Liquid leakage monitoring and positioning method, system and equipment for flow battery energy storage system and medium

Abstract

The invention relates to a liquid leakage monitoring and positioning method, system and equipment for a flow battery energy storage system, and a medium. The method comprises the following steps: determining whether liquid leakage occurs according to whether insulation reduction occurs in the flow battery energy storage system; acquiring a resistance value of a liquid leakage detection line arranged on the electrolyte pipeline, and determining whether liquid leakage occurs in the electrolyte pipeline or not and a liquid leakage position when liquid leakage occurs according to the resistance value; video data of the flow battery energy storage system are obtained through a camera device arranged at a preset position, the video data are identified through a pre-established liquid leakage detection neural network model, and whether liquid leakage occurs or not and the liquid leakage position when liquid leakage occurs are determined. And comprehensively determining whether liquid leakage occurs in the liquid flow energy storage system or not and the liquid leakage position when liquid leakage occurs. Through combination of various means, the accuracy of liquid leakage judgment is improved, liquid leakage can be found and solved in time, and harm expansion is prevented. And meanwhile, the detection result is not easily influenced by environmental factors, and the anti-interference capability is relatively high.

Description

Technical Field

[0001] The present invention belongs to the technical field of power station operation, and in particular relates to a method, system, electronic equipment and storage medium for monitoring and locating leakage of a liquid flow battery energy storage system. Background Art

[0002] As the global demand for clean energy grows, battery energy storage technology, as an important energy storage method, has been widely used. Among them, flow batteries are widely used in power storage, backup power supply and other fields due to their high efficiency, safety and environmental protection.

[0003] However, during the operation of flow batteries, due to the flow and reaction of electrolytes, leakage may occur, which will not only affect the performance and life of the battery, but may also cause safety problems. Therefore, how to effectively determine and locate the leakage position of flow batteries is of great significance to ensure the safe operation of the battery and increase its service life. Summary of the invention

[0004] To solve the above problems, the present invention provides a method, system, electronic device and storage medium for monitoring and locating leakage in a flow battery energy storage system. The present invention improves the accuracy of leakage determination by combining multiple means, and can timely discover and solve the problem to prevent the damage from expanding.

[0005] In order to solve the above technical problems, the first aspect of the present invention provides a method for monitoring and locating leakage of a flow battery energy storage system, the method comprising:

[0006] Performing insulation testing on the liquid flow battery energy storage system, and determining whether leakage occurs according to whether insulation reduction occurs in the liquid flow battery energy storage system;

[0007] Obtaining a resistance value of a leakage detection line disposed on an electrolyte pipeline, and determining whether leakage occurs in the electrolyte pipeline and a leakage position when leakage occurs according to the resistance value;

[0008] Acquire video data of the liquid flow battery energy storage system through a camera device arranged at a preset position, identify the video data through a pre-established leakage detection neural network model, and determine whether leakage occurs and the leakage position when leakage occurs;

[0009] The above steps are combined to determine whether the liquid flow energy storage system has leakage and the leakage position when leakage occurs.

[0010] According to a preferred embodiment of the present invention, the method further comprises:

[0011] For the horizontally arranged electrolyte pipeline, the leakage detection line is arranged on the vertical lower surface of the electrolyte pipeline;

[0012] For the electrolyte pipeline arranged vertically, the leakage detection wires are wound around the outer surface of the electrolyte pipeline at intervals.

[0013] According to a preferred embodiment of the present invention, the step of obtaining a resistance value of a leakage detection line disposed on an electrolyte pipeline and determining whether leakage occurs in the electrolyte pipeline and a leakage position when leakage occurs according to the resistance value includes:

[0014] Obtaining the resistance value of the leakage detection line;

[0015] When the resistance value of the leakage detection line changes, it is determined that leakage occurs in the electrolyte pipeline;

[0016] When leakage occurs in the electrolyte pipeline, based on a calibration table of leakage resistance value and detection line length, a leakage detection line length value corresponding to the resistance value is determined;

[0017] The leakage position is determined by the length value of the leakage detection line.

[0018] According to a preferred embodiment of the present invention, the method further comprises:

[0019] Performing a leakage test on the leakage detection line, and when leakage occurs at different positions of the leakage detection line, recording the detection resistance value and the detection length value corresponding to the leakage detection line;

[0020] The detection resistance values ​​and detection length values ​​are matched one by one to generate a calibration table of leakage resistance values ​​and detection line lengths.

[0021] According to a preferred embodiment of the present invention, the method further comprises:

[0022] Acquiring historical video data of the flow battery energy storage system;

[0023] Extracting the video frame where the leakage occurs from the historical video data, and marking the leakage position in the video frame;

[0024] The video frames with the leakage position marked and the video frames without leakage in the historical video data are input into the convolutional neural network for training, and the leakage detection neural network model is obtained after the training is completed.

[0025] According to a preferred embodiment of the present invention, the method further comprises:

[0026] When the insulation of the flow battery energy storage system is reduced and it is determined that leakage has occurred, or when it is determined that leakage has occurred in the electrolyte pipeline according to the resistance value, the leakage position where the leakage has occurred is marked in the real-time video frame of the video data;

[0027] The liquid leakage detection neural network model is trained through the real-time video frames to obtain the optimized liquid leakage detection neural network model.

[0028] According to a preferred embodiment of the present invention, the method further comprises:

[0029] When leakage occurs at any position of the liquid flow battery energy storage system, an alarm is issued.

[0030] In order to solve the above technical problems, the second aspect of the present invention proposes a liquid flow battery energy storage system leakage monitoring and positioning system, the system comprising:

[0031] An insulation detection device connected to the liquid flow battery energy storage system, used to perform insulation detection on the liquid flow battery energy storage system;

[0032] A leakage detection line arranged on the electrolyte pipeline of the liquid flow battery energy storage system, and a resistance value detection device connected to the leakage detection line;

[0033] A camera device arranged at a preset position, used to obtain video data of the liquid flow battery energy storage system;

[0034] The data processor connected to the insulation detection device, the resistance value detection device and the camera device respectively is used to determine whether leakage occurs according to whether insulation reduction occurs in the liquid flow battery energy storage system, and to determine whether leakage occurs in the electrolyte pipeline and the leakage position when leakage occurs according to the resistance value, and to identify the video data through a pre-established leakage detection neural network model to determine whether leakage occurs and the leakage position when leakage occurs, and to comprehensively determine whether leakage occurs in the liquid flow energy storage system and the leakage position when leakage occurs.

[0035] In order to solve the above technical problem, the third aspect of the present invention provides an electronic device, comprising:

[0036] Processor; and

[0037] A memory storing computer executable instructions, wherein when the computer executable instructions are executed, the processor executes the method described in any one of the above embodiments.

[0038] In order to solve the above technical problems, the fourth aspect of the present invention proposes a computer storage medium, wherein the computer storage medium stores one or more programs, and when the one or more programs are executed by a processor, the method described in any one of the above embodiments is implemented.

[0039] Compared with the prior art, the present invention has the following advantages: the present invention detects leakage of the energy storage system by online monitoring of the system insulation resistance, deploys the leakage detection line on the pipeline, detects pipeline leakage and locates the leakage position, realizes accurate positioning of the leakage position, monitors the video information of the energy storage system, uses a neural network model to identify the video, judges the leakage and locates the leakage position, realizes automated leakage detection and positioning, avoids manual intervention, improves operational efficiency, is conducive to timely handling of leakage problems, and avoids the difficulties caused by the inability to accurately locate the leakage position. By combining a variety of means, the accuracy of leakage judgment is improved, and it can be discovered and solved in time to prevent the damage from expanding. At the same time, the detection results of the present invention are not easily affected by environmental factors and have strong anti-interference capabilities.

[0040] Other features and advantages of the present disclosure will be described in the following description, and partly become apparent from the description, or be understood by implementing the present disclosure. The purpose and other advantages of the present disclosure can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0042] Figure 1 A first flow chart of a method for monitoring and locating leakage in a flow battery energy storage system according to an embodiment of the present disclosure is shown;

[0043] Figure 2 A schematic diagram showing the structure of a liquid leakage detection line deployed in a horizontal electrolyte pipeline according to an embodiment of the present disclosure is shown;

[0044] Figure 3 A schematic diagram showing a structure in which a leakage detection line is deployed in a vertical electrolyte pipeline according to an embodiment of the present disclosure;

[0045] Figure 4 A second flow chart of a method for monitoring and locating leakage in a flow battery energy storage system according to an embodiment of the present disclosure is shown;

[0046] Figure 5 A block diagram of a liquid flow battery energy storage system leakage monitoring and positioning system according to an embodiment of the present disclosure is shown;

[0047] Figure 6 A schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure is shown.

[0048] In the figure: 1. Insulation layer; 2. Leakage detection line; 3. Vertical upper surface of horizontal electrolyte pipeline; 4. Vertical lower surface of horizontal electrolyte pipeline. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0050] The same reference numerals in the drawings represent the same or similar elements, components or parts, and thus the repeated description of the same or similar elements, components or parts may be omitted below. It should also be understood that although the first, second, third and other attributives representing the numbers may be used herein to describe various devices, elements, components or parts, these devices, elements, components or parts should not be limited by these attributives. In other words, these attributives are only used to distinguish one from another. For example, the first device may also be called the second device, but it does not deviate from the essential technical solution of the present invention. In addition, the terms "and / or" and "and / or" refer to all combinations including any one or more of the listed items.

[0051] See also Figure 1 , Figure 1 This is a flow chart of a method for monitoring and locating leakage in a flow battery energy storage system provided by the present invention. Figure 1 As shown, the method includes:

[0052] S11. Perform insulation testing on the liquid flow battery energy storage system, and determine whether leakage occurs based on whether insulation degradation occurs in the liquid flow battery energy storage system.

[0053] In this embodiment, the liquid flow battery energy storage system includes: a container-type liquid flow battery energy storage system, specifically, for example, a container-type iron-chromium liquid flow battery energy storage system, which utilizes the redox reaction of iron and chromium ions dissolved in the electrolyte to store and release electrical energy.

[0054] In this embodiment, a systematic insulation resistance test is performed on the flow battery energy storage system. The container energy storage system is generally equipped with an insulation detection function by the PCS (energy storage converter) and the BMS (battery management system), which can monitor and alarm when the insulation resistance of the system is low.

[0055] In this embodiment, insulation degradation refers to the degradation of the insulation performance of the insulating material, which causes electrical safety hazards of electrical equipment or lines. In electrical equipment, insulating materials play an important role in protecting the internal circuits of electrical appliances from external interference. However, when the insulation performance of the insulating material is degraded, the safety of electrical equipment and lines will be threatened.

[0056] In this embodiment, this scheme can reuse this function to make a preliminary judgment on the leakage situation. In cases of non-electrical breakdown, damage to electrical related equipment, etc. (the monitorable equipment has no fault feedback of its own), it is highly likely that the leakage is caused by reduced insulation. Based on this point, a preliminary judgment on the occurrence of leakage can be made.

[0057] S12, obtaining the resistance value of the leakage detection line 2 arranged on the electrolyte pipeline, and determining whether the electrolyte pipeline is leaking and the leakage position when leakage occurs according to the resistance value.

[0058] In this embodiment, an acid-resistant leakage detection line can be deployed to increase the service life of the leakage detection line 2 and avoid frequent maintenance of the leakage detection line 2. The change in the resistance value of the leakage detection line 2 is used to determine whether the electrolyte pipeline is leaking and the location of the leakage. Specifically, after the leakage occurs at the leakage location, the electrolyte will flow out and contact the leakage detection line 2, causing the resistance value of the leakage detection line 2 to change, and based on the change in the resistance value of the leakage detection line 2, the location of the leakage is confirmed.

[0059] In this embodiment, the horizontal electrolyte pipeline is Figure 2 As shown in the figure, the leakage detection line 2 is arranged at the lower end of the outer wall of the pipeline. The leaked electrolyte will be collected on the vertical lower surface 4 of the horizontal electrolyte pipeline due to gravity. The probability of electrolyte appearing on the vertical upper surface 3 of the horizontal electrolyte pipeline is also small. Figure 3 As shown in the figure, the leakage detection line 2 is arranged around the outer wall of the pipeline by an interval winding method. The leakage detection line 2 can be wound at a preset interval, or the deployment interval can be adjusted according to the welding point or connection point of the electrolyte pipeline. In this embodiment, the acid-resistant leakage detection line is arranged between the electrolyte pipeline and the insulation layer 1, which can effectively determine the leakage in the insulation layer 1, improve the detection efficiency, and deal with the leakage problem in time.

[0060] Specifically, calibration points can be set for the leakage detection line 2, and the resistance value of the leakage detection line 2 when leakage occurs at each calibration point can be detected in turn as a reference resistance value. The resistance value detected in real time is compared with the reference resistance value, and the calibration point corresponding to the reference resistance value closest to the resistance value is used as the leakage position, so as to determine the leakage position when leakage occurs.

[0061] In this embodiment, since most of the electrolyte leakage points are the pipe welds, butt flanges, pipe seat threads and other connections of the pipeline process system, all pipe welds, butt flanges, pipe seat threads and other connections can be used as calibration points to calibrate the corresponding leakage resistance value and detection line length value.

[0062] In this solution, the binary method can be used to quickly find the leakage position interval where the resistance value detected in real time is located according to the calibrated leakage resistance value and the detection line length value, and the real-time leakage position can be calibrated using the following calculation method:

[0063]

[0064] Among them, r x Indicates the resistance value of leakage detection line 2 detected in real time; r j-1 and r j and j-1 and j The j-1th and jth adjacent leakage calibration points have been calibrated and their corresponding detection line length values; j∈[1,N], N is the total number of calibration points, r θ Indicates the detection error tolerance threshold.

[0065] The resistance values ​​of the leakage calibration points obtained by the above scheme and the corresponding detection line length values ​​can be used to establish a calibration table, and the leakage position can be quickly determined through the calibration table. Furthermore, more calibration points can be added to the leakage detection line 2 to achieve more accurate leakage position determination. For example, a leakage test is performed on the leakage detection line 2. When leakage occurs at different positions of the leakage detection line 2, the detection resistance value and detection length value corresponding to the leakage detection line 2 are recorded; each detection resistance value and detection length value are matched one by one to generate a calibration table of leakage resistance value and detection line length. The more calibration points there are, the more accurately the final calibration table can determine the leakage position.

[0066] The leakage position of the electrolyte can be determined through the above calibration table. Specifically, the resistance value of the leakage detection line 2 is obtained; when the resistance value of the leakage detection line 2 changes, it is determined that the electrolyte pipeline is leaking; when the electrolyte pipeline is leaking, based on the leakage resistance value and the detection line length calibration table, the length value of the leakage detection line 2 corresponding to the resistance value is determined; the leakage position is determined by the length value of the leakage detection line 2.

[0067] S13, acquiring video data of the liquid flow battery energy storage system through a camera device set at a preset position, identifying the video data through a pre-established leakage detection neural network model, and determining whether leakage occurs and the leakage location when leakage occurs.

[0068] In this embodiment, model pre-training and cloud-edge collaboration are used for installation and deployment. That is, a neural network computing model with fixed parameters is deployed at the edge (the site of the flow battery energy storage system where the surveillance camera is located), and the on-site cameras of all flow battery energy storage systems transmit real-time image data to the cloud server. The edge uses the model for real-time calculation to determine the occurrence and location of the leakage.

[0069] In this embodiment, the cloud server is a self-built server to ensure the security requirements of data generation, transmission, and storage. A computer with GPU acceleration function is used in the cloud, and the deep learning framework PyTorch is installed. The training batch size is set to 64, the learning rate is 0.01, and the number of iterations is 1000. The collected video information is sliced, and the size of each frame image is set to 224*224 pixels, and then input into the convolutional neural network for training. After the training is completed, the network can automatically identify the leakage of the liquid flow battery energy storage system and output the coordinates of the leakage location.

[0070] In this embodiment, the cloud server can be set to automatically send the cloud neural network model parameters to all flow battery energy storage systems after receiving and training the data of every five fault leakage situations, so as to update and synchronize the model. While increasing the detection accuracy, it can also reduce the network occupancy and edge CPU overhead.

[0071] In this embodiment, when leakage occurs at any position of the liquid flow battery energy storage system, an alarm is issued.

[0072] S14, combining the above steps to determine whether the liquid flow energy storage system has leakage and the leakage location when leakage occurs.

[0073] In this embodiment, the above three methods are used in combination: the above three leakage detection methods are organically combined to form a complete set of comprehensive leakage judgment and positioning system for container flow battery energy storage system, which can accurately judge and quickly locate the leakage of the flow battery energy storage system, and effectively prevent the damage caused by the leakage from expanding. Specifically, the steps in this embodiment do not limit the execution order of this scheme, but are one of the embodiments of this scheme. The three steps of this scheme can be executed in any order, and this scheme will not be repeated.

[0074] The present invention detects leakage of the energy storage system by online monitoring of the system insulation resistance, deploys the leakage detection line 2 on the pipeline, detects pipeline leakage and locates the leakage position, realizes accurate positioning of the leakage position, monitors the video information of the energy storage system, uses a neural network model to identify the video, judges the leakage and locates the leakage position, realizes automated leakage detection and positioning, avoids manual intervention, improves operational efficiency, is conducive to timely handling of leakage problems, and avoids the difficulties caused by the inability to accurately locate the leakage position. By combining a variety of means, the accuracy of leakage judgment is improved, and it can be discovered and solved in time to prevent the expansion of hazards. At the same time, the detection results of the present invention are not easily affected by environmental factors and have strong anti-interference capabilities.

[0075] See also Figure 4 , Figure 4 The second flow chart of the method for monitoring and locating leakage of a flow battery energy storage system provided by the present invention is as follows: Figure 4 As shown, the following steps are included:

[0076] S21. Obtain historical video data of the liquid flow battery energy storage system.

[0077] In this embodiment, in order to improve the accuracy of the constructed model for leakage detection and avoid a large amount of data storage affecting system operation, when leakage occurs in the flow battery energy storage system, the video data of the leakage can be persistently stored, and a portion of the video data without leakage can be periodically extracted for storage to reduce the amount of data storage.

[0078] In this embodiment, the amount of video data without leakage can be consistent with the amount of video data with leakage, and the amount of positive samples and negative samples finally used to train the model is not much different, which can effectively improve the model's recognition accuracy for leakage detection.

[0079] S22, extracting the video frame where the leakage occurs from the historical video data, and marking the leakage position in the video frame.

[0080] In this embodiment, in this step, the stored video data of the leakage is directly extracted, and the leakage position of each video frame where the leakage occurs is marked.

[0081] S23, inputting the video frames with the leakage position marked and the video frames without leakage in the historical video data into the convolutional neural network for training, and obtaining the leakage detection neural network model after the training is completed.

[0082] In this embodiment, the video frames with the leakage position marked and the video frames without leakage in the historical video data are input as positive and negative samples into the convolutional neural network for training and learning. Specifically, the video frames with the leakage position marked are input into the convolutional neural network to generate a recognition result. The accuracy of the recognition is determined based on the relative deviation between the recognition result and the marked leakage position. The relative deviation can be calculated based on the overlapping area of ​​the recognition result and the leakage position. The larger the overlapping area, the smaller the relative deviation. When the recognition is inaccurate, the convolutional neural network is adjusted. When the convolutional neural network recognizes all the video frames correctly, or recognizes a preset proportion of the video frames correctly, a trained leakage detection neural network model is obtained.

[0083] In this embodiment, when the insulation of the flow battery energy storage system is reduced and leakage is determined to have occurred, or when leakage is determined to have occurred in the electrolyte pipeline based on the resistance value, the leakage location where the leakage occurs is marked in the real-time video frame of the video data; the leakage detection neural network model is trained through the real-time video frame to obtain an optimized leakage detection neural network model.

[0084] In this embodiment, regarding the deployment of the pre-trained model, in the early stage of the project, there is no initial leakage and the situation of monitoring video data under normal conditions. A laboratory test system is used to accumulate data and perform model training deployment.

[0085] The cloud server is common to all projects, and any edge container can be connected to the cloud through configuration, including the laboratory system. For projects implemented later, the edge computing model can be deployed directly using the model parameters trained by the data accumulated from all previous projects. Advantages: Using the same neural network model for training, data accumulation is gradually enriched; using cloud-edge collaboration, the cloud neural network can be trained in real time, the edge computing model can be updated in real time, and the leakage detection precision and accuracy can be improved in real time.

[0086] The cloud-edge asynchronous update method is adopted to increase the stability of the computing model and reduce the network bandwidth requirements and edge CPU performance requirements; the one cloud to multiple edge methods are adopted, which can be applicable to container energy storage systems of any capacity scale, and there is no need to perform model pre-training and initialization for newly built energy storage projects, and existing computing models and parameters can be directly reused.

[0087] See also Figure 5 , Figure 5 The present invention provides a liquid flow battery energy storage system leakage monitoring and positioning system, the system comprising:

[0088] In this embodiment, the insulation detection device connected to the liquid flow battery energy storage system is used to perform insulation detection on the liquid flow battery energy storage system.

[0089] In this embodiment, a leakage detection line 2 is provided on the electrolyte pipeline of the liquid flow battery energy storage system, and a resistance value detection device connected to the leakage detection line 2 is provided.

[0090] In this embodiment, a camera device disposed at a preset position is used to obtain video data of the liquid flow battery energy storage system.

[0091] In this embodiment, the data processor connected to the insulation detection device, the resistance value detection device and the camera device respectively is used to determine whether leakage occurs according to whether insulation reduction occurs in the liquid flow battery energy storage system, and to determine whether leakage occurs in the electrolyte pipeline and the leakage position when leakage occurs according to the resistance value, and to identify the video data through a pre-established leakage detection neural network model to determine whether leakage occurs and the leakage position when leakage occurs, and to comprehensively determine whether leakage occurs in the liquid flow energy storage system and the leakage position when leakage occurs.

[0092] In this embodiment, for a horizontally arranged electrolyte pipeline, the leakage detection line 2 is arranged on the vertical lower surface of the electrolyte pipeline.

[0093] In this embodiment, for the vertically arranged electrolyte pipeline, the leakage detection wires 2 are wound around the outer surface of the electrolyte pipeline at intervals.

[0094] In this embodiment, the data processor is specifically used to determine that leakage has occurred in the electrolyte pipeline when the resistance value of the leakage detection line 2 changes; when leakage has occurred in the electrolyte pipeline, determine the length value of the leakage detection line 2 corresponding to the resistance value based on the calibration table of the leakage resistance value and the detection line length; determine the leakage location by the length value of the leakage detection line 2.

[0095] In this embodiment, the system also includes: a calibration test device, which is connected to the resistance value detection device and the data processor, and is used to perform a leakage test on the leakage detection line 2. When leakage occurs at different positions of the leakage detection line 2, the detection resistance value and the detection length value corresponding to the leakage detection line 2 are recorded, and the detection resistance value and the detection length value corresponding to the leakage detection line 2 are transmitted to the data processor.

[0096] In this embodiment, the data processor is also used to make a one-to-one correspondence between each detection resistance value and detection length value, and generate a calibration table of leakage resistance value and detection line length.

[0097] In this embodiment, the data processor is also used to obtain historical video data of the liquid flow battery energy storage system; extract video frames where leakage occurs from the historical video data, and mark the leakage position in the video frames; input the video frames with the leakage position marked and the video frames in the historical video data where no leakage occurs into the convolutional neural network for training, and obtain the leakage detection neural network model after the training is completed.

[0098] In this embodiment, the data processor is also used to mark the leakage location in the real-time video frame of the video data when the insulation of the liquid flow battery energy storage system is reduced and leakage is determined, or when leakage is determined in the electrolyte pipeline based on the resistance value; and train the leakage detection neural network model through the real-time video frame to obtain an optimized leakage detection neural network model.

[0099] In this embodiment, the system further includes: an alarm device connected to the data processor, which is used to sound an alarm when leakage occurs at any position of the liquid flow battery energy storage system.

[0100] like Figure 6 As shown, an embodiment of the present invention provides an electronic device, including a processor 1110, a communication interface 1120, a memory 1130 and a communication bus 1140, wherein the processor 1110, the communication interface 1120, and the memory 1130 communicate with each other through the communication bus 1140;

[0101] Memory 1130, used for storing computer programs;

[0102] The processor 1110 is used to implement any of the above methods when executing the program stored in the memory 1130.

[0103] In the electronic device provided by the embodiment of the present invention, the processor 1110 determines whether leakage occurs according to whether insulation reduction occurs in the liquid flow battery energy storage system by executing the program stored in the memory 1130, and determines whether leakage occurs in the electrolyte pipeline and the leakage position when leakage occurs according to the resistance value, and identifies video data through a pre-established leakage detection neural network model to determine whether leakage occurs and the leakage position when leakage occurs, and comprehensively determines whether leakage occurs in the liquid flow energy storage system and the leakage position when leakage occurs.

[0104] The communication bus 1140 mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0105] The communication interface 1120 is used for communication between the above electronic device and other devices.

[0106] The memory 1130 may include a random access memory 1130 (RAM), or may include a non-volatile memory 1130 (non-volatile memory), such as at least one disk memory 1130. Optionally, the memory 1130 may also be at least one storage device located away from the processor 1110.

[0107] The above-mentioned processor 1110 can be a general-purpose processor 1110, including a central processing unit 1110 (CPU), a network processor 1110 (NP), etc.; it can also be a digital signal processor 1110 (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0108] An embodiment of the present invention provides a computer-readable storage medium, which stores one or more programs. The one or more programs can be executed by one or more processors 1110 to implement the method of any of the above embodiments.

[0109] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk SolidStateDisk (SSD)), etc.

[0110] Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A method for monitoring and locating leakage in a flow battery energy storage system, characterized in that: The method comprises: Performing insulation testing on the liquid flow battery energy storage system, and determining whether leakage occurs according to whether insulation reduction occurs in the liquid flow battery energy storage system; Obtaining a resistance value of a leakage detection line disposed on an electrolyte pipeline, and determining whether leakage occurs in the electrolyte pipeline and a leakage position when leakage occurs according to the resistance value; Acquire video data of the liquid flow battery energy storage system through a camera device arranged at a preset position, identify the video data through a pre-established leakage detection neural network model, and determine whether leakage occurs and the leakage position when leakage occurs; The above steps are combined to determine whether the liquid flow energy storage system has leakage and the leakage position when leakage occurs.

2. The method according to claim 1, characterized in that The method further comprises: For the horizontally arranged electrolyte pipeline, the leakage detection line is arranged on the vertical lower surface of the electrolyte pipeline; For the electrolyte pipeline arranged vertically, the leakage detection wires are wound around the outer surface of the electrolyte pipeline at intervals.

3. The method according to claim 1, characterized in that: The step of obtaining a resistance value of a leakage detection line disposed on an electrolyte pipeline and determining whether leakage occurs in the electrolyte pipeline and a leakage position when leakage occurs according to the resistance value comprises: Obtaining the resistance value of the leakage detection line; When the resistance value of the leakage detection line changes, it is determined that leakage occurs in the electrolyte pipeline; When leakage occurs in the electrolyte pipeline, based on a calibration table of leakage resistance value and detection line length, a leakage detection line length value corresponding to the resistance value is determined; The leakage position is determined by the length value of the leakage detection line.

4. The method according to claim 3, characterized in that The method further comprises: Performing a leakage test on the leakage detection line, and when leakage occurs at different positions of the leakage detection line, recording the detection resistance value and the detection length value corresponding to the leakage detection line; Each detection resistance value and detection length value is matched one by one to generate a calibration table of leakage resistance value and detection line length.

5. The method according to claim 1, characterized in that The method further comprises: Acquiring historical video data of the flow battery energy storage system; Extracting the video frame where the leakage occurs from the historical video data, and marking the leakage position in the video frame; The video frames with the leakage position marked and the video frames without leakage in the historical video data are input into the convolutional neural network for training, and the leakage detection neural network model is obtained after the training is completed.

6. The method according to claim 5, characterized in that The method further comprises: When the insulation of the flow battery energy storage system is reduced and it is determined that leakage has occurred, or when it is determined that leakage has occurred in the electrolyte pipeline according to the resistance value, the leakage position where the leakage has occurred is marked in the real-time video frame of the video data; The liquid leakage detection neural network model is trained through the real-time video frames to obtain the optimized liquid leakage detection neural network model.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: When leakage occurs at any position of the liquid flow battery energy storage system, an alarm is issued.

8. A liquid flow battery energy storage system leakage monitoring and positioning system, characterized in that: The system comprises: An insulation detection device connected to the liquid flow battery energy storage system, used to perform insulation detection on the liquid flow battery energy storage system; A leakage detection line arranged on the electrolyte pipeline of the liquid flow battery energy storage system, and a resistance value detection device connected to the leakage detection line; A camera device arranged at a preset position, used to obtain video data of the liquid flow battery energy storage system; The data processor connected to the insulation detection device, the resistance value detection device and the camera device respectively is used to determine whether leakage occurs according to whether insulation reduction occurs in the liquid flow battery energy storage system, and to determine whether leakage occurs in the electrolyte pipeline and the leakage position when leakage occurs according to the resistance value, and to identify the video data through a pre-established leakage detection neural network model to determine whether leakage occurs and the leakage position when leakage occurs, and to comprehensively determine whether leakage occurs in the liquid flow energy storage system and the leakage position when leakage occurs.

9. An electronic device, characterized in that: include: processor; as well as A memory storing computer executable instructions which, when executed, cause the processor to perform the method according to any one of claims 1-7.

10. A computer storage medium, characterized in that: in, The computer storage medium stores one or more programs, and when the one or more programs are executed by a processor, the method of any one of claims 1 to 7 is implemented.

Images