Anomaly monitoring method and apparatus for coiled tubing, and electronic device

Abstract

The present application belongs to the technical field of the safety of coiled tubing construction operation. Disclosed are an anomaly monitoring method and apparatus for coiled tubing, and an electronic device. An image collection device is disposed on coiled tubing. The anomaly monitoring method for coiled tubing comprises: acquiring a monitoring video stream from an image collection device, and on the basis of the monitoring video stream, determining a plurality of information lists, wherein each information list comprises a preset number of frames of image data; for each information list, determining abnormal image information on the basis of the image data, wherein the abnormal image information comprises an information list where abnormal image data is located, and the number of frames of the abnormal image data in the information list; and inputting the abnormal image information into a target detection model, so as to determine an anomaly type of the abnormal image data, wherein the target detection model is obtained by means of performing training using, as training data, historical image data of coiled tubing collected by the image collection device, and annotations of the abnormal image data in the historical image data.

Description

Methods, devices and electronic equipment for abnormal monitoring of coiled tubing

[0001] Cross-references

[0002] This application claims priority to Chinese Patent Application No. 202510350293.4, filed on March 24, 2025, entitled “Method, Apparatus and Electronic Equipment for Anomaly Monitoring of Continuous Tubing”, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application belongs to the field of safety technology for coiled tubing construction operations, and specifically relates to a method, device and electronic equipment for abnormal monitoring of coiled tubing. Background Technology

[0004] Coiled tubing is a long, unthreaded tubing that is wound around a drum, straightened, and can be continuously lowered into or pulled out of an oil well. It features pressurized operation and continuous lowering and pulling. Coiled tubing operations are increasingly widely used in oil and gas fields. However, due to the long-term operation of coiled tubing in complex and variable natural environments, such as high temperature, high pressure, corrosive media, and mechanical stress, its safety and reliability face severe challenges.

[0005] In related technologies, coiled tubing operations are monitored manually at the site to observe whether the coiled tubing above the blowout preventer is entering and exiting the well normally, whether buckling has occurred, and whether there are any abnormalities such as leaks. Because coiled tubing operations are often prolonged, manual monitoring can lead to fatigue and the risk of failing to detect abnormalities in a timely manner. Summary of the Invention

[0006] This application aims to provide a method, apparatus, and electronic device for anomaly monitoring of coiled tubing.

[0007] In a first aspect, embodiments of this application propose an anomaly monitoring method for coiled tubing, wherein an image acquisition device is installed on the coiled tubing. The method includes: acquiring a monitoring video stream from the image acquisition device and determining multiple information lists based on the monitoring video stream, each information list including image data with a preset number of frames; for each information list, determining abnormal image information based on the image data, the abnormal image information including the information list where the abnormal image data is located and the frame number of the abnormal image data in the information list; inputting the abnormal image information into a target detection model to determine the anomaly type of the abnormal image data, wherein the target detection model is trained using historical image data of the coiled tubing acquired by the image acquisition device and annotations of abnormal image data in the historical image data as training data.

[0008] Secondly, this application proposes an anomaly monitoring device for coiled tubing, wherein an image acquisition device is installed on the coiled tubing. The device includes: an acquisition module, configured to acquire a monitoring video stream from the image acquisition device and determine multiple information lists based on the monitoring video stream, each information list including image data with a preset number of frames; a determination module, configured to determine abnormal image information for each information list based on the image data, the abnormal image information including the information list where the abnormal image is located and the frame number of the abnormal image in the information list; and an anomaly detection module, configured to input the abnormal image information into a target detection model to determine the anomaly type of the abnormal image, the target detection model being trained using historical image data of the coiled tubing acquired by the image acquisition device and annotations of abnormal images in the historical image data as training data.

[0009] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method described in the first aspect. Attached Figure Description

[0010] Figure 1 is a flowchart of an anomaly monitoring method for coiled tubing provided in an embodiment of this application;

[0011] Figure 2 is a schematic diagram of the installation location of an image acquisition device provided in an embodiment of this application;

[0012] Figure 3 is a schematic diagram of an abnormality monitoring device for coiled tubing provided in an embodiment of this application;

[0013] Figure 4 is a schematic diagram of an electronic device provided in an embodiment of this application.

[0014] Explanation of reference numerals in the attached drawings: 201-continuous tubing, 202-blowout preventer box, 203-injection head clamping block, 301-acquisition module, 302-determination module, 303-anomaly detection module, 400-electronic device, 401-processor, 402-memory. Detailed Implementation

[0015] Embodiments of the present invention will now be described in detail. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0016] The terms "first" and "second" in the specification and claims of this application may explicitly or implicitly include one or more of the features. In the description of this invention, unless otherwise stated, "a plurality of" means two or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0017] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this invention and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0018] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0019] The following description, in conjunction with Figures 1 to 4, details a method, apparatus, and electronic device for anomaly monitoring of coiled tubing provided in this application, through specific embodiments and application scenarios.

[0020] Figure 1 shows a flowchart of an anomaly monitoring method for coiled tubing provided in an embodiment of this application. As shown in Figure 1, an image acquisition device is installed on the coiled tubing, and the anomaly monitoring method for the coiled tubing may include the contents shown in steps 101 to 103.

[0021] In S101, the monitoring video stream from the image acquisition device is acquired, and multiple information lists are determined based on the monitoring video stream. Each information list includes image data of a preset number of frames.

[0022] The installation position of the image acquisition device can be as shown in Figure 2. The left side of Figure 2 shows that the image acquisition device can be installed below the injection head near the blowout preventer. The right side of Figure 2 shows the shooting angle of the image acquisition device, that is, the image acquisition device can capture multiple positions such as the continuous tubing 201, the blowout preventer 202, and the injection head clamping block 203. The image acquisition device can also be installed in other positions, as long as it can capture positions such as the continuous tubing 201, the injection head clamping block 203, and the blowout preventer 202. If more positions need to be captured in actual applications, it is only necessary to adjust the shooting angle of the image acquisition device or change the installation position of the image acquisition device. The actual application shall prevail, and this embodiment does not limit it.

[0023] In this embodiment, the monitoring video stream from the image acquisition device is monitored frame by frame, and a set number of consecutive frames of image data are defined as an information list. Based on each information list, images are compared to identify abnormal image data more quickly.

[0024] In S102, for each information list, abnormal image information is determined based on the image data. The abnormal image information includes the information list where the abnormal image data is located and the frame number of the abnormal image data in the information list.

[0025] In S103, abnormal image information is input into the target detection model to determine the abnormal type of the abnormal image data. The target detection model is trained using historical image data of continuous tubing acquired by the image acquisition device and the annotation of abnormal image data in the historical image data as training data.

[0026] The abnormal image information can be from a single information list or from multiple information lists, depending on the actual application. This embodiment does not impose any limitations on this.

[0027] It should be noted that the target detection model utilizes historical monitoring videos from image acquisition devices installed on the coiled tubing equipment to annotate anomalies occurring during operations, such as injection head clamp block drops, coiled tubing bending, and blowout preventer seal leaks, forming an anomaly image data standard library. Based on this standard library, a target detection model is trained using target detection algorithms to identify the aforementioned anomalies. The target detection algorithm can use any open-source method, such as You Only Look Once (YOLO), Regions with Convolutional Neural Networks (RCNN), Single Shot MultiBox Detector (SSD), RetinaNet, MMDetection, Multi-Object Tracking Detection (MotDet), etc., depending on the actual application; this embodiment does not impose any limitations.

[0028] In the embodiments of this application, firstly, a monitoring video stream is acquired based on an image acquisition device installed on the coiled tubing, and multiple information lists are determined based on the monitoring video stream. Each information list includes image data with a preset number of frames. Then, for each information list, abnormal image information is determined based on the image data. The abnormal image information includes the information list where the abnormal image data is located and the frame number of the abnormal image data in the information list. Finally, the abnormal image information is input into a target detection model to determine the abnormal type of the abnormal image data. The target detection model is trained using historical image data of the coiled tubing acquired by the image acquisition device and the annotations of abnormal image data in the historical image data as training data. The embodiments of this application use automated methods such as image processing and target detection to replace manual anomaly monitoring and analysis of the coiled tubing, and can determine the anomaly type for reference by operators, reducing the operational safety risks caused by human fatigue during coiled tubing operations and improving the efficiency of anomaly monitoring.

[0029] In one possible implementation of this application, determining multiple information lists based on a surveillance video stream may include: using a first preset number of consecutive image data frames from the surveillance video stream as a first information list; deleting the first image data frame from the previous information list each time an additional frame of image data is added, to obtain a new information list, until multiple information lists corresponding to the surveillance video stream are determined.

[0030] In this embodiment, a preset number of consecutive image frames are stored as a sliding information list. When another frame of image data is acquired, the first frame is deleted, and the image data of that frame is added to the end of the information list as the next information list. This process is repeated to slide the information list and obtain multiple information lists. By determining the information list frame by frame, it is possible to avoid missing any frame of image data, thus enabling comprehensive monitoring and preventing omissions.

[0031] In one possible implementation of this application, determining abnormal image information based on image data for each information list may include: determining the similarity between each frame of image data based on each frame of image data in the information list; if the similarity is less than a similarity threshold, determining the abnormal image information, and determining the next information list.

[0032] In this embodiment, a similarity threshold can be set. When the calculated similarity is less than the similarity threshold, it is considered that the two frames of image data being compared have a large difference and that the image has abnormal changes. There are many similarity comparison methods, such as Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM), perceptual hashing algorithm, and calculating feature points.

[0033] In other embodiments, other image comparison methods may also be used to determine abnormal image information, depending on the actual application.

[0034] In one possible implementation of this application, determining the similarity between image data frames based on image data frames in the information list may include: determining a first frame image data; comparing the other frame image data in the information list with the first frame image data to determine the corresponding similarity, wherein the other frame image data are image data in the information list other than the first frame image data.

[0035] In this embodiment, all image data in an information list are compared with the first frame image data. By comparing the similarity and the similarity threshold, abnormal image data can be quickly identified.

[0036] In one possible embodiment of this application, the anomaly monitoring method for coiled tubing may further include: determining the next information list when the similarity between the image data of each frame in any information list is greater than or equal to a similarity threshold.

[0037] If the similarity between all frames in an information list is not less than the similarity threshold, it means that there is no abnormal image data in the information list, and the next information list can be obtained and determined.

[0038] In one possible implementation of this application, inputting abnormal image information into a target detection model to determine the abnormal type of the abnormal image may include: acquiring image data of a second preset number of frames after the abnormal image data based on the abnormal image information; inputting the abnormal image data and the image data of the second preset number of frames after the abnormal image data into the target detection model to determine the abnormal type of the abnormal image data and the image data of the second preset number of frames after the abnormal image data.

[0039] In this embodiment, after identifying abnormal image information, image data of a second preset number of frames following the abnormal image data can be obtained from the monitoring video stream. Both the abnormal image data and the image data of the second preset number of frames following the abnormal image data are input into the target detection model for judgment. This embodiment uses both the abnormal image data and the multi-frame data following the abnormal image for joint detection, avoiding abnormal data caused by errors in image comparison, thus improving the accuracy of anomaly detection.

[0040] In one possible embodiment of this application, the method for monitoring anomalies in coiled tubing may further include: issuing an anomaly type alarm when the anomaly type of the anomaly image is included in the anomaly types labeled by the target detection model; and issuing an unknown anomaly alarm and alerting the operator when the anomaly type of the anomaly image is not included in the anomaly types labeled by the target detection model.

[0041] In this embodiment, since the types of tags in the historical data are limited, when an anomaly of a certain type occurs, an alarm can be triggered based on that anomaly. When an anomaly type that is not tagged occurs, an alarm can be triggered based on an unknown anomaly. This alerts the operators to the occurrence of an unknown anomaly, prompts them to pay attention to the monitoring video, and allows for on-site detection and other processing methods to avoid affecting the progress of the operation.

[0042] In one possible embodiment of this application, the anomaly monitoring method for coiled tubing may further include: storing and backing up image data of a preset number of frames in an information list containing abnormal image information, abnormal image data input into a target detection model, and image data of a second preset number of frames after the abnormal image data, as well as anomaly diagnosis results.

[0043] After detecting abnormal image data, the image data in the information list containing the abnormal image data, as well as the data input into the target detection model, can be backed up and stored for subsequent alarm tracing and model optimization. This can include image data at the time of the anomaly, operational data such as tensioning, clamping, finger weight, tubing insertion depth, injection head motor pressure, circulation pressure, displacement, and other operational data, as well as equipment alarm data.

[0044] In one specific embodiment of this application, the anomaly monitoring method for coiled tubing is as follows: First, an anomaly image data standard library is established. This involves using historical image data collected by image acquisition devices installed on the coiled tubing and labeling anomalies such as injection head clamp block drop, coiled tubing bending, and blowout preventer seal leakage in the historical image data to obtain the anomaly image data standard library. Based on this anomaly image data standard library, a target detection algorithm is used to train a target detection model to identify the above-mentioned anomaly types. Then, on-site operation data is collected, and monitoring video streams from the coiled tubing equipment are obtained. Monitoring is performed frame by frame, and 10 consecutive frames of image data are stored as a sliding information list. When the 11th frame of image data is obtained, the first frame of image data is deleted, and the 11th frame of image data is added to the end of the information list to obtain a second information list. This process is repeated to slide the information list. Each information list is guaranteed to have 10 frames of image data for analysis. The data of the sliding information list is then obtained. A similarity threshold is set. In this embodiment, the SSIM method is selected for similarity comparison. Based on on-site monitoring data testing, the set similarity threshold can be adjusted to 0.8. This threshold has the highest recognition accuracy for abnormal situations and the fewest false alarms. When the calculated similarity is less than this index, it is considered that the difference between the two frames of image data being compared is large, and the image has abnormal changes. The subsequent 9 frames of image data are compared with the first frame of image data, and the corresponding similarity values ​​are calculated. It is determined whether there are any images with a similarity value less than 0.8 in the subsequent 9 frames of image data. If there are no images with a similarity value less than 0.8, the next information list is obtained for judgment; if there are images with a similarity value less than 0.8, the information of the first abnormal image in the current information list is recorded. The current information list and the information of the first abnormal image are passed into the target detection model to obtain the next information list. Based on the first abnormal image information in the information list, the image data of the first abnormal information and the image data of the next four frames are obtained from the monitoring video stream. These five frames of image data are then fed into the target detection model. In this embodiment, the target detection model labels three abnormal conditions: injection head clamping block drop, continuous tubing bending, and blowout preventer seal leakage. Therefore, detailed alarms can be issued for these three common abnormal conditions. Other abnormalities are alarmed as unknown abnormalities. The target detection model in this embodiment uses the v8 version of the YOLO algorithm, which has the advantages of a more lightweight network structure and easier training. The model determines which type of abnormality the five frames of data belong to. If there is an abnormality that has been labeled in the sample database, an abnormality alarm is issued; if there is no abnormality that has been labeled in the sample database, the alarm is issued as an unknown abnormality, reminding the operators that an unknown abnormality has occurred and that they need to pay attention to the monitoring video.

[0045] This embodiment uses image processing and target detection technology to replace manual labor for real-time monitoring and analysis of anomalies such as injection head clamp block falling, coiled tubing bending, and blowout preventer seal leakage. It outputs anomaly alarm signals, reducing the operational safety risks caused by human fatigue during coiled tubing operations and lowering labor costs.

[0046] Figure 3 is a schematic diagram of an anomaly monitoring device for coiled tubing provided in an embodiment of this application. As shown in Figure 3, the anomaly monitoring device for coiled tubing may include an acquisition module 301, a determination module 302, and an anomaly detection module 303.

[0047] The acquisition module 301 is used to acquire the monitoring video stream from the image acquisition device and determine multiple information lists based on the monitoring video stream. Each information list includes image data with a preset number of frames. The determination module 302 is used to determine abnormal image information based on the image data for each information list. The abnormal image information includes the information list where the abnormal image is located and the frame number of the abnormal image in the information list. The anomaly detection module 303 is used to input the abnormal image information into the target detection model to determine the anomaly type of the abnormal image. The target detection model is trained using historical image data of continuous tubing acquired by the image acquisition device and the annotations of abnormal images in the historical image data as training data.

[0048] In the embodiments of this application, the acquisition module 301 first acquires a monitoring video stream based on the image acquisition device installed on the coiled tubing, and determines multiple information lists based on the monitoring video stream. Each information list includes image data with a preset number of frames. Then, the determination module 302 determines abnormal image information for each information list based on the image data. The abnormal image information includes the information list where the abnormal image data is located and the frame number of the abnormal image data in the information list. Finally, the anomaly detection module 303 inputs the abnormal image information into the target detection model to determine the anomaly type of the abnormal image data. The target detection model is trained using historical image data of the coiled tubing acquired by the image acquisition device and the annotations of abnormal image data in the historical image data as training data. The embodiments of this application use automated methods such as image processing and target detection to replace manual anomaly monitoring and analysis of the coiled tubing, and can determine the anomaly type for reference by operators, reducing the operational safety risks caused by human fatigue during coiled tubing operations and improving anomaly monitoring efficiency.

[0049] In one possible implementation of this application, the acquisition module 301 is configured to: take a first preset number of consecutive image data in the monitoring video stream as a first information list; and delete the first frame image data in the previous information list when each frame of image data is added, to obtain a new information list, until multiple information lists corresponding to the monitoring video stream are determined.

[0050] In one possible implementation of this application, the determining module 302 is configured to: for each information list, determine the similarity between each frame of image data based on each frame of image data in the information list; if the similarity is less than the similarity threshold, determine abnormal image information and determine the next information list.

[0051] In one possible implementation of this application, the determining module 302 is used to: determine the first frame image data; compare the other frame image data in the information list with the first frame image data respectively, and determine the corresponding similarity, wherein the other frame image data are the image data in the information list other than the first frame image data.

[0052] In one possible implementation of this application, the determining module 302 is used to: determine the next information list when the similarity between the image data of each frame in any information list is greater than or equal to the similarity threshold.

[0053] In one possible implementation of this application, the anomaly detection module 303 is used to: acquire image data of a second preset number of frames after the abnormal image data based on the abnormal image information; input the abnormal image data and the image data of the second preset number of frames after the abnormal image data into the target detection model, and determine the anomaly type of the abnormal image data and the image data of the second preset number of frames after the abnormal image data.

[0054] In one possible embodiment of this application, the abnormality monitoring device for the coiled tubing may further include: a first alarm module and a second alarm module.

[0055] The first alarm module is used to issue an alarm for an abnormal type when the abnormal type of the abnormal image is included in the abnormal types labeled by the target detection model; the second alarm module is used to issue an alarm for an unknown abnormality when the abnormal type of the abnormal image is not included in the abnormal types labeled by the target detection model, and to notify the operator that an unknown abnormality has occurred.

[0056] In one possible embodiment of this application, the abnormality monitoring device for the coiled tubing may further include a backup module.

[0057] The backup module is used to store and back up image data of a preset number of frames in the information list containing abnormal image information, abnormal image data input into the target detection model, image data of a second preset number of frames after the abnormal image data, and abnormal diagnosis results.

[0058] The abnormal monitoring device for coiled tubing provided in this application embodiment can realize all the processes implemented in the method embodiments of Figures 1-2 and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0059] As shown in Figure 4, this application embodiment also provides an electronic device 400, including a processor 401, a memory 402, and a program or instructions stored in the memory 402 and executable on the processor 401. When the program or instructions are executed by the processor 401, they implement the various processes of the above-described abnormal monitoring method embodiment for continuous tubing and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0060] This application also provides a storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the anomaly monitoring method for continuous tubing provided in any of the above embodiments. Since the same technical effects can be achieved, further details are omitted here to avoid repetition.

[0061] The processor is the processor in the electronic device described in the above embodiments. The storage medium includes computer storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0062] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described embodiments of the abnormal monitoring method for continuous tubing, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0063] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0064] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described embodiments of the anomaly monitoring method for coiled tubing, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0065] This application also provides a processing device configured to execute the various processes of the above-described embodiments of the anomaly monitoring method for coiled tubing, and to achieve the same technical effect. To avoid repetition, it will not be described again here.

[0066] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0067] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0068] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for anomaly monitoring of coiled tubing, wherein an image acquisition device is installed on the coiled tubing, the method comprising: Acquire the monitoring video stream from the image acquisition device, and determine multiple information lists based on the monitoring video stream, each information list including image data of a preset number of frames; For each information list, abnormal image information is determined based on the image data. The abnormal image information includes the information list where the abnormal image data is located and the frame number of the abnormal image data in the information list. The abnormal image information is input into the target detection model to determine the abnormal type of the abnormal image data. The target detection model is trained using historical image data of the coiled tubing acquired by the image acquisition device and the annotations of abnormal image data in the historical image data as training data.

2. The method according to claim 1, wherein, The determination of multiple information lists based on the monitored video stream includes: The image data of a first preset number of consecutive frames in the monitoring video stream are used as the first information list; With each new frame of image data added, the first frame of image data in the previous information list is deleted to obtain a new information list, until multiple information lists corresponding to the monitoring video stream are determined.

3. The method according to claim 1, wherein, For each information list, determining abnormal image information based on the image data includes: For each information list, the similarity between the frame image data is determined based on each frame image data in the information list; If the similarity is less than the similarity threshold, abnormal image information is identified, and the next information list is determined.

4. The method according to claim 3, wherein, Determining the similarity between the frame image data based on the frame image data in the information list includes: Determine the first frame of image data; The other frame image data in the information list are compared with the first frame image data to determine the corresponding similarity. The other frame image data are the image data in the information list other than the first frame image data.

5. The method according to claim 3, wherein, The method further includes: If the similarity between the frame image data in any information list is greater than or equal to the similarity threshold, then the next information list is determined.

6. The method according to claim 1, wherein, The step of inputting the abnormal image information into the target detection model to determine the abnormal type of the abnormal image includes: Based on the abnormal image information, image data of a second preset number of frames is obtained after the abnormal image data; The abnormal image data and the image data of the second preset number of frames following the abnormal image data are input into the target detection model to determine the abnormal type of the abnormal image data and the image data of the second preset number of frames following the abnormal image data.

7. The method according to claim 1, wherein, The method further includes: If the anomaly type of the abnormal image is included in the anomaly type labeled by the target detection model, an alarm for the anomaly type is triggered. If the anomaly type of the abnormal image is not included in the anomaly types labeled by the target detection model, an unknown anomaly alarm will be issued, and the operator will be notified that an unknown anomaly has occurred.

8. The method according to claim 1, wherein, The method further includes: The image data of a preset number of frames in the information list containing abnormal image information, the abnormal image data input into the target detection model, and the image data of a second preset number of frames after the abnormal image data, as well as the abnormal diagnosis results, are stored and backed up.

9. An anomaly monitoring device for coiled tubing, wherein an image acquisition device is installed on the coiled tubing, the device comprising: The acquisition module is used to acquire the monitoring video stream on the image acquisition device and determine multiple information lists based on the monitoring video stream, each information list including image data of a preset number of frames; The determination module is used to determine abnormal image information based on the image data for each information list. The abnormal image information includes the information list in which the abnormal image is located and the frame number of the abnormal image in the information list. An anomaly detection module is used to input the abnormal image information into a target detection model to determine the anomaly type of the abnormal image. The target detection model is trained using historical image data of the coiled tubing acquired by the image acquisition device and the annotations of abnormal images in the historical image data as training data.

10. An electronic device comprising a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method as claimed in any one of claims 1 to 8.

Images