Battery fault diagnosis method, device and equipment and storage medium

Abstract

The invention provides a battery fault diagnosis method, device and equipment and a storage medium, and the method is applied to a cloud server, and comprises the steps: obtaining the actual operation data of a to-be-diagnosed battery and a battery resource set corresponding to the to-be-diagnosed battery; determining a target risk score of the to-be-diagnosed battery according to the actual operation data of the to-be-diagnosed battery; according to the target risk score of the to-be-diagnosed battery and the historical risk score of each associated battery, determining the sequence of the to-be-diagnosed battery and each associated battery in the battery resource set, and according to the sequence of the to-be-diagnosed battery and each associated battery in the battery resource set, determining the target fault level of the to-be-diagnosed battery; and determining a fault diagnosis result of the to-be-diagnosed battery according to the target fault level of the to-be-diagnosed battery. According to the method, multiple faults can be diagnosed at the same time, large-scale energy storage battery data analysis and processing requirements are met, multiple data conjoint analysis can be carried out on the battery, and the diagnosis precision of fault diagnosis is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery data processing, in particular to a battery fault diagnosis method and device, equipment and a storage medium. BACKGROUND

[0002] Lithium iron phosphate energy storage batteries are widely used in photovoltaic storage systems and other fields due to their high energy density, long service life, high safety and other characteristics. However, during use, energy storage batteries are inevitably affected by external environmental factors and internal factors, and are prone to failure. Therefore, an effective fault diagnosis method is very important to ensure the safe and reliable operation of the battery and prolong the service life of the battery.

[0003] The fault diagnosis method in the prior art is usually based on a local server, which calls and detects the battery data in the battery management system to realize fault diagnosis of the battery.

[0004] However, this fault diagnosis method can only diagnose a single or several faults, and cannot diagnose multiple faults at the same time. In addition, it can only start from a single parameter of the battery and cannot perform multi-parameter joint analysis on the battery, which greatly affects the diagnosis accuracy of the battery fault. Therefore, there is a problem that it cannot meet the demand of large-scale energy storage battery data analysis and processing. Moreover, it is subject to local computing power during calculation, resulting in a large time delay and failing to meet the demand of efficient and real-time fault diagnosis. SUMMARY

[0005] The present application aims to solve the problems in the prior art that it cannot meet the demand of large-scale energy storage battery data analysis and processing and cannot meet the demand of efficient and real-time fault diagnosis.

[0006] To achieve the above-mentioned purpose, the technical solutions adopted by the embodiments of the present application are as follows:

[0007] In a first aspect, an embodiment of the present application provides a battery fault diagnosis method applied to a cloud server, which comprises:

[0008] obtaining actual operation data of a battery to be diagnosed and a battery resource set corresponding to the battery to be diagnosed, wherein the battery resource set comprises historical risk scores and historical operation data of each associated battery of the battery to be diagnosed, and the associated battery has the same portrait as the battery to be diagnosed;

[0009] determining a target risk score of the battery to be diagnosed according to the actual operation data of the battery to be diagnosed;

[0010] According to the target risk score of the battery to be diagnosed and the historical risk scores of the associated batteries, an order of the battery to be diagnosed and the associated batteries in the battery resource set is determined, and a target failure level of the battery to be diagnosed is determined according to the order of the battery to be diagnosed and the associated batteries in the battery resource set, and the target risk score of the battery to be diagnosed and actual operation data are added to the battery resource set;

[0011] According to the target failure level of the battery to be diagnosed, a failure diagnosis result of the battery to be diagnosed is determined.

[0012] In a possible implementation, the determining of the target risk score of the battery to be diagnosed according to the actual operation data of the battery to be diagnosed comprises:

[0013] According to the actual operation data, occurrence degree coefficients, severity degree coefficients and detection degree coefficients of the battery to be diagnosed are respectively calculated;

[0014] According to the occurrence degree coefficients, the severity degree coefficients and the detection degree coefficients, the target risk score of the battery to be diagnosed is determined.

[0015] In a possible implementation, the process of calculating the occurrence degree coefficients comprises:

[0016] According to the number of times of occurrence of a preset mode of failure of the battery to be diagnosed in a preset historical period, the running time length of the battery to be diagnosed in the preset historical period and a failure number threshold corresponding to the preset historical period, the occurrence degree coefficients are calculated.

[0017] In a possible implementation, the process of calculating the severity degree coefficients comprises:

[0018] According to the equipment performance loss information of the battery to be diagnosed in a preset historical period and normal equipment performance information of the battery to be diagnosed, the severity degree coefficients are calculated.

[0019] In a possible implementation, the process of calculating the detection degree coefficients comprises:

[0020] According to the failure time of the battery to be diagnosed in a preset historical period and the normal detection time of the battery to be diagnosed in the preset historical period, the detection degree coefficients are calculated.

[0021] In a possible implementation, the determining of the target failure level of the battery to be diagnosed according to the order of the battery to be diagnosed and the associated batteries in the battery resource set comprises:

[0022] According to the total number of the battery to be diagnosed and each associated battery, the order of the battery to be diagnosed and each associated battery in the battery resource set, and a preset grade division ratio, a target fault level of the battery to be diagnosed is determined.

[0023] In a possible implementation, the determining of the fault diagnosis result of the battery to be diagnosed according to the target fault level of the battery to be diagnosed comprises:

[0024] According to the actual operation data of the battery to be diagnosed and the historical operation data of each associated battery, a fault score of the battery to be diagnosed is determined.

[0025] According to the target fault level of the battery to be diagnosed and the fault score of the battery to be diagnosed, a fault diagnosis result of the battery to be diagnosed is determined.

[0026] In a possible implementation, the determining of the fault score of the battery to be diagnosed according to the actual operation data of the battery to be diagnosed and the historical operation data of each associated battery comprises:

[0027] According to the historical operation data of each associated battery, a distance matrix is generated, and a low-density model is determined according to the distance matrix.

[0028] Distance information between the actual operation data of the battery to be diagnosed and the low-density model is determined.

[0029] According to the distance information, the fault score of the battery to be diagnosed is determined.

[0030] In a second aspect, another embodiment of the present application provides a battery fault diagnosis device, applied to a cloud server, the device comprising:

[0031] An acquisition module is configured to acquire actual operation data of a battery to be diagnosed and a battery resource set corresponding to the battery to be diagnosed, wherein the battery resource set comprises historical risk scores and historical operation data of each associated battery of the battery to be diagnosed, and the associated battery has the same portrait as the battery to be diagnosed.

[0032] A determination module is configured to determine a target risk score of the battery to be diagnosed according to the actual operation data of the battery to be diagnosed.

[0033] The determination module is configured to determine an order of the battery to be diagnosed and each associated battery in the battery resource set according to the target risk score of the battery to be diagnosed and the historical risk scores of each associated battery, determine a target fault level of the battery to be diagnosed according to the order of the battery to be diagnosed and each associated battery in the battery resource set, and add the target risk score and the actual operation data of the battery to be diagnosed to the battery resource set.

[0034] determine a fault diagnosis result of the battery to be diagnosed according to a target fault level of the battery to be diagnosed.

[0035] In a possible implementation, the determining module is specifically configured to:

[0036] calculate an occurrence degree coefficient, a severity degree coefficient and a detection degree coefficient of the battery to be diagnosed according to the actual operation data;

[0037] determine a target risk score of the battery to be diagnosed according to the occurrence degree coefficient, the severity degree coefficient and the detection degree coefficient.

[0038] In a possible implementation, the determining module is specifically configured to:

[0039] calculate the occurrence degree coefficient according to a number of times of occurrence of a preset mode of fault of the battery to be diagnosed in a preset historical period, an operation duration of the battery to be diagnosed in the preset historical period and a fault number threshold corresponding to the preset historical period.

[0040] In a possible implementation, the determining module is specifically configured to:

[0041] calculate the severity degree coefficient according to device performance loss information of the battery to be diagnosed in a preset historical period and normal device performance information of the battery to be diagnosed.

[0042] In a possible implementation, the determining module is specifically configured to:

[0043] calculate the detection degree coefficient according to a fault time of the battery to be diagnosed in a preset historical period and a normal detection time of the battery to be diagnosed in the preset historical period.

[0044] In a possible implementation, the determining module is specifically configured to:

[0045] determine a target fault level of the battery to be diagnosed according to a total number of the battery to be diagnosed and each associated battery, a sorting of the battery to be diagnosed and each associated battery in the battery resource set and a preset level division ratio.

[0046] In a possible implementation, the determining module is specifically configured to:

[0047] determine a fault score of the battery to be diagnosed according to actual operation data of the battery to be diagnosed and historical operation data of each associated battery;

[0048] According to the target fault level of the battery to be diagnosed and the fault score of the battery to be diagnosed, a fault diagnosis result of the battery to be diagnosed is determined.

[0049] In a possible implementation, the determining module is specifically configured to:

[0050] According to historical operation data of each associated battery, a distance matrix is generated, and a low-density model is determined according to the distance matrix;

[0051] Distance information between actual operation data of the battery to be diagnosed and the low-density model is determined;

[0052] According to the distance information, a fault score of the battery to be diagnosed is determined.

[0053] In a third aspect, another embodiment of the present application provides an electronic device, including a processor, a storage medium, and a bus. The storage medium stores machine readable instructions executable by the processor. When the electronic device is running, the processor and the storage medium communicate through the bus. The processor executes the machine readable instructions to perform the steps of the method according to any one of the first aspect.

[0054] In a fourth aspect, another embodiment of the present application provides a storage medium, which stores a computer program. When the computer program is run by a processor, the steps of the method according to any one of the first aspect are performed.

[0055] The present application has the following beneficial effects: by obtaining actual operation data of a battery to be diagnosed and a battery resource set corresponding to the battery to be diagnosed, a target risk score of the battery to be diagnosed is determined according to the actual operation data of the battery to be diagnosed, and the battery to be diagnosed and each associated battery in the battery resource set are sorted according to the target risk score of the battery to be diagnosed and historical risk scores of each associated battery. The target fault level of the battery to be diagnosed is determined according to the sorting of the battery to be diagnosed and each associated battery in the battery resource set, so that the fault diagnosis result of the battery to be diagnosed can be determined according to the target fault level. Multiple faults can be diagnosed at the same time, meeting the demand for large-scale energy storage battery data analysis and processing. In addition, the battery can be analyzed in combination with multiple data when diagnosing faults, ensuring the diagnosis accuracy of fault diagnosis. At the same time, since the battery fault diagnosis method provided by the embodiment of the present application is executed by a cloud server, the local computing power is avoided during running, meeting the demand for efficient and real-time fault diagnosis. In addition, the safety and reliability of the battery can be improved. BRIEF DESCRIPTION OF DRAWINGS

[0056] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can also be obtained without creative labor under the guidance of the content of the present application.

[0057] Figure 1 A flowchart of a battery fault diagnosis method provided by an embodiment of the present application;

[0058] Figure 2 A flowchart of determining a target risk score of a battery to be diagnosed in a battery fault diagnosis method provided by an embodiment of the present application;

[0059] Figure 3 A flowchart of determining a fault diagnosis result of a battery to be diagnosed in a battery fault diagnosis method provided by an embodiment of the present application;

[0060] Figure 4 A flowchart of determining a fault score of a battery to be diagnosed in a battery fault diagnosis method provided by an embodiment of the present application;

[0061] Figure 5 A structural diagram of a battery fault diagnosis device provided by an embodiment of the present application;

[0062] Figure 6 A structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of illustration and description, and do not serve to limit the protection scope of the present application. In addition, it should be understood that the schematic drawings are not drawn according to the actual proportions. The flowchart shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can not be implemented in sequence, and the steps without logical contextual relationship can be reversed in sequence or implemented simultaneously. In addition, one or more other operations can be added to the flowchart or one or more operations can be removed from the flowchart under the guidance of the content of the present application.

[0064] In addition, the described embodiments are only some of the embodiments of the present application, not all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0065] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0066] The prior art fault diagnosis method is generally based on a local server to call and detect faults of battery data in a battery management system, thereby realizing fault diagnosis of the battery.

[0067] However, this fault diagnosis method can generally only diagnose a single or several faults, and cannot diagnose multiple faults at the same time. At the same time, it can only start from a single parameter of the battery, and cannot perform multi-parameter joint analysis on the battery, which greatly affects the diagnosis accuracy of the battery fault. Therefore, there is a problem that it cannot meet the demand of large-scale energy storage battery data analysis and processing. Moreover, it is subject to local computing power when calculating, and there is a large time delay, which cannot meet the efficient and real-time fault diagnosis demand.

[0068] Based on the above problems, the embodiments of the present application propose a battery fault diagnosis method, which obtains actual running data of a battery to be diagnosed and a battery resource set corresponding to the battery to be diagnosed, thereby determining a target risk score of the battery to be diagnosed according to the actual running data of the battery to be diagnosed, and determining a sorting of the battery to be diagnosed and each associated battery in the battery resource set according to the target risk score of the battery to be diagnosed and the historical risk score of each associated battery. At the same time, the target fault level of the battery to be diagnosed is determined according to the sorting of the battery to be diagnosed and each associated battery in the battery resource set, so that the fault diagnosis result of the battery to be diagnosed can be determined according to the target risk score and the target fault level of the battery to be diagnosed. It can meet the demand of large-scale energy storage battery data analysis and processing and meet the efficient and real-time fault diagnosis demand.

[0069] Firstly, the scene to which the battery fault diagnosis method provided by the embodiments of the present application is applied is described.

[0070] It can be understood that the battery fault diagnosis method provided in the embodiments of the present application can be applied to the scenario of diagnosing the fault of the battery. In a possible application scenario, before the battery is shipped, a tester can test the battery, after the test is completed, the battery is taken as a battery to be diagnosed, the running data of the battery during the test is taken as the actual running data of the battery to be diagnosed, and the corresponding battery resource set is determined, so that the battery fault diagnosis method provided in the embodiments of the present application is executed to diagnose the fault of the battery, and the fault diagnosis result of the battery is obtained.

[0071] In another possible application scenario, after receiving the fault indication of a certain battery, a tester can take the fault battery as a battery to be diagnosed, take the running data of the fault battery as the actual running data of the battery to be diagnosed, and determine the corresponding battery resource set, so that the battery fault diagnosis method provided in the embodiments of the present application is executed to diagnose the fault of the fault battery, and the fault diagnosis result of the fault battery is obtained.

[0072] It can be understood that the battery fault diagnosis method provided in the embodiments of the present application can be deployed on a cloud server, through load balancing and fault tolerance technology, the high availability of the battery fault diagnosis method provided in the embodiments of the present application is ensured, at the same time, the computing resources can be flexibly expanded or reduced, the cost is saved, and the energy consumption is reduced.

[0073] The battery fault diagnosis method provided in the present application is described in detail in combination with multiple embodiments.

[0074] Figure 1 For a flowchart of the battery fault diagnosis method provided in the embodiments of the present application, refer to FIG. 1. Figure 1 As shown in FIG. 1, the battery fault diagnosis method is applied to a cloud server, and the method comprises the following steps.

[0075] S101, actual running data of a battery to be diagnosed and a battery resource set corresponding to the battery to be diagnosed are obtained.

[0076] The battery resource set comprises historical risk scores and historical running data of each associated battery of the battery to be diagnosed, and the associated battery has the same profile as the battery to be diagnosed.

[0077] Optionally, the battery to be diagnosed is a battery that needs to be diagnosed for fault, the actual running data of the battery to be diagnosed can be obtained by testing or using. The battery resource set corresponding to the battery to be diagnosed can be stored in the cloud server, and the battery resource set corresponding to the battery to be diagnosed can comprise a plurality of associated batteries related to the battery to be diagnosed and historical risk scores and historical running data of each associated battery.

[0078] The actual operation data of the battery to be diagnosed can include battery design data, charging safety data, discharging safety data, environmental data, short circuit data, etc. of the battery to be diagnosed, for example, battery data such as voltage, current, temperature, etc.

[0079] The associated battery related to the battery to be diagnosed can be an associated battery with the same profile as the battery to be diagnosed. Specifically, the same profile can be the same time and the same or similar fault type. The historical risk score of the associated battery can be a risk score of the associated battery occurring a fault under historical operation data. The historical operation data of the associated battery can include battery design data, charging safety data, discharging safety data, environmental data, short circuit data, etc. of the associated battery, for example, battery data such as voltage, current, temperature, etc.

[0080] Optionally, after obtaining the actual operation data of the battery to be diagnosed, the actual operation data of the battery to be diagnosed can be uploaded to the cloud server, and data cleaning and data transformation can be performed in the cloud server, so as to improve the accuracy and effectiveness of the actual operation data of the battery to be diagnosed.

[0081] For example, when the actual operation data of the battery to be diagnosed is cleaned and transformed, the actual operation data of the battery to be diagnosed can be processed for outlier rejection, null value processing, repeated value and irrelevant value removal, and normalization.

[0082] S102, according to the actual operation data of the battery to be diagnosed, determining the target risk score of the battery to be diagnosed.

[0083] Optionally, after obtaining the actual operation data of the battery to be diagnosed, the actual operation data of the battery to be diagnosed can be processed to determine the target risk score of the battery to be diagnosed. The target risk score is used to indicate the target risk score of the battery to be diagnosed under the current actual operation data.

[0084] Optionally, the battery design data, charging safety data, discharging safety data, environmental data, short circuit data, etc. in the actual operation data of the battery to be diagnosed can be processed respectively to calculate the battery design score, charging safety score, discharging safety score, environmental score, and short circuit score of the battery to be diagnosed, so as to determine the target risk score of the battery to be diagnosed.

[0085] S103, according to the target risk score of the battery to be diagnosed and the historical risk score of each associated battery, determining the order of the battery to be diagnosed and each associated battery in the battery resource set, and determining the target fault level of the battery to be diagnosed according to the order of the battery to be diagnosed and each associated battery in the battery resource set, and adding the target risk score and the actual operation data of the battery to be diagnosed to the battery resource set.

[0086] It can be understood that, after obtaining the target risk score of the battery to be diagnosed, since the battery to be diagnosed and each associated battery belong to the same type of battery, the ranking of the battery to be diagnosed and each associated battery in the battery resource set can be determined by comparing the target risk score of the battery to be diagnosed with the historical risk score of each associated battery, so that the batteries in the battery resource set can be ranked according to the risk score according to the ranking of the battery to be diagnosed and each associated battery in the battery resource set, so as to determine the target failure level of the battery to be diagnosed.

[0087] That is, comparing the target risk score of the battery to be diagnosed with the historical risk score of each associated battery can determine the ranking of the battery to be diagnosed and each associated battery in the battery resource set, so as to determine the emergency degree or priority of the failure corresponding to the target risk score of the battery to be diagnosed, so as to realize accurate diagnosis of the failure. At the same time, since the battery to be diagnosed and each associated battery are the same type of battery, the influence of the different use time of the battery on the failure diagnosis can be reduced, and the accuracy of the battery failure diagnosis method provided by the embodiment of the application can be improved.

[0088] Optionally, after obtaining the target failure level of the battery to be diagnosed, the battery to be diagnosed can be added to the battery resource set as an associated battery in the battery resource set, and the target risk score of the battery to be diagnosed can be added to the battery resource set as the historical risk score of the associated battery, and the actual operation data of the battery to be diagnosed can be added to the battery resource set as the historical operation data of the associated battery.

[0089] Exemplarily, after obtaining the target risk score of the battery to be diagnosed, the target risk score of the battery to be diagnosed and the historical risk score of each associated battery are sorted in the battery resource set according to the order of the score from large to small, to obtain the ranking sequence of the battery to be diagnosed and each associated battery in the battery resource set, and the target failure level of the battery to be diagnosed is determined based on statistical methods according to the ranking sequence of the battery to be diagnosed and each associated battery in the battery resource set, and the target risk score and the actual operation data of the battery to be diagnosed are added to the battery resource set. The statistical method can include correlation and regression algorithm, variance method, clustering method and the like.

[0090] S104, determining the failure diagnosis result of the battery to be diagnosed according to the target failure level of the battery to be diagnosed.

[0091] Optionally, after obtaining the target failure level of the battery to be diagnosed, the target failure level of the battery to be diagnosed and the actual operation data of the battery to be diagnosed can be processed to determine the failure diagnosis result of the battery to be diagnosed.

[0092] Exemplarily, the actual operation data of the battery to be diagnosed and the target fault level of the battery to be diagnosed can be processed through a preset algorithm to determine the fault diagnosis result of the battery to be diagnosed.

[0093] Optionally, after obtaining the target fault level of the battery to be diagnosed, the target fault level of the battery to be diagnosed, the actual operation data of the battery to be diagnosed, and the historical operation data of each associated battery can be processed to determine the fault diagnosis result of the battery to be diagnosed.

[0094] Exemplarily, the fault score of the battery to be diagnosed can be determined according to the actual operation data of the battery to be diagnosed and the historical operation data of each associated battery, and the fault diagnosis result of the battery to be diagnosed can be determined according to the fault score of the battery to be diagnosed and the target fault level of the battery to be diagnosed.

[0095] In the embodiment, by obtaining the actual operation data of the battery to be diagnosed and the battery resource set corresponding to the battery to be diagnosed, the target risk score of the battery to be diagnosed is determined according to the actual operation data of the battery to be diagnosed, and the sorting of the battery to be diagnosed and each associated battery in the battery resource set is determined according to the target risk score of the battery to be diagnosed and the historical risk score of each associated battery, and the target fault level of the battery to be diagnosed is determined according to the sorting of the battery to be diagnosed and each associated battery in the battery resource set, so that the fault diagnosis result of the battery to be diagnosed can be determined according to the target fault level. A variety of faults can be diagnosed at the same time, meeting the large-scale energy storage battery data analysis and processing demand, and the joint analysis of multiple data of the battery can be performed when diagnosing the fault, ensuring the diagnosis accuracy of the fault diagnosis. At the same time, since the battery fault diagnosis method provided by the embodiment of the application is executed through a cloud server, the local computing power is avoided during operation, meeting the efficient and real-time fault diagnosis demand. In addition, the safety and reliability of the battery use can be improved.

[0096] Figure 2 A flowchart for determining the target risk score of the battery to be diagnosed in the battery fault diagnosis method provided by the embodiment of the application.

[0097] In a possible implementation manner, referring to FIG. 10, Figure 2 When the target risk score of the battery to be diagnosed is determined according to the actual operation data of the battery to be diagnosed in step S102, the following steps can be performed, specifically including:

[0098] S201, respectively calculating the occurrence coefficient, severity coefficient and detection coefficient of the battery to be diagnosed according to the actual operation data.

[0099] Optionally, the occurrence degree coefficient, the severity coefficient and the detection degree coefficient of the battery to be diagnosed can be calculated according to the battery design data, the charging safety data, the discharging safety data, the environmental data, the short circuit data and the like in the actual operation data. The occurrence degree coefficient is used to indicate the occurrence frequency of the fault of the battery to be diagnosed, the severity coefficient is used to indicate the influence degree of the current fault of the battery to be diagnosed on the battery performance, and the detection degree coefficient is used to indicate the probability of the current fault of the battery to be diagnosed being successfully detected.

[0100] S202, determining the target risk score of the battery to be diagnosed according to the occurrence degree coefficient, the severity coefficient and the detection degree coefficient.

[0101] Optionally, after obtaining the occurrence degree coefficient, the severity coefficient and the detection degree coefficient, the target risk score of the battery to be diagnosed can be calculated according to the occurrence degree coefficient, the severity coefficient and the detection degree coefficient.

[0102] Exemplarily, after obtaining the occurrence degree coefficient, the severity coefficient and the detection degree coefficient, the target risk score RPN of the battery to be diagnosed can be calculated according to the occurrence degree coefficient, the severity coefficient and the detection degree coefficient by using the following formula (1):

[0103] RPN = O x S x D (1)

[0104] Wherein, O is the occurrence degree coefficient, S is the severity coefficient, and D is the detection degree coefficient.

[0105] The process of determining the target risk score of the battery to be diagnosed in the battery fault diagnosis method provided by the embodiment of the application is described above. It can be understood that the occurrence degree coefficient, the severity coefficient and the detection degree coefficient can be calculated in multiple ways. The following is an exemplary calculation method.

[0106] In one possible implementation, the process of calculating the occurrence degree coefficient in the above step S201 includes:

[0107] The occurrence degree coefficient is calculated according to the number of faults of the preset mode of the battery to be diagnosed in the preset historical period, the running time of the battery to be diagnosed in the preset historical period and the fault number threshold corresponding to the preset historical period.

[0108] Optionally, the occurrence degree coefficient O can be calculated by using the following formula (2):

[0109]

[0110] Wherein, N f is the number of faults of the preset mode of the battery to be diagnosed in the preset historical period, N tN is the running time of the battery to be diagnosed within a preset historical period max N is the running time of the battery to be diagnosed within a preset historical period

[0111] The occurrence degree coefficient of the battery to be diagnosed is calculated by the number of times of the preset mode of failure of the battery to be diagnosed within the preset historical period, the running time of the battery to be diagnosed within the preset historical period, and the failure time threshold corresponding to the preset historical period, which can ensure the accuracy of the obtained occurrence degree coefficient, thereby ensuring the diagnosis accuracy of the failure diagnosis.

[0112] In a possible implementation, the process of calculating the severity coefficient in the step S201 includes:

[0113] The severity coefficient is calculated according to the equipment performance loss information of the battery to be diagnosed within the preset historical period and the normal equipment performance information of the battery to be diagnosed.

[0114] Optionally, the severity coefficient S can be calculated by using the following formula (3):

[0115]

[0116] Wherein, L f L is the equipment performance loss information of the battery to be diagnosed within the preset historical period, L n N is the normal equipment performance information of the battery to be diagnosed.

[0117] The severity coefficient of the battery to be diagnosed is calculated by the equipment performance loss information of the battery to be diagnosed within the preset historical period and the normal equipment performance information of the battery to be diagnosed, which can ensure the accuracy of the obtained severity coefficient, thereby ensuring the diagnosis accuracy of the failure diagnosis.

[0118] In a possible implementation, the process of calculating the detection degree coefficient in the step S201 includes:

[0119] The detection degree coefficient is calculated according to the failure time of the battery to be diagnosed within the preset historical period and the normal detection time of the battery to be diagnosed within the preset historical period.

[0120] Optionally, the detection degree coefficient D can be calculated by using the following formula (4):

[0121]

[0122] Wherein, T f T is the failure time of the battery to be diagnosed within the preset historical period, T n N is the normal detection time of the battery to be diagnosed within the preset historical period.

[0123] The detection degree coefficient of the battery to be diagnosed is calculated based on the fault time of the battery to be diagnosed in a preset historical period and the normal detection time of the battery to be diagnosed in the preset historical period, so that the accuracy of the obtained detection degree coefficient is ensured, and the diagnosis accuracy of the fault diagnosis is ensured.

[0124] In a possible implementation, when the target fault level of the battery to be diagnosed is determined according to the order of the battery to be diagnosed and the associated batteries in the battery resource set in step S103, the following steps can be performed, specifically including:

[0125] The target fault level of the battery to be diagnosed is determined according to the total number of the battery to be diagnosed and the associated batteries, the order of the battery to be diagnosed and the associated batteries in the battery resource set, and a preset level division ratio.

[0126] Optionally, after the order sequence of the battery to be diagnosed and the associated batteries in the battery resource set is obtained, when the target fault level of the battery to be diagnosed is determined based on the order sequence of the battery to be diagnosed and the associated batteries in the battery resource set according to a statistical method, the target fault level of the battery to be diagnosed can be determined according to the total number of the battery to be diagnosed and the associated batteries, the order of the battery to be diagnosed and the associated batteries in the battery resource set, and a preset level division ratio.

[0127] For example, the distribution of the risk scores corresponding to the battery to be diagnosed and the associated batteries is determined according to the total number of the battery to be diagnosed and the associated batteries and the order of the battery to be diagnosed and the associated batteries in the battery resource set, so that the target fault level of the battery to be diagnosed can be determined according to the preset level division ratio. The preset level division ratio is used to indicate the distribution ratio of the priority of the fault, and can be obtained by user pre-configuration.

[0128] The target fault level of the battery to be diagnosed is determined according to the total number of the battery to be diagnosed and the associated batteries, the order of the battery to be diagnosed and the associated batteries in the battery resource set, and a preset level division ratio, so that the diagnosis accuracy of the battery fault diagnosis method provided in the embodiments of the present application is ensured.

[0129] Figure 3 A flowchart for determining the fault diagnosis result of the battery to be diagnosed in the battery fault diagnosis method provided in the embodiments of the present application.

[0130] In a possible implementation, referring to Figure 3 As shown in the figure, when the fault diagnosis result of the battery to be diagnosed is determined according to the target fault level of the battery to be diagnosed in step S104, the following steps are included:

[0131] S301, determine a fault score of the battery to be diagnosed according to actual operation data of the battery to be diagnosed and historical operation data of each associated battery.

[0132] Optionally, the fault score of the battery to be diagnosed can be determined according to the actual operation data of the battery to be diagnosed and the historical operation data of each associated battery in combination with a preset algorithm. The preset algorithm can be a fault diagnosis algorithm based on a sparse data observer.

[0133] S302, determine a fault diagnosis result of the battery to be diagnosed according to the target fault level of the battery to be diagnosed and the fault score of the battery to be diagnosed.

[0134] Optionally, after obtaining the fault score of the battery to be diagnosed, fault analysis can be performed according to the target fault level of the battery to be diagnosed and the fault score of the battery to be diagnosed to obtain the fault diagnosis result of the battery to be diagnosed.

[0135] For example, the cloud server can store preconfigured fault diagnosis rules. The fault diagnosis result of the battery to be diagnosed can be obtained by fault matching according to the target fault level of the battery to be diagnosed and the fault score of the battery to be diagnosed. For example, if the fault score of the battery to be diagnosed indicates that the battery to be diagnosed has an overheating fault, and the target fault level of the battery to be diagnosed indicates that the overheating fault will have a serious impact on the use of the battery to be diagnosed and is not easy to be detected, the cloud server will diagnose the fault as a high-level fault, and the high-level fault is taken as the fault diagnosis result of the battery to be diagnosed. If the target fault level of the battery to be diagnosed indicates that the overheating fault will have a low impact on the use of the battery to be diagnosed and is easy to be detected, the cloud server will diagnose the fault as a low-level fault, and the low-level fault is taken as the fault diagnosis result of the battery to be diagnosed.

[0136] By using the actual operation data of the battery to be diagnosed and the historical operation data of each associated battery, the fault score of the battery to be diagnosed is determined, and according to the target fault level of the battery to be diagnosed and the fault score of the battery to be diagnosed, the fault diagnosis result of the battery to be diagnosed is determined. This can diagnose multiple faults at the same time, meet the demand of large-scale energy storage battery data analysis and processing, and can also perform joint analysis of multiple data of the battery during fault diagnosis, thereby ensuring the diagnosis accuracy of fault diagnosis.

[0137] Figure 4 A flowchart for determining the fault score of the battery to be diagnosed in the battery fault diagnosis method provided by the embodiments of the present application is shown.

[0138] In one possible implementation, refer to Figure 4As shown, when determining the fault score of the battery to be diagnosed according to the actual operation data of the battery to be diagnosed and the historical operation data of each associated battery in step S301, the following steps are included:

[0139] S401, generating a distance matrix according to the historical operation data of each associated battery, and determining a low-density model according to the distance matrix.

[0140] Exemplarily, the battery voltage sequence V can be obtained according to the historical operation data of each associated battery, that is, V = {v1, v2, …, v m}, where m is the length of the voltage sequence, and a set O of k objects is randomly extracted from the battery voltage sequence V, that is, O = {O1, O2, …, O k}, and the objects in O are taken as observers. The number of observers is estimated according to statistical sampling calculation.

[0141] Wherein, the average error of non-replacement sampling can be obtained according to the following formula (5):

[0142]

[0143] Wherein, the limit error can be obtained according to the following formula (6):

[0144]

[0145] Wherein, the number of observers can be obtained according to the following formula (7):

[0146]

[0147] Wherein, Δ is the error, σ is the standard deviation, Δ = 0.1σ, Z is the confidence coefficient, and exemplarily, when the confidence level is 95%, Z = 1.96.

[0148] Exemplarily, the distance matrix D is created by measuring the distance between each observer and each voltage data, that is, D = {D i，j , i ∈ (1, 2, …, m), j ∈ (1, 2, …, k)}, and the distance matrix D is sorted and simplified to an observation matrix I, which stores the identifiers of the nearest x observers of each voltage data in the battery voltage sequence, where x is a robustness parameter, usually taking a value of 3-10, and will not cause a large deviation to the abnormality degree value. At this time, the distance matrix D satisfies D i，j = d(V i , O j ), where d(·, ·) is the Euclidean distance.

[0149] Exemplarily, the low-density model P is created by counting the number of occurrences of each observer in the observation matrix I, i.e. P = {P j , j e (1, 2,..., k)} is deleted when the observer is not observed for q times, which can effectively prevent the selection of outliers as observers, and only representative data points are used to construct the low-density model. It can be understood that after deleting the idle observers, there are only k act active observers left. Wherein, q = Q ρ (P), Q ρ (·) is a quantile function. In general, it is known from experience that a better result can be obtained when p = 0.3.

[0150] S402, determine the distance information of the actual running data of the battery to be diagnosed and the low-density model.

[0151] Exemplarily, the distance between the actual running data of the battery to be diagnosed and the low-density model P obtained in the above step S402 is calculated to obtain a distance array with a length of k act , and the identifiers of the nearest x observers are stored in the observation array.

[0152] S403, determine the fault score of the battery to be diagnosed according to the distance information.

[0153] Exemplarily, according to the distance array obtained in the above step S402, the average distance between the actual running data of the battery to be diagnosed and the distance array is calculated, and the abnormality degree y i is obtained according to the following formula (8):

[0154]

[0155] Exemplarily, the abnormality degree y i is taken as the fault score of the battery to be diagnosed.

[0156] It can be understood that the abnormality degree of the battery to be diagnosed can be obtained by evaluating the deviation of the observed voltage relative to its nearest observer object, so that whether the battery is faulty can be judged according to the abnormality degree of the voltage sequence. At the same time, the establishment of the low-density model for each battery to be diagnosed can effectively overcome the adverse effects caused by the inconsistency of the batteries, and avoid the influence of the obvious difference in the voltage of the battery to be diagnosed caused by aging and abuse operation on the diagnosis accuracy.

[0157] It can be understood that for the abnormality degree obtained in the above step S403, when the voltage at a certain moment deviates from the entire voltage sequence, the abnormality degree is higher, which can be regarded as an outlier, indicating that the battery to be diagnosed has a fault. When the abnormality degree of the voltage sequence is close to 0, it means that the voltage is normal, i.e. the battery to be diagnosed is normal.

[0158] Based on the same inventive concept, the application also provides a battery fault diagnosis device corresponding to the battery fault diagnosis method. Since the device solves problems in the same principle as the above-mentioned battery fault diagnosis method, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described here.

[0159] Figure 5 A structural schematic diagram of a battery fault diagnosis device provided in the application is shown in FIG. 5. Figure 5 The device is applied to a cloud server, and the device comprises an acquisition module 501 and a determination module 502.

[0160] The acquisition module 501 is configured to acquire actual operation data of a battery to be diagnosed and a battery resource set corresponding to the battery to be diagnosed, wherein the battery resource set comprises historical risk scores and historical operation data of each associated battery of the battery to be diagnosed, and the associated battery has the same portrait as the battery to be diagnosed.

[0161] The determination module 502 is configured to determine a target risk score of the battery to be diagnosed according to the actual operation data of the battery to be diagnosed.

[0162] The determination module 502 is configured to determine the order of the battery to be diagnosed and each associated battery in the battery resource set according to the target risk score of the battery to be diagnosed and the historical risk scores of each associated battery, determine the target fault level of the battery to be diagnosed according to the order of the battery to be diagnosed and each associated battery in the battery resource set, and add the target risk score and the actual operation data of the battery to be diagnosed to the battery resource set.

[0163] The determination module 502 is configured to determine a fault diagnosis result of the battery to be diagnosed according to the target fault level of the battery to be diagnosed.

[0164] In a possible implementation, the determination module 502 is specifically configured to:

[0165] According to the actual operation data, the occurrence coefficient, the severity coefficient and the detection coefficient of the battery to be diagnosed are calculated respectively.

[0166] According to the occurrence coefficient, the severity coefficient and the detection coefficient, the target risk score of the battery to be diagnosed is determined.

[0167] In a possible implementation, the determination module 502 is specifically configured to:

[0168] According to the number of times of the battery to be diagnosed in the preset mode of fault in the preset historical period, the running time of the battery to be diagnosed in the preset historical period and the fault number threshold corresponding to the preset historical period, the occurrence coefficient is calculated.

[0169] In a possible implementation, the determining module 502 is specifically configured to:

[0170] According to the device performance loss information of the battery to be diagnosed within a preset historical period and the normal device performance information of the battery to be diagnosed, the severity coefficient is calculated.

[0171] In a possible implementation, the determining module 502 is specifically configured to:

[0172] According to the fault time of the battery to be diagnosed within a preset historical period and the normal detection time of the battery to be diagnosed within the preset historical period, the detection degree coefficient is calculated.

[0173] In a possible implementation, the determining module 502 is specifically configured to:

[0174] According to the total number of the battery to be diagnosed and each associated battery, the ranking of the battery to be diagnosed and each associated battery in the battery resource set, and the preset grade division ratio, the target fault grade of the battery to be diagnosed is determined.

[0175] In a possible implementation, the determining module 502 is specifically configured to:

[0176] According to the actual running data of the battery to be diagnosed and the historical running data of each associated battery, the fault score of the battery to be diagnosed is determined.

[0177] According to the target fault grade of the battery to be diagnosed and the fault score of the battery to be diagnosed, the fault diagnosis result of the battery to be diagnosed is determined.

[0178] In a possible implementation, the determining module 502 is specifically configured to:

[0179] According to the historical running data of each associated battery, a distance matrix is generated, and a low-density model is determined according to the distance matrix.

[0180] The distance information between the actual running data of the battery to be diagnosed and the low-density model is determined.

[0181] According to the distance information, the fault score of the battery to be diagnosed is determined.

[0182] The description of the processing procedure of each module in the apparatus and the interaction procedure between the modules can refer to the related description in the above method embodiments, and will not be described in detail here.

[0183] The embodiment of the application further provides an electronic device 600, as shown in Figure 6 , and the apparatus includes the above-described determining module 502. Figure 6A schematic diagram of the structure of an electronic device provided in an embodiment of the present application includes: a processor 601, a memory 602, and optionally, a bus 603. The memory 602 stores machine-readable instructions executable by the processor 601 (for example, Figure 5 The device acquires the execution instructions corresponding to the module 501 and the determination module 502, etc.), when the electronic device 600 is running, the processor 601 communicates with the memory 602 through the bus 603, and when the machine-readable instructions are executed by the processor 601, the steps of the above-mentioned battery fault diagnosis method are performed.

[0184] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned battery fault diagnosis method are executed.

[0185] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the method embodiment, and will not be repeated in this application. In the several embodiments provided in this application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0186] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. When the functions are realized in the form of software function units and sold or used as an independent product, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0187] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A battery failure diagnosis method characterized by comprising: The application is applied to a cloud server, and comprises: obtaining actual operation data of a battery to be diagnosed and a battery resource set corresponding to the battery to be diagnosed, the battery resource set comprising historical risk scores and historical operation data of each associated battery of the battery to be diagnosed, the associated battery having the same portrait as the battery to be diagnosed; determining a target risk score of the battery to be diagnosed according to the actual operation data of the battery to be diagnosed; determining a ranking of the battery to be diagnosed and each associated battery in the battery resource set according to the target risk score of the battery to be diagnosed and the historical risk scores of each associated battery, determining a target failure level of the battery to be diagnosed according to the ranking of the battery to be diagnosed and each associated battery in the battery resource set, and adding the target risk score and the actual operation data of the battery to be diagnosed to the battery resource set; determining a failure diagnosis result of the battery to be diagnosed according to the target failure level of the battery to be diagnosed.

2. The battery failure diagnosis method according to claim 1, characterized by, The method comprises the following steps: calculating an occurrence coefficient, a severity coefficient and a detection coefficient of the battery to be diagnosed according to the actual operation data; determining the target risk score of the battery to be diagnosed according to the occurrence coefficient, the severity coefficient and the detection coefficient.

3. The battery failure diagnosis method according to claim 2, characterized by, The method comprises the following steps: calculating the occurrence coefficient according to the number of times of a preset mode of failure of the battery to be diagnosed in a preset historical period, the operation time length of the battery to be diagnosed in the preset historical period and a failure number threshold corresponding to the preset historical period.

4. The battery failure diagnosis method according to claim 2, characterized by, The method comprises the following steps: calculating the severity coefficient according to the device performance loss information of the battery to be diagnosed in the preset historical period and normal device performance information of the battery to be diagnosed.

5. The battery failure diagnosis method according to claim 2, characterized by, The method comprises the following steps: calculating the detection coefficient according to the failure time of the battery to be diagnosed in the preset historical period and the normal detection time of the battery to be diagnosed in the preset historical period.

6. The battery failure diagnosis method according to any one of claims 1 to 5, characterized by, The method comprises the following steps: determining the target failure level of the battery to be diagnosed according to the total number of the battery to be diagnosed and each associated battery, the ranking of the battery to be diagnosed and each associated battery in the battery resource set and a preset level division ratio.

7. The battery failure diagnosis method according to any one of claims 1 to 5, characterized by, The method comprises the following steps: determining a failure score of the battery to be diagnosed according to the actual operation data of the battery to be diagnosed and the historical operation data of each associated battery; determining the failure diagnosis result of the battery to be diagnosed according to the target failure level of the battery to be diagnosed and the failure score of the battery to be diagnosed.

8. The battery failure diagnosis method according to claim 7, characterized by, The method comprises the following steps: According to historical operation data of each associated battery, a distance matrix is generated, and a low-density model is determined according to the distance matrix; Distance information between actual operation data of the battery to be diagnosed and the low-density model is determined; According to the distance information, a fault score of the battery to be diagnosed is determined.

9. A battery failure diagnosis device characterized by comprising: Applied to a cloud server, comprising: An acquisition module is configured to acquire actual operation data of a battery to be diagnosed and a battery resource set corresponding to the battery to be diagnosed, wherein the battery resource set includes historical risk scores and historical operation data of each associated battery of the battery to be diagnosed, and the associated battery has the same portrait as the battery to be diagnosed; A determination module is configured to determine a target risk score of the battery to be diagnosed according to the actual operation data of the battery to be diagnosed; A determination module is configured to determine a ranking of the battery to be diagnosed and each associated battery in the battery resource set according to the target risk score of the battery to be diagnosed and the historical risk scores of each associated battery, determine a target fault level of the battery to be diagnosed according to the ranking of the battery to be diagnosed and each associated battery in the battery resource set, and add the target risk score and actual operation data of the battery to be diagnosed to the battery resource set; A determination module is configured to determine a fault diagnosis result of the battery to be diagnosed according to the target fault level of the battery to be diagnosed.

10. An electronic device, comprising: Comprising: A processor and a memory, the memory stores machine readable instructions executable by the processor, when the electronic device is running, the processor executes the machine readable instructions to perform the steps of the battery fault diagnosis method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that The computer readable storage medium stores a computer program, and the computer program is run by the processor to perform the steps of the battery fault diagnosis method according to any one of claims 1 to 8.

Images