Method and device for automatically identifying abnormal battery pack of battery swap station and medium

Abstract

The invention discloses a method and equipment for automatically identifying an abnormal battery pack of a battery swap station, and a medium, belongs to the technical field of sensor data processing, and aims to solve the problems that an existing identification process of the abnormal battery pack of the battery swap station is low in automation degree; and the abnormal battery pack is easy to miss the optimal hidden danger elimination time due to manual intervention time and the like. The method comprises the following steps: acquiring a detection data group returned by a detector group corresponding to any battery pack in a battery swap station; performing feature extraction on the detection data corresponding to each detector in the detector group to obtain detection features corresponding to the detection data; performing feature matching on the detection features through a plurality of preset detection features in a preset detection feature library, and determining a detection code corresponding to the detection features according to a matching result; and determining the abnormal state of any battery pack according to the detection code.

Description

[0001] This application claims the priority of Chinese Patent Application CN202311870435.7 with an application date of December 29, 2023. This application incorporates the entire text of the above-mentioned Chinese patent application by reference. Technical Field

[0002] The present invention relates to the technical field of sensor data processing, and particularly to a method, device, and medium for automatically identifying abnormal battery packs in a battery swapping station. Background Art

[0003] When initial abnormal characteristics appear in the battery packs of existing battery swapping stations, the abnormal phenomena of the battery packs are mainly identified by the staff stationed at the charging station end, and auxiliary methods such as a temperature measuring gun, a battery management system (BMS), optical fiber alarm, on-site video monitoring, and on-site smoke sensors are combined to identify the upcoming or already occurred shape variations or smoking and fire hazards of the battery packs.

[0004] However, in this method of determining the initial battery failure phenomena, it is necessary to ensure that physical devices such as BMS, optical fiber temperature measurement system, video monitoring, and smoke sensors have been integrated at the battery or battery swapping station site, and the supporting software has been installed, and under the condition of their normal operation, manual squatting inspections are required.

[0005] This way of determining the initial battery failure will lead to the abnormal battery packs in the battery swapping station missing the best time to eliminate potential hazards due to the standardization level of the staff at the battery swapping station and the different intervention times of the staff. At the same time, the maintenance and installation of various physical devices and supporting software also require high human and material costs. Summary of the Invention

[0006] Embodiments of the present invention provide a method, device, and medium for automatically identifying abnormal battery packs in a battery swapping station, which are used to solve the following technical problems: The automation degree of the existing identification process of abnormal battery packs in a battery swapping station is not high, and it is easy for abnormal battery packs to miss the best time to eliminate potential hazards due to reasons such as the time of manual intervention.

[0007] Embodiments of the present invention adopt the following technical solutions:

[0008] In a first aspect, embodiments of the present invention provide a method for automatically identifying abnormal battery packs in a battery swapping station, the method including: obtaining a detection data set returned by a detector group corresponding to any battery pack in the battery swapping station; extracting features of the detection data corresponding to each detector in the detector group to obtain detection features corresponding to the detection data; performing feature matching on the detection features through a plurality of preset detection features in a preset detection feature library, and determining a detection code corresponding to the detection features according to the matching result; determining the abnormal state of the any battery pack according to the detection code.

[0009] In a possible implementation manner of the present invention, the method further includes: when it is determined that any one of the battery packs is abnormal, determining the type of abnormality corresponding to the abnormal battery pack according to the detection code.

[0010] The present invention obtains the detection data of the battery pack through the detector group installed in the battery swapping station, extracts features from the detection data and then performs feature matching, and finally identifies the abnormal battery packs in the battery swapping station through the results of the feature matching, realizing the automatic detection of abnormal battery packs in the battery swapping station, improving the automation degree of detecting abnormal battery packs in the battery swapping station, enabling the timely detection of abnormal battery packs, thus ensuring the timeliness of subsequent maintenance of the battery packs, avoiding the drawback that the traditional manual participation in the detection process leads to low detection efficiency and may cause the best remedial opportunity of the abnormal battery pack to be missed. Moreover, in the present invention, different encodings are performed on the detection features of the battery pack according to different abnormal conditions or types of the abnormal battery pack, so that when it is determined that the battery pack is abnormal, the type of abnormality corresponding to the abnormal battery pack can be determined through the detection code of its corresponding detection feature, providing a basis for the subsequent maintenance or repair of the abnormal battery pack, facilitating the maintenance personnel to timely master the type of abnormality of the battery pack and thus improving the maintenance efficiency.

[0011] In a possible implementation manner of the present invention, before obtaining the detection data group returned by the detector group corresponding to any one of the battery packs in the battery swapping station, the method further includes: starting the detector group corresponding to any one of the battery packs and powering on the detector group; after powering on, performing a power-on state detection on the detector group, and the result of the power-on state detection is used to indicate whether each detector in the detector group can work normally; after the detection passes, receiving the detection data group returned by the detector group.

[0012] Before obtaining the detection data returned by the detector group, the present invention performs a power-on detection on the detector group to determine whether each detector in the detector group can work normally and return the detection data normally, so as to avoid the situation of missed detection of abnormal battery packs caused by a certain detector in the detector group not being able to return data normally, and improve the accuracy and credibility of the detection results of abnormal battery packs.

[0013] In a possible implementation manner of the present invention, the detector group includes: a visual detector for collecting image data of any one of the battery packs to detect the surface integrity and combustion condition of any one of the battery packs through the image data; and / or, a voice detector for collecting voice data around any one of the battery packs to detect the abnormal sound condition of any one of the battery packs through the voice data; and / or, a gas concentration detector for collecting gas concentration data around any one of the battery packs to detect the gas around any one of the battery packs through the gas concentration data.

[0014] The present invention collects the image, sound, and gas concentration data of the battery pack in the battery swapping station through a visual detector, a voice detector, and a gas concentration detector respectively, and can detect the appearance, sound, and gas concentration of the battery pack, realizing multi-dimensional detection of the battery pack, so as to detect various abnormal conditions of the battery pack, ensuring the detection rate of abnormal battery packs. At the same time, the process of collecting battery pack data by various detectors also provides a data basis for realizing automatic detection of abnormal battery packs.

[0015] In a possible implementation manner of the present invention, the detector group at least includes a visual detector and a gas concentration detector; the combustion condition of any battery pack is detected through the visual detector; if the detected combustion condition is the presence of combustion appearance characteristics, the combustion chemical gas around the battery pack is further detected through the gas concentration detector.

[0016] The present application can determine the combustion condition of the battery pack through a visual detector and a gas concentration detector. First, the image collected by the visual detector is used to judge whether the battery pack has combustion appearance characteristics, and then the combustion chemical gas around the battery pack is detected through the gas concentration detector. Through the combination or cooperation of the two detectors, the combustion detection of the battery pack is realized.

[0017] In a possible implementation manner of the present invention, feature extraction is performed on the detection data corresponding to each detector in the detector group, including: performing convolution processing on the image data through a convolutional neural network model to extract the appearance characteristics corresponding to any battery pack; performing Fourier transform on the voice data to obtain the spectrum information corresponding to the voice data, and extracting the frequency domain characteristics corresponding to any battery pack through the spectrum information, where the frequency domain characteristics at least include Mel frequency cepstral coefficients; plotting a gas concentration change curve for the gas concentration data, and extracting the gas concentration characteristics corresponding to any battery pack through the gas concentration change curve, where the gas concentration characteristics are used to characterize the change trend of the gas concentration change curve.

[0018] The present invention adopts different feature extraction methods for different detection data, performs convolution on the image data to extract the appearance characteristics of the image data, performs Fourier transform on the voice data to extract the spectrum characteristics of the voice data, and extracts the gas concentration characteristics through the plotted gas concentration change curve, so as to realize the extraction of detection features, ensuring the pertinence of the feature extraction process and the effectiveness of the extracted detection features, and also providing a basis for the subsequent feature matching process, thereby ensuring the accuracy of the abnormal battery pack detection result.

[0019] In a possible implementation manner of the present invention, after obtaining the detection features, the method further includes: permanently storing the acquired detection data and the extracted detection features in a one-to-one correspondence manner between the detection data and the detection features.

[0020] By storing the detection data and the detection features, the present invention facilitates the subsequent maintenance personnel to view the historical detection situation of the battery pack and realizes the anomaly traceability of the battery pack.

[0021] In a possible implementation manner of the present invention, feature matching is performed on the detection features by using a number of preset detection features in a preset detection feature library, and a detection code corresponding to the detection features is determined according to the matching result, including: matching the appearance feature with the damaged appearance feature, the deformed appearance feature, and the burning appearance feature in the preset detection features, and generating an appearance code corresponding to the appearance feature when the appearance feature matches at least one of the damaged appearance feature, the deformed appearance feature, and the burning appearance feature; matching the frequency domain feature with the gas release sound feature, the battery explosion sound feature, and the shell cracking sound feature in the preset detection features, and generating a frequency domain code corresponding to the frequency domain feature when the frequency domain feature matches at least one of the gas release sound feature, the battery explosion sound feature, and the shell cracking sound feature; matching the gas concentration feature with the toxic gas feature of the battery pack, the gas concentration feature before the battery pack burns, and the gas concentration feature when the battery pack burns, and generating a gas concentration code corresponding to the gas concentration feature when the gas concentration feature matches at least one of the toxic gas concentration feature of the battery pack and the gas concentration feature when the battery pack burns; sequentially splicing the appearance code, the frequency domain code, and the gas concentration code to obtain the detection code.

[0022] By matching the extracted detection features with the preset detection features, where the preset detection features here can be the features corresponding to some abnormal situations of the battery pack, the present invention can determine whether the battery pack corresponding to the detection features is an abnormal battery pack, realizes the automatic detection of abnormal battery packs, and at the same time, the feature matching scheme also ensures the accuracy of the detection results of abnormal battery packs.

[0023] In a possible implementation manner of the present invention, the appearance code includes 3 bits, the frequency domain code includes 3 bits, and the gas concentration code includes 2 bits; and the appearance code, the frequency domain code, and the gas concentration code are all one-hot codes, and each bit in each code corresponds to a feature in the preset detection feature library.

[0024] The present invention generates a detection code corresponding to the detected feature according to the result of feature matching, which enables the operation and maintenance personnel to intuitively obtain the types of anomalies of the abnormal battery pack, facilitating the operation and maintenance personnel to promptly understand the abnormal conditions of the abnormal battery pack, thereby quickly determining the operation and maintenance plan to ensure the timeliness of the operation and maintenance of the abnormal battery pack. At the same time, the one-hot code used in the detection code also represents the abnormal conditions that do not occur in the battery pack, enabling the operation and maintenance personnel to understand not only the abnormal conditions that occur in the abnormal battery pack but also the abnormal conditions that do not occur, so that the operation and maintenance personnel can obtain the performance advantages and disadvantages of all aspects of the abnormal battery pack.

[0025] In a possible implementation manner of the present invention, after obtaining the detection code, the method further includes: determining whether there is at least one bit with a value of 1 in the detection code; if so, determining that the any battery pack is an abnormal battery pack and triggering an alarm system to give an alarm; and determining the type of anomaly of the abnormal battery pack according to the preset detection feature corresponding to the position where the value is 1.

[0026] In the present invention, when there is a 1 in the detection code, it indicates that there is an anomaly in the abnormal battery pack. At this time, an alarm is sent to notify the operation and maintenance personnel of the battery pack or the duty personnel in the battery swapping station. At the same time, the position of the 1 in the detection code can be used to quickly locate the type of anomaly of the abnormal battery pack. Compared with the solution of performing on-site anomaly detection after receiving the alarm, it enables the operation and maintenance personnel to promptly and quickly determine the type of anomaly of the abnormal battery pack, and also provides a guarantee for the timeliness of the maintenance / repair of the abnormal battery pack.

[0027] In a second aspect, an embodiment of the present invention further provides a device for automatically identifying abnormal battery packs in a battery swapping station. The device includes: a data acquisition module that acquires a detection data set returned by a detector group corresponding to any battery pack in the battery swapping station; a feature extraction module that extracts features from the detection data corresponding to each detector in the detector group to obtain the detected feature corresponding to the detection data; a feature matching module that performs feature matching on the detected feature through a plurality of preset detection features in a preset detection feature library and determines the detection code corresponding to the detected feature according to the matching result; and an abnormal state determination module that determines the abnormal state of the any battery pack according to the detection code.

[0028] In a third aspect, the present application further provides an electronic device. The device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, so that the at least one processor can execute the method for automatically identifying abnormal battery packs in a battery swapping station as described in any one of the above.

[0029] Fourthly, an embodiment of the present invention further provides a non-volatile computer storage medium, on which computer-executable instructions are stored, and the computer-executable instructions are configured to execute the method for automatically identifying an abnormal battery pack in a swapping station as described in any one of the above.

[0030] Compared with the prior art, a method, a device and a medium for automatically identifying an abnormal battery pack in a swapping station provided by the embodiment of the present invention have the following beneficial effects:

[0031] The detection data of the battery pack is collected by a detector group in the swapping station, the features of the detection data are extracted and then feature matching is performed, a detection code is generated according to the feature matching result, and when there is a 1 in the detection code, it is determined that the battery pack is abnormal, realizing the automatic detection of the abnormal battery pack, avoiding the participation of manual work, improving the efficiency of the detection process, and sending an abnormal alarm when there is a 1 in the detection code to notify the operation and maintenance personnel in time. After the operation and maintenance personnel arrive at the scene, they can directly determine the type of abnormality of the abnormal battery pack according to the position of 1 in the detection code, which is convenient for the operation and maintenance personnel to repair the abnormal battery pack in time and quickly. Compared with the traditional process of detecting the type of abnormality and determining the repair plan after receiving the alarm, it is less likely to miss the best repair opportunity of the abnormal battery pack. Description of the Drawings

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments recorded in the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings. In the drawings:

[0033] Figure 1 It is a flowchart of a method for automatically identifying an abnormal battery pack in a swapping station provided by an embodiment of the present invention;

[0034] Figure 2 It is a schematic structural diagram of a device for automatically identifying an abnormal battery pack in a swapping station provided by an embodiment of the present invention. Detailed Embodiments

[0035] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0036] The method in the embodiment of the present invention is described in detail below with reference to the accompanying drawings.

[0037] Figure 1 A flow chart of a method for automatically identifying abnormal battery packs in a battery swap station provided by an embodiment of the present invention, such as Figure 1 As shown, the method for identifying an abnormal battery pack in an embodiment of the present invention at least includes the following execution steps:

[0038] Step 101: Obtain a detection data group returned by a detector group corresponding to any battery pack in the battery swap station.

[0039] In order to realize the automatic detection of abnormal battery packs in the present invention, a detector group is installed in the battery swap station. The detector group is used to collect various data of any battery pack in the battery swap station to obtain a detection data group. Any battery pack here refers to any battery pack in the battery swap station, and each detection data in the detection data group here corresponds one-to-one to each detector in the detector group, that is, each detector summarizes the detection data it detects and uniformly feeds back in the form of a data group to avoid data confusion caused by each detector feeding back data separately.

[0040] In one possible implementation of the present invention, the detector group includes at least a visual detector, and / or a voice detector, and / or a gas concentration detector. These detectors can be sensors or ordinary collectors, and are mainly used to collect image data, voice data and gas concentration data of the battery pack being inspected. The image data, voice data and gas concentration data here also constitute the aforementioned detection data group.

[0041] Furthermore, the image data collected by the visual detector can be used to determine the surface integrity and combustion conditions of the battery pack. The surface integrity here is mainly used to determine whether the battery pack surface is damaged or deformed. The deformation here can include deformation caused by battery pack leakage and deformation caused by squeezing, vehicle bumps, etc. The voice data collected by the voice detector can be used to determine the sound of the battery pack. The different abnormal sounds of the battery pack can be determined by the differences in various sounds. The abnormal sounds here can include the sound of the battery pack releasing gas, the sound of the battery pack exploding, and the sound of the battery pack shell cracking. The gas concentration data collected by the gas concentration detector can be used to determine the gas concentration around the battery pack. The concentration of different gases around the battery pack can be used to determine whether the battery pack is burning, providing further judgment basis for the identification of abnormal combustion of the battery pack. The gas concentration data here includes the gas concentration before the battery pack burns and the gas concentration when the battery pack burns.

[0042] As a feasible implementation, each detector within the detector group can be installed at different positions within the battery swapping station according to the type of collected data. For example, to ensure that the visual detector for collecting image data can capture the overall appearance of the battery pack, it needs to be installed at a relatively high position compared to the battery pack, such as on the inner top of the battery compartment used to place the battery pack. Another example is that the voice detector for collecting voice data and the gas concentration detector for collecting the gas concentration around the battery pack can be directly installed at any position in the battery compartment, as long as it can ensure the collection of data corresponding to its battery pack.

[0043] Furthermore, the aforementioned detector group can correspond one-to-one with the battery packs within the battery swapping station. That is, one detector group can be used to detect the data of only one battery pack. However, since there are multiple battery packs in the battery swapping station, to save detector resources and reduce the installation and operation and maintenance costs of the detectors, when the scenario of the battery swapping station permits, two or even more battery packs in the battery swapping station can share one detector. When it is subsequently determined that the detection data corresponding to this detector is abnormal, as long as the maintenance personnel can identify on-site which battery pack is abnormal.

[0044] In a possible implementation of the present invention, when the detector group is used to detect the combustion situation of the battery pack, the detector group at least includes a visual detector and a gas concentration detector. During the detection, first, the combustion situation of the battery pack is detected by the image collected by the visual detector. When the detected combustion situation has the appearance characteristics of combustion, the combustion chemical gas around the battery pack is then detected by the gas concentration detector. That is, first, the visual detector is used to detect whether there is a combustion situation in the image. When there is, the gas concentration detector is then used to detect the combustion chemical gas around the battery pack. Through the combined or coordinated operation of these two detectors, the detection of the combustion situation of the battery pack is achieved.

[0045] In a possible implementation of the present invention, in order to determine that each detector within the detector group can work properly, and thus determine that the data in the detection data group returned by the detector group is itself problem-free, before receiving the detection data returned by the detector, a power-on detection of the detector group will be performed first. Specifically, after starting the detector group, power is supplied to the detector group, and the power-on state is detected. Here, the power-on state refers to the state of whether each detector within the detector group can work properly after being powered on. If each detector within the detector group passes the power-on state detection, it indicates that the detector group is okay at this time and can detect data normally. At this time, the detection data group returned by the detector group can be received. If an abnormality is found during the power-on state detection of a certain detector within the detector group, it indicates that this detector cannot detect data normally. At this time, the detector needs to be repaired or replaced by the staff, and then a good detector is used to collect the detection data group.

[0046] Step 102: Extract features from the detection data corresponding to each detector in the detector group to obtain the detection features corresponding to the detection data.

[0047] After obtaining the detection data group returned by the detector group, split the detection data group to obtain the image data, voice data, and gas concentration data corresponding to the battery pack. Then, extract features from these three types of data to obtain the detection features of the battery pack.

[0048] In a possible implementation manner of the present invention, different feature extraction schemes are adopted for different types of detection data. Specifically, for image data, in the present invention, the image data is subjected to convolution processing by using a convolutional neural network model, and the appearance features of the battery pack are extracted from the features output by the model. For voice data, after obtaining the spectrum information corresponding to the voice data by using Fourier transform, frequency domain features are extracted at the center of the spectrum information. The frequency domain features extracted here can be the Mel frequency cepstral coefficients corresponding to the voice data. For gas concentration data, the gas concentration features that can represent the gas concentration change trend can be extracted from the curve by plotting the gas concentration change curve. The appearance features, frequency domain features, and gas concentration features extracted also constitute the detection features of the battery pack.

[0049] In a possible implementation manner of the present invention, in order to trace the detection data when an abnormality occurs in the battery pack and achieve the traceability of the detection data, and also in order for the operation and maintenance personnel to view the historical detection data of the battery pack, after the detection features are extracted from the detection data in the present invention, the detection data and the detection features are stored in correspondence, and the storage period is permanent storage. Here, storing the detection features is also to facilitate the subsequent operation and maintenance personnel to quickly identify the abnormality of the battery pack by using the detection features, without the need to extract the features again for the detection data, and the direct use of the detection features can be realized, providing convenience for the abnormality traceability of the battery pack.

[0050] Step 103: Perform feature matching on the detection features by using a number of preset detection features in a preset detection feature library, and determine the detection code corresponding to the detection features according to the matching result.

[0051] When using the detection features to identify the abnormality of the battery pack, a preset detection feature library can be introduced for feature matching. A number of preset detection features are stored in the preset detection feature library. Here, the number of preset detection features corresponds to different abnormal situations of the battery pack. That is, when the detection features of the battery pack match the preset detection features successfully, the abnormal situation of the battery pack corresponding to the detection features can be determined according to the abnormal situation corresponding to the successfully matched preset detection features, so as to realize the identification of the abnormal battery pack.

[0052] Specifically, in the preset detection feature library, there are damaged appearance features, deformed appearance features, and burning appearance features for the appearance of the battery pack; there are gas release sound features, battery explosion sound features, and shell cracking sound features for abnormal sounds of the battery pack; and there are battery pack toxic gas features, pre-combustion gas concentration features of the battery pack, and in-combustion gas concentration features of the battery pack for the gas concentration around the battery pack. Therefore, when performing feature matching on the detection features, for the appearance features in the detection features, match them with the damaged appearance features, deformed appearance features, and burning appearance features in the preset detection features, and when at least one of the appearance features matches successfully with the aforementioned damaged appearance features, deformed appearance features, and burning appearance features, generate an appearance code corresponding to the appearance feature; for the frequency domain features in the detection features, match them with the gas release sound features, battery explosion sound features, and shell cracking sound features in the preset detection features, and when at least one of the frequency domain features matches successfully with the gas release sound features, battery explosion sound features, and shell cracking sound features, generate a frequency domain code corresponding to the frequency domain feature; for the gas concentration features in the detection features, match them with the battery pack toxic gas features, pre-combustion gas concentration features of the battery pack, and in-combustion gas concentration features of the battery pack in the preset detection features, and when at least one of the gas concentration features matches successfully with the battery pack toxic gas concentration features, pre-combustion gas concentration features of the battery pack, and in-combustion gas concentration features of the battery pack, generate a gas concentration code corresponding to the gas concentration feature. It should be noted that the feature matching process here can be achieved by calculating the similarity between the detection features and the preset detection features, and different similarity calculation schemes are adopted for different feature types. The similarity calculation process here can be implemented through existing schemes or methods, and the present invention will not elaborate on this here. As long as it can be determined whether two features match successfully.

[0053] Furthermore, sequentially splice the obtained appearance code, frequency domain code, and gas concentration code to obtain the detection code corresponding to the battery pack. It should be noted that there is no fixed order limit for the feature matching process of the aforementioned appearance features, frequency domain features, and gas concentration features. It is also possible to first perform the matching of the frequency domain features, then perform the matching of the gas concentration features, and finally perform the matching of the appearance features, as long as the matching process of the three features can be completed.

[0054] In a possible implementation manner of the present invention, the detection coding adopts one-hot coding. In one-hot coding, when a feature match is successful, the bit corresponding to the feature takes a value of 1, and when the feature match fails, the bit corresponding to the feature takes a value of 0. Moreover, after the foregoing appearance feature matching is completed, the obtained appearance coding has 3 bits, which respectively correspond one-to-one to the damage feature, the deformation feature, and the combustion feature. After the foregoing frequency-domain feature matching is completed, the obtained frequency-domain coding has 3 bits, which respectively correspond one-to-one to the gas release feature, the battery explosion feature, and the housing cracking feature. After the foregoing gas concentration feature matching is completed, the obtained gas concentration coding has 2 bits, which respectively correspond one-to-one to the gas concentration feature before the battery pack burns and the gas concentration feature when the battery pack burns.

[0055] As a feasible implementation manner, when the detected feature fails to match the preset detected feature, for example, when the appearance feature fails to match the damage feature, the deformation feature, and the combustion feature in the preset detected feature, a 000 appearance coding is directly generated.

[0056] Step 104: Determine the abnormal state of any battery pack according to the detection coding.

[0057] The foregoing abnormal state includes that the battery pack has an abnormality and the battery pack is normal. When it is determined according to the detection coding that the abnormal state of any battery pack is an abnormality, the abnormal type corresponding to the abnormal battery pack is determined according to the detection coding.

[0058] Specifically, after obtaining the detection coding corresponding to the battery pack, the values of each bit in the detection coding are judged. If at least one of the values is 1, it means that the battery pack has an abnormality. At this time, the alarm system will be triggered to send an alarm to notify the operation and maintenance personnel or the on-duty personnel in the battery replacement station. And since the positions in the detection coding correspond one-to-one to the respective features included in the preset detected feature, in this way, the preset detected feature corresponding to this position can be obtained according to the position where the value is 1, and this preset detected feature is the abnormal type corresponding to the battery pack. For example, if the detection coding of a certain battery pack is 01000000, it means that the battery pack has an abnormality, and the type of the abnormality is that the battery pack is deformed.

[0059] In the present invention, the detection code is used as the final feedback for the abnormal battery pack. On the one hand, it enables the operation and maintenance personnel to directly obtain what kind of abnormality has occurred in the abnormal battery pack at this time, facilitating the quick formulation of a maintenance plan, thereby avoiding missing the best repair opportunity for the abnormal battery pack. On the other hand, it allows the operation and maintenance personnel to understand the occurrence of other abnormal types of the abnormal battery pack, without the need to re-detect other abnormal types, avoiding the secondary detection by the operation and maintenance personnel, and saving resources and costs. For example, if the detection code of an abnormal battery pack is 01000000, after the operation and maintenance personnel arrive at the scene, they can directly obtain from the detection code that the abnormal type of the abnormal battery pack is appearance deformation. At this time, the operation and maintenance personnel only need to repair the deformed appearance. For other abnormal types, the operation and maintenance personnel can directly conclude that a certain abnormal type has not occurred based on the value of 0 at the corresponding position of the abnormal type in the detection code, without the need to detect and verify again, thereby saving the operation and maintenance time of the operation and maintenance personnel and improving the operation and maintenance efficiency.

[0060] Based on the same inventive concept, an embodiment of the present invention further provides a device for automatically identifying abnormal battery packs in a battery swapping station, and its structure is as Figure 2 shown.

[0061] Figure 2 FIG. is a schematic structural diagram of a device for automatically identifying abnormal battery packs in a battery swapping station provided by an embodiment of the present invention. As Figure 2 shown, the device 200 for automatically identifying abnormal battery packs in an embodiment of the present invention specifically includes: at least one processor 201; and a memory 203 communicatively connected to the at least one processor 201 (connected through a bus 202); wherein, the memory 203 stores instructions that can be executed by the at least one processor 201, so that the at least one processor 201 can execute a method for automatically identifying abnormal battery packs in a battery swapping station as described in any of the above embodiments.

[0062] In one or more possible implementation manners of an embodiment of the present invention, the foregoing processor is used to execute: obtaining a detection data set returned by a detector group corresponding to any battery pack in the battery swapping station; extracting features of the detection data corresponding to each detector in the detector group to obtain detection features corresponding to the detection data; performing feature matching on the detection features through a number of preset detection features in a preset detection feature library, and determining a detection code corresponding to the detection features according to the matching result; and determining an abnormal state of the any battery pack according to the detection code.

[0063] An apparatus for automatically identifying abnormal battery packs in a battery swapping station according to the present application may further include: a data acquisition module configured to acquire a set of detection data returned by a detector group corresponding to any battery pack in the battery swapping station; a feature extraction module configured to perform feature extraction on the detection data corresponding to each detector in the detector group to obtain detection features corresponding to the detection data; a feature matching module configured to perform feature matching on the detection features by using a number of preset detection features in a preset detection feature library, and determine a detection code corresponding to the detection features according to a matching result; and an abnormal state determination module configured to determine an abnormal state of the any battery pack according to the detection code.

[0064] In addition, an embodiment of the present invention further provides a non-volatile computer storage medium, on which computer-executable instructions are stored, and the computer-executable instructions are configured to be capable of executing a method for automatically identifying abnormal battery packs in a battery swapping station as described in any of the above embodiments.

[0065] In one or more possible implementation manners of an embodiment of the present invention, the foregoing computer-executable instructions are configured to be capable of executing: acquiring a set of detection data returned by a detector group corresponding to any battery pack in the battery swapping station; performing feature extraction on the detection data corresponding to each detector in the detector group to obtain detection features corresponding to the detection data; performing feature matching on the detection features by using a number of preset detection features in a preset detection feature library, and determining a detection code corresponding to the detection features according to a matching result; and determining an abnormal state of the any battery pack according to the detection code.

[0066] Each embodiment in the present invention is described in a progressive manner, and the same or similar parts among the embodiments may be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the Internet of Things devices and media, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts may refer to the partial description of the method embodiments.

[0067] The systems and media provided by the embodiments of the present invention correspond one-to-one to the methods. Therefore, the systems and media also have beneficial technical effects similar to those of the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media are not described herein again.

[0068] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) that contain computer-usable program code.

[0069] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0070] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device realizes the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0071] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for realizing the functions specified in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0072] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and a memory.

[0073] The memory may include non-permanent memory in the computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.

[0074] A computer-readable medium includes permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transitory medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer-readable medium does not include transitory computer-readable media, such as modulated data signals and carrier waves.

[0075] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0076] The above are only embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, various changes and modifications can be made to the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the scope of the claims of the present invention.

Claims

1. A method for automatically identifying abnormal battery packs in a battery swapping station, characterized in that, The method includes: Obtaining a detection data set returned by a detector group corresponding to any battery pack in the battery swapping station; Performing feature extraction on the detection data corresponding to each detector in the detector group to obtain detection features corresponding to the detection data; Performing feature matching on the detection features by using a number of preset detection features in a preset detection feature library, and determining a detection code corresponding to the detection features according to the matching result; Determining the abnormal state of the any battery pack according to the detection code; 2. The method for automatically identifying an abnormal battery pack in a battery swapping station according to claim 1, wherein The method further includes: When it is determined that the any battery pack is abnormal, determining the type of abnormality corresponding to the abnormal battery pack according to the detection code; 3. A method for automatically identifying abnormal battery packs in a battery swapping station according to claim 1, characterized in that, Before obtaining the detection data set returned by the detector group corresponding to any battery pack in the battery swapping station, the method further includes: Starting the detector group corresponding to the any battery pack and powering on the detector group; After powering on, performing a power-on state detection on the detector group, and the result of the power-on state detection is used to indicate whether each detector in the detector group can work normally; After the detection passes, receiving the detection data set returned by the detector group; 4. A method for automatically identifying abnormal battery packs in a battery swapping station according to claim 1, characterized in that, The detector group includes: A visual detector, configured to collect image data of the any battery pack to detect the surface integrity condition and combustion condition of the any battery pack through the image data; And / or, a voice detector, configured to collect voice data around the any battery pack to detect abnormal sound conditions of the any battery pack through the voice data; And / or, a gas concentration detector, configured to collect gas concentration data around the any battery pack to detect the gas around the any battery pack through the gas concentration data; 5. The method for automatically identifying an abnormal battery pack in a battery swapping station according to claim 4, characterized in that, The detector group includes at least a visual detector and a gas concentration detector; Detecting the combustion condition of the any battery pack through the visual detector; If the detected combustion condition is that there are combustion appearance features, then detecting the combustion chemical gas around the battery pack through the gas concentration detector; 6. The method for automatically identifying an abnormal battery pack in a battery swapping station according to claim 4, wherein Performing feature extraction on the detection data corresponding to each detector in the detector group includes: Performing convolution processing on the image data through a convolutional neural network model to extract the appearance features corresponding to the any battery pack; Performing Fourier transform on the voice data to obtain the frequency spectrum information corresponding to the voice data, and extracting the frequency domain features corresponding to the any battery pack through the frequency spectrum information, and the frequency domain features at least include Mel frequency cepstral coefficients; Drawing a gas concentration change curve for the gas concentration data, and extracting the gas concentration features corresponding to the any battery pack through the gas concentration change curve, and the gas concentration features are used to characterize the change trend of the gas concentration change curve; 7. The method for automatically identifying abnormal battery packs in a battery swapping station according to claim 6, characterized in that, After obtaining the detection features, the method further includes: Permanently storing the obtained detection data and the extracted detection features, and the storage method is that the detection data and the detection features are in one-to-one correspondence; 8. The method for automatically identifying an abnormal battery pack in a battery swapping station according to claim 6, wherein, Performing feature matching on the detection features by using a number of preset detection features in a preset detection feature library, and determining a detection code corresponding to the detection features according to the matching result, includes: Match the appearance features with the damaged appearance features, deformed appearance features, and burned appearance features among the preset detection features. When the appearance features match at least one of the damaged appearance features, deformed appearance features, and burned appearance features, generate the appearance code corresponding to the appearance features; Match the frequency domain features with the gas release sound features, battery burst sound features, and housing cracking sound features among the preset detection features. When the frequency domain features match at least one of the gas release sound features, battery burst sound features, and housing cracking sound features, generate the frequency domain code corresponding to the frequency domain features; Match the gas concentration features with the toxic gas features of the battery pack, the gas concentration features before battery pack combustion, and the gas concentration features during battery pack combustion among the preset detection features. When the gas concentration features match at least one of the toxic gas concentration features of the battery pack, the gas concentration features before battery pack combustion, and the gas concentration features during battery pack combustion, generate the gas concentration code corresponding to the gas concentration features; Sequentially splice the appearance code, the frequency domain code, and the gas concentration code to obtain the detection code.

9. The method for automatically identifying an abnormal battery pack in a battery swapping station according to claim 8, wherein The appearance code includes 3 bits, the frequency domain code includes 3 bits, and the gas concentration code includes 2 bits; and the appearance code, the frequency domain code, and the gas concentration code are all one-hot codes, and each bit in each code corresponds to a feature in the preset detection feature library.

10. The method for automatically identifying an abnormal battery pack in a battery swapping station according to claim 9, wherein, After obtaining the detection code, the method further includes: Determine whether there is at least one bit with a value of 1 in the detection code; If so, determine that the any battery pack is an abnormal battery pack and trigger an alarm system to give an alarm; Determine the type of abnormality of the abnormal battery pack according to the preset detection feature corresponding to the position where the value is 1.

11. An apparatus for automatically identifying abnormal battery packs in a battery swapping station, characterized in that, Includes: A data acquisition module that acquires a detection data group returned by a detector group corresponding to any battery pack in the battery swap station; A feature extraction module that extracts features from the detection data corresponding to each detector in the detector group to obtain the detection features corresponding to the detection data; A feature matching module that performs feature matching on the detection features through a number of preset detection features in a preset detection feature library, and determines the detection code corresponding to the detection features according to the matching result; An abnormal state determination module that determines the abnormal state of the any battery pack according to the detection code.

12. An electronic device, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, so that the at least one processor can execute the method for automatically identifying abnormal battery packs in a battery swap station according to any one of claims 1-10.

13. A non-volatile computer storage medium having computer-executable instructions stored thereon, characterized in that, The computer-executable instructions are set to execute the method for automatically identifying abnormal battery packs in a battery swap station according to any one of claims 1-10.

Images