Battery information processing method and device, computing equipment and computer program product

Abstract

The embodiment of the invention provides a battery information processing method. The method comprises the following steps: acquiring corresponding charging detection data when a low-voltage battery configured in a vehicle is charged; inputting the charging detection data into a target neural network, and determining first weight information corresponding to the charging information; weighting the first weight information in combination with the environment information to obtain second weight information; and executing the target neural network according to the second weight information so as to output the battery charge state corresponding to the low-voltage battery. Therefore, the calibration process of the battery state of charge of the low-voltage battery is realized, the charging information is fitted through the neural network, the weight adjustment is performed in combination with the environment where the low-voltage battery is located, the battery state of charge can be dynamically estimated, and the accuracy of the battery state of charge data of the low-voltage battery is improved.

Description

Technical Field

[0001] The present specification relates to the field of computer application technology, specifically, to battery information processing technology under the field of computer application technology, and more specifically, to a battery information processing method, device, computing equipment and computer program product. Background Art

[0002] The low-voltage battery of a vehicle often ages during use, resulting in a false battery state of charge. That is, the battery power corresponding to 100% may not be the same as the battery power corresponding to 100% due to battery aging. This makes it impossible for users to intuitively know the current battery status of the vehicle, affecting the accuracy of the battery state of charge information. Summary of the invention

[0003] The embodiments of this specification provide a method, apparatus, computing device, and computer program product for processing battery information to achieve dynamic detection of the battery state of charge.

[0004] To achieve the above technical objectives, the embodiments of this specification provide the following technical solutions:

[0005] In a first aspect, an embodiment of the present specification provides a method for processing battery information, including:

[0006] Acquire charging detection data corresponding to the low-voltage battery configured for the vehicle during charging, wherein the charging detection data includes charging information and environmental information;

[0007] Inputting the charging detection data into a target neural network, and determining first weight information corresponding to the charging information;

[0008] weighting the first weight information in combination with the environmental information to obtain second weight information;

[0009] The target neural network is executed according to the second weight information to output a battery state of charge corresponding to the low-voltage battery.

[0010] In a second aspect, an embodiment of the present specification provides a battery information processing device, including:

[0011] An acquisition unit, used to acquire charging detection data corresponding to a low-voltage battery configured for a vehicle during charging, wherein the charging detection data includes charging information and environmental information;

[0012] a processing unit, configured to input the charging detection data into a target neural network and determine first weight information corresponding to the charging information;

[0013] The processing unit is further used to weight the first weight information in combination with the environmental information to obtain second weight information;

[0014] The processing unit is further used to execute the target neural network according to the second weight information to output the battery state of charge corresponding to the low-voltage battery.

[0015] In a third aspect, an embodiment of the present specification further provides a computing device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the battery information processing method as described above when executing the computer program.

[0016] In a fourth aspect, an embodiment of the present specification further provides a vehicle, wherein the vehicle executes the battery information processing method as described in any of the above aspects.

[0017] In a fifth aspect, an embodiment of the present specification further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the battery information processing method as described above is implemented.

[0018] In a sixth aspect, an embodiment of the present specification provides a computer program product or a computer program, wherein the computer program product includes a computer program, and the computer program can be stored in a computer-readable storage medium or in the cloud; the processor of the computer device reads the computer program, and the processor implements the steps of the above-mentioned battery information processing method when executing the computer program.

[0019] It can be seen from the above technical solution that the battery information processing method provided in the embodiment of this specification obtains the charging detection data corresponding to the low-voltage battery configured by the vehicle when charging, and the charging detection data includes charging information and environmental information; then the charging detection data is input into the target neural network, and the first weight information corresponding to the charging information is determined; and the first weight information is weighted in combination with the environmental information to obtain the second weight information; and then the target neural network is executed according to the second weight information to output the battery state of charge corresponding to the low-voltage battery. Thereby, the calibration process of the battery state of charge of the low-voltage battery is realized, and the charging information is fitted by the neural network, and the weight is adjusted in combination with the environment in which the low-voltage battery is located, so that the battery state of charge can be dynamically estimated, and the accuracy of the battery state of charge data of the low-voltage battery is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0021] Figure 1 A schematic diagram of an application environment of a method for processing battery information provided in one embodiment of this specification;

[0022] Figure 2 A flowchart of a method for processing battery information provided in accordance with an embodiment of the present specification;

[0023] Figure 3 A schematic diagram of a scenario of a method for processing battery information provided in one embodiment of this specification;

[0024] Figure 4 A schematic diagram of another method for processing battery information provided in accordance with an embodiment of the present specification;

[0025] Figure 5 A schematic diagram of another method for processing battery information provided in accordance with an embodiment of the present specification;

[0026] Figure 6 A schematic diagram of functional modules of a battery information processing device provided in one embodiment of this specification;

[0027] Figure 7 A schematic diagram of the structure of a computing device provided for one embodiment of the present specification. DETAILED DESCRIPTION

[0028] Unless otherwise defined, the technical terms or scientific terms used in the embodiments of this specification should be understood by people with ordinary skills in the field to which this specification belongs. The words "first", "second" and similar words used in the embodiments of this specification do not indicate any order, quantity or importance, but are only used to avoid confusion of constituent elements.

[0029] Unless the context requires otherwise, throughout the specification, "plurality" means "at least two", and "including" is interpreted as an open, inclusive meaning, that is, "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "examples", "specific examples" or "some examples" are intended to indicate that a particular feature, structure, material or characteristic associated with the embodiment or example is included in at least one embodiment or example of the specification. The schematic representation of the above terms does not necessarily refer to the same embodiment or example.

[0030] The following is an explanation of the abbreviations that appear in this manual:

[0031] Neural network (Back Propagation, BP): Back propagation neural network is a multi-layer feedforward neural network. Its training process mainly uses the error back propagation algorithm and gradient descent method to adjust the weights and biases of the network so that the network output gradually approaches the target output.

[0032] Battery State of Charge (SOC): refers to the ratio of the energy currently stored in the battery to the energy it should store when fully charged. This parameter can be expressed as a percentage, ranging from 0 to 100%. When SOC is 0%, it means that the battery is fully discharged; when SOC is 100%, it means that the battery is fully charged.

[0033] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0034] Low-voltage batteries are widely used in automotive electrical systems, energy storage systems, and other applications that require low-voltage power. For example, in pure electric vehicles, low-voltage batteries are not only used to start the vehicle, but also provide power for the in-vehicle entertainment system, electric windows, airbags, etc. Therefore, it is necessary to accurately estimate the battery state of charge of the low-voltage battery.

[0035] Generally, the determination of the battery state of charge is based on chemical or electrophysical modeling, that is, a model is established through the battery's electrode material, internal resistance, and capacitance to simulate the changing trend of the battery state of charge, thereby obtaining the battery state of charge.

[0036] However, due to the instability of the attenuation process of electrode materials, modeling based on chemical change dimensions is easily interfered by external factors, resulting in inaccurate estimation of the battery state of charge.

[0037] To solve the above problems, the embodiments of this specification provide a battery information processing system, and the battery information processing method provided in the embodiments of this specification is applied to the battery information processing system. From a data perspective, the processing system reversely fits the SOC based on the battery test data, reducing the difficulty of the algorithm in understanding and modeling the battery physics; at the same time, during the actual vehicle operation, the battery data can be collected from the cloud, and after analyzing the big data, the algorithm parameters can be dynamically changed to more accurately fit the current health of the battery to calculate the SOC. .

[0038] Specifically, the battery information processing system may include: Figure 1 The operating environment formed by the client 110, server 120 and vehicle 130 in the embodiment. The client 110 communicates with the server 120 through the network. The client 110 is wirelessly connected to the vehicle 130. The vehicle 130 communicates with the server 120 through a network connection. Among them, the client 110 can be an electronic device with network access capability. Specifically, for example, the client 110 can be a desktop computer, a tablet computer, a laptop computer, a smart phone, a digital assistant, a smart wearable device, a shopping guide terminal, a television, a smart speaker, a microphone, etc. Among them, smart wearable devices include but are not limited to smart bracelets, smart watches, smart glasses, smart helmets, smart necklaces, etc. Alternatively, the client 110 can also be software that can be run in the electronic device. The server 120 can be an electronic device with certain computing and processing capabilities. It can have a network communication module, a processor and a memory, etc. Of course, the server 120 can also refer to software running in the electronic device. The server 120 can also be a distributed server, which can be a system with multiple processors, memories, network communication modules, etc. operating in collaboration. Alternatively, the server 120 can also be a cluster formed by several servers 120. Alternatively, with the development of science and technology, the server 120 may also be a new technical means capable of realizing the corresponding functions of the embodiments of the specification, for example, a new form of "server" based on quantum computing.

[0039] Specifically, based on the above-mentioned processing system, when performing game interaction in the vehicle, the charging detection data corresponding to the low-voltage battery configured in the vehicle is obtained during charging, and the charging detection data includes charging information and environmental information; then the charging detection data is input into the target neural network, and the first weight information corresponding to the charging information is determined; and the first weight information is weighted in combination with the environmental information to obtain the second weight information; and then the target neural network is executed according to the second weight information to output the battery state of charge corresponding to the low-voltage battery. Thus, the calibration process of the battery state of charge of the low-voltage battery is realized, and the charging information is fitted by the neural network, and the weight is adjusted in combination with the environment in which the low-voltage battery is located, so that the battery state of charge can be dynamically estimated, thereby improving the accuracy of the battery state of charge data of the low-voltage battery.

[0040] Based on the above concept, an embodiment of the present specification provides a method for processing battery information. The following will exemplarily describe the method for processing battery information provided in the embodiment of the present specification in conjunction with the accompanying drawings.

[0041] To be applied to Figure 1 Taking the client in the example, some implementations of this specification exemplarily illustrate the method for processing the battery information, such as Figure 2 As shown, Figure 2 A flowchart of a method for processing battery information provided in accordance with an embodiment of the present specification, the method for processing battery information comprising:

[0042] 201. Obtain charging detection data corresponding to a low-voltage battery configured for a vehicle during charging, where the charging detection data includes charging information and environmental information.

[0043] In this embodiment, the low-voltage battery is a small on-board battery, which is an auxiliary battery on the vehicle and can also be called a 12V battery. It provides power support for the vehicle's electrical system: when the vehicle is not started, it powers electronic devices in the vehicle such as radios, lights, dashboards, etc. When the vehicle is started, the power battery powers these devices and also charges the small battery. The low-voltage battery also supports some specific functions of the vehicle: such as automatic start-stop system, electronic handbrake, electric windows, etc. At the moment when the vehicle stops working, the small battery can ensure the normal operation of these functions. The low-voltage battery can also provide backup power for the vehicle's control system: when the vehicle fails or an unexpected situation causes the main power supply to be interrupted, the small battery can provide short-term power support for the vehicle's key control system to ensure the safety of the vehicle. Therefore, the low-voltage battery has the characteristics of high-frequency intermittent operation, its battery health is easy to decay, and the battery state of charge is easy to change. This embodiment is designed based on a multi-dimensional curve fitting low-voltage battery SOC solution for this feature to perform self-calibration of the battery state of charge.

[0044] Specifically, from a data perspective, this embodiment reversely fits the SOC based on the battery charging detection data, thereby reducing the difficulty of the algorithm in understanding and modeling the battery physics. Among them, the collection process of charging detection data can be carried out periodically, that is, first obtain the detection cycle for the low-voltage battery configuration in the vehicle, such as collecting charging detection data within 10 minutes; then perform parameter detection on the charging process of the low-voltage battery in the corresponding period of the detection cycle to obtain charging information; and further determine the corresponding environmental information of the vehicle in the detection cycle; and then combine the charging information and environmental information to obtain charging detection data. It can be seen that the charging detection data of this embodiment is a multi-dimensional composite collection process, in which the charging information is used as the input feature of the target neural network for identification, and the environmental information is used for weight adjustment, thereby realizing a dynamic SOC simulation process.

[0045] It is understandable that for the scenario where the detection cycle is the initial cycle, parameter compensation can also be performed; that is, when performing the SOC algorithm charging self-calibration, the reference in the initial cycle is the current SOC charging ampere-hours of the battery from the static state to the current state. If it is greater than the current value retained after the last charging, SOC compensation is required. This is because the charging current of the battery that has been charging is smaller than the charging current of the battery that has just been static, and the SOC will be considered to be larger. In order to avoid the error caused by this influence, the corresponding parameter compensation is performed.

[0046] In one possible scenario, the charging information is the charging parameters corresponding to the low-voltage battery during charging, which includes the current, voltage, and charge capacity of the real-time detection parameters, as well as the health of the evaluation parameters; specifically, first obtain the current parameters, voltage parameters, and charge capacity of the low-voltage battery in the corresponding period of the detection cycle; then compare the current parameters, voltage parameters, and charge capacity with their respective calibration parameters to obtain the health parameters; and then combine the current parameters, voltage parameters, charge capacity, and health parameters to obtain the charging information. By judging the charge capacity, the change in the capacity of the low-voltage battery can be intuitively reflected; and further, the health parameters are combined to verify the authenticity of the capacity, thereby performing a composite capacity simulation process.

[0047] In another possible scenario, the environmental information is the environment in which the low-voltage battery is located during the charging process, wherein the environment includes the environment in the internal dimension of the vehicle where the battery is located (temperature, humidity, etc.), and may also include the environment in the external dimension of the vehicle (altitude, air pressure, etc.). This is because as the altitude increases, the atmospheric pressure gradually decreases, resulting in a decrease in air density, which will affect the flow of gas and liquid inside the battery, thereby affecting the performance of the battery. Therefore, it is necessary to weight the corresponding input features (features of charging information) according to the vehicle's driving scene data (plateau areas, coastal areas, etc.), that is, considering that the vehicle driving scene is complex. Specifically, firstly, the battery environmental parameters are obtained based on the environmental detection of the sensors configured in the vehicle; then the vehicle is detected during the detection cycle to obtain the positioning parameters, that is, the geographical coordinates of the vehicle; then data retrieval is performed based on the positioning parameters to determine the vehicle environmental parameters associated with the positioning parameters, wherein the data retrieval can be to send the positioning parameters to the cloud, so as to obtain the altitude, air pressure and other parameters corresponding to the coordinates; and then the battery environmental parameters and the vehicle environmental parameters are combined to obtain environmental information. Thereby improving the accuracy of the battery state of charge estimation during the vehicle driving in different environments.

[0048] Therefore, this embodiment can collect battery data from the cloud, and after analyzing the big data, it can dynamically change the weight parameters in the subsequent neural network to more accurately calculate the SOC in line with the current health of the battery and environmental factors.

[0049] Furthermore, since the vehicle's driving process is continuous, the driving area statistics can also be performed based on the above environmental information to configure the corresponding weights. That is, first call the driving record corresponding to the vehicle; then determine the multiple areas involved in the driving record to obtain regional information, such as the driving mileage in the plateau area, the driving mileage in the coastal area, etc.; then determine the associated area to which the positioning parameter belongs in the regional information; and use the statistical information corresponding to the associated area as the vehicle environmental parameter. For example, if the positioning parameter indicates that the vehicle is in the coastal area (associated area), call the low driving data in the coastal area to update the mileage to update the weight.

[0050] 202. Input the charging detection data into the target neural network, and determine the first weight information corresponding to the charging information.

[0051] In this embodiment, the target neural network is used to perform multidimensional curve fitting to calculate the SOC of the low-voltage battery, thereby performing charging self-calibration. Specifically, the structure of the target neural network is as follows: Figure 3 As shown, Figure 3 A scenario diagram of a method for processing battery information provided for one embodiment of the present specification; the figure shows that the target neural network is a multi-layer feedforward network trained by error back propagation, which consists of an input layer, several hidden layers and an output layer.

[0052] Specifically, the input layer is used to receive input data from the outside, and each input node corresponds to an input feature. For example, if you want to classify a set of images, the input layer nodes may correspond to the pixel values ​​of the image or the extracted feature values.

[0053] There can be one or more hidden layers. The neurons in the hidden layer receive input from the previous layer, process it through the activation function, and pass the output to the next layer. The role of the hidden layer is to extract features and perform nonlinear transformation on the input data to enhance the learning and expression capabilities of the network.

[0054] The output layer is used to generate the final output of the network. The number of nodes in the output layer depends on the specific task requirements. For example, for a binary classification problem, the output layer may have only one node, which represents the probability of belonging to a certain category; for a multi-classification problem, the number of nodes in the output layer is the same as the number of categories.

[0055] The neurons in the above layers are connected to each other through connection weights. The connection weights represent the degree of influence of the neurons in the previous layer on the neurons in the next layer. During the training process, the network continuously adjusts the connection weights to make the output of the network as close to the actual target value as possible.

[0056] In this embodiment, the first weight information is the connection weight configured by the target neural network for the input features corresponding to the charging information. The configuration of the input features corresponding to the charging information includes the curve fitting characteristics corresponding to different charging parameters, that is, the changing trend characteristics composed of multiple detection points in the charging detection data.

[0057] 203. Weight the first weight information in combination with the environmental information to obtain second weight information.

[0058] In this embodiment, the second weight information is the connection weight obtained by adaptively adjusting the connection weight (first weight information) based on the environmental information. The specific description of the influencing factor parameter of the environmental information in step 201 is omitted here.

[0059] Specifically, the input data (charging detection data) passes through each hidden layer in turn from the input layer and finally reaches the output layer. In each layer, the input of each neuron is the sum of the product of the output of the neurons in the previous layer and the connection weight. Therefore, for a neuron in the hidden layer, its input is the sum of the product of the output of all neurons in the previous layer and the corresponding connection weight, that is:

[0060] input=∑ i y i x i +b

[0061] Among them, yi Represents the second weight information; x i represents the output of the previous layer of neurons; b represents the bias term.

[0062] Furthermore, for the process of determining the second weight information, since the environmental information includes battery environmental parameters and vehicle environmental parameters, the two belong to influencing factors of different dimensions and need to be weighted and combined. That is, first determine the battery environmental parameters and vehicle environmental parameters contained in the environmental information; then perform parameter comparison based on the battery environmental parameters to determine the first adjustment factor; and obtain the mileage data corresponding to the different regional information in the vehicle environmental parameters; then integrate the adjustment factors corresponding to each region based on the mileage data to obtain the second adjustment factor; and then weight the first weight information according to the first adjustment factor and the second adjustment factor to obtain the second weight information. Therefore, the process of determining the second weight information can be expressed as:

[0063] y i =(a i c i ) i

[0064] Among them, w i Represents the first weight information; a i represents the first adjustment factor; c i Represents the second adjustment factor.

[0065] In summary, we can obtain the connection weight that comprehensively considers the charging dimension and the environmental dimension.

[0066] 204. Execute the target neural network according to the second weight information to output the battery state of charge corresponding to the low-voltage battery.

[0067] In this embodiment, the target neural network is executed according to the second weight information, that is, the connection weight adapted to the current low-voltage battery environment is determined to estimate the SOC. That is, the input and output of the charging self-calibration algorithm can be expressed as:

[0068] Algorithm input: battery voltage, current, temperature, battery health SOH during charging; air humidity, altitude, and ampere-hours corresponding to this charge;

[0069] Algorithm output: battery SOC, remaining available power.

[0070] Among them, the remaining available power is the power data calculated based on the battery SOC, so that users can make intuitive power judgments.

[0071] It can be understood that the above-mentioned SOC simulation process is also applicable to the discharge process. First, the discharge detection data corresponding to the low-voltage battery configured in the vehicle during discharge is obtained, and the discharge detection data includes discharge information and environmental information; then the discharge detection data is input into the target neural network, and the third weight information corresponding to the discharge information is determined; and the third weight information is weighted in combination with the environmental information to obtain the fourth weight information; and then the target neural network is executed according to the fourth weight information to output the battery charge state corresponding to the low-voltage battery.

[0072] The determination of the discharge information refers to the description of the above-mentioned charging information, and the environmental information corresponds to the description of the above-mentioned environmental information; and the fourth weight information is the third weight information adjusted based on the environmental factors.

[0073] In one possible scenario, the input and output of the discharge self-calibration algorithm can be expressed as:

[0074] Algorithm input: battery voltage, current, temperature, battery health SOH during charging; air humidity, altitude, and ampere-hours released during this discharge;

[0075] Algorithm output: battery SOC, remaining available power.

[0076] Combining the above examples, we can get Figure 4 The test results shown, Figure 4 A scenario diagram of another method for processing battery information provided for an embodiment of the present specification; the figure shows a comparison between a charging and discharging process based on a direct current (DC-DC) power supply and a SOC simulation curve, and it can be seen that the change trend of the simulation data is similar to the test data of the charging and discharging process, achieving good SOC estimation accuracy.

[0077] In addition, the training process of the above-mentioned target neural network can be carried out by a cloud server, that is, by collecting the corresponding relationship between charging information and SOC under different environmental information to perform model training. The specific training process is based on the activation function and adopts the back propagation algorithm. For the activation function, since the output of the neuron is obtained by processing the input through the activation function. Therefore, the role of the activation function is to introduce nonlinearity so that the network can learn complex functional relationships.

[0078] Specifically, the activation functions of this embodiment include sigmoid function, tanh function and ReLU function. For example, the sigmoid function maps the input value to between 0 and 1. That is, during the training process, the input data is first input into the network, and the output of the network is obtained through forward propagation. Then, the output of the network is compared with the true target value to calculate the error. The error can be measured using a loss function, and common loss functions include mean square error (MSE), cross entropy, etc.

[0079] Furthermore, for the process of error back propagation, error back propagation is the core mechanism of BP neural network. According to the error, starting from the output layer, the error gradient of each layer of neurons is calculated in turn, and the connection weights and bias items are adjusted according to the error gradient, so that the output of the network gradually approaches the target value. Specifically, for each connection weight, the weight is updated using the gradient descent method according to the error gradient and the output of the previous layer of neurons.

[0080] By repeating the above process, the BP neural network gradually learns the mapping relationship between input data (charging information) and output results (battery state of charge), thereby dynamically predicting the battery state of charge and improving the accuracy and complexity of battery SOC calculation.

[0081] It is understandable that, since the environmental information in this embodiment involves different natural environments, multiple environmental chambers can be configured in different regions to perform simulations under specific environments. Figure 5 The training architecture shown, Figure 5 A scenario diagram of another method for processing battery information provided for an embodiment of the present specification; that is, for the above-mentioned training process, multiple environmental chambers simulating the environment of the vehicle can be first determined, and the environmental chambers can be configured in different geographical areas; then different charging information is executed based on different environmental information, and the battery state of charge corresponding to the low-voltage battery is determined to collect training data; and then the target neural network is trained based on the training data. By using environmental chambers to simulate different air humidity and temperature, and different electronic loads at experimental sites at different altitudes, the battery is discharged, and the corresponding relationship data between SOC and battery voltage is collected, the accuracy of environmental information during the training process is improved, and the accuracy of the target neural network in SOC estimation under different environments is improved.

[0082] In summary, this embodiment obtains the charging detection data corresponding to the low-voltage battery configured in the vehicle when it is charging, and the charging detection data includes charging information and environmental information; then inputs the charging detection data into the target neural network, and determines the first weight information corresponding to the charging information; and weights the first weight information in combination with the environmental information to obtain the second weight information; and then executes the target neural network according to the second weight information to output the battery state of charge corresponding to the low-voltage battery. Thus, the calibration process of the battery state of charge of the low-voltage battery is realized, and the charging information is fitted by the neural network, and the weight is adjusted in combination with the environment in which the low-voltage battery is located, so that the battery state of charge can be dynamically estimated, thereby improving the accuracy of the battery state of charge data of the low-voltage battery.

[0083] It should be noted that the multiple embodiments in this specification emphasize the parts that are different from other embodiments, and the various embodiments can be explained in comparison with each other. Any combination of the multiple embodiments in this specification by technicians in the relevant field based on general technical knowledge is included in the disclosure scope of this specification.

[0084] In an exemplary embodiment of the present specification, a battery information processing device 600 is also provided. Figure 6 As shown, Figure 6 This is a functional module diagram of a battery information processing device provided in one embodiment of this specification. The processing device 600 includes:

[0085] An acquisition unit 601 is used to acquire charging detection data corresponding to a low-voltage battery configured for a vehicle during charging, wherein the charging detection data includes charging information and environmental information;

[0086] The processing unit 602 is used to input the charging detection data into a target neural network and determine first weight information corresponding to the charging information;

[0087] The processing unit 602 is further configured to weight the first weight information in combination with the environment information to obtain second weight information;

[0088] The processing unit 602 is further used to execute the target neural network according to the second weight information to output the battery state of charge corresponding to the low-voltage battery.

[0089] Optionally, in some possible embodiments, the acquisition unit 601 is specifically used to acquire a detection cycle for a low-voltage battery configuration in the vehicle;

[0090] The acquisition unit 601 is specifically used to perform parameter detection on the charging process of the low-voltage battery in the corresponding time period of the detection cycle to obtain the charging information;

[0091] The acquisition unit 601 is specifically used to determine the environmental information corresponding to the vehicle in the detection period;

[0092] The acquisition unit 601 is specifically configured to combine the charging information and the environmental information to obtain the charging detection data.

[0093] Optionally, in some possible embodiments, the acquisition unit 601 is specifically used to acquire the current parameter, voltage parameter and charge capacity of the low-voltage battery in a time period corresponding to the detection cycle;

[0094] The acquisition unit 601 is specifically configured to compare the current parameter, the voltage parameter and the charge amount with the respective corresponding calibration parameters to obtain a health parameter;

[0095] The acquisition unit 601 is specifically configured to obtain the charging information by combining the current parameter, the voltage parameter, the charge amount and the health parameter.

[0096] Optionally, in some possible embodiments, the acquisition unit 601 is specifically configured to obtain battery environment parameters by performing environment detection based on sensors configured in the vehicle;

[0097] The acquisition unit 601 is specifically configured to perform position detection on the vehicle within the detection period to obtain positioning parameters;

[0098] The acquisition unit 601 is specifically configured to perform data retrieval based on the positioning parameter to determine the vehicle environment parameter associated with the positioning parameter;

[0099] The acquisition unit 601 is specifically configured to obtain the environmental information by combining the battery environmental parameters and the vehicle environmental parameters.

[0100] Optionally, in some possible embodiments, the acquisition unit 601 is specifically used to call the driving record corresponding to the vehicle;

[0101] The acquisition unit 601 is specifically used to determine multiple areas involved in the driving record to obtain area information;

[0102] The acquisition unit 601 is specifically configured to determine the associated region to which the positioning parameter belongs in the region information;

[0103] The acquisition unit 601 is specifically configured to use the statistical information corresponding to the associated area as the vehicle environment parameter.

[0104] Optionally, in some possible embodiments, the processing unit 602 is specifically configured to determine the battery environment parameters and the vehicle environment parameters included in the environment information;

[0105] The processing unit 602 is specifically configured to perform parameter comparison based on the battery environment parameter to determine a first adjustment factor;

[0106] The processing unit 602 is specifically used to obtain mileage data corresponding to different area information in the vehicle environment parameters;

[0107] The processing unit 602 is specifically configured to integrate the adjustment factors corresponding to each area based on the mileage data to obtain a second adjustment factor;

[0108] The processing unit 602 is specifically configured to weight the first weight information according to the first adjustment factor and the second adjustment factor to obtain second weight information.

[0109] Optionally, in some possible embodiments, the processing unit 602 is specifically used to determine a plurality of environmental bins simulating the environment of the vehicle, wherein the environmental bins are configured in different geographical areas;

[0110] The processing unit 602 is specifically used to execute different charging information based on different environmental information, and determine the battery charge state corresponding to the low-voltage battery to collect training data;

[0111] The processing unit 602 is specifically configured to train the target neural network based on the training data.

[0112] Optionally, in some possible embodiments, the acquisition unit 601 is specifically used to acquire discharge detection data corresponding to the low-voltage battery configured for the vehicle during discharge, and the discharge detection data includes discharge information and environmental information;

[0113] The processing unit 602 is specifically configured to input the discharge detection data into a target neural network and determine third weight information corresponding to the discharge information;

[0114] The processing unit 602 is specifically configured to weight the third weight information in combination with the environment information to obtain fourth weight information;

[0115] The processing unit 602 is specifically configured to execute the target neural network according to the fourth weight information to output a battery state of charge corresponding to the low-voltage battery.

[0116] Specifically, the processing unit and the acquisition unit in this embodiment may correspond to physical components. For example, the processing unit may be a processing module such as a CPU, a GPU, or an FPGA, and the acquisition unit may be an acquisition module such as a detector or a sensor. The specific physical components may be any components or combinations of components having the above functions. The specific method depends on the actual scenario and is not limited here.

[0117] The above-mentioned processing device obtains the charging detection data corresponding to the low-voltage battery configured in the vehicle when charging, and the charging detection data includes charging information and environmental information; then inputs the charging detection data into the target neural network, and determines the first weight information corresponding to the charging information; and weights the first weight information in combination with the environmental information to obtain the second weight information; and then executes the target neural network according to the second weight information to output the battery state of charge corresponding to the low-voltage battery. Thus, the calibration process of the battery state of charge of the low-voltage battery is realized, and the charging information is fitted by the neural network, and the weight is adjusted in combination with the environment in which the low-voltage battery is located, so that the battery state of charge can be dynamically estimated, thereby improving the accuracy of the battery state of charge data of the low-voltage battery.

[0118] For the specific definition of the battery information processing device, please refer to the definition of the battery information processing method mentioned above, which will not be repeated here. The various unit modules in the above-mentioned battery information processing device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0119] Another embodiment of the present application further provides a computing device, see Figure 7 As shown, an exemplary embodiment of the present specification also provides a computing device, including: a memory and a processor, the memory storing a computer program, and the processor executing the computer program when executing the steps of the battery information processing method according to various embodiments of the present specification described in the above embodiments of the present specification.

[0120] The internal structure of the computing device can be as follows Figure 7As shown, the computing device includes a processor, a memory, a network interface and an input device connected via a system bus. The processor of the computing device is used to provide computing and control capabilities. The memory of the computing device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computing device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the steps of the method for processing battery information according to various embodiments of the present specification are described in the above embodiments of the present specification.

[0121] The processor may include a main processor and may also include a baseband chip, a modem, etc.

[0122] The memory stores a program for executing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes computer operation instructions. More specifically, the memory may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0123] The processor may be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the scheme of the present invention. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0124] The input device may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0125] Output devices may include means that allow information to be output to a user, such as display screens, printers, speakers, etc.

[0126] The communication interface may include using any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0127] The processor executes the program stored in the memory and calls other devices, which can be used to implement each step of any battery information processing method provided in the above embodiments of the present application.

[0128] The computing device may also include a display component and a voice component. The display component may be a liquid crystal display or an electronic ink display. The input device of the computing device may be a touch layer covered on the display component, or a button, trackball or touchpad provided on the housing of the computing device, or an external keyboard, touchpad or mouse.

[0129] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of this specification, and does not constitute a limitation on the computing device to which the scheme of this specification is applied. The specific computing device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0130] In addition to the above-mentioned methods and devices, the battery information processing method provided in the embodiments of this specification may also be a computer program product, which includes a computer program, which, when executed by a processor, enables the processor to execute the steps of the battery information processing method according to various embodiments of this specification described in the above "Exemplary Method" section of this specification.

[0131] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present specification, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0132] In addition, an embodiment of the present specification also provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to execute the steps of the battery information processing method according to various embodiments of the present specification described in the above "Exemplary Method" section of the present specification.

[0133] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this specification can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0134] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0135] The above-mentioned embodiments only express several implementation methods of this specification, and the descriptions are relatively specific and detailed, but they cannot be understood as limiting the scope of the solutions provided by the embodiments of this specification. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of this specification, which all belong to the protection scope of this specification. Therefore, the protection scope of the patent of this specification shall be based on the attached claims.

Claims

1. A method for processing battery information, characterized in that: include: Acquire charging detection data corresponding to the low-voltage battery configured for the vehicle during charging, wherein the charging detection data includes charging information and environmental information; Inputting the charging detection data into a target neural network, and determining first weight information corresponding to the charging information; weighting the first weight information in combination with the environmental information to obtain second weight information; The target neural network is executed according to the second weight information to output a battery state of charge corresponding to the low-voltage battery.

2. The method according to claim 1, characterized in that The obtaining of charging detection data corresponding to the low-voltage battery configured in the vehicle during charging includes: Obtaining a detection cycle for a low-voltage battery configuration in the vehicle; Performing parameter detection on the charging process of the low-voltage battery in a time period corresponding to the detection cycle to obtain the charging information; Determining environmental information corresponding to the vehicle during the detection period; The charging information and the environmental information are combined to obtain the charging detection data.

3. The method according to claim 2, characterized in that The performing parameter detection on the charging process of the low-voltage battery in the time period corresponding to the detection cycle to obtain the charging information includes: Obtaining current parameters, voltage parameters and charging capacity of the low-voltage battery in a time period corresponding to the detection cycle; Comparing the current parameter, the voltage parameter and the charge amount with respective corresponding calibration parameters to obtain a health parameter; The charging information is obtained by combining the current parameter, the voltage parameter, the charge amount and the health parameter.

4. The method according to claim 2, characterized in that: The determining of the environmental information corresponding to the vehicle within the detection period includes: Performing environmental detection based on sensors configured in the vehicle to obtain battery environmental parameters; Performing position detection on the vehicle within the detection period to obtain positioning parameters; Performing data retrieval based on the positioning parameters to determine vehicle environment parameters associated with the positioning parameters; The environmental information is obtained by combining the battery environmental parameters and the vehicle environmental parameters.

5. The method according to claim 4, characterized in that The performing data retrieval based on the positioning parameter to determine the vehicle environment parameter associated with the positioning parameter includes: Calling the driving record corresponding to the vehicle; Determining multiple areas involved in the driving record to obtain area information; Determining the associated region to which the positioning parameter belongs in the region information; The statistical information corresponding to the associated area is used as the vehicle environment parameter.

6. The method according to claim 1, characterized in that The step of weighting the first weight information in combination with the environment information to obtain second weight information includes: Determining battery environmental parameters and vehicle environmental parameters included in the environmental information; Perform parameter comparison based on the battery environment parameter to determine a first adjustment factor; Obtaining mileage data corresponding to different area information in the vehicle environmental parameters; Integrating the adjustment factors corresponding to the various regions based on the mileage data to obtain a second adjustment factor; The first weight information is weighted according to the first adjustment factor and the second adjustment factor to obtain second weight information.

7. The method according to claim 1, characterized in that The training process of the target neural network includes: Determine a plurality of environmental chambers simulating the environment of the vehicle, wherein the environmental chambers are arranged in different geographical areas; Execute different charging information based on different environmental information, and determine the battery state of charge corresponding to the low-voltage battery to collect training data; The target neural network is trained based on the training data.

8. The method according to any one of claims 1 to 7, characterized in that: The method further comprises: Acquire discharge detection data corresponding to a low-voltage battery configured for a vehicle during discharge, wherein the discharge detection data includes discharge information and environmental information; Inputting the discharge detection data into a target neural network, and determining third weight information corresponding to the discharge information; weighting the third weight information in combination with the environmental information to obtain fourth weight information; The target neural network is executed according to the fourth weight information to output a battery state of charge corresponding to the low-voltage battery.

9. A vehicle, characterized in that: The vehicle executes the battery information processing method according to any one of claims 1 to 8.

10. A computing device, characterized in that The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the battery information processing method according to any one of claims 1 to 8 when executing the computer program.

11. A computer program product, characterized in that include: A computer program, wherein when the computer program is executed by a processor, the method for processing battery information according to any one of claims 1 to 8 is implemented.

Images