Method and system for controlling vehicle battery pack based on battery health model

Abstract

Methods and systems for controlling a vehicle battery pack based on a battery health model are provided. Controlling an electric vehicle having a battery pack includes, after a plurality of charge-discharge operations of the battery pack, controlling power usage of the battery pack based on battery health measurements from a battery health model that uses a plurality of detected battery health inputs, the plurality of detected battery health inputs includes a current lifetime and an initial throughput characteristic of the electric vehicle.

Description

Technical Field

[0001] The present disclosure generally relates to managing a battery pack of an electric vehicle. Background Art

[0002] An electric vehicle (EV) includes a battery pack, sometimes referred to as a traction battery, for providing power to an electric motor to propel the EV. One or more operating characteristics of the battery pack can be monitored to evaluate the battery health (e.g., state of health (SOH)) of the EV and / or control the operation of the battery pack. Summary of the Invention

[0003] A method for controlling an electric vehicle (EV) having a battery pack includes: after a plurality of charge-discharge operations of the battery pack, controlling power usage of the battery pack based on battery health measurements from a battery health model that uses a plurality of detected battery health inputs, the plurality of detected battery health inputs including a current life and initial throughput characteristics of the EV.

[0004] A system for controlling an electric vehicle having a battery pack includes: one or more processors and one or more memories storing programming instructions executable by the one or more processors and causing the one or more processors to control power usage of the battery pack after a plurality of charge-discharge operations of the battery pack based on battery health measurements from a battery health model that uses a plurality of detected battery health inputs, the plurality of detected battery health inputs including a current life and initial throughput characteristics of the electric vehicle.

[0005] A vehicle includes: a battery pack; and one or more processors that control power usage of the battery pack based on battery health measurements from a battery health model that uses a plurality of detected battery health inputs, the plurality of detected battery health inputs including a current life and initial throughput characteristics of the vehicle. Brief Description of the Drawings

[0006] Figure 1 Shows a vehicle service server that communicates with an electric vehicle to provide battery health measurements of the electric vehicle according to the present disclosure;

[0007] Figure 2 is an example block diagram of an electric vehicle according to the present disclosure;

[0008] Figure 3 is a block diagram of a battery pack and a battery controller according to the present disclosure; and

[0009] Figure 4It is a flowchart of an exemplary battery control routine in accordance with the present disclosure. Detailed implementation

[0010] As needed, detailed embodiments of the present invention are disclosed herein; however, it should be understood that the disclosed embodiments are merely examples of the present invention that can be implemented in various forms and alternative forms. The drawings are not necessarily to scale; some features may be enlarged or minimized to show details of particular components. Thus, the specific structural details and functional details disclosed herein are not to be construed as limiting, but rather as a representative basis for teaching those skilled in the art to practice the present invention in various ways.

[0011] Estimating and monitoring the performance and health of a battery pack is commonly used to evaluate whether the battery pack, which may be the main power source in an EV, is reliable, efficient, and capable of delivering power and energy when needed. Battery health, which can be provided as state of health (SOH), is a known metric used to control the charging rate, estimate the state of charge (SOC), plan the route of an EV, and plan battery maintenance and other tasks / operations involving the battery pack.

[0012] In one form, the present disclosure provides a vehicle battery health monitoring (VBHM) system that employs a battery health model trained using simulated data and real-world data to estimate battery health measurements in real time. More specifically, an EV is configured to provide battery health inputs to a vehicle service server, which in turn uses the battery health model to estimate battery health measurements. In some applications, the EV is configured to control the operation of the battery pack based on the battery health model.

[0013] Among other features, the VBHM system also provides a model that is scalable at the retail customer level to, for example, analyze multiple EVs with similar characteristics together. The VBHM system also predicts / estimates SOH in real time and / or provides a distributed computing platform to support SOH assessment, thereby removing the computational load from the EV and making the battery health model accessible to various EVs.

[0014] Reference Figure 1, one or more EV 100A, EV 100B, EV 100C (collectively referred to as "EV 100") communicate with a vehicle service server 102, which is a cloud-based server remote from the EV 100. As described in detail herein, the vehicle service server 102 uses the battery health model and battery health inputs from the respective EV 100 to detect the battery health measurements of the EV 100. In some variations, the vehicle service server 102 may also provide vehicle control recommendations to the respective EV 100 based on the battery health measurements. In one form, one of the EV 100 and the vehicle service server 102 form a VBHM system 104 for the EV 100.

[0015] In one form, the EV 100 is provided as a battery electric vehicle (BEV) powered by an electric motor. In a non-limiting example, reference Figure 2 , the EV 100 includes a powertrain having one or more electric motors 204 (i.e., electric machines), a battery pack 206 (i.e., traction battery), and a power electronics module 208. The EV 100 of the present disclosure does not include an engine, and thus, the battery pack 206 provides all of the propulsion power. In other variations, the present disclosure may be applied to other types of EVs, such as plug-in hybrid electric vehicles (PHEVs) having an engine, and is not limited to pure EVs.

[0016] The electric motor 204 provides the powered movement of the EV 100, and in a non-limiting example, the electric motor is mechanically connected to a transmission 210, the transmission is mechanically connected to a drive shaft 212, and the drive shaft is mechanically connected to the wheels 214 of the EV 100. In addition to providing propulsion power, the electric motor 204 may also be configured to operate as a generator to recover energy that would otherwise be lost as heat in the friction braking system of the EV 100.

[0017] The battery pack 206 provides a high voltage (HV) direct current (DC) output that is used to power the electric motor 204 via the power electronics module 208. In one form, the power electronics module 208, which may include an inverter, provides a bi-directional transfer of energy between the battery pack 206 and the electric motor 204. Specifically, as is known, the power electronics module 208 converts the DC voltage to a three-phase AC current to operate the electric motor 204, and in the regenerative mode, the power electronics module 208 converts the three-phase AC current from the electric motor 204 acting as a generator to a DC voltage compatible with the battery pack 206.

[0018] The battery pack 206 can be recharged by an external power source 220 (e.g., the power grid), which is electrically connected to an electric vehicle supply equipment (EVSE) 222. The EVSE 222 provides circuits and controls to control and manage the electrical energy transfer between the external power source 220 and the EV 100. The external power source 220 can supply DC or AC power to the EVSE 222. The EVSE 222 can have a charging connector 224 for insertion into a charging port 226 of the EV 100.

[0019] The EV 100 can also include a power conversion module 228, which is an on-vehicle charger with a DC / DC converter to regulate the power supplied from the EVSE 222 and provide a suitable voltage level and current level to the battery pack 206. The power conversion module 228 can dock with the EVSE 222 to coordinate the power delivery to the battery pack 206.

[0020] In addition to providing electrical energy for propulsion, the battery pack 206 can also provide electrical energy for other electrical systems in the EV 100, such as high-voltage (HV) loads like electric heaters and air-conditioning systems, and low-voltage (LV) loads like auxiliary batteries. Additionally, the battery pack 206 is configured to have a bi-directional power transfer capability to provide power to systems external to the EV 100 (i.e., external systems), such as but not limited to homes, enterprises, and / or microgrids. In a non-limiting example, the battery pack 206 is electrically connected to an external system using the EVSE connector 224 and is operable to provide energy based on the transient load recommended for the external system and the amount of energy available from the battery pack 206.

[0021] In one form, the EV 100 includes a control system 230, which can also be referred to as a "vehicle controller" to coordinate the operation of various components. The control system 230 includes electronics, software, or both to perform the necessary control functions for operating the EV 100. The control system 230 can be a combination of a vehicle control system and a powertrain control module (VSC / PCM). Although the control system 230 is shown as a single device, the control system 230 can also include multiple controllers in the form of multiple hardware devices, or multiple software controllers with one or more hardware devices. In this regard, the reference to "controller" herein can refer to one or more controllers.

[0022] In one form, the EV 100 includes a battery controller (BC) 232 that is configured to monitor one or more operating characteristics of the battery pack 206 and control the operation of the battery pack 206 at least based on the operating characteristics using known techniques (e.g., manage the charging / discharging of the battery pack 206). The BC 232 communicates with one or more battery sensors (BS) 234 provided in the battery pack 206 to detect at least some of the operating characteristics. As described in detail below, the BC 232 is also configured to obtain battery health inputs and monitor the health of the battery pack 206 by requesting battery health measurement results based on the battery health inputs from the vehicle service server 102.

[0023] The EV 100 includes other devices / systems for performing tasks other than propelling the EV 100. In a non-limiting example, the EV 100 includes a communication system 236 that is configured to communicate with devices / servers external to the EV 100 (such as the vehicle service server 102) using wireless communication, which is established using cellular communication, WI-FI, Bluetooth, and / or other communication technologies. Thus, in addition to other components, the communication system 240 also includes at least one of the following: a telematics control unit configured to establish vehicle-to-everything (V2X) communication, a global navigation satellite system (GNSS), and / or a Bluetooth module having a Bluetooth transceiver.

[0024] The EV 100 also includes one or more sensors 238 throughout the EV 100 to detect various characteristics in and / or around the EV 100. In a non-limiting example, the sensors 242 include one or more temperature sensors that detect the temperature in the passenger compartment of the EV 100 and the external temperature (i.e., the external ambient temperature).

[0025] The control system 230, BC 232, communication system 236, sensors 238, and other devices / controllers / modules in the EV 100 communicate information with each other via the vehicle network 244. In a non-limiting example, the vehicle network 244 can be a wired network (such as a controlled local area network (CAN)) or a wireless communication network.

[0026] Reference Figure 3 , the battery pack 206 includes a plurality of battery cells 302 that are electrically coupled to each other and electrically coupled to a positive power bus 304A and a negative power bus 304B (collectively referred to as "power buses 304"). Although four battery cells 302 are shown, the battery pack 206 can include two or more battery cells 302. Additionally, although the battery cells 302 are depicted as being arranged in series, the battery cells 302 can be connected in series, parallel, or in a combination thereof.

[0027] In one form, the battery sensor 234 communicates with the BC 232 to provide data indicative of electrical characteristics (voltage and / or current) and / or temperature. In a non-limiting example, the battery sensor 234 includes a current sensor 306, a voltage sensor 308, and a battery pack temperature (temp.) sensor 310. The current sensor 306 is configured to detect the current output from (i.e., discharged) or input to (i.e., charged) the battery pack 206. The voltage sensor 308 is configured to detect the terminal voltage of the battery pack 206. The battery pack temperature sensor 310 (e.g., a thermistor) is configured to detect the temperature of the battery pack 206, and while one temperature sensor 310 is provided, multiple temperature sensors may be used.

[0028] In one form, the BC 232 is configured to control the operation of the battery pack 206 and perform a battery health check (BHC), and includes a battery control module 320 and a BHC module 322. In one form, the battery control module 320 is configured to detect and monitor the operating characteristics of the battery pack 206 using defined algorithms and data from the battery sensor 234 and other devices (such as but not limited to a control system 230 that provides a desired output of the electric motor 204). In a non-limiting example, the operating characteristics of the battery pack 206 include: the charge capacity of the battery pack 206, the state of charge (SOC), the throughput of the battery pack 206 (i.e., the power capacity), and / or temperature. In one form, the battery control module 320 is configured to store data regarding the operating characteristics in a data store 324.

[0029] The charge capacity of the battery pack 206 indicates the maximum amount of electrical energy that the battery pack 206 can store. The SOC of the battery pack 206 indicates the current amount of charge stored in the battery pack 206. The SOC of the battery pack 206 can be expressed as a percentage of the charge capacity, which can be stored by the BC 232.

[0030] The throughput of the battery pack 206 is a measure of the total amount of energy that can be charged / discharged over the entire life of the battery pack 206, and can be measured in ampere-hours (Ah). To this end, the throughput of the battery pack 206 corresponds to the discharge power limit and the charge power limit, which define the amount of electrical power that can be supplied by or supplied to the battery pack 206 at a given time.

[0031] In one form, the battery control module 320 provides one or more of the operating characteristics to the control system 230 such that the control system 230 knows how much power the battery pack 206 can provide (discharge) or absorb (charge). Accordingly, the control system 230 operates, for example, the powertrain to meet the user's performance requirements. The battery control module 320 can also provide the operating characteristics to other systems that can draw power from or supply power to the battery pack 206.

[0032] The BHC module 322 is configured to detect and monitor battery health measurements of the battery pack 206. More specifically, the BHC module 322 is configured to obtain a BHC input and request battery health measurements from the vehicle service server 102 based on the BHC input. In one form, the BHC input includes an initial throughput characteristic, a vehicle life measurement, a throughput characteristic, a previous state of health (SOH) measurement, and an average ambient temperature during a selected period associated with the plurality of charge-discharge operations, and an incremental throughput characteristic during the selected period. In some variations, the BHC input can include other data such as, but not limited to, the temperature of the battery pack 206.

[0033] The initial throughput characteristic is the original or, in other words, the first throughput characteristic measurement defined at the time of manufacturing the EV 100 and can be stored by the BHC module 322. The throughput characteristic is the throughput of the battery pack 206 and indicates the ampere power passing through the battery pack 206 and is routinely measured after a plurality of charge-discharge operations during a selected period.

[0034] The vehicle life measurement indicates the current life of the EV 100, which can be provided using at least one of mileage and / or numerical life.

[0035] The average ambient temperature is the average of the temperature measurements of the external environment during a selected period. That is, the temperature at which the EV 100 travels and thus operates can affect battery health. For example, low temperatures may increase the internal resistance of the battery cells and thus reduce the current capacity of the battery pack 206, while high temperatures may reduce the efficiency of the chemical reactions within the battery cells 302.

[0036] In addition to the battery health input, the BHC module 322 can also provide other information to the vehicle service server 102 such as, but not limited to: vehicle identification (e.g., vehicle identification number, make / model of the vehicle, model year of the vehicle) and a timestamp.

[0037] In operation, the BHC module 322 is configured to monitor the vehicle life that can be provided by the control system 230 and the number of charging / discharging operations being performed provided by the battery control module 320. After a selected time period (which may be associated with a selected number of charging / discharging operations to be performed), a selected cumulative mileage (e.g., 100 miles, 500 miles, etc.), and / or a selected duration (e.g., weekly), the BHC module obtains BHC inputs and forwards a request for battery health measurements to the vehicle service server 102 via the communication system 230.

[0038] As described herein, the vehicle service server 102 determines the battery health measurement results and provides the battery health measurement results and the recommended control operations (if any) for the battery pack 206. Once the battery health measurement results are received, the BHC module 322 stores the battery health measurement results, and the battery control module 320 is configured to control the operation of the battery pack 206 based on the battery health measurement results or the recommended control operations (if any).

[0039] Reference Figure 1 , the vehicle service server 102 is configured to include a Battery Health Model (BHM) database 120, a Battery Health Record (BHR) database 122, a Battery Health module 124, and a Vehicle Control Recommendation (VCR) module 126. The vehicle service server 102 may include other modules / controllers, such as but not limited to known communication systems for establishing communication with the EV 100.

[0040] The BHM database 122 is configured to store a plurality of battery health models that are employed by the battery health module 124 to determine the battery health measurement results for the requesting EV 100. In one form, the battery health model uses the battery health inputs and the initial throughput characteristics of the requesting EV 100 to provide the battery health measurement results. In one form, the battery health measurement results provide an indication of the State of Health (SOH) change (i.e., incremental SOH) of the current current capacity relative to the initial (first measured) current capacity.

[0041] In one form, a physics-based model and a regression-based machine learning algorithm are used to define a battery health model to map battery health inputs (e.g., initial throughput characteristics, vehicle life measurements, throughput characteristics, previous SOH measurements, and average ambient temperature, etc.) to an incremental SOH as an output. More specifically, in a non-limiting example, the physics-based model is trained simulation data and real-world data from various EVs. Various regression-based machine learning platforms can be employed, such as but not limited to XGBoost-type models. Thus, instead of a pure mathematical algorithm, the battery health model provides a data-driven method for estimating battery health measurements, which can be provided as battery health measurements.

[0042] In some variations, the BHM database 122 stores battery health models for different types of EVs such that the battery health models for EV 100A and EV 100B are different from that of EV 100C because EV 100A and EV 100B are SUVs and have different performance requirements than EV 100C, which is a sedan. Additionally, the BHM database 122 can store battery health models for different operating states of the battery pack 206 and / or the EV 100. In a non-limiting example, the operating states can include a driving state, a charging state, and a shutdown state, in which the battery pack 206 is substantially at the external ambient temperature. Each of these states can have a different impact on battery health. In some applications in which the battery pack 206 is operable to provide bidirectional power transfer, the battery health model can be trained to use measurements of health inputs that reflect the battery pack 206 discharging to charge an external system (e.g., a home or a microgrid), which may have a different impact on battery health compared to discharging the battery pack 206 to provide power to, for example, an on-vehicle system. Thus, the battery health inputs from the EV 100 can indicate the operating state of the EV 100 relative to the battery health inputs.

[0043] The BHR database 122 is configured to store EV records associated with the EV 100 that requests battery health measurements. In a non-limiting example, the EV records can include: vehicle identification (e.g., vehicle identification number, make / model of the EV); initial throughput characteristics of the EV100; a battery health model identification indicating the file name of one or more battery health models for the EV 100; a calculation history including battery health inputs from the EV and the estimated battery health measurements; and recommended control actions (if any) for the EV 100.

[0044] The battery health module 124 is configured to estimate battery health measurement results of the requesting EV 100. Specifically, the battery health module 124 receives a message from the requesting EV 100, where the message includes information such as, but not limited to, vehicle identification and battery health inputs. Using the received information, the battery health module 124 obtains an EV record associated with the EV 100 from the BHR database 122 and selects a battery health model from the BHM database 120. Then, the battery health module 124 uses the battery health input to estimate the incremental SOH.

[0045] In one form, the VCR module 126 is configured to provide recommended operation control for the battery pack 206 based at least on the battery health measurement results estimated by the battery health module 124. In a non-limiting example, the VCR module 126 is configured to define a plurality of condition controls that determine whether the estimated incremental SOH is within a nominal range, and if not, provide recommendations designed to reduce the rate of degradation of the SOH, where such recommendations are developed via experimentation, analysis of real-life data to identify trends / relationships between one or more battery health inputs and the incremental SOH. For example, if multiple fast charging operations within a short period of time are identified as increasing the rate of degradation of the battery pack 206, the VCR module 126 is configured to implement the recommended operation control, which includes limiting the DC charging rate of the fast charging operation.

[0046] Reference Figure 4 Referring, a battery control routine 400 performed by the VBHM system 104 is provided. At operation 402, the system 104 obtains battery health inputs after a plurality of charge-discharge operations of the EV 100 of the system 104. In one form, the battery health inputs include vehicle life, throughput characteristics, previous SOH measurement results, average ambient temperature during a selected period associated with the plurality of charge-discharge operations, and incremental throughput characteristics during the selected period. At operation 404, the system 104 selects a battery health model from a plurality of available battery health models based at least on vehicle identification data associated with the EV 100. Other information can be used to select the battery health model, such as, but not limited to, the operating state associated with the battery health input. At operation 406, the system 104 is configured to estimate battery health measurement results using the battery health inputs, initial throughput characteristics, and the selected battery health model. At operation 408, the system 104 is configured to control the power usage of the battery pack 206 based on the battery health measurement results. More specifically, in a non-limiting example, the system 104 is configured to determine whether the battery health measurement result (which can be the change (i.e., incremental) SOH) is within a nominal threshold, and if not, the system 104 provides recommended control operations for the battery pack 206.

[0047] While the foregoing describes exemplary embodiments, these embodiments are not intended to describe all possible forms of the invention. Rather, the words used in the specification are descriptive words rather than limiting words, and it is to be understood that various changes may be made without departing from the spirit and scope of the invention. Additionally, the features of various embodiments may be combined to form further embodiments of the invention.

[0048] In this application, the term "module" may refer to, be part of, or include the following: an application specific integrated circuit (ASIC); a digital, analog, or mixed analog / digital discrete circuit; a digital, analog, or mixed analog / digital integrated circuit; a combinatorial logic circuit; a field programmable gate array (FPGA); a processor circuit (shared, dedicated, or group) that executes code; a memory circuit (shared, dedicated, or group) that stores code executed by the processor circuit; other suitable hardware components that provide the described functionality; or a combination of some or all of the above, such as in a system on a chip.

[0049] The term "memory" or "memory device" is a subset of the term "computer-readable medium". As used herein, the term computer-readable medium does not cover transitory electrical or electromagnetic signals propagated through a medium (such as on a carrier wave); thus, the term computer-readable medium can be considered tangible and non-transitory. Non-limiting examples of non-transitory tangible computer-readable media are non-volatile memory circuits (such as flash memory circuits, erasable programmable read-only memory circuits, or mask read-only circuits), volatile memory circuits (such as static random access memory circuits or dynamic random access memory circuits), magnetic storage media (such as analog or digital magnetic tape or hard disk drives), and optical storage media (such as CDs, DVDs, or Blu-ray discs).

[0050] The devices and methods described in this application may be implemented, in part or in whole, by a special purpose computer created by configuring a general purpose computer to execute one or more specific functions embodied in a computer program. Functional blocks, flowchart components, and other elements described above serve as software specifications that may be translated into a computer program by routine work of a technician or programmer.

[0051] As used herein, the phrase "at least one of A, B, and C" should be construed to represent the logical (A or B or C) using non-exclusive logic "or", and should not be construed to mean "at least one of A, at least one of B, and at least one of C".

[0052] The description of the present disclosure is merely exemplary in nature and, thus, variations that do not depart from the essence of the present disclosure are intended to be within the scope of the present disclosure. Such variations should not be regarded as departing from the spirit and scope of the present disclosure.

[0053] According to the present invention, a method for controlling an electric vehicle (EV) having a battery pack includes: after a plurality of charge-discharge operations of the battery pack, controlling power usage of the battery pack based on battery health measurements from a battery health model that uses a plurality of detected battery health inputs, the plurality of detected battery health inputs including a current life and an initial throughput characteristic of the EV.

[0054] In one aspect of the present invention, the plurality of detected battery health inputs further include previous state of health (SOH) measurements, an average ambient temperature during a selected time period associated with the plurality of charge-discharge operations, and an incremental throughput characteristic during the selected time period.

[0055] In one aspect of the present invention, the battery health measurement is an incremental SOH indicating a current capacity relative to an initial current capacity.

[0056] In one aspect of the present invention, the method includes employing a physics-based model and a regression-based machine learning algorithm to define the battery health model.

[0057] In one aspect of the present invention, the method includes employing simulated data and real-world vehicle data to train the battery health model.

[0058] In one aspect of the present invention, the method includes selecting the battery health model from a plurality of battery health models stored in a database based at least on vehicle identification data associated with the EV.

[0059] In one aspect of the present invention, the battery health model is also selected based on an operating state associated with the battery health inputs.

[0060] In one aspect of the present invention, the operating state includes at least one of a driving state of the EV, a charging state of the EV, and a shutdown state of the EV.

[0061] According to the present invention, there is provided a system for controlling an electric vehicle having a battery pack, the system having: one or more processors; and one or more memories configured to store programming instructions executable by the one or more processors and configured to cause the one or more processors to control power usage of the battery pack based on battery health measurements from a battery health model after a plurality of charge-discharge operations of the battery pack, the battery health model using a plurality of detected battery health inputs including a current life and initial throughput characteristics of the electric vehicle.

[0062] According to an embodiment, the plurality of detected battery health inputs further include previous health state measurements, an average ambient temperature during a selected period associated with the plurality of charge-discharge operations, and incremental throughput characteristics during the selected period.

[0063] According to an embodiment, the battery health measurement result is an incremental health state indicating a current current capacity relative to an initial current capacity.

[0064] According to an embodiment, the programming instructions further cause the one or more processors to define the battery health model using a physics-based model and a regression-based machine learning algorithm.

[0065] According to an embodiment, the programming instructions further cause the one or more processors to train the battery health model using simulated data and real-world vehicle data.

[0066] According to an embodiment, the programming instructions further cause the one or more processors to select the battery health model from a plurality of battery health models stored in a database based at least on vehicle identification data associated with the electric vehicle.

[0067] According to an embodiment, the battery health model is also selected based on an operating state associated with the battery health inputs.

[0068] According to an embodiment, the operating state includes at least one of a driving state of the electric vehicle, a charging state of the electric vehicle, and a stopped state of the electric vehicle.

[0069] According to an embodiment, the present invention is further characterized by a plurality of sensors arranged on the electric vehicle to detect at least one of electrical characteristics of the battery pack and an external ambient temperature around the electric vehicle, wherein the plurality of detected battery health inputs are detected based on at least one of the electrical characteristics of the battery pack and the external ambient temperature around the electric vehicle.

[0070] According to the present invention, a vehicle is provided having: a battery pack; and one or more processors programmed to control power usage of the battery pack based on battery health measurements from a battery health model that uses a plurality of detected battery health inputs, the plurality of detected battery health inputs including a current life and an initial throughput characteristic of the vehicle.

[0071] According to an embodiment, the plurality of detected battery health inputs further includes a previous health state measurement, an average ambient temperature during a selected period associated with a plurality of charge-discharge operations, and an incremental throughput characteristic during the selected period.

[0072] According to an embodiment, the present invention is further characterized by a plurality of sensors for detecting at least one of electrical characteristics of the battery pack and an external ambient temperature around the vehicle, wherein the plurality of detected battery health inputs are detected based on at least one of the electrical characteristics of the battery pack and the external ambient temperature around the vehicle.

Claims

1. A method for controlling an electric vehicle (EV) having a battery pack, comprising: After a plurality of charge-discharge operations of the battery pack, power usage of the battery pack is controlled based on battery health measurements from a battery health model that uses a plurality of detected battery health inputs including current life and initial throughput characteristics of the EV.

2. The method of claim 1, wherein the plurality of detected battery health inputs further comprises previous state of health (SOH) measurements, an average ambient temperature over a selected time period associated with the plurality of charge-discharge operations, and an average throughput characteristic over the selected time period.

3. The method of claim 1, wherein the battery health measurement result is a delta SOH indicating a current current capacity relative to an initial current capacity.

4. The method of claim 1 further comprising employing a physics-based model and a regression-based machine learning algorithm to define the battery health model.

5. The method of claim 4 further comprising training the battery health model using simulated data and real-world vehicle data.

6. The method of claim 1, further comprising selecting the battery health model from a plurality of battery health models stored in a database based at least on vehicle identification data associated with the EV.

7. The method of claim 6, wherein the battery health model is selected further based on an operating state associated with the battery health input. 8 . The method of claim 7 , wherein the operating state includes at least one of a driving state of the EV, a charging state of the EV, and a stop state of the EV.

9. A system for controlling an electric vehicle having a battery pack, comprising: one or more processors; as well as One or more memories configured to store programming instructions executable by the one or more processors and configured to cause the one or more processors to control power usage of the battery pack based on battery health measurements from a battery health model after a plurality of charge-discharge operations of the battery pack, the battery health model using a plurality of detected battery health inputs including current life and initial throughput characteristics of the electric vehicle.

10. The system of claim 9, wherein the plurality of detected battery health inputs further include previous state of health measurements, an average ambient temperature over a selected time period associated with the plurality of charge-discharge operations, and an average throughput characteristic over the selected time period.

11. The system of claim 9, wherein the battery health measurement is a delta health state indicating a present current capacity relative to an initial current capacity.

12. The system of claim 9, wherein the programming instructions further cause the one or more processors to employ a physics-based model and a regression-based machine learning algorithm to define the battery health model.

13. The system of claim 12, wherein the programming instructions further cause the one or more processors to train the battery health model using simulated data and real-world vehicle data.

14. The system of claim 9, wherein the programming instructions further cause the one or more processors to select the battery health model from a plurality of battery health models stored in a database based at least on vehicle identification data associated with the electric vehicle.

15. The system of claim 14, wherein the battery health model is selected further based on an operating state associated with the battery health input.

Images