Safety valve lead sealing state identification method, device and equipment and storage medium

Abstract

The invention discloses a safety valve lead seal state recognition method, device and equipment and a storage medium, and the recognition method comprises the steps: obtaining a picture sample of a safety valve provided with a safety valve lead seal in a refinery plant; more than two signboards are connected to a lead wire of the safety valve lead seal; framing a safety valve region in the picture sample to serve as a training sample of a deep learning algorithm; and training the training samples exceeding the preset number to generate an image recognition model used for obtaining the state recognition result of the safety valve lead seal. In the invention, a plurality of signboards are added on the lead seal, the distance between the signboards is calculated by identifying the distance between the signboards, and the lead seal state of the safety valve is identified, so that the accuracy of identifying the lead seal state of the safety valve by the detection model can be improved; in addition, the color of the signboard is determined through the color of the safety valve lead seal, so that the accuracy of identifying the safety valve lead seal state by the detection model is further improved.

Description

Technical Field

[0001] The invention relates to the field of safety valve lead seals, and in particular to a safety valve lead seal state identification method, device, equipment and storage medium. Background Art

[0002] Safety valve lead seal status inspection is an important inspection item in refinery inspection.

[0003] In recent years, as my country's industry has gradually upgraded to intelligence, manual inspections in refineries have become increasingly difficult to adapt to the current development situation. More and more refineries are using robot inspections instead of manual inspections.

[0004] The robot inspection method in the prior art generally uses machine vision algorithms, such as convolutional neural networks and other image recognition technologies to identify the status of the safety valve seal to determine whether the safety valve seal is normal or disconnected.

[0005] The inventor has found through research that the state identification technology of safety valve lead seal in the prior art still has at least the following defects:

[0006] It is difficult to identify the thread of the safety valve lead seal, which results in poor accuracy in the identification result of the safety valve lead seal status.

[0007] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgment or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0008] The purpose of the present invention is to improve the accuracy of the seal status recognition result.

[0009] The present invention provides a method for identifying the state of a safety valve lead seal, comprising the steps of:

[0010] S11. Obtain a sample of images of safety valves with safety valve lead seals in a refinery; the thread of the safety valve lead seal is connected with two or more identification plates;

[0011] S12, selecting a safety valve area in the image sample as a training sample for a deep learning algorithm;

[0012] S13, training with more than a preset number of training samples to generate an image recognition model for obtaining a state recognition result of the safety valve lead seal.

[0013] Preferably, the present invention further provides a method for identifying the state of a safety valve lead seal, comprising the steps of:

[0014] S21, acquiring image data of the safety valve seal to be identified; the thread of the safety valve seal is connected with two or more identification plates; the identification plates are arranged according to a preset layout rule; the layout rule includes setting a distance between two identification plates;

[0015] S22, identifying each of the identification plates according to the image data;

[0016] S23, generating a state recognition result of the safety valve seal by judging whether the distribution characteristics of the identification plates conform to preset rules; the preset rules include a maximum spacing threshold between adjacent identification plates.

[0017] Preferably, in the embodiment of the present invention, it also includes:

[0018] The color of the identification plate is determined according to the background color of the safety valve lead seal.

[0019] Preferably, in an embodiment of the present invention, it includes:

[0020] The color difference between the color of the identification plate and the background color of the safety valve seal is greater than a preset color difference threshold.

[0021] Preferably, in the embodiment of the present invention, it also includes:

[0022] When the number of the identification plates is greater than three, the identification plates are arranged at equal distances from each other.

[0023] Preferably, in an embodiment of the present invention, it includes:

[0024] The identification plate is configured to have a three-dimensional structure.

[0025] Preferably, in an embodiment of the present invention, it includes:

[0026] The three-dimensional structure includes a sphere.

[0027] In another aspect of the present invention, a device for identifying the state of a safety valve lead seal is provided, comprising:

[0028] An image acquisition unit, used for acquiring image data of the safety valve seal to be identified; the thread of the safety valve seal is connected with two or more identification plates; the identification plates are arranged according to a preset layout rule; the layout rule includes setting a distance between two identification plates;

[0029] A sign recognition unit, used for recognizing each of the signboards according to the image data;

[0030] The state recognition unit is used to generate the state recognition result of the safety valve seal by judging whether the distribution characteristics of the identification plates meet the preset rules; the preset rules include the maximum spacing threshold of adjacent identification plates.

[0031] Preferably, in an embodiment of the present invention, the sign recognition unit includes:

[0032] The first label recognition unit is used to determine the color of the label according to the background color of the safety valve seal.

[0033] On the other hand, a device for identifying the state of a safety valve seal is provided according to an embodiment of the present invention; the device for identifying the state of a safety valve seal includes a computer program stored on a medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer executes the methods described in the above aspects and achieves the same technical effects.

[0034] In another aspect of the embodiment of the present invention, a storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, each step of the method for identifying the state of a safety valve seal as described in any one of the above items is implemented.

[0035] On the other hand, a safety valve seal status recognition system is provided, comprising an inspection robot and the safety valve seal status recognition device as described above; the inspection robot is used to collect image data of the safety valve seal to be recognized on site.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] In the present invention, firstly, image samples of safety valves with safety valve seals in refineries are obtained; then, the safety valve area in the image samples is framed and used as training samples for the deep learning algorithm; finally, training is performed using no less than a preset number of training samples, and an image recognition model is generated for obtaining status recognition results of safety valve seals.

[0038] In the present invention, an identification plate is provided on the safety valve lead seal. Since the area of ​​the identification plate is much larger than the thread of the safety valve lead seal, the identification plate can be quickly and accurately identified when collecting images, thereby improving the efficiency and effect of image recognition.

[0039] In addition, the present invention can also significantly reduce the proportion of invalid images in the images collected by the inspection robot, thereby improving the coverage of inspection items and providing strong technical support for unmanned inspection of refineries. Furthermore, in the present invention, a color difference threshold can be preset, and then the color of the identification plate can be set according to the background color of the safety valve lead seal, so that the identification plate can be more easily identified; thereby further improving the efficiency and effect of image recognition.

[0040] In addition, the present invention can improve the coverage rate of inspection items and provide strong technical support for unmanned inspection of refineries.

[0041] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention and implement it according to the contents of the specification, and to make the above and other purposes, technical features and advantages of the present invention easier to understand, one or more preferred embodiments are listed below and described in detail with the accompanying drawings as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 It is a step diagram of the method for identifying the state of the safety valve lead seal of the present invention;

[0044] Figure 2 It is another step diagram of the state identification method of the safety valve lead seal of the present invention;

[0045] Figure 3 It is a structural schematic diagram of the state identification device of the safety valve lead seal of the present invention;

[0046] Figure 4 It is a structural schematic diagram of the state identification device of the safety valve lead seal in the present invention. DETAILED DESCRIPTION

[0047] The specific implementation modes of the present invention are described in detail below in conjunction with the accompanying drawings, but it should be understood that the protection scope of the present invention is not limited by the specific implementation modes.

[0048] Unless explicitly stated otherwise, throughout the specification and claims, the term “comprise” or variations such as “include” or “comprising”, etc., will be understood to include the stated elements or components but not to exclude other elements or components.

[0049] In this document, the terms "first", "second", etc. are used to distinguish two different elements or parts, and are not used to limit a specific position or relative relationship. In other words, in some embodiments, the terms "first", "second", etc. can also be interchangeable.

[0050] Embodiment 1

[0051] In order to improve the accuracy of the safety valve lead seal status recognition results, such as Figure 1 As shown, in an embodiment of the present invention, a method for identifying the state of a safety valve lead seal is provided, comprising the steps of:

[0052] S11. Obtain a sample of images of safety valves with safety valve lead seals in a refinery; the thread of the safety valve lead seal is connected with two or more identification plates;

[0053] After research, the inventors found that there are two difficulties in the current robot inspection method. First, it is difficult for the robot to reach the location of some target objects at close range, so it is impossible to capture a clear image of the safety valve; second, the safety valve seal is very thin and the color is similar to the background. When the target recognition algorithm collects samples, the picture of the broken safety valve seal is not much different from the normal picture. Traditional machine vision algorithms such as convolutional neural networks cannot effectively identify them. Samples that are too similar bring great difficulties to the image recognition algorithm.

[0054] Based on the above cognition, the inventive ideas of the embodiments of the present invention include:

[0055] In an embodiment of the present invention, a plurality of identification plates are pre-set on the safety valve seal; in this way, the identification plates can be accurately identified based on the collected images of the inspection robot; then, the safety valve seal status is indirectly identified through a deep learning algorithm based on image recognition, or by calculating the distance between the identification plates after the identification plates are identified; since the area of ​​the identification plates fixedly connected to the silk thread in the embodiment of the present invention is much larger than the silk thread itself in the image, the accuracy of the image recognition algorithm in identifying the safety valve seal status can be effectively improved; thereby, the accuracy of the detection model in identifying the safety valve seal status can be improved.

[0056] The safety valve seal in the embodiment of the present invention has two or more identification plates pre-arranged on its wire; in practical applications, the identification plate in the embodiment of the present invention can be set in the shape of a circular sheet, or in the shape of a polygonal sheet.

[0057] When the identification plates are fixed on the silk thread, the distance between the identification plates can be fixed or within a certain range when the silk thread is intact; after the silk thread breaks, the distance between the identification plates will exceed the initial distance between the identification plates, and the relative position of the identification plates and the safety valve seal may also change; in addition, if multiple identification plates are of different colors, then after the silk thread on which the identification plates are set breaks, it will sag significantly due to the influence of gravity, causing the relative position of the identification plates to change.

[0058] From the above, it can be seen that in the embodiment of the present invention, on the one hand, after the identification plate is set in the embodiment of the present invention, since the area of ​​the identification plate in the image occupies a large proportion, it is easier to perform image recognition; on the other hand, by setting the identification plate, the present invention can also make the image difference between the silk thread after breaking and the initial state more obvious, thereby further improving the recognition.

[0059] In addition, in the embodiment of the present invention, the color corresponding to the identification plate can also be determined according to the background color of the safety valve lead seal, thereby further improving the accuracy of the detection model in identifying the safety valve lead seal status. Specifically:

[0060] In the embodiment of the present invention, the method may further include determining the color of the identification plate according to the background color of the safety valve seal.

[0061] For image recognition technology, the greater the color difference between an object and its background, the easier it is to accurately identify the object; therefore, in order to effectively improve the recognition rate of the identification plate, in the embodiment of the present invention, the color of the identification plate can also be set according to the background color of the safety valve seal, thereby effectively improving the efficiency and effect of image recognition.

[0062] Specifically, in an embodiment of the present invention, a color difference threshold between the color of the identification plate and the background color of the safety valve seal can be preset first; then, the color of the identification plate is determined according to the background color of the safety valve seal based on the color difference threshold, thereby further improving the recognition effect.

[0063] In order to further improve the recognition effect of the safety valve seal status, in an embodiment of the present invention, it can also include: when the number of the identification plates is greater than three, the identification plates are arranged at equal distances from each other; the seal status can be judged by the distance between two adjacent identification plates, and if it is recognized that the distance between any two adjacent identification plates is greater than a set spacing threshold, it can be judged that the safety valve seal is broken; then, based on the two identification plates with excessive distances, the break position of the wire can also be indirectly judged.

[0064] In order to further improve the recognition effect of the lead sealing status of the safety valve, in an embodiment of the present invention, it can include: the identification plate is set to have a three-dimensional structure; in actual applications, the three-dimensional structure of the identification plate can specifically be a sphere, that is, the identification plate can be set to a sphere, so that when the inspection robot is used to collect images, there are more options for the angle and orientation of the image of the identification plate, thereby improving the efficiency of the robot inspection and the recognition effect of the collected images.

[0065] S12, selecting a safety valve area in the image sample as a training sample for a deep learning algorithm;

[0066] In an embodiment of the present invention, a target detection YOLO5 algorithm can be used to train a large number of image samples to achieve long-distance identification of safety valves with safety valve lead seals in sample images, and the location of the safety valve is marked in the sample images, which are used as training samples for the deep learning algorithm.

[0067] S13, training with more than a preset number of training samples to generate an image recognition model for obtaining a state recognition result of the safety valve lead seal.

[0068] In the embodiment of the present invention, the image recognition model is trained by a large number of training samples, so that the image recognition model generated in this way is more conducive to obtaining the state recognition result of the safety valve lead seal.

[0069] In practical applications, an inspection robot equipped with a variable-focus high-definition camera pan-tilt can be selected, and its SDK can be called to adjust the pan-tilt angle according to the position of the safety valve in the image so that the safety valve to be inspected is in the center of the image. The position of the safety valve can be identified by applying the target recognition algorithm. Then, the camera is zoomed in and the image of the safety valve at a distance is re-shot, so that the safety valve seal can be identified. By applying the target recognition algorithm again, it is determined whether the safety valve seal of the current safety valve is broken, and the recognition result is uploaded to the upper computer of the inspection robot, thus completing a status detection of the safety valve seal.

[0070] In summary, in the present invention, firstly, image samples of safety valves with safety valve seals in refineries are obtained; then, the safety valve areas in the image samples are framed and used as training samples for the deep learning algorithm; finally, training is performed using no less than a preset number of training samples to generate an image recognition model for obtaining status recognition results of safety valve seals.

[0071] Since the area of ​​the identification plate fixedly connected to the silk thread in the embodiment of the present invention in the image is much larger than the silk thread itself, the accuracy of the image recognition algorithm in identifying it can be effectively improved; thereby, the accuracy of the detection model in identifying the lead sealing status of the safety valve can also be improved.

[0072] In addition, through the embodiments of the present invention, the proportion of invalid images in the images collected by the inspection robot can be greatly reduced, thereby improving the coverage of inspection items and providing strong technical support for unmanned inspection of refineries. Furthermore, in the embodiments of the present invention, a color difference threshold can be preset, and then the color of the identification plate can be set according to the background color of the safety valve lead seal, so that the identification plate can be more easily identified; thereby further improving the efficiency and effect of image recognition.

[0073] Embodiment 2

[0074] In order to improve the accuracy of the safety valve lead seal status recognition results, such as Figure 2 As shown, in an embodiment of the present invention, another method for identifying the state of a safety valve lead seal is provided, comprising the steps of:

[0075] S21, acquiring image data of the safety valve seal to be identified; the thread of the safety valve seal is connected with two or more identification plates; the identification plates are arranged according to a preset layout rule; the layout rule includes setting a distance between two identification plates;

[0076] In an embodiment of the present invention, image data of a safety valve seal to be identified is first obtained, and more than two identification plates are set on the thread of the safety valve seal in the image data; thus, the actual distance between the corresponding physical identification plates is obtained by identifying each identification plate in the image and calculating the spacing between adjacent identification plates.

[0077] The safety valve seal in the embodiment of the present invention has two or more identification plates pre-arranged on its wire; in practical applications, the identification plate in the embodiment of the present invention can be set in the shape of a circular sheet, or in the shape of a polygonal sheet.

[0078] In order to further improve the recognition effect of the lead sealing status of the safety valve, in the embodiment of the present invention, the identification plate can be further set to have a three-dimensional structure; in practical applications, the three-dimensional structure of the identification plate can specifically be a sphere, that is, the identification plate can be set to a sphere, so that when the inspection robot is used to collect images, there are more options for the angle and orientation of the identification plate image, thereby improving the efficiency of the robot inspection and the recognition effect of the collected images.

[0079] S22, identifying each of the identification plates according to the image data;

[0080] Preferably, in the embodiment of the present invention, the color corresponding to the identification plate can also be determined according to the background color of the safety valve lead seal, thereby further improving the accuracy of the lead seal status recognition, specifically:

[0081] In the embodiment of the present invention, the method may further include determining the color of the identification plate according to the background color of the safety valve seal.

[0082] For image recognition technology, the greater the color difference between an object and its background, the easier it is to accurately identify the object; therefore, in order to effectively improve the recognition rate of the identification plate, in the embodiment of the present invention, the color of the identification plate can also be set according to the background color of the safety valve seal, thereby effectively improving the efficiency and effect of image recognition.

[0083] Specifically, in an embodiment of the present invention, a color difference threshold between the color of the identification plate and the background color of the safety valve seal can be preset first; then, the color of the identification plate can be determined according to the background color of the safety valve seal based on the color difference threshold, thereby further improving the recognition effect.

[0084] S23, generating a state recognition result of the safety valve seal by judging whether the distribution characteristics of the identification plates conform to preset rules; the preset rules include a maximum spacing threshold between adjacent identification plates.

[0085] In the embodiment of the present invention, after the identification plates are fixed on the wire, the distance between the identification plates can be fixed or within a certain range when the wire is intact; after the wire breaks, the distance between the identification plates on both sides of the break position will exceed the initial distance.

[0086] In an embodiment of the present invention, determining whether the distribution characteristics of the signboards conform to preset rules may specifically include determining whether the distance between two adjacent signboards exceeds a preset maximum distance threshold; in actual applications, the maximum distance threshold may be equal to the distance between the signboards set in the layout rules.

[0087] Preferably, in an embodiment of the present invention, the layout rules may further include: when the number of the identification plates is greater than three, the identification plates are arranged equidistantly; in this way, the state of the safety valve seal can be judged by the spacing between different identification plates; for example, when it is identified that the distance between any two adjacent identification plates is greater than a set spacing threshold, it can be determined that the safety valve seal is broken; in addition, if it is identified that the difference between a certain spacing value and other spacing values ​​is too large, it can also be determined that the safety valve seal is broken; in addition, based on the two identification plates whose distance exceeds the standard, the breaking position of the wire can also be indirectly determined.

[0088] To sum up, in the embodiments of the present invention, on the one hand, after the identification plate is set in the embodiments of the present invention, image recognition is easier because the area of ​​the identification plate in the image occupies a large proportion; on the other hand, the present invention can quickly identify the status of the safety valve seal according to the change of the spacing of the identification plates by setting a preset spacing of the identification plates.

[0089] The embodiments of the present invention improve the accuracy of identifying the lead seal state of the safety valve, thereby solving the problem of poor accuracy of the identification result of the lead seal state of the safety valve caused by the difficulty in identifying the thread of the lead seal of the safety valve in the prior art.

[0090] Furthermore, in the embodiment of the present invention, the color of the identification plate can be set by the background color of the safety valve seal, and the difficulty of identifying the identification plate can be further reduced by maintaining a certain color difference between the two colors, thereby further improving the efficiency and effect of image recognition.

[0091] In addition, the embodiments of the present invention can improve the coverage rate of inspection items and provide strong technical support for unmanned inspection of refineries.

[0092] Embodiment 3

[0093] Corresponding to the above method embodiment, in another aspect of the embodiment of the present invention, a device for identifying the state of a safety valve lead seal is also provided. Figure 3 The schematic diagram of the structure of the safety valve lead seal state recognition device provided by the embodiment of the present invention is shown. Figure 2 The device corresponding to the state recognition method of the safety valve lead seal described in the corresponding embodiment, that is, the virtual device is used to realize Figure 2 In the corresponding embodiment, the state recognition method of the safety valve lead seal, each virtual module constituting the state recognition device of the safety valve lead seal can be executed by an electronic device, such as a network device, a terminal device or a server. Specifically, the state recognition device of the safety valve lead seal in the embodiment of the present invention includes:

[0094] The image acquisition unit 01 is used to acquire image data of the safety valve seal to be identified; the thread of the safety valve seal is connected with two or more identification plates; the identification plates are arranged according to a preset layout rule; the layout rule includes setting the distance between the two identification plates;

[0095] In an embodiment of the present invention, image data of a safety valve seal to be identified is obtained, and in the image data, more than two identification plates are provided on the thread of the safety valve seal. The distance between the identification plates is calculated by identifying the spacing between the identification plates, thereby improving the accuracy of the detection model in identifying the safety valve seal status.

[0096] The layout rules may also include: when there are more than three identification plates, the identification plates are arranged at equal distances from each other; the seal status of the safety valve can be judged by the maximum distance between two adjacent identification plates. If it is identified that the maximum distance between any two adjacent identification plates is greater than a set spacing threshold, it can be judged that the seal of the safety valve is broken; if it is identified that the difference between a certain spacing value and other spacing values ​​is too large, it can also be judged that the seal of the safety valve is broken; in addition, based on the two identification plates whose distance exceeds the standard, the break position of the wire can also be indirectly determined.

[0097] In addition, in order to further improve the recognition effect of the lead sealing status of the safety valve, the identification plate can be set to have a three-dimensional structure, such as setting the identification plate as a sphere. When the inspection robot is used to collect images, there are more options for the angle and orientation of the identification plate image, thereby improving the efficiency of the robot inspection and the recognition effect of the collected images.

[0098] A sign recognition unit 02, used to recognize each of the signboards according to the image data;

[0099] In an embodiment of the present invention, the nameplate recognition unit includes: a first nameplate recognition unit, which is used to determine the color of the nameplate according to the background color of the safety valve seal; the color of the nameplate can be determined according to the background color of the safety valve seal; the background color of the safety valve seal is first identified, and then the color of the matching nameplate is determined according to the background color to improve the recognition effect.

[0100] The state recognition unit 03 is used to generate the state recognition result of the safety valve seal by judging whether the distribution characteristics of the identification plates conform to the preset rules; the preset rules include the maximum spacing threshold of adjacent identification plates.

[0101] In an embodiment of the present invention, the status recognition result of the safety valve seal can be used to determine whether the safety valve seal is broken by judging the maximum distance between two adjacent identification plates; if the maximum distance between any two adjacent identification plates is greater than the set maximum spacing threshold, it can be determined that the safety valve seal is broken.

[0102] Optionally, the state recognition device for the safety valve lead seal in the embodiment of the present invention can also be used with Figure 1 The device corresponding to the state recognition method of the safety valve lead seal described in the corresponding embodiment, that is, the virtual device is used to realize Figure 1 In the corresponding embodiment, the method for identifying the state of the safety valve seal and the various virtual modules constituting the device for identifying the state of the safety valve seal can be executed by electronic devices, such as network devices, terminal devices or servers.

[0103] It should be noted that the specific implementation method and technical effect of the safety valve lead seal status identification device in the embodiment of the present invention can be referred to Figure 2 or Figure 1 The corresponding method for identifying the state of the safety valve lead seal will not be described in detail here.

[0104] Embodiment 4

[0105] Corresponding to the method embodiment, in the embodiment of the present invention, a state identification device for a safety valve lead seal is also provided, such as a terminal, a server, etc. Among them, the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto.

[0106] An example of a hardware structure block diagram of a safety valve lead seal status recognition device provided by an embodiment of the present invention is shown in FIG. Figure 4 As shown, it may include:

[0107] Processor 1, communication interface 2, memory 3 and communication bus 4;

[0108] The processor 1, the communication interface 2, and the memory 3 communicate with each other via the communication bus 4;

[0109] Optionally, the communication interface 2 may be an interface of a communication module, such as an interface of a GSM module;

[0110] The processor 1 may be a central processing unit CPU, or an application-specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0111] The memory 3 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0112] The processor 1 is specifically used to execute the computer program stored in the memory 3 to perform the following steps:

[0113] S11. Obtain a sample of images of safety valves with safety valve lead seals in a refinery; the thread of the safety valve lead seal is connected with two or more identification plates;

[0114] S12, selecting a safety valve area in the image sample as a training sample for a deep learning algorithm;

[0115] S13, training with more than a preset number of training samples to generate an image recognition model for obtaining a state recognition result of the safety valve lead seal.

[0116] Optionally, the processor 1 is specifically configured to execute the computer program stored in the memory 3, and may further perform the following steps:

[0117] S21, acquiring image data of the safety valve seal to be identified; the thread of the safety valve seal is connected with two or more identification plates; the identification plates are arranged according to a preset layout rule; the layout rule includes setting a distance between two identification plates;

[0118] S22, identifying each of the identification plates according to the image data;

[0119] S23, generating a state recognition result of the safety valve seal by judging whether the distribution characteristics of the identification plates conform to preset rules; the preset rules include a maximum spacing threshold between adjacent identification plates.

[0120] The above product can execute the method provided by the embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method. For technical details not fully described in this embodiment, please refer to the state identification method of the safety valve lead seal provided by the embodiment of the present invention.

[0121] Embodiment 5

[0122] In an embodiment of the present invention, a storage medium is further provided, which may store a program suitable for execution by a processor, wherein the program is used to:

[0123] S11. Obtain a sample of images of safety valves with safety valve lead seals in a refinery; the thread of the safety valve lead seal is connected with two or more identification plates;

[0124] S12, selecting a safety valve area in the image sample as a training sample for a deep learning algorithm;

[0125] S13, training with more than a preset number of training samples to generate an image recognition model for obtaining a state recognition result of the safety valve lead seal.

[0126] Optionally, the program may also be used to:

[0127] S21, acquiring image data of the safety valve seal to be identified; the thread of the safety valve seal is connected with two or more identification plates; the identification plates are arranged according to a preset layout rule; the layout rule includes setting a distance between two identification plates;

[0128] S22, identifying each of the identification plates according to the image data;

[0129] S23, generating a state recognition result of the safety valve seal by judging whether the distribution characteristics of the identification plates conform to preset rules; the preset rules include a maximum spacing threshold between adjacent identification plates.

[0130] Optionally, the detailed functions and extended functions of the program may refer to the above description.

[0131] The above product can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the methods provided by other embodiments of the present invention.

[0132] Embodiment 6

[0133] On the other hand, a safety valve seal status recognition system is provided, comprising an inspection robot and the safety valve seal status recognition device as described above; the inspection robot is used to collect image data of the safety valve seal to be recognized on site.

[0134] In practical applications, the inspection robot first collects the image data of the safety valve seal to be identified, then obtains the identification result of the safety valve seal through the safety valve seal status recognition device, and uploads the identification result to the inspection robot's host computer to complete the safety valve seal status detection.

[0135] It should be noted that the specific implementation method and technical effect of the safety valve lead seal status recognition system in the embodiment of the present invention can be referred to Figure 4 The corresponding safety valve lead seal state recognition device is not described in detail here. For technical details not described in detail in this embodiment, please refer to the safety valve lead seal state recognition device provided in the embodiment of the present invention.

[0136] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0137] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0138] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0139] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0140] It should be understood that in the embodiments of the present application, the various embodiments and features can be combined with each other to solve the aforementioned technical problems.

[0141] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0142] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying the state of a safety valve lead seal, characterized in that: Includes steps: S11. Obtain a sample of images of safety valves with safety valve lead seals in a refinery; the thread of the safety valve lead seal is connected with two or more identification plates; S12, selecting a safety valve area in the image sample as a training sample for a deep learning algorithm; S13, training with more than a preset number of training samples to generate an image recognition model for obtaining a state recognition result of the safety valve lead seal.

2. A method for identifying the state of a safety valve lead seal, characterized in that: Includes steps: S21, acquiring image data of the safety valve seal to be identified; the thread of the safety valve seal is connected with two or more identification plates; the identification plates are arranged according to a preset layout rule; the layout rule includes setting a distance between two identification plates; S22, identifying each of the identification plates according to the image data; S23, generating a state recognition result of the safety valve seal by judging whether the distribution characteristics of the identification plates conform to preset rules; the preset rules include a maximum spacing threshold between adjacent identification plates.

3. The method for identifying the state of a safety valve seal according to claim 1 or 2, characterized in that: Also includes: The color of the identification plate is determined according to the background color of the safety valve lead seal.

4. The method for identifying the state of a safety valve seal according to claim 3, characterized in that: include: The color difference between the color of the identification plate and the background color of the safety valve seal is greater than a preset color difference threshold.

5. The method for identifying the state of a safety valve seal according to claim 4, characterized in that: Also includes: When the number of the identification plates is greater than three, the identification plates are arranged at equal distances from each other.

6. The method for identifying the state of a safety valve seal according to claim 5, characterized in that: include: The identification plate is configured to have a three-dimensional structure.

7. The method for identifying the state of a safety valve seal according to claim 6, characterized in that: include: The three-dimensional structure includes a sphere.

8. A device for identifying the state of a safety valve lead seal, characterized in that: include: An image acquisition unit, used for acquiring image data of the safety valve seal to be identified; the thread of the safety valve seal is connected with two or more identification plates; the identification plates are arranged according to a preset layout rule; the layout rule includes setting a distance between two identification plates; A sign recognition unit, used for recognizing each of the signboards according to the image data; The state recognition unit is used to generate the state recognition result of the safety valve seal by judging whether the distribution characteristics of the identification plates conform to the preset rules; the preset rules include the maximum spacing threshold of adjacent identification plates.

9. The device for identifying the state of the safety valve lead seal according to claim 8, characterized in that: The sign recognition unit comprises: The first label recognition unit is used to determine the color of the label according to the background color of the safety valve seal.

10. A safety valve lead seal status identification device, characterized in that: include: Memory for storing computer programs; A processor is used to call and execute the computer program to implement the steps of the state identification method of the safety valve seal as described in any one of claims 1 to 7.

11. A storage medium, characterized in that: The method comprises a software program, wherein the software program is suitable for executing, by a processor, the steps of the method for identifying the state of a safety valve seal as claimed in any one of claims 1 to 7.

12. A safety valve lead seal status recognition system, characterized in that: It includes an inspection robot and a safety valve seal status recognition device as described in right 10; The inspection robot is used to collect image data of the safety valve seal to be identified on site.

Images