Vehicle maintenance method for evaluating the battery status of an electrochemical power battery installed in a vehicle

Abstract

The present application relates to a vehicle maintenance method for evaluating the battery status of an electrochemical power battery (10) installed in a vehicle (100), the method comprising: connecting (S110) a mobile measuring device (20) to the vehicle (100) for establishing an electrical connection between the mobile measuring device (20) and the power battery (10) in a state of being installed in the vehicle (100); performing maintenance measurement (S130) to obtain maintenance measurement data (72), including measuring an electrical impedance spectrum of the power battery (10); transmitting (S140) the maintenance measurement data (72) to a server (80); and evaluating (S160) the maintenance measurement data (72) on the server (80) using a trained machine learning algorithm (84), including processing the measured electrical impedance spectrum and generating an output representing battery status information (74); transmitting (S170) the battery status information (74) to a mobile communication device (50); and outputting (S180) the battery status information (74) to a user.

Description

[0001] The present invention relates to a vehicle maintenance method for evaluating the battery status of an electrochemical traction battery of a vehicle, for example a traction battery of an industrial vehicle (such as an industrial truck or forklift, a truck, a construction machine, etc.) or a traction battery of an electric locomotive, etc. SUMMARY OF THE INVENTION

[0003] Electric vehicles rely heavily on batteries for power, which makes testing the remaining capacity of the battery critical to ensure its optimal performance, efficiency, and safety. Typically, the battery must be disassembled for accurate and reliable capacity testing. However, battery removal is associated with certain disadvantages. Removing a battery from an industrial vehicle for capacity testing means temporarily stopping the vehicle from operation. This downtime affects productivity and interrupts workflow. Battery removal requires skilled technicians, specialized equipment, and additional time. The process of removing and reinstalling the battery can carry the risk of battery damage or mishandling.

[0004] The object of the present invention is to provide a vehicle maintenance method which simplifies the assessment of the battery state of an electrochemical power battery of the vehicle.

[0005] It is desirable that the method allow the battery state of batteries of the same kind to be assessed in a simple and time-saving manner.

[0006] It would be desirable to be able to assess the battery status of a battery without requiring battery history information and without reading the battery's battery management system.

[0007] The invention is specified in the independent claim. Further embodiments are specified in the dependent claims.

[0008] According to one aspect of the present invention, a vehicle maintenance method is provided, the method using a mobile communication device (50) and a mobile measurement device to evaluate the battery state of an electrochemical power battery installed in the vehicle, the mobile measurement device being configured to perform electrical impedance spectrum measurement on the electrochemical battery electrically connected to the mobile measurement device (20), the method comprising:

[0009] Connecting the mobile measuring device to the vehicle to establish an electrical connection between the mobile measuring device and the power battery installed in the vehicle;

[0010] performing maintenance measurements on the power battery to obtain maintenance measurement data, wherein the maintenance measurements are performed by the mobile measurement device when the power battery is in a state in which it is installed in the vehicle, and wherein performing the maintenance measurements includes measuring an electrical impedance spectrum of the power battery;

[0011] transmitting maintenance measurement data from the mobile measurement device to the mobile communication device;

[0012] transmitting the maintenance measurement data from the mobile communication device to the server via the communication network; and

[0013] Evaluate maintenance measurement data using trained machine learning algorithms on the server,

[0014] Among them, the use of trained machine learning algorithms to evaluate maintenance measurement data includes:

[0015] The measured electrical impedance spectrum of the power battery is input into the machine learning algorithm.

[0016] The measured electrical impedance spectrum is processed by a machine learning algorithm, and

[0017] generating an output by the machine learning algorithm, wherein the output represents battery status information associated with the power battery, wherein the method further comprises:

[0018] transmitting battery status information associated with the power battery to the mobile communication device via the communication network; and

[0019] The battery status information is output to the user by the mobile communication device or the mobile measuring device.

[0020] For example, the vehicle may be a forklift, a truck, a construction machine or any other kind of battery-driven industrial vehicle, or an electric locomotive. In particular, the vehicle may be an electric vehicle or a hybrid vehicle.

[0021] By using a mobile communication device to communicate with the server, the steps performed by the mobile communication device can be performed by a general mobile communication device. In addition, the mobile communication unit can be easily used at the vehicle (e.g., on site). For example, the mobile communication device can be a mobile computing and communication device. For example, the mobile communication device can be a laptop computer, a tablet computer, or a mobile phone (such as a smart phone). The mobile communication device can be configured to control a mobile measurement device. The mobile communication device may include software configured to control the steps to be performed by the mobile measurement device. For example, the mobile communication device may include an application software configured to control the mobile measurement device to perform the steps performed by the mobile measurement device. In particular, the mobile measurement device can be controlled to perform the corresponding steps of the method. For example, the application software can be configured to control the mobile measurement device to perform one or more of the following steps: perform maintenance measurement on the power battery to obtain maintenance measurement data; transmit the maintenance measurement data from the mobile measurement device to the mobile communication device. The mobile communication device may include software configured to perform the steps performed by the mobile communication device. For example, the mobile communication device may include the above-mentioned application software or an application software configured to perform one or more of the following steps: receiving maintenance measurement data from the mobile measurement device; transmitting the maintenance measurement data to a server via a communication network; obtaining battery status information associated with the power battery from the server via the communication network; and outputting the battery status information to the user.

[0022] The mobile measuring device may also be referred to as a portable measuring device. For example, the mobile measuring device may include a measuring connector for connecting the mobile measuring device to a vehicle and / or to a power battery installed in the vehicle. For example, the measuring connector may be configured to connect the mobile measuring device to the battery pole of a power battery in a state of being installed in a vehicle. For example, the measuring connector may be configured to implement a 4-terminal measurement (or Kelvin measurement) of a battery. This is particularly important for accurately measuring electrical impedance. Therefore, a 4-terminal electrical connection of the mobile measuring device to the power battery may be established. For example, the measuring connector may be a flexible measuring connector that may be integrated in a flexible connecting cable. For example, the measuring connector may be arranged to extend to the outside of the housing of the mobile measuring device. For example, the mobile measuring device may be configured to be controlled by a mobile communication device to perform the following steps: performing maintenance measurements on the power battery to obtain maintenance measurement data; and / or transmitting the maintenance measurement data from the mobile measuring device to the mobile communication device.

[0023] For a vehicle maintenance method, a simple and user-friendly method is provided that allows the battery state of an electrochemical power battery of a vehicle to be evaluated when the power battery is in the state in which it is installed in the vehicle. The method allows the battery state of the installed power battery to be evaluated in a simple and time-saving manner by connecting a mobile measuring device to the vehicle or in particular to the power battery and performing maintenance measurements by the mobile measuring device. That is, for an electrochemical power battery installed in a vehicle, the electrical impedance spectrum of the battery is measured by a mobile communication device.

[0024] The vehicle maintenance method can allow an electrochemical power battery installed in a vehicle to be evaluated independently of the battery history of the power battery and in particular without reading the battery management system of the power battery. Thus, the battery state can be reliably evaluated even if the exact battery history is not available.

[0025] Thus, the vehicle maintenance method can allow a quick and reliable assessment of the battery state of an electrochemical power battery installed in a vehicle, making it possible to estimate, for example, the remaining capacity of the battery. Thus, the method can allow ensuring optimal performance, efficiency and safety of the power battery without removing the battery from the vehicle.

[0026] The vehicle maintenance method simplifies the evaluation of the battery status of an electrochemical power battery. Keeping the battery in the vehicle while evaluating the battery status prevents downtime when the vehicle is temporarily out of service due to removal of the battery from the vehicle, thereby allowing the user to save money. Furthermore, the need for skilled technicians and specialized equipment is reduced, as is the risk of damage when removing and reinstalling the battery.

[0027] The vehicle maintenance method may be a method for evaluating the battery state of an electrochemical power battery mounted to a vehicle on-site. The step of performing maintenance measurements on the power battery may be a step of performing on-site maintenance measurements on the power battery.

[0028] The measured maintenance measurement data are transmitted from the mobile measurement device to the mobile communication device. For example, the mobile measurement device may include a communication unit. In particular, the mobile measurement device may be connected to the mobile communication device via the communication unit of the mobile measurement device, or the mobile measurement device may include a wireless communication unit for communicating with the mobile communication device. For example, the mobile measurement device may transmit the maintenance measurement data to the mobile communication device via the communication unit of the mobile measurement. For example, the mobile communication device may include a communication unit. In particular, the mobile communication device may be connected to the mobile measurement device via the communication unit of the mobile communication device, or the mobile communication device may include a wireless communication unit for communicating with the mobile measurement device. The communication unit of the mobile measurement device and / or the communication unit of the mobile communication device may respectively include a serial data communication interface, such as a universal serial bus interface, a Bluetooth communication unit or any other communication link in the prior art.

[0029] The mobile communication device is configured to transmit the maintenance measurement data to the server via the communication network. In particular, the mobile communication device may be configured to transmit the maintenance measurement data to the server via the mobile communication unit of the mobile communication device. The server may be a remote server. The communication network may be a remote communication network. For example, the communication network may include the Internet and / or a mobile communication network. Thus, the mobile communication device and the server may be configured for remote communication. For example, the server may include a communication unit. In particular, the server may be configured to communicate with the mobile communication device via the communication unit of the server.

[0030] The method may include performing an electrical impedance spectroscopy (EIS) measurement on the power battery when the power battery is in a state where it is installed in a vehicle, and the electrical impedance spectroscopy (EIS) measurement includes the measurement of the electrical impedance spectrum of the power battery. Electrical impedance spectroscopy measurement may also be referred to as electrical impedance spectroscopy measurement. Measuring the electrical impedance spectrum of the power battery may include recording the electrical impedance spectrum. Using electrochemical impedance spectroscopy, the electrochemical process in the electrochemical cell is characterized by electrical measurement results, which characterize the AC response of the electrochemical cell to an applied AC signal. In addition to the structural configuration and the configuration of the internal connector, the chemical process in the battery also results in a characteristic frequency correlation of the measured impedance. During the electrical impedance measurement at a specific measurement frequency, a DC offset signal (offset voltage or offset current) or a DC bias signal may be applied to the battery, which is modulated by the AC signal of the measurement frequency.

[0031] The EIS measurement or the measurement of the electrical impedance spectrum can include multiple electrical impedance measurements at different measurement frequencies. For example, the number of different measurement frequencies can be at least four, at least eight, at least 16, at least 32 or at least 64. For example, the corresponding measurement frequency can be the frequency of the signal input to the electrochemical cell. For example, the signal can be a sinusoidal signal. Preferably, each electrical impedance value of the electrical impedance spectrum measured includes a complex number, which defines the real part and the imaginary part of the corresponding electrical impedance. That is, the spectrum is a complex spectrum. Preferably, the electrical impedance spectrum measured adopts the form of digital representation. The electrical impedance of the corresponding measurement frequency can be measured in any order and / or simultaneously.

[0032] Preferably, the measuring frequency comprises a measuring frequency in the range of 0.1 Hz to 1.0 Hz.

[0033] Preferably, the measurement frequencies include measurement frequencies in the range of 1 kHz to 10 kHz. Preferably, the number of different measurement frequencies in the range of 0.1 Hz to 5000 Hz is at least four, at least eight, at least 16, at least 32 or at least 64. Preferably, the measurement frequencies include at least 4 (four) measurement frequencies per decade of the measurement frequency range, more preferably at least five measurement frequencies per decade of the measurement frequency range.

[0034] The maintenance measurement data is evaluated using a trained machine learning algorithm on the server. In particular, the machine learning algorithm is configured to receive a measured electrical impedance spectrum of the battery as input. The machine learning algorithm may be a machine learning algorithm trained based on at least training measurement data of each of a plurality of batteries of the same type as the power battery. The training measurement data may include a remaining battery capacity of the corresponding battery and an electrical impedance spectrum of the corresponding battery.

[0035] In the present disclosure, batteries of the same kind are understood to include batteries having the same nominal battery parameters or nominal characteristics (battery parameters / characteristics according to the manufacturer), in particular, batteries having the same nominal voltage, the same nominal capacity (e.g., in mAh) and the same nominal energy capacity (e.g., in Wh) (if applicable). In the present disclosure, the method can also be applied to batteries of the same kind selected based on common and / or similar usage or use locations when there is no difference in the known battery parameters, or when the batteries are batteries of the same kind according to their appearance. Battery parameters that can be considered may include at least one of voltage rating, capacity rating, energy rating, nominal voltage, nominal battery capacity (e.g., in mAh), nominal energy capacity (e.g., in Wh), manufacturer's battery type information or code, battery cell chemistry information, voltage of each battery cell, number of battery cells in the battery, etc. In the present disclosure, the term "multiple batteries of the same kind" or "battery of the same kind" refers to the type of battery. The kind of battery may include the type of battery (or battery type).

[0036] In this document, the term "battery" or in particular "power battery" should be understood to include battery cells. The battery may include one or more battery cells. In particular, the term "battery" includes battery cells and batteries consisting of multiple battery cells. In particular, an electrochemical (power) battery is understood to define a device consisting of one or more electrochemical battery cells with external electrical connections. For example, a battery may include two external electrical connections for drawing power from one or more electrochemical battery cells, and in the case of a rechargeable electrochemical battery, for (re)charging one or more electrochemical battery cells. For example, the electrochemical battery may be a lithium-ion battery or a lead-acid battery.

[0037] For example, the machine learning algorithm may be or may include at least one of: an artificial neural network, a support vector machine, a k-nearest neighbor algorithm, and a machine learning decision tree.

[0038] The neural network can be configured to process the measured electrical impedance spectrum. For example, the neural network can include a deep neural network (DNN). The deep neural network has an input layer, more than one hidden layer and an output layer. For example, the neural network can include a convolutional neural network (CNN). The convolutional neural network has an input layer, at least one convolutional layer and an output layer. CNN can be a deep neural network.

[0039] For example, a machine learning algorithm may be configured to process the measured electrical impedance spectrum to generate an output. The machine learning algorithm may be a machine learning algorithm trained based on training measurement data of at least one battery. For example, the training measurement data may be used to perform the training machine learning algorithm. The trained machine learning algorithm is used to evaluate the maintenance measurement data. For example, the trained machine learning algorithm may be applied to the maintenance measurement data, and in particular, the trained machine learning algorithm may be applied to the electrical impedance spectrum of the power battery by inputting the electrical impedance spectrum of the power battery into the machine learning algorithm. The machine learning algorithm is processing the electrical impedance spectrum and generating an output. For example, a server may include software configured to perform the following steps: inputting the measured electrical impedance spectrum of the battery into the machine learning algorithm, processing the measured electrical impedance spectrum by the machine learning algorithm, and generating an output by the machine learning algorithm. The electrical impedance spectrum is used as an input in the step of inputting the measured electrical impedance spectrum, and the battery state may be an output (target value) in the step of generating an output by the machine learning algorithm. Therefore, the output representing the battery state information may be determined based on the processing of the measured electrical impedance spectrum by the machine learning algorithm. For example, the output of the machine learning algorithm may be referred to as a prediction. In particular, the battery state information output to the user may be the output of the machine learning algorithm.

[0040] The server transmits the generated battery status information associated with the power battery to the mobile communication device via the communication network. The mobile communication device can output the battery status information associated with the power battery to the user. For example, the output of the battery status information can be performed by the mobile communication device or the mobile measurement device.

[0041] For example, the server may be configured to transmit the output of the machine learning algorithm to the mobile communication device via the communication network. For example, the server may be configured to transmit battery status information to the mobile communication device via the communication network.

[0042] For example, the mobile communication device may be configured to output the output of the machine learning algorithm to the user. For example, the mobile communication device or the mobile measurement device may be configured to output the battery status information according to the output of the machine learning algorithm to the user. For example, the mobile measurement device or the mobile communication device may include an output unit configured to output the battery status information to the user.

[0043] In the present disclosure, when a mobile measuring device, a mobile communication device or a server is configured to transmit measurement results, data or information to a server, a mobile measuring device or a mobile communication device, respectively, the corresponding server, mobile measuring device or mobile communication device may be configured to receive the measurement results, data or information accordingly.

[0044] For example, the battery status information may be output by the mobile communication device or the mobile measurement unit via an output unit such as a display, a printer and / or a computer. The battery status information may be displayed and / or printed. For example, a label indicating the battery status information may be printed.

[0045] In an embodiment, the method further comprises the step of obtaining identification data of the power battery by the mobile measuring device or by the mobile communication device. The identification data may include at least one of an identification code (such as a serial number) and information related to the battery type of the power battery (such as a battery type code).

[0046] In an embodiment, the step of obtaining the identification data of the power battery includes: scanning a battery barcode using an input device. For example, the battery barcode may be scanned from the power battery. The battery barcode may include the identification data of the power battery. For example, the mobile measurement device or the mobile communication device may include the input device. The input device may include a scanner or a camera.

[0047] For example, based on the obtained identification data, the mobile measurement device, the mobile communication device or the server can determine information related to the battery type of the power battery. The battery type can include the type of battery or the battery type.

[0048] In an embodiment, the battery status information may include at least one of a remaining battery capacity, a state of health, and a classification. For example, the output of the machine learning algorithm may represent one of a remaining battery capacity, a state of health (SoH), and a classification. For example, the output of the machine learning algorithm may be one of an estimated remaining battery capacity, an estimated state of health, and a classification. For example, the estimated state of health (SoH) may be determined by dividing the estimated remaining battery capacity (output by the machine learning algorithm) by the nominal battery capacity associated with the battery type of the power battery. This may be represented by the following equation: SoH = estimated remaining battery capacity / nominal battery capacity. The nominal battery capacity may be the battery capacity of the power battery in its original condition (or manufacturing condition) according to the battery type. For example, the classification may be determined according to the estimated state of health and / or according to the estimated battery capacity. This does not exclude that additional parameters may be used additionally to determine the classification.

[0049] The classification that the machine learning algorithm and / or the mobile communication device or the mobile measurement device can output is a classification of battery status. It can also be called a battery grade or a battery rating. For example, the classification is selected from a certain number of classes, categories, grades or ratings. The number is, for example, less than 10, or less than 8, or in the range of 3 to 6. For example, the number can be 4 or 5. For example, the classes can be "A", "B", "C" and "D". The number may depend on the type of battery to be evaluated.

[0050] For example, when performing maintenance measurement on a power battery, in addition to the electrical impedance spectroscopy measurement or measuring the electrical impedance spectrum of the power battery, no battery capacity measurement is performed. Since there is no need to charge or discharge the power battery, the maintenance measurement can be performed in a short time.

[0051] In an embodiment, the measured impedance spectrum of the power battery includes the electrical impedance spectrum of the entire power battery and / or the electrical impedance spectrum of at least one battery string in a plurality of battery strings of the power battery. Therefore, measuring the electrical impedance spectrum of the power battery may include measuring the electrical impedance spectrum of the entire power battery and / or measuring the electrical impedance spectrum of at least one battery string in a plurality of battery strings of the power battery. For example, the mobile measuring device may be configured to measure the electrical impedance spectrum of the entire power battery and / or the electrical impedance spectrum of at least one battery string in a plurality of battery strings of the power battery.

[0052] The maintenance measurement data may further include a measurement result of a DC voltage of the power battery, or a measurement result of a DC voltage of at least one battery string among a plurality of battery strings of the power battery.

[0053] In an embodiment, the step of connecting the mobile measurement device to the vehicle comprises connecting the mobile measurement device to a vehicle bus interface of the vehicle, such as a controller area network (CAN) bus. For example, the mobile measurement device may be configured to connect to a serial data bus of the vehicle. In particular, the mobile measurement device may be configured to connect to a controller area network (CAN) bus of the vehicle.

[0054] In an embodiment, the method further includes: selecting at least one battery string among the multiple battery strings of the power battery and / or the entire power battery via the vehicle bus interface of the vehicle for measuring the electrical impedance spectrum, wherein the measured electrical impedance spectrum includes the electrical impedance spectrum of at least one battery string among the multiple battery strings of the selected power battery and / or the entire power battery. For example, the mobile measuring device can be configured to perform the step of selecting at least one battery string among the multiple battery strings of the power battery and / or the entire power battery via the vehicle bus interface of the vehicle for measuring the electrical impedance spectrum. In particular, the mobile communication device can be configured to control the mobile measuring unit to select at least one battery string among the multiple battery strings of the power battery and / or the entire power battery via the vehicle bus interface.

[0055] In an embodiment, the method comprises: obtaining identification data of the power battery by the mobile measuring device via the vehicle bus interface of the vehicle. Therefore, the step of obtaining identification data of the power battery can be performed by the mobile measuring device obtaining identification data of the power battery via the vehicle bus interface of the vehicle.

[0056] In an embodiment, the step of connecting the mobile measuring device to the vehicle comprises: connecting at least one temperature sensor to the battery and / or connecting the mobile measuring device to at least one temperature sensor of the battery. For example, the mobile measuring device may be configured to connect to at least one temperature sensor of the battery.

[0057] In an embodiment, the step of performing maintenance measurements includes measuring a temperature value of the power battery. In particular, the step of performing maintenance measurements may include measuring a temperature value of at least one of a plurality of battery strings of a power battery and / or the entire power battery (in particular, at least one of a plurality of battery strings of a selected power battery and / or the entire power battery). In particular, the maintenance measurement data may include a temperature value of the power battery. In particular, the maintenance measurement data may include a temperature value of at least one of a plurality of battery strings of a power battery (for example, selected) and / or the entire power battery.

[0058] In an embodiment, the method comprises: before transmitting the maintenance measurement data from the mobile communication device to the server via the communication network, caching the maintenance measurement data on the mobile communication device. For example, the step of transmitting the maintenance measurement data from the mobile communication device to the server may comprise caching the maintenance measurement data on the mobile communication device. In particular, the mobile communication device may be configured to perform the step of caching the maintenance measurement data on the mobile communication device in the case where the communication network is not available. The mobile communication device may be configured to perform the step of transmitting the cached maintenance measurement data from the mobile communication device to the server in the case where the communication network is available.

[0059] In an embodiment, the method further comprises: training the machine learning algorithm using the maintenance measurement data as training measurement data. The server may be configured to perform the step of training the machine learning algorithm by using the maintenance measurement data as training measurement data. For example, the training step may be performed automatically. Thus, the step of training a machine learning algorithm (e.g., a neural network) based on the maintenance measurement data as training measurement data may be self-learning or self-training of the machine learning algorithm or the neural network. In the present disclosure, the terms "self-learning" and "self-training" are used synonymously.

[0060] In an embodiment, the machine learning algorithm is a machine learning algorithm trained based on training measurement data for each of a plurality of batteries of at least two different types of batteries. Information and / or identification data related to the (identified) battery type (type of battery) may be additionally transmitted to the server, for example as part of the maintenance measurement data. Information related to the battery type may be additionally input to the machine learning algorithm. Additionally or alternatively, in an embodiment, the server may be configured to provide (implement) one or more additional machine learning algorithms, wherein each machine learning algorithm (including the initially mentioned machine learning algorithm) is associated with a corresponding battery type. In particular, training of each machine learning algorithm may be performed based on corresponding training measurement data for each battery type. The server may be configured to perform steps to adapt the machine learning algorithm to the identified battery type. In the following, in order to simplify the description, only one machine learning algorithm is described. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Hereinafter, preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, in which:

[0062] Figure 1 A schematic diagram showing a vehicle maintenance method for evaluating a battery state of an electrochemical power battery installed in a vehicle;

[0063] Figure 2 A schematic diagram of evaluating a battery state of an electrochemical power battery installed in a vehicle using a vehicle maintenance method is shown.

[0064] Figure 1 A vehicle maintenance method for evaluating a battery state of an electrochemical power battery installed in a vehicle is schematically shown, and Figure 2 Schematically shows the use of Figure 1 The illustrated vehicle maintenance method evaluates the battery status of an electrochemical power battery installed to the vehicle.

[0065] In step S110, the mobile measuring device 20 is connected to the power battery 10 mounted to the vehicle 100 through the flexible measuring connector of the flexible cable 40. The power battery 10 is connected to the measuring unit 24 of the mobile measuring device 20 using the flexible cable 40 having four terminals 42 for connecting the power battery 10. At least one temperature sensor 44 of the battery 10 or at least one temperature sensor 44 of the mobile measuring device 20 can be connected to the mobile measuring device 20 via a temperature sensor connector 46. In addition, the mobile measuring device 20 is connected to a vehicle bus interface 48 of the vehicle 100, in particular, to a controller area network (CAN) bus of the vehicle 100.

[0066] In step S120, identification data of the battery type including the power battery 10 may be obtained by the mobile measurement device 20. This may be accomplished by scanning a barcode using the input device 28 or a built-in camera of the mobile communication device 50, or by communicating via the vehicle bus interface 48.

[0067] In step S130, when the power battery 10 is in a state where it is installed in the vehicle 100, the mobile measuring device 20 performs maintenance measurement on the power battery 10 to obtain maintenance measurement data 72. Performing the maintenance measurement S130 includes measuring the electrical impedance spectrum of the power battery 10. The mobile measuring device 20 can select at least one battery string of the multiple battery strings of the power battery 10 and / or the entire power battery 10 to measure its electrical impedance spectrum. Several battery strings of the power battery 10 can be selected in sequence for sequentially measuring the corresponding electrical impedance spectra.

[0068] Performing maintenance measurement S130 may include measuring the temperature of power battery 10. The temperature measurement may be performed using temperature sensor 44 or using a built-in temperature sensor of power battery 10 that may be read via vehicle bus interface 48. Performing maintenance measurement S130 may include measuring the DC voltage of power battery 10.

[0069] The measuring unit 24 of the mobile measuring device 20 is controlled by the controller 22 of the mobile measuring device 20. The mobile communication device 50 is configured for controlling the mobile measuring device 20. In particular, the mobile communication device 50 comprises software configured for controlling the mobile measuring device 20 to perform maintenance measurements. The software can be controlled by a user via a graphical user interface 56.

[0070] In step S140, the maintenance measurement data 72 is transmitted from the mobile measuring device 20 to the mobile communication device 50. In particular, the measured maintenance measurement data 72 may be transmitted from the mobile measuring device 20 to the mobile communication device 50 via the communication unit 60 of the mobile communication device 50 by the communication unit 26 of the mobile measuring device 20. The mobile communication device 50 may be connected to the mobile measuring device 20, for example, via a serial communication interface such as a USB (Universal Serial Bus), or the maintenance measurement data 72 may be transmitted by wireless communication. In addition, the maintenance measurement data 72 includes identification data of the power battery 10 or the battery type.

[0071] In step S150, the maintenance measurement data 72 is transmitted from the mobile communication device 50 to the remote server 80 via the remote communication network 70. In particular, the maintenance measurement data 72 is transmitted by the remote communication unit 62 of the mobile communication device 50 to the remote communication unit 82 of the remote server 80.

[0072] The mobile communication device 50 may cache the maintenance measurement data 72 on the mobile communication device 50. In particular, where the remote communication network 70 is available for communication between the mobile communication device 50 and the remote server 80, the cached maintenance measurement data 72 may be transmitted from the mobile communication device 50 to the remote server 80.

[0073] In step S160, the maintenance measurement data 72 is evaluated on the server 80 using the trained machine learning algorithm 84 on the server 80. The server 80 inputs the transmitted maintenance measurement data 72 into the trained machine learning algorithm 84, and the maintenance measurement data 72 includes the measured electrical impedance spectrum of the power battery 10. The electrical impedance spectrum of the power battery 10 is processed by the trained machine learning algorithm 84. The trained machine learning algorithm 84 generates an output representing the battery status information 74 of the power battery 10. In particular, the battery status information is at least one of the remaining battery capacity, the state of health (SoH), and the classification. For example, the battery status information 74 may include the state of health of the power battery 10 and the grade or classification determined by classifying the power battery 10 according to the determined state of health.

[0074] The machine learning algorithm 84 of the server 80 includes an artificial neural network having an input layer 86, at least one hidden layer 88, and an output layer 90. The input layer 86 is configured to accept as input the electrical impedance spectrum measured by the mobile measurement device 20. The neural network is configured to process the electrical impedance spectrum and generate an output 74 at its output layer 90 based on the electrical impedance spectrum. The output 74 of the machine learning algorithm 84 represents the battery status information 74 of the power battery 10.

[0075] In step S170 , the battery status information 74 of the power battery 10 is transmitted to the mobile communication device 50 via the remote communication network 70 .

[0076] In step S180, the mobile communication device 50 outputs the battery status information 74 of the power battery 10 to the user via the output unit 54 (such as a display). For example, a grade or classification ("A") and a graphical display of the health status may be output.

Claims

1. A vehicle maintenance method for evaluating the battery state of an electrochemical power battery (10) mounted to a vehicle (100) using a mobile communication device (50) and a mobile measurement device (20), wherein the mobile measurement device (20) is configured to perform electrical impedance spectroscopy measurements on an electrochemical battery electrically connected to the mobile measurement device (20), the method comprising: Connecting (S110) the mobile measuring device (20) to the vehicle (100) to establish an electrical connection between the mobile measuring device (20) and the power battery (10) installed in the vehicle (100); performing maintenance measurements (S130) on the power battery (10) to obtain maintenance measurement data (72), wherein the maintenance measurements are performed by the mobile measurement device (20) when the power battery (10) is in a state where it is installed in the vehicle, and wherein performing the maintenance measurements (S130) includes measuring an electrical impedance spectrum of the power battery (10); transmitting (S140) the maintenance measurement data (72) from the mobile measurement device (20) to the mobile communication device (50); transmitting (S150) the maintenance measurement data (72) from the mobile communication device (50) to a server (80) via a communication network (70); and evaluating (S160) the maintenance measurement data (72) using a trained machine learning algorithm (84) on the server (80), Wherein, evaluating (S160) the maintenance measurement data (72) using the trained machine learning algorithm (84) comprises: inputting the measured electrical impedance spectrum of the power battery (10) into the machine learning algorithm (84), processing the measured electrical impedance spectrum by the machine learning algorithm (84), and generating an output by the machine learning algorithm (84), wherein the output represents battery status information (74) associated with the power battery (10), Wherein, the method further comprises: transmitting (S170) the battery status information (74) associated with the power battery (10) to the mobile communication device (50) via the communication network (70); and The battery status information (74) is output (S180) to a user by the mobile communication device (50) or the mobile measuring device (20).

2. The method according to claim 1, further comprising: The identification data of the power battery (10) is obtained (S120) by the mobile measuring device (20) or by the mobile communication device (50).

3. The method according to claim 2, wherein: The step of obtaining (S120) the identification data of the power battery (10) comprises: using an input device (28) to scan a battery barcode.

4. A method according to any one of the preceding claims, wherein: The battery status information (74) includes at least one of remaining battery capacity, health status, and classification.

5. A method according to any one of the preceding claims, wherein: The measured impedance spectrum of the power battery (10) includes an electrical impedance spectrum of the entire power battery (10) and / or an electrical impedance spectrum of at least one battery string among a plurality of battery strings of the power battery (10).

6. A method according to any one of the preceding claims, wherein: The step of connecting (S110) the mobile measuring device (20) to the vehicle (100) includes connecting the mobile measuring device (20) to a vehicle bus interface (48) of the vehicle (100).

7. A method according to any one of the preceding claims, wherein: The method further includes: selecting at least one battery string among the multiple battery strings of the power battery (10) and / or the entire power battery (10) via a vehicle bus interface (48) of the vehicle (100) for measuring the electrical impedance spectrum, wherein the measured electrical impedance spectrum includes the electrical impedance spectrum of at least one battery string selected among the multiple battery strings of the power battery (10) and / or the entire power battery (10).

8. A method according to any one of the preceding claims, wherein: The method comprises: obtaining (S120) identification data of the power battery (10) by the mobile measuring device (20) via a vehicle bus interface (48) of the vehicle (100).

9. A method according to any one of the preceding claims, wherein: The step of connecting (S110) the mobile measuring device (20) to the vehicle (100) comprises connecting at least one temperature sensor (44) to the battery (10) and / or connecting the mobile measuring device (20) to at least one temperature sensor (44) of the battery (10).

10. A method according to any one of the preceding claims, wherein: The step of performing the maintenance measurement (S130) includes measuring a temperature value of at least one battery string among a plurality of battery strings of the power battery (10) and / or the entire power battery (10).

11. A method according to any one of the preceding claims, wherein: The method comprises: buffering (S200) the maintenance measurement data (72) on the mobile communication device (50) before transmitting (S150) the maintenance measurement data (72) from the mobile communication device (50) to the server (80) via the communication network (70).

12. The method according to any one of the preceding claims, further comprising: The machine learning algorithm (84) is trained (S190) using the maintenance measurement data (72) as training measurement data.

Images