Fault warning method, device, electronic device and storage medium for charging and swapping stations

Abstract

The present application discloses a fault warning method, device, electronic device, and storage medium for a charging and swapping station. The fault warning method for the charging and swapping station includes: obtaining first sensing information reported by a first smart fuse, where the first smart fuse is a smart fuse configured for any branch of a first battery compartment, and the first battery compartment is any one of multiple battery compartments; determining the operating status of the branch monitored by the first smart fuse based on the first sensing information, where the operating status includes a normal state and an abnormal state; and sending a warning message to a user device when the operating status is an abnormal state, where the warning message includes the abnormality type and abnormal area. The present application is conducive to improving the timeliness and accuracy of fault identification of the circuit system of the battery compartment in the charging and swapping station.

Description

Technical Field

[0001] The present application relates to the technical field of new energy charging and swapping stations, and specifically to a fault warning method, device, electronic equipment and storage medium for a charging and swapping station. Background Art

[0002] A charging and swapping station is a device that uses an external power source to charge various charging card batteries or rechargeable batteries, which can be used to charge the power batteries of electric vehicles. Existing charging and swapping stations are equipped with fuses for overcurrent protection. In the event of an overload or short circuit at the charging and swapping station, the overheating fuse will melt the fuse, disconnecting the circuit, thereby preventing damage to the charging and swapping station or the risk of fire. After the fuse melts, the charging and swapping station will report the operational failure to notify operations and maintenance personnel for repairs. Until the repairs are completed, the charging and swapping station's operations will be restricted, affecting the overall stability and smoothness of the charging and swapping station's business. Summary of the Invention

[0003] The embodiments of the present application provide a fault warning method, device, electronic device and storage medium for a charging and swapping station, in order to improve the timeliness and accuracy of fault identification of the circuit system of the battery compartment in the charging and swapping station and optimize the operating efficiency of the charging and swapping station.

[0004] In a first aspect, an embodiment of the present application provides a fault warning method for a charging and swapping station, which is applied to a server in a fault warning system, wherein the fault warning system includes the server, the charging and swapping station, and a user device, wherein the charging and swapping station and the user device are respectively communicatively connected to the server, the charging and swapping station includes multiple battery compartments, and the circuit system of a single battery compartment includes a signal branch, a charging branch, and a control branch, wherein the signal branch, the charging branch, and the control branch are all configured with an intelligent fuse, and the intelligent fuse is used to collect sensory information corresponding to the monitored branch, wherein the sensory information includes current, temperature, and voltage; the method includes:

[0005] Obtaining first sensing information reported by a first smart fuse, where the first smart fuse is a smart fuse configured for any branch of a first battery compartment, and the first battery compartment is any one of the multiple battery compartments;

[0006] Determine, based on the first sensing information, a working state of the branch monitored by the first smart fuse, where the working state includes a normal state and an abnormal state;

[0007] When the working state is an abnormal state, early warning information is sent to the user equipment, where the early warning information includes an abnormality type and an abnormal area.

[0008] In a second aspect, an embodiment of the present application provides a fault warning device for a charging and swapping station, which is applied to a server in a fault warning system. The fault warning system includes the server, the charging and swapping station, and a user device. The charging and swapping station and the user device are respectively communicatively connected to the server. The charging and swapping station includes multiple battery compartments. The circuit system of a single battery compartment includes a signal branch, a charging branch, and a control branch. The signal branch, the charging branch, and the control branch are all configured with an intelligent fuse. The intelligent fuse is used to collect sensory information corresponding to the monitored branch, and the sensory information includes current, temperature, and voltage. The fault warning device of the charging and swapping station includes:

[0009] an acquiring unit, configured to acquire first sensing information reported by a first smart fuse, where the first smart fuse is a smart fuse configured for any branch of a first battery compartment, and the first battery compartment is any one of the multiple battery compartments;

[0010] a determining unit, configured to determine, based on the first sensing information, a working state of the branch monitored by the first smart fuse, where the working state includes a normal state and an abnormal state;

[0011] An early warning unit is used to send early warning information to the user equipment when the working state is an abnormal state, wherein the early warning information includes an abnormal type and an abnormal area.

[0012] In a third aspect, an embodiment of the present application provides an electronic device comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in the first aspect of the embodiment of the present application.

[0013] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium that stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute some or all of the steps described in the first aspect of this embodiment.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, in which electronic data is stored. When the electronic data is executed by a processor, the electronic data is used to execute the electronic data to implement some or all of the steps described in the first aspect of the present application.

[0015] In a fifth aspect, the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a computer to perform some or all of the steps described in the first aspect of the present application. The computer program product may be a software installation package.

[0016] It can be seen that in this embodiment, by obtaining the first perception information reported by the first intelligent fuse, the first intelligent fuse is an intelligent fuse configured for any branch of the first battery compartment, and the first battery compartment is any one of the multiple battery compartments; the working status of the branch monitored by the first intelligent fuse is determined according to the first perception information, and the working status includes normal status and abnormal status; when the working status is abnormal, an early warning information is sent to the user device, and the early warning information includes the abnormal type and abnormal area. The present application can detect the abnormal state of the branch according to the first perception information, so that the abnormal operation can be identified before the charging and swapping station reports the branch operation failure, and then the operation and maintenance personnel can be notified to perform maintenance by sending an early warning information to the user equipment, so that the operation and maintenance personnel can arrange the maintenance time in advance to avoid affecting the normal operation of the charging and swapping station. At the same time, by realizing timely monitoring and troubleshooting, it can also avoid the chain reaction of risks of other battery compartments caused by a single battery compartment problem, which is conducive to reducing the risk of failure. It can be seen that compared with the existing scheme for monitoring the status of charging and swapping stations based on fuses, the present application can be refined to the dimensions of key circuit branches in the circuit system of each battery compartment, and can comprehensively and accurately collect the perception information of each key circuit branch, so that the server can process the collected perception information in real time, comprehensively and finely, and analyze and identify the working status of each branch in each battery compartment, thereby improving the accuracy, real-time and intelligence of fault diagnosis of charging and swapping stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 This is a schematic diagram of the architecture of a fault warning system provided by an embodiment of the present application;

[0019] Figure 2 This is a flow chart of a fault warning method for a charging and swapping station provided in an embodiment of the present application;

[0020] Figure 3 This is an interface display diagram of a user device displaying warning information provided by an embodiment of the present application;

[0021] Figure 4 This is a block diagram of the functional units of a fault warning device for a charging and swapping station provided in an embodiment of the present application;

[0022] Figure 5This is a block diagram of the functional units of another fault warning device for a charging and swapping station provided in an embodiment of the present application;

[0023] Figure 6 This is an example diagram of the composition of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0025] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0026] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0027] The embodiments of the present application are described below with reference to the accompanying drawings.

[0028] See Figure 1 , Figure 1 This is a schematic diagram of the architecture of a fault warning system provided by an embodiment of the present application. Figure 1 As shown, the fault warning system 10 includes a server 110, a charging and swapping station 120, and a user device 130. The charging and swapping station 120 and the user device 130 are respectively connected to the server 110 for communication.

[0029] Specifically, the charging and swapping station includes multiple battery compartments (such as the first battery compartment, the second battery compartment... and the Nth battery compartment). The circuit architecture of a single battery compartment generally includes: a battery pack, a battery management system (i.e., BMS, Battery Management System), a charging and discharging circuit, and a communication circuit. In this embodiment, the circuit system of the battery compartment is divided into key circuit branches such as a signal branch, a charging branch, and a control branch. Among them, the control branch includes at least a battery pack and a battery management system, the charging branch includes at least a charging and discharging circuit, and the signal branch includes at least a communication circuit. For example, see Figure 1 The first battery compartment 121 includes a first signal branch 122, a first charging branch 123, and a first control branch 124; the second battery compartment includes a second signal branch, a second charging branch, and a second control branch... The Nth battery compartment includes an Nth signal branch, an Nth charging branch, and an Nth control branch. Each of these signal branches, charging branches, and control branches is equipped with a smart fuse, which is used to collect sensory information from the corresponding monitored branch. This sensory information includes parameters such as current, temperature, and voltage. For example, the smart fuse may include a built-in MCU (Micro Control Unit) and a sensing circuit, where the sensing circuit may be configured with components such as current sensors, voltage sensors, and temperature sensors. After collecting sensory information related to the branch within the charging and swapping station, the smart fuse can transmit this information to the signal branch, which then transmits it to the operation and maintenance platform server. Alternatively, the smart fuse can directly transmit the collected data to the operation and maintenance platform server via wireless communication technology.

[0030] Specifically, server 110 refers to a remote computer used to process large amounts of computing tasks and store data. Exemplarily, server 110 can be an outsourced server, a cloud server, an edge server, an intelligent robot, and the like, without limitation. The server can statistically analyze the acquired sensor information from each branch and simultaneously identify the operating status of multiple branches. When an abnormality is detected in a branch based on the identification and analysis results, it can promptly issue an early warning signal and synchronize the abnormality type and area. Operations and maintenance personnel can then pre-arrange maintenance work based on the early warning signal.

[0031] Specifically, user device 130 generally refers to a device used by operations and maintenance personnel. For example, user device 130 may be a smartphone (e.g., an Android phone, an iOS phone, a Windows Phone phone, etc.), a smart computer (e.g., a tablet computer, a PDA, a laptop computer, a desktop computer, etc.), a driving recorder, a mobile internet device (MID), or a wearable device (e.g., a smartwatch, smart glasses, etc.). The above are merely examples, not an exhaustive list, and include, but are not limited to, the above devices.

[0032] Based on this, the present application provides a fault warning method, device, electronic device and storage medium for a charging and swapping station. The present application is described in detail below with reference to the accompanying drawings.

[0033] See also Figure 2 , Figure 2 This is a flow chart of a fault warning method for a charging and swapping station provided by an embodiment of the present application, such as Figure 2 As shown, the fault warning method of the charging and swapping station includes the following steps:

[0034] S210: Obtain first perception information reported by the first smart fuse.

[0035] Among them, the first smart fuse is a smart fuse configured for any branch of the first battery compartment, and the first battery compartment is any one of the multiple battery compartments in the charging and swapping station.

[0036] Specifically, the first smart fuse can collect and report parameter data such as the current, voltage, and temperature of the monitored branch in real time. The data reported by each smart fuse can be stored separately to prevent data contamination that could affect the accuracy of analysis and identification. Similarly, the sensory information collected by the same smart fuse can be classified and stored separately based on data type (such as current, voltage, or temperature).

[0037] S220: Determine the working status of the branch monitored by the first smart fuse based on the first perception information.

[0038] The operating status includes a normal state and an abnormal state. Specifically, a normal state means that the monitored branch is operating normally. An abnormal state means that the monitored branch is at risk of failure or has already failed.

[0039] In a specific implementation, the server can train a corresponding model based on historical data, then use the acquired first perception information as model input to perform predictions and obtain prediction results. Based on the prediction results, the server analyzes whether the branch monitored by the first smart fuse has a fault risk. If not, the operating status of the branch is marked as normal; if so, the operating status of the branch is marked as abnormal.

[0040] In a specific implementation, before the server performs analysis and prediction based on the first perception information, it can also directly analyze and identify the current or voltage values ​​in the first perception information (such as when the voltage is zero, etc.) to determine whether the current branch is operating normally. Alternatively, the intelligent fuse can directly report fault information when the fuse blows. The above-mentioned method of identifying whether the operation of the current branch is normal or the above-mentioned method of receiving and reporting fault information can enable the server to determine whether the current branch has failed. If a fault is detected, the working state of the branch is directly marked as abnormal. If no fault is detected, further analysis can be performed based on the first perception information. By identifying whether a fault has occurred before performing analysis and prediction based on the first perception information, the accuracy of monitoring can be further improved, and unexpected events caused by the actual situation deviating from the prediction can be avoided, resulting in untimely maintenance.

[0041] S230: When the working state is an abnormal state, send warning information to the user equipment.

[0042] The warning information includes an abnormality type and an abnormality area. The abnormality type includes circuit break, overcharge, overheating, etc. The abnormality area is used to indicate the location of the branch monitored by the first smart fuse.

[0043] Specifically, when it is determined that the working state of the current branch is an abnormal state, the server can further analyze the first perception information to determine the abnormality type corresponding to the current abnormal state based on the first perception information.

[0044] Specifically, the server may pre-store the location information of each smart fuse. When determining that the current branch's operating state is abnormal, the server may retrieve the location information corresponding to the smart fuse in the current branch and identify this location information as the abnormal area. Alternatively, when determining that the current branch's operating state is abnormal, the server may send a location acquisition request to the smart fuse or the signal branch of the branch where the smart fuse is located, and identify the location described in the response information to the acquisition request as the abnormal area.

[0045] In a specific implementation, if a single operation and maintenance personnel is configured for the charging and swapping station, the operation and maintenance personnel can receive the early warning information through a user device. If multiple operation and maintenance personnel are configured for the charging and swapping station, the user device can be a device used by the management personnel. After the management personnel receive the early warning information through the user device, they can dispatch different operation and maintenance personnel for maintenance based on the abnormal type and abnormal area. For example, an operation and maintenance personnel with abnormal type maintenance capabilities in the abnormal area can be dispatched to improve the efficiency and reliability of maintenance. Alternatively, when multiple operation and maintenance personnel are configured for the charging and swapping station, the user device can also be a device used by the operation and maintenance personnel. In this case, the fault early warning system includes multiple user devices that are communicatively connected to the server. The server can send early warning information to the user device used by the adapted operation and maintenance personnel based on the abnormal type and abnormal area. In this case, the operation and maintenance personnel are operation and maintenance personnel with abnormal type maintenance capabilities in the abnormal area.

[0046] Specifically, the warning information received by the user device can be presented in the form of SMS notification, application message notification, message pop-up window and application program interface. For example, when the user device is a smart phone, the warning information can be presented through the application interface of the software program application supported by the fault warning system, such as Figure 3 As shown, the application interface includes a first area 310 and a second area 320. The first area 310 is used to display the abnormality type (such as short circuit), and the second area 320 is used to display the abnormal area (such as the first charging branch in the first battery compartment). Figure 3 The second area 320 may also include a "location navigation" control. When the operation and maintenance personnel trigger the "location navigation" control by single-clicking, double-clicking, or long pressing, the user device may correspondingly present a three-dimensional image of the abnormal area marked by the charging and swapping station or information such as a navigation route to the abnormal area.

[0047] Specifically, the warning information may also include a recommended tool, which is a tool recommended for troubleshooting the abnormality type. The recommendation is the content obtained by the server matching the abnormality type in the database. Or, specifically, the warning information may also include the first perception information, such as Figure 3 As shown, this can be further confirmed by manual identification, thereby further ensuring the accuracy of content analysis and identification such as working status and abnormal type. Among them, the data in the first perception information can be presented in the form of images or data text. When presented in the form of images, multiple types of parameters in the first perception information can be presented through one or more images, without further limitation. For example, see Figure 3 In the third area 330 shown, the operation and maintenance personnel can trigger the "temperature data" control, "current data" control or "voltage data" control in the third area 330 by single-clicking, double-clicking or long pressing to present the corresponding content.

[0048] It can be seen that in this embodiment, by obtaining the first perception information reported by the first intelligent fuse, the first intelligent fuse is an intelligent fuse configured for any branch of the first battery compartment, and the first battery compartment is any one of the multiple battery compartments; the working status of the branch monitored by the first intelligent fuse is determined according to the first perception information, and the working status includes normal status and abnormal status; when the working status is abnormal, an early warning information is sent to the user device, and the early warning information includes the abnormal type and abnormal area. The present application can detect the abnormal state of the branch according to the first perception information, so that the abnormal operation can be identified before the charging and swapping station reports the branch operation failure, and then the operation and maintenance personnel can be notified to perform maintenance by sending an early warning information to the user equipment, so that the operation and maintenance personnel can arrange the maintenance time in advance to avoid affecting the normal operation of the charging and swapping station. At the same time, by realizing timely monitoring and troubleshooting, it can also avoid the chain reaction of risks of other battery compartments caused by a single battery compartment problem, which is conducive to reducing the risk of failure. It can be seen that compared with the existing scheme for monitoring the status of charging and swapping stations based on fuses, the present application can be refined to the dimensions of key circuit branches in the circuit system of each battery compartment, and can comprehensively and accurately collect the perception information of each key circuit branch, so that the server can process the collected perception information in real time, comprehensively and finely, and analyze and identify the working status of each battery compartment, thereby improving the accuracy, real-time and intelligence of fault diagnosis of charging and swapping stations.

[0049] In one possible example, determining the working state of the branch monitored by the first smart fuse based on the first perception information includes: inputting the first perception information into a pre-trained normal state model to obtain a predicted value; determining the working state of the branch monitored by the first smart fuse based on the predicted value; when the working state is an abnormal state, inputting the first perception information into a pre-trained fault type identification model to obtain the abnormal type.

[0050] The normal state model and the fault type identification model are used to assist in determining the working state of the branch and the abnormal type in the event of an abnormality, respectively.

[0051] In a specific implementation, each battery compartment can use the same normal state model to process the first data to reduce the performance requirements of the server. Alternatively, the server can train and configure different normal state models for each battery compartment to process the perception information reported by each battery compartment separately, so that the output results of the normal state model are more consistent with the actual usage of the battery compartment.

[0052] In one possible example, the normal state model is determined according to the following method: obtaining a first initial model and a training data set; obtaining second data of the first battery compartment, the second data including at least one of the usage history, battery type and environmental information of the first battery compartment; adjusting the model parameters of the first initial model according to the second data to obtain a second initial model; training the second initial model according to the training data set to obtain the normal state model.

[0053] Among them, the first initial model can be constructed using a deep autoencoder. Exemplarily, the model structure of the first initial model may include an input layer, 5 hidden layers and an output layer. The number of neurons in each layer can be gradually reduced from 100 in the input layer to 10 in the middle hidden layer, and then gradually increased to 100 in the output layer. Among them, the training data set is the historical data of the first battery compartment, or the training data set is the historical data of other battery compartments with the same usage time, battery type, environmental conditions and other factors as the first battery compartment. The training data set includes information such as current, voltage and temperature.

[0054] The usage history is used to characterize the usage duration of the first battery compartment. The battery type is used to characterize the type of battery pack configured in the first battery compartment, such as a lithium-ion battery, lead-acid battery, or flow battery. The battery type can further characterize the manufacturer of the battery pack. The environmental information is used to characterize the geographical environment conditions of the first battery compartment.

[0055] In a specific implementation, the server is pre-configured with a parameter adjustment strategy corresponding to the usage history, battery type, and environmental information. When constructing a normal state model corresponding to the first battery compartment, the model parameters of the first initial model can be adjusted according to the second data of the first battery compartment obtained and the pre-configured parameter adjustment strategy to obtain a second initial model. Specifically, the parameter adjustment strategy may include: pre-configuring specific model parameters according to different battery types and different environmental information, and configuring adjustment measures according to differences in usage time. Among them, the adjustment measures are to adjust the model parameters of the first initial model to specific model parameters based on different battery types and different environmental information, and further adjust the weight attenuation coefficients between the hidden layers of the model according to the preset ratio corresponding to the usage time. For example, the usage time can be divided into multiple time nodes such as within one year, more than one year and less than two years, more than two years and less than five years, and more than five years. The adjustment measures corresponding to each time node correspond to a preset ratio.

[0056] Specifically, adjusting the model parameters of the first initial model based on the second data to obtain the second initial model may be performed by: after obtaining the second data of the first battery compartment, obtaining corresponding specific model parameters based on the battery type and environmental information in the second data, and adjusting the model parameters of the first initial model to the specific model parameters. The server may then determine the usage duration corresponding to the usage history in the second data and obtain adjustment measures corresponding to the usage duration. Specifically, if the usage duration is less than one year, the model adjusted to the specific model parameters may be directly determined as the second initial model. If the usage duration is between one and two years, the weight decay coefficients between hidden layers may be further increased by a first preset ratio based on the model adjusted to the specific model parameters to obtain the second initial model. If the usage duration is between two and five years, the weight decay coefficients between hidden layers may be further increased by a second preset ratio based on the model adjusted to the specific model parameters to obtain the second initial model. If the usage duration is greater than five years, the weight decay coefficients between hidden layers may be further increased by a third preset ratio based on the model adjusted to the specific model parameters to obtain the second initial model. The weight attenuation coefficient corresponding to the first preset ratio is less than the weight attenuation coefficient corresponding to the second preset ratio, and less than the weight attenuation coefficient corresponding to the third preset ratio. This allows the second initial model to focus more on recent data features to better reflect the current performance status of the battery compartment.

[0057] In a specific implementation, during the training of the second initial model based on the training dataset, the server may preprocess the data in the training dataset and use it as input for the second initial model, thereby performing feature extraction and encoding through multiple hidden layers. The second initial model may be trained by minimizing the mean square error between the input data and the reconstructed data, so that the second initial model learns the intrinsic relationship between various parameters in the perceptual information under normal conditions, thereby obtaining a normal state model. The preprocessing operations performed on the data in the training dataset include at least one of data cleaning, data correlation verification, data filtering, and data normalization.

[0058] In a specific implementation, the preprocessing operation performed on the data in the training data set includes data cleaning of the first perception data. Specifically, data in the training data set that exceeds a preset range can be eliminated, and the preset range can be set to a current range, a voltage range, or a temperature range, etc. corresponding to the parameters in the perception information. Taking the current data in the training data set as an example, the server can eliminate negative numbers in the current data and data that exceeds ten times the normal operating current range of the battery compartment to eliminate abnormal individual current values ​​in the training data set. Specifically, missing data can be filled by interpolation or other methods to ensure the consistency of the data. For example. Missing data can be filled based on data at adjacent moments. By cleaning the training data set, abnormal data in the training data set can be removed, which is conducive to ensuring the accuracy of subsequent analysis and identification.

[0059] In a specific implementation, the preprocessing of the data in the training dataset also includes verifying the data correlation of the training dataset. Specifically, the server can pre-build a data correlation model based on Kirchhoff's laws and battery charge and discharge characteristics. The correlation between temperature, voltage, and current can be determined based on the data correlation model. For example, after acquiring the training dataset or a cleaned training dataset, the acquired data can be input into the data correlation model to determine the correlation between the temperature, voltage, and current data at the same moment. If the correlation is less than a preset standard, the abnormal parameter data (i.e., data corresponding to parameters with large deviations) in the sensed information at that moment can be further cleaned. Alternatively, the server can verify the correlation between theoretical data and actual collected data based on relative deviation. For example, during the charging process, the data correlation model can determine the theoretical voltage at the battery output based on the input voltage, current, and the equivalent internal resistance of the batteries deployed in the battery compartment. The server can then calculate the relative deviation between the theoretical voltage and the actual voltage collected in the training dataset. Based on this relative deviation, the correlation between the theoretical voltage and the voltage collected in the training dataset can be determined. If the correlation is less than a preset standard, the voltage data can be cleaned.

[0060] In a specific implementation, the preprocessing operation performed on the data in the training data set may also include data filtering of the training data set. Specifically, the server may also use an adaptive Kalman filter algorithm to filter the above-mentioned processed data, so as to automatically adjust the filter parameters according to the real-time changes of the current, temperature and voltage in the training data set through the algorithm, thereby improving the accuracy of the filtering. For example, when the working stage of the battery compartment is the fast charging stage, the current fluctuation of the battery compartment will be aggravated. At this time, the adaptive Kalman filter algorithm can be used to automatically increase the process noise covariance, so that the filtering result is closer to the true value, effectively removing high-frequency noise and random interference, and ensuring the authenticity and accuracy of the data.

[0061] In a specific implementation, the preprocessing operations performed on the data in the training dataset may also include data standardization of the training dataset. Specifically, for the original data in the training dataset or the data after the above-mentioned cleaning and filtering processes, the server can further perform Z-score standardization processing to calculate the mean μ and standard deviation σ for each parameter type of sensory information in each battery compartment (i.e., current, temperature, voltage), and convert the training data x in the training dataset into training data represented in the form of z = (x-μ) / σ. This allows data from different battery compartments and different types to be unified into a standard normal distribution with a mean of 0 and a standard deviation of 1, facilitating subsequent analysis and model training.

[0062] It can be seen that in this example, by training and configuring different normal state models for each battery compartment in the above manner, the predicted value output by the normal state model corresponding to the first battery compartment can be more in line with the actual situation of the first battery compartment.

[0063] In a specific implementation, after the first perception information is input into a pre-trained normal state model, the normal state model will output a prediction value, which can be used to characterize the expected operation of the first battery compartment under normal conditions, that is, the data corresponding to the parameters in the expected perception information. Based on the prediction value, it can be determined whether the actual first perception information meets expectations. If it meets expectations, the working state of the current branch is determined to be normal; if it does not meet expectations, the working state is determined to be abnormal. Specifically, if it is determined that the working state of the current branch is normal, this round of fault warning analysis operation is terminated. If it is determined that the working state of the current branch is abnormal, the first perception information can be further input into a pre-trained fault type recognition model for identification to determine the abnormality type corresponding to the current abnormality.

[0064] It can be seen that in this example, by obtaining the abnormal type in the abnormal state according to the first perception information through the normal state model and the fault type identification model, it is possible to perform prediction and identification before the fault occurs, thereby ensuring the timeliness and accuracy of maintenance.

[0065] Specifically, determining whether the actual first perception information meets expectations based on the predicted value may include determining whether the data in the first perception information and the data corresponding to the predicted value are identical; if so, the expectations are met; if not, the expectations are not met. Alternatively, determining whether the actual first perception information meets expectations based on the predicted value may include determining whether the deviation between the data in the first perception information and the data corresponding to the predicted value is less than a preset threshold; if so, the expectations are met; if not, the expectations are not met.

[0066] In one possible example, determining the working status of the branch monitored by the first smart fuse based on the predicted value includes: determining a data deviation value based on the first perception information and the predicted value, the data deviation value being used to characterize the degree of deviation between the first perception information and the predicted value; obtaining the abnormality threshold of the branch monitored by the first smart fuse; comparing the data deviation value and the abnormality threshold to obtain a comparison result; and determining the working status of the branch monitored by the first smart fuse based on the comparison result.

[0067] The data deviation value may be any one of an absolute deviation, a relative deviation, or a rate of change deviation, or may be an average value or a weighted value of at least two of the absolute deviation, the relative deviation, or the rate of change deviation.

[0068] Specifically, the predicted value may be data corresponding to a parameter in the perception information. Taking the current in the first perception information as an example, the data deviation value can be determined based on the current in the first perception information and the current corresponding to the predicted value. Taking the voltage in the first perception information as an example, the data deviation value can be determined based on the voltage in the first perception information and the voltage corresponding to the predicted value. Alternatively, taking the temperature in the first perception information as an example, the data deviation value can be determined based on the temperature in the first perception information and the temperature corresponding to the predicted value. Alternatively, specifically, when the predicted value includes data corresponding to at least two parameters in the perception information, the data sub-deviation values ​​can be calculated respectively according to the type, and then the comprehensive deviation value, i.e., the data deviation value, can be determined by weighted averaging of the multiple data sub-deviation values.

[0069] The following example illustrates the calculation process for a data deviation value when the predicted value is a single parameter. When the predicted value includes at least two parameters, the data deviation values ​​described in the following example can also be compared to the data sub-deviation values ​​corresponding to a single parameter.

[0070] Exemplarily, in one possible example, determining the data deviation value based on the first perception information and the predicted value includes: determining the absolute value of the difference between the first perception information and the predicted value to obtain an absolute deviation value; determining the ratio of the absolute deviation value to the predicted value to obtain a relative deviation value; determining the absolute value of the difference between the rate of change of the first perception information and the rate of change of the predicted value to obtain a rate of change deviation value; obtaining the working stage of the branch monitored by the first intelligent fuse, the working stage including the early charging stage, the middle charging stage and the late charging stage; obtaining a weight ratio according to the working stage of the branch monitored by the first intelligent fuse; performing weighted summation of the absolute deviation value, the relative deviation value and the rate of change deviation value according to the weight ratio to obtain the data deviation value.

[0071] Among them, the working stage can be determined as the early charging stage, the middle charging stage and the late charging stage according to the state of the battery to be charged. In a specific implementation, the server can pre-configure a weight ratio corresponding to the early charging stage, the middle charging stage and the late charging stage, and store them accordingly, so that the corresponding weight ratio can be obtained after determining the working stage of the current branch. Specifically, in the early charging stage, the weight of the absolute deviation value can be set to be greater than the weight of the change rate deviation value, which is greater than the weight of the relative deviation value. As time changes, the weight of the absolute deviation value is lowered, and the weight of the relative deviation value is increased, until in the late charging stage, the weight of the relative deviation value is greater than the weight of the change rate deviation value, which is greater than the weight of the absolute deviation value. In this way, it can adapt to the current changes corresponding to the charging stage and ensure the accuracy of the data deviation value. Exemplarily, the over-matching ratios corresponding to different working stages can be: the weight ratio in the early stage of charging is an absolute deviation value of 0.5, a weight of the change rate deviation value of 0.3, and a relative deviation value of 0.2; the weight ratio in the middle stage of charging is an absolute deviation value of 0.33, a weight of the change rate deviation value of 0.34, and a relative deviation value of 0.33; the weight ratio in the late stage of charging is an absolute deviation value of 0.2, a weight of the change rate deviation value of 0.3, and a relative deviation value of 0.5.

[0072] It can be seen that in this example, by differentially configuring weight ratios of different deviations in different working stages, it is possible to adapt to current changes in different charging stages, so as to ensure that the final determined data deviation value more accurately reflects the branch situation and improves the accuracy of abnormality identification.

[0073] In a specific implementation, the abnormality threshold is a preset value, which can be configured according to the needs and is not further restricted here. By comparing the data deviation value and the abnormality threshold, it can be determined whether the data deviation value exceeds expectations. Specifically, the comparison result can be that the data deviation value is greater than the abnormality threshold or the data deviation value is less than or equal to the abnormality threshold. When the comparison result is that the data deviation value is greater than the abnormality threshold, it indicates that the difference between the actual data collected and the predicted value is large. At this time, the working state of the branch can be marked as an abnormal state. When the comparison result is that the data deviation value is less than or equal to the preset threshold, it indicates that the difference between the actual data collected and the predicted value is within the allowable error range. At this time, the working state of the branch can be marked as a normal state.

[0074] As can be seen, in this example, by determining the data deviation value between the first perception information and the predicted value, and then comparing the data deviation value with the abnormality threshold, the size of the data difference between the actually collected first perception information and the predicted value can be identified, thereby determining the operating status of the current branch. The comparison of the data deviation value with the abnormality threshold is a low-level process and can ensure recognition accuracy.

[0075] In one possible example, obtaining the abnormal threshold of the branch monitored by the first intelligent fuse includes: obtaining historical data of the first battery compartment; extracting data collected in the historical data in the sub-period that is the same as the sub-period for collecting the first perception information within a preset time period to obtain historical perception data; wherein the preset time period includes multiple unit time periods, and a single unit time period includes multiple unit sub-periods; classifying the historical perception data according to the working stage to obtain classified historical perception data; wherein the working stage includes the early charging stage, the middle charging stage, and the late charging stage; determining the threshold corresponding to each working stage according to the classified historical perception data; and determining the threshold corresponding to the working stage that is the same as the working stage of the branch monitored by the first intelligent fuse as the abnormal threshold.

[0076] The historical data includes current, voltage, and temperature. The preset period can be a week, a month, a quarter, or a year. The unit sub-period can be set based on the preset period as needed. For example, the unit sub-period can be a time period within a day or a day of the week, without further limitation.

[0077] In a specific implementation, the historical data may include all or part of the data stored after the first battery compartment began to be used. The server may first extract from the historical data the data for the preset time period that is adjacent to and before the time when the first perception information was collected, and then filter out the data for the sub-period that is the same as the sub-period for collecting the first perception information, and determine it as the historical perception data. For example, if the preset time period is one week, the unit sub-period is 8 hours, and the sub-period for collecting the first perception information is 8:00-16:00, then the historical perception data is the data collected from 8:00-16:00 every day in the week before the current moment.

[0078] In a specific implementation, the server may classify the acquired historical sensing data according to operating stages to obtain classified historical sensing data. The classified historical sensing data may then be statistically analyzed to determine thresholds corresponding to each operating stage, and the threshold corresponding to the operating stage corresponding to the first sensing information may be determined as the abnormality threshold. Specifically, the server may analyze the classified historical sensing data to determine the normal fluctuation range of the parameters in the sensing information under different conditions, and then further determine the current abnormality threshold based on the current conditions of the battery compartment. For example, the server may analyze the classified historical sensing data to determine current data fluctuations under different temperature and voltage conditions, and further obtain current fluctuations under conditions identical or similar to the current temperature and voltage of the first battery compartment to determine the abnormality threshold. Specifically, the server may obtain all current data in the historical sensing data under conditions identical or similar to the current temperature and voltage of the first battery compartment, and determine the difference between the maximum and minimum values ​​as the abnormality threshold; alternatively, the server may determine the maximum difference between the individual current data and the average value as the abnormality threshold. This ensures that the abnormality threshold corresponds to the operating state of the battery compartment under different temperature and voltage conditions at different time periods.

[0079] It can be seen that in this example, the accuracy of abnormal state identification can be further improved by dynamically setting the abnormality threshold according to the historical data and real-time operating status of the battery compartment.

[0080] In one possible example, when the working state is an abnormal state, the first perception information is input into a pre-trained fault type recognition model to obtain the abnormal type, including: obtaining a fault database, the fault database is established based on historical fault data, the fault database includes multiple fault types and features of the corresponding perception information; inputting the first perception information into a pre-trained fault type recognition model to obtain a first feature of the first perception information; matching the first feature with the fault database to obtain a matching result; and determining the abnormal type based on the matching result.

[0081] The historical fault data may include at least fault data for all battery compartments in the power conversion station. The fault data includes the fault type and corresponding sensory information data features. The sensory information corresponding to the fault type in the fault database may be stored in the form of a feature vector.

[0082] In a specific implementation, the fault type recognition model can be a convolutional neural network model, which is used to extract features of sensory information. For example, it may include three convolutional layers, two pooling layers, and two fully connected layers. Before the first sensory information is input into the fault type recognition model, the server may convert the first sensory information into an image format, thereby inputting the first sensory data in image format into the fault type recognition model. The fault type recognition model then extracts the vector features of the first sensory information, i.e., the first features. The image corresponding to the first sensory information can represent how current, temperature, and voltage change over time.

[0083] Specifically, the server can match the first feature with features in the fault database to determine the fault type corresponding to the feature with the highest similarity as the matching result. Alternatively, specifically, matching the first feature with the fault database to obtain a matching result includes: statistically calculating the probability of different fault types occurring based on historical fault data, as well as the conditional probability of various features appearing under different fault types. The Bayesian formula is then used to calculate the probability of each fault type occurring in the first feature corresponding to the first perception information, and the fault type with the highest probability is determined as the matching result. This matching result is highly reliable.

[0084] It can be seen that in this example, the image feature comparison method can be used to integrate multiple parameters such as current, temperature, and voltage for fault identification, quickly locate the abnormality type, and improve the efficiency of abnormality type determination.

[0085] In accordance with the above-mentioned embodiment, please refer to Figure 4 , Figure 4 This is a functional unit composition block diagram of a fault warning device of a charging and swapping station provided in an embodiment of the present application. The fault warning device of the charging and swapping station is a server or a part of a server in the above-mentioned fault warning system. The fault warning system includes a server, a charging and swapping station, and a user device. The charging and swapping station and the user device are respectively connected to the server for communication. The charging and swapping station includes multiple battery compartments. The circuit system of a single battery compartment includes a signal branch, a charging branch, and a control branch. The signal branch, the charging branch, and the control branch are all equipped with smart fuses. The smart fuses are used to collect sensory information of the corresponding monitored branch. The sensory information includes current, temperature, and voltage. The fault warning device 40 of the charging and swapping station includes:

[0086] an acquiring unit 410, configured to acquire first sensing information reported by a first smart fuse, where the first smart fuse is a smart fuse configured for any branch of a first battery compartment, and the first battery compartment is any one of the multiple battery compartments;

[0087] a determining unit 420, configured to determine, based on the first sensing information, an operating state of the branch monitored by the first smart fuse, where the operating state includes a normal state and an abnormal state;

[0088] The early warning unit 430 is configured to send early warning information to the user equipment when the working state is abnormal, where the early warning information includes an abnormal type and an abnormal area.

[0089] In one possible example, in terms of determining the working state of the branch monitored by the first smart fuse based on the first perception information, the determination unit is specifically used to: input the first perception information into a pre-trained normal state model to obtain a predicted value; determine the working state of the branch monitored by the first smart fuse based on the predicted value; when the working state is an abnormal state, input the first perception information into a pre-trained fault type identification model to obtain the abnormal type.

[0090] In one possible example, in terms of determining the working status of the branch monitored by the first smart fuse based on the predicted value, the determination unit is specifically used to: determine a data deviation value based on the first perception information and the predicted value, and the data deviation value is used to characterize the degree of deviation between the first perception information and the predicted value; obtain the abnormality threshold of the branch monitored by the first smart fuse; compare the data deviation value and the abnormality threshold to obtain a comparison result; and determine the working status of the branch monitored by the first smart fuse based on the comparison result.

[0091] In one possible example, in terms of determining the data deviation value based on the first perception information and the predicted value, the determination unit is specifically further used to: determine the absolute value of the difference between the first perception information and the predicted value to obtain an absolute deviation value; determine the ratio of the absolute deviation value to the predicted value to obtain a relative deviation value; determine the absolute value of the difference between the change rate of the first perception information and the change rate of the predicted value to obtain a change rate deviation value; obtain the working stage of the branch monitored by the first intelligent fuse, the working stage including the early charging stage, the middle charging stage and the late charging stage; obtain a weight ratio according to the working stage of the branch monitored by the first intelligent fuse; and perform weighted summation of the absolute deviation value, the relative deviation value and the change rate deviation value according to the weight ratio to obtain the data deviation value.

[0092] In one possible example, in terms of obtaining the abnormal threshold of the branch monitored by the first intelligent fuse, the determination unit is specifically further used to: obtain historical data of the first battery compartment; extract data collected in the historical data in the sub-period that is the same as the sub-period for collecting the first perception information within a preset time period to obtain historical perception data; wherein the preset time period includes multiple unit time periods, and a single unit time period includes multiple unit sub-periods; classify the historical perception data according to the working stage to obtain classified historical perception data; wherein the working stage includes the early charging stage, the middle charging stage and the late charging stage; determine the thresholds corresponding to each working stage according to the classified historical perception data; and determine the threshold corresponding to the working stage that is the same as the working stage of the branch monitored by the first intelligent fuse as the abnormal threshold.

[0093] In one possible example, the fault warning device of the charging and swapping station also includes a training unit, which is specifically used to determine a normal state model, and the normal state model is determined according to the following method: obtaining a first initial model and a training data set; obtaining second data of the first battery compartment, the second data including at least one of the usage history, battery type and environmental information of the first battery compartment; adjusting the model parameters of the first initial model according to the second data to obtain a second initial model; training the second initial model according to the training data set to obtain the normal state model.

[0094] In one possible example, when the working state is an abnormal state, the first perception information is input into a pre-trained fault type recognition model to obtain the abnormal type. The determination unit is specifically used to: obtain a fault database, which is established based on historical fault data, and the fault database includes multiple fault types and their corresponding perception information features; input the first perception information into a pre-trained fault type recognition model to obtain a first feature of the first perception information; match the first feature with the fault database to obtain a matching result; and determine the abnormal type based on the matching result.

[0095] It can be understood that since the method embodiment and the device embodiment are different presentation forms of the same technical concept, the content of the method embodiment part in this application should be synchronously adapted to the device embodiment part and will not be repeated here.

[0096] In the case of using an integrated unit, the functional unit composition block diagram of another fault warning device of a charging and swapping station provided in an embodiment of the present application is as follows: Figure 5 As shown. Figure 5In the embodiment, the fault warning device 40 of the charging and swapping station includes: a processing module 520 and a communication module 510. The processing module 520 is used to control and manage the actions of the fault warning device 40 of the charging and swapping station, for example, the steps performed by the acquisition unit 410, the determination unit 420 and the warning unit 430, and / or other processes for performing the technology described herein. The communication module 510 is used to support the interaction between the fault warning device 40 of the charging and swapping station and other devices. Figure 5 As shown, the fault warning device 40 of the charging and swapping station may further include a storage module 530 , which is used to store program codes and data of the fault warning device 40 of the charging and swapping station.

[0097] Among them, the processing module 520 can be a processor or controller, for example, a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an ASIC, an FPGA or other programmable logic device, a transistor logic device, a hardware component or any combination thereof. It can implement or execute the various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of the embodiments of the present application. The processor can also be a combination that implements computing functions, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like. The communication module 510 can be a transceiver, an RF circuit or a communication interface, etc. The storage module 530 can be a memory.

[0098] Among them, all relevant contents of each scenario involved in the above method embodiment can be referred to the functional description of the corresponding functional module, and will not be repeated here. The fault warning device 40 of the above charging and swapping station can execute the above Figure 2 The fault warning method of the charging and swapping station shown.

[0099] Figure 6 This is an example diagram of the composition of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 60 can be any one of the above-mentioned servers, charging and swapping stations or user equipment, which is used to perform the above-mentioned method. The electronic device 60 may include a processor 610, a memory 620, a communication interface 630 and one or more programs 621, wherein the processor 610, the memory 620 and the communication interface 630 are interconnected and complete the communication work between each other. The one or more programs 621 are stored in the above-mentioned memory 620 and are configured to be executed by the above-mentioned processor 610. The one or more programs 621 include instructions for executing any step in the above-mentioned method embodiment.

[0100] The communication interface 630 is used to support communication between the electronic device 60 and other devices. The processor 610 can be, for example, a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, units, and circuits described in conjunction with the disclosure of the embodiments of this application. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0101] Memory 620 may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. Nonvolatile memory may be read-only memory (ROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SynchLink DRAM, SLDRAM), and direct RAM bus random access memory (DRRAM).

[0102] In a specific implementation, the processor 610 is used to execute any step in the above method embodiment, and when performing data transmission such as sending, it can choose to call the communication interface 630 to complete the corresponding operation.

[0103] It should be noted that the structural diagram of the electronic device 60 is merely an example, and the specific components included may be more or less, and this is not a sole limitation.

[0104] The present application can divide the functional units of the electronic device according to the above method examples. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0105] An embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes a server.

[0106] The present application also provides a computer program product comprising a non-transitory computer-readable storage medium storing a computer program. The computer program is operable to cause a computer to execute some or all of the steps of any of the charging and swapping station fault warning methods described in the above method embodiments. The computer program product may be a software installation package.

[0107] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0108] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0109] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the above-mentioned units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0110] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0111] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0112] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the existing technology, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the above-mentioned methods in each embodiment of the present application. The aforementioned memory includes: USB flash drives, read-only memories (ROM), random access memories (RAM), mobile hard drives, magnetic disks, or optical disks, and other media that can store program code.

[0113] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, ROM, RAM, a magnetic disk or an optical disk, etc.

[0114] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein 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 and core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there may 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.

Claims

1. A fault warning method for a charging and swapping station, characterized in that: A server is applied to a fault warning system, the fault warning system including the server, the charging and swapping station, and a user device, the charging and swapping station and the user device are respectively communicatively connected to the server, the charging and swapping station includes multiple battery compartments, the circuit system of each battery compartment includes a signal branch, a charging branch, and a control branch, the signal branch, the charging branch, and the control branch are all configured with an intelligent fuse, the intelligent fuse is used to collect sensory information corresponding to the monitored branch, the sensory information including current, temperature, and voltage; the method includes: Obtaining first sensing information collected and reported by a first smart fuse, where the first smart fuse is a smart fuse configured for any branch of a first battery compartment, and the first battery compartment is any one of the multiple battery compartments; Inputting the first sensed information into a pre-trained normal state model to obtain a predicted value, where the predicted value includes at least one of a predicted current, a predicted voltage, or a predicted temperature; determining an absolute value of a difference between the first perception information and the predicted value to obtain an absolute deviation value; Determine the ratio of the absolute deviation value to the predicted value to obtain a relative deviation value; determining an absolute value of a difference between a rate of change of the first perception information and a rate of change of the predicted value to obtain a rate of change deviation value; Obtaining a working stage of the branch monitored by the first smart fuse, where the working stage includes an early charging stage, a mid-charging stage, and a late charging stage; Obtaining a weight ratio according to a working phase of the branch monitored by the first smart fuse; Performing a weighted summation of the absolute deviation value, the relative deviation value, and the change rate deviation value according to the weight ratio to obtain a data deviation value, wherein the data deviation value is used to represent a degree of deviation between the first perception information and the predicted value; Obtaining an abnormal threshold of a branch monitored by the first intelligent fuse; Comparing the data deviation value with the abnormality threshold to obtain a comparison result; Determine the working state of the branch monitored by the first intelligent fuse according to the comparison result, where the working state includes a normal state and an abnormal state; When the working state is an abnormal state, the first sensing information is input into a pre-trained fault type recognition model to obtain an abnormality type; When the working state is an abnormal state, the position information corresponding to the first smart fuse of the current branch is retrieved, and the position information is determined as an abnormal area, where the abnormal area is used to indicate the position of the branch monitored by the first smart fuse; Sending warning information to the user equipment, where the warning information includes the abnormality type and the abnormal area.

2. The method according to claim 1, wherein The obtaining of an abnormal threshold of a branch monitored by the first smart fuse includes: Acquire historical data of the first battery compartment; Extracting data collected in a sub-period within a preset period that is the same as the sub-period for collecting the first perception information from the historical data to obtain historical perception data; wherein the preset period includes a plurality of unit periods, and a single unit period includes a plurality of unit sub-periods; Classifying the historical perception data according to the working stage to obtain classified historical perception data; Determining thresholds corresponding to respective working stages according to the classified historical perception data; A threshold corresponding to a working phase that is the same as the working phase of the branch monitored by the first smart fuse is determined as the abnormal threshold.

3. The method according to claim 1, wherein The normal state model is determined according to the following method: Obtain a first initial model and a training data set; Acquire second data of the first battery compartment, where the second data includes at least one of a usage history of the first battery compartment, a battery type, and environmental information; adjusting the model parameters of the first initial model according to the second data to obtain a second initial model; The second initial model is trained according to the training data set to obtain the normal state model.

4. The method according to claim 1, wherein When the working state is an abnormal state, inputting the first perception information into a pre-trained fault type recognition model to obtain the abnormality type includes: Acquire a fault database, where the fault database is established based on historical fault data and includes features of multiple fault types and corresponding sensing information; Inputting the first perception information into a pre-trained fault type recognition model to obtain a first feature of the first perception information; Matching the first feature with the fault database to obtain a matching result; The abnormality type is determined according to the matching result.

5. A fault warning device for a charging and swapping station, characterized in that: A server used in a fault warning system, the fault warning system including the server, the charging and swapping station, and a user device, the charging and swapping station and the user device being respectively communicatively connected to the server, the charging and swapping station including multiple battery compartments, the circuit system of a single battery compartment including a signal branch, a charging branch, and a control branch, the signal branch, the charging branch, and the control branch being each configured with an intelligent fuse, the intelligent fuse being used to collect sensory information corresponding to the monitored branch, the sensory information including current, temperature, and voltage; the fault warning device of the charging and swapping station including: an acquiring unit, configured to acquire first sensing information collected and reported by a first smart fuse, where the first smart fuse is a smart fuse configured for any branch of a first battery compartment, and the first battery compartment is any one of the multiple battery compartments; a determination unit, configured to input the first perception information into a pre-trained normal state model to obtain a predicted value, wherein the predicted value includes at least one of a predicted current, a predicted voltage, or a predicted temperature; determine the absolute value of the difference between the first perception information and the predicted value to obtain an absolute deviation value; determine the ratio of the absolute deviation value to the predicted value to obtain a relative deviation value; determine the absolute value of the difference between the rate of change of the first perception information and the rate of change of the predicted value to obtain a rate of change deviation value; obtain the working stage of the branch monitored by the first intelligent fuse, wherein the working stage includes the early charging stage, the middle charging stage, and the and late charging; obtaining a weight ratio according to the working stage of the branch monitored by the first smart fuse; performing weighted summation on the absolute deviation value, the relative deviation value, and the change rate deviation value according to the weight ratio to obtain a data deviation value, wherein the data deviation value is used to characterize the degree of deviation between the first perception information and the predicted value; obtaining an abnormality threshold value of the branch monitored by the first smart fuse; comparing the data deviation value with the abnormality threshold value to obtain a comparison result; determining the working state of the branch monitored by the first smart fuse according to the comparison result, wherein the working state includes a normal state and an abnormal state; An early warning unit is configured to input the first perception information into a pre-trained fault type recognition model to obtain an abnormal type when the working state is an abnormal state; and when the working state is an abnormal state, retrieve the position information corresponding to the first smart fuse of the current branch, and determine the position information as an abnormal area, wherein the abnormal area is used to indicate the position of the branch monitored by the first smart fuse; and send early warning information to the user device, wherein the early warning information includes the abnormal type and the abnormal area.

6. An electronic device, characterized in that: The method comprises a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that A computer program for electronic data exchange is stored, wherein the computer program enables a computer to execute the steps of the method according to any one of claims 1 to 4.

Images