Vehicle battery abnormality processing, abnormality information determination method, processing system, and medium

Abstract

The present disclosure relates to the field of battery, in particular, to a vehicle battery abnormality processing method, an abnormality information determination method, a processing system and a medium. The method comprises: obtaining abnormality information of a battery, wherein the abnormality information comprises alarm information indicating that the battery currently has an abnormality, and / or early warning information indicating that the battery will have an abnormality in the future; and determining an abnormality processing strategy according to the number of vehicles in a consist and the abnormality information. In this way, when it is determined that the battery of the vehicle currently or in the future has an abnormality, a processing strategy that is adapted to the actual state of the vehicle can be determined in combination with the number of vehicles in the consist, so that the battery on the train is maintained and serviced in time more accurately, and the operation safety of the vehicle is improved.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of battery, in particular, to a vehicle battery abnormality processing method, an abnormality information determination method, a processing system and a medium. BACKGROUND

[0002] With the continuous development of new energy technology, power batteries begin to be applied to urban rail trains, so that the power batteries are directly used to provide power for the trains, reducing the cost of track construction. The state of the power battery affects the operation efficiency and running safety of the train, so higher requirements are put forward for the timely maintenance, maintenance and early fault prediction of the train power battery. At present, in order to ensure the safety of train operation, the train is directly controlled to stop when it is determined that the battery on the train is abnormal, which may cause unnecessary stop and it is difficult to quickly determine a processing strategy that can adapt to the actual state of the vehicle. SUMMARY

[0003] The purpose of the present disclosure is to provide a vehicle battery abnormality processing method, an abnormality information determination method, a processing system and a medium, which can determine a processing strategy that can adapt to the actual state of the vehicle in combination with the number of vehicle marshalling.

[0004] In order to achieve the above purpose, the first aspect of the present disclosure provides a vehicle battery abnormality processing method, comprising:

[0005] Obtaining abnormality information of the battery, wherein the abnormality information includes alarm information indicating that the battery currently has an abnormality, and / or early warning information indicating that the battery will have an abnormality in the future;

[0006] Determining an abnormality processing strategy according to the number of vehicle marshalling and the abnormality information.

[0007] The second aspect of the present disclosure provides a vehicle battery abnormality information determination method, comprising:

[0008] Determining the predicted capacity of the battery through a battery capacity prediction model that has been pre-trained, wherein the battery capacity prediction model is obtained based on a tentacle search algorithm optimization;

[0009] Generating abnormality information of the battery according to the real-time capacity and the predicted capacity, wherein the abnormality information is used to implement the steps of the vehicle battery abnormality processing method provided in the first aspect of the present disclosure.

[0010] The third aspect of the present disclosure provides a vehicle battery abnormality processing system, comprising:

[0011] An intelligent operation and maintenance platform for implementing the steps of the vehicle battery abnormality information determination method provided in the second aspect of the present disclosure.

[0012] The vehicle dispatching system is used to implement the steps of the vehicle battery abnormality processing method provided in the first aspect of the present disclosure.

[0013] The fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium, which stores a computer program. When the program is executed by a processor, the steps of the method provided in the first aspect or the second aspect of the present disclosure are implemented.

[0014] In the above technical solution, the abnormal information of the battery is acquired, wherein the abnormal information includes alarm information indicating that the battery currently has an abnormality, and / or early warning information indicating that the battery will have an abnormality in the future; and the abnormality processing strategy is determined according to the grouping number of the vehicle and the abnormal information. In this way, when it is determined that the battery of the vehicle currently has or will have an abnormality, the processing strategy that is suitable for the actual state of the vehicle can be quickly determined in combination with the grouping number of the vehicle, so that the battery on the train is more accurately and timely maintained, and the operation safety of the vehicle is improved.

[0015] Other features and advantages of the present disclosure will be described in detail in the following specific embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0016] The accompanying drawings are included to provide a further understanding of the present disclosure and constitute a part of the specification, and are used together with the following specific embodiments to explain the present disclosure, but do not constitute a limitation on the present disclosure. In the drawings:

[0017] Figure 1 is a flowchart of a vehicle battery abnormality processing method provided by an exemplary embodiment of the present disclosure.

[0018] Figure 2 is a flowchart of a vehicle battery abnormality processing method provided by an exemplary embodiment of the present disclosure.

[0019] Figure 3 is a flowchart of a vehicle battery abnormality information determination method provided by an exemplary embodiment of the present disclosure.

[0020] Figure 4 is a block diagram of a vehicle battery abnormality processing system provided by an exemplary embodiment of the present disclosure.

[0021] Figure 5 is a flowchart of a vehicle battery abnormality information determination method provided by an exemplary embodiment of the present disclosure.

[0022] Figure 6 is a block diagram of a vehicle battery abnormality processing device provided by an exemplary embodiment of the present disclosure.

[0023] Figure 7 is a block diagram of a vehicle battery abnormality information determination device provided by an exemplary embodiment of the present disclosure.

[0024] Figure 8 is a block diagram of an electronic device provided by an example embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] The specific embodiments of the present disclosure are described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended to illustrate and explain the present disclosure, and are not intended to limit the present disclosure.

[0026] Figure 1 is a flowchart of a vehicle battery abnormality processing method provided by an example embodiment of the present disclosure. The method can be applied to an automatic train scheduling system (ATS). As shown in Figure 1 , the method can include S101 and S102.

[0027] S101, obtaining abnormality information of a battery, wherein the abnormality information includes alarm information indicating that the battery currently has an abnormality, and / or early warning information indicating that the battery will have an abnormality in the future.

[0028] For example, the battery can be a power battery of any car of a train. The abnormality information of the battery can be uploaded by an intelligent operation and maintenance platform, or uploaded by other devices capable of determining the abnormality information of the battery, which is not limited here.

[0029] The alarm information indicating that the battery currently has an abnormality can include capacity alarm information indicating that the real-time capacity of the battery is abnormal, and / or decay rate alarm information indicating that the real-time capacity decay rate of the battery is abnormal; the early warning information indicating that the battery will have an abnormality in the future can include capacity early warning information indicating that the predicted capacity of the battery is abnormal, and / or decay rate early warning information indicating that the predicted capacity decay rate of the battery is abnormal. For example, the capacity alarm information can represent that the real-time capacity of the battery is less than a capacity threshold; the capacity early warning information can represent that the predicted capacity of the battery is less than the capacity threshold; the decay rate alarm information can represent that the real-time decay rate is greater than a decay rate threshold; and the decay rate early warning information can represent that the predicted decay rate is greater than the decay rate threshold. The capacity threshold and the decay rate threshold can be pre-set based on actual needs. If the abnormality information of the battery is obtained, it can be determined that the battery currently or in the future has an abnormality. In order to ensure the operation safety of the vehicle, the corresponding abnormality processing strategy can be taken in combination with the marshalling number of the vehicle.

[0030] S102, determining an abnormality processing strategy according to the marshalling number of the vehicle and the abnormality information.

[0031] For example, if the vehicle is a single-formation vehicle, the running state of a single car does not affect other cars in the same formation; if the vehicle is a multi-formation vehicle, the running state of a single car can affect other cars in the same formation, and the cars in the same formation can provide electric energy to each other, for example, if the power battery of the second car is abnormal, the power batteries of the first car and the third car can temporarily provide running energy. Therefore, according to the number of formations of the vehicle, different abnormal handling strategies that can adapt to the actual running state of the vehicle can be provided for single-formation vehicles and multi-formation vehicles.

[0032] For example, when the vehicle is a single-formation vehicle and the abnormal information is alarm information indicating that the battery currently has an abnormality, the vehicle can be controlled to stop running to ensure the safety of the vehicle. For another example, when the vehicle is a single-formation vehicle and the abnormal information is early warning information indicating that the battery will have an abnormality in the future, the vehicle operation strategy can be adjusted to reduce the planned mileage of the vehicle to reduce the possibility of the vehicle having an abnormality in subsequent operation, so that the vehicle can complete the operation plan before the abnormality occurs. For another example, when the vehicle is a multi-formation vehicle and the abnormal information is alarm information indicating that the battery currently has an abnormality, if the distance to the next station is less than a distance threshold, the vehicle can be stopped from going online when it arrives at the next station to minimize the impact on passengers in the vehicle; if the distance to the next station is not less than the distance threshold, the vehicle can be directly stopped from going online. For another example, when the vehicle is a multi-formation vehicle and the abnormal information is early warning information indicating that the battery will have an abnormality in the future, the vehicle can be marked and the vehicle operation strategy can be adjusted to reduce the planned mileage of the vehicle to reduce the possibility of the vehicle having an abnormality in subsequent operation, so that the vehicle can complete the operation plan before the abnormality occurs.

[0033] In the above technical solution, the abnormal information of the battery is obtained, wherein the abnormal information includes alarm information indicating that the battery currently has an abnormality and / or early warning information indicating that the battery will have an abnormality in the future; and the abnormal handling strategy is determined according to the number of formations of the vehicle and the abnormal information. In this way, when it is determined that the battery of the vehicle currently has an abnormality or will have an abnormality in the future, a handling strategy that can adapt to the actual state of the vehicle can be quickly determined in combination with the number of formations of the vehicle, so that the battery on the train can be more accurately and timely maintained, and the operation safety of the vehicle is improved.

[0034] In an optional embodiment, the vehicle battery abnormal handling method provided by the present disclosure can further include:

[0035] When the information indicating the abnormality of the capacity attenuation rate is received, the received information is displayed.

[0036] For example, receiving the information indicating the abnormality of the capacity attenuation rate is receiving the attenuation rate alarm information and / or the attenuation rate early warning information. When the information indicating the abnormality of the capacity attenuation rate is received, it can be determined that the battery has an abnormal attenuation rate or is extremely likely to have an abnormal attenuation rate at a future time. The abnormality of the attenuation rate is relatively complex to troubleshoot. To ensure the accuracy of troubleshooting and maintenance, the received information indicating the abnormality of the capacity attenuation rate can be displayed on the display screen of the vehicle dispatching system ATS, so as to timely remind the relevant personnel to troubleshoot the factors that may cause the battery capacity attenuation rate to be too fast, and propose a solution, thereby ensuring the subsequent operation safety of the vehicle.

[0037] In an optional embodiment, in S102, the abnormality processing strategy is determined according to the number of vehicle groupings and the abnormality information, which can include:

[0038] When the information indicating the abnormality of the capacity size is received and the information indicating the abnormality of the capacity attenuation rate is not received, the abnormality processing strategy is determined according to the number of groupings and the information indicating the abnormality of the capacity size.

[0039] For example, receiving the information indicating the abnormality of the capacity size is receiving the capacity alarm information and / or the capacity early warning information; and not receiving the information indicating the abnormality of the capacity attenuation rate is not receiving the attenuation rate alarm information or the attenuation rate early warning information.

[0040] If the information indicating the abnormality of the capacity size is received and the information indicating the abnormality of the capacity attenuation rate is not received, it can be determined that the battery has no abnormal attenuation rate, and the abnormality of the battery is related to the size of the battery capacity. At this time, the abnormality processing strategy can be determined according to the number of groupings and the information indicating the abnormality of the capacity size.

[0041] In an optional embodiment, when the information indicating the abnormality of the capacity size is received and the information indicating the abnormality of the capacity attenuation rate is not received, the abnormality processing strategy is determined according to the number of groupings and the information indicating the abnormality of the capacity size, which can include:

[0042] When the information indicating the abnormality of the capacity size is received and the information indicating the abnormality of the capacity attenuation rate is not received, if the vehicle is a single grouping vehicle and the received information is the capacity alarm information, the vehicle is controlled to stop operation, and a dispatching and maintenance request is generated.

[0043] For example, the vehicle is a single-unit vehicle, and there is no other vehicle compartment that can affect the running state of the vehicle compartment where the abnormal battery is located; the received information is the capacity warning information, and it can be determined that the battery has an abnormality related to the capacity size, and the abnormality may directly affect the current operation safety of the vehicle. Therefore, in order to ensure the operation safety of the vehicle, the vehicle can be controlled to stop operation, and a dispatch repair request can be generated. In this way, while the vehicle is stopped from online operation, relevant personnel can timely dispatch other vehicles to replace the abnormal vehicle for operation based on the dispatch repair request, and timely arrange to repair the battery of the vehicle to solve the abnormality of the battery as soon as possible. Further, the battery processing suggestion such as replacing the battery pack can also be generated at the same time as the dispatch repair request is generated.

[0044] In an optional embodiment, when the information indicating the capacity size abnormality is received and the information indicating the capacity decay rate abnormality is not received, the abnormality processing strategy is determined according to the number of units and the information indicating the capacity size abnormality, which can include:

[0045] When the information indicating the capacity size abnormality is received and the information indicating the capacity decay rate abnormality is not received, if the vehicle is a single-unit vehicle and the received information is the capacity warning information, the abnormality processing strategy is determined according to the predicted capacity decay rate and the first capacity decay rate threshold.

[0046] For example, the vehicle is a single-unit vehicle, and there is no other vehicle compartment that can affect the running state of the vehicle compartment where the abnormal battery is located; the received information is the capacity warning information, and it can be determined that the battery has an abnormality related to the capacity size, and the abnormality may directly affect the current operation safety of the vehicle. Therefore, in order to ensure the operation safety of the vehicle, the vehicle can be controlled to stop operation, and a dispatch repair request can be generated. In this way, while the vehicle is stopped from online operation, relevant personnel can timely dispatch other vehicles to replace the abnormal vehicle for operation based on the dispatch repair request, and timely arrange to repair the battery of the vehicle to solve the abnormality of the battery as soon as possible. Further, the battery processing suggestion such as replacing the battery pack can also be generated at the same time as the dispatch repair request is generated.

[0047] Optionally, the abnormality processing strategy is determined according to the predicted capacity decay rate and the first capacity decay rate threshold, which can include:

[0048] If the predicted capacity decay rate is greater than the first capacity decay rate threshold, a battery capacity recalibration request is generated; or,

[0049] If the predicted capacity decay rate is less than or equal to the first capacity decay rate threshold, a vehicle operation strategy adjustment request is generated.

[0050] For example, the first capacity decay rate threshold can be set to 10%. The predicted capacity decay rate can be determined based on the predicted capacity. If the predicted capacity decay rate is greater than the first capacity decay rate threshold, it can be determined that the accuracy of the predicted capacity may be insufficient, and the received information is capacity warning information, that is, the battery has not yet had any abnormalities related to the capacity size at the current moment. Therefore, a request to recalibrate the battery capacity can be generated to re-determine the real-time capacity and predicted capacity of the battery, thereby ensuring the reliability of the subsequent abnormality handling strategy. Among them, the request to recalibrate the battery capacity can be sent by the vehicle dispatch system ATS to the intelligent operation and maintenance platform, so that the intelligent operation and maintenance platform can recalibrate the battery capacity.

[0051] If the predicted capacity decay rate is less than or equal to the first capacity decay rate threshold, it can be determined that the predicted capacity is highly accurate and the received information is capacity warning information, meaning that the battery has not yet experienced any abnormality related to capacity size at the current moment. A vehicle operation strategy adjustment request can be generated at this time to reduce the possibility of abnormalities occurring in the subsequent operation of the vehicle and enable the vehicle to complete its operation plan before the abnormality occurs. For example, the possibility of abnormalities occurring in the subsequent operation of the vehicle can be reduced by reducing the mileage of the vehicle's planned operation. In addition, the vehicle operation strategy adjustment request may include information indicating the predicted capacity decay rate and the first capacity decay rate threshold to facilitate relevant personnel in adjusting the vehicle's operation strategy.

[0052] In an optional embodiment, when information indicating a capacity size abnormality is received and information indicating a capacity decay rate abnormality is not received, determining an abnormality handling strategy based on the number of trains and the information indicating a capacity size abnormality may include:

[0053] When receiving information indicating abnormal capacity size and not receiving information indicating abnormal capacity decay rate, if the vehicle is a multi-unit vehicle and the received information is a capacity alarm information, determining the real-time average capacity decay rate of the batteries of the vehicles in the unit;

[0054] Determine the abnormality handling strategy based on the real-time average capacity decay rate and the second capacity decay rate threshold.

[0055] For example, if the train is a multi-unit train, there may be other train cars that can affect the operating status of the train car where the abnormal battery is located. If the received information is a capacity alarm, it can be determined that the battery is very likely to have an abnormality related to the capacity size, and this abnormality may directly affect the current operation of the train. In this case, the real-time average capacity decay rate of the batteries in the train car can be determined to determine the extent of the abnormality's impact on the train operation, and then determine the abnormality handling strategy to be adopted. The average capacity decay rate r can be determined using the following formula:

[0056]

[0057] wherein A0is the initial capacity of the battery of each car, A k is the capacity of the battery of the kth car, m is the total number of cars, and k ranges from 1 to m. In determining the real-time average capacity decay rate, the specific value of A k may be the real-time capacity of the battery of the kth car; in determining the predicted average capacity decay rate, the specific value of A k may be the predicted capacity of the battery of the kth car. The second capacity decay rate threshold value can be pre-set, for example, can be set to 15%, and the first capacity decay rate threshold value can be less than the second capacity decay rate threshold value.

[0058] Optionally, determining the abnormality handling strategy according to the real-time average capacity decay rate and the second capacity decay rate threshold value can comprise:

[0059] if the real-time average capacity decay rate is greater than the second capacity decay rate threshold value, controlling the vehicle to stop operation and generating a dispatch repair request; or,

[0060] if the real-time average capacity decay rate is less than or equal to the second capacity decay rate threshold value, marking the vehicle, controlling the vehicle to continue operation and generating a vehicle operation strategy adjustment request.

[0061] For example, if the real-time average capacity decay rate is greater than the second capacity decay rate threshold value, it can be determined that the actual capacity decay rate of the vehicle as a whole is large, and even if it continues to run, there is a large risk of operation. Therefore, the vehicle can be controlled to stop operation, and a dispatch repair request can be generated to repair the vehicle and call other vehicles to replace its operation.

[0062] If the real-time average capacity decay rate is less than or equal to the second capacity decay rate threshold value, it can be determined that the actual capacity decay rate of the vehicle as a whole is small, and safe operation within a certain mileage can still be maintained, so the vehicle can be controlled to continue operation. However, although the operation at this time can continue to be maintained, there is a certain risk, so a vehicle operation strategy adjustment request is generated to reduce the possibility of abnormality of the vehicle in subsequent operation. In addition, since there is a certain risk in its operation, the vehicle can be marked so that relevant personnel pay special attention to it, and the vehicle can be quickly located for repair after it is parked. The vehicle operation strategy adjustment request can include information indicating the real-time average capacity decay rate and the second capacity decay rate threshold value, so that relevant personnel can adjust the operation strategy of the vehicle.

[0063] In an optional embodiment, when the information indicating the capacity size abnormality is received and the information indicating the capacity decay rate abnormality is not received, determining the abnormality handling strategy according to the marshalling number and the information indicating the capacity size abnormality can comprise:

[0064] determining a predicted average capacity fade rate of the vehicle batteries within the consist, when the received information is capacity warning information and the vehicle is a multiple unit vehicle;

[0065] determining an abnormality handling strategy according to the predicted average capacity fade rate and a first capacity fade rate threshold.

[0066] For example, the vehicle is a multiple unit vehicle, and there are other carriages that can affect the running state of the carriage where the abnormal battery is located. The received information is capacity warning information, which can determine that the battery is likely to have a capacity size-related abnormality in the future, and the abnormality may affect the future operation of the vehicle. At this time, the predicted average capacity fade rate of the vehicle batteries within the consist can be determined to determine the degree of influence of the vehicle by the battery abnormality at a future time, and then determine the abnormality handling strategy to be adopted.

[0067] Optionally, determining an abnormality handling strategy according to the predicted average capacity fade rate and a first capacity fade rate threshold can include:

[0068] If the predicted average capacity fade rate is greater than the first capacity fade rate threshold, a battery capacity recalibration request is generated and a vehicle operation strategy adjustment request is generated; or,

[0069] If the predicted average capacity fade rate is less than or equal to the first capacity fade rate threshold, the vehicle is controlled to maintain the current operation strategy to continue operation.

[0070] For example, if the predicted average capacity fade rate is greater than the first capacity fade rate threshold, it may be affected by the lack of accuracy of the predicted capacity, and the received information is capacity warning information, i.e. the battery has not yet appeared a capacity size-related abnormality at the current time, therefore, a battery capacity recalibration request can be generated. And the predicted average capacity fade rate is greater than the first capacity fade rate threshold, which can determine that the degree of influence of the vehicle by the battery abnormality at a future time may be large, in order to ensure the safety of the subsequent operation of the vehicle, a vehicle operation strategy adjustment request can be generated to reduce the possibility of the vehicle appearing abnormal in the subsequent operation process, so that the vehicle completes the operation plan before the abnormality occurs.

[0071] If the predicted average capacity fade rate is less than or equal to the first capacity fade rate threshold, it can be determined that the degree of influence of the vehicle by the battery abnormality at a future time may be small, and the safety of the subsequent operation of the vehicle is high, and the vehicle can be controlled to maintain the current operation strategy to continue operation, in order to reduce the change to the vehicle operation plan.

[0072] Figure 2 is a flowchart of a vehicle battery abnormality handling method provided by an exemplary embodiment of the present disclosure. The method can be applied to an ATS vehicle scheduling system, and the method is used to Figure 2The implementation process of the vehicle battery abnormality processing method provided by the present disclosure can be more clearly understood. As shown in Figure 2 The method can include S201 to S218.

[0073] S201, it is judged whether the attenuation rate alarm information or the attenuation rate early warning information is received. If yes, S202 is executed, and if no, S203 is executed.

[0074] S202, the received information is displayed.

[0075] S203, it is judged whether the capacity early warning information is received. If yes, S204 is executed, and if no, S212 is executed.

[0076] S204, it is judged whether the vehicle is a single-formation vehicle. If yes, S205 is executed, and if no, S208 is executed.

[0077] S205, it is judged whether the predicted capacity attenuation rate is greater than the first capacity attenuation rate threshold. If yes, S206 is executed, and if no, S207 is executed.

[0078] S206, a battery capacity recalibration request is generated.

[0079] S207, a vehicle operation strategy adjustment request is generated.

[0080] S208, the predicted average capacity attenuation rate of the vehicle battery in the formation is determined.

[0081] S209, it is judged whether the predicted average capacity attenuation rate is greater than the first capacity attenuation rate threshold. If yes, 210 is executed, and if no, S211 is executed.

[0082] S210, a battery capacity recalibration request is generated and a vehicle operation strategy adjustment request is generated.

[0083] S211, the vehicle is controlled to maintain the current operation strategy to continue running.

[0084] S212, it is judged whether the capacity alarm information is received. If yes, S213 is executed, and if no, S201 is re-executed.

[0085] S213, it is judged whether the vehicle is a single-formation vehicle. If yes, S214 is executed, and if no, S215 is executed.

[0086] S214, the vehicle is controlled to stop operation, and a dispatch repair request is generated.

[0087] S215, the real-time average capacity attenuation rate of the vehicle battery in the formation is determined.

[0088] S216, determining whether the real-time average capacity attenuation rate is greater than a second capacity attenuation rate threshold. If yes, S217 is executed, and if no, S218 is executed.

[0089] S217, controlling the vehicle to stop operation and generating a dispatch repair request.

[0090] S218, marking the vehicle, controlling the vehicle to continue operation and generating a vehicle operation strategy adjustment request.

[0091] In this way, it can be determined whether the battery of the vehicle may have a capacity size abnormality or a capacity attenuation rate abnormality from the current and future dimensions, and in combination with the number of vehicle marshalling, a processing strategy suitable for the actual state of the vehicle can be quickly determined, the dependence on manpower is reduced, and the batteries on the train can be maintained and maintained in time more accurately, and the operation safety of the vehicle is improved.

[0092] Figure 3 is a flowchart of a vehicle battery abnormal information determination method provided by an example embodiment of the present disclosure. The method can be applied to an intelligent operation and maintenance platform, specifically, to a battery attenuation monitoring platform of the intelligent operation and maintenance platform. As shown in Figure 3 , the method can include S301 and S302.

[0093] S301, determining the predicted capacity of the battery through a pre-trained battery capacity prediction model, wherein the battery capacity prediction model is obtained based on a golden section search algorithm optimization.

[0094] For example, the battery can refer to the power battery of any car of the train. The model can be pre-stored in the intelligent operation and maintenance platform. As shown in Figure 4 , the real-time data of the battery can be collected by a high-voltage detection module (HVSU) inside the battery, and the real-time data can be forwarded to the information terminal of the vehicle through the battery management controller (BMS) for storage. The information terminal can transmit the real-time data to the intelligent operation and maintenance platform through wireless communication technology, such as a 4G network, and then input the real-time data as reference data into the battery capacity prediction model to obtain the predicted capacity output by the battery capacity prediction model. The predicted capacity can refer to the estimated value of the battery capacity after half a year, or the estimated value of the battery capacity after other target time, and the specific target time can be set based on actual needs. The real-time data can include the current time, the current environment temperature, and the number of battery cycles, etc. The number of battery cycles can refer to the number of complete charge and discharge cycles of the battery.

[0095] Currently, power batteries are applied to urban rail trains. Once the power battery fails, it may cause the running line to be out of service, and therefore, higher requirements are put forward for the early prediction of train power battery failures. In the vehicle battery abnormal information determination method provided in the present disclosure, the predicted capacity of the battery is determined by the battery capacity prediction model optimized based on the tentacle search algorithm, and the tentacle search algorithm has the characteristics of simple principle, few parameters and less calculation, and has an advantage in processing low-dimensional optimization targets. Therefore, the battery capacity prediction model optimized based on the tentacle search algorithm can quickly determine the predicted capacity with high accuracy.

[0096] S302, generating abnormal information of the battery according to the real-time capacity and the predicted capacity, wherein the abnormal information is used to implement the vehicle battery abnormality processing method described in any of the above embodiments.

[0097] For example, the real-time capacity of the rail vehicle battery, i.e., the battery described above, can be automatically collected by the ampere-hour integration method, i.e., the actual charging current and time of the battery during the charging and discharging process, to calculate the real-time capacity of the battery. The real-time capacity and the predicted capacity are for the same battery. The abnormal information of the battery can refer to at least one of the capacity alarm information, the capacity early warning information, the decay rate alarm information and the decay rate early warning information described above. After generating the abnormal information of the battery, the intelligent operation and maintenance platform can upload the abnormal information to the vehicle dispatching system ATS, so that the vehicle dispatching system ATS determines the abnormality processing method to be adopted.

[0098] The battery capacity prediction model optimized based on the tentacle search algorithm can quickly determine the predicted capacity with high accuracy; according to the real-time capacity and the predicted capacity, when it is determined that the battery of the vehicle is abnormal at present or in the future, the corresponding abnormal information can be generated, and the comprehensiveness of the abnormal information is improved. Therefore, reliable judgment basis can be provided for the determination of subsequent abnormality processing strategies.

[0099] In an optional embodiment, the predicted capacity of the battery is determined by the battery capacity prediction model trained in advance, comprising:

[0100] The reference data of the battery and the target time are input into the battery capacity prediction model to obtain the predicted capacity corresponding to the target time, wherein the reference data includes the reference time, the reference environmental temperature and the reference number of cycles of the battery.

[0101] For example, the reference data can be the real-time data of the battery collected by the HVSU. The target time can be set by the user and input into the battery capacity prediction model. That is, the content input into the battery capacity prediction model is the reference data of the battery and the target time, and the output content of the battery capacity prediction model is the predicted capacity of the battery.

[0102] Alternatively, the battery capacity prediction model can be trained in the following way:

[0103] obtain training data;

[0104] input the training data into a preset model, and optimize initialization parameters of the preset model based on a tentacle search algorithm until a condition of completing training is met, to obtain a battery capacity prediction model.

[0105] The training data can include, in a charging process starting from an initial SOC value of the battery being less than or equal to a first SOC threshold and ending when the SOC of the battery reaches a second SOC threshold, historical cycle times, historical capacities, historical times and historical ambient temperatures of the battery. The first SOC threshold can be set to 5%, and the second SOC threshold can be set to 100%. The composition of each training data can be s j = [T j , R j , C j ], where s j is the jth training data, T j is the historical time in the jth training data, R j is the historical ambient temperature in the jth training data, and C j is the historical cycle times in the jth training data. The condition of completing training can be that the number of iterations of the model reaches a preset number of iterations.

[0106] In the process of fully charging the battery, the intelligent operation and maintenance platform can first determine whether the SOC of the battery is less than or equal to 5%; if so, data is continuously recorded starting from the moment of starting charging, and the recorded data can include the SOC, the current, the current ambient temperature, the cumulative charging capacity and other information of the battery during the charging period; if not, no data is recorded. When the battery is charged to 100%, the data recording can be stopped, and the data recorded during this period can be used as training data in the future. If the charging is stopped when the SOC of the battery does not reach 100%, the data is not exported, i.e., it is not used as training data in the future; if the charging is not stopped when the SOC of the battery reaches 100%, the data is exported when the SOC of the battery just reaches 100%, and the subsequent data is not recorded and is not used as training data in the future.

[0107] Optionally, the objective function y i of the preset model can be constructed according to the following formula:

[0108]

[0109] where y i is the predicted capacity corresponding to the ith input data output by the model, w1 is a first weight matrix, w2 is a second weight matrix, w3 is a bias matrix, s iis the ith input data. The ith input data s i may include the corresponding time T i , the ambient temperature R i of the battery, and the cycle number C i . Wherein, the first weight matrix w1, the second weight matrix w2 and the bias matrix w3 are the parameters to be optimized in the preset model.

[0110] Optionally, the fitness function f(x) of the preset model can be constructed according to the following formula:

[0111]

[0112] Wherein, y j0 is the actual historical capacity of the jth training data, y j is the predicted historical capacity of the jth training data, and n is the total amount of training data.

[0113] Wherein, the process of optimizing the initialization parameters of the preset model by the weaver search algorithm can include:

[0114] determining the normalized weaver orientation;

[0115] determining the left weaver position and the right weaver position of the weaver according to the weaver orientation, the weaver centroid position and the distance between the two weaver antennae of the weaver;

[0116] calculating the fitness of the left weaver position and the fitness of the right weaver position of the weaver through the fitness function f(x) above;

[0117] updating the weaver centroid position and the parameters to be optimized according to the fitness of the two weaver positions and the step length, wherein the step length and the iteration number are in a negative correlation, that is, the step length decreases with the increase of the iteration number;

[0118] iteratively executing the above steps until the iteration number reaches the preset iteration number, to obtain the optimized initialization parameters.

[0119] Wherein, the normalized weaver orientation can be determined by the following formula

[0120]

[0121] Wherein, random(3,3) is a randomly generated matrix with a shape of 3x3, and ‖·‖ is a normalization processing function.

[0122] The left weaver position of the weaver can be determined by the following formula The right weaver position of the weaver can be determined by the following formula Wherein, x t is the weaver centroid position at time t, and dt is the distance between the two antennae of the beetle at time t.

[0123] The position of the centroid of the beetle can be updated by the following equation:

[0124]

[0125] where x t is the position of the centroid of the beetle at time t, x t+1 is the position of the centroid of the beetle at time t+1, δ t is the step size, is the normalized orientation of the antennae of the beetle, sign(·) is the sign function, is the fitness of the left antenna position, is the fitness of the right antenna position.

[0126] As described above, the beetle antenna algorithm has the characteristics of simple principle, few parameters and small amount of calculation, and has an advantage in processing low-dimensional optimization targets. Therefore, based on the beetle antenna search algorithm to optimize the initialization parameters of the preset model, a battery capacity prediction model with high accuracy can be simply and quickly determined to determine the accurate predicted capacity through the battery capacity prediction model.

[0127] In an optional embodiment, in S302, the abnormal information of the battery is generated according to the real-time capacity and the predicted capacity, which can include:

[0128] generating information indicating a capacity size abnormality according to the real-time capacity and the predicted capacity;

[0129] determining a predicted attenuation rate according to the predicted capacity;

[0130] generating information indicating a capacity attenuation rate abnormality according to the real-time attenuation rate and the predicted attenuation rate.

[0131] For example, the information indicating a capacity size abnormality is generated according to the real-time capacity and the predicted capacity, which can include:

[0132] If the real-time capacity is less than a capacity threshold, capacity alarm information indicating a real-time capacity size abnormality of the battery is generated; if the predicted capacity is less than the capacity threshold, capacity warning information indicating a predicted capacity size abnormality of the battery is generated.

[0133] The capacity threshold can be pre-set based on actual needs, for example, can be set to 80%. If the real-time capacity is less than the capacity threshold, it can be determined that the current battery capacity size is abnormal, and the capacity alarm information is generated. If the predicted capacity is less than the capacity threshold, it can be determined that the battery capacity at a target time, i.e., at a certain time in the future, can be an abnormal value, and the capacity warning information is generated.

[0134] For example, a predicted attenuation curve of the battery capacity can be generated based on the predicted capacities at multiple time points, and a slope of the curve corresponding to the target time is determined as the corresponding predicted attenuation rate. The real-time attenuation rate and the predicted attenuation rate are for the same battery.

[0135] For example, generating information indicating an abnormality of the capacity attenuation rate according to the real-time attenuation rate and the predicted attenuation rate can include:

[0136] If the real-time attenuation rate is greater than the attenuation rate threshold, attenuation rate alarm information indicating an abnormality of the real-time capacity attenuation rate of the battery is generated; if the predicted attenuation rate is greater than the attenuation rate threshold, attenuation rate early warning information indicating an abnormality of the predicted capacity attenuation rate of the battery is generated.

[0137] The attenuation rate threshold can be pre-set based on actual needs. If the real-time attenuation rate is greater than the attenuation rate threshold, it can be determined that the current battery capacity attenuation rate has an abnormality, and the attenuation rate alarm information is generated. If the predicted attenuation rate is greater than the attenuation rate threshold, it can be determined that the battery capacity attenuation rate at the target time, i.e., at a certain time in the future, can be an abnormal value, and the attenuation rate early warning information is generated.

[0138] Figure 5 is a flowchart of a vehicle battery abnormal information determination method provided by an example embodiment of the present disclosure. The method can be applied to an intelligent operation and maintenance platform, specifically, a battery attenuation monitoring platform of the intelligent operation and maintenance platform. Through the method, the real-time capacity attenuation rate of the battery can be determined, and the abnormal information of the battery can be determined based on the real-time capacity attenuation rate and the predicted capacity attenuation rate. Figure 5 The implementation process of the vehicle battery abnormal information determination method provided by the present disclosure can be more clearly understood. As shown in Figure 5 The method can include S501 to S514.

[0139] S501, acquiring real-time data of the battery.

[0140] S502, inputting the real-time data into a battery capacity prediction model optimized based on the tentacle search algorithm to obtain a predicted capacity.

[0141] S503, determining a real-time capacity of the battery.

[0142] S504, determining a real-time attenuation rate of the battery.

[0143] S505, determining a predicted attenuation rate according to the predicted capacity.

[0144] S506, judging whether the real-time capacity is less than a capacity threshold. If yes, S507 is executed; if no, S503 is executed.

[0145] S507, generating capacity alarm information indicating an abnormality of the real-time capacity size of the battery.

[0146] S508, determine whether the predicted capacity is less than the capacity threshold. If yes, perform S509; if no, perform S501.

[0147] S509, generate capacity warning information indicating that the predicted capacity of the battery is abnormal.

[0148] S510, determine whether the real-time attenuation rate is greater than the attenuation rate threshold. If yes, perform S511; if no, perform S503.

[0149] S511, generate attenuation rate alarm information indicating that the real-time capacity attenuation rate of the battery is abnormal.

[0150] S512, determine whether the predicted attenuation rate is greater than the attenuation rate threshold. If yes, perform S513; if no, perform S501.

[0151] S513, generate attenuation rate warning information indicating that the predicted capacity attenuation rate of the battery is abnormal.

[0152] S514, send the abnormal information to the vehicle dispatching system ATS.

[0153] Based on the battery capacity prediction model optimized by the tentacle search algorithm, the prediction capacity with high accuracy can be quickly determined; according to the real-time capacity, the predicted capacity, the real-time attenuation rate and the predicted attenuation rate, when it is determined that the battery of the vehicle has an abnormality at present or in the future, the corresponding abnormal information can be generated, and the comprehensiveness of the abnormal information is improved. In this way, reliable judgment basis can be provided for subsequent determination of abnormal handling strategy.

[0154] Based on the same inventive concept, the present disclosure also provides a vehicle battery abnormality handling device. Figure 6 is a block diagram of a vehicle battery abnormality handling device 600 provided by an exemplary embodiment of the present disclosure. Referring to Figure 6 , the vehicle battery abnormality handling device 600 can include:

[0155] The acquisition module 601 is configured to acquire abnormal information of the battery, wherein the abnormal information includes alarm information indicating that the battery currently has an abnormality, and / or warning information indicating that the battery will have an abnormality in the future.

[0156] The first determination module 602 is configured to determine an abnormality handling strategy according to the number of vehicles in the consist and the abnormal information.

[0157] In the technical solution, the abnormal information of the battery is acquired, wherein the abnormal information includes alarm information indicating that the battery currently has an abnormality and / or early warning information indicating that the battery will have an abnormality in the future; and the abnormality processing strategy is determined according to the marshalling quantity of the vehicle and the abnormal information. In this way, when it is determined that the battery of the vehicle currently or in the future has an abnormality, the processing strategy suitable for the actual state of the vehicle can be quickly determined in combination with the marshalling quantity of the vehicle, so that the battery on the train can be more accurately and timely maintained, and the operation safety of the vehicle is improved.

[0158] Optionally, the alarm information includes capacity alarm information indicating that the real-time capacity size of the battery is abnormal and / or decay rate alarm information indicating that the real-time capacity decay rate of the battery is abnormal; and the early warning information includes capacity early warning information indicating that the predicted capacity size of the battery is abnormal and / or decay rate early warning information indicating that the predicted capacity decay rate of the battery is abnormal.

[0159] Optionally, the first determining module 602 includes:

[0160] The first determining sub-module is configured to, when the information indicating the capacity size abnormality is received and the information indicating the capacity decay rate abnormality is not received, determine the abnormality processing strategy according to the marshalling quantity and the information indicating the capacity size abnormality.

[0161] Optionally, the first determining sub-module includes:

[0162] The second determining sub-module is configured to, when the information indicating the capacity size abnormality is received and the information indicating the capacity decay rate abnormality is not received, if the vehicle is a single-marshalling vehicle and the received information is the capacity alarm information, control the vehicle to stop operation and generate a dispatching maintenance request.

[0163] Optionally, the first determining sub-module includes:

[0164] The third determining sub-module is configured to, when the information indicating the capacity size abnormality is received and the information indicating the capacity decay rate abnormality is not received, if the vehicle is a single-marshalling vehicle and the received information is the capacity early warning information, determine the abnormality processing strategy according to the predicted capacity decay rate and a first capacity decay rate threshold.

[0165] Optionally, the third determining sub-module is configured to determine the abnormality processing strategy according to the predicted capacity decay rate and the first capacity decay rate threshold by:

[0166] if the predicted capacity decay rate is greater than the first capacity decay rate threshold, generating a request for recalibrating the battery capacity; or

[0167] If the predicted capacity decay rate is less than or equal to the first capacity decay rate threshold, a vehicle operation strategy adjustment request is generated.

[0168] Optionally, the first determining sub-module comprises:

[0169] The fourth determining sub-module is configured to, when the received information indicates a capacity size abnormality and no information indicating a capacity decay rate abnormality is received, determine a real-time average capacity decay rate of the vehicle battery within the consist if the vehicle is a multiple-unit vehicle and the received information is the capacity alarm information.

[0170] The fifth determining sub-module is configured to determine the abnormality processing strategy according to the real-time average capacity decay rate and a second capacity decay rate threshold.

[0171] Optionally, the fifth determining sub-module is configured to determine the abnormality processing strategy according to the real-time average capacity decay rate and the second capacity decay rate threshold in the following manner:

[0172] If the real-time average capacity decay rate is greater than the second capacity decay rate threshold, the vehicle is controlled to stop operation, and a dispatch repair request is generated; or

[0173] If the real-time average capacity decay rate is less than or equal to the second capacity decay rate threshold, the vehicle is marked, the vehicle is controlled to continue operation, and a vehicle operation strategy adjustment request is generated.

[0174] Optionally, the first determining sub-module comprises:

[0175] The sixth determining sub-module is configured to, when the received information indicates a capacity size abnormality and no information indicating a capacity decay rate abnormality is received, determine a predicted average capacity decay rate of the vehicle battery within the consist if the vehicle is a multiple-unit vehicle and the received information is the capacity early warning information.

[0176] The seventh determining sub-module is configured to determine the abnormality processing strategy according to the predicted average capacity decay rate and a first capacity decay rate threshold.

[0177] Optionally, the seventh determining sub-module is configured to determine the abnormality processing strategy according to the predicted average capacity decay rate and the first capacity decay rate threshold in the following manner:

[0178] If the predicted average capacity decay rate is greater than the first capacity decay rate threshold, a battery capacity recalibration request is generated, and a vehicle operation strategy adjustment request is generated; or

[0179] If the predicted average capacity decay rate is less than or equal to the first capacity decay rate threshold, the vehicle is controlled to maintain the current operation strategy to continue operation.

[0180] Optionally, the first determining module 602 is further configured to display the received information when the information indicating the abnormal capacity decay rate is received.

[0181] With regard to the apparatus in the above embodiments, the specific manners in which the various modules perform operations have been described in detail in the embodiments of the method, and thus will not be described in detail here.

[0182] Based on the same inventive concept, the present disclosure further provides a vehicle battery abnormal information determination apparatus. Figure 7 FIG. 7 is a block diagram of a vehicle battery abnormal information determination apparatus 700 provided by an exemplary embodiment of the present disclosure.

[0183] With reference to Figure 7 The vehicle battery abnormal information determination apparatus 700 can include:

[0184] A second determining module 701 configured to determine a predicted capacity of a battery by using a battery capacity prediction model that has been pre-trained, wherein the battery capacity prediction model is obtained based on a tentacle search algorithm.

[0185] A generating module configured to generate abnormal information of the battery according to a real-time capacity and the predicted capacity, wherein the abnormal information is used to implement the steps of the vehicle battery abnormal processing method according to any one of the above embodiments.

[0186] In this way, the battery capacity prediction model obtained based on the tentacle search algorithm can quickly determine a predicted capacity with high accuracy. According to the real-time capacity and the predicted capacity, corresponding abnormal information can be generated when it is determined that the battery of the vehicle is currently or will be in the future abnormal, thereby improving the comprehensiveness of the abnormal information. In this way, reliable judgment basis can be provided for subsequent determination of abnormal processing strategies.

[0187] Optionally, the second determining module 701 is configured to determine the predicted capacity of the battery by using the battery capacity prediction model that has been pre-trained in the following manner:

[0188] The reference data and a target time of the battery are input into the battery capacity prediction model to obtain a predicted capacity corresponding to the target time, wherein the reference data includes a reference time, a reference environmental temperature, and a reference number of battery cycles.

[0189] Optionally, the battery capacity prediction model is trained in the following manner:

[0190] Acquire training data, wherein the training data includes historical cycle counts, historical capacities, historical times, and historical ambient temperatures of the battery during a charging process starting from when an initial SOC value of the battery is less than or equal to a first SOC threshold and ending when the SOC of the battery reaches a second SOC threshold;

[0191] The training data is input into a preset model, and the initialization parameters of the preset model are optimized based on the longicorn beetle whisker search algorithm until the training completion conditions are met, thereby obtaining the battery capacity prediction model.

[0192] Optionally, the objective function y of the preset model is constructed according to the following formula: i :

[0193]

[0194] Among them, y i is the predicted capacity output by the model corresponding to the i-th input data, w1 is the first weight matrix, w2 is the second weight matrix, w3 is the bias matrix, s i is the i-th input data.

[0195] Optionally, the fitness function f(x) of the preset model is constructed according to the following formula:

[0196]

[0197] Among them, y j0 is the actual historical capacity of the jth training data, y j is the predicted historical capacity of the jth training data, and n is the total amount of the training data.

[0198] Optionally, the generating module 702 includes:

[0199] A first generating submodule is configured to generate information indicating abnormal capacity size based on the real-time capacity and the predicted capacity;

[0200] an eighth determining submodule, configured to determine a predicted attenuation rate based on the predicted capacity;

[0201] The second generating submodule is used to generate information indicating abnormal capacity decay rate according to the real-time decay rate and the predicted decay rate.

[0202] Optionally, the first generating submodule is configured to generate information indicating abnormal capacity size by:

[0203] If the real-time capacity is less than the capacity threshold, generating capacity alarm information indicating that the real-time capacity of the battery is abnormal;

[0204] If the predicted capacity is less than the capacity threshold, capacity early warning information indicating that the battery predicted capacity is abnormal is generated.

[0205] Optionally, the second generating sub-module is configured to generate information indicating that the capacity attenuation rate is abnormal by the following method, comprising:

[0206] If the real-time attenuation rate is greater than the attenuation rate threshold, attenuation rate alarm information indicating that the battery real-time capacity attenuation rate is abnormal is generated.

[0207] If the predicted attenuation rate is greater than the attenuation rate threshold, attenuation rate early warning information indicating that the battery predicted capacity attenuation rate is abnormal is generated.

[0208] As to the device in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments of the method, and will not be described in detail here.

[0209] The present disclosure also provides a vehicle battery abnormality processing system, comprising:

[0210] The intelligent operation and maintenance platform is configured to implement the steps of the vehicle battery abnormality information determination method according to any one of the above embodiments.

[0211] The vehicle dispatching system is configured to implement the steps of the vehicle battery abnormality processing method according to any one of the above embodiments.

[0212] Figure 8 is a block diagram of an electronic device 1900 provided by an example embodiment of the present disclosure. For example, the electronic device 1900 can be provided as a server. Referring to Figure 8 , the electronic device 1900 includes a processor 1922, the number of which can be one or more, and a memory 1932 for storing a computer program executable by the processor 1922. The computer program stored in the memory 1932 can include one or more modules each corresponding to a set of instructions. In addition, the processor 1922 can be configured to execute the computer program to perform the vehicle battery abnormality processing method or the vehicle battery abnormality information determination method described above.

[0213] In addition, the electronic device 1900 can further include a power supply component 1926 which can be configured to perform power management of the electronic device 1900, and a communication component 1950 which can be configured to implement communication of the electronic device 1900, for example, wired or wireless communication. In addition, the electronic device 1900 can further include an input / output (I / O) interface 1958. The electronic device 1900 can operate based on an operating system stored in the memory 1932.

[0214] In another exemplary embodiment, a computer readable storage medium including program instructions is also provided, which when executed by a processor implement the steps of the vehicle battery abnormality processing method or the vehicle battery abnormality information determination method described above. For example, the non-transitory computer readable storage medium can be the memory 1932 described above including program instructions executable by the processor 1922 of the electronic device 1900 to complete the vehicle battery abnormality processing method or the vehicle battery abnormality information determination method described above.

[0215] In another exemplary embodiment, a computer program product is also provided, which contains a computer program executable by a programmable apparatus, the computer program having code portions for performing the vehicle battery abnormality processing method or the vehicle battery abnormality information determination method described above when executed by the programmable apparatus.

[0216] The preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details of the above-described embodiments. Various simple modifications can be made to the technical solutions of the present disclosure within the scope of the technical concepts of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.

[0217] In addition, it should be noted that each specific technical feature described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, various possible combinations are not described again in the present disclosure.

[0218] Furthermore, any combination of the various different embodiments of the present disclosure can also be made, as long as it does not deviate from the idea of the present disclosure, it should also be considered as disclosed by the present disclosure.

Claims

1. A method for handling vehicle battery abnormality, characterized in that: include: Obtaining abnormality information of the battery, wherein the abnormality information includes alarm information indicating a current abnormality of the battery and / or early warning information indicating a future abnormality of the battery, the alarm information includes capacity alarm information indicating an abnormality in the real-time capacity of the battery and / or decay rate alarm information indicating an abnormality in the real-time capacity decay rate of the battery; the early warning information includes capacity alarm information indicating an abnormality in the predicted capacity of the battery and / or decay rate alarm information indicating an abnormality in the predicted capacity decay rate of the battery; Determining an exception handling strategy based on the number of vehicles in the group and the exception information; The determining of an exception handling strategy based on the number of vehicles in the group and the exception information includes: When receiving information indicating abnormal capacity size and not receiving information indicating abnormal capacity decay rate, determining an abnormality handling strategy based on the number of trains and the information indicating abnormal capacity size; Wherein, when receiving the information indicating the abnormal capacity size and not receiving the information indicating the abnormal capacity decay rate, determining the abnormality handling strategy according to the number of trains and the information indicating the abnormal capacity size, includes: When information indicating abnormal capacity size is received and information indicating abnormal capacity decay rate is not received, if the vehicle is a single-unit vehicle and the received information is the capacity alarm information, the vehicle is controlled to stop operating and a scheduling maintenance request is generated.

2. The vehicle battery abnormality processing method according to claim 1, characterized in that: When the information indicating the abnormal capacity size is received and the information indicating the abnormal capacity decay rate is not received, determining the abnormality handling strategy according to the number of trains and the information indicating the abnormal capacity size includes: When information indicating an abnormal capacity size is received and information indicating an abnormal capacity decay rate is not received, if the vehicle is a single-unit vehicle and the received information is the capacity warning information, the abnormality handling strategy is determined based on the predicted capacity decay rate and the first capacity decay rate threshold.

3. The vehicle battery abnormality processing method according to claim 2, characterized in that: The determining the abnormality handling strategy according to the predicted capacity decay rate and the first capacity decay rate threshold includes: If the predicted capacity decay rate is greater than the first capacity decay rate threshold, generating a request to recalibrate the battery capacity; or, If the predicted capacity decay rate is less than or equal to the first capacity decay rate threshold, a vehicle operation strategy adjustment request is generated.

4. The vehicle battery abnormality processing method according to claim 1, characterized in that: When the information indicating the abnormal capacity size is received and the information indicating the abnormal capacity decay rate is not received, determining the abnormality handling strategy according to the number of trains and the information indicating the abnormal capacity size includes: When receiving information indicating abnormal capacity size and not receiving information indicating abnormal capacity decay rate, if the vehicle is a multi-unit vehicle and the received information is the capacity alarm information, determining the real-time average capacity decay rate of the batteries of the vehicles in the unit; The abnormality handling strategy is determined according to the real-time average capacity decay rate and the second capacity decay rate threshold.

5. The vehicle battery abnormality processing method according to claim 4, characterized in that: The determining the abnormality handling strategy according to the real-time average capacity decay rate and the second capacity decay rate threshold includes: If the real-time average capacity decay rate is greater than the second capacity decay rate threshold, the vehicle is controlled to stop operating and a scheduling maintenance request is generated; or If the real-time average capacity decay rate is less than or equal to the second capacity decay rate threshold, the vehicle is marked, the vehicle is controlled to continue operating, and a vehicle operation strategy adjustment request is generated.

6. The vehicle battery abnormality processing method according to claim 1, characterized in that: When the information indicating the abnormal capacity size is received and the information indicating the abnormal capacity decay rate is not received, determining the abnormality handling strategy according to the number of trains and the information indicating the abnormal capacity size includes: When receiving information indicating abnormal capacity size and not receiving information indicating abnormal capacity decay rate, if the vehicle is a multi-train vehicle and the received information is the capacity warning information, determining a predicted average capacity decay rate of the batteries of the vehicles in the train; The abnormality handling strategy is determined according to the predicted average capacity decay rate and a first capacity decay rate threshold.

7. The vehicle battery abnormality processing method according to claim 6, characterized in that: The determining the abnormality handling strategy according to the predicted average capacity decay rate and the first capacity decay rate threshold includes: If the predicted average capacity decay rate is greater than the first capacity decay rate threshold, a request to recalibrate the battery capacity and a request to adjust the vehicle operation strategy are generated; or, If the predicted average capacity decay rate is less than or equal to the first capacity decay rate threshold, the vehicle is controlled to maintain the current operation strategy and continue to operate.

8. The vehicle battery abnormality processing method according to claim 1, characterized in that: The vehicle battery abnormality processing method further includes: When information indicating an abnormal capacity decay rate is received, the received information is displayed.

9. A method for determining abnormal information of a vehicle battery, characterized in that: include: Determine the predicted capacity of the battery by using a pre-trained battery capacity prediction model, wherein the battery capacity prediction model is optimized based on a longhorn beard search algorithm; According to the real-time capacity and the predicted capacity, abnormality information of the battery is generated, wherein the abnormality information is used to implement the steps of the vehicle battery abnormality processing method according to any one of claims 1 to 8.

10. The vehicle battery abnormality information determination method according to claim 9, characterized in that: The method of determining the predicted capacity of the battery using the pre-trained battery capacity prediction model includes: The reference data and target time of the battery are input into the battery capacity prediction model to obtain the predicted capacity corresponding to the target time, wherein the reference data includes reference time, reference ambient temperature and reference number of battery cycles.

11. The vehicle battery abnormality information determination method according to claim 9, characterized in that: The battery capacity prediction model is trained in the following way: Acquire training data, wherein the training data includes historical cycle counts, historical capacities, historical times, and historical ambient temperatures of the battery during a charging process starting from when an initial SOC value of the battery is less than or equal to a first SOC threshold and ending when the SOC of the battery reaches a second SOC threshold; The training data is input into a preset model, and the initialization parameters of the preset model are optimized based on the longicorn beetle whisker search algorithm until the training completion conditions are met, thereby obtaining the battery capacity prediction model.

12. The vehicle battery abnormality information determination method according to claim 11, characterized in that: The objective function of the preset model is constructed according to the following formula : in, The output of the model is The predicted capacity corresponding to the input data, is the first weight matrix, is the second weight matrix, is the bias matrix, For the Input data.

13. The vehicle battery abnormality information determination method according to claim 11, characterized in that: The fitness function of the preset model is constructed according to the following formula: : in, For the The actual historical capacity of training data, For the The predicted historical capacity of training data, is the total amount of training data.

14. The vehicle battery abnormality information determination method according to claim 9, characterized in that: The generating of battery abnormality information according to the real-time capacity and the predicted capacity includes: generating information indicating abnormal capacity size based on the real-time capacity and the predicted capacity; determining a predicted decay rate based on the predicted capacity; Information indicating abnormal capacity decay rate is generated based on the real-time decay rate and the predicted decay rate.

15. The vehicle battery abnormality information determination method according to claim 14, characterized in that: The generating, based on the real-time capacity and the predicted capacity, information indicating abnormal capacity size includes: If the real-time capacity is less than the capacity threshold, generating capacity alarm information indicating that the real-time capacity of the battery is abnormal; If the predicted capacity is less than the capacity threshold, capacity warning information is generated to indicate that the predicted battery capacity is abnormal.

16. The vehicle battery abnormality information determination method according to claim 14, characterized in that: The generating, according to the real-time attenuation rate and the predicted attenuation rate, information indicating abnormal capacity attenuation rate includes: If the real-time decay rate is greater than the decay rate threshold, a decay rate alarm message is generated indicating that the real-time capacity decay rate of the battery is abnormal; If the predicted decay rate is greater than the decay rate threshold, decay rate warning information is generated indicating that the predicted capacity decay rate of the battery is abnormal.

17. A vehicle battery abnormality processing system, characterized in that: include: An intelligent operation and maintenance platform for implementing the steps of the vehicle battery abnormality information determination method according to any one of claims 9 to 16; A vehicle dispatching system is used to implement the steps of the vehicle battery abnormality processing method according to any one of claims 1 to 8.

18. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the vehicle battery abnormality processing method described in any one of claims 1 to 8 are implemented, or the steps of the vehicle battery abnormality information determination method described in any one of claims 9 to 16 are implemented.

Images