventionally used traction batteries.

[0068] As a specific example, the hybrid power supply system disclosed herein may include a traction battery having a cell energy density of no more than about 500 Wh / L, 450 Wh / L, 400 Wh / L, 350 Wh / L, 300 Wh / L or less, more generally in the range of 300 to 500 Wh / L, but having a relatively high cycle life of 2000 cycles, 2500 cycles, 3000 cycles or more, more generally in the range of 2000 to 3200 cycles.

[0069] High-density battery cells used in range extender batteries or intermediate batteries as disclosed herein can have relatively high cell energy densities of 800 Wh / L, 1000 Wh / L, 1100 Wh / L, 1200 Wh / L or greater than 1200 Wh / L, or in the range of 800 to 1400 Wh / L, and relatively low expected cycle lives of 300, 400 or 500 cycles or less, or in the range of 100 to 500 cycles or less. Other battery types and chemistry can be used, particularly in embodiments using more than two chemistry. For example, Figure 4B Any battery type shown between the medium traction region 414 and the range extension region 418 can be used for a medium-density battery, which can have a cycle life in the range of 1,000 to 2,000 cycles and an energy density in the range of 500 to 800 Wh / L.

[0070] The graph of interest for battery chemistry used with the embodiments disclosed herein is the energy density per cycle (EDC), which is determined as the ratio of the battery's cell energy density to its expected cycle life. For example, as Figure 4B As shown, the HE traction battery can have a cell energy density of approximately 400 Wh / L and a cycle life of 3000 cycles, resulting in an EDC of approximately 0.13 Wh / L / cycle. In contrast, Figure 4B The solid-state battery in range extension region 418 can have an energy density of approximately 1000 Wh / L and a cycle life of approximately 400 cycles, resulting in an EDC of approximately 2.5 Wh / L / cycle. Conventional battery chemistry with an EDC of 1.0 or greater has previously been considered unsuitable for use in electric vehicles due to its relatively low cycle life. As previously disclosed, the embodiments provided herein allow for the efficient use of such batteries in electric vehicles when used in conjunction with other chemistry.

[0071] As a specific example, the embodiments disclosed herein may use a traction battery with an EDC of approximately 0.12 to 0.16 Wh / L / cycle and a range extender battery with an EDC of 1.0 or greater, 2.0 or greater than 2.0, 5.0 or greater than 5.0, or any value in between. Other chemistry may also be used; for example, in the case of using three chemistry compounds, the traction battery may have an EDC of 0.12 to 0.16 Wh / L / cycle, and the other batteries in the system may have an EDC between that of the traction battery and that of the highest-density battery, wherein the highest-density battery has an EDC of 1 Wh / L / cycle or greater.

[0072] More generally, any number of battery chemistry can be used with “daily” traction batteries with lower EDC and more special-purpose battery chemistry with higher EDC values. As another example, a single battery chemical in daily use traction zone 414 can be used with any number of batteries in range extension zone 418 and / or... Figure 4B Any number of batteries within any intermediate range shown may be used in combination. For example, a third battery chemical may be used in combination with previously disclosed traction and range extender batteries, wherein the third chemical has a battery cell energy density of 400 to 1200, 1300 or 1400 Wh / L or greater than 1400 Wh / L.

[0073] Figure 5A An illustrative embodiment of a power supply system 100 is shown. The system includes a traction battery 102, multiple high-energy-density hybrid modules 112 connected in parallel with the main traction bus / high-voltage DC bus, multiple traction modules 122, and multiple bidirectional DC-DC converters 502. Furthermore, the system has an onboard AC-DC charger 504 for recharging the power system from the grid, a 12V battery 512 for powering the vehicle's lights and ignition, and an auxiliary DC-DC converter 506 for maintaining the 12V battery 512 and supplying power to the vehicle's 12V system. This embodiment also includes contactors 508 for switching various circuits on or off and a control module 510 for controlling the power supply. By placing the 12V battery 512 within the power supply system (within the traction battery 102) rather than externally as in conventional systems, the contactor 508 can be controlled, for example, to remain closed, even if other transient problems occur with the 12V system. In the illustrative embodiment, a transient loss of battery power (e.g., approximately 100 ms or longer) may cause the contactor to open. This loss could be caused by a single faulty wire outside the battery pack. This risk can be mitigated by introducing 12V into the battery pack.

[0074] In such Figure 5AIn the illustrated embodiment, each high-energy-density hybrid module 112 has approximately 56 battery cells 114 connected in series. The specific number of battery cells is illustrative, and other numbers of battery cells may be used without departing from the scope of the invention. An operationally coupled hybrid module controller 118 (such as an on-board hybrid module controller 118, etc.) is configured to measure the voltage, current, temperature, SOC, and SOH of each battery cell 114. Each of the 56 battery cells 114 may have an associated voltage sensor 116. Knowing the current and temperature passing through the battery cell 114 (such as the temperature of various points on the high-energy-density hybrid module 112, etc.), the SOH, SOC, and other parameters of the battery cell 114 can be calculated to determine whether the energy output of the corresponding high-energy-density hybrid module 112 can be connected to the traction battery 102 via a corresponding bidirectional DC-DC converter 502 or, in some cases, to the drive unit 110. Furthermore, a bidirectional DC-DC converter 502 for each high-energy-density hybrid module 112 can be used to precisely control the current input and output for each high-energy-density hybrid module 112, unlike the loads of conventional power supplies which offer no control over changes in drive power. In the illustrative embodiment, charging and discharging pulses are generated for the high-energy-density hybrid module 112. By controlling the current of the series-connected battery cells 114 of the high-energy-density hybrid module 112 using the bidirectional DC-DC converter 502 and measuring the voltage of each battery cell 114, the impedance of each battery cell 114 can be calculated and compared with reference data to identify any unwanted deviations in the battery cell impedance and corresponding changes in battery cell health.

[0075] The current input to each high-energy-density hybrid module 112 can come from the charger after the traction battery has been charged or substantially charged. For maintenance and / or diagnostic purposes, the hybrid modules can be discharged and recharged when not strictly required to function as a range extender. For example, if several months have passed since the hybrid module has been used as a range extender, it may be discharged and recharged during normal daily use to train the battery cells. The frequency of discharge and recharge of the range extender battery outside of normal use, or even whether such discharge / charge is performed, can be selected based on one or more specific chemistry used in the range extender battery.

[0076] The hybrid module controller 118 can also manage the strain on the battery cells 114 by monitoring and aligning them. For example, when it is determined that one battery cell 114 (cell A) is at a lower SOC (e.g., 20%) than another battery cell 114 (cell B) (70%) connected in series, cell B will reach full charge earlier than cell A, and therefore charging of cell B needs to be stopped to prevent overcharging. By using a shunt resistor to reduce the SOC of cell B to that of cell A, both cells can be charged to a predetermined full charge at the same rate. Therefore, the hybrid module controller 118 keeps the SOCs of the 56 battery cells 114 equal or substantially equal (e.g., within + / -10%, + / -5%, or + / -1%), allowing the full range of the module to be used. In another example, by identifying battery cells 114 with a lower self-discharge rate than other battery cells 114, the hybrid module controller 118 determines which battery cells 114 selectively discharge to a defined charge in order to subsequently charge all 56 battery cells 114.

[0077] In another illustrative embodiment, since the high energy density hybrid modules 112 are connected in parallel and controlled independently, each high energy density hybrid module 112 can be independently removed for repair by slowing down charging and discharging without affecting the normal operation of the power supply system 100.

[0078] Figure 5BAn example charge-discharge curve 500 of a battery cell is illustrated, including a voltage axis 514, a capacity axis 516, a discharge curve 518, and a charge curve 520. As shown in the discharge curve 518, at high discharge current / C rate 522 (e.g., 5C), the battery cell capacity is not fully utilized, and the battery cell voltage drops due to internal resistance. The current flowing through the battery cell causes an IR voltage drop across the internal resistance of the battery cell, which lowers the terminal voltage of the battery cell during discharge and increases the voltage required to charge the battery cell, thereby reducing the effective capacity of the battery cell and reducing its charge / discharge efficiency. Higher discharge rates produce higher internal voltage drops, which explains the lower voltage discharge curve at high C rate 522 and the different shape of the curve. By discharging and charging at various C rates 522, since the current can be precisely controlled using a bidirectional DC-DC converter 502, any impedance problem of the battery cell can be inferred and mitigated by comparing it with a reference profile, such as a previously stored profile of the battery cell 114. This can be achieved using a controlled step response to characterize the behavior of the battery cell 114 over time. One mitigation operation includes first discharging the high-energy-density hybrid module 112, which does not have the identified battery cell problem. Another mitigation operation includes slowing down the discharge of the high-energy-density hybrid module 112, which has the identified battery cell impedance problem.

[0079] Figure 6 Another example configuration of the power supply system 100 disclosed herein is shown, which includes an onboard energy management system 602. In this example, the traction battery 102 has a capacity of 44 kWh and provides a voltage of 320 V, and the hybrid range extender battery 124 has a capacity of 120 kWh through six 20 kWh high-energy-density hybrid modules 112, each hybrid module 112 having a voltage of 48 V. The onboard energy management system 602 has a battery management system (not shown) and is configured as a three-voltage system to handle 12 V, 48 V, and 320 V. Furthermore, the onboard energy management system 602 provides six bidirectional DC-DC converters (not shown), each bidirectional DC-DC converter being operatively coupled to the high-energy-density hybrid modules 112. By configuring the bidirectional DC-DC converters to provide, for example, 10 kW of power, the energy management system 602 can provide a 60 kW (6 × 10 kW) bidirectional 48 to 500 V DC-DC converter with a peak efficiency of 98.5%. Of course, the specific arrangement of voltage, power capacity, and other characteristics is not limiting, and other configurations are possible according to this specification. The examples in this invention are for clarity of description only and are not intended to limit the scope of the illustrative embodiments. According to the invention, other operations, actions, tasks, activities, and manipulations are conceived, and such operations, actions, tasks, activities, and manipulations can be considered within the scope of the illustrative embodiments.

[0080] Current standard battery capacities for electric vehicles range from just 17.6 kWh in smart cars with a range of only 58 miles to 100 kWh in some Tesla models (Tesla is a trademark of Tesla Inc. in the U.S. and other countries). This can be improved by introducing scalable architectures, such as... Figure 7 As shown, various configurations are available to meet different mileage requirements. Figure 7 In the illustrative embodiment, compared to configuration 1 702, the available capacity is increased from 130 kWh to 200 kWh by providing five additional high-energy-density hybrid modules 112 in configuration 2 704, and a capacity of 270 kWh is obtained for configuration 3 706 by introducing another five additional high-energy-density hybrid modules 112 into configuration 2 704. Furthermore, the scalable architecture allows for different locations within the vehicle, such as the chassis 304 of vehicle 302. Figure 3 The modules can be placed without restriction outside the conventional placement area on the battery, because each module only needs to be individually connected to the traction battery or the high-voltage DC bus. As disclosed herein, for example with respect to Figure 4, various high-energy-density modules can use different chemistry, thus allowing for additional flexibility in terms of usage conditions, energy density, and expected cycle life.

[0081] Figure 8 Another configuration of a power supply system with a traction battery 102, multiple high-energy-density hybrid modules 112, and multiple bidirectional DC-DC converters 502 is shown. In this configuration, the module is disabled because a SOH check indicates a problem with battery cell 114. The disabled hybrid module 802 is offline and can undergo formation recharging to extend its life, wherein the module is slowly discharged in, for example, a 20-hour period and slowly recharged in, for example, another 20-hour period to rebuild its chemistry at a defined temperature. The modular nature of the configuration provides that the vehicle remains usable during formation recharging without the need for physical removal of the disabled hybrid module 802. In the example herein, the shunt resistor of battery cell 114 is used for both charging and discharging operations.

[0082] The figure also illustrates a reduced-capacity hybrid module A 804, a reduced-capacity hybrid module B 806, and a conventional-capacity hybrid module 808. The hybrid module controller 118 of either the reduced-capacity hybrid module A 804 or the reduced-capacity hybrid module B 806 is configured to detect problems with the battery cell 114 and make independent decisions regarding its discharge rate, for example, by reducing the power output from 2kW to 1kW.

[0083] In step 902, process 900 provides a traction battery comprising one or more traction modules controlled by a battery management system (BMS) to connect and disconnect from the high-voltage DC bus of the electric vehicle 302. Hereinafter, the traction battery is configured to power the electric vehicle 302. In step 904, process 900 provides a hybrid range extender battery 124 comprising a plurality of high-energy-density hybrid modules 112 connected in parallel to each other and connected to the high-voltage DC bus to which the traction battery 102 is also connected. Each of the plurality of high-energy-density hybrid modules 112 includes a corresponding hybrid module controller (HMC) and a plurality of battery cells 114 connected in series. The health of each of the plurality of battery cells 114 is configured to be independently measurable via the corresponding HMC. The state of charge (SOC) of each battery cell can also be controlled by a balancing device 128 (such as a shunt resistor connected in parallel with the battery cells 114). Therefore, the battery cells of each module can be controlled independently and as a whole.

[0084] In step 906, a plurality of bidirectional DC-DC converters 502 are arranged between a plurality of high energy density hybrid modules 112 and the high-voltage DC bus of the electric vehicle 302, and / or between a plurality of high energy density hybrid modules 112 and the traction battery 102.

[0085] Process 900 operatively couples the DC current from one or more of the plurality of high-energy-density hybrid modules 112 to the high-voltage DC bus of the traction battery 102 (step 908) and / or the electric vehicle 302 (step 910) to charge the traction battery and / or power the electric vehicle 302 accordingly. In step 912, process 900 controls the power generation mode of the power supply system by acquiring sensor information relating to independently measurable battery cells 114. In step 914, process 900 uses each of the plurality of corresponding HMCs to control the charging and discharging rates of the corresponding high-energy-density hybrid module of that HMC, based on the acquired sensor information relating to independently controllable battery cells.

[0086] Intelligent power control

[0087] This illustrative embodiment further recognizes that conventional electric vehicle power systems configured to estimate the state of health (SOH) or state of charge (SOC) of battery components are primarily reactive, unable to predict energy consumption demands, and limited to using remaining available energy in a largely retrospective manner. This illustrative embodiment recognizes that while estimates can currently be obtained based on the perceived state of interest, few mitigation measures are available to ensure battery safety or maintain battery life and capacity. Furthermore, the load-following nature of conventional electric vehicle power computer systems (which lack control over changes in drive power) means that the current input and output of the battery modules cannot be precisely controlled.

[0088] In managing the chemistry of individual modules within a power supply system, conventional batteries charge and discharge all modules together. However, the embodiments disclosed herein recognize that monitoring the chemistry of individual battery modules within a larger power supply system and controlling these modules individually to ensure the safety of the entire system can provide additional benefits not available in conventional battery systems and electric vehicles. For example, in conventional systems, individual modules used for formation and recharging cannot be disabled without requiring the larger power supply system to be shut down, thus compromising the safety of the power supply system, and the usable lifespan of individual modules is unduly shortened due to overcharging and over-discharging.

[0089] The embodiments disclosed herein recognize that currently available tools or solutions do not address the requirement to provide intelligent management of individual modules in a hybrid architecture to provide additional power when needed, while maintaining or maximizing battery life cycles and thus maintaining or maximizing the lifespan, safety, and maximum capacity of individual modules in a manner that allows mileage and distance targets to be achieved. The illustrative embodiments used to describe the invention address and resolve the aforementioned and other related problems by intelligently supplying power to the electric vehicle using a high-energy-density hybrid module 112 in the power supply system. These illustrative embodiments can also address these problems in the proactive and / or preparatory processing of anticipating the power needs of the electric vehicle and operating to meet those needs.

[0090] In the embodiments, certain operations are described as occurring at a specific component or location. This locality of operation is not intended to limit the illustrative embodiments. Any operation described herein as occurring at or performed by a specific component (e.g., predictive analytics of battery data and / or natural language processing (NLP) analysis of contextual calendar data) can be implemented in such a way that a component-specific function enables an operation to occur at or be performed at another component (e.g., at a local or remote machine learning (ML) or NLP engine, respectively).

[0091] One embodiment monitors and manages the accumulated energy of a hybrid electric supply system. Another embodiment monitors various profile sources configured for a user. A profile source is an electronic data source from which information for determining a user's profile characteristics can be obtained. For example, a profile source can be a user's preference configuration on a computing device, such as desired speed or route, a calendar application planning future events for the user and recording past events, a destination in a Global Positioning System (GPS) application for the user entering the current destination, and feedback from the user or group, etc. A profile source can be a device, equipment, software, or platform that provides information from which a user's driving characteristics can be derived. For example, within the scope of the illustrative embodiment, an electric vehicle dashboard can operate as a profile source. Furthermore, a group, such as a platoon of electric vehicles, can be a profile source, where multiple driving characteristics of the user profile can be obtained to derive preferences, likes, emotions, or use of the electric vehicle. In addition, measured health metrics or parameters related to the individual modules of the battery packs in the platoon of vehicles can be profile sources from the group and can be utilized to learn and derive patterns for delivering power in the main electric vehicle. Therefore, batteries from the vehicle queue can be adapted to their predicted and shared values ​​for prediction / recommendation purposes.

[0092] User profile data, information, and preferences are interchangeable terms used herein to refer to constraints affecting power delivery in a power supply system for one or more users. Furthermore, information / data regarding the electric vehicle and power supply system 100 (such as vehicle speed, module current, temperature, voltage, impedance, health status, state of charge, and average energy consumption, or other main electric vehicle parameters 1220) may form part of or be separate from the constraints, and this information / data may be obtained as input to the intelligent power control module for predictive analysis, as described below. Therefore, profile source information, along with electric vehicle and power supply system data (main electric vehicle parameters 1220), collectively form at least part of input data 1202 or constraints for the intelligent power control module to predict the output power levels obtained from the individual batteries of the hybrid architecture to achieve mileage or distance targets, while considering the safety, battery life, and battery capacity of the power supply system 100 in the electric vehicle (these are referred to below as attributes of the power supply system 100).

[0093] Therefore, input data can be determined directly from measurements obtained from the components of the electric vehicle. Alternatively, input data can be directly indicated in the information from the profiling source. For example, a user can have explicitly stated preferences for destination arrival time or mileage targets during a specified time period or until further modification of preferences.

[0094] Input data can also be exported from information collected from a self-profile source. For example, an embodiment can be configured to analyze a user's calendar to export arrival times at a destination. Furthermore, information such as text or comments on a driving network can be analyzed in context to determine upcoming traffic. In another example, the landscape of a geographic area can be obtained from an environmental profile and examined to establish the nature of the terrain (e.g., steep slopes in a mountainous area, as obtained from an imaging device or database), thus requiring increased battery power output.

[0095] The input data determined by the embodiments can vary over time. For example, a user may prefer a predetermined route for short driving distances to and from their workplace, and may prefer a route that optimizes energy consumption during long holiday trips. Therefore, preferences can change when holiday driving characteristics obtained from the user profile become prioritized. In this case, the intelligent power control module can prioritize the use of the high-energy-density hybrid module 112 of the hybrid range extender battery 124 over the use of the traction module 122 of the traction battery 102 to extend the range of the traction battery 102.

[0096] Similarly, driving to the workplace may not require the use of the hybrid range extender battery 124. However, since the route to the normal workplace is determined to have traffic and context establishment (e.g., the user has a meeting in 1 hour), the user's "fast driving characteristics" can be prioritized, causing the vehicle navigation system to abandon the normal route and favor a new route (albeit a mountainous one). Based on predictive analysis relating the power or energy required to traverse the mountainous route in 1 hour to be greater than the available traction battery power or energy, or at least greater than a threshold power or energy, the power control module determines that the high energy density hybrid module 112 is needed to complete the drive to the workplace. Furthermore, at least during the meeting context establishment, the power control module can be configured to independently and automatically precharge the traction battery 102 to the threshold charge expected during driving via a bidirectional DC-DC converter 502 connected to the high energy density hybrid module 112.

[0097] Importantly, the power control module can control the output power obtained from one or more high-energy-density hybrid modules 112 while simultaneously ensuring the safety, maximum lifespan cycles, and maximum capacity attributes of each high-energy-density hybrid module 112. For example, if sensor information obtained relating to independently measurable battery cells of high-energy-density hybrid module 112A determines that high-energy-density hybrid module 112A is faulty, the power control module can deactivate module A and utilize high-energy-density hybrid module 112B to precharge the traction battery 102, thereby ensuring the safety of the battery pack and allowing the deactivated module A to eventually be restored through formation recharging. In another example, if high-energy-density hybrid module 112C is determined to have six remaining lifespan cycles, the power control module can prioritize depleting module 112C before utilizing power from other modules. User feedback, determined by the power control module, on the accuracy of the indications for the output power to be retrieved from the high-energy-density hybrid modules 112, is used to modify the power control module to produce better results.

[0098] Operating using profile information from one or more profile sources, this embodiment routinely evaluates constraints applicable to users of electric vehicles. This embodiment may add new constraints / input data (when discovered in profile information analysis), modify existing constraints (when demonstrated in profile information analysis), and reduce the use of past constraints based on feedback, observed constraint usage, and / or the presence of support for past constraints in the profile information. Past constraints can be reduced or aged by degrading them to some extent, including removing / deleting / or invalidating past constraints. Profile information sources may include, for example, calendar entries in a phone, tablet, or other device paired with the vehicle and / or management system; user-associated accounts or apps that the dispatcher can provide access to; or information directly entered by the user; and so on. More generally, profile information can be obtained from any source that can be directly or indirectly available to the vehicle and can be associated with the user or owner of the vehicle.

[0099] Operating using profile information from one or more profile sources, this embodiment predicts a user's activities during a future time period. For example, based on calendar data, this embodiment can determine, for instance, through NLP of calendar entries, that a user plans to work at location A at 9:00 AM tomorrow, have lunch from 12:00 PM to 1:00 PM, and visit a doctor after 3:00 PM. This embodiment derives tomorrow's energy requirements based on calendar activity and precharges the traction battery 102 using one or more high-energy-density hybrid modules 112, or allocates high-energy-density hybrid modules 112 for use tomorrow. Allocation can also be made without using NLP to interpret the calendar data, as this is not intended to be limiting. Furthermore, these examples of input data / constraints, prioritization, secondary considerations, etc., are not intended to be limiting. Within the scope of the illustrative embodiments of the invention, those skilled in the art will be able to conceive of and contemplate many other aspects that can be used for similar purposes.

[0100] The intelligent power control systems and technologies described herein are typically unavailable in conventional approaches within the technical field of electric vehicles. When implemented on a device or data processing system, the methods of the embodiments described herein include significantly enhancing the functionality of the device or data processing system in terms of power output recommendations by obtaining constraint recommendations and using a hybrid battery architecture that enables control of input and output currents while ensuring that the safety, lifetime, and capacity properties of the modules of the hybrid battery architecture are maximized.

[0101] In another embodiment, a machine learning engine can be provided to improve the resolution and effectiveness of predictions made by the controller based on comparisons of sensed and received information. The machine learning engine can detect patterns and, based on these patterns, measure possible outcomes and energy demand profiles. As users interact with vehicles, data about the journey can be collected and stored for analysis by the controller or other network-connected computerized devices. Data related to the journeys of multiple users in multiple electric vehicles can be aggregated to allow for additional resolution in pattern detection and behavior prediction.

[0102] For example, a driver might travel along a road such as a county road that connects to an interstate highway. Geolocation sensors can detect that a vehicle is on the road and moving in the direction of the interstate highway. Data collected from multiple vehicles can indicate that most vehicles traveling along that county road in the direction of the interstate highway are likely to enter the interstate highway. Data collected from multiple vehicles can initially indicate that the driver is typically entering the interstate highway in a southbound direction (e.g., a direction from a city or a location with multiple workplaces).

[0103] The machine learning engine can use this information to predict the energy demand profile for a journey. This profile can be provided as a baseline because real-world scenarios can deviate from the predicted journey. Considering the example above, the driver of an electric vehicle might deviate from the predicted journey and drive onto an incline along an interstate highway. The machine learning engine can then determine the deviation from the predicted journey that has already occurred and update the energy demand profile to reflect the next most likely scenario, such as driving to a relevant house or other location with public access located 30 miles outside the interstate highway entry point.

[0104] In another example, it is assumed without limitation that sensors located on the vehicle can detect the amount of torque required to move the electric vehicle in the forward direction. In this example, it can be determined that a considerable amount of torque is needed to accelerate the vehicle. It can also be determined that a larger amount of regenerative energy is generated as the vehicle decelerates. The machine learning engine can determine that the vehicle is towing another mass. The controller can perform calculations to modify the amount of stored energy required to complete the journey while towing the mass. These modifications can be applied and may affect the energy demand profile to reflect the additional energy demand of the journey. For example, the controller can adjust the energy demand profile to anticipate a higher energy demand while towing the mass.

[0105] The predictive profile of the machine learning engine can include an aggregated or baseline profile that provides an overall indication of route characteristics and energy consumption needs from the user. The predictive profile of the machine learning engine can also include a local profile that indicates public journeys undertaken by the user, public destinations, and other public characteristics associated with those journeys. In one embodiment, an energy demand profile can be generated for each user. And in this embodiment, the user can be identified by a dedicated remote key, a mobile computing device connected to the vehicle's entertainment system, voice recognition, seat weight sensors, and / or other information indicating the operator's identity. When identifying the operator, the machine learning engine can adjust its predictive model to accommodate statistically probable routes, driving habits, and other useful characteristics of the operator. The energy demand profile can be adjusted accordingly for the local profile associated with the operator.

[0106] Machine learning engines can operate by updating vehicle parameter assumptions and predicting destination-weighted energy requirements. At the start of a journey, assumptions can be made about the vehicle and the anticipated journey. These assumptions can be supported by information determined by the vehicle and can be recorded as time-series data that can be used to calculate physical parameters. Example physical parameters may include rate, net battery system power, traction motor power, geolocation, and other parameters that those skilled in the art will understand upon learning of the present invention. Additional information, such as latitude, longitude, heading, altitude, speed, acceleration, inertia, and other information, can be derived.

[0107] Vehicle-derived information can be supplemented by information from network sources. Such information may include wind speed, weather information, route, distance to destination, route elevation and terrain profile, traffic, and other information that may affect the energy requirements of the journey.

[0108] The machine learning engine can analyze time-series data collected at the vehicle, supplementary information such as that provided via the network, and / or other information used to plot correlations. For example, the machine learning engine can perform linear algebraic regression analysis on time-series step data to find the most suitable vehicle parameter values. Examples of the most suitable vehicle parameter values ​​may include mass, rolling drag coefficient, aerodynamic drag coefficient, and other values ​​that will be understood by those skilled in the art. The machine learning engine can also return vehicle parameters that can be used by the controller in energy management, such as mass, rolling drag coefficient, aerodynamic drag coefficient, average auxiliary power load, and other returned parameters that will be understood by those skilled in the art. An example calculation that can be used to determine the average auxiliary power load may be the sum of the net battery system power and the traction motor power, but is not limited to this.

[0109] Machine learning engines can be advantageous in predicting destination-weighted energy requirements. These requirements can help determine whether to transfer electrical energy stored in high-energy-range batteries to high-power traction batteries for electric vehicles or other loads. In making predictions, the machine learning engine can determine routes from the current location to various candidate charging locations. Journey information can be received from the vehicle's navigation system, directions provided by the user's mobile computing device, or historical predictions based on driver behavior. The presence of charging locations (such as the user's home or public charging facilities) can be determined based on journey history, sources provided by the internet, navigation directions, and other sources.

[0110] Charging location candidates are likely to be favored if they are located within an acceptable short distance of the journey's destination. Favored charging locations can be promoted when the expected energy demand is calculated by a machine learning engine. Similarly, unfavored charging locations may be de-emphasized and / or removed when the expected energy demand for the journey is determined.

[0111] Continuing with the example above, the machine learning engine can calculate various route options to guide the operator from the origin to the indicated destination. Journey options may consider factors such as the presence of charging facilities, expected road stops, acceptable distances between charging facilities, unacceptable distances between charging facilities, elevation changes, traffic, and other characteristics associated with the respective route option. Given the current charging status of the operator's vehicle, the machine learning engine may disapprove of route options that appear inaccessible.

[0112] In another example, assuming, but not limited to, that the machine learning engine can determine that the state of charge (SOC) of a high-range battery is approximately 50%, a first route, such as the most direct route, might require at least 75% SOC to reach a charging facility under normal operating conditions. Alternative routes that require only 25% SOC to reach the charging facility can be identified and presented to the user. The machine learning engine can then recommend routes that provide earlier access to the charging facility, thus avoiding the need to keep at least a portion of the high-range battery online.

[0113] Furthermore, in this example, the operator can choose to override the recommended route, such as by driving on an alternative route. If it is determined that the operator has chosen to take a disapproved route and begins to move in the direction indicated by following the disapproved route, the machine learning engine can instruct at least a portion of the high-energy mileage battery to be online to provide supplemental energy that may be needed to reach charging facilities located outside the expected remaining capacity in the high-energy traction battery.

[0114] As those skilled in the art will understand, the machine learning engine can assign various weights to sensed information, conditions, parameters, journey details, and other factors that may influence the estimated energy consumption required to conform to the predicted energy usage profile. Examples of parameters that can be weighted to influence the predicted energy usage profile may include geographic location, GPS location, time of day, date of week, vehicle mass, towed mass, temperature, auxiliary power demand, rolling drag coefficient, aerodynamic coefficient area, time since the last charge of the battery pack, time since the last charge occurred at the candidate location, and / or other factors and parameters that will become apparent to those skilled in the art upon benefiting from this invention.

[0115] The machine learning engine can then correlate these parameters, at least in part, based on the weighted effects of the considered parameters to predict energy requirements. For example, the machine learning engine can apply a calculation that assumes the energy requirement is approximately equal to the sum of the mass included by the vehicle and other mass being towed or carried by the vehicle. This value can be multiplied by the expected energy required to complete the intended route. The machine learning engine can then analyze these factors and predict a profile of the expected energy requirements associated with the intended journey. The battery pack controller can then move power between the high-energy range battery and the high-power traction battery to compensate for any predicted under-charging inaccuracies currently maintained by the high-power traction battery.

[0116] Redundancy will now be discussed in more detail. In one embodiment, redundancy features can be provided to mitigate the risk of one or more battery modules experiencing total depletion and / or failure of their stored energy. Multiple energy management components may be included, such that the failure of one energy management component is unlikely to cause a system-wide failure. In one example, the battery pack may include modular components comprising connected battery management components, high-power traction battery modules, high-energy-range battery modules, cooling features, and / or other aspects to aid in storage and power delivery. In this example, if one of the modular components fails, the remaining modular components can continue to provide power delivery from their connected aspects.

[0117] In one embodiment, a separate observer module may be included to provide backup functionality otherwise provided by the energy management component. In this example, even in the event of a failure of the energy management component otherwise connected to the corresponding battery pack, the separate observer module can continue to operate the vehicle or other connected loads based on the electrical energy stored in the battery pack. For example, in the event of a failure of the connected energy management component, the redundancy feature of the separate observer module can take over the operation of energy management, allowing the connected load (e.g., the vehicle) to continue operating substantially safely until the problems causing the separate observer module's intervention can be investigated and / or repaired. By providing such redundancy and safety features to mitigate system failures, the system implemented by this invention can be certified as ASIL D architecture.

[0118] The descriptions of certain types of data, functions, algorithms, equations, model configurations, locations of embodiments, additional data, devices, data processing systems, environments, components, and applications are merely illustrative examples. Any particular manifestation of these and other similar techniques is not intended to limit the invention. Any suitable manifestation of these and other similar techniques may be chosen within the scope of the illustrative embodiments.

[0119] Furthermore, illustrative embodiments can be implemented for any type of data, data source, or access to a data source via a data network. Within the scope of this invention, any type of data storage device can provide data to embodiments of the invention locally on the data processing system or via a data network. In the case of embodiments described using mobile devices, within the scope of the illustrative embodiments, any type of data storage device suitable for use with a mobile device can provide data to such embodiments locally on the mobile device or via a data network.

[0120] The illustrative embodiments are described using specific code, designs, architectures, protocols, layouts, diagrams, and tools as examples only, and are not limited to. Furthermore, the illustrative embodiments are described using specific software, tools, and data processing environments in some instances only as examples of clarity of description. The illustrative embodiments can be used in conjunction with other equivalent or similar structures, systems, applications, or architectures. For example, therefore, within the scope of this invention, other equivalent mobile devices, structures, systems, applications, or architectures can be used in conjunction with such embodiments of the invention. The illustrative embodiments can be implemented in hardware, software, or a combination thereof.

[0121] The examples in this invention are for clarity of description only and are not intended to limit the scope of the illustrative embodiments. Other data, operations, actions, tasks, activities, and manipulations may be conceived in accordance with the invention, and such data, operations, actions, tasks, activities, and manipulations may be considered within the scope of the illustrative embodiments.

[0122] Any advantages listed herein are merely illustrative and are not intended to be limited to the illustrative embodiments. Additional or different advantages may be achieved through specific illustrative embodiments. Furthermore, a particular illustrative embodiment may have some, all, or none of the advantages described above.

[0123] Refer to the accompanying drawings, especially the following: Figure 10 and Figure 11 These figures are example diagrams of a data processing environment in which illustrative embodiments can be implemented. Figure 10 and Figure 11 This is merely an example and is not intended to assert or imply any limitation regarding the environments in which different embodiments may be implemented. Based on the following description, a particular implementation may make many modifications to the depicted environment.

[0124] Figure 10A block diagram depicts a network that can be used to implement a data processing system according to the illustrative embodiments. Data processing environment 1000 is a computer network that can implement the illustrative embodiments. Data processing environment 1000 includes network / communication infrastructure 1002. Network / communication infrastructure 1002 is a medium for providing communication links between various devices, databases, and computers connected within data processing environment 1000. Network / communication infrastructure 1002 may include connections such as wired, wireless communication links, or fiber optic cables.

[0125] The client or server are merely example roles of certain data processing systems connected to network / communication infrastructure 1002, and are not intended to exclude other configurations or roles of these data processing systems. Servers 1004 and 1006 are coupled to network / communication infrastructure 1002 together with storage unit 1008. Software applications can execute on any computer in data processing environment 1000. Clients 1010, 1012, and dashboard 1014 are also coupled to network / communication infrastructure 1002. Client 1010 can be a remote computer with a display. Client 1012 can be a mobile device configured with an application for sending or receiving information, such as for receiving charging conditions of power supply system 100 or for sending information about a user's calendar. Dashboard 1014 can be located inside an electric vehicle and can be configured to send or receive any information discussed herein. Data processing systems such as server 1004 or server 1006 or clients (client 1010, client 1012, dashboard 1014) can contain data and can have software applications or software tools executing thereon.

[0126] This is merely an example and does not imply any limitations on this architecture. Figure 10 Certain components that may be used in the example implementations of the embodiments are depicted. For example, the server and client are merely examples and do not imply any limitation on the client-server architecture. As another example, as shown, the embodiments may be distributed across several data processing systems and data networks. In contrast, within the scope of the illustrative embodiments, another embodiment may be implemented on a single data processing system. The data processing systems (server 1004, server 1006, client 1010, client 1012, dashboard 1014) also represent example nodes in clusters, partitions, and other configurations suitable for implementing the embodiments.

[0127] The power supply system 100 includes a traction battery 102 comprising one or more traction units and a hybrid range extender battery 124 comprising one or more high-energy-density hybrid modules 112. As discussed, the one or more high-energy-density hybrid modules 112 are configured to have a chemical whose high energy density takes precedence over the available cycle life, and each high-energy-density hybrid module 112 includes a corresponding hybrid module controller 118 and a plurality of battery cells connected in series, wherein each of the plurality of battery cells is configured to be independently measurable by the corresponding hybrid module controller 118.

[0128] The embodiments described herein can be implemented in client application 1020, dashboard application 1022, or any other application (such as server application 1016). Any application can use data from power supply system 100 and profile sources to predict electricity or energy demand. The application can also obtain data for predictive analysis from storage unit 1008. The application can also execute in any data processing system (server 1004 or server 1006, client 1010, client 1012, dashboard 1014).

[0129] Server 1004, server 1006, storage unit 1008, client 1010, client 1012, and dashboard 1014 can be coupled to network / communication infrastructure 1002 using wired connections, wireless communication protocols, or other suitable data connections. Client 1010, client 1012, and dashboard 1014 can be, for example, mobile phones, personal computers, or network computers.

[0130] In the depicted example, server 1004 can provide data such as boot files, operating system images, and applications to clients 1010, 1012, and dashboard 1014. In this example, clients 1010, 1012, and dashboard 1014 can be clients of server 1004. Clients 1010, 1012, and dashboard 1014, or combinations thereof, can include their own data, boot files, operating system images, and applications. Data processing environment 1000 may include additional servers, clients, and other devices not shown.

[0131] As described herein with respect to various embodiments, server 1006 may include a search engine configured to search for information such as terrain conditions, rate limits, user feedback, alternative profile sources, GPS information, traffic conditions or other driving characteristics, and battery measurements (e.g., real-time battery measurements from the individual battery cells of the high-energy-density hybrid module 112) in response to a request for power delivery from an operator.

[0132] In the depicted example, the data processing environment 1000 can be the Internet. The network / communication infrastructure 1002 can represent a collection of networks and gateways communicating with each other using Transmission Control Protocol / Internet Protocol (TCP / IP) and other protocols. The core of the Internet is the backbone of data communication links between major nodes or host computers, including thousands of commercial, government, educational, and other computer systems used for routing data and messages. Of course, the data processing environment 1000 can also be implemented as various different types of networks, such as intranets, local area networks (LANs), or wide area networks (WANs). Figure 10 This is intended as an example, not as a limitation of different illustrative embodiments of the architecture.

[0133] In other uses, the data processing environment 1000 can be used to implement a client-server environment that enables the illustrative embodiments. The client-server environment allows software applications and data to be distributed across a network, enabling applications to function through the interoperability between client-side and server-side data processing systems. The data processing environment 1000 can also employ a service-oriented architecture, where interoperable software components distributed across the network can be packaged together as a consistent business application. The data processing environment 1000 can also be cloud-based and employ a service-delivered cloud computing model to enable convenient, on-demand network access to a shared pool of configurable computing resources (e.g., networks, network bandwidth, servers, processing, memory, storage devices, applications, virtual machines, and services), which can be rapidly provisioned and released with minimal management effort or interaction with service providers.

[0134] Figure 11 A block diagram depicts a data processing system that can implement illustrative embodiments. Data processing system 1100 is an example of a computer, such as... Figure 10 The client 1010, client 1012, dashboard 1014, or server 1004, server 1006, or other types of means that can be located with respect to the illustrative embodiments to implement the processing, such as computer-usable program code or instructions.

[0135] The data processing system 1100 is described as a computer by way of example only and is not limited thereto. Without departing from the general description of the operation and function of the data processing system 1100 described herein, Figure 10 In this context, implementations in the form of other devices may modify the data processing system 1100, for example, by adding a touch interface and even removing certain depicted components from the data processing system 1100.

[0136] In the depicted example, the data processing system 1100 employs a hub architecture including a Northbridge and memory controller hub (NB / MCH) 1102 and a Southbridge and input / output (I / O) controller hub (SB / ICH) 1104. A processing unit 1106, main memory 1108, and a graphics processor 1110 are coupled to the Northbridge and memory controller hub (NB / MCH) 1102. The processing unit 1106 may contain one or more processors and can be implemented using one or more heterogeneous processor systems. The processing unit 1106 may be a multi-core processor. In some implementations, the graphics processor 1110 may be coupled to the Northbridge and memory controller hub (NB / MCH) 1102 via an Accelerated Graphics Port (AGP).

[0137] In the depicted example, a local area network (LAN) adapter 1112 is coupled to the Southbridge and input / output (I / O) controller hub (SB / ICH) 1104. An audio adapter 1116, a keyboard and mouse adapter 1120, a modem 1122, a read-only memory (ROM) 1124, a universal serial bus (USB) and other ports 1132, and a PCI / PCIe device 1134 are coupled to the Southbridge and input / output (I / O) controller hub (SB / ICH) 1104 via bus 1118. A hard disk drive (HDD) or solid-state drive (SSD) 1126a and a CD-ROM 1130 are coupled to the Southbridge and input / output (I / O) controller hub (SB / ICH) 1104 via bus 1128. The PCI / PCIe device 1134 may include, for example, an Ethernet adapter, an add-in card, and a PC card for a notebook computer. PCI uses a card bus controller, while PCIe does not. Read-only memory (ROM) 1124 may be, for example, a flash binary input / output system (BIOS). Hard disk drive (HDD) or solid-state drive (SSD) 1126a and CD-ROM 1130 may use, for example, an integrated drive electronics (IDE), a serial advanced technology accessory (SATA) interface, or a variant such as external SATA (eSATA) and microSATA (mSATA). Super I / O (SIO) device 1136 may be coupled to the southbridge and input / output (I / O) controller hub (SB / ICH) 1104 via bus 1118.

[0138] Memory such as main memory 1108, read-only memory (ROM) 1124, or flash memory (not shown) are some examples of computer-usable storage devices. Hard disk drive (HDD) or solid-state drive (SSD) 1126a, CD-ROM 1130, and other similar available devices are some examples of computer-usable storage devices (including computer-usable storage media).

[0139] The operating system runs on the processing unit 1106. The operating system coordinates and provides services to... Figure 11 The data processing system 1100 controls various components within it. The operating system can be a commercial operating system for any type of computing platform, including but not limited to server systems, personal computers, and mobile devices. Object-oriented or other types of programming systems can operate in conjunction with the operating system and make calls to the operating system from programs or applications executing on the data processing system 1100.

[0140] For use in operating systems, object-oriented programming systems, and applications or programs (such as...) Figure 10 The instructions for applications 1016 and client applications 1020 (e.g., in the processing unit 1106) reside on a storage device, such as in the form of code 1126b on a hard disk drive (HDD) or solid-state drive (SSD) 1126a, and can be loaded into at least one of one or more memories (e.g., main memory 1108) for execution by the processing unit 1106. The processing in the illustrative embodiment can be performed by the processing unit 1106 using computer-implemented instructions, which may reside in memory, such as main memory 1108, read-only memory (ROM) 1124, or one or more peripheral devices.

[0141] Furthermore, in one case, code 1126b can be downloaded from remote system 1114b via network 1114a; in another case, at remote system 1114b, similar code 1114c is stored on storage device 1114d, and code 1126b can be downloaded to remote system 1114b via network 1114a, where the downloaded code 1114c is stored on storage device 1114d.

[0142] Figure 10 and Figure 11 The hardware can vary depending on the implementation. Besides... Figure 10 and Figure 11 The hardware described in the text, or its replacement Figure 10 and Figure 11 The hardware depicted can utilize other internal hardware or peripheral devices such as flash memory, equivalent non-volatile memory, or optical disc drives. Furthermore, the processing described in the illustrative embodiments can be applied to multiprocessor data processing systems.

[0143] In some illustrative examples, the data processing system 1100 may be a personal digital assistant (PDA), which is typically configured with flash memory to provide non-volatile memory for storing operating system files and / or user-generated data. The bus system may include one or more buses, such as a system bus, I / O bus, and PCI bus. Of course, the bus system can be implemented using any type of communication construct or architecture that provides data transfer between different components or devices attached to the construct or architecture.

[0144] The communication unit may include one or more devices for sending and receiving data, such as a modem or network adapter. The memory may be, for example, main memory 1108 or a cache, such as the cache found in the Northbridge and Memory Controller Hub (NB / MCH) 1102. The processing unit may include one or more processors or CPUs.

[0145] Figure 10 and Figure 11 The examples depicted and those described above are not intended to imply architectural limitations. For example, in addition to taking the form of a mobile or wearable device, the data processing system 1100 could also be a tablet computer, a laptop computer, or a telephone device.

[0146] In this context, the computer or data processing system is described as a virtual machine, virtual device, or virtual component, which operates in a manner similar to the data processing system 1100 using a virtualized representation of some or all of the components depicted in the data processing system 1100. For example, in a virtual machine, virtual device, or virtual component, the processing unit 1106 represents a virtualized instance of all or part of the hardware processing units 1106 available in the host data processing system, the main memory 1108 represents a virtualized instance of all or part of the main memory 1108 available in the host data processing system, and the hard disk drive (HDD) or solid-state drive (SSD) 1126a represents a virtualized instance of all or part of the hard disk drive (HDD) or solid-state drive (SSD) 1126a available in the host data processing system. In this case, the host data processing system is represented by the data processing system 1100.

[0147] about Figure 12 This figure depicts an example configuration for smart power control according to an illustrative embodiment. It can be used... Figure 12 Application 1204 is used to realize intelligent power control. Application 1204 is... Figure 10Examples of server application 1016, client application 1020, or dashboard application 1022 are provided. Application 1204, for example, receives or monitors a set of input data 1202 in real time. Input data includes main electric vehicle parameters 1220, such as the current of the high-energy-density hybrid module, the temperature of each battery cell 114 and its adjacent battery cells, the voltage of battery cell 114, the impedance of battery cell 114, the health status of battery cell 114, the capacity of battery cell 114, the calculated polarization curve or charge / discharge curve 500 for identifying the graphitization plateaus of battery cell 114, the vehicle's maximum speed / acceleration, the vehicle's total mass, the vehicle's aerodynamic drag, location, nearest charging station, etc. Input data also includes driving characteristics from profile source 1226 (user profile 1222, group profile 1224, environment profile 1230), such as user preferences, number of planned stops during the journey, average daily driving distance, driving energy consumption per mile past, duration of stops, calendar data, and environmental data such as terrain data, road slope angle, air drag coefficient, and road rolling resistance coefficient.

[0148] In one or more embodiments described herein, features, attributes, and / or preferences associated with users, groups, environments, main electric vehicles, power supply systems, etc., are referred to as “features.” In one or more embodiments, configuration 1200 defines and configures algorithms and / or rules to drive feature selection outcomes. In a particular embodiment, the algorithm may, for example, include determining the lowest common value of a feature among users and determining whether that value satisfies a threshold (e.g., 90%) for the feature as the best match. In embodiments, the system may prioritize certain features such that features such as battery module safety, arrival time, or SOH or driving distance carry different weights. In embodiments, after discovering common benchmarks in the vehicle queue, configuration 1200 understands the problems of individual vehicles and extracts and derives optimal feature values ​​that help control the power of the main electric vehicle.

[0149] In this embodiment, the feature extraction component 1214 is configured to generate relevant features of the main electric vehicle based on the content of a request from application 1204, using data from all different available features (e.g., main electric vehicle parameters 1220, user profile 1222, group profile 1224, and environment profile 1230). In this embodiment, the feature extraction component 1214 receives a request from application 1204, which includes at least an identifier for the main electric vehicle 1232 and / or its user or location, and instructions to suggest obtaining power output from one or more high-energy-density hybrid modules 112 to complete a 10-mile journey. Using the main electric vehicle 1232 and / or user information, the feature extraction component 1214 obtains a combination of specific main electric vehicle parameters 1220, user profile information from user profile 1222, group profile information from group profile 1224, and environmental data from environment profile 1230. In this embodiment, the feature extraction component 1214 uses a defined priority ranking algorithm to generate features as a feature profile. In a particular embodiment, the feature profile includes features (e.g., 1. current in battery cell 114, 2. temperature of battery cell 114, 3. voltage of battery cell 114, 4. impedance of battery cell 114, 5. user calendar, 6. GPS location, 7. destination, 8. mileage requirement, 9. health audit report indicating the safety, capacity, and remaining life cycle of battery cell 114, 10. weights assigned to each feature). The power control module 1216 uses the extracted features and a trained M / L model 1206 trained using a large number of different datasets to determine a power output recommendation 1212 for the main electric vehicle 1232. A major benefit of employing a hybrid architecture that prioritizes high energy density over the number of available charge and / or discharge cycles of battery cell 114 is a significant increase in the mileage of the traction battery 102 of the power supply system 100. Furthermore, a highly modular architecture is achieved by individually controlling the current input and output of the high-energy-density hybrid module 112 with series-connected battery cells 114. This architecture increases the safety of individual battery cells 114 or modules by, for example, the ability to control which modules are enabled or disabled when a short circuit is detected to prevent further damage caused by localized faults. By modularly controlling the high-energy-density hybrid module 112 based on measurements obtained regarding the component battery cells 114, the maximum lifetime cycle life of each high-energy-density hybrid module 112 can be ensured by preventing only the rapid degradation of battery cells associated with battery cell problems that are not typically detected in parallel-connected battery cells in conventional solutions. For example, if one battery cell overheats and goes undetected, it may begin to affect a chain reaction in other battery cells.The ability of the balancing device 128 to modularly control the current and charge / discharge rates of the individual series-connected battery cells ensures the maximum capacity of the battery cell 114 and thus maintains its usable lifespan. Therefore, by employing a power control module 1216 based on a machine learning model that considers preferences and the health parameters of the main electric vehicle, the output of each high-energy-density hybrid module 112 can be intelligently and in real-time controlled to efficiently respond to the vehicle's varying energy demands, while allowing the user to achieve their mileage or destination goals without compromising the benefits offered by the hybrid architecture. In an embodiment, the power control module 1216 is trained to maximize the benefits discussed herein.

[0150] Return to Figure 12The feature extraction component 1214 can be incorporated into the deep neural network. Alternatively, the feature extraction component 1214 can be located outside the deep neural network. The power control module 1216 uses the features obtained from the feature extraction component 1214 to generate a power output recommendation 1212. The power output recommendation 1212 may include, for example, information related to the power or energy or C-rate 522 required to meet immediate or extended distance or mileage targets based on a request from the application 1204. The power output recommendation 1212 may also include information for indicating the predicted state of one or more components of the power supply system 100 and indications for mitigating predicted / potential failure modes. Furthermore, the power output recommendation 1212 may include information related to which high-energy-density hybrid modules 112 the defined power output is obtained, the charging or discharging rate of the battery cell 114 or traction battery through one or more bidirectional DC-DC converters 502, the start time of said charging or discharging, and the optimized path, etc. These examples are not intended to be limiting, and any combination of these examples and other examples of power output suggestions can be similar to the description. The power control module 1216 can be based, for example, on neural networks such as recurrent neural networks (RNNs) and dynamic neural networks (DNNs), but this is not intended to be limiting. An RNN is an artificial neural network designed to identify patterns in data sequences, such as digital time series prediction or forecasting, and to perform digital time series anomaly detection using data from sensors, thereby generating image descriptions and text summaries. RNNs use regressive connections (opposite to the direction of the “normal” signal flow), which form loops in the network topology. Computations derived from earlier inputs are fed back into the network, giving RNNs “short-term memory.” Feedback networks such as RNNs are dynamic; the “state” of the feedback network changes continuously until it reaches an equilibrium point. Therefore, RNNs are particularly well-suited for detecting cross-time relationships in a given dataset. Recurrent networks take not only the current input examples they see as their input, but also what they have previously perceived in time as their input. The decisions of the recurrent network arriving at time step t-1 influence the decisions that will arrive at a later time step t. Therefore, recurrent networks have two input sources: the current input and the most recent past input. These two input sources are combined to determine how they respond to new data. DNNs rely on the dynamic declaration of the network structure. In a conventional static model, a computation graph (typically defined as a symbolic representation of the computations utilizing the neural network) is then fed into an engine that performs that computation and computes its derivatives. However, for static graphs, the input size must be defined at the beginning, which can be inconvenient for applications with variable inputs.However, in DNNs, a dynamic declaration strategy is used, where the computational graph is implicitly constructed by executing procedural code that computes the network output, given the ability to use different network structures for each input. Therefore, during training, the computational graph can be redefined for each training example. Thus, the computational graph is dynamically built immediately after the input variables are declared. Consequently, the graph is flexible and allows modification and examination of its internal features at any time. Therefore, instead of maintaining relationships between all inputs and layers of the neural network, decisions can be made to dynamically change the structure of the neural network to cause a corresponding change in the output when defined parameters exceed a threshold level of priority increase, addressing the new functional requirements of the power supply system 100 caused by priority increase, and vice versa. Therefore, in a dynamic neural network, the output depends on the input, the current and past values ​​of the output, and the network structure. Neural networks with this feedback are suitable for system modeling, identification, control, and filtering operations, and are particularly important for nonlinear dynamic power supply systems. Of course, the examples are non-limiting, and other examples can be obtained from the specification.

[0151] In an illustrative embodiment, the power output recommendation 1212 may be presented by the presentation component 1208 of application 1204. The adaptation component 1210 is configured to receive input from the user to adapt the power output recommendation 1212 as necessary. For example, changing the route recommended by the power control module 1216 results in a recalculation of the recommended power output taking into account the terrain and distance of the new route.

[0152] Feedback component 1218 optionally collects user feedback 1224 relative to the power output recommendation 1212. In one embodiment, application 1204 is configured not only to calculate the power output recommendation 1212, but also to provide a method for user input feedback, wherein the feedback indicates the accuracy of the calculated power output recommendation 1212. Feedback component 1218 applies feedback from machine learning techniques to profiles 1222, 1224, 1230, or M / L model 1206 to modify M / L model 1206 to obtain better recommendations. In an illustrative embodiment, the application analyzes the feedback input and applies enhancements to the M / L model 1206 of the power control module 1216. If the feedback is positive or unsatisfactory regarding the accuracy of the recommendation, the application strengthens or weakens the parameters of M / L model 1206, respectively. In an example, the recommendation is to turn on the hybrid range extender battery 124 30 miles before reaching the mountain, so that at the summit, there will be sufficient battery capacity and power so that power throttling is not required at the summit. However, when it is determined that the power at the mountain top is actually limited and therefore may be maintained at a lower rate than expected, inaccurate feedback is given to the power control module 1216 regarding the recommendations / predictions.

[0153] The input layer of the neural network model can be, for example, a vector representing the current, voltage, or impedance values ​​of battery cell 114, pixels of a 2D image of terrain data, contextual calendar data provided by NLP engine 1228, etc. In the example, a CNN (Convolutional Neural Network) uses convolution to extract features from the input image. In an embodiment, upon receiving a request to provide a suggestion, application 1204 creates an array of values ​​that are input to the input neurons of M / L model 1206 to produce an array containing power output suggestions 1212.

[0154] The neural network M / L model 1206 is trained using various types of training datasets, including stored profiles and a large number of sample vehicle and battery cell measurement results. As shown in the block diagram, an example training architecture 1302 for machine learning-based recommendation generation according to an illustrative embodiment is illustrated. Figure 13 As shown, the program code extracts various features 1306 from training data 1304. The components of training data 1304 have a label L. Features are used to develop a prediction function H(x) or hypothesis, which is used by the program code as an M / L model 1308. In identifying various features in training data 1304, the program code may utilize various techniques, including but not limited to mutual information, which is an example of a method that can be used to identify features in the embodiments. Other embodiments may utilize varying techniques to select features, including but not limited to principal component analysis, diffusion mapping, random forests, and / or recursive feature elimination (a brute-force method for feature selection). “P” is an available output (e.g., a power output value, a high-energy-density hybrid module 112 from which the power output value is obtained, etc.), which, upon receipt, may further trigger the power supply system 100 or the vehicle to perform other steps, such as steps of stored instructions. The program code can use the machine learning m / L algorithm 1312 to train (this training includes providing weights for the output) the M / L model 1308, enabling the program code to prioritize various changes based on the prediction function including the M / L model 1308. The output can be evaluated using a quality metric 1310.

[0155] By selecting different sets of training data 1304, the program code trains the M / L model 1308 to identify and weight various features of the main electric vehicle 1232, the driver, the vehicle convoy, environmental conditions, etc. To utilize the M / L model 1308, the program code obtains (or derives) input data or features to generate an array of values ​​input to the input neurons of the neural network. In response to these inputs, the output neurons of the neural network produce an array including power output suggestions 1212 to be presented or used simultaneously.

[0156] refer to Figure 14This figure depicts a flowchart of an example process 1400 for providing a power output recommendation for an electric vehicle according to an illustrative embodiment. It can be used... Figure 12 The application 1204 is used to process 1400.

[0157] In step 1402, process 1400 independently measures parameters of each of the multiple battery cells of at least one high-energy-density hybrid module of the power supply system via at least one hybrid module controller (HMC). The multiple battery cells are connected in series in at least one high-energy-density hybrid module.

[0158] In step 1404, process 1400 receives measured parameters of the battery cell as at least a portion of a set of main electric vehicle parameters used by the power control module to indicate one or more characteristics of the main electric vehicle. These parameters may include at least current, temperature, and voltage. Other parameters, including capacity, polarization profile with a graphitization plateau, and impedance (DC IR, AC IR), may be derived from single or time-series measurements of current, temperature, and voltage. For example, the polarization profile with a graphitization plateau (where iron insertion occurs) may be used by process 1400 to interpret the type of fault occurring in battery cell 114, such as lithium loss or loss of active sites storing lithium.

[0159] In step 1406, process 1400 generates input data using at least the main electric vehicle parameter set. In step 1408, process 1400 extracts one or more features from the input data, which represent a request to complete the power output recommendation operation, such as a user's calendar with an upcoming meeting. Feature extraction may be separate from the model or included in one or more layers of the model tuned during training. Figure 15 As shown, one or more features may also represent attributes obtained from the attribute prioritization step 1502. In attribute prioritization 1502, one or more attributes 1510 are obtained for consideration in the power output recommendation operation. One or more attributes may have different assigned priorities or weights, or may have the same or even no assigned priority or weight. By training the M / L model 1206 with a large number of different datasets considering attribute 1510, different scenarios can be addressed by the power control module 1216. In illustrative and non-limiting embodiments, attribute 1510 includes indications for maximizing or enforcing the safety attribute 1504, maximizing the lifetime attribute 1506, and maximizing the capacity attribute 1508. In step 1410, the process 1400 uses the power control module to propose at least one power output recommendation for the main electric vehicle.

[0160] At least one power output recommendation may consider attributes, due to attribute priority ordering 1502, namely, maximizing the safety 1504 of the power supply system 100. In an illustrative embodiment, maximizing safety means considering possible or observed activities in the battery cell chemistry (e.g., a short circuit between the anode and cathode manifested as self-discharge), wherein the power control module 1216 recommends and implements a pause in the operation of the segmented / high-energy-density hybrid module 112 of the battery pack without affecting other modules / high-energy-density hybrid modules 112 (a step that would otherwise be unavailable in a conventional battery pack). Implementation may also include removing energy from or discharging the high-energy-density hybrid module 112 and shutting it off to isolate it for safety benefits. Furthermore, by observing an abnormal temperature rise without any corresponding current change, the power control module 1216 can infer a fire event or circuit board failure, and thus discharge the corresponding module near the temperature rise to prevent the spread of fire or failure. In another example, by observing the isolation loss between chassis 304 and the high-voltage bus, the power control module reduces the charging state of one or more modules and provides service warnings, thereby maximizing the safety of the power supply system 100 (and thus the electric vehicle).

[0161] At least one power output recommendation may consider attribute priority ranking 1502, namely the maximum lifespan 1506 of the power supply system 100. In an illustrative embodiment, maximizing lifespan includes maximizing the health of the battery cell 114, i.e., the battery's ability to discharge current. By observing an increase in battery impedance, the power supply system 100 causes a change in the maximum current of the battery cell 114 to avoid overheating or "overloading" of the battery cell 114, thereby maximizing the lifespan of the battery cell 114. Therefore, a defined discharge power is determined to compensate for the health state of the battery cell 114. In this embodiment, impedance is measured based on the discharge and recharge of the battery cell and a comparison of discharge parameters and recharge parameters with an ideal standard, wherein the battery cell 114 is graded in a SOH grading operation. The battery cell 114 is, for example, graded as A, B, C, D, and E, where A represents high SOH and E represents low SOH. Therefore, in this embodiment, all modules with battery cells 114 classified as D and E can be operated by the power control module 1216 at a C-rate 522 of C / 10, and modules with battery cells classified as B and C can be operated at a C-rate 522 of C / 5, and modules with battery cells classified as A can be operated at a C-rate 522 of C / 3. The operating C-rate 522 is the discharge power limit of each high-energy-density hybrid module 112. The power control module 1216 keeps learning and adjusting according to these limitations that combine safety and capacity attributes. Thus, if a battery cell 114 is classified as A and its modules are offline due to safety issues, another battery cell 114 can be upgraded from B to A, or the modules of that other battery cell can be configured with a more "busy" duty cycle due to the absence of the offline battery cell 114.

[0162] Due to attribute priority ranking 1502, at least one power output recommendation can consider the maximum capacity 1508 of the power supply system 100. In the illustrative embodiment, the capacity is maximized by identifying the impedance problem of the battery cell. For a battery cell with high impedance, the power control module 1216 can operate the corresponding high energy density hybrid module 112 at the lowest C rate 522 to provide energy for the longest time and thus maximize capacity, even if it is unlikely that the high energy density hybrid module 112 would be operated first based solely on lifetime attribute 1510. Furthermore, for a series of battery cells in a group, the capacity of the group is limited by the weakest battery cell. If all battery cells have 100 Ah and the weakest battery cell has 60 Ah, the weakest battery cell limits the other battery cells because once zero charge is reached, the remaining battery cells in the series cannot be discharged further to avoid damaging the weakest battery cell. The power control module 1216 operates to avoid capacity divergence between battery cells to protect the weakest battery cell and prevent it from being burdened. In addition, the power control module 1216 can discharge the weakest battery cell and slowly charge it during formation charging to restore the capacity of the battery cell.

[0163] Therefore, in the illustrative embodiment, the power control module 1216 operates based on the advantages and disadvantages of the system for maximizing lifespan, safety, capacity, and other attributes, while also taking into account input data such as geography, maximum current, and rate, and predicting how to benefit attribute objectives by reviewing all inputs. Frequent / periodic SOH checks allow for the grading of battery cells / modules to keep track of their health status and make informed decisions. For example, a calendar can be used to view upcoming journeys and whether SOH checks can be performed to identify weak battery modules, thus determining whether improvements can be made. Identified weak battery modules can be charged very slowly before the journey to address health issues encountered during the journey.

[0164] Therefore, computer-implemented methods, systems, or devices and computer program products are provided in the description of power supply and other related features, functions, or operations for electric vehicles. Specifically, embodiments of a portion of the computer-implemented method, system, or device and computer program product are described with respect to a type of apparatus, wherein the computer-implemented method, system, or device, computer program product, or a portion thereof is adapted or configured for use with a suitable and comparable manifestation of that type of apparatus.

[0165] When embodiments are described as implementations within an application, the delivery of an application in a Software as a Service (SaaS) model is considered within the scope of the illustrative embodiments. In the SaaS model, the ability to implement an application embodiment is provided to the user by executing the application within a cloud infrastructure. Users can access the application using various client devices through a lightweight client interface such as a web browser (e.g., web-based email) or other lightweight client applications. Users do not manage or control the underlying cloud infrastructure (including networks, servers, operating systems, or storage devices within the cloud infrastructure). In some cases, users may not even manage or control the functionality of the SaaS application. In some other cases, the SaaS implementation of an application may allow for possible exceptions to limited user-specific application configuration settings.

[0166] This invention can be an integrated system, method, and / or computer program product at any possible level of technical detail. The computer program product may include a computer-readable storage medium (or medium) having computer-readable program instructions on it for causing a processor to execute aspects of the invention.

[0167] A computer-readable storage medium can be a tangible means capable of retaining and storing instructions used by an instruction execution device. A computer-readable storage medium can be, for example, but not limited to, electronic storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. A non-exhaustive list of more specific examples of computer-readable storage media includes: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable optical disc read-only memory (CD-ROM), digital versatile disc (DVD), memory sticks, floppy disks, mechanically encoded means (such as punched cards or raised structures in slots containing recorded instructions), and any suitable combination thereof. Computer-readable storage media, including but not limited to computer-readable storage devices as used herein, should not be construed as instantaneous signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides, or other transmission media (e.g., light pulses passing through fiber optic cables), or electrical signals transmitted over lines.

[0168] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a corresponding computing / processing device or to an external computer or external storage device via a network (e.g., the Internet, a local area network, a wide area network, and / or a wireless network). The network may include copper cables, optical fibers, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. Network adapter cards or network interfaces in each computing / processing device receive the computer-readable program instructions from the network and forward them for storage in a computer-readable storage medium within the corresponding computing / processing device.

[0169] Computer-readable program instructions used to perform the operations of this invention may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, configuration data for integrated circuits, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​(such as Smalltalk or C++) and procedural programming languages ​​(such as the "C" programming language or similar programming languages). The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)) or may be connected to an external computer (e.g., via the Internet provided by an Internet service provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs) may perform aspects of the invention by executing the computer-readable program instructions using state information from the computer-readable program instructions to personalize the electronic circuitry.

[0170] The aspects of the present invention are described herein as relating to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that computer-readable program instructions can implement the individual blocks in the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams.

[0171] These computer-readable program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create components for implementing the functions / actions specified in one or more boxes of a flowchart and / or block diagram. These computer-readable program instructions may also be stored in a computer-readable storage medium that can instruct a computer, programmable data processing apparatus, and / or other means to function in a particular manner, such that the computer-readable storage medium storing the instructions includes an article of manufacture comprising instructions for implementing aspects of the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0172] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer-implemented process, such that the instructions, which execute on the computer, other programmable apparatus or other device, implement the function / action specified in one or more boxes of a flowchart and / or block diagram.

[0173] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, blocks in the flowcharts or block diagrams may represent modules, segments, or portions of instructions comprising one or more executable instructions for implementing (one or more) a specified logical function. In some alternative implementations, the functions indicated in the blocks may occur in a sequence other than that indicated in the figures. For example, two blocks shown consecutively may actually be executed substantially simultaneously, or sometimes the blocks may be executed in reverse order, depending on the functions involved. It will also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a system based on dedicated hardware that performs a specific function or action or executes a combination of dedicated hardware and computer instructions.

Claims

1. A power supply system for an electric vehicle, the power supply system comprising: A traction battery is configured to connect and disconnect from the high-voltage DC bus of the electric vehicle to supply power to the electric vehicle. A hybrid range extender battery comprising multiple high-energy-density hybrid modules connected in parallel, wherein each high-energy-density hybrid module includes a corresponding hybrid module controller (HMC) and multiple battery cells connected in series; and Multiple bidirectional DC-DC converters are correspondingly arranged between the multiple high-energy-density hybrid modules and the high-voltage DC bus of the electric vehicle; Each of the arranged bidirectional DC-DC converters operably couples DC current from the corresponding high-energy-density hybrid module to the traction battery and / or power system via the high-voltage DC bus of the electric vehicle, so as to charge the traction battery and / or supply power to the electric vehicle accordingly. The traction battery comprises a first chemical type and a cell energy density of no more than 500 Wh / L; and The hybrid range extender battery includes a second chemical type different from the first chemical type and has a battery cell energy density of not less than 1000Wh / L.

2. The power supply system according to claim 1, wherein, Each of the plurality of high-energy-density mixing modules is configured with chemicals that prioritize high energy density over available cycle life.

3. The power supply system according to claim 1, wherein, The traction battery includes one or more traction modules controlled by a battery management system (BMS).

4. The power supply system according to claim 1, wherein, The traction battery has one or more traction modules, which are multiple traction modules connected in series.

5. The power supply system according to claim 1, wherein, Each of the plurality of battery cells is configured to be independently measurable by its respective HMC.

6. The power supply system according to claim 1, wherein, The plurality of high-energy-density hybrid modules are configured to manage charging and / or discharging via corresponding bidirectional DC-DC converters.

7. The power supply system according to claim 1, wherein, The corresponding HMC of the high energy density hybrid module is also configured to manage the power generation mode of the power supply system by controlling the charging and discharging rate of the high energy density hybrid module of the HMC using sensor information obtained from battery cells that can be measured independently.

8. The power supply system of claim 1 further includes a balancing device for each battery cell of the high energy density hybrid module, the balancing device being configured to selectively discharge the charge stored in the battery cell.

9. The power supply system according to claim 8, wherein, The balancing device is a shunt resistor connected in parallel with each battery cell.

10. The power supply system according to claim 1, wherein, The hybrid range extender battery comprises a variety of chemicals.

11. The power supply system according to claim 1, wherein, At least one high-energy-density hybrid module has a battery cell with a battery cell energy density of 1000Wh / L or greater than 1000Wh / L.

12. The power supply system according to claim 1, wherein, The range extender battery has a cycle life of 200 cycles.

13. The power supply system according to claim 1, wherein, The traction battery is separated from the hybrid range extender battery.

14. The power supply system according to claim 1, wherein, The traction battery is load-following.

Images