Energy storage module fault detection method, apparatus and system, computer device, and storage medium

Abstract

An energy storage module fault detection method, apparatus and system, a computer device, a storage medium, and a computer program product. The method comprises: determining a target detection angle of an internal visual probe on the basis of battery position information of an energy storage module (step S201); controlling the internal visual probe to enter the interior of the energy storage module, so as to collect internal module images of the energy storage module inside the energy storage module at the target detection angle by means of the internal visual probe (step S202); and performing fault identification on the internal module images by means of a trained fault detection model to obtain a target fault detection result of the energy storage module, the target fault detection result including a battery fault detection result and a wiring fault detection result for the energy storage module (step S203). By using the method, the convenience of fault detection for the energy storage module can be improved.

Description

Methods, devices, systems, computer equipment, and storage media for fault detection of energy storage modules Technical Field

[0001] This application relates to the field of energy storage module technology, and in particular to a method, apparatus, system, computer equipment, storage medium and computer program product for fault detection of energy storage modules. Background Technology

[0002] Electrochemical energy storage, as an important energy storage technology, plays a crucial role in the development of smart grids, renewable energy generation, and the energy internet. However, safety accidents at energy storage power stations have become a significant bottleneck restricting the rapid development of electrochemical energy storage systems. In the past, several electrochemical energy storage fires have occurred both domestically and internationally, raising widespread concerns about the safety and reliability of energy storage power stations. Although some safety protection technologies have been adopted in battery design and system integration, it is still impossible to completely eliminate battery abnormalities and wiring faults, which can easily lead to safety accidents such as battery thermal runaway.

[0003] Currently, batteries are usually encapsulated in an insulating plate with ventilation holes inside the energy storage module. It is impossible to directly observe the battery condition inside the energy storage module from the outside. The module must be shut down and staff must disassemble and inspect it, which is time-consuming, labor-intensive, and affects the operation of the energy storage module.

[0004] Summary of the Invention

[0005] Therefore, it is necessary to provide a method, device, system, computer equipment, computer-readable storage medium, and computer program product for detecting energy storage module faults, which can improve the convenience of fault detection of energy storage modules, in response to the above-mentioned technical problems.

[0006] Firstly, this application provides a method for fault detection of an energy storage module. The method includes:

[0007] Based on the battery location information of the energy storage module, determine the target detection angle of the internal vision probe;

[0008] The internal vision probe is controlled to enter the interior of the energy storage module, so as to acquire an image of the interior of the energy storage module according to the target detection angle.

[0009] The trained fault detection model is used to identify faults in the internal images of the module to obtain the target fault detection results of the energy storage module; the target fault detection results include the battery fault detection results and wiring fault detection results of the energy storage module.

[0010] In one embodiment, a trained fault detection model is used to identify faults in the internal images of the module to obtain the target fault detection result of the energy storage module, including:

[0011] Using the fault detection model, fault identification is performed on the internal image of the module for the wiring terminals and the screws of the wiring terminals to obtain the wiring fault detection result;

[0012] The fault detection model is used to identify battery bulging and battery leakage in the internal images of the module, and the battery fault detection results are obtained.

[0013] The target fault detection result is obtained based on the wiring fault detection result and the battery fault detection result.

[0014] In one embodiment, after obtaining the target fault detection result, the method further includes:

[0015] Based on the target fault detection results, the internal image of the module is annotated to obtain the annotated internal image of the module;

[0016] The annotated internal image of the module is displayed.

[0017] In one embodiment, the internal vision probe acquires images of the energy storage module's interior at the target detection angle, including:

[0018] Obtain the internal brightness information of the energy storage module;

[0019] Based on the brightness information, determine multiple illumination brightness levels of the internal vision probe;

[0020] The internal vision probe is controlled to acquire multiple images of the module's interior under the specified illumination brightness at the target detection angle.

[0021] In one embodiment, determining the target detection angle of the internal vision probe based on the battery location information of the energy storage module includes:

[0022] The first detection angle of the internal vision probe is obtained based on the top position of the battery in the energy storage module.

[0023] The second detection angle of the internal vision probe is obtained based on the bottom position of the battery in the energy storage module.

[0024] The target detection angle of the internal vision probe is obtained based on the first detection angle and the second detection angle.

[0025] Secondly, this application provides a fault detection system for an energy storage module. The system includes an internal vision probe, a controller, and an energy storage module; the size of the internal vision probe is much smaller than the size of the energy storage module.

[0026] The controller is used to determine the target detection angle of the internal vision probe based on the battery position information of the energy storage module, and control the internal vision probe to collect images of the inside of the energy storage module according to the target detection angle.

[0027] The internal vision probe is used to send the acquired images of the module's interior to the controller;

[0028] The controller is further configured to perform fault identification on the received internal image of the module using a trained fault detection model to obtain the fault detection result of the energy storage module; the fault detection result includes the battery fault detection result for the battery in the energy storage module and the wiring fault detection result for the wiring in the energy storage module.

[0029] Thirdly, this application also provides a fault detection device for an energy storage module. The device includes:

[0030] The detection angle determination module is used to determine the target detection angle of the internal vision probe based on the battery position information of the energy storage module.

[0031] An internal image acquisition module is used to control the internal vision probe to enter the interior of the energy storage module, so as to acquire an internal image of the energy storage module according to the target detection angle through the internal vision probe.

[0032] The detection result acquisition module is used to identify faults in the internal images of the module using a trained fault detection model, and obtain the target fault detection result of the energy storage module; the target fault detection result includes the battery fault detection result and the wiring fault detection result of the energy storage module.

[0033] Fourthly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0034] Based on the battery location information of the energy storage module, determine the target detection angle of the internal vision probe;

[0035] The internal vision probe is controlled to enter the interior of the energy storage module, so as to acquire an image of the interior of the energy storage module according to the target detection angle.

[0036] The trained fault detection model is used to identify faults in the internal images of the module to obtain the target fault detection results of the energy storage module; the target fault detection results include the battery fault detection results and wiring fault detection results of the energy storage module.

[0037] Fifthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0038] Based on the battery location information of the energy storage module, determine the target detection angle of the internal vision probe;

[0039] The internal vision probe is controlled to enter the interior of the energy storage module, so as to acquire an image of the interior of the energy storage module according to the target detection angle.

[0040] The trained fault detection model is used to identify faults in the internal images of the module to obtain the target fault detection results of the energy storage module; the target fault detection results include the battery fault detection results and wiring fault detection results of the energy storage module.

[0041] Sixthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0042] Based on the battery location information of the energy storage module, determine the target detection angle of the internal vision probe;

[0043] The internal vision probe is controlled to enter the interior of the energy storage module, so as to acquire an image of the interior of the energy storage module according to the target detection angle.

[0044] The trained fault detection model is used to identify faults in the internal images of the module to obtain the target fault detection results of the energy storage module; the target fault detection results include the battery fault detection results and wiring fault detection results of the energy storage module.

[0045] The aforementioned energy storage module fault detection method, device, system, computer equipment, storage medium, and computer program products determine the target detection angle of the internal vision probe based on the battery location information of the energy storage module; control the internal vision probe to enter the interior of the energy storage module to acquire internal images of the energy storage module according to the target detection angle; and use a trained fault detection model to identify faults in the internal images of the module, obtaining the target fault detection results of the energy storage module. The target fault detection results include battery fault detection results and wiring fault detection results. This method, by acquiring internal images of the energy storage module through an internal vision probe and analyzing and identifying internal faults based on these images, improves the convenience of fault detection for energy storage modules, promptly alerts maintenance personnel to handle issues, prevents safety accidents such as fires, protects personnel and property safety, and ensures the normal operation of the energy storage module. Attached Figure Description

[0046] Figure 1 is an application environment diagram of the energy storage module fault detection method in one embodiment;

[0047] Figure 2 is a flowchart illustrating a fault detection method for an energy storage module in one embodiment;

[0048] Figure 3 is a flowchart illustrating the steps for obtaining the target fault detection result of the energy storage module in one embodiment;

[0049] Figure 4 is a schematic diagram of the network structure of a fault detection model in one embodiment;

[0050] Figure 5 is a schematic diagram of the internal image of the module after annotation in one embodiment;

[0051] Figure 6 is a flowchart illustrating the energy storage module fault detection method in another embodiment;

[0052] Figure 7 is a schematic diagram of an energy storage module fault detection system in another embodiment;

[0053] Figure 8 is a structural block diagram of an energy storage module fault detection device in one embodiment;

[0054] Figure 9 is an internal structure diagram of a computer device in one embodiment. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, internal images of energy storage modules, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data must comply with relevant regulations.

[0057] The energy storage module fault detection method provided in this application embodiment can be applied to the application environment shown in Figure 1. The controller 101 communicates with an internal vision probe 102 via a network. The internal vision probe 102 is used to enter the interior of the energy storage module 103 to collect images. A data storage system can store the data that the controller 101 needs to process. The data storage system can be integrated on the controller, integrated on a server, or placed on a cloud or other network server. The controller 101 determines the target detection angle of the internal vision probe 102 based on the battery location information of the energy storage module; it controls the internal vision probe 102 to enter the interior of the energy storage module to collect images of the interior of the energy storage module according to the target detection angle; and it uses a trained fault detection model to identify faults in the images of the interior of the module to obtain the target fault detection result of the energy storage module. The controller 101 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices equipped with display units (such as displays).

[0058] In one embodiment, as shown in Figure 2, a fault detection method for an energy storage module is provided. Taking the application of this method to the controller in Figure 1 as an example, the method includes the following steps:

[0059] Step S201: Determine the target detection angle of the internal vision probe based on the battery position information of the energy storage module.

[0060] The energy storage module consists of one or more battery packs (such as lithium-ion batteries), which are enclosed inside. The interior of the energy storage module is dark and has narrow passages. The energy storage module also has ventilation openings, which are mainly used for heat dissipation, that is, to dissipate the heat generated by the batteries and reduce the internal temperature of the energy storage module.

[0061] The internal vision probe is a flexible and compact visual inspection probe. Its lead wire is 6mm in diameter and insulated, allowing it to be inserted into the battery module through the module's ventilation opening for observation. The insulated outer wall effectively prevents short circuits. The internal vision probe also features multiple high-speed output interfaces for efficient image transmission.

[0062] Specifically, the controller can obtain the design drawings and structural information of the energy storage module from the database, and then extract the battery location information of the energy storage module. Based on the battery location information, it determines the location inside the energy storage module that needs to be detected for faults. Combined with the size of the internal vision probe and the shooting position of the internal vision probe, it comprehensively derives the target detection angle of the internal vision probe. The target detection angle refers to the shooting angle of the shooting device on the internal vision probe when performing image acquisition operations.

[0063] Step S202: Control the internal vision probe to enter the interior of the energy storage module, so as to collect the internal image of the energy storage module according to the target detection angle.

[0064] Among them, the internal image of the module refers to the image collected by the internal vision probe inside the energy storage module.

[0065] Specifically, the controller establishes a communication connection with the internal vision probe beforehand. The controller drives the internal vision probe to enter the interior of the energy storage module through the ventilation port. Because the internal vision probe uses flexible materials, it can flexibly capture images from multiple angles within the confined space inside the energy storage module. The controller sends the calculated target detection angle to the internal vision probe; then, the internal vision probe acquires images of the interior of the energy storage module according to the received target detection angle and sends the acquired images of the interior of the module back to the energy storage module through a high-speed output interface.

[0066] Step S203: Using the trained fault detection model, fault identification is performed on the internal image of the module to obtain the target fault detection result of the energy storage module; the target fault detection result includes the battery fault detection result and the wiring fault detection result of the energy storage module.

[0067] Among them, the fault detection model is used to detect faults or identify defects in the input image (such as an image inside the module). The fault detection model can be constructed by a deep learning model. For example, the fault detection model can be constructed by a backbone network, a multi-scale fusion network, and multiple different types of prediction networks.

[0068] Specifically, the controller also includes a database storing a large number of historical images of faulty modules. The controller uses a trained fault detection model to identify faults in these images, such as battery abnormalities (e.g., battery bulging, battery leakage) and wiring faults (e.g., warped terminals, loose screws). This results in a first fault detection result for the module's internal image. The controller then performs similarity matching between the module's internal image and historical images in the database to detect similarities, resulting in a second fault detection result. Finally, the controller combines the first and second fault detection results to obtain the target fault detection result for the energy storage module.

[0069] In the aforementioned energy storage module fault detection method, the target detection angle of the internal vision probe is determined based on the battery location information of the energy storage module. The internal vision probe is then controlled to enter the interior of the energy storage module, acquiring internal images of the module at the target detection angle. A trained fault detection model is used to identify faults in the internal images, yielding the target fault detection results. These results include battery fault detection and wiring fault detection. This method, by acquiring internal images of the energy storage module through an internal vision probe and analyzing and identifying faults based on these images, improves the convenience of fault detection. It also promptly alerts maintenance personnel to address issues, preventing fires and other safety accidents, ensuring personnel and property safety, and guaranteeing the normal operation of the energy storage module.

[0070] In one embodiment, as shown in Figure 3, step S203 above, which uses a trained fault detection model to identify faults in the internal images of the module, obtains the target fault detection result of the energy storage module, specifically includes the following:

[0071] Step S301: Using the fault detection model, perform fault identification on the internal image of the module for the wiring terminals and screws, and obtain the wiring fault detection result.

[0072] Step S302: Using the fault detection model, perform fault identification on the internal images of the module for battery bulging and battery leakage, and obtain battery fault detection results.

[0073] Step S303: Based on the wiring fault detection results and the battery fault detection results, obtain the target fault detection results.

[0074] Specifically, the controller trains at least a first prediction network for predicting wiring faults using historical module internal images and their labels for predicting wiring fault types, and a second prediction network for predicting battery faults using historical module internal images and their labels for predicting battery fault types. Of course, more prediction networks for predicting wiring faults and / or for predicting battery faults can also be trained. Then, the first and second prediction networks are connected to the trained multi-scale fusion network, respectively. Next, the multi-scale fusion network is connected to the trained backbone network, and the controller obtains the trained fault detection model.

[0075] Furthermore, Figure 4 is a schematic diagram of the network structure of the fault detection model. The controller inputs the internal image of the module into the backbone network of the trained fault detection model to extract initial features from the internal image of the module through the backbone network. The backbone network also includes CBS (Cross-Branch Switch), CSP (Cross Stage Partial Network), and SPPF (Spatial Pyramid Pooling-Fast). Among them, CBS is composed of Conv (convolutional layer), BN (Batch Normalization), and SILU (Sigmoid Linear Unit). Residual blocks can also be obtained by performing residual connections between multiple CBSs. For example, Resx represents the x-th residual block in the Residual Block structure. The initial features and module content images are then input into a multi-scale fusion network within a trained fault detection model. This network performs feature stitching (Contact) on the initial features to obtain higher-level processed features. Next, the processed features and module content images are input into a first prediction network and a second prediction network, respectively. The first prediction network uses the processed features to identify faults in the module's internal images, specifically wiring terminals and screws, yielding wiring fault detection results. Simultaneously, the second prediction network uses the processed features to identify faults in the module's internal images, specifically battery bulging and battery leakage, yielding battery fault detection results. The controller then combines the wiring fault detection results and the battery fault detection results to form the target fault detection result for the energy storage module.

[0076] In practical applications, lightweight networks can be used in the backbone network to improve its feature extraction capabilities and increase data processing speed. Furthermore, loss functions can be used to balance the output loss of the prediction network, thereby improving its inference accuracy.

[0077] Currently, image processing models and algorithms are highly complex, resulting in high latency in image display after inference, with single-frame inference time reaching 50ms. To address this issue, this embodiment incorporates a graphics processing unit (GPU) within the processor and deploys a high-performance deep learning inference optimizer on top of it to accelerate fault detection and further reduce the detection latency of the fault detection model. After acceleration, the single-frame inference time is stabilized below 15ms, representing a 70% improvement in inference speed, a significant increase, and the image display is smooth.

[0078] In this embodiment, a fault detection model is used to identify faults in the module's internal images, such as those related to wiring terminals and screws, as well as those related to battery bulging and leakage. The model then comprehensively judges the target fault detection results of the energy storage module based on both wiring fault detection results and battery fault detection results, thereby improving the accuracy of fault detection inside the energy storage module.

[0079] In one embodiment, after obtaining the target fault detection result based on the wiring fault detection result and the battery fault detection result in step S303, the method further includes: annotating the internal image of the module based on the target fault detection result to obtain the annotated internal image of the module; and displaying the annotated internal image of the module.

[0080] Specifically, the controller can set a probability threshold of 0.7 for the predicted probability in the target fault detection result. This means that annotation is only performed when the predicted probability is greater than 0.7, avoiding duplicate and inaccurate annotations and thus further improving recognition accuracy. When annotation is required, if the target fault detection result indicates normal behavior, the controller marks the wiring and battery in the module's internal image according to the first annotation mode; if the target fault detection result indicates abnormal behavior, the controller marks the wiring and battery in the module's internal image according to the second annotation mode. Finally, the controller obtains the annotated module internal image and displays it on the interface. The first annotation mode is used to add annotation boxes to the wiring and / or battery, and to add a status indicator to these boxes. This status indicator reflects that the fault detection result for the wiring and / or battery indicates normal behavior, and also indicates the predicted probability corresponding to the fault detection result. The second annotation mode is used to add annotation boxes with different styles from the first annotation mode to the wiring and / or battery, and to add status indicators of different types to the annotation boxes. The status indicators are used to reflect the abnormality of the fault detection results of the wiring and / or battery, and to indicate the predicted probability corresponding to the fault detection results.

[0081] In practical applications, Figure 5 is a schematic diagram of the internal image of the labeled module. Figure 5 illustrates two labeled internal images of the module. Solid lines represent normal operation, and dashed lines represent abnormal operation. Additionally, different colored boxes can be used to represent normal and abnormal operation respectively; for example, a green box can represent normal operation, and a red box can represent abnormal operation. The text "yes1" above the solid lines indicates that the battery is normal, and "yes2" indicates that the wiring is normal. The text "no1" above the dashed lines indicates that the battery is abnormal, and "no2" indicates that the wiring is abnormal. The numbers following the text represent the detection probabilities output by the fault detection model. For example, "yes1: 0.95" indicates a 95% probability that the battery is normal, "no1: 0.90" indicates a 90% probability that the battery is abnormal, "no2: 0.95" indicates a 95% probability that the wiring is abnormal, and "yes2: 0.91" indicates a 91% probability that the wiring is normal.

[0082] In this embodiment, the decision to annotate the internal image of the module can be made based on whether the predicted probability in the target fault detection result is greater than the probability threshold, which further improves the fault identification accuracy. In addition, different annotation modes are adopted for the internal image of the module according to whether the target fault detection result is normal or abnormal. Finally, the annotated internal image of the module is displayed on the interface, realizing the visualization of the fault identification result, which is convenient for users to view.

[0083] In one embodiment, step S202, which involves acquiring images of the inside of the energy storage module from the target detection angle using an internal vision probe, specifically includes: acquiring brightness information of the inside of the energy storage module; determining multiple illumination brightness levels for the internal vision probe based on the brightness information; and controlling the internal vision probe to acquire images of the inside of the module under multiple illumination brightness levels at the target detection angle.

[0084] The internal vision probe is also equipped with a photosensitive sensor and a lighting lamp.

[0085] Specifically, the interior of an energy storage module is typically dimly lit. After an internal vision probe enters the module, its photosensor acquires brightness information about the module's interior and transmits this information to the controller via a transmission interface. Based on the received brightness information, the controller calculates a suitable candidate illumination range for the module's interior and determines multiple illumination levels within that range. It then controls the internal vision probe to capture images at each target detection angle using these multiple illumination levels, thus obtaining images of the module's interior under different illumination levels for each target detection angle.

[0086] In this embodiment, multiple illumination brightness levels of the internal vision probe are determined by the brightness information inside the energy storage module. Then, the internal vision probe is controlled to collect images of the module's interior under different illumination brightness levels at each target detection angle, which improves the diversity of the images inside the module and provides richer feature information for the fault detection model. This is beneficial to improving the accuracy of the target fault detection results output by the fault detection model, thereby improving the reliability of fault detection of the energy storage module.

[0087] In one embodiment, step S201 above, which determines the target detection angle of the internal vision probe based on the battery position information of the energy storage module, specifically includes the following: obtaining the first detection angle of the internal vision probe based on the top position of the battery in the energy storage module; obtaining the second detection angle of the internal vision probe based on the bottom position of the battery in the energy storage module; and obtaining the target detection angle of the internal vision probe based on the first detection angle and the second detection angle.

[0088] Specifically, the controller can calculate a first detection angle for photographing the top of the battery in the energy storage module based on the battery top position, the size information of the internal vision probe, and the shooting position information of the internal vision probe inside the energy storage module. The controller can also calculate a second detection angle for photographing the bottom of the battery based on the battery bottom position, the size information of the internal vision probe, and the shooting position information of the internal vision probe inside the energy storage module. Both the first and second detection angles are set as the target detection angles for the internal vision probe.

[0089] The first detection angle is used to detect the wiring above the battery in the energy storage module to determine if there is a wiring fault (such as a warped terminal or loose screws); the second detection angle is used to detect the battery at the bottom of the battery in the energy storage module to determine if there is any battery abnormality (such as battery bulging or battery leakage).

[0090] In this embodiment, the first and second detection angles of the internal vision probe are calculated based on the top and bottom positions of the battery in the energy storage module. This allows for observation of the wiring and battery conditions within the energy storage module from multiple different target detection angles, providing multifaceted image data for fault detection of the energy storage module and a reliable data source for subsequent detection of faults in the wiring and battery aspects of the energy storage module.

[0091] In one embodiment, as shown in Figure 6, another method for detecting faults in an energy storage module is provided. Taking the application of this method to the controller in Figure 1 as an example, the method includes the following steps:

[0092] Step S601: Determine the target detection angle of the internal vision probe based on the battery position information of the energy storage module.

[0093] Step S602: Control the internal vision probe to enter the interior of the energy storage module and obtain the brightness information inside the energy storage module; determine multiple illumination brightnesses of the internal vision probe based on the brightness information.

[0094] Step S603: Control the internal vision probe at the target detection angle to acquire internal images of the module under multiple lighting conditions.

[0095] Step S604: Using the fault detection model, perform fault identification on the internal image of the module for the wiring terminals and screws, and obtain the wiring fault detection result.

[0096] Step S605: Using the fault detection model, perform fault identification on the internal images of the module for battery bulging and battery leakage, and obtain battery fault detection results.

[0097] Step S606: Based on the wiring fault detection results and the battery fault detection results, obtain the target fault detection results.

[0098] Step S607: Based on the target fault detection results, the internal image of the module is annotated to obtain the annotated internal image of the module.

[0099] Step S608: Display the internal image of the labeled module.

[0100] The above-mentioned energy storage module fault detection method can achieve the following beneficial effects: by acquiring images of the inside of the energy storage module through an internal vision probe, and analyzing and identifying faults inside the energy storage module based on the acquired images, the convenience of fault detection of the energy storage module is improved. It can also promptly remind maintenance personnel to handle the situation in a timely manner, prevent safety accidents such as fires, protect personnel and property safety, and ensure the normal operation of the energy storage module.

[0101] To more clearly illustrate the energy storage module fault detection method provided in this disclosure, a specific embodiment is given below to describe the above-mentioned energy storage module fault detection method. Another energy storage module fault detection method is provided, which can be applied to the controller in Figure 1, and specifically includes the following:

[0102] S1: Insert the energy storage module into the specially designed internal vision probe;

[0103] S2: Drive the vision inspection probe through the controller to obtain visual image information inside the energy storage module;

[0104] S3: The controller uses deep learning models and databases to identify battery and wiring faults, and can mark the fault location and display it on the controller's display screen in real time.

[0105] In this embodiment, an internal visual inspection probe specifically designed for electrochemical energy storage modules is used to collect and analyze battery anomalies and wiring faults within the energy storage module. This allows for simple and reliable fault identification. The device can effectively identify faults, alerting operation and maintenance personnel to address them promptly, preventing safety accidents such as fires, protecting personnel and property safety, and ensuring the normal operation of the energy storage system.

[0106] In one embodiment, as shown in Figure 7, a fault detection system for an energy storage module is provided. The system includes: an internal vision probe, a controller, and an energy storage module. The size of the internal vision probe is much smaller than the size of the energy storage module. The controller is used to determine the target detection angle of the internal vision probe based on the battery location information of the energy storage module, and to control the internal vision probe to acquire images of the internal components of the energy storage module according to the target detection angle. The internal vision probe is used to send the acquired images of the internal components to the controller. The controller is also used to perform fault identification on the received images of the internal components using a trained fault detection model to obtain fault detection results for the energy storage module. The fault detection results include battery fault detection results for the batteries in the energy storage module and wiring fault detection results for the wiring in the energy storage module.

[0107] Specifically, the controller is equipped with at least a display unit, an operating system, a central processing unit (CPU), a graphics processing unit (GPU), and storage media; wherein the operating system includes Windows 10 or above, the CPU includes an i5-11400H 2.70GHz or above, the GPU includes an RTX3060 6G or above, and the memory includes 16G or above. The controller can deploy deep learning models (such as fault detection models) to efficiently process the internal images of the module acquired by the internal vision probe through the GPU. The specific interaction process between the controller, the internal vision probe, and the energy storage module is detailed in the above embodiments and will not be repeated here.

[0108] In this embodiment, images of the energy storage module are captured by an internal vision probe, enabling the controller to analyze and identify internal faults based on the captured images. This alerts maintenance personnel to address the issues promptly, preventing fires and other safety accidents, ensuring the safety of personnel and property, and guaranteeing the normal operation of the energy storage module.

[0109] In one embodiment, the internal vision probe is also equipped with multiple lights; the controller is also used to control the illumination brightness of the multiple lights of the internal vision probe, and to collect images of the inside of the energy storage module under different illumination brightness according to the target detection angle.

[0110] The lighting can be LED (light emitting diode) lamps.

[0111] Specifically, the internal vision probe can be equipped with six LEDs, and the brightness of the LEDs can be adjusted to adapt to image acquisition under various lighting intensities. The resolution of the image acquisition unit of the internal vision probe is set to 640×480, and the focal length is set to 3-10cm. At each target detection angle, the controller controls the internal vision probe's illumination lamps to sequentially illuminate with different brightness levels, thereby controlling the internal vision probe to acquire internal module images at each target detection angle under different lighting conditions.

[0112] In this embodiment, the internal vision probe is controlled to acquire images of the module's interior under different lighting conditions at each target detection angle. This increases the diversity of the images inside the module, provides richer feature information for the fault detection model, and helps improve the accuracy of the target fault detection results output by the fault detection model, thereby improving the reliability of fault detection of the energy storage module.

[0113] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0114] Based on the same inventive concept, this application also provides an energy storage module fault detection device for implementing the above-mentioned energy storage module fault detection method. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more energy storage module fault detection device embodiments provided below can be found in the limitations of the energy storage module fault detection method described above, and will not be repeated here.

[0115] In one embodiment, as shown in FIG8, an energy storage module fault detection device 800 is provided, comprising: a detection angle determination module 801, an internal image acquisition module 802, and a detection result acquisition module 803, wherein:

[0116] The detection angle determination module 801 is used to determine the target detection angle of the internal vision probe based on the battery position information of the energy storage module.

[0117] The internal image acquisition module 802 is used to control the internal vision probe to enter the interior of the energy storage module, so as to acquire the internal image of the energy storage module according to the target detection angle.

[0118] The detection result acquisition module 803 is used to identify faults in the internal images of the module through a trained fault detection model to obtain the target fault detection results of the energy storage module; the target fault detection results include the battery fault detection results and wiring fault detection results of the energy storage module.

[0119] In one embodiment, the detection result obtaining module 803 is further configured to use a fault detection model to perform fault identification on the internal image of the module for the wiring terminals and screws of the wiring terminals, and obtain wiring fault detection results; use a fault detection model to perform fault identification on the internal image of the module for battery bulging and battery leakage, and obtain battery fault detection results; and obtain target fault detection results based on the wiring fault detection results and battery fault detection results.

[0120] In one embodiment, the energy storage module fault detection device 800 further includes an image annotation and display module, which is used to annotate the internal image of the module according to the target fault detection result, to obtain the annotated internal image of the module, and to display the annotated internal image of the module.

[0121] In one embodiment, the internal image acquisition module 802 is further configured to acquire brightness information inside the energy storage module; determine multiple illumination brightness levels of the internal vision probe based on the brightness information; and control the internal vision probe at the target detection angle to acquire internal images of the module under multiple illumination brightness levels.

[0122] In one embodiment, the detection angle determination module 801 is further configured to obtain a first detection angle of the internal vision probe based on the top position of the battery of the energy storage module; obtain a second detection angle of the internal vision probe based on the bottom position of the battery of the energy storage module; and obtain a target detection angle of the internal vision probe based on the first detection angle and the second detection angle.

[0123] Each module in the aforementioned energy storage module fault detection device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0124] In one embodiment, a computer device is provided, which may be a controller, and its internal structure diagram is shown in Figure 9. The computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for detecting faults in an energy storage module. The display unit of the computer device is used to form a visually visible image and may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0125] Those skilled in the art will understand that the structure shown in Figure 9 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or may combine certain components, or may have different component arrangements.

[0126] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0127] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0128] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0129] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0130] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0131] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for fault detection of an energy storage module, characterized in that, The method comprises: According to the battery position information of the energy storage module, the target detection angle of the internal visual probe is determined; The internal visual probe is controlled to enter the inside of the energy storage module, so that the internal visual probe collects a module internal image of the energy storage module inside the energy storage module according to the target detection angle; Through a trained fault detection model, the module internal image is subjected to fault identification, and a target fault detection result of the energy storage module is obtained; the target fault detection result comprises a battery fault detection result and a wiring fault detection result of the energy storage module.

2. The method of claim 1, wherein, The target fault detection result is obtained by the trained fault detection model, and the module internal image is subjected to fault identification, and the target fault detection result of the energy storage module is obtained, comprising: Through the fault detection model, the module internal image is subjected to fault identification for the wiring terminal and the screw of the wiring terminal, and the wiring fault detection result is obtained; Through the fault detection model, the module internal image is subjected to fault identification for the battery bulge and the battery leakage, and the battery fault detection result is obtained; According to the wiring fault detection result and the battery fault detection result, the target fault detection result is obtained.

3. The method of claim 2, wherein, After obtaining the target fault detection result, it further comprises: according to the target fault detection result, the module internal image is labeled to obtain a labeled module internal image; the labeled module internal image is displayed.

4. The method of claim 1, wherein, The module internal image of the energy storage module is collected by the internal visual probe inside the energy storage module according to the target detection angle, comprising: Obtain the brightness information of the inside of the energy storage module; According to the brightness information, a plurality of illumination brightnesses of the internal visual probe are determined; The internal visual probe is controlled to collect a plurality of module internal images under the illumination brightness at the target detection angle.

5. The method of claim 1, wherein, According to the battery position information of the energy storage module, the target detection angle of the internal visual probe is determined, comprising: According to the top position of the battery of the energy storage module, a first detection angle of the internal visual probe is obtained; According to the bottom position of the battery of the energy storage module, a second detection angle of the internal visual probe is obtained; According to the first detection angle and the second detection angle, a target detection angle of the internal visual probe is obtained.

6. An energy storage module fault detection apparatus, comprising: The device comprises: A detection angle determination module is configured to determine a target detection angle of an internal visual probe according to battery position information of an energy storage module; An internal image collection module is configured to control the internal visual probe to enter the inside of the energy storage module, so that the internal visual probe collects a module internal image of the energy storage module inside the energy storage module according to the target detection angle; A detection result obtaining module is configured to perform fault identification on the module internal image through a trained fault detection model, and obtain a target fault detection result of the energy storage module; the target fault detection result comprises a battery fault detection result and a wiring fault detection result of the energy storage module.

7. An energy storage module fault detection system, comprising: The system comprises an internal visual probe, a controller and an energy storage module; the size of the internal visual probe is much smaller than the size of the energy storage module; The controller is configured to determine a target detection angle of the internal visual probe according to battery position information of the energy storage module, and control the internal visual probe to collect a module internal image of the energy storage module at the target detection angle inside the energy storage module. The internal visual probe is configured to send the collected module internal image to the controller. The controller is further configured to perform fault identification on the received module internal image by using a trained fault detection model, and obtain a fault detection result of the energy storage module; the fault detection result comprises a battery fault detection result for a battery in the energy storage module and a wiring fault detection result for a wiring in the energy storage module.

8. The system of claim 7, wherein, The internal visual probe is further provided with a plurality of illuminating lamps. The controller is further configured to control the illumination brightness of the plurality of illuminating lamps of the internal visual probe, and collect module internal images under different illumination brightness at the target detection angle inside the energy storage module. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 5.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

11. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 5.

Images