Method for detecting battery fault, apparatus, device, and medium

Abstract

A method for detecting a battery fault, an apparatus, a device, and a medium. The method comprises: acquiring a plurality of measurement parameters for one group of batteries and an equivalent circuit model corresponding to physical characteristics of the group of batteries (202). The method also comprises: on the basis of the plurality of measurement parameters and the equivalent circuit model, determining a plurality of estimated circuit parameters of the equivalent circuit model that correspond to the plurality of measurement parameters (204). The method further comprises detecting a fault in the group of batteries on the basis of the plurality of estimated circuit parameters (206). A battery fault can be quickly determined on the basis of measurement parameters of batteries, so that the complexity of battery fault detection is reduced, thereby preventing damage to the batteries or an energy storage apparatus comprising same, and improving the battery safety.

Description

Methods, apparatus, equipment, and media for detecting battery faults. Technical Field

[0001] The embodiments of this disclosure generally relate to the field of battery technology, and more specifically to methods, apparatus, devices, and media for detecting battery faults. Background Technology

[0002] A battery is a device that stores and releases electrical energy, typically composed of electrodes, an electrolyte, and other components. With the development of battery technology, various types of batteries have emerged. For example, lithium-ion batteries, with their small size, high voltage, and large charge storage capacity, have become a major battery product. They are not only used in various portable electronic products but are now also used in electric vehicles. With their cost decreasing significantly, lithium-ion batteries have become the primary carrier for realizing new energy technologies.

[0003] With the increasing use of batteries, some batteries are being used in energy storage systems to store electrical energy and provide it when needed. For example, a battery energy storage system (BESS) utilizes batteries to store electrical energy. Various types of batteries can be used in this system to store electrical energy. Battery energy storage systems have been used in many fields, such as as backup power sources or for regulating electrical loads at different times.

[0004] Summary of the Invention

[0005] Embodiments of this disclosure provide a method, apparatus, device, and medium for detecting battery faults.

[0006] According to a first aspect of this disclosure, a method for detecting battery faults is provided. The method includes acquiring multiple measurement parameters for a group of batteries and an equivalent circuit model corresponding to the physical characteristics of the group of batteries. The method further includes determining multiple estimated circuit parameters of the equivalent circuit model corresponding to the multiple measurement parameters based on the multiple measurement parameters and the equivalent circuit model. The method also includes detecting faults in the group of batteries based on the multiple estimated circuit parameters.

[0007] Based on the above method, embodiments of this disclosure can measure the measurement parameters of a group of batteries, and then use an equivalent circuit model for that group of batteries to determine multiple estimated circuit parameters corresponding to the measurement parameters. These multiple estimated circuit parameters can reflect the state of the batteries. Therefore, these multiple estimated circuit parameters can be used to detect faults in the group of batteries. Since the equivalent circuit model of the batteries is used directly, there is no need to process the actual physical parameters of the batteries, reducing the complexity of battery fault detection and increasing the speed of fault detection. This allows for early warning, preventing damage to the batteries or energy storage devices including the batteries, and improving battery safety.

[0008] In some embodiments of the first aspect, the plurality of measurement parameters include a first measurement parameter and a second measurement parameter, and determining a plurality of estimated circuit parameters of an equivalent circuit model corresponding to the plurality of measurement parameters includes: generating a predicted parameter corresponding to the second measurement parameter using the equivalent circuit model based on the first measurement parameter; determining the difference between the second measurement parameter and the predicted parameter; and determining the plurality of estimated circuit parameters in response to the difference exceeding a threshold. In this manner, the difference between the measurement parameter and the predicted parameter is used to further determine whether it is necessary to determine the plurality of estimated circuit parameters, thereby avoiding fault detection of normal batteries and reducing the amount of data processing.

[0009] In some embodiments of the first aspect, the first measurement parameter is either voltage or current, and the second measurement parameter is either voltage or current. In this way, rapid fault detection can be achieved using either the voltage or current parameter.

[0010] In some embodiments of the first aspect, generating prediction parameters corresponding to the second measurement parameters using an equivalent circuit model includes: determining multiple circuit parameters for the equivalent circuit model; and generating prediction parameters based on the multiple circuit parameters by inputting the first measurement parameter into the equivalent circuit model. In this manner, the prediction parameters can be calculated quickly and accurately by utilizing the equivalent circuit model.

[0011] In some embodiments of the first aspect, determining the plurality of estimated circuit parameters includes: determining the plurality of estimated circuit parameters corresponding to the plurality of measured parameters by inputting the plurality of measured parameters into an equivalent circuit model. In this manner, the predicted parameters can be quickly calculated using the equivalent circuit model.

[0012] In some embodiments of the first aspect, detecting a fault in a group of batteries includes: mapping a plurality of estimated circuit parameters to a first target location in a first predetermined space; determining a first distance between the first target location and a first reference location in the first predetermined space for a group of batteries, the first reference location corresponding to a group of batteries in a normal state; and determining that a group of batteries has faulted in response to the first distance being greater than a first threshold distance. This method, by calculating the distance to the location of a normal battery to determine whether a battery has faulted, improves the accuracy and convenience of fault detection, and increases the efficiency of fault detection.

[0013] In some embodiments of the first aspect, detecting a fault in a group of batteries further includes: determining that a group of batteries is normal in response to a first distance being less than or equal to a first threshold distance. In this way, normal batteries can be quickly identified through distance comparison.

[0014] In some embodiments of the first aspect, detecting a fault in a group of batteries includes: determining multiple physical parameters of a multi-physics model of the group of batteries corresponding to the multiple estimated circuit parameters based on multiple estimated circuit parameters; and detecting a fault in the group of batteries based on the multiple physical parameters. This method utilizes the physical parameters of the physical model to detect battery faults, improving the accuracy of fault detection and avoiding false detections.

[0015] In some embodiments of the first aspect, detecting a fault in a group of batteries based on multiple physical parameters includes: mapping the multiple physical parameters to a second target location in a second predetermined space; determining a second distance between the second target location and a second reference location in the second predetermined space for a group of batteries, the second reference location corresponding to a group of batteries in a normal state; and determining that a group of batteries has faulted in response to the second distance being greater than a second threshold distance. In this manner, battery faults can be detected using the location of physical parameters within a predetermined space and the distance between the physical parameters of normal batteries within the physical space, improving the convenience and accuracy of fault detection and increasing detection efficiency.

[0016] In some embodiments of the first aspect, detecting a fault in a group of batteries based on the plurality of physical parameters further includes: determining that a group of batteries is normal in response to a second distance being less than or equal to a second threshold distance. This method allows for the rapid detection of normal batteries.

[0017] In some embodiments of the first aspect, where the predicted parameter is a first predicted parameter, and based on multiple physical parameters, detecting a fault in a group of batteries includes: generating a second predicted parameter corresponding to the first measured parameter using an equivalent circuit model based on a second measured parameter; and detecting the type of fault in the group of batteries based on the first measured parameter, the second measured parameter, the first predicted parameter, the second predicted parameter, and the multiple physical parameters. This method, after determining that a battery fault has occurred, can further determine the type of fault, improving fault detection and providing useful information for subsequent fault handling, thus enhancing the user experience.

[0018] In some embodiments of the first aspect, detecting the type of fault in a group of batteries based on a first measurement parameter, a second measurement parameter, a first prediction parameter, a second prediction parameter, and multiple physical parameters includes: inputting the first measurement parameter, the second measurement parameter, the first prediction parameter, and the second prediction parameter into each of multiple prediction sub-models to determine the difference between the measurement parameter and the prediction parameter, wherein the multiple sub-models include sub-models corresponding to the fault types of the batteries; and determining the fault type of the group of batteries based on the difference and the multiple physical parameters. In this manner, by utilizing the detection parameter, the prediction parameter, and the actual physical parameters, the type of fault can be accurately detected, improving the accuracy of fault type identification and enhancing the user experience.

[0019] In a second aspect of this disclosure, an apparatus for detecting battery faults is provided. The apparatus includes an acquisition module configured to acquire multiple measurement parameters for a group of batteries and an equivalent circuit model corresponding to the physical characteristics of the group of batteries; a circuit parameter determination module configured to determine multiple estimated circuit parameters of the equivalent circuit model corresponding to the multiple measurement parameters based on the multiple measurement parameters and the equivalent circuit model; and a fault detection module configured to detect faults in the group of batteries based on the multiple estimated circuit parameters.

[0020] In a third aspect of this disclosure, an electronic device is provided, including at least one processor; and a storage device for storing at least one program, which, when executed by the at least one processor, causes the at least one processor to perform the method according to any one of the first aspects of this disclosure.

[0021] In a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the method described in any of the first aspects of this disclosure.

[0022] In a fifth aspect of this disclosure, a computer program product is provided. The computer program product includes a computer program that, when executed by a processor, implements the method described according to any one of the first aspects of this disclosure.

[0023] It should be understood that the content described in this section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0024] The above and other objects, features and advantages of this disclosure will become more apparent from the accompanying drawings, in which like reference numerals generally denote like parts.

[0025] Figure 1 illustrates a schematic diagram of an example environment in which the devices and / or methods of the embodiments of this disclosure may be implemented;

[0026] Figure 2 illustrates a flowchart of an example method for detecting battery faults according to an embodiment of the present disclosure;

[0027] Figure 3 illustrates a schematic diagram of an example of a multiphysics model according to an embodiment of the present disclosure;

[0028] Figure 4 illustrates a schematic diagram of an example of an equivalent circuit model according to an embodiment of the present disclosure;

[0029] Figure 5 illustrates a schematic diagram of an example workflow for detecting battery faults according to an embodiment of the present disclosure;

[0030] Figure 6 illustrates a schematic diagram of an example of a cluster of circuit parameters according to an embodiment of the present disclosure;

[0031] Figure 7 illustrates a schematic diagram of an example of battery variation according to an embodiment of the present disclosure;

[0032] Figure 8 illustrates a schematic diagram of an example of a fault diagnosis module according to an embodiment of the present disclosure;

[0033] Figure 9 illustrates a schematic block diagram of an apparatus for detecting battery faults according to an embodiment of the present disclosure;

[0034] Figure 10 illustrates a schematic block diagram of an example device suitable for implementing embodiments of the present disclosure.

[0035] In the various figures, the same or corresponding reference numerals indicate the same or corresponding parts.

[0036] List of reference numerals in the attached diagram:

[0037] 102: Multiple measurement parameters

[0038] 104: Computing equipment

[0039] 106: Equivalent Circuit Model

[0040] 108: Multiple estimated circuit parameters

[0041] 110: A battery pack malfunction

[0042] 202: Obtain multiple measurement parameters for a group of batteries and an equivalent circuit model corresponding to the physical characteristics of the group of batteries.

[0043] 204: Based on multiple measurement parameters and an equivalent circuit model, determine multiple estimated circuit parameters of the equivalent circuit model corresponding to the multiple measurement parameters.

[0044] 206: Detecting faults in a group of batteries based on multiple estimated circuit parameters.

[0045] 302: Materials Yard

[0046] 304: Chemical Field

[0047] 306: Warm-up

[0048] 308: Electric Field

[0049] 310: Cathode region

[0050] 312: Anode region

[0051] 314: Separation Region

[0052] 402: Battery

[0053] 404: Resistor

[0054] 406: Resistor

[0055] 408: Resistor

[0056] 410: Capacitor

[0057] 412: Capacitor

[0058] 414: Current

[0059] 416: Voltage

[0060] 502: Offline module

[0061] 504: Online module

[0062] 506: Multiple Physics Model

[0063] 508: Internal characteristics of the battery

[0064] 510: Equivalent Circuit Model

[0065] 512: Multiple estimated circuit parameters

[0066] 514: Fault Diagnosis Module

[0067] 516: Early Protection

[0068] 518: Information on normal or abnormal scenarios

[0069] 520: Historical Data

[0070] 522: Measurement parameters

[0071] 602: Cluster Area

[0072] 604: Cluster Area

[0073] 606: Cluster Area

[0074] 608: Cluster Area

[0075] 702: Area

[0076] 704: Area

[0077] 706: Area

[0078] 802: Input Data

[0079] 804: Input data

[0080] 806: Sub-model

[0081] 808: Sub-model

[0082] 810: Sub-model

[0083] 812: Sub-model

[0084] 814: Failure Probability Model

[0085] 816: Multiple Probabilities

[0086] 818: Multiple physical parameters

[0087] 900: Device

[0088] 902: Get Module

[0089] 904: Circuit Parameter Determination Module

[0090] 906: Fault Detection Module

[0091] 1000: Equipment

[0092] 1001: CPU

[0093] 1002: ROM

[0094] 1003: RAM

[0095] 1004: Bus

[0096] 1005: I / O Interface

[0097] 1006: Input Unit

[0098] 1007: Output Unit

[0099] 1008: Storage Unit

[0100] 1009: Communication Unit Detailed Implementation

[0101] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure. Nouns and pronouns relating to persons in this patent application are not limited to specific genders.

[0102] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0103] As mentioned above, battery energy storage systems can store electrical energy and provide it to users. However, batteries may malfunction during use. Battery malfunctions often lead to serious damage, and the root cause is often difficult to determine. In most cases, battery malfunctions cause fire damage, and due to their destructive nature, determining the root cause of the battery energy storage system malfunction afterward is extremely difficult.

[0104] To address these issues, some solutions utilize fire suppression systems with gas / temperature sensors to prevent damage to battery storage systems caused by battery failures. However, the gas and temperature sensors in these systems lack sufficient sensitivity to faults, meaning that once measured values ​​exceed thresholds, a failure has already occurred and is unavoidable. Furthermore, this fire suppression system can only prevent the spread of the accident but cannot salvage the infrastructure, including the batteries. Additionally, while battery management systems (BMS) can manage battery charging and discharging, their limited battery monitoring coverage restricts their ability to prevent failures and cannot accurately and promptly identify battery malfunctions.

[0105] Therefore, embodiments of this disclosure propose a method for detecting battery faults. In this method, a computing device first acquires multiple measurement parameters for a group of batteries and an equivalent circuit model corresponding to the physical characteristics of the group of batteries. Then, the computing device uses the multiple measurement parameters and the equivalent circuit model to calculate multiple estimated circuit parameters of the equivalent circuit model corresponding to the multiple measurement parameters. Finally, the computing device uses the obtained multiple estimated circuit parameters to detect faults in the group of batteries. Through this method, embodiments of this disclosure can measure the measurement parameters of a group of batteries in real time, and then use the equivalent circuit model for the group of batteries to determine multiple estimated circuit parameters corresponding to the measurement parameters. These multiple estimated circuit parameters can reflect the state of the battery. Therefore, these multiple estimated circuit parameters can be used to detect faults in the group of batteries. Since the equivalent circuit model of the battery is used directly, the actual physical parameters of the battery do not need to be processed, reducing the complexity of battery fault detection and increasing the speed of fault detection. This allows for early warning, preventing damage to the battery or energy storage device including the battery, and improving battery safety.

[0106] Embodiments of the present disclosure will now be described in further detail with reference to the accompanying drawings. Figure 1 illustrates an example environment in which the devices and / or methods of the embodiments of the present disclosure may be implemented. In environment 100, computing device 104 is used to detect whether a group of batteries has malfunctioned based on relevant battery data.

[0107] Examples of computing device 104 include, but are not limited to, personal computers, server computers, handheld or laptop devices, mobile devices (such as mobile phones, personal digital assistants (PDAs), media players, etc.), multiprocessor systems, consumer electronics, minicomputers, mainframe computers, and distributed computing environments that include any of the above systems or devices.

[0108] As shown in Figure 1, computing device 104 receives multiple measurement parameters 102 for a group of batteries. For example, the multiple measurement parameters 102 include at least the voltage and current of the group of batteries. In one example, the group of batteries includes a single battery cell. In another example, the group of batteries includes multiple batteries, such as three or four batteries. In yet another example, the group of batteries can be all the batteries in a battery energy storage system. The batteries can be any suitable type, such as lithium-ion batteries, solid-state batteries, or hydrogen fuel cells.

[0109] The computing device 104 can also obtain an equivalent circuit model 106 corresponding to the battery bank. Typically, the physical characteristics of a battery bank are described using a multiphysics model. However, multiphysics models include too many parameters, such as material, chemical, thermal, and electronic parameters of the battery bank. Because the number of parameters is very large, it is not suitable to directly use the multiphysics model to detect battery faults. To reduce the complexity of the battery fault detection process, an equivalent circuit model 106 corresponding to the multiphysics model can be used. This equivalent circuit model 106 can be used to simulate the physical characteristics of a battery bank. In one example, the equivalent circuit model is a second-order RC model. In another example, the equivalent circuit model is a first-order RC model. In yet another example, the equivalent circuit model is an internal resistance model. The above examples are only for describing this disclosure and are not intended to limit the specific scope of this disclosure. Those skilled in the art can use any suitable equivalent circuit model as needed.

[0110] Figure 1 illustrates computing device 104 receiving equivalent circuit model 106 and multiple measurement parameters 102, which is merely an example. The equivalent circuit model 106 and the multiple measurement parameters may also be stored in the local memory of computing device 104. Additionally, the multiple measurement parameters 102 may be obtained in real time.

[0111] Next, the computing device 104 can use the acquired multiple measurement parameters 102 and the equivalent circuit model 106 to calculate multiple estimated circuit parameters 108 for the equivalent circuit model. The process of calculating the multiple estimated circuit parameters 108 will be described later. In some embodiments, after the multiple measurement parameters 102 have been processed by the equivalent circuit model, if it is determined that the multiple measurement parameters 102 are incorrect, the computing device 104 needs to calculate the multiple estimated circuit parameters 108 of the equivalent circuit model 106; if it is determined that the multiple measurement parameters 102 are correct, the multiple estimated circuit parameters 108 of the equivalent circuit model 106 are not calculated. In some embodiments, the computing device 104 can calculate the estimated circuit parameters for all acquired measurement parameters. The above examples are only for describing this disclosure and are not intended to specifically limit this disclosure.

[0112] After obtaining multiple estimated circuit parameters 108, the computing device 104 can further process the estimated circuit parameters 108 to detect a fault 110 in a group of batteries. For example, the computing device 104 can map the multiple estimated circuit parameters 108 to a predetermined space, such as a one-dimensional space or a multi-dimensional space. Then, it calculates the distance between the position of the multiple estimated parameters 108 in the space and the position of the circuit parameters of a normal battery in the space. The distance is then used to determine whether the group of batteries is faulty. For example, if the distance is greater than a threshold distance, the group of batteries is considered faulty. If the distance is less than or equal to the threshold distance, the group of batteries is considered not faulty.

[0113] In some embodiments, the computing device 104 may further determine the type of battery fault based on multiple estimated circuit parameters and multiple measurement parameters to clarify the specific battery fault. Additionally, after determining that the battery pack is faulty, alarm information can be provided to the user. For example, an alarm can be provided by emitting an audible message or displaying a text message. In one example, an alarm can be provided by emitting a buzzer sound. In another example, a display screen can be used to show that the battery pack is faulty. The above examples are merely illustrative of this disclosure and not intended to limit its specific scope. If the type of battery fault can be determined, the computing device 104 may also provide a corresponding solution to handle the fault.

[0114] Using this method, embodiments of the present disclosure can measure the measurement parameters of a group of batteries, and then use an equivalent circuit model for that group of batteries to determine multiple estimated circuit parameters corresponding to the measurement parameters. These multiple estimated circuit parameters can reflect the state of the batteries. Therefore, these multiple estimated circuit parameters can be used to detect faults in the group of batteries. Because the equivalent circuit model of the batteries is used directly, the actual physical parameters of the batteries do not need to be processed, reducing the complexity of battery fault detection and increasing the speed of fault detection. This allows for early warning, preventing damage to the batteries or energy storage devices including the batteries, and improving battery safety.

[0115] The above description, with reference to FIG1, illustrates an example environment in which the devices and / or methods according to embodiments of the present disclosure may be implemented. The following description, with reference to FIG2, is a flowchart of an example method for detecting battery failure according to embodiments of the present disclosure. The process shown in FIG2 can be performed at the computing device 104 shown in FIG1 or any other suitable computing device.

[0116] At box 202, computing device 104 acquires multiple measured parameters for a group of batteries and an equivalent circuit model corresponding to the physical characteristics of the group of batteries. To ensure the safety of the battery group, these batteries need to be tested, and the detected parameters are transmitted to computing device 104 to detect whether a fault has occurred. Additionally, this set of parameters can be parameters measured in real time. This set of parameters may include one or more of the measured current, voltage, capacity, and temperature of the battery group.

[0117] At box 204, computing device 104 determines multiple estimated circuit parameters of the equivalent circuit model corresponding to the multiple measurement parameters based on multiple measurement parameters and the equivalent circuit model. After obtaining the multiple measurement parameters of the battery pack, in order to detect battery faults, it is also necessary to obtain the equivalent circuit model of the battery pack. The equivalent circuit model of the battery pack can be determined based on the physical characteristics of the battery pack or a multi-physics model of the battery pack. In this case, the equivalent circuit model has corresponding predetermined parameter values. For example, when the equivalent circuit model is a second-order RC model, the equivalent circuit has current and voltage corresponding to the battery, and has corresponding resistance values, capacitance values, and voltage values ​​for the resistors.

[0118] In some embodiments, the plurality of measurement parameters includes at least two measurement parameters, which may be referred to as the first measurement parameter and the second measurement parameter, respectively. When determining the plurality of estimated circuit parameters using an equivalent circuit model, the computing device can input the first measurement parameter into the equivalent circuit model to generate a predicted parameter corresponding to the second measurement parameter. For example, if the first measurement parameter is a measured current and the second measurement parameter is a measured voltage, a predicted voltage corresponding to the measured voltage can be generated by inputting the current into the equivalent circuit model. If the first measurement parameter is a measured voltage and the second measurement parameter is a measured current, a predicted current corresponding to the measured current can be generated by inputting the measured voltage into the equivalent circuit model. Next, the computing device further determines the difference between the second measurement parameter and the predicted parameter. For example, it determines the difference between the measured voltage and the predicted voltage, or the difference between the measured current and the predicted current.

[0119] The computing device 104 further checks whether the difference exceeds a threshold. If the difference is less than or equal to the threshold, the detected multiple measurement parameters can be considered normal, and therefore the battery pack can be determined to be fault-free. If the difference is greater than the threshold, it can be determined that multiple measurement parameters are problematic, and further detection of battery faults is required. In one example, the threshold is 0, indicating that battery fault detection is required whenever the measured value differs from the predicted value. In another example, to save computing resources, those skilled in the art can set the threshold to a suitable non-zero value, where the probability of battery faults is higher when the value is greater than the threshold. Therefore, subsequent fault detection is only performed when the value is greater than the threshold.

[0120] In the following operations, multiple estimated circuit parameters need to be calculated using the detected multiple measurement parameters and the equivalent circuit model. For example, the circuit parameters of the equivalent circuit model are recalculated by using multiple measurement parameters as inputs. At this point, the measurement parameters can be treated as known, while the circuit parameters are treated as unknown, and the values ​​of the circuit parameters are calculated using the formulas of the equivalent circuit model to obtain multiple estimated circuit parameters.

[0121] In some embodiments, the computing device 104 performs fault detection upon receiving multiple measurement parameters. In this case, for each received measurement parameter, multiple estimated circuit parameters are determined using an equivalent circuit model. When the multiple measurement parameters are correct, the multiple circuit parameters predetermined by the equivalent circuit model for those multiple circuit parameters can be determined as the multiple estimated circuit parameters. When the multiple measurement parameters are incorrect, the multiple estimated circuit parameters are recalculated in the manner described above.

[0122] At box 206, computing device 104 detects a fault in a group of batteries based on multiple estimated circuit parameters. After obtaining the multiple estimated circuit parameters, computing device 104 can detect whether the group of batteries has failed and can further determine the type of fault.

[0123] There are several ways to determine whether a battery has malfunctioned using multiple estimated circuit parameters. In some embodiments, when detecting a malfunction in a group of batteries, the computing device 104 can map multiple estimated circuit parameters to a first target location in a first predetermined space. This first predetermined space can be a one-dimensional space, a two-dimensional space, or a multi-dimensional space with more than two dimensions. When the first predetermined space is a one-dimensional space, the computing device 104 can map multiple estimated circuit parameters to a point on a line. Simultaneously, the computing device 104 can also map multiple circuit parameters of the battery in its normal state to a line as a reference point. When the first predetermined space is a two-dimensional space, the computing device 104 can map multiple estimated circuit parameters to a point in a plane, and simultaneously, the computing device 104 can also map multiple circuit parameters of the battery in its normal state to a point on that plane as a reference point. Additionally, the computing device 104 can map multiple reference points for normal batteries within the first predetermined space. Then, the computing device 104 calculates the distance between the first target location and the one or more reference points. In some embodiments, the computing device 104 can employ a machine learning algorithm to map multiple estimated circuit parameters into the predetermined space. In some embodiments, the computing device 104 may employ a function to map multiple estimated circuit parameters into a predetermined space. The computing device then determines a first distance between a first target location and a first reference location corresponding to multiple circuit parameters of a fault-free group of batteries in the first predetermined space. If the first distance is greater than a first threshold distance, a faulty group of batteries is determined; if the first distance is less than or equal to the first threshold distance, a normal group of batteries is determined.

[0124] The embodiment described above uses multiple estimated circuit parameters to directly determine whether a fault has occurred. The embodiment described below requires first using multiple estimated circuit parameters to determine multiple physical parameters of a multi-physics model of a group of batteries corresponding to the multiple estimated circuit parameters. Then, the multiple physical parameters are used to detect faults in a group of batteries. At this time, the computing device can map the multiple physical parameters to a second target location in a second predetermined space. This second predetermined space can be the same space as the first predetermined space or a different space. The mapping method of the physical parameters is the same as or similar to the mapping method of the multiple estimated circuit parameters to the predetermined space. Then, the computing device determines a second distance between the second target location and a second reference location corresponding to the multiple physical parameters of a group of batteries without faults in the second predetermined space. If the second distance is greater than a second threshold distance, a group of batteries is determined to be faulty. If the second distance is less than or equal to the second threshold distance, a group of batteries is determined to be normal.

[0125] In some embodiments, when detecting a fault, the type of fault can be further detected. As mentioned above, the computing device calculates a predicted parameter corresponding to the second measurement parameter; for ease of description, this predicted parameter is also referred to as the first predicted parameter. The computing device further needs to input the second measurement parameter into an equivalent circuit model to generate a second predicted parameter corresponding to the first measurement parameter. Next, the computing device 104 uses the acquired first measurement parameter, second measurement parameter, first predicted parameter, and second predicted parameter, along with multiple physical parameters, to detect the type of fault in a group of batteries.

[0126] In this process, the computing device first inputs a first measurement parameter, a second measurement parameter, a first prediction parameter, and a second prediction parameter into each of a plurality of prediction sub-models to determine the difference between the measurement parameter and the prediction parameter. The plurality of sub-models includes sub-models corresponding to battery fault types, such as a sub-model for predicting solid electrolyte interface film degradation. In some embodiments, each of the plurality of prediction sub-models is implemented using a machine learning model. In other embodiments, each of the plurality of prediction sub-models is implemented using a predetermined function. Additionally, the calculated difference includes the difference between the first measurement parameter and the second prediction parameter and / or the difference between the second measurement parameter and the first prediction parameter. The computing device then uses this difference, along with a plurality of physical parameters, to detect fault types in a set of batteries. For example, the difference and the plurality of physical parameters are input into a pre-trained fault detection model to determine the type of fault.

[0127] The flowchart of an example method for detecting battery faults according to an embodiment of the present disclosure is described above with reference to FIG2; the schematic diagram of an example multi-physics model according to an embodiment of the present disclosure is described below with reference to FIG3. In example 300, the multi-physics model of the battery includes parameters of four physical fields, such as material field 302, chemical field 304, thermal field 306, and electric field 308. For example, material field 302 includes battery cathode material and anode material, etc.; chemical field 304 includes changes in electrolyte during charging and discharging. Thermal field 306 includes temperature, etc., and electric field 308 includes voltage and current, etc.

[0128] Example 300 also shows the structure of a battery including a cathode region 310, an anode region 312, and a separation region 314 between the cathode and anode regions. The battery, including the anode region 312, the cathode region 310, and the separation region 314, has a length of L. Each region exhibits a different voltage variation.

[0129] Figure 4 illustrates a schematic diagram of an example of an equivalent circuit model according to an embodiment of the present disclosure. As shown in Figure 3, since the multiphysics battery model includes many parameters, it can be converted into an equivalent circuit model to facilitate fault detection. Figure 4 shows an example 400 of an equivalent circuit model. In this example, a battery 402 provides an open-circuit voltage. The circuit also includes resistors 404, 406, and 408, and capacitors 410 and 412, with resistors 406 and 408 having corresponding voltages. This equivalent circuit model provides a current 414 and a voltage 416 corresponding to a set of batteries in Figure 1. In some embodiments, a machine learning model can be used to implement the conversion from the multiphysics battery model to the equivalent circuit model. In some embodiments, a multinomial regression algorithm can be used to implement the conversion from the multiphysics battery model to the equivalent circuit model. As shown in Figure 4, the equivalent circuit model is a second-order RC circuit model (ECM). By using a second-order RC circuit model, the complexity of fault detection is reduced and the sensitivity of fault detection is improved.

[0130] The above describes a schematic diagram of an example of an equivalent circuit model according to an embodiment of the present disclosure with reference to FIG4, and FIG5 below describes a schematic diagram of an example of a workflow for detecting battery faults according to an embodiment of the present disclosure.

[0131] In Example 500, there are an offline module 502 and an online module 504. The offline module 502 includes a multiphysics model 506 and battery internal characteristics 508. Battery internal characteristics 508 mainly describe some state changes of the battery, such as the characteristics exhibited by the battery under a certain fault state. The multiphysics model 506 can acquire information 518 of normal or abnormal scenarios, as well as corresponding historical data 520. Therefore, the conversion from the multiphysics model 506 to the equivalent circuit model 510 can be achieved using the information 518 of normal or abnormal scenarios and the corresponding historical data 520. For example, the received historical data can be used to train a machine learning model so that the machine learning model can achieve the conversion between the two models. Alternatively, a multinomial regression algorithm can be used to achieve the conversion between the two models using the acquired historical data. Thus, the equivalent circuit model 510 for online applications can be obtained.

[0132] During the online phase, the equivalent circuit model 510 in the online module 504 receives the actual measurement parameters 522 and then uses the equivalent circuit model 510 to detect whether the measured parameters are consistent with the corresponding predicted parameters or whether the difference between them exceeds a threshold. If the measured parameters are consistent with the corresponding predicted parameters or the difference between them does not exceed the threshold, it can be determined that the detected parameters are fine and the battery is normal. If the measured parameters are inconsistent with the corresponding predicted parameters or the difference between them exceeds the threshold, it is necessary to use the equivalent circuit model to determine multiple estimated circuit parameters 512 corresponding to the actual measured parameters. In one example, multiple estimated circuit parameters 512 can be directly input into the fault diagnosis module 514 to determine the fault based on the estimated circuit parameters. For example, the estimated circuit parameters can be mapped to a predetermined space to calculate the distance to the circuit parameters of a normal battery to determine whether a fault has occurred. In another example, the multiple estimated circuit parameters 512 are first remapped to multiple physical parameters of a multi-physics model and calibrated using the battery's internal characteristics 508, for example, limiting a certain physical parameter to a predetermined range when a predetermined condition (battery over-discharge) occurs. Then, multiple physical parameters are input into the fault diagnosis module 514 to detect faults. At this point, the distance between the multiple physical parameters and the physical parameters of a normal battery can also be calculated by mapping them to a predetermined space. After a fault is detected, early protection 516 can be executed, such as issuing a warning message to indicate a battery fault. The fault diagnosis module 514 can further determine the type of fault, which is described in more detail in Figure 8. If the fault diagnosis module 514 can determine the type of fault, the corresponding solution strategy can be executed in the early protection 516.

[0133] The above description, in conjunction with Figure 5, illustrates how multiple estimated circuit parameters can be mapped to a predetermined space. The points mapped to the predetermined space can be as shown in Figure 6. Figure 6 illustrates a schematic diagram of an example cluster of circuit parameters according to an embodiment of this disclosure. In this example 600, for measurement parameters at different times, multiple points are mapped, including points indicating a normal battery state and points indicating a battery malfunction. The horizontal axis represents the percentage change in capacitance relative to the corresponding normal value, and the vertical axis can be the percentage change in resistance relative to the corresponding normal value. After processing with a clustering algorithm, these points can be divided into several categories. Points within cluster region 606 correspond to normal batteries, while points outside cluster region 606 can be considered points indicating battery malfunctions. Furthermore, during clustering, points within cluster regions 602, 604, and 608 can be determined to correspond to different types of malfunctions. In a high-dimensional space, different degrees and types of battery malfunctions will result in different cluster centers for electrical parameters. Therefore, data-driven methods or machine learning methods can be used to map electrical parameters to a suitable data space for clustering.

[0134] Furthermore, the severity of battery failures can be quantified by calculating the distance between cluster centers. At this point, cluster boundaries can be discovered using data-driven or machine learning models, enabling early fault warnings for lithium-ion battery energy storage systems and estimating the extent of battery failures. This information will contribute to predictive maintenance of BESS.

[0135] Figure 7 illustrates a schematic diagram of examples of battery variations according to embodiments of the present disclosure. Example 700 shows the degree of battery failure development with different numbers of charge-discharge cycles. In Example 700, the horizontal axis represents the number of charge-discharge cycles, and the vertical axis represents the degree of failure development. In region 706, the number of charge-discharge cycles is relatively low, and the impact on the battery is minimal. As the number of charge-discharge cycles increases, detectable changes in the battery are observed in region 704. In region 702, after the number of charge-discharge cycles increases to a certain extent, the battery is damaged, and the probability of battery failure is relatively high.

[0136] The effect of charge-discharge cycle count on the battery has been described above with reference to Figure 7. An example of the fault diagnosis module in Figure 5 is further described below with reference to Figure 8. Figure 8 illustrates a schematic diagram of an example of a fault diagnosis module according to an embodiment of this disclosure.

[0137] As shown in Figure 8, input data 802 can be the measured current and the voltage predicted according to the equivalent circuit model, and input data 804 can be the measured voltage and the current predicted according to the equivalent circuit model. Then, input data 802 and input data 804 are respectively input to multiple sub-models, such as sub-model 806, which is a model for detecting normal battery conditions; sub-model 808, which is a model for detecting the first type of battery fault; sub-model 810, which is a model for detecting the second type of battery fault; and sub-model 812, which is a model for detecting the Nth type of battery fault. For example, sub-model 810 is used to detect solid electrolyte interface film degradation, sub-model 812 is used to detect dendrite growth, and sub-model 813 is used to detect electrolyte degradation. These sub-models all output the calculated differences, which are then input to the fault probability model 814. At this time, the fault probability model 814 also receives multiple physical parameters 818 to calculate multiple probabilities 816 for normal conditions and different types of faults. For example, these multiple physical parameters 818 are calculated from multiple estimated circuit parameters in Figure 5. For example, the fault probability model 814 can be a conditional probability density estimator or any suitable machine learning model. Then, the type corresponding to the highest probability 816 can be selected to determine the type of the detected battery group. For example, if the selected probability corresponds to solid electrolyte interface film degradation, then it can be determined that this type of fault exists in the battery group.

[0138] Figure 9 shows a schematic block diagram of an apparatus for detecting battery faults according to an embodiment of the present disclosure. As shown in Figure 9, the apparatus 900 includes an acquisition module 902 configured to acquire multiple measurement parameters for a group of batteries and an equivalent circuit model corresponding to the physical characteristics of the group of batteries; a circuit parameter determination module 904 configured to determine multiple estimated circuit parameters of the equivalent circuit model corresponding to the multiple measurement parameters based on the multiple measurement parameters and the equivalent circuit model; and a fault detection module 906 configured to detect faults in a group of batteries based on the multiple estimated circuit parameters.

[0139] In some embodiments, the plurality of measurement parameters include a first measurement parameter and a second measurement parameter, and the circuit parameter determination module 904 includes: a first prediction parameter determination module configured to generate a prediction parameter corresponding to the second measurement parameter based on the first measurement parameter using an equivalent circuit model; a difference determination module configured to determine the difference between the second measurement parameter and the prediction parameter; and an estimated circuit parameter determination module configured to determine a plurality of estimated circuit parameters in response to the difference exceeding a threshold.

[0140] In some embodiments, the first measurement parameter is one of voltage or current, and the second measurement parameter is the other of voltage or current.

[0141] In some embodiments, the first prediction parameter determination module includes: a plurality of circuit parameter determination modules configured to determine a plurality of circuit parameters for an equivalent circuit model; and a generation module configured to generate prediction parameters based on the plurality of circuit parameters by inputting a first measurement parameter into the equivalent circuit model.

[0142] In some embodiments, the estimated circuit parameter determination module includes a corresponding circuit parameter determination module configured to determine a plurality of estimated circuit parameters corresponding to the plurality of measurement parameters by inputting a plurality of measurement parameters into an equivalent circuit model.

[0143] In some embodiments, the fault detection module 906 includes: a first target location determination module configured to map a plurality of estimated circuit parameters to a first target location in a first predetermined space; a first distance determination module configured to determine a first distance between the first target location and a first reference location for a group of batteries in the first predetermined space, the first reference location corresponding to a group of batteries in a normal state; and a first fault determination module configured to determine that a group of batteries has failed in response to the first distance being greater than a first threshold distance.

[0144] In some embodiments, the fault detection module 906 further includes a first normal battery determination module, configured to determine a group of batteries as normal in response to a first distance being less than or equal to a first threshold distance.

[0145] In some embodiments, the fault detection module 906 includes: a physical parameter determination module configured to determine multiple physical parameters of a multi-physical model of a group of batteries corresponding to multiple estimated circuit parameters based on multiple estimated circuit parameters; and a first fault detection module configured to detect faults in a group of batteries based on multiple physical parameters.

[0146] In some embodiments, the first fault detection module includes: a second target location determination module configured to map a plurality of physical parameters to a second target location in a second predetermined space; a second distance determination module configured to determine a second distance between the second target location and a second reference location in the second predetermined space for a group of batteries, the second reference location corresponding to a group of batteries in a normal state; and a second fault determination module configured to determine that a group of batteries has failed in response to the second distance being greater than a second threshold distance.

[0147] In some embodiments, the first fault detection module further includes a second normal battery determination module, configured to determine a group of batteries as normal in response to a second distance being less than or equal to a second threshold distance.

[0148] In some embodiments, the prediction parameter is a first prediction parameter, and the first fault detection module includes: a second prediction parameter generation module configured to generate a second prediction parameter corresponding to the first measurement parameter using an equivalent circuit model based on the second measurement parameter; and a type detection module configured to detect the type of fault of a group of batteries based on the first measurement parameter, the second measurement parameter, the first prediction parameter, the second prediction parameter, and a plurality of physical parameters.

[0149] In some embodiments, the type detection module includes: a difference determination module configured to input a first measurement parameter, a second measurement parameter, a first prediction parameter, and a second prediction parameter into each of a plurality of prediction sub-models to determine a difference between the measurement parameter and the prediction parameter, the plurality of sub-models including a sub-model corresponding to a battery fault type; and a fault type determination module configured to determine a set of battery fault types based on the difference and a plurality of physical parameters.

[0150] Figure 10 shows a schematic block diagram of an example device 1000 that can be used to implement embodiments of the present disclosure. The computing device 104 in Figure 1 can be implemented using device 1000. As shown, device 1000 includes a central processing unit (CPU) 1001, which can perform various appropriate actions and processes according to computer program instructions stored in read-only memory (ROM) 1002 or loaded from storage unit 1008 into random access memory (RAM) 1003. Various programs and data required for the operation of device 1000 may also be stored in RAM 1003. CPU 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. Input / output (I / O) interface 1005 is also connected to bus 1004.

[0151] Multiple components in device 1000 are connected to I / O interface 1005, including: input unit 1006, such as keyboard, mouse, etc.; output unit 1007, such as various types of monitors, speakers, etc.; storage page 1008, such as disk, optical disk, etc.; and communication unit 1009, such as network card, modem, wireless transceiver, etc. Communication unit 1009 allows device 1000 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0152] The various processes and handling described above, such as method 200, can be executed by processing unit 1001. For example, in some embodiments, method 200 can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1008. In some embodiments, part or all of the computer program can be loaded and / or installed on device 1000 via ROM 1002 and / or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by CPU 1001, one or more actions of method 200 described above can be performed.

[0153] This disclosure can be a method, apparatus, system, and / or computer program product. A computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for performing various aspects of this disclosure.

[0154] Computer-readable storage media can be tangible devices capable of holding and storing instructions for use by an instruction execution device. Computer-readable storage media can be, for example—but not limited to—electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disc read-only memory (CD-ROM), digital multifunction disc (DVD), memory sticks, floppy disks, mechanical encoding devices, such as punch cards or recessed protrusions storing instructions thereon, and any suitable combination of the foregoing. The computer-readable storage media used herein are not to be construed as transient signals themselves, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or electrical signals transmitted through wires.

[0155] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0156] Computer program instructions used to perform the operations of this disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, status setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing the status information of the computer-readable program instructions to implement various aspects of this disclosure.

[0157] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0158] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processing unit of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner. Thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0159] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0160] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0161] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, and are not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical applications, or technical improvements to the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. A method (200) for detecting battery faults, comprising: Obtain (202) multiple measurement parameters for a group of batteries and an equivalent circuit model corresponding to the physical characteristics of the group of batteries; Based on the multiple measurement parameters and the equivalent circuit model, determine (204) multiple estimated circuit parameters of the equivalent circuit model corresponding to the multiple measurement parameters; as well as Based on the multiple estimated circuit parameters, the fault of the group of batteries is detected (206).

2. The method (200) according to claim 1, wherein the plurality of measurement parameters includes a first measurement parameter and a second measurement parameter, and determining (204) a plurality of estimated circuit parameters of the equivalent circuit model corresponding to the plurality of measurement parameters includes: Based on the first measurement parameters, the equivalent circuit model is used to generate prediction parameters corresponding to the second measurement parameters; Determine the difference between the second measured parameter and the predicted parameter, and In response to the difference exceeding a threshold, the plurality of estimated circuit parameters are determined.

3. The method (200) according to claim 2, wherein the first measurement parameter is one of voltage or current, and the second measurement parameter is the other of voltage or current.

4. The method (200) according to claim 2, wherein generating the prediction parameter corresponding to the second measurement parameter using an equivalent circuit model comprises: Determine multiple circuit parameters for the equivalent circuit model; as well as Based on the multiple circuit parameters, the predicted parameters are generated by inputting the first measurement parameter into the equivalent circuit model.

5. The method (200) according to claim 2, wherein determining the plurality of estimated circuit parameters comprises: By inputting the plurality of measurement parameters into the equivalent circuit model, the plurality of estimated circuit parameters corresponding to the plurality of measurement parameters are determined.

6. The method (200) according to claim 1, wherein detecting a fault in the group of batteries (206) comprises: Map the plurality of estimated circuit parameters to a first target location in a first predetermined space; Determine the first target location and the first reference position for the group of batteries in the first predetermined space. The first distance between the positions, the first reference position corresponding to the group of batteries in a normal state; as well as In response to the first distance being greater than a first threshold distance, it is determined that the group of batteries has malfunctioned.

7. The method (200) according to claim 6, wherein detecting (206) a fault in the group of batteries further comprises: In response to the first distance being less than or equal to the first threshold distance, it is determined that the group of batteries is normal.

8. The method (200) according to claim 1, wherein detecting a fault in the group of batteries (206) comprises: Based on the multiple estimated circuit parameters, multiple physical parameters of the multi-physics model of the set of batteries corresponding to the multiple estimated circuit parameters are determined; as well as Based on the aforementioned physical parameters, faults in the group of batteries are detected.

9. The method (200) according to claim 8, wherein detecting a fault in the group of batteries based on the plurality of physical parameters comprises: Map the plurality of physical parameters to a second target location in a second predetermined space; Determine a second distance between the second target location and a second reference location in the second predetermined space for the group of batteries, the second reference location corresponding to the group of batteries in a normal state; as well as In response to the second distance being greater than the second threshold distance, it is determined that the group of batteries has malfunctioned.

10. The method (200) according to claim 9, wherein detecting a fault in the group of batteries based on the plurality of physical parameters further comprises: In response to the second distance being less than or equal to the second threshold distance, it is determined that the group of batteries is normal.

11. The method (200) of claim 8, wherein the prediction parameter is a first prediction parameter, and detecting a fault in the group of batteries based on the plurality of physical parameters comprises: Based on the second measurement parameters, a second prediction parameter corresponding to the first measurement parameters is generated using the equivalent circuit model. Based on the first measurement parameter, the second measurement parameter, the first prediction parameter, the second prediction parameter, and the plurality of physical parameters, the type of fault of the group of batteries is detected.

12. The method (200) according to claim 11, wherein detecting the type of fault of the group of batteries based on the first measurement parameter, the second measurement parameter, the first prediction parameter, the second prediction parameter, and the plurality of physical parameters includes: The first measurement parameter, the second measurement parameter, the first prediction parameter, and the second prediction parameter are used to... Each of the multiple prediction sub-models is input to determine the difference between the measured parameters and the predicted parameters, the multiple sub-models including sub-models corresponding to the battery fault type; as well as Based on the differences and the multiple physical parameters, the fault type of the group of batteries is determined.

13. A device (900) for detecting battery faults, comprising: The acquisition module (902) is configured to acquire multiple measurement parameters for a group of batteries and an equivalent circuit model corresponding to the physical characteristics of the group of batteries; The circuit parameter determination module (904) is configured to determine, based on the plurality of measurement parameters and the equivalent circuit model, a plurality of estimated circuit parameters of the equivalent circuit model corresponding to the plurality of measurement parameters; as well as The fault detection module (906) is configured to detect faults in the group of batteries based on the plurality of estimated circuit parameters.

14. An electronic device (1000), comprising: At least one processor (1001); as well as A storage device for storing at least one program, which, when executed by the at least one processor (1001), causes the at least one processor (1001) to implement the method according to any one of claims 1-12.

15. A computer-readable storage medium (1003) having a computer program stored thereon, the computer program implementing the method according to any one of claims 1-12 when executed by a processor (1001).

16. A computer program product comprising a computer program that, when executed by a processor, performs the method of any one of claims 1-12.

Images