Battery health status assessment method, device and electronic equipment

Abstract

The present application relates to a battery health status assessment method, device and electronic device, belonging to the field of battery health monitoring technology, wherein the method includes: real-time acquisition of battery operation data collected by sensors; real-time acquisition of battery status data estimated by Kalman filter; normalization of the battery operation data and the battery status data to obtain time series data; inputting the time series data as input features into a well-trained deep learning model to obtain estimated battery health status data. The present application accurately estimates battery status data through an adaptive filter, uses the battery status data estimated by the filter and the battery operation data collected by the sensor as inputs to the deep learning model, realizes the deep fusion of the physical model and the data-driven model, and realizes high-precision and real-time evaluation of the battery health status.

Description

Technical Field

[0001] The present application relates to the technical field of battery health monitoring, and in particular to a battery health status assessment method, device and electronic equipment. Background Art

[0002] With the widespread application of electric vehicles, energy storage systems and portable electronic devices, the performance and safety of lithium-ion batteries have received great attention. During long-term use, batteries will experience aging phenomena such as capacity decay and increased internal resistance. Accurately evaluating the battery's state of health (SOH) is crucial to extending battery life and ensuring system safety.

[0003] Existing SOH assessment methods mainly include data-driven methods. In this method, it is usually difficult to obtain parameters that characterize the internal state of the battery in real time during parameter selection, and the estimated battery health status data has low accuracy. Summary of the invention

[0004] In view of this, it is necessary to provide a battery health status assessment method, device and electronic device to solve the problem in the prior art that it is difficult to obtain parameters characterizing the internal state of the battery in real time and the estimated battery health status data has low accuracy.

[0005] In order to solve the above problems, the present application provides a battery health status assessment method, including: Obtain battery operation data collected by sensors in real time; Real-time acquisition of battery status data estimated by the Kalman filter; Normalizing the battery operation data and the battery status data to obtain time series data; The time series data is input as input features into a well-trained deep learning model to obtain estimated battery health status data.

[0006] In some possible implementations, the battery operation data includes voltage, current, temperature, and state of charge data.

[0007] In some possible implementations, after acquiring the battery operation data collected by the sensor in real time, the method further includes: Performing filtering and denoising on the voltage and current data in the collected battery operation data to obtain denoised battery operation data; Performing time alignment on the data from different sensors in the denoised battery operation data to obtain synchronized battery operation data; The synchronized battery operation data is normalized to obtain normalized battery operation data.

[0008] In some possible implementations, the Kalman filter adopts a second-order RC equivalent circuit model, and the battery status data includes open circuit voltage, branch voltage, and internal resistance data of the battery.

[0009] In some possible implementations, the Kalman filter estimates the battery status data in real time by the following steps: The open circuit voltage and branch voltage of the equivalent circuit model corresponding to the Kalman filter are used as state vectors to construct state equations and observation equations, and initialize the state and error covariance matrices; According to the state equation, a predicted value of the state at the current moment is calculated based on the state at the previous moment, and a predicted value of the error covariance matrix at the current moment is calculated based on the error covariance matrix at the previous moment and the measurement noise covariance matrix at the previous moment; According to the observation equation, the Kalman gain at the current moment is updated based on the predicted value of the state at the current moment and the measurement noise covariance matrix at the current moment, and the process noise covariance matrix at the current moment is updated based on the predicted value of the state at the current moment and the Kalman gain at the current moment; According to the observation equation, the current state is updated based on the predicted value of the current state and the current Kalman gain, and the current error covariance matrix is ​​updated based on the predicted value of the current error covariance matrix and the current Kalman gain.

[0010] In some possible implementations, the calculation formula of the Kalman gain at the current moment is:

[0011]

[0012] In the formula, express The moment Kalman gain, express The predicted value of the moment error covariance matrix, express The moment measurement noise covariance matrix; The calculation formula of the process noise covariance matrix at the current moment is:

[0013]

[0014]

[0015] In the formula, express The moment process noise covariance matrix, express The moment process noise covariance matrix, express The moment Kalman gain, express The residual is measured at all times, express The measured value of the state at the moment, Represents the forgetting factor, which ranges from 0 to 1. Represents internal resistance, express Always input control.

[0016] In some possible implementations, the fully trained deep learning model includes an input layer, a Bi-LSTM layer, an attention mechanism layer, a fully connected layer and an output layer connected in sequence, based on the input layer being used to receive the input features, the Bi-LSTM layer being used to extract features of the time series data, the attention mechanism layer being used to perform weighted summation of the output features of the Bi-LSTM layer, the fully connected layer being used to map the output features of the attention mechanism layer to battery health status data, and the output layer being used to output the battery health status data.

[0017] In some possible implementations, the method further includes: When the amount of the estimated battery health status data reaches a preset value, an incremental learning algorithm is used to update the deep learning model.

[0018] The present application also provides a battery health status assessment device, comprising: A data acquisition unit, used for acquiring in real time the battery operation data collected by the sensor and the battery status data estimated by the Kalman filter; A data processing unit, used for normalizing the battery operation data and the battery status data to obtain time series data; A model evaluation unit is used to input the time series data as input features into a well-trained deep learning model to obtain estimated battery health status data.

[0019] The present application also provides an electronic device, including a memory and a processor; The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of the battery health status assessment method described above.

[0020] The beneficial effects of the present application are as follows: the battery health status assessment method provided by the present application accurately estimates the battery status data through an adaptive filter, uses the battery status data estimated by the filter and the battery operation data collected by the sensor as the input of the deep learning model, realizes the deep fusion of the physical model and the data-driven model, and combines the nonlinear fitting capability of the deep learning model to realize high-precision and real-time assessment of the battery health status. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flowchart of an embodiment of a battery health status assessment method provided in the present application; Figure 2 A schematic diagram of an embodiment of preprocessing battery operation data provided in the present application; Figure 3 Schematic diagram of the second-order RC equivalent circuit model provided for this application; Figure 4 A schematic diagram of an embodiment of a Kalman filter for real-time estimation of battery status data provided by the present application; Figure 5 A schematic diagram of the structure of an embodiment of a battery health status assessment device provided in the present application; Figure 6 A schematic diagram of the structure of an embodiment of an electronic device provided in this application. DETAILED DESCRIPTION

[0022] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0023] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed in order or implemented simultaneously. In addition, those skilled in the art may add one or more other operations to the flowcharts, or may remove one or more operations from the flowcharts, under the guidance of the content of this application. Some of the block diagrams shown in the accompanying drawings are functional entities, and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor systems and / or microcontroller systems.

[0024] The descriptions of "first", "second", etc. involved in the embodiments of the present application are only used to describe the implicit purpose, and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features. "And / or" describes the association relationship of the associated objects, indicating that three relationships may exist, for example: A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone.

[0025] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0026] The present application provides a battery health status assessment method, which is described below.

[0027] Figure 1 A flowchart of an embodiment of a battery health status assessment method provided in this application is as follows: Figure 1 As shown, the battery health status assessment method includes: S101, acquiring battery operation data collected by a sensor in real time; S102, acquiring battery status data estimated by a Kalman filter in real time; S103, normalizing the battery operation data and the battery status data to obtain time series data; It should be noted that the min-max normalization method is specifically adopted.

[0028] S104: Input the time series data as input features into a well-trained deep learning model to obtain estimated battery health status data.

[0029] Compared with the prior art, the present application accurately estimates battery status data through an adaptive filter, and uses the battery status data estimated by the filter and the battery operation data collected by the sensor as the input of the deep learning model, thereby realizing the deep fusion of the physical model and the data-driven model, and combining the nonlinear fitting capability of the deep learning model to achieve high-precision and real-time evaluation of the battery health status.

[0030] Considering that the selection of battery operation data will directly affect the prediction accuracy, in order to improve the prediction accuracy, in some embodiments, the battery operation data includes voltage, current, temperature and state of charge data.

[0031] It should be noted that the voltage is acquired by measuring the terminal voltage of the battery in real time through a high-precision voltage sensor with a sampling frequency of 10Hz; the current is acquired by measuring the charge and discharge current of the battery in real time through a Hall sensor; the temperature is acquired by installing a temperature sensor on the surface of the battery to monitor the temperature change in real time; the state of charge (SOC) is estimated and updated in real time through the ampere-hour integration method.

[0032] Furthermore, in order to improve the quality of battery operation data, in some embodiments, after collecting the battery operation data, the data needs to be preprocessed. Specifically, Figure 2 As shown, after step S101, the method further includes: S201, filtering and denoising the voltage and current data in the collected battery operation data to obtain denoised battery operation data; It should be noted that an adaptive median filter is used to filter the voltage and current data to remove the spike noise.

[0033] S202, time-aligning the data from different sensors in the denoised battery operation data to obtain synchronized battery operation data; S203 , normalizing the synchronized battery operation data to obtain normalized battery operation data.

[0034] It should be noted that the specific step is to normalize the data to the interval [0, 1] to eliminate dimensional differences.

[0035] Considering that the selection of battery status data will directly affect the prediction accuracy, in order to improve the prediction accuracy, in some embodiments, the Kalman filter adopts Figure 3 The second-order RC equivalent circuit model shown in Figure 1 is a 2-order RC equivalent circuit model, where the open circuit voltage ( ) reflects the static voltage characteristics of the battery, and the ohmic internal resistance ( ) describes the internal resistance of the battery, the first branch of RC ( , ) describes the short-term polarization effect of the battery, the second branch of RC ( , ) describes the long-term polarization effect of the battery. Therefore, the battery status data includes the battery's open circuit voltage, branch voltage and internal resistance data.

[0036] In order to improve the quality of battery status data, in some embodiments, such as Figure 4 As shown, the Kalman filter estimates the battery status data in real time through the following steps: S401, using the open circuit voltage and branch voltage of the equivalent circuit model corresponding to the Kalman filter as the state vector, constructing the state equation and observation equation, and initializing the state and error covariance matrix; It should be noted that the state vector for: , where express Open circuit voltage at any moment, express The voltage of the first branch at time express The voltage of the second branch at the moment, initial state for: , the initial error covariance matrix for: , the state equation and observation equation are:

[0037]

[0038] In the formula, express Input control at all times, express The moment process noise has a mean of zero and follows a multivariate normal distribution. ,in, express The moment process noise covariance matrix, express Status at all times The measured value of express The moment measurement noise has a mean of zero and follows a multivariate normal distribution. ,in, express The moment measurement noise covariance matrix, represents the state transformation matrix, , represents the input control matrix, , and represents the observation matrix, , ,in, Indicates internal resistance.

[0039] S402, calculating a predicted value of the current state based on the state at the previous moment, and calculating a predicted value of the error covariance matrix at the current moment based on the error covariance matrix at the previous moment and the measurement noise covariance matrix at the previous moment; It should be noted that the calculation formula for the predicted value of the current state and error covariance matrix is:

[0040]

[0041] In the formula, Indicates known Status at all times , The predicted value of the state at the moment, express Moment status, express Input control at all times, Indicates known Time error covariance matrix , The predicted value of the moment error covariance matrix, express The moment process noise covariance matrix.

[0042] S403, based on the predicted value of the current state and the current measurement noise covariance matrix, the current Kalman gain is updated, and based on the predicted value of the current state and the current Kalman gain, the current process noise covariance matrix is ​​updated; It should be noted that the calculation formula of the Kalman gain and process noise covariance matrix at the current moment is:

[0043]

[0044]

[0045] In the formula, express The moment Kalman gain, express The predicted value of the moment error covariance matrix, express The moment measurement noise covariance matrix, express The residual is measured at all times, express The measured value of the state at the moment, Represents the forgetting factor, which ranges from 0 to 1. express The moment process noise covariance matrix, express The moment-to-moment process noise covariance matrix is ​​calculated, and thus the process noise covariance matrix is ​​adjusted in real time to adapt to changes in complex working conditions.

[0046] S404, updating the current state based on the predicted value of the current state and the current Kalman gain, and updating the current error covariance matrix based on the predicted value of the current error covariance matrix and the current Kalman gain; It should be noted that the calculation formula of the current state and the current error covariance matrix is:

[0047]

[0048] In the formula, express Moment status, express The predicted value of the state at the moment, express The moment Kalman gain, express The residual is measured at all times, express The moment error covariance matrix, express The predicted value of the moment error covariance matrix.

[0049] In order to better estimate the battery health state, in some embodiments, the deep learning model is constructed based on a bidirectional long short-term memory network and an attention mechanism. The long-term and short-term dependencies of time series data are captured through the bidirectional long short-term memory network to improve prediction accuracy. The weights of input features are dynamically allocated through the attention mechanism to enhance the model's attention to important features.

[0050] Specifically, the fully trained deep learning model includes an input layer, a Bi-LSTM layer, an attention mechanism layer, a fully connected layer and an output layer, which are connected in sequence. The input layer is used to receive input features, the Bi-LSTM layer is used to extract features of time series data, the attention mechanism layer is used to perform weighted summation of the output features of the Bi-LSTM layer, the fully connected layer is used to map the output features of the attention mechanism layer to the battery health status data, and the output layer is used to output the battery health status data, i.e., SOH.

[0051] It should be noted that the attention mechanism layer is specifically:

[0052]

[0053]

[0054] In the formula, represents the input features, and represents the learnable parameters, represents the attention weight, represents the output features of the Bi-LSTM layer, Represents the output features of the attention mechanism layer.

[0055] It should also be noted that the mean square error (MSE) loss function is used in deep learning model training, the Adam optimizer is used, the learning rate is set to 0.001, and the early stopping method is used to prevent overfitting. The batch size is set to 64 during batch training, and the number of iterations is determined according to the loss convergence of the validation set. Finally, the trained model parameters are saved as a file for loading during online evaluation.

[0056] In order to improve the prediction accuracy of the model, in some embodiments, the deep learning model needs to be updated online, including: when the amount of estimated battery health status data reaches a preset value, using an incremental learning algorithm to update the deep learning model; dynamically adjusting model parameters according to the error and trend of the battery health status data estimation; regularly evaluating the performance of the deep learning model, and retraining or optimizing when the accuracy of the deep learning model decreases.

[0057] In order to better implement a battery health status evaluation method in an embodiment of the present application, based on a battery health status evaluation method, correspondingly, Figure 5 As shown, the embodiment of the present application also provides a battery health status assessment device 500, including: A data acquisition unit 501 is used to acquire in real time the battery operation data collected by the sensor and the battery status data estimated by the Kalman filter; The data processing unit 502 is used to normalize the battery operation data and the battery status data to obtain time series data; The model evaluation unit 503 is used to input the time series data as input features into a well-trained deep learning model to obtain estimated battery health status data.

[0058] The battery health status assessment device 500 provided in the above embodiment can implement the technical solution described in the above battery health status assessment method embodiment. The specific implementation principles of the above units can refer to the corresponding contents in the above battery health status assessment method embodiment, which will not be repeated here.

[0059] like Figure 6 As shown, the present application also provides an electronic device 600. The electronic device 600 includes a processor 601, a memory 602 and a display 603. Figure 6 Only some components of the electronic device 600 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0060] In some embodiments, the memory 602 may be an internal storage unit of the electronic device 600, such as a hard disk or memory of the electronic device 600. In other embodiments, the memory 602 may also be an external storage device of the electronic device 600, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 600.

[0061] Furthermore, the memory 602 may include both an internal storage unit of the electronic device 600 and an external storage device. The memory 602 is used to store application software installed in the electronic device 600 and various data.

[0062] In some embodiments, the processor 601 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 602, such as the battery health status assessment method in the present application.

[0063] In some embodiments, the display 603 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 603 is used to display information on the electronic device 600 and to display a visual user interface. The components 601-603 of the electronic device 600 communicate with each other via a system bus.

[0064] In some embodiments of the present application, when the processor 601 executes the battery health status evaluation program in the memory 602, the following steps may be implemented: Obtain battery operation data collected by sensors in real time; Real-time acquisition of battery status data estimated by the Kalman filter; Normalize the battery operation data and battery status data to obtain time series data; The time series data is fed as input features into a well-trained deep learning model to obtain the estimated battery health status data.

[0065] It should be understood that: when the processor 601 executes the battery health status assessment program in the memory 602, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.

[0066] Furthermore, the embodiment of the present application does not specifically limit the type of the electronic device 600 mentioned, and the electronic device 600 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present application, the electronic device 600 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0067] The above is a detailed introduction to a battery health status assessment method provided by the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0068] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed in the present application should be covered within the protection scope of the present application.

Claims

1. A battery health status assessment method, characterized in that: include: Obtain battery operation data collected by sensors in real time; Real-time acquisition of battery status data estimated by the Kalman filter; Normalizing the battery operation data and the battery status data to obtain time series data; The time series data is input as input features into a well-trained deep learning model to obtain estimated battery health status data.

2. The battery health status assessment method according to claim 1, characterized in that: The battery operation data includes voltage, current, temperature and state of charge data.

3. The battery health status assessment method according to claim 2, characterized in that: After acquiring the battery operation data collected by the sensor in real time, the method further includes: Performing filtering and denoising on the voltage and current data in the collected battery operation data to obtain denoised battery operation data; Performing time alignment on the data from different sensors in the denoised battery operation data to obtain synchronized battery operation data; The synchronized battery operation data is normalized to obtain normalized battery operation data.

4. The battery health status assessment method according to claim 1, characterized in that: The Kalman filter adopts a second-order RC equivalent circuit model, and the battery status data includes the open circuit voltage, branch voltage and internal resistance data of the battery.

5. The battery health status assessment method according to claim 4, characterized in that: The Kalman filter estimates the battery status data in real time through the following steps: The open circuit voltage and branch voltage of the equivalent circuit model corresponding to the Kalman filter are used as state vectors to construct state equations and observation equations, and initialize the state and error covariance matrices; According to the state equation, a predicted value of the state at the current moment is calculated based on the state at the previous moment, and a predicted value of the error covariance matrix at the current moment is calculated based on the error covariance matrix at the previous moment and the measurement noise covariance matrix at the previous moment; According to the observation equation, the Kalman gain at the current moment is updated based on the predicted value of the state at the current moment and the measurement noise covariance matrix at the current moment, and the process noise covariance matrix at the current moment is updated based on the predicted value of the state at the current moment and the Kalman gain at the current moment; According to the observation equation, the current state is updated based on the predicted value of the current state and the current Kalman gain, and the current error covariance matrix is ​​updated based on the predicted value of the current error covariance matrix and the current Kalman gain.

6. The battery health status assessment method according to claim 5, characterized in that: The calculation formula of the Kalman gain at the current moment is: In the formula, express The moment Kalman gain, express The predicted value of the moment error covariance matrix, express The moment measurement noise covariance matrix; The calculation formula of the process noise covariance matrix at the current moment is: In the formula, express The moment process noise covariance matrix, express The moment process noise covariance matrix, express The moment Kalman gain, express The residual is measured at all times, express The measured value of the state at the moment, Represents the forgetting factor, which ranges from 0 to 1. Represents internal resistance, express Always input control.

7. The battery health status assessment method according to claim 1, characterized in that: The fully trained deep learning model includes an input layer, a Bi-LSTM layer, an attention mechanism layer, a fully connected layer and an output layer connected in sequence, based on the input layer being used to receive the input features, the Bi-LSTM layer being used to extract features of the time series data, the attention mechanism layer being used to perform weighted summation of the output features of the Bi-LSTM layer, the fully connected layer being used to map the output features of the attention mechanism layer to battery health status data, and the output layer being used to output the battery health status data.

8. The battery health status assessment method according to claim 1, characterized in that: The method further comprises: When the amount of the estimated battery health status data reaches a preset value, an incremental learning algorithm is used to update the deep learning model.

9. A battery health status assessment device, characterized in that: include: A data acquisition unit, used for acquiring in real time the battery operation data collected by the sensor and the battery status data estimated by the Kalman filter; A data processing unit, used for normalizing the battery operation data and the battery status data to obtain time series data; A model evaluation unit is used to input the time series data as input features into a well-trained deep learning model to obtain estimated battery health status data.

10. An electronic device, characterized in that: including memory and processor; The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps of the battery health status assessment method described in any one of claims 1 to 8 above.

Images