An industrial gas cylinder filling monitoring method, device, terminal device and storage medium

Abstract

The present application provides an industrial gas cylinder filling monitoring method, device, terminal device and storage medium, which are applicable to the field of data processing technology. The method includes: obtaining industrial gas cylinder image information and filling time information; obtaining bottle body texture information, bottle body color information corresponding to the standard filling gas type information, gas cylinder identification information, gas type information to be filled, and gas cylinder scrapping time information according to the industrial gas cylinder image information; generating gas cylinder identification information to be filled according to the gas cylinder identification information, filling time information, gas cylinder scrapping time information, gas type information to be filled, standard filling gas type information and a preset time difference threshold; and performing monitoring and processing on the industrial gas cylinder according to the gas cylinder filling monitoring parameter information received in real time, the gas cylinder identification information to be filled and a preset gas cylinder filling parameter threshold. The present application is used for automatically monitoring the gas filling process of industrial gas cylinders, and improving the efficiency and safety of the industrial gas cylinder filling work.

Description

Technical Field

[0001] This application belongs to the technical field of data processing, and particularly relates to an industrial gas cylinder filling monitoring method, device, terminal device, and storage medium. Background Art

[0002] Industrial gas cylinders are special containers used to store compressed gases or liquefied gases and are widely used in the industrial field. They are usually made of high-strength alloy steel or composite materials, have good pressure resistance performance and are safe and reliable, and play an important role in multiple industries such as metal processing, chemical industry, and medical treatment. Industrial gas cylinders can be classified in various ways. According to the properties and uses of the gases, they can be divided into oxygen cylinders, nitrogen cylinders, hydrogen cylinders, acetylene cylinders, etc. In the filling operation of industrial gas cylinders, since the filling medium has properties such as flammability, explosiveness, and toxicity, and the filling process has characteristics such as repeated filling of gas cylinders, non-fixed operators, and real-time changes in the filling environmental conditions, real-time monitoring is required during the filling process of industrial gas cylinders to avoid the occurrence of dangerous accidents.

[0003] In the prior art, for the tracking and management of the gas cylinder filling process, the special barcodes on the outer side of the gas cylinder are usually scanned manually and the information carried in the barcodes is entered into the management system for statistics of the filled gas cylinder information; or the video information during the filling process is obtained, and the filling operator information and gas cylinder information in the video information are compared manually in the background to prevent operators from privately replacing gas cylinders for illegal filling to seek personal gain.

[0004] However, in the prior art, the collection and comparison of gas cylinder information and filling operator information are carried out manually before the gas cylinder filling operation, and during the filling operation, the filling operator observes the abnormal conditions of the filling environment, and it is impossible to determine whether the quality of the gas cylinder is suitable for filling, resulting in a reduction in the monitoring efficiency of the filling process and making it difficult to ensure the accuracy and safety of gas filling for industrial gas cylinders. Summary of the Invention

[0005] In view of this, the embodiments of this application provide an industrial gas cylinder filling monitoring method, device, terminal device, and storage medium, aiming to solve the problems in the prior art that the monitoring of industrial gas cylinder filling operations cannot be separated from manual operations, and the quality problems of industrial gas cylinders and the types of filling gases are not identified, resulting in low monitoring efficiency, high filling error rate, and poor safety during the industrial gas cylinder filling process.

[0006] The first aspect of the embodiments of this application provides an industrial gas cylinder filling monitoring method, including:

[0007] Obtain industrial gas cylinder image information and filling time information;

[0008] Identify and process the industrial gas cylinder image information to obtain the cylinder body texture information, cylinder body color information, and gas cylinder label information; the cylinder body color information corresponds one-to-one with the standard filling gas type information; the gas cylinder label information carries the gas cylinder identification information, the gas type information to be filled, and the gas cylinder scrapping time information;

[0009] Detect defects in the cylinder body texture information to generate gas cylinder surface defect confirmation information;

[0010] When the difference between the filling time information and the gas cylinder scrapping time information is greater than the preset time difference threshold, and when the gas type information to be filled is consistent with the standard filling gas type information, obtain the gas cylinder identification information to be filled according to the gas cylinder surface defect confirmation information and the gas cylinder identification information;

[0011] Monitor and process the industrial gas cylinder according to the gas cylinder filling monitoring parameter information received in real time, the gas cylinder identification information to be filled, and the preset gas cylinder filling parameter threshold information.

[0012] The second aspect of the embodiments of the present application provides an industrial gas cylinder filling process monitoring device, including:

[0013] An information acquisition module for acquiring industrial gas cylinder image information and filling time information;

[0014] An image information recognition module for identifying and processing the industrial gas cylinder image information to obtain the cylinder body texture information, cylinder body color information, and gas cylinder label information; the cylinder body color information corresponds one-to-one with the standard filling gas type information; the gas cylinder label information carries the gas cylinder identification information, the gas type information to be filled, and the gas cylinder scrapping time information;

[0015] A cylinder body texture information defect detection module for detecting defects in the cylinder body texture information to generate gas cylinder surface defect confirmation information;

[0016] A gas cylinder identification information generation module to be filled for obtaining the gas cylinder identification information to be filled according to the gas cylinder surface defect confirmation information and the gas cylinder identification information when the difference between the filling time information and the gas cylinder scrapping time information is greater than the preset time difference threshold, and when the gas type information to be filled is consistent with the standard filling gas type information; and

[0017] An industrial gas cylinder monitoring and processing module for monitoring and processing the industrial gas cylinder according to the gas cylinder filling monitoring parameter information received in real time, the gas cylinder identification information to be filled, and the preset gas cylinder filling parameter threshold information.

[0018] In a third aspect of the embodiments of the present application, a terminal device is provided. The terminal device includes a memory and a processor. A computer program that can run on the processor is stored on the memory. When the processor executes the computer program, the steps of the industrial gas cylinder filling monitoring method described in any one of the above first aspects are implemented.

[0019] In a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, including: a stored computer program, characterized in that when the computer program is executed by a processor, the steps of the industrial gas cylinder filling monitoring method described in any one of the above first aspects are implemented.

[0020] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: Before the gas cylinder is filled with gas, the bottle body texture information, bottle body color information, gas type information to be filled, and gas cylinder scrapping time information included in the industrial gas cylinder image are automatically identified first. By performing defect detection on the bottle body texture information, industrial gas cylinders with situations such as undercut, edge dislocation, weld bead, pit, surface pores, and surface cracks on the bottle body are automatically screened out. Furthermore, according to the current filling time information and the gas cylinder scrapping time information, it is automatically determined whether the industrial gas cylinder reaches the condition that needs to be scrapped, so as to ensure that the quality of the industrial gas cylinders used for gas filling is qualified. At the same time, by judging the consistency between the gas type to be filled and the standard filling gas type, the situation of incorrect gas filling resulting in the inability to accurately determine the filling gas type through the bottle body color is avoided. During the filling process, by receiving the filling monitoring parameters sent by each sensor, the safety of the filling process is automatically monitored, realizing the automatic monitoring of the industrial gas cylinder filling operation, thereby improving the efficiency, accuracy, and safety of the industrial gas cylinder filling operation. Description of the Drawings

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0022] Figure 1 It is a schematic flowchart of the implementation of the industrial gas cylinder filling monitoring method provided in Embodiment 1 of the present application;

[0023] Figure 2 It is a schematic flowchart of the implementation of the industrial gas cylinder filling monitoring method provided in Embodiment 2 of the present application;

[0024] Figure 3 It is a schematic flowchart of the implementation of the industrial gas cylinder filling monitoring method provided in Embodiment 3 of the present application;

[0025] Figure 4 It is a schematic diagram of the implementation process of the industrial gas cylinder filling monitoring method provided in the fourth embodiment of the present application;

[0026] Figure 5 It is a schematic diagram of the implementation process of the industrial gas cylinder filling monitoring method provided in the fifth embodiment of the present application;

[0027] Figure 6 It is a schematic diagram of the implementation process of the industrial gas cylinder filling monitoring method provided in the sixth embodiment of the present application;

[0028] Figure 7 It is a schematic diagram of the implementation process of the industrial gas cylinder filling monitoring method provided in the seventh embodiment of the present application;

[0029] Figure 8 It is a schematic structural diagram of the industrial gas cylinder filling process monitoring device provided in the embodiment of the present application;

[0030] Figure 9 It is a schematic diagram of the terminal device provided in the embodiment of the present application. Detailed implementation manners

[0031] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0032] In order to illustrate the technical solutions described in the present application, the following will be described through specific embodiments.

[0033] Figure 1 The implementation flowchart of the industrial gas cylinder filling monitoring method provided in the first embodiment of the present application is shown, and the details are as follows:

[0034] Step S101, obtain industrial gas cylinder image information and filling time information.

[0035] In this embodiment, the industrial gas cylinder image information can be obtained by shooting with a camera installed at the industrial gas cylinder filling operation site. It can be understood that the industrial gas cylinder image can be an image of the gas cylinder to be filled taken by the camera at the filling operation site before the gas filling of the gas cylinder starts. The filling time information can refer to the start time of the current gas filling operation, which can be taken as the time point when the gas cylinder image is taken before filling, including year, month, day information, and can also include hour, minute, and second information.

[0036] Step S102: Identify and process the industrial gas cylinder image information to obtain the bottle body texture information, bottle body color information, and gas cylinder label information. The bottle body color information corresponds one-to-one with the standard filling gas type information. The gas cylinder label information carries the gas cylinder identification information, the gas type information to be filled, and the gas cylinder scrapping time information.

[0037] In this embodiment, the identification and processing of the industrial gas cylinder image information can be carried out by means of image processing or image segmentation to separate the bottle body surface image information and the gas cylinder label information from the industrial gas cylinder image information, and then perform texture and color identification and processing on the bottle body surface image information to obtain the bottle body texture information and the bottle body color information. The bottle body texture information can be the pattern shape on the bottle body surface. The gas cylinder label information can be the label on the industrial gas cylinder body or the label attached to the valve of the industrial gas cylinder. It can be understood that the bottle body color of the industrial gas cylinder corresponds one-to-one with a specific filling gas type. For example, if the bottle body color is black, it indicates that the industrial gas cylinder is an acetylene cylinder; if the bottle body color is green, it indicates that the industrial gas cylinder is an oxygen cylinder; if the bottle body color is light purple, it indicates that the industrial gas cylinder is a hydrogen cylinder. Therefore, when filling gas into an industrial gas cylinder, it is necessary to strictly fill a specific type of gas according to the bottle body color. The name of this specific type of gas can be called the standard filling gas type information, which is used to judge whether it is consistent with the gas type to be filled before filling. The gas cylinder scrapping time information can be set when the gas cylinder leaves the factory, which is used to indicate the service life of the gas cylinder. When the gas cylinder reaches the scrapping time, the gas cylinder needs to be scrapped. It can be understood that industrial gas cylinders are usually involved in repeated filling, and it is very likely that the gas cylinders to be filled with gas are mixed with gas cylinders that are very close to the scrapping time.

[0038] Step S103: Detect defects in the bottle body texture information to generate gas cylinder surface defect confirmation information.

[0039] In this embodiment, the bottle body texture information can be presented in the form of an image. The method of defect detection can be to process the image of the bottle body texture information to identify defect conditions such as undercut, edge dislocation, weld bead, pit, surface porosity, and surface crack contained in the bottle body texture information. When it is identified that the bottle body surface of the gas cylinder has a defect condition, gas cylinder surface defect confirmation information is generated according to the specific situation of the defect, which is used to characterize the defect condition of the industrial gas cylinder, so as to screen out the gas cylinder with the defect condition and avoid filling gas into the defective gas cylinder, resulting in an accident.

[0040] Step S104: Determine whether the difference between the filling time information and the gas cylinder scrapping time information is greater than a preset time difference threshold; if so, when the type information of the gas to be filled is consistent with the type information of the standard filling gas, obtain the identification information of the gas cylinder to be filled according to the surface defect confirmation information of the gas cylinder and the identification information of the gas cylinder; if not, scrap the industrial gas cylinder corresponding to the filling time information.

[0041] In this embodiment, the preset time difference threshold can be set manually to prevent the gas cylinder from reaching the scrapping time immediately after filling. It can be understood that when the filling time is after the gas cylinder scrapping time, the difference between the filling time information and the gas cylinder scrapping time information is calculated, and the difference between the filling time information and the gas cylinder scrapping time information is compared with the time difference threshold to determine whether the service life of the industrial gas cylinder has reached or is about to reach the scrapping period. When the difference between the filling time information and the gas cylinder scrapping time information is greater than the preset time difference threshold, it is determined that there is no problem of the industrial gas cylinder being about to be scrapped. Then, it is necessary to determine whether the gas to be filled shown in the label information of the gas cylinder is consistent with the standard filling gas corresponding to the bottle body color to avoid incorrect filling of the gas type for the industrial gas cylinder. Only when the service life of the gas cylinder is far from reaching the scrapping period and the gas to be filled shown in the label information of the gas cylinder is consistent with the standard filling gas corresponding to the bottle body color, the filling work of the gas cylinder is carried out. When it is detected that the gas to be filled shown in the label information of the gas cylinder is inconsistent with the standard filling gas corresponding to the bottle body color, the gas cylinder is recycled for subsequent modification of the label information to facilitate reuse before the scrapping period. When the filling time is before the gas cylinder scrapping time, the industrial gas cylinder corresponding to the scrapping time of the gas cylinder is directly scrapped.

[0042] Step S105: Monitor and process the industrial gas cylinder according to the gas cylinder filling monitoring parameter information received in real time, the identification information of the gas cylinder to be filled, and the preset gas cylinder filling parameter threshold information.

[0043] In this embodiment, the gas cylinder filling monitoring parameter information can be collected and sent by sensors at the filling operation site. The gas cylinder filling monitoring parameter information can be the gas pressure information inside the bottle, the filling pipeline temperature information, the filling pipeline pressure information, the gas filling speed information, etc. The preset gas cylinder filling parameter threshold information can be set manually, which can be the gas pressure threshold inside the bottle, the filling pipeline temperature threshold, the filling pipeline pressure threshold, the gas filling speed threshold, etc. When the gas cylinder filling monitoring parameter information is greater than or less than the preset gas cylinder filling parameter threshold information, it indicates that an abnormal situation occurs during the filling process, and it is necessary to timely adjust the working state of the equipment for filling to avoid the occurrence of adverse accidents.

[0044] The industrial gas cylinder filling monitoring method provided by the embodiment of the present application first automatically identifies the bottle body texture information, bottle body color information, type information of the gas to be filled, and gas cylinder scrapping time information included in the industrial gas cylinder image. By performing defect detection on the bottle body texture information, industrial gas cylinders with situations such as undercut, edge dislocation, weld bead, pit, surface pores, and surface cracks on the bottle body are automatically screened out. Furthermore, according to the current filling time information and the gas cylinder scrapping time information, it is judged whether the industrial gas cylinder meets the conditions for scrapping treatment, so as to ensure that the industrial gas cylinders used for gas filling are of qualified quality. At the same time, by judging the consistency between the type of gas to be filled and the standard filling gas type, the situation of incorrect gas filling resulting in the inability to accurately determine the type of filled gas through the bottle body color is avoided. During the filling process, by receiving the filling monitoring parameters sent by each sensor, the safety of the filling process is monitored, thereby improving the efficiency, accuracy, and safety of the industrial gas cylinder filling operation.

[0045] Figure 2 The implementation flowchart of the industrial gas cylinder filling monitoring method provided by the second embodiment of the present application is shown. The difference from the first embodiment above is that: step S102 specifically includes:

[0046] Step S201, randomly generate the initial center points of the gas cylinder surface information class and the initial center points of the label information class.

[0047] In this embodiment, the initial center points of the gas cylinder surface information class and the initial center points of the label information class are randomly generated by a computer and are used to analyze the gas cylinder image to initially classify the pixel points in the gas cylinder image, so as to separate the gas cylinder surface information and the label information. It can be understood that the label information of the industrial gas cylinder can be on the bottle body or outside the bottle body.

[0048] Step S202, according to the preset pixel sampling interval information, perform pixel sampling processing on the industrial gas cylinder image information to obtain a plurality of gas cylinder image pixel sample points.

[0049] In this embodiment, the preset pixel sampling interval information can be set manually and is used to represent how many pixel points are sampled at a time to avoid selecting every pixel of the image and reduce the computational complexity. The sampled pixel points are the gas cylinder image pixel sample points.

[0050] Step S203, calculate the Euclidean distance values between the plurality of gas cylinder image pixel sample points and the initial center points of the gas cylinder surface information class and the initial center points of the label information class respectively, and generate the initial membership degree matrix of the gas cylinder surface information and the initial membership degree matrix of the label information.

[0051] In this embodiment, the Euclidean distance value between the pixel sample points of the gas cylinder image and the central point of the initial gas cylinder surface information class is calculated to obtain the membership degree of the gas cylinder surface. The membership degrees of multiple gas cylinder surfaces are output in the form of a matrix to obtain the initial membership degree matrix of the gas cylinder surface information. The Euclidean distance value between the pixel sample points of the gas cylinder image and the central point of the initial label information class is calculated to obtain the membership degree of the gas cylinder label. The membership degrees of multiple gas cylinder labels are output in the form of a matrix to obtain the initial membership degree matrix of the label information.

[0052] Step S204: Extract the maximum value element of the initial membership degree matrix of the gas cylinder surface information, and use the pixel sample point of the gas cylinder image corresponding to the maximum value element of the initial membership degree matrix of the gas cylinder surface information as the central point of the intermediate gas cylinder surface information class.

[0053] In this embodiment, the maximum value among all the elements in the initial membership degree matrix of the gas cylinder surface information is extracted, and the pixel sample point of the gas cylinder image corresponding to this maximum value is used as the new central point. This new central point can be called the central point of the intermediate gas cylinder surface information class to reclassify the pixel sample points of the gas cylinder image, avoiding inaccurate classification caused by random factors in the initial classification, so as to accurately separate the gas cylinder surface information from the gas cylinder image.

[0054] Step S205: Extract the maximum value element of the initial membership degree matrix of the label information, and use the pixel sample point of the gas cylinder image corresponding to the maximum value element of the initial membership degree matrix of the label information as the central point of the intermediate label information class.

[0055] In this embodiment, the maximum value among all the elements in the initial membership degree matrix of the label information is extracted, and the pixel sample point of the gas cylinder image corresponding to this maximum value is used as the new central point. This new central point can be used as the central point of the intermediate label information class to reclassify the pixel sample points of the gas cylinder image, avoiding inaccurate classification caused by random factors in the initial classification, so as to accurately separate the label information from the gas cylinder image.

[0056] Step S206: Obtain the bottle body texture information, the bottle body color information, and the gas cylinder label information according to the pixel sample points of the gas cylinder image, the central point of the intermediate gas cylinder surface information class, and the central point of the intermediate label information class.

[0057] In this embodiment, it may be to recalculate the Euclidean distances between the pixel sample points of the gas cylinder image, the center points of the intermediate gas cylinder surface information class, and the center points of the intermediate label information class respectively, to obtain the membership degrees of the intermediate gas cylinder surface information and the intermediate label information, so as to divide the pixel sample points of the gas cylinder image through the membership degrees of the intermediate gas cylinder surface information and the intermediate label information, and obtain the gas cylinder surface information and the gas cylinder label information. Further image processing can be performed on the gas cylinder surface information. It may be to obtain the gas cylinder texture information through high-resolution reconstruction, or to obtain the gas cylinder color information through color recognition.

[0058] The industrial gas cylinder filling monitoring method provided by the embodiment of the present application classifies the pixel sample points of the gas cylinder image through the randomly generated initial center points of the gas cylinder surface information class and the initial center points of the label information class. By separately calculating the logical distances between each pixel sample point of the gas cylinder image and the initial center points of the gas cylinder surface information class and the initial center points of the label information class, the membership degree of each pixel sample point of the gas cylinder image is quantified, avoiding image segmentation errors caused by slight occlusion, thereby improving the accuracy of image segmentation, facilitating the accurate extraction of the gas cylinder surface information and label information in the industrial gas cylinder image information, and being used for subsequent accurate discrimination of the quality and service life of the gas cylinder, so as to improve the safety and reliability of the gas cylinder filling work.

[0059] Figure 3 The flowchart of implementing the industrial gas cylinder filling monitoring method provided by the third embodiment of the present application is shown. The difference from the second embodiment above is that the step S206 specifically includes:

[0060] Step S301, determine whether the center points of the intermediate gas cylinder surface information class and the center points of the intermediate label information class are the same as the initial center points of the gas cylinder surface information class and the initial center points of the label information class respectively. If so, enter step S302; if not, enter step S312.

[0061] In this embodiment, when the center points of the intermediate gas cylinder surface information class are the same as the initial center points of the gas cylinder surface information class, and the center points of the intermediate label information class are the same as the initial center points of the label information class, it indicates that the classification calculation of the pixel sample points of the gas cylinder image has achieved convergence, and the current calculation result is the global optimal solution of the classification calculation, and there is no need to perform further classification calculation on the pixel sample points of the gas cylinder image. When the center points of the intermediate gas cylinder surface information class are different from the initial center points of the gas cylinder surface information class, or the center points of the intermediate label information class are different from the initial center points of the label information class, it indicates that the classification calculation of the pixel sample points of the gas cylinder image has not achieved convergence, and the current calculation result is not the global optimal solution of the classification calculation, and further classification calculation needs to be performed on the pixel sample points of the gas cylinder image.

[0062] Step S302: Use the center point of the intermediate gas cylinder surface information class and the center point of the intermediate label information class as the target gas cylinder surface information class center point and the target label information class center point respectively.

[0063] In this embodiment, when the center point of the intermediate gas cylinder surface information class is the same as the center point of the initial gas cylinder surface information class, and the center point of the intermediate label information class is the same as the center point of the initial label information class, it indicates that the classification calculation of the gas cylinder image pixel sample points has achieved convergence. At this time, the center point of the intermediate gas cylinder surface information class and the center point of the intermediate label information class are used as the target gas cylinder surface information class center point and the target label information class center point respectively to directly classify the gas cylinder image pixel sample points. It can be understood that, for example, when the logical distance between a gas cylinder image pixel sample point and the target gas cylinder surface information class center point is much smaller than the logical distance between the gas cylinder image pixel sample point and the target label information class center point, it indicates that the gas cylinder image pixel sample point belongs to the pixel points of the gas cylinder surface information and can be used to synthesize the gas cylinder surface information.

[0064] Step S303: Calculate the Euclidean distance between multiple gas cylinder image pixel sample points and the target gas cylinder surface information class center point to obtain multiple membership values of the gas cylinder surface pixel sample points.

[0065] In this embodiment, calculate the Euclidean distance between all gas cylinder image pixel sample points and the target gas cylinder surface information class center point respectively, and use the calculated Euclidean distance as the membership value of the gas cylinder surface pixel sample point to determine whether the gas cylinder image pixel sample point can be used as a pixel point of the gas cylinder surface information for synthesizing the gas cylinder surface information.

[0066] Step S304: Determine whether the membership value of the gas cylinder surface pixel sample point is less than or equal to a preset membership threshold of the gas cylinder surface pixel sample point. If so, proceed to step S305; if not, determine the gas cylinder image pixel sample point corresponding to the membership value of the gas cylinder surface pixel sample point as a non-gas cylinder surface information pixel point.

[0067] In this embodiment, when the membership value of the gas cylinder surface pixel sample point is less than or equal to the preset membership threshold of the gas cylinder surface pixel sample point, it indicates that the gas cylinder image pixel sample point corresponding to the membership value of the gas cylinder surface pixel sample point can be used as a pixel point of the gas cylinder surface information and can be used to synthesize the gas cylinder surface information. When the membership value of the gas cylinder surface pixel sample point is greater than the preset membership threshold of the gas cylinder surface pixel sample point, it indicates that the gas cylinder image pixel sample point corresponding to the membership value of the gas cylinder surface pixel sample point cannot be used as a pixel point of the gas cylinder surface information. Therefore, the gas cylinder image pixel sample point corresponding to the membership value of the gas cylinder surface pixel sample point is determined as a non-gas cylinder surface information pixel point and cannot be used to synthesize the gas cylinder surface information.

[0068] Step S305: Determine the gas cylinder image pixel sample points corresponding to the membership values of the gas cylinder surface pixel sample points as the gas cylinder surface information pixel points.

[0069] In this embodiment, the gas cylinder image pixel sample points corresponding to the membership values of the gas cylinder surface pixel sample points can be used as the gas cylinder surface information pixel points and can be used to synthesize the gas cylinder surface information.

[0070] Step S306: Generate the gas cylinder surface information based on the gas cylinder surface information pixel points.

[0071] In this embodiment, the gas cylinder surface information can be generated by directly splicing the gas cylinder surface information pixel points, or by interpolating and splicing the gas cylinder surface information pixel points.

[0072] Step S307: Identify and analyze the gas cylinder surface information to obtain the bottle body texture information and the bottle body color information.

[0073] In this embodiment, the bottle body texture information can be obtained by first performing high-resolution reconstruction on the gas cylinder surface information, and the bottle body color information can be obtained by calculating the RGB values of the gas cylinder surface information.

[0074] Step S308: Calculate the Euclidean distances between multiple gas cylinder image pixel sample points and the center point of the target label information class to obtain multiple membership values of the label information pixel sample points.

[0075] In this embodiment, calculate the Euclidean distances between all gas cylinder image pixel sample points and the center point of the target label information class respectively, and use the calculated Euclidean distances as the membership values of the label information pixel sample points to determine whether the gas cylinder image pixel sample points can be used as the pixel points of the label information for synthesizing the gas cylinder label information.

[0076] Step S309: Determine whether the membership value of the label information pixel sample point is less than or equal to the preset membership threshold of the label information pixel sample point. If so, proceed to step S310; if not, determine the gas cylinder image pixel sample points corresponding to the membership value of the label information pixel sample point as non-gas cylinder label pixel points.

[0077] In this embodiment, when the membership value of the gas cylinder surface pixel sample point is less than or equal to the preset membership threshold of the label information pixel sample point, it indicates that the gas cylinder image pixel sample point corresponding to the membership value of the gas cylinder surface pixel sample point can be used as a pixel point of the label information and can be used to synthesize the label information. When the membership value of the gas cylinder surface pixel sample point is greater than the preset membership threshold of the label information pixel sample point, it indicates that the gas cylinder image pixel sample point corresponding to the membership value of the gas cylinder surface pixel sample point cannot be used as a pixel point of the label information. Therefore, the gas cylinder image pixel sample point corresponding to the membership value of the gas cylinder surface pixel sample point is determined as a non-gas cylinder label information pixel point and cannot be used to synthesize the gas cylinder label information.

[0078] Step S310: Determine the gas cylinder image pixel sample point corresponding to the membership value of the label information pixel sample point as a gas cylinder label pixel point.

[0079] In this embodiment, the gas cylinder image pixel sample point corresponding to the membership value of the label information pixel sample point can be used as a gas cylinder label pixel point and can be used to synthesize the gas cylinder label information.

[0080] Step S311: Obtain the gas cylinder label information according to the gas cylinder label pixel points.

[0081] In this embodiment, the gas cylinder label information can be generated by directly splicing the gas cylinder label pixel points, or by interpolating and splicing the gas cylinder label pixel points.

[0082] Step S312: Use the intermediate gas cylinder surface information class center point and the intermediate label information class center point as the initial gas cylinder surface information class center point and the initial label information class center point, and return to step S203.

[0083] In this embodiment, when the intermediate gas cylinder surface information class center point is different from the initial gas cylinder surface information class center point, or the intermediate label information class center point is different from the initial label information class center point, it indicates that the classification calculation of the gas cylinder image pixel sample points has not converged, and the current calculation result is not the optimal solution of the classification calculation. Therefore, adjust the intermediate gas cylinder surface information class center point and the intermediate label information class center point for reclassification until the intermediate gas cylinder surface information class center point and the intermediate label information class center point no longer change.

[0084] The industrial gas cylinder filling monitoring method provided by the embodiments of the present application calculates the Euclidean distances between the pixel sample points of the gas cylinder image and the central points of the intermediate gas cylinder surface information class and the central points of the intermediate label information class respectively, so as to quantify the membership degree of the pixel sample points of the gas cylinder image, and accurately classify the pixel sample points of the gas cylinder image. When the classification calculation fails to converge, by adjusting the central points of the intermediate gas cylinder surface information class and the central points of the intermediate label information class, the calculation result approaches the global optimal solution, ensuring the accurate extraction and separation of the gas cylinder surface information, effectively improving the accuracy of gas cylinder quality detection and wrong gas type filling detection through the gas cylinder surface information, and thus ensuring the safety and effectiveness of gas cylinder filling.

[0085] Figure 4 The flowchart of the implementation of the industrial gas cylinder filling monitoring method provided by Embodiment 4 of the present application is shown. The difference from Embodiment 1 above is that step S103 specifically includes:

[0086] Step S401: Generate a plurality of anchor box pixel information according to the bottle body texture information, the preset anchor box width, and the preset anchor box height.

[0087] In this embodiment, the preset anchor box width and the preset anchor box height can be set manually. The bottle body texture information can be presented in the form of an image composed of multiple pixel points. Multiple anchor boxes are formed in the bottle body texture information, and the height and width of the anchor boxes can be dynamically changed to extract the local pixels of the bottle body texture information, and the extracted pixels are the anchor box pixel information.

[0088] Step S402: Calculate the similarity between the plurality of anchor box pixel information to obtain the anchor box pixel matching degree.

[0089] In this embodiment, it can be the cosine similarity, and the calculated cosine similarity is used as the anchor box pixel matching degree to represent the overlapping degree of the plurality of anchor box pixel information.

[0090] Step S403: Determine whether the anchor box pixel matching degree is less than or equal to the preset matching degree threshold. If so, go to step S404; if not, do not use the plurality of anchor box pixel information corresponding to the anchor box pixel matching degree as the bottle body texture pixel feature class information.

[0091] In this embodiment, when the anchor box pixel matching degree is less than or equal to the preset matching degree threshold, it means that the logical distance of the plurality of anchor box pixel information is small and can be used as pixel points of the same type of bottle body texture pixel feature class information for analysis and calculation. When the anchor box pixel matching degree is greater than the preset matching degree threshold, it means that the logical distance of the plurality of anchor box pixel information is large and cannot be used as pixel points of the same type of bottle body texture pixel feature class information for analysis and calculation.

[0092] Step S404: Use the multiple anchor pixel information corresponding to the anchor pixel matching degree as the bottle body texture pixel feature class information.

[0093] In this embodiment, the logical distances of the multiple anchor pixel information are small, and they can be analyzed and calculated as pixel points of the same class of bottle body texture pixel feature class information.

[0094] Step S405: According to the bottle body texture pixel feature class information and a preset feature representation function, obtain a bottle body texture feature representation information map.

[0095] In this embodiment, the preset feature representation function can be set manually. It can be a convolution calculation of the bottle body texture pixel feature class information and the feature representation function, and the calculation result can be output in the form of a matrix, that is, output the bottle body texture feature representation information map.

[0096] Step S406: Generate gas cylinder surface defect confirmation information according to the bottle body texture feature representation information map, a preset first coefficient matrix, a preset second coefficient matrix, a preset spatial displacement variable matrix, and a preset spatial mapping function.

[0097] In this embodiment, the preset first coefficient matrix, the preset second coefficient matrix, the preset spatial displacement variable matrix, and the preset spatial mapping function can all be set manually. Among them, the first coefficient matrix and the second coefficient matrix are used to quantify the importance of multiple bottle body texture features. It can be understood that to avoid missing important features of the bottle body texture, multiple coefficient matrices are set for quantification to ensure that as many important features as possible can be considered to improve the detection accuracy of gas cylinder surface defects. The spatial mapping function is used to map the important features of the bottle body texture from the linear space to the non-linear space, so that the important features can be fully considered and analyzed. The spatial displacement variable matrix is used to characterize the displacement amount of the important features in the non-linear space, which is used to enhance the connection of the important features in the non-linear space to improve the sufficiency and accuracy of analyzing the important features.

[0098] The industrial gas cylinder filling monitoring method provided by the embodiment of the present application divides different information in the bottle body texture information by generating anchor boxes to obtain anchor box pixel information, locks the obtained anchor box pixel information by calculating the anchor box pixel matching degree, performs feature extraction operations on the locked pixels through a feature characterization function, quantifies the extracted pixel features through a coefficient matrix to obtain important features, projects the quantified important features into a non-linear space through a space mapping function to enhance the expression of important pixel features, and enhances the connection and difference between important features through a space displacement variable matrix, thereby improving the recognition accuracy of the bottle body texture information, avoiding misdetection of the surface information of industrial gas cylinders, ensuring that the quality of industrial gas cylinders for gas filling meets the standards, and improving the safety and reliability of the gas cylinder filling operation.

[0099] Figure 5 The implementation flowchart of the industrial gas cylinder filling monitoring method provided in the fifth embodiment of the present application is shown. The difference from the fourth embodiment above is that step S405 specifically includes:

[0100] Step S501: Perform a convolution operation on the bottle body texture pixel feature class information and a preset first feature characterization function to generate multiple initial bottle body texture feature information maps.

[0101] In this embodiment, the preset first feature characterization function can be set artificially. It can be understood that the result of the convolution operation can be output in the form of a matrix, and the output result after the convolution operation of the bottle body texture pixel feature class information and the first feature characterization function can be the initial bottle body texture feature information map.

[0102] Step S502: Extract the extreme value elements of multiple initial bottle body texture feature information maps respectively to generate a first intermediate bottle body texture feature information map.

[0103] In this embodiment, extracting the extreme value elements of the initial bottle body texture feature information map is used to compress the initial bottle body texture feature information map. The result of the compression process is the first intermediate bottle body texture feature information map, which is used to reduce the amount of calculation while ensuring that the bottle body texture features are fully considered in subsequent calculations, so as to reduce the calculation complexity.

[0104] Step S503: Perform a convolution operation on the first intermediate bottle body texture feature information map and a preset second feature characterization function to generate multiple second intermediate bottle body texture feature information maps.

[0105] In this embodiment, the preset second feature characterization function can be set artificially. It can be understood that the result of the convolution operation can be output in the form of a matrix, and the output result after the convolution operation of the first intermediate bottle body texture feature information map and the second feature characterization function can be the second intermediate bottle body texture feature information map.

[0106] Step S504: Extract the extreme value elements of multiple said second intermediate bottle body texture feature information graphs respectively to generate a target bottle body texture feature information graph.

[0107] In this embodiment, the extreme value elements of the second intermediate bottle body texture feature information graph are extracted to perform a re-compression process on the bottle body texture feature information graph. The result after the compression process is the target bottle body texture feature information graph, which is used to reduce the amount of computation while ensuring that the bottle body texture features are fully considered in subsequent calculations, thereby reducing the computational complexity.

[0108] Step S505: Normalize the said target bottle body texture feature information graph to obtain a bottle body texture feature representation information graph.

[0109] In this embodiment, the normalization process can adopt the Z-Score function or the hyperbolic tangent function, which is used to avoid misidentifying the bottle body texture due to the numerical value exceeding a specific dimension during the calculation process.

[0110] The industrial gas cylinder filling monitoring method provided by the embodiment of the present application, through multiple convolution operations and compression processes on the feature characterization function and the bottle body texture pixel information, while fully extracting the bottle body texture features, reduces the computational complexity, improves the computational convergence speed, thereby improving the recognition accuracy and efficiency of the bottle body information, and ensuring the quality reliability of the gas cylinders used for gas filling.

[0111] Figure 6 The implementation flowchart of the industrial gas cylinder filling monitoring method provided by the sixth embodiment of the present application is shown. The difference from the fourth embodiment above is that the step S406 specifically includes:

[0112] Step S601: Perform an inner product operation on the said bottle body texture feature representation information graph and a preset first coefficient matrix to obtain a first bottle body texture feature variable matrix.

[0113] In this embodiment, the preset first coefficient matrix can be set artificially. By performing an inner product operation on the bottle body texture feature representation information graph and the first coefficient matrix, the difference between all bottle body texture features is increased, and the expression effect of the important features in the bottle body texture features is highlighted. The result of the inner product operation is the first bottle body texture feature variable matrix.

[0114] Step S602: Perform an inner product operation on the said first bottle body texture feature variable matrix and a preset second coefficient matrix to obtain a second bottle body texture feature variable matrix.

[0115] In this embodiment, the preset second coefficient matrix can be set manually. By performing an inner product operation on the first bottle body texture feature variable matrix and the second coefficient matrix, the differences between all bottle body texture features are further increased, and the expression effect of important features in the bottle body texture features is further highlighted. The result of the inner product operation is the second bottle body texture feature variable matrix.

[0116] Step S603: Obtain the bottle body texture feature spatial displacement variable according to the second bottle body texture feature variable matrix and the preset spatial displacement variable matrix.

[0117] In this embodiment, it can be to perform an addition calculation on each element of the second bottle body texture feature variable matrix and the spatial displacement variable matrix, and the result of the addition calculation is the bottle body texture feature spatial displacement variable.

[0118] Step S604: Generate a bottle body texture spatial mapping feature map according to the bottle body texture feature spatial displacement variable and the preset spatial mapping function.

[0119] In this embodiment, the preset spatial mapping function can be the Sigmoid function. The bottle body texture feature spatial displacement variable can be used as the independent variable of the spatial mapping function, and the calculated function value is the bottle body texture spatial mapping feature map.

[0120] Step S605: Calculate the matching probability value between the bottle body texture spatial mapping feature map and the preset standard bottle body texture spatial mapping feature map.

[0121] In this embodiment, the preset standard bottle body texture spatial mapping feature map can be obtained by collecting and summarizing a large number of bottle body defect pictures, and is used to determine whether there are defects in the bottle body texture. The matching probability value can be the recall rate.

[0122] Step S606: Determine whether the matching probability value is not less than the preset matching probability threshold. If so, go to step S607; if not, generate a normal confirmation information for the gas cylinder surface texture according to the bottle body texture pixel feature class information.

[0123] In this embodiment, when the matching probability value is not less than the preset matching probability threshold, it indicates that there is a high probability that the bottle body texture pixels show the defect situation of the bottle body, and a defect confirmation information for the gas cylinder surface is generated to indicate that the gas cylinder cannot be used for gas filling work. When the matching probability value is less than the preset matching probability threshold, it indicates that there is a high probability that the bottle body texture pixels show that the bottle body has no defect, and a normal confirmation information for the gas cylinder surface texture is generated to indicate that the gas cylinder can be used for normal gas filling work.

[0124] Step S607: Generate a defect confirmation information for the gas cylinder surface according to the bottle body texture pixel feature class information.

[0125] In this embodiment, the specific defect information of the bottle body texture pixel display can be determined by the matching probability value between the bottle body texture pixel feature class information and multiple standard bottle body texture space mapping feature maps, and this specific defect information is generated into the gas cylinder surface defect confirmation information, which is used to characterize that the surface of the gas cylinder has defects and cannot be used for gas filling work.

[0126] The industrial gas cylinder filling monitoring method provided by the embodiment of the present application performs multiple inner product calculations on the bottle body texture feature representation information through multiple coefficient matrices, increasing the gap between different bottle body texture features, making the important bottle body texture features fully prominent, and being able to fully consider the existence of important features in the calculation process of the non-linear space. Therefore, even the image features of very subtle bottle body defects can increase the distance from the image features of the normal bottle body in the calculation, effectively reducing the missed detection probability of the bottle body defect situation, thereby improving the recognition accuracy of the bottle body texture information, ensuring that the bottle body of the industrial gas cylinder used for gas filling does not have defects, and guaranteeing the safety of the gas filling work and the stability and reliability of the gas cylinder during use.

[0127] Figure 7 The implementation flowchart of the industrial gas cylinder filling monitoring method provided by the seventh embodiment of the present application is shown. The difference from the first embodiment above is that: the gas cylinder filling monitoring parameter information includes the bottle internal pressure information and the filling pipeline temperature information; the bottle internal pressure information corresponds one-to-one with the to-be-filled gas cylinder identification information; the preset gas cylinder filling parameter threshold information includes the preset bottle internal pressure threshold information, the preset first filling pipeline temperature threshold information, and the preset second filling pipeline temperature threshold information;

[0128] The step S105 specifically includes:

[0129] Step S701, determine whether the filling pipeline temperature information is greater than the preset first filling pipeline temperature threshold information; if so, enter step S702; if not, enter step S705.

[0130] In this embodiment, the preset first filling pipeline temperature threshold information can be set artificially. When the filling pipeline temperature information is less than the preset first filling pipeline temperature threshold information, it indicates that the current filling pipeline temperature is too low, and the gas cylinder filling work needs to be stopped in time to avoid abnormal filling caused by liquefaction of the gas in the pipeline.

[0131] Step S702, determine whether the filling pipeline temperature information is less than the preset second filling pipeline temperature threshold information; if so, enter step S703; if not, enter step S705.

[0132] In this embodiment, the preset temperature threshold information of the second filling pipeline can be set manually. It can be understood that the temperature threshold information of the first filling pipeline is less than that of the second filling pipeline. When the temperature information of the filling pipeline is greater than the preset temperature threshold information of the second filling pipeline, it indicates that the current temperature of the filling pipeline is too high, and the gas cylinder filling work needs to be stopped in time, otherwise the gas cylinder body is very likely to burst. When the temperature information of the filling pipeline is greater than the preset temperature threshold information of the first filling pipeline and less than the preset temperature threshold information of the second filling pipeline, it indicates that the current temperature of the filling pipeline is within the normal range, and it is necessary to determine whether the pressure information in the cylinder is normal.

[0133] Step S703, determine whether the pressure information in the cylinder is greater than or equal to the preset pressure threshold information in the cylinder; if so, proceed to step S704; if not, proceed to step S705.

[0134] In this embodiment, the preset pressure threshold information in the cylinder can be set manually. When the pressure information in the cylinder is less than the preset pressure threshold information in the cylinder, it indicates that the current pressure in the cylinder is within the normal range, and the gas cylinder can continue to be filled. When the pressure information in the cylinder is greater than or equal to the preset pressure threshold information in the cylinder, it indicates that the current pressure in the cylinder is too high, and the filling work of the gas cylinder needs to be stopped in time, otherwise the gas cylinder is very likely to burst.

[0135] Step S704, determine the identification information of the gas cylinder to be filled corresponding to the pressure information in the cylinder, and stop filling the industrial gas cylinder corresponding to the identification information of the gas cylinder to be filled.

[0136] In this embodiment, when the pressure information in the cylinder is greater than or equal to the preset pressure threshold information in the cylinder, it indicates that the current pressure in the cylinder is too high, and the filling work of the industrial gas cylinder corresponding to the pressure information in the cylinder needs to be stopped in time, otherwise the gas cylinder is very likely to burst.

[0137] Step S705, stop filling each industrial gas cylinder.

[0138] In this embodiment, when the temperature information of the filling pipeline is greater than the preset temperature threshold information of the second filling pipeline, it indicates that the current temperature of the filling pipeline is too high, and the filling work of all gas cylinders needs to be stopped in time, otherwise the gas cylinder body is very likely to burst.

[0139] The industrial gas cylinder filling monitoring method provided by the embodiments of the present application detects and manages the safety of the filling process by receiving the in-cylinder pressure information and the filling pipeline temperature information in real time during the filling process. When the temperature of the filling pipeline is too low, the filling work of all industrial gas cylinders is stopped in time to avoid the gas filled into the gas cylinders from vaporizing. When the temperature of the filling pipeline is too high or the pressure in the cylinder is too high, the filling operation of the industrial gas cylinders is stopped immediately to avoid the rupture of the gas cylinders during the filling operation, thereby avoiding industrial accidents, reducing the risk losses of the gas cylinder filling operation, and effectively improving the safety of the gas cylinder filling process.

[0140] Corresponding to the method in the above embodiment, Figure 8 The structural block diagram of the industrial gas cylinder filling process monitoring device provided by the embodiments of the present application is shown. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown. Figure 8 The exemplary industrial gas cylinder filling process monitoring device may be the execution subject of the industrial gas cylinder filling monitoring method provided in the foregoing Embodiment 1.

[0141] Referring to Figure 8 , the industrial gas cylinder filling process monitoring device includes:

[0142] An information acquisition module 810, configured to acquire industrial gas cylinder image information and filling time information;

[0143] An image information recognition module 820, configured to perform recognition processing on the industrial gas cylinder image information to obtain bottle body texture information, bottle body color information, and gas cylinder label information; the bottle body color information corresponds one-to-one with the standard filling gas type information; the gas cylinder label information carries gas cylinder identification information, the type of gas to be filled, and the gas cylinder scrapping time information;

[0144] A bottle body texture information defect detection module 830, configured to perform defect detection on the bottle body texture information to generate gas cylinder surface defect confirmation information;

[0145] A to-be-filled gas cylinder identification information generation module 840, configured to obtain to-be-filled gas cylinder identification information according to the gas cylinder surface defect confirmation information and the gas cylinder identification information when the difference between the filling time information and the gas cylinder scrapping time information is greater than a preset time difference threshold and when the type of gas to be filled is consistent with the standard filling gas type information; and

[0146] An industrial gas cylinder monitoring and processing module 850, configured to perform monitoring and processing on industrial gas cylinders according to the gas cylinder filling monitoring parameter information received in real time, the to-be-filled gas cylinder identification information, and the preset gas cylinder filling parameter threshold information.

[0147] For the process in which each module in the industrial gas cylinder filling process monitoring device provided by the embodiments of this application realizes its respective functions, reference may specifically be made to the description of Embodiment 1 shown above, which will not be elaborated herein. Figure 1 Shown in the above-mentioned Embodiment 1, which will not be elaborated herein.

[0148] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not imply the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this application.

[0149] It should be understood that when used in the description of this application specification and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0150] It should also be understood that the term "and / or" used in the description of this application specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0151] As used in the description of this application specification and the appended claims, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" according to the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" according to the context.

[0152] In addition, in the description of this application specification and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and should not be understood as indicating or implying relative importance. It should also be understood that although the terms "first", "second", etc. are used in the text in some embodiments of this application to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, the first table can be named the second table, and similarly, the second table can be named the first table, without departing from the scope of the various described embodiments. The first table and the second table are both tables, but they are not the same table.

[0153] Reference to "one embodiment" or "some embodiments" etc. described in the specification of this application means that a specific feature, structure or characteristic described in connection with the embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments" etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0154] The industrial gas cylinder filling monitoring method provided by the embodiments of this application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, in-vehicle devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), etc. The embodiments of this application do not impose any restrictions on the specific types of terminal devices.

[0155] For example, the terminal device can be a station (STAION, ST) in a WLAN, can be a cellular phone, cordless phone, Session Initiation Protocol (SIP) phone, Wireless Local Loop (WLL) station, Personal Digital Assistant (PDA) device, handheld device with wireless communication function, computing device or other processing device connected to a wireless modem, in-vehicle device, vehicle networking terminal, computer, laptop computer, handheld communication device, handheld computing device, satellite wireless device, wireless modem card, set top box (STB), customer premise equipment (CPE) and / or other devices for communicating on a wireless system, and next-generation communication systems, for example, mobile terminals in a 5G network or mobile terminals in a future evolved Public Land Mobile Network (PLMN) network, etc.

[0156] By way of example and not limitation, when the terminal device is a wearable device, the wearable device can also be a general term for devices developed by applying wearable technologies to the intelligent design of daily wear, such as glasses, gloves, watches, clothing, shoes, etc. A wearable device is a portable device that is either worn directly on the body or integrated into the user's clothing or accessories. A wearable device is not just a hardware device, but also realizes powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable intelligent devices include those with complete functions and large sizes that can achieve complete or partial functions without relying on a smart phone, such as smart watches or smart glasses, as well as those that only focus on a certain type of application function and need to cooperate with other devices such as smart phones, such as various smart bracelets and smart jewelry for physical sign monitoring.

[0157] Figure 9 is a schematic structural diagram of a terminal device provided by an embodiment of the present application. As Figure 9 shown, the terminal device 9 of this embodiment includes: at least one processor 90 ( Figure 9 only one is shown in the figure), a memory 91, and a computer program 92 that can run on the processor 90 is stored in the memory 91. When the processor 90 executes the computer program 92, the steps in the embodiments of the above various industrial gas cylinder filling monitoring methods are implemented, such as Figure 1 the steps S101 to S105 shown in the figure. Alternatively, when the processor 90 executes the computer program 92, the functions of each module / unit in the above device embodiments are implemented, such as Figure 8 the functions of the modules 810 to 850 shown in the figure.

[0158] The terminal device 9 can be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor 90 and a memory 91. Those skilled in the art can understand that Figure 9 this is only an example of the terminal device 9 and does not constitute a limitation on the terminal device 9. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, the terminal device may also include an input and sending device, a network access device, a bus, etc.

[0159] The so-called processor 90 may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0160] In some embodiments, the memory 91 may be an internal storage unit of the terminal device 9, such as the hard disk or memory of the terminal device 9. The memory 91 may also be an external storage device of the terminal device 9, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., equipped on the terminal device 9. Further, the memory 91 may also include both the internal storage unit of the terminal device 9 and the external storage device. The memory 91 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program, etc. The memory 91 may also be used to temporarily store data that has been sent or will be sent.

[0161] In addition, in each embodiment of the present application, each functional unit may be integrated in a processing unit, may also exist physically alone for each unit, or two or more units may be integrated in one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0162] The embodiments of the present application also provide a terminal device, which includes at least one memory, at least one processor, and a computer program stored in the at least one memory and executable on the at least one processor. When the processor executes the computer program, the terminal device implements the steps in any of the above-mentioned method embodiments.

[0163] The embodiments of the present application also provide a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps in the above-mentioned various method embodiments can be implemented.

[0164] An embodiment of the present application provides a computer program product. When the computer program product runs on a terminal device, it enables the terminal device to execute the steps in the above-mentioned method embodiments when executed.

[0165] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-mentioned method embodiments of the present application, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps in the above-mentioned method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0166] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0167] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0168] The unit described as a separate component may or may not be physically separated, and the component shown as a unit may or may not be a physical unit, that is, it may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for monitoring filling of industrial gas cylinders, characterized in that: include: Obtain image information and filling time information of industrial gas cylinders; The industrial gas cylinder image information is identified and processed to obtain the bottle body texture information, bottle body color information and gas cylinder label information; the bottle body color information corresponds to the standard filling gas type information one by one; the gas cylinder label information carries the gas cylinder identification information, the gas type information to be filled and the gas cylinder scrapping time information; Generate multiple anchor frame pixel information according to the bottle body texture information, a preset anchor frame width, and a preset anchor frame height; Calculate the similarity between multiple anchor frame pixel information to obtain the anchor frame pixel matching degree; When the anchor frame pixel matching degree is less than or equal to a preset matching degree threshold, multiple anchor frame pixel information corresponding to the anchor frame pixel matching degree is used as bottle body texture pixel feature class information; Performing a convolution operation on the bottle body texture pixel feature information and a preset first feature representation function to generate a plurality of initial bottle body texture feature information maps; Extracting the extreme value elements of the plurality of initial bottle body texture feature information maps respectively to generate a first intermediate bottle body texture feature information map; Performing a convolution operation on the first intermediate bottle body texture feature information graph and a preset second feature representation function to generate a plurality of second intermediate bottle body texture feature information graphs; Extracting the extreme value elements of the plurality of second intermediate bottle body texture feature information maps respectively to generate a target bottle body texture feature information map; Normalizing the target bottle body texture feature information map to obtain a bottle body texture feature representation information map; Perform an inner product operation on the bottle body texture feature representation information graph and a preset first coefficient matrix to obtain a first bottle body texture feature variable matrix; Performing an inner product operation on the first bottle body texture feature variable matrix and a preset second coefficient matrix to obtain a second bottle body texture feature variable matrix; Obtaining bottle body texture feature spatial displacement variables according to the second bottle body texture feature variable matrix and a preset spatial displacement variable matrix; Generate a bottle body texture spatial mapping feature map according to the bottle body texture feature spatial displacement variable and a preset spatial mapping function; Calculating a matching probability value between the bottle body texture space mapping feature map and a preset standard bottle body texture space mapping feature map; When the matching probability value is not less than a preset matching probability threshold, generating cylinder surface defect confirmation information according to the bottle body texture pixel feature information; When the difference between the filling time information and the gas cylinder scrapping time information is greater than a preset time difference threshold, and when the gas type information to be filled is consistent with the standard filling gas type information, the identification information of the gas cylinder to be filled is obtained according to the gas cylinder surface defect confirmation information and the gas cylinder identification information; The industrial gas cylinders are monitored and processed according to the gas cylinder filling monitoring parameter information received in real time, the identification information of the gas cylinder to be filled and the preset gas cylinder filling parameter threshold information.

2. The industrial gas cylinder filling monitoring method according to claim 1, characterized in that: The step of identifying and processing the industrial gas cylinder image information to obtain bottle body texture information, bottle body color information and gas cylinder label information specifically includes: Randomly generate the center point of the initial gas cylinder surface information class and the center point of the initial label information class; According to preset pixel sampling interval information, pixel sampling processing is performed on the industrial gas cylinder image information to obtain a plurality of gas cylinder image pixel sample points; Respectively calculating the Euclidean distance values ​​between a plurality of the gas cylinder image pixel sample points and the center point of the initial gas cylinder surface information class and the center point of the initial label information class, and generating an initial gas cylinder surface information membership matrix and an initial label information membership matrix; Extracting the maximum value element of the initial gas cylinder surface information membership matrix, and taking the gas cylinder image pixel sample point corresponding to the maximum value element of the initial gas cylinder surface information membership matrix as the center point of the intermediate gas cylinder surface information class; Extracting the maximum value element of the initial label information membership matrix, and taking the gas cylinder image pixel sample point corresponding to the maximum value element of the initial label information membership matrix as the center point of the intermediate label information class; According to the gas cylinder image pixel sample points, the center point of the intermediate gas cylinder surface information class and the center point of the intermediate label information class, the bottle body texture information, the bottle body color information and the gas cylinder label information are obtained.

3. The industrial gas cylinder filling monitoring method according to claim 2, characterized in that: The step of obtaining the bottle body texture information, the bottle body color information and the gas cylinder label information according to the gas cylinder image pixel sample points, the intermediate gas cylinder surface information class center point and the intermediate label information class center point specifically includes: Determine whether the center point of the intermediate gas cylinder surface information class and the center point of the intermediate label information class are respectively the same as the center point of the initial gas cylinder surface information class and the center point of the initial label information class; If yes, the center point of the intermediate gas cylinder surface information class and the center point of the intermediate label information class are used as the center point of the target gas cylinder surface information class and the center point of the target label information class respectively; Calculating the Euclidean distances between a plurality of gas cylinder image pixel sample points and a center point of the target gas cylinder surface information class to obtain membership values ​​of a plurality of gas cylinder surface pixel sample points; When the membership value of the gas cylinder surface pixel sample point is less than or equal to a preset gas cylinder surface pixel sample point membership threshold, the gas cylinder image pixel sample point corresponding to the gas cylinder surface pixel sample point membership value is determined as the gas cylinder surface information pixel point; Generate the surface information of the gas cylinder according to the pixel points of the surface information of the gas cylinder; Identify and analyze the surface information of the gas cylinder to obtain the texture information and color information of the cylinder; Calculating the Euclidean distances between a plurality of the gas cylinder image pixel sample points and the target label information class center point to obtain a plurality of label information pixel sample point membership values; When the label information pixel sample point membership value is less than or equal to a preset label information pixel sample point membership threshold, the gas cylinder image pixel sample point corresponding to the label information pixel sample point membership value is determined as the gas cylinder label pixel point; Obtaining gas cylinder label information according to the gas cylinder label pixel points; If not, the center point of the intermediate gas cylinder surface information class and the center point of the intermediate label information class are used as the center point of the initial gas cylinder surface information class and the center point of the initial label information class, and the process returns to the step of respectively calculating the Euclidean distance values ​​between a plurality of gas cylinder image pixel sample points and the center point of the initial gas cylinder surface information class and the center point of the initial label information class to generate an initial gas cylinder surface information membership matrix and an initial label information membership matrix.

4. An industrial gas cylinder filling process monitoring device, characterized in that: include: An information acquisition module is used to obtain image information and filling time information of industrial gas cylinders; An image information recognition module is used to recognize and process the image information of the industrial gas cylinder to obtain bottle body texture information, bottle body color information and cylinder label information; the bottle body color information corresponds to the standard filling gas type information one by one; the cylinder label information carries the cylinder identification information, the type of gas to be filled and the cylinder scrapping time information; A bottle body texture information defect detection module is used to perform defect detection on the bottle body texture information and generate cylinder surface defect confirmation information; A gas cylinder identification information generation module for obtaining the identification information of the gas cylinder to be filled according to the gas cylinder surface defect confirmation information and the gas cylinder identification information when the difference between the filling time information and the gas cylinder scrapping time information is greater than a preset time difference threshold and when the gas type information to be filled is consistent with the standard filling gas type information; as well as An industrial gas cylinder monitoring and processing module, used to monitor and process the industrial gas cylinder according to the real-time received gas cylinder filling monitoring parameter information, the identification information of the gas cylinder to be filled and the preset gas cylinder filling parameter threshold information; The step of performing defect detection on the bottle body texture information to generate cylinder surface defect confirmation information specifically includes: Generate multiple anchor frame pixel information according to the bottle body texture information, a preset anchor frame width, and a preset anchor frame height; Calculate the similarity between multiple anchor frame pixel information to obtain the anchor frame pixel matching degree; When the anchor frame pixel matching degree is less than or equal to a preset matching degree threshold, multiple anchor frame pixel information corresponding to the anchor frame pixel matching degree is used as bottle body texture pixel feature class information; Performing a convolution operation on the bottle body texture pixel feature information and a preset first feature representation function to generate a plurality of initial bottle body texture feature information maps; Extracting the extreme value elements of the plurality of initial bottle body texture feature information maps respectively to generate a first intermediate bottle body texture feature information map; Performing a convolution operation on the first intermediate bottle body texture feature information graph and a preset second feature representation function to generate a plurality of second intermediate bottle body texture feature information graphs; Extracting the extreme value elements of the plurality of second intermediate bottle body texture feature information maps respectively to generate a target bottle body texture feature information map; Normalizing the target bottle body texture feature information map to obtain a bottle body texture feature representation information map; Perform an inner product operation on the bottle body texture feature representation information graph and a preset first coefficient matrix to obtain a first bottle body texture feature variable matrix; Performing an inner product operation on the first bottle body texture feature variable matrix and a preset second coefficient matrix to obtain a second bottle body texture feature variable matrix; Obtaining bottle body texture feature spatial displacement variables according to the second bottle body texture feature variable matrix and a preset spatial displacement variable matrix; Generate a bottle body texture spatial mapping feature map according to the bottle body texture feature spatial displacement variable and a preset spatial mapping function; Calculating a matching probability value between the bottle body texture space mapping feature map and a preset standard bottle body texture space mapping feature map; When the matching probability value is not less than a preset matching probability threshold, the cylinder surface defect confirmation information is generated according to the bottle body texture pixel feature information.

5. A terminal device, characterized in that: The terminal device includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the processor implements the steps of the method according to any one of claims 1 to 3 when executing the computer program.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images