Fusing event prediction method and device, server, medium and vehicle

Abstract

The invention relates to a fusing event prediction method and device, a server, a medium and a vehicle. The fusing event prediction method comprises the steps of obtaining original data of a target vehicle in a target time period, and performing feature extraction processing on the original data to obtain target feature data; inputting the target feature data into a trained fusing prediction model to obtain a fusing prediction probability output by the fusing prediction model; and if the fusing prediction probability meets a preset probability condition, predicting that the fuse of the target vehicle is subjected to a fusing event. According to the embodiment of the invention, the method can accurately predict the fusing event of the fuse, and guarantees the safety of a vehicle during driving.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a method, device, server, medium and vehicle for predicting a fuse event. Background Art

[0002] In recent years, with the rapid development of new energy vehicles, people have higher requirements for the intelligence and safety of vehicles. The development trend of automobile intelligence, networking and electrification is becoming increasingly significant, and the market size of new energy electric vehicles is gradually increasing. For new energy vehicles, the safety and troubleshooting of the entire vehicle circuit is of paramount importance. Among them, fuses are indispensable for each power module.

[0003] In the related technology, for fuses, it is necessary to calculate the melting time based on the fatigue damage, creep damage, and physical properties of the fuses, such as the state of grains, grain boundaries, and atomic loss, and then issue an early warning. However, this method is greatly restricted by experimental conditions, and it is difficult to accurately predict the melting time of the fuse, and the safety of driving cannot be guaranteed. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a method, device, server, medium and vehicle for predicting a fuse event.

[0005] In a first aspect, the present disclosure provides a method for predicting a fuse event, comprising:

[0006] Obtain the original data of the target vehicle within the target time period;

[0007] Perform feature extraction on the original data to obtain target feature data;

[0008] Input the target feature data into the trained circuit breaker prediction model to obtain the circuit breaker prediction probability output by the circuit breaker prediction model;

[0009] If the predicted probability of the fuse blowing meets the preset probability condition, it is predicted that the fuse of the target vehicle will blow.

[0010] In a second aspect, the present disclosure provides a device for predicting a fuse event, comprising:

[0011] A first acquisition module is used to acquire raw data of a target vehicle within a target time period;

[0012] The first processing module is used to perform feature extraction processing on the original data to obtain target feature data;

[0013] The second processing module is used to input the target feature data into the trained fuse prediction model to obtain the fuse prediction probability output by the fuse prediction model;

[0014] The blown fuse prediction module is used to predict a blown fuse event of the target vehicle if the blown fuse prediction probability meets a preset probability condition.

[0015] In a third aspect, the present disclosure provides a server, including:

[0016] processor;

[0017] A memory for storing executable instructions;

[0018] The processor is used to read executable instructions from the memory and execute the executable instructions to implement the fuse event prediction method of the first aspect.

[0019] In a fourth aspect, the present disclosure provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements the method for predicting a fuse event in the first aspect.

[0020] In a fifth aspect, the present disclosure provides a vehicle, comprising the above-mentioned fuse event prediction device.

[0021] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0022] The method, device, server, medium and vehicle for predicting a blown fuse event of the disclosed embodiments can obtain the original data of the target vehicle within the target time period, and perform feature extraction processing on the original data to obtain target feature data, and then input the target feature data into a trained blown fuse prediction model to obtain a blown fuse prediction probability output by the blown fuse prediction model. If the blown fuse prediction probability satisfies a preset probability condition, then a blown fuse event is predicted to occur in the target vehicle. Thus, feature extraction processing can be performed on the original data to obtain the target feature data, and blown fuse prediction processing can be performed on the target feature data to obtain a blown fuse prediction probability. Finally, when the blown fuse prediction probability satisfies the preset probability condition, a blown fuse event is predicted to occur in the target vehicle, thereby accurately predicting a blown fuse event to ensure the safety of the vehicle while driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0024] Figure 1 A schematic diagram of a flow chart of a method for predicting a fuse event provided in an embodiment of the present disclosure;

[0025] Figure 2 A schematic diagram of the structure of a device for predicting a fuse event provided in an embodiment of the present disclosure;

[0026] Figure 3 A schematic diagram of the structure of a server provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0027] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0028] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0029] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0030] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0031] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0032] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0033] In order to solve the above problems, the embodiments of the present disclosure provide a method, device, server, medium and vehicle for predicting a fuse event. Figure 1 The method for predicting a fuse event provided by an embodiment of the present disclosure is described in detail.

[0034] Figure 1 A flow chart of a method for predicting a fuse event provided in an embodiment of the present disclosure is shown.

[0035] In the embodiment of the present disclosure, the fuse event prediction method may be executed by a server. Specifically, the server may include but is not limited to a cloud server or a cloud server cluster.

[0036] like Figure 1 As shown, the fuse event prediction method may include the following steps.

[0037] S110: Acquire original data of the target vehicle within a target time period.

[0038] In the disclosed embodiment, the server may obtain raw data of the target vehicle within a target time period.

[0039] Optionally, the target vehicle may be a moving vehicle.

[0040] Optionally, the target time period may be a pre-set time period. For example, the target time period may be set in units of seconds, minutes, days, months, years, etc., such as within 10 seconds, within a day, within a month, etc., which is not limited here.

[0041] Optionally, the raw data may be various data of the target vehicle, for example, the raw data may include battery current data, battery temperature data, fuse temperature data, fuse internal resistance data, battery life data, vehicle mileage data, etc., which are not limited here.

[0042] Specifically, when the target vehicle is driving, the vehicle motion domain controller (XCU) can collect the original data of the target vehicle and upload it to the server's database for storage via the HU. The server can search and obtain the original data of the target vehicle within the target time period in the database.

[0043] S120, performing feature extraction processing on the original data to obtain target feature data.

[0044] In the disclosed embodiment, after obtaining the original data, the server may perform feature extraction processing on the original data to obtain target feature data.

[0045] Optionally, the feature extraction process may be a process for extracting required feature data from the data. For example, the feature extraction process may be a process for extracting time-based target feature data from the data.

[0046] Optionally, the target feature data may be data with specific features. For example, the target feature data may include short-time scale feature data, long-time scale feature data, and full-life cycle statistical feature data, etc., which are not limited here.

[0047] Specifically, after obtaining the original data, the server may perform feature extraction processing on the original data, that is, extract required feature data from the original data to obtain target feature data.

[0048] Optionally, after obtaining the raw data, the server may preprocess the raw data, such as performing deduplication processing, denoising processing, etc., and then perform feature extraction processing on the preprocessed raw data.

[0049] S130. Input the target feature data into the trained fuse prediction model to obtain the fuse prediction probability output by the fuse prediction model.

[0050] In the disclosed embodiment, after obtaining the target feature data, the server may input the target feature data into a trained fuse prediction model to obtain the fuse prediction probability output by the fuse prediction model.

[0051] Optionally, the trained fuse prediction model may be a pre-trained machine learning model for performing fuse prediction processing. For example, the trained fuse prediction model may be a binary classification model.

[0052] Optionally, the blown fuse prediction process may be a process of predicting the probability of a fuse blowing.

[0053] Optionally, the predicted probability of a blown fuse may be used to characterize the probability of a blown fuse. For example, the predicted probability of a blown fuse may be expressed in the form of a percentage, a fraction, etc., such as 60%, 3 / 4, etc., which is not limited here.

[0054] Specifically, after obtaining the target feature data, the server can input the target feature data into a trained fuse prediction model. The trained fuse prediction model can perform fuse prediction processing on the input target feature data, thereby outputting a corresponding fuse prediction probability, and the server can obtain the fuse prediction probability.

[0055] S140: If the predicted probability of the fuse blowing meets the preset probability condition, it is predicted that the fuse of the target vehicle will blow.

[0056] In the disclosed embodiment, after obtaining the predicted probability of the fuse being blown, if the predicted probability of the fuse being blown satisfies a preset probability condition, the server predicts that a fuse blown event will occur in the target vehicle's fuse.

[0057] Optionally, the preset probability condition may be a predefined probability condition.

[0058] Optionally, the fuse can be used for overload protection. For example, when the current rises to a certain height and temperature, the fuse will melt and cut off the current, thus protecting the safe operation of the circuit.

[0059] Specifically, after obtaining the predicted probability of the fuse, the server can judge the predicted probability of the fuse, and if the predicted probability of the fuse meets the preset probability condition, it can be determined that the fuse of the target vehicle is about to have a fuse blown event. The specific judgment method is described below.

[0060] Therefore, in the disclosed embodiment, the original data of the target vehicle within the target time period can be obtained, and the original data can be subjected to feature extraction processing to obtain target feature data, and then the target feature data is input into the trained fuse prediction model to obtain the fuse prediction probability output by the fuse prediction model. If the fuse prediction probability meets the preset probability condition, it is predicted that the fuse of the target vehicle will have a fuse blown event. Therefore, the original data can be subjected to feature extraction processing to obtain the target feature data, and the target feature data can be subjected to fuse prediction processing to obtain the fuse prediction probability. Finally, when the fuse prediction probability meets the preset probability condition, it is predicted that the fuse of the target vehicle will have a fuse blown event, thereby accurately predicting the fuse blown event and ensuring the safety of the vehicle while driving.

[0061] In some embodiments, the target characteristic data may include short time scale characteristic data.

[0062] Optionally, the short-time scale characteristic data may be characteristic data obtained with a short time as the scale.

[0063] Optionally, S120 may specifically include: based on a preset current threshold, counting the number of overcurrent times of the original data within a first preset time; adding a current weighting coefficient to the overcurrent times information to obtain short-time scale characteristic data.

[0064] In the embodiment of the present disclosure, the server may count the number of overcurrent times of the original data within a first preset time based on a preset current threshold.

[0065] Optionally, the preset current threshold may be a pre-set current threshold. For example, the preset current threshold is set according to different fuse models, such as the preset current threshold may be 5A, 6A, etc., which is not limited here.

[0066] Optionally, the first preset time may be a preset time, for example, the first preset time may be 1 day, 2 days, etc., which is not limited here.

[0067] Optionally, the overcurrent count information may be used to indicate the number of times the current exceeds a preset current threshold.

[0068] Specifically, after obtaining the original data, the server can count the number of times the current exceeds the preset current threshold within a first preset time in the original data, such as 1 day, to obtain overcurrent information, and set a time step, such as counting the overcurrent information within a week.

[0069] Furthermore, the server may add a current weighting coefficient to the overcurrent number information to obtain short-time scale characteristic data.

[0070] Optionally, the current weighting coefficient may be a coefficient used to characterize the weight of the current.

[0071] Specifically, the server can add a current weighting coefficient to the overcurrent count information to obtain short-time scale characteristic data. Since the current data changes frequently and the sampling frequency is generally in units of 10ms or 100ms, adding a current weighting coefficient to the current that changes dramatically can improve the effectiveness of the overcurrent count information.

[0072] In other embodiments, the target characteristic data may also include long time scale characteristic data.

[0073] Optionally, the long-time scale characteristic data may be characteristic data obtained with a long time as a scale.

[0074] Optionally, S120 may specifically include: counting the heat generation calculated value of the original data within the second preset time; based on a preset temperature threshold, counting the heat generation calculated value and the step overtemperature information within the second preset time to obtain long-time scale characteristic data.

[0075] In the embodiment of the present disclosure, the server may count the sum of the heat generation calculation values ​​of the original data within the second preset time.

[0076] Optionally, the second preset time may be a pre-set time, such as one month, one year, etc., which is not limited here.

[0077] Optionally, the sum of the heat generation calculation values ​​may be the sum of the heat generation calculation values ​​of the fuse within the second preset time.

[0078] Specifically, since the main reason for the blowing of the fuse is the excessive heat generation of the device, and the effect of excessive heat generation has a cumulative effect, the server can count the sum of the heat generation calculation values ​​of the original data within the second preset time. For example, the server can count the sum of the heat generation calculation values ​​of multiple fuses within one month. The heat generation calculation value can be the square of the current within 10s * power-on time * theoretical internal resistance * life coefficient, so as to obtain the corresponding heat generation calculation value.

[0079] Furthermore, after obtaining the heat generation calculation value and, based on a preset temperature threshold, the server can statistically calculate the heat generation calculation value and the step over-temperature information within a second preset time to obtain long-time scale characteristic data.

[0080] Optionally, the preset temperature threshold may be a pre-set temperature threshold, for example, the preset temperature threshold may be 80°, 90°, etc., which is not limited here.

[0081] Optionally, the step over-temperature information may be information used to indicate that the temperature exceeds a preset temperature threshold.

[0082] Specifically, the server can set preset temperature thresholds for different stages, compare the obtained heat production calculation value with the preset temperature threshold, and count the corresponding step over-temperature information within the second preset time. For example, if the heat production calculation value is greater than the preset temperature threshold of the first stage, the corresponding first-level step over-temperature information is obtained, and all step over-temperature information within one month is counted to obtain long-time scale characteristic data.

[0083] In some other embodiments, the target characteristic data may also include full life cycle statistical characteristic data.

[0084] Optionally, the full life cycle statistical feature data may be statistical feature data over the full life cycle.

[0085] Optionally, the full life cycle statistical characteristic data may include battery life information and vehicle mileage information.

[0086] Optionally, the battery life information may be information used to characterize the battery life of the target vehicle. The vehicle mileage information may be information used to characterize the mileage of the target vehicle.

[0087] Specifically, the server can obtain the statistical characteristic data of the target vehicle's entire life cycle in the database, including battery life information and vehicle mileage information. The battery life information and vehicle mileage information can be collected using the vehicle motion domain controller (XCU) of the target vehicle and uploaded to the server's database via the HU for storage.

[0088] Optionally, before inputting the target feature data into the trained fuse prediction model, the fuse event prediction method may also include: obtaining historical original data, and performing feature extraction processing on the historical original data to obtain historical feature data; labeling the historical feature data to obtain a training feature data set and a verification feature data set; based on the training feature data set and the verification feature data set, performing model training and model verification on the fuse prediction model to obtain a trained fuse prediction model.

[0089] In the disclosed embodiment, the server may obtain the historical raw data of the target vehicle, and perform feature extraction processing on the historical raw data to obtain historical feature data.

[0090] Optionally, the historical raw data may be various data of the target vehicle in the historical time. For example, the historical raw data may include battery current data, battery temperature data, fuse temperature data, fuse internal resistance data, battery life data, vehicle mileage data, etc., which are not limited here.

[0091] Optionally, the historical feature data may be historical data with specific features. For example, the historical feature data may include historical short-time scale feature data, historical long-time scale feature data, and historical full-life cycle statistical feature data, etc., which are not limited here.

[0092] Specifically, when the target vehicle is driving, the vehicle motion domain controller (XCU) can collect the historical raw data of the target vehicle and upload it to the server's database for storage via the HU. The server can search and obtain the historical raw data in the database, and then perform feature extraction processing on the historical raw data to obtain the corresponding historical feature data.

[0093] Furthermore, the server may label the historical feature data to obtain a training feature data set and a verification feature data set.

[0094] Optionally, the label marking may be marking different data with different labels.

[0095] Optionally, the training feature data set may be a feature data set for model training.

[0096] Optionally, the verification feature dataset may be a feature dataset for performing model verification.

[0097] Specifically, the server can label the historical feature data to obtain a training feature data set and a verification feature data set. For example, in order to achieve early warning of failures, the historical feature data obtained by the server can be data for at least two days before the circuit breaker, and the historical feature data on the day of the circuit breaker, the previous day, and the previous two days can be marked as positive samples, and the historical feature data from the previous three days and before can be marked as negative samples.

[0098] Furthermore, after obtaining the training feature data set and the verification feature data set, the server can perform model training and model verification on the fuse prediction model to obtain a trained fuse prediction model.

[0099] Specifically, after obtaining the training feature data set and the verification feature data set, the server can first oversample the training feature data set (Synthetic Minority Oversampling Technique, SMOTE), and then train the fuse prediction model through the oversampled training feature data set, adjust the model parameters according to the training results, and then verify the fuse prediction model through the verification feature data set, so as to obtain a trained fuse prediction model.

[0100] Optionally, S140 may specifically include: if the ranking of the predicted probability of the blown fuse is within a preset ranking range, and the predicted probability of the blown fuse is greater than or equal to a preset probability of the blown fuse corresponding to the preset ranking range, determining that the predicted probability of the blown fuse meets a preset probability condition.

[0101] In the embodiment of the present disclosure, after obtaining the fuse prediction probability, if the ranking of the fuse prediction probability is within a preset ranking range and the fuse prediction probability is greater than or equal to the preset fuse probability corresponding to the preset ranking range, the server determines that the fuse prediction probability meets the preset probability condition.

[0102] Optionally, the preset ranking range may be a predefined ranking range.

[0103] Optionally, the preset fuse probability can be a preset fuse probability corresponding to different preset ranking ranges. For example, there are 100 vehicles in a day, the top 10 vehicles are preset as the first preset ranking range, the top 11-30 vehicles are set as the second preset ranking range, the top 31-60 vehicles are set as the third preset ranking range, the top 61-100 vehicles are set as the fourth preset ranking range, etc., which are not limited here, and the first preset fuse probability corresponding to the first preset ranking range is set, and the preset fuse probability corresponding to each preset ranking range is set similarly.

[0104] For example, after obtaining the fuse prediction probability, the server can first determine the ranking of the fuse prediction probability among 100 vehicles in one day. If it is in the top 10, that is, the first preset ranking range, then determine whether the fuse prediction probability is greater than or equal to the first preset fuse probability corresponding to the first preset ranking range. For example, the fuse prediction probability can be 95%, and the first preset fuse probability can be 90%. At this time, the server can determine that the fuse prediction probability meets the preset probability condition, otherwise it does not meet the preset probability condition.

[0105] Therefore, only when the fuse prediction probability meets the preset probability conditions can the fuse of the target vehicle be predicted to have a blown event. Through double filtering and judgment, false alarms can be avoided, occasional vehicles with unstable probability output can be filtered out, and the accuracy of the prediction can be improved.

[0106] Optionally, after the server predicts that the fuse of the target vehicle has blown, the after-sales service can proactively recall the target vehicle and replace the fuse in advance. The replaced fuse can be X-rayed to determine whether it has melted severely based on internal testing. The test result should be used as a true label sample of the feature, which will be re-entered into the model training process to further improve the model coverage.

[0107] Figure 2 A schematic diagram of the structure of a fuse event prediction device provided by an embodiment of the present disclosure is shown.

[0108] In some embodiments of the present disclosure, Figure 2 The fuse event prediction device shown can be set in a server. Specifically, the server can include but is not limited to a cloud server or a cloud server cluster.

[0109] like Figure 2 As shown, the fuse event prediction device 200 may include a first acquisition module 210 , a first processing module 220 , a second processing module 230 and a fuse prediction module 240 .

[0110] The first acquisition module 210 can be used to acquire raw data of the target vehicle within a target time period.

[0111] The first processing module 220 can be used to perform feature extraction processing on the original data to obtain target feature data.

[0112] The second processing module 230 can be used to input the target feature data into the trained fuse prediction model to obtain the fuse prediction probability output by the fuse prediction model.

[0113] The blown fuse prediction module 240 may be used to predict a blown fuse event of the target vehicle if the blown fuse prediction probability satisfies a preset probability condition.

[0114] Therefore, in the disclosed embodiment, the original data of the target vehicle within the target time period can be obtained, and the original data can be subjected to feature extraction processing to obtain target feature data, and then the target feature data is input into the trained fuse prediction model to obtain the fuse prediction probability output by the fuse prediction model. If the fuse prediction probability meets the preset probability condition, it is predicted that the fuse of the target vehicle will have a fuse blown event. Therefore, the original data can be subjected to feature extraction processing to obtain the target feature data, and the target feature data can be subjected to fuse prediction processing to obtain the fuse prediction probability. Finally, when the fuse prediction probability meets the preset probability condition, it is predicted that the fuse of the target vehicle will have a fuse blown event, thereby accurately predicting the fuse blown event and ensuring the safety of the vehicle while driving.

[0115] In some embodiments of the present disclosure, the target characteristic data may include short-time scale characteristic data.

[0116] In some embodiments of the present disclosure, the first processing module 220 may include a first statistical unit and a current weighting unit.

[0117] The first statistical unit can be used to count the number of overcurrent times of the original data within a first preset time based on a preset current threshold.

[0118] The current weighting unit can be used to add a current weighting coefficient to the overcurrent number information to obtain short-time scale characteristic data.

[0119] In some embodiments of the present disclosure, target characteristic data may include long time scale characteristic data.

[0120] In some embodiments of the present disclosure, the first processing module 220 may include a second statistical unit and a third statistical unit.

[0121] The second statistical unit can be used to calculate the sum of the heat generation calculation values ​​of the original data within the second preset time.

[0122] The third statistical unit can be used to obtain long-time scale characteristic data by counting the heat generation calculation value and the step overtemperature information within the second preset time based on the preset temperature threshold.

[0123] In some embodiments of the present disclosure, the target characteristic data may include full life cycle statistical characteristic data, and the full life cycle statistical characteristic data may include battery life information and vehicle mileage information.

[0124] In some embodiments of the present disclosure, the fuse event prediction device 200 may further include a second acquisition module, a label marking module and a model training module.

[0125] The second acquisition module can be used to acquire historical original data and perform feature extraction processing on the historical original data to obtain historical feature data before inputting the target feature data into the trained fuse prediction model.

[0126] The labeling module can be used to label historical feature data to obtain a training feature data set and a verification feature data set.

[0127] The model training module can be used to perform model training and model verification on the fuse prediction model based on the training feature data set and the verification feature data set to obtain a trained fuse prediction model.

[0128] In some embodiments of the present disclosure, the fuse prediction module 240 can be specifically used to determine that the fuse prediction probability meets the preset probability condition if the ranking of the fuse prediction probability is within a preset ranking range and the fuse prediction probability is greater than or equal to the preset fuse probability corresponding to the preset ranking range.

[0129] It should be noted that Figure 2 The fuse event prediction device 200 shown can execute Figure 1 The various steps in the method embodiment shown in the figure are implemented Figure 1 The various processes and effects in the method embodiment shown are not described in detail here.

[0130] Figure 3 A schematic diagram of the structure of a server provided by an embodiment of the present disclosure is shown.

[0131] In some embodiments of the present disclosure, Figure 3 The server shown may be a server with a fuse event prediction function. Specifically, the server may include but is not limited to a cloud server or a cloud server cluster.

[0132] like Figure 3 As shown, the server may include a processor 301 and a memory 302 storing computer program instructions.

[0133] Specifically, the processor 301 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0134] The memory 302 may include a large capacity memory for information or instructions. By way of example and not limitation, the memory 302 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 302 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 302 may be inside or outside the integrated gateway device. In a particular embodiment, the memory 302 is a non-volatile solid-state memory. In a particular embodiment, the memory 302 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (Electrically Erasable Programmable ROM, EEPROM), an electrically rewritable ROM (EAROM) or a flash memory, or a combination of two or more of these.

[0135] The processor 301 reads and executes the computer program instructions stored in the memory 302 to perform the steps of the fuse event prediction method provided in the embodiment of the present disclosure.

[0136] In one example, the server may further include a transceiver 303 and a bus 304. Figure 3 As shown, the processor 301, the memory 302 and the transceiver 303 are connected via a bus 304 and communicate with each other.

[0137] The bus 304 includes hardware, software, or both. For example, but not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a Memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 304 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0138] The embodiments of the present disclosure further provide a computer-readable storage medium, which may store a computer program. When the computer program is executed by a processor, the processor implements the fuse event prediction method provided by the embodiments of the present disclosure.

[0139] The above-mentioned storage medium may, for example, include a memory 302 of computer program instructions, and the above-mentioned instructions may be executed by the processor 301 of the server to complete the fuse event prediction method provided in the embodiment of the present disclosure. Optionally, the storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a ROM, a random access memory (Random Access Memory, RAM), a compact disc read-only memory (Compact Disc ROM, CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0140] The present disclosure also provides a vehicle, which includes the above-mentioned fuse event prediction device. It is understandable that the vehicle may also include: a processor, a memory, and a computer program. The computer program is stored in the memory and is configured to be executed by the processor to implement the fuse event prediction method provided by the present disclosure. The processor and the memory are already in Figure 3 The parts described in the illustrated embodiment are not repeated here.

[0141] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0142] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting a fuse event, characterized in that: include: Obtain the original data of the target vehicle within the target time period; Performing feature extraction processing on the original data to obtain target feature data; Inputting the target feature data into a trained fuse prediction model to obtain a fuse prediction probability output by the fuse prediction model; If the predicted probability of the fuse blowing meets a preset probability condition, then a fuse blowing event is predicted for the target vehicle.

2. The method according to claim 1, characterized in that The target characteristic data includes short time scale characteristic data; The step of performing feature extraction processing on the original data to obtain target feature data includes: Based on a preset current threshold, counting the number of overcurrent times of the original data within a first preset time; A current weighting coefficient is added to the overcurrent number information to obtain the short-time scale characteristic data.

3. The method according to claim 1, characterized in that: The target characteristic data includes long time scale characteristic data; The step of performing feature extraction processing on the original data to obtain target feature data includes: Counting the sum of the heat generation calculation values ​​of the original data within the second preset time; Based on a preset temperature threshold, the heat generation calculation value and the step over-temperature information within the second preset time are counted to obtain the long-time scale characteristic data.

4. The method according to claim 1, characterized in that The target characteristic data includes full life cycle statistical characteristic data, and the full life cycle statistical characteristic data includes battery life information and vehicle mileage information.

5. The method according to claim 1, characterized in that Before inputting the target feature data into the trained fuse prediction model, the method further includes: Acquiring historical original data, and performing feature extraction processing on the historical original data to obtain historical feature data; Labeling the historical feature data to obtain a training feature data set and a verification feature data set; Based on the training feature data set and the verification feature data set, model training and model verification are performed on the fuse prediction model to obtain the trained fuse prediction model.

6. The method according to claim 1, characterized in that The predicted probability of the fuse meeting the preset probability condition includes: If the ranking of the fuse prediction probability is within a preset ranking range, and the fuse prediction probability is greater than or equal to a preset fuse probability corresponding to the preset ranking range, it is determined that the fuse prediction probability meets the preset probability condition.

7. A device for predicting a fuse event, characterized in that: include: A first acquisition module is used to acquire raw data of a target vehicle within a target time period; A first processing module is used to perform feature extraction processing on the original data to obtain target feature data; A second processing module is used to input the target feature data into a trained fuse prediction model to obtain a fuse prediction probability output by the fuse prediction model; The fuse prediction module is used to predict that the fuse of the target vehicle will have a fuse blown event if the fuse prediction probability meets a preset probability condition.

8. A server, characterized in that: include: processor; A memory for storing executable instructions; The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the fuse event prediction method described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the method for predicting a fuse event according to any one of claims 1 to 6.

10. A vehicle, characterized in that: It includes the fuse event prediction device as described in any one of Claims 7 or the server as described in Claim 8 or the computer-readable storage medium as described in Claim 9.

Images