Tube rolling length detection device

Abstract

The present application provides a device for detecting the length of a rolled tube. The device obtains first pulse information triggered by the first end of the rolled tube to be detected on the conveying platform through a laser sensor, and sends the first pulse signal to the server. It obtains first image information of the rolled tube to be detected on the conveying platform through a camera, and sends the first image information to the server. It obtains second pulse information triggered by the second end of the rolled tube to be detected on the conveying platform through the laser sensor, and sends the second pulse signal to the server, so that the server uses a preset length detection model and determines the length information of the rolled tube to be detected according to the first pulse signal, the first image information, the second pulse signal and the conveying speed of the conveying platform, thereby significantly improving the detection accuracy and efficiency, reducing the labor cost, and enhancing the quality control in the production process at the same time.

Description

Technical Field

[0001] The present application relates to data processing technologies, and in particular, to a pipe rolling length detection device. Background Art

[0002] In the modern steel pipe manufacturing industry, accurate measurement of the length of rolled pipes is crucial. With the application of a large number of automated devices, the length of rolled pipes is used in product physical weight control, dimensional accuracy control, and even auxiliary monitoring of the heating process during the technological process.

[0003] Traditional manual detection methods are not only time-consuming but also prone to errors. Especially on continuous production lines, manual detection cannot meet the requirements of high speed and high precision. Therefore, it is particularly necessary to develop a device that can detect the length of rolled pipes in real time, automatically, and accurately. Summary of the Invention

[0004] The present application provides a pipe rolling length detection device to solve the technical problem of low efficiency of manual detection in the prior art.

[0005] In a first aspect, the present application provides a pipe rolling length detection device, including: a conveying platform, a camera, a laser sensor, and a server, where the conveying platform, the camera, and the laser sensor are respectively communicatively connected to the server;

[0006] At a first moment, a first pulse signal triggered by a first end of a to-be-detected rolled pipe on the conveying platform is obtained through the laser sensor, and the first pulse signal is sent to the server;

[0007] At a second moment, first image information of the to-be-detected rolled pipe on the conveying platform is obtained through the camera, and the first image information is sent to the server;

[0008] At a third moment, a second pulse signal triggered by a second end of the to-be-detected rolled pipe on the conveying platform is obtained through the laser sensor, and the second pulse signal is sent to the server, where the second moment is between the first moment and the third moment;

[0009] The server uses a preset length detection model and determines the length information of the to-be-detected rolled pipe according to the first pulse signal, the first image information, the second pulse signal, and the conveying speed of the conveying platform.

[0010] In the above solution, by constructing a pipe length detection device including a conveying platform, a camera, a laser sensor and a server, and then, through this device, key data required for pipe length detection is collected and processed in real time, so as to detect the length of the pipe to be detected by using pulse information and image information, thereby ensuring the automation and continuity of pipe detection, and further improving the pipe detection efficiency and the smoothness of the production process.

[0011] Optionally, the server uses a preset length detection model and determines the length information of the pipe to be detected according to the first pulse signal, the first image information, the second pulse signal, and the conveying speed of the conveying platform, including:

[0012] The server uses Formula 1 and determines the transmission characteristic distance s of the pipe to be detected in the transmission direction of the conveying platform according to the time difference Δt between the first pulse signal and the second pulse signal and the conveying speed v c to determine the transmission characteristic distance s of the pipe to be detected in the transmission direction of the conveying platform c , and Formula 1 is:

[0013] s c = v c ·Δt

[0014] The server uses a contour extraction model and determines the first boundary contour of the pipe to be detected according to the first image information, so as to determine the first boundary feature vector according to the first boundary contour The first boundary contour is a contour line along the axial direction of the pipe to be detected;

[0015] The server uses Formula 2 and determines the length information L of the pipe to be detected according to the transmission characteristic distance s c , the first boundary feature vector and a preset feature vector to determine the length information L of the pipe to be detected. The preset feature vector is a unit vector in the transmission direction of the conveying platform, and Formula 2 is:

[0016]

[0017] where is the modulus of the first boundary feature vector , is the modulus of the preset feature vector .

[0018] In the above solution, the server uses specific mathematical models and algorithms, including time difference, transmission speed, and image contour analysis, to calculate the length information of the rolled pipe. By combining the time pulse signal of the laser sensor with the image information of the camera, it can accurately measure the actual displacement of the rolled pipe on the conveying platform, and then accurately calculate its length, improving the detection accuracy and data reliability.

[0019] Optionally, after determining the first boundary contour of the rolled pipe to be detected according to the first image information, it further includes:

[0020] The server uses Formula 3 and updates the length information of the rolled pipe to be detected based on the conveying characteristic distance s c , the first boundary feature vector and the preset feature vector to generate the first updated length information L ′ , and Formula 3 is:

[0021]

[0022] where D is the preset diameter of the rolled pipe to be detected.

[0023] In the above solution, considering the placement method of the rolled pipe to be detected on the conveying platform, for example, the axial direction corresponding to the placement method has an angle with the conveying direction of the conveying platform, that is, the rolled pipe to be detected is placed obliquely on the conveying platform. The server can use the above Formula 3 to update the length information, thereby correcting the length information. This method can correct the measurement error caused by the oblique placement of the rolled pipe and ensure the accuracy of length detection.

[0024] Optionally, a weight sensor is further provided on the conveying platform, and the weight sensor is communicatively connected to the server; after obtaining the first pulse information triggered by the first end of the rolled pipe to be detected on the conveying platform through the laser sensor, it further includes:

[0025] At the second moment, obtain the first weight information of the rolled pipe to be detected through the weight sensor and send the first weight information to the server;

[0026] Correspondingly, after updating the first updated length information L of the rolled pipe to be detected based on the conveying characteristic distance s c , the first boundary feature vector and the preset feature vector , it further includes: ′ After that, it includes:

[0027] If the server determines the length information L of the rolled pipe to be detected ′Within a preset length range, and if it is determined that the first weight in the first weight information exceeds the preset weight range, it is determined that the to-be-detected rolled pipe is in a cutting anomaly state, where the cutting anomaly state includes that there is an anomaly in the end cutting. The minimum value of the preset weight range is the first weight threshold, and the maximum value is the second weight threshold. The ratio between the first weight threshold and the calibrated weight of the to-be-detected rolled pipe is between 0.95 and 0.99, and the ratio between the second weight threshold and the calibrated weight of the to-be-detected rolled pipe is between 1.01 and 1.05.

[0028] In the above solution, a weight sensor is added to obtain the weight information of the rolled pipe and combine it with the length information to determine whether there is a cutting anomaly. Here, the cutting anomaly usually refers to the oblique cutting at the end of the rolled pipe. At this time, the overall length of the rolled pipe is within the preset length range of the normal calibration. However, due to the oblique cutting, the overall weight is on the low side. Therefore, by monitoring the matching degree of the weight and the length, this function can timely detect cutting errors, prevent unqualified products from flowing into the subsequent processes, and improve the quality of the finished products and the rigor of production management.

[0029] Optionally, after updating the first updated length information L of the to-be-detected rolled pipe according to the transmission characteristic distance s c and the first boundary feature vector and the preset feature vector it further includes: ′ After that, it further includes:

[0030] If the server determines that the length information L of the to-be-detected rolled pipe ′ is within the preset length range, and it is determined that the first weight in the first weight information exceeds the third weight threshold, it is determined that the to-be-detected rolled pipe is in a quantity anomaly state, where the ratio between the third weight threshold and the calibrated weight of the to-be-detected rolled pipe is between 1.5 and 1.9.

[0031] In the above solution, when it is detected that the length exceeds the normal range and the weight is abnormal, it is determined as a quantity anomaly. This detection mechanism helps to identify possible batch production failures, such as the situation where multiple rolled pipes are stuck together and cut, ensuring the stable operation of the production line and the consistency of the products.

[0032] Optionally, after obtaining the first image information of the to-be-detected rolled pipe on the conveying platform through the camera, it further includes:

[0033] The server uses the contour extraction model and determines the second boundary contour of the to-be-detected rolled pipe according to the first image information, so as to determine the second boundary feature vector according to the second boundary contour The second boundary contour is the contour line along the radial direction of the to-be-detected rolled pipe;

[0034] The server uses Formula 4 and, based on the first boundary feature vector and the second boundary feature vector to determine the end angle eigenvalue k of the pipe to be detected. Formula 4 is as follows:

[0035]

[0036] wherein, is the modulus of the second boundary feature vector ;

[0037] If the server determines that the end angle eigenvalue k is less than the preset angle feature threshold, it determines that the abnormal state of the pipe to be detected is that there is an abnormality in the end cutting angle.

[0038] In the above solution, by analyzing the radial contour line, calculating the end angle eigenvalue, and judging whether there is an abnormal angle cutting, the cutting accuracy of the pipe end is ensured, subsequent processing problems caused by angle deviation are prevented, and the mechanical properties and appearance quality of the product are improved.

[0039] Optionally, the pipe length detection device further includes: a display, and the server is communicatively connected to the display;

[0040] After determining that the abnormal state of the pipe to be detected is that there is an abnormality in the end cutting, it further includes:

[0041] The server generates a first abnormal prompt image based on the first image information and the abnormal state, and sends the first abnormal prompt image to the display. The first abnormal image includes the pipe to be detected, an abnormal identification frame displayed on the end of the pipe to be detected, and a prompt message for prompting the tool maintenance of the cutting device;

[0042] The display displays the first image information.

[0043] In the above solution, when an abnormality is detected, an abnormal prompt image is generated, which facilitates the operator to quickly locate the problem. Moreover, the instant feedback of the abnormal prompt image improves the operation response speed, simplifies the problem troubleshooting process, reduces the production downtime, and promotes the timeliness of equipment maintenance.

[0044] In a second aspect, the present application provides a method for detecting the length of a pipe, characterized in that it is applied to a pipe length detection device. The pipe length detection device includes: a conveying platform, a camera, a laser sensor, and a server. The conveying platform, the camera, and the laser sensor are respectively communicatively connected to the server; the method includes:

[0045] At the first moment, the first pulse information triggered by the first end of the pipe to be detected on the conveying platform is obtained through the laser sensor, and the first pulse signal is sent to the server;

[0046] At the second moment, the first image information of the pipe to be detected on the conveying platform is obtained through the camera, and the first image information is sent to the server;

[0047] At the third moment, the second pulse information triggered by the second end of the pipe to be detected on the conveying platform is obtained through the laser sensor, and the second pulse signal is sent to the server, where the second moment is between the first moment and the third moment;

[0048] The server uses a preset length detection model and determines the length information of the pipe to be detected according to the first pulse signal, the first image information, the second pulse signal, and the conveying speed of the conveying platform.

[0049] Optionally, the server uses a preset length detection model and determines the length information of the pipe to be detected according to the first pulse signal, the first image information, the second pulse signal, and the conveying speed of the conveying platform, including:

[0050] The server uses formula 1 and determines the conveying characteristic distance s of the pipe to be detected in the conveying direction of the conveying platform according to the time difference Δt between the first pulse signal and the second pulse signal and the conveying speed v c where the formula 1 is: c s

[0051] s c =v c ·Δt

[0052] The server uses a contour extraction model and determines the first boundary contour of the pipe to be detected according to the first image information, so as to determine the first boundary feature vector according to the first boundary contour The first boundary contour is a contour line along the axial direction of the pipe to be detected.

[0053] The server uses formula 2 and determines the length information L of the pipe to be detected according to the conveying characteristic distance s c , the first boundary feature vector and a preset feature vector where the preset feature vector is a unit vector in the conveying direction of the conveying platform, and the formula 2 is:

[0054]

[0055] Among them, is the modulus length of the first boundary feature vector . is the modulus length of the preset feature vector .

[0056] Optionally, after determining the first boundary contour of the to-be-detected rolling pipe according to the first image information, it further includes:

[0057] The server uses formula 3 and updates the length information of the to-be-detected rolling pipe according to the transmission feature distance s c , the first boundary feature vector and the preset feature vector to generate the first updated length information L ′ , and the formula 3 is:

[0058]

[0059] Among them, D is the preset diameter of the to-be-detected rolling pipe.

[0060] Optionally, a weight sensor is further arranged on the transfer platform, and the weight sensor is communicatively connected to the server; after obtaining the first pulse information triggered by the first end of the to-be-detected rolling pipe on the transfer platform through the laser sensor, it further includes:

[0061] At the second moment, obtain the first weight information of the to-be-detected rolling pipe through the weight sensor and send the first weight information to the server;

[0062] Correspondingly, after updating the first updated length information L c of the to-be-detected rolling pipe according to the transmission feature distance s , the first boundary feature vector and the preset feature vector ′ , it further includes:

[0063] If the server determines that the length information L ′ of the to-be-detected rolling pipe is within the preset length range and determines that the first weight in the first weight information exceeds the preset weight range, it is determined that the to-be-detected rolling pipe is in a cutting abnormal state, and the cutting abnormal state includes that there is an abnormality in the end cutting. The minimum value of the preset weight range is the first weight threshold, the maximum value is the second weight threshold, and the ratio between the first weight threshold and the calibrated weight of the to-be-detected rolling pipe is between 0.95 and 0.99, and the ratio between the second weight threshold and the calibrated weight of the to-be-detected rolling pipe is between 1.01 and 1.05.

[0064] Optionally, based on the transmission feature distance s c , the first boundary feature vector and a preset feature vector update the first updated length information L of the pipe to be detected ′ After that, it further includes:

[0065] If the server determines that the length information L of the pipe to be detected ′ is within a preset length range, and determines that the first weight in the first weight information exceeds a third weight threshold, then it is determined that the pipe to be detected is in an abnormal quantity state, and the ratio between the third weight threshold and the calibrated weight of the pipe to be detected is between 1.5 and 1.9.

[0066] Optionally, after obtaining the first image information of the pipe to be detected on the transmission platform through the camera, it further includes:

[0067] The server uses the contour extraction model and determines the second boundary contour of the pipe to be detected according to the first image information, so as to determine the second boundary feature vector according to the second boundary contour The second boundary contour is a contour line along the radial direction of the pipe to be detected;

[0068] The server uses formula 4 and based on the first boundary feature vector and the second boundary feature vector determines the end angle eigenvalue k of the pipe to be detected, and formula 4 is:

[0069]

[0070] wherein, is the modulus of the second boundary feature vector ;

[0071] If the server determines that the end angle eigenvalue k is less than a preset angle feature threshold, then it is determined that the abnormal state of the pipe to be detected is that the end cutting angle is abnormal.

[0072] Optionally, the pipe length detection device further includes: a display, and the server is communicatively connected to the display;

[0073] After determining that the abnormal state of the pipe to be detected is that the end cutting is abnormal, it further includes:

[0074] The server generates a first abnormal prompt image based on the first image information and the abnormal state, and sends the first abnormal prompt image to the display. The first abnormal image includes the to-be-detected rolling pipe, an abnormal identification frame displayed on the end of the to-be-detected rolling pipe, and prompt information for prompting the tool maintenance of the cutting device;

[0075] The display displays the first image information.

[0076] In a third aspect, the present application provides an electronic device, including:

[0077] A processor; and,

[0078] A memory for storing executable instructions of the processor;

[0079] Wherein, the processor is configured to execute any possible method described in the first aspect by executing the executable instructions.

[0080] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement any possible method described in the first aspect.

[0081] The rolling pipe length detection device provided by the present application obtains first pulse information triggered by the first end of the to-be-detected rolling pipe on the conveying platform through a laser sensor, and sends the first pulse signal to the server. It obtains first image information of the to-be-detected rolling pipe on the conveying platform through a camera, and sends the first image information to the server. It obtains second pulse information triggered by the second end of the to-be-detected rolling pipe on the conveying platform through a laser sensor, and sends the second pulse signal to the server, so that the server uses a preset length detection model and determines the length information of the to-be-detected rolling pipe according to the first pulse signal, the first image information, the second pulse signal, and the conveying speed of the conveying platform, thereby significantly improving the detection accuracy and efficiency, reducing the labor cost, and at the same time enhancing the quality control in the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0083] Figure 1 is a schematic structural diagram of a rolling pipe length detection device shown according to an exemplary embodiment of the present application;

[0084] Figure 2 is a schematic flowchart of a rolling pipe length detection method shown according to an exemplary embodiment of the present application;

[0085] Figure 3 This is a schematic structural diagram of an electronic device shown according to an exemplary embodiment of the present application.

[0086] Through the above-mentioned drawings, specific embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter. These drawings and textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. Detailed implementation manners

[0087] Here, exemplary embodiments will be described in detail, and examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0088] To solve the above problems, the embodiments provided by the present application propose an integrated detection system including a conveying platform, a camera, a laser sensor, and a server. Each component is interconnected through a network, realizing the automation and continuity of the length detection of rolled tubes and significantly improving the detection efficiency. Among them, for the provided detection device, the specific design concept is as follows:

[0089] Precise length measurement: Using the pulse signal triggered by the laser sensor and the image information captured by the camera, combined with a preset mathematical model and algorithm, accurately measure the actual displacement of the rolled tube, and then calculate its length. By analyzing the time difference between pulse signals and the moving speed of the conveying platform, combined with image contour analysis, the high precision of the detection is ensured.

[0090] Length correction mechanism: Considering that the rolled tube may be placed obliquely on the conveying platform, the embodiments of the present application provide a method for correcting the length measurement error. The server updates the length information according to a specific formula to compensate for the measurement deviation caused by the oblique placement and ensure the accuracy of the length detection result.

[0091] Weight monitoring and anomaly detection: A weight sensor is added to realize the real-time monitoring of the weight of the rolled tube. By comparing the weight with the length information, abnormal cutting and abnormal quantity conditions can be effectively identified, such as insufficient weight caused by oblique cutting or excessive weight due to adhesion of multiple rolled tubes, ensuring product quality and production stability.

[0092] End angle analysis: By analyzing the contour of the end of the rolled tube, calculate the end angle characteristic value to judge whether there is an abnormal angle cutting, ensuring the cutting precision, preventing subsequent processing problems, and improving the mechanical performance and appearance quality of the product.

[0093] Instant feedback mechanism: Configure a display. When an abnormality is detected, the server generates an abnormality prompt image and displays it on the display, facilitating the operator to quickly locate the problem, simplifying the troubleshooting process, reducing production downtime, and promoting the timeliness of equipment maintenance.

[0094] Intelligent data analysis: The entire detection process is uniformly managed by the server. It intelligently analyzes pulse signals, image information, and weight data, and automatically determines whether the length, weight, and end angle of the rolled pipe meet the standards, greatly improving the intelligence level of detection.

[0095] It can be seen that by constructing an integrated detection system, using the data of laser sensors, cameras, and weight sensors, and combining advanced mathematical models and algorithms, the accurate detection of the length, weight, and end angle of the rolled pipe is realized, effectively improving the production efficiency and product quality control ability.

[0096] Figure 1 It is a schematic structural diagram of a rolled pipe length detection device shown according to an exemplary embodiment of the present application. As Figure 1 described, the rolled pipe length detection device 100 provided in this embodiment includes:

[0097] A conveying platform 110, a camera 120, a laser sensor 130, and a server 140. The conveying platform 110, the camera 120, and the laser sensor 130 are respectively communicatively connected to the server 140;

[0098] At a first moment, the first pulse information triggered by the first end of the rolled pipe to be detected on the conveying platform 110 is obtained through the laser sensor 130, and the first pulse signal is sent to the server 140;

[0099] At a second moment, the first image information of the rolled pipe to be detected on the conveying platform 110 is obtained through the camera 120, and the first image information is sent to the server 140;

[0100] At a third moment, the second pulse information triggered by the second end of the rolled pipe to be detected on the conveying platform 110 is obtained through the laser sensor 130, and the second pulse signal is sent to the server 140. The second moment is between the first moment and the third moment;

[0101] The server 140 uses a preset length detection model and determines the length information of the rolled pipe to be detected according to the first pulse signal, the first image information, the second pulse signal, and the conveying speed of the conveying platform 110.

[0102] In this embodiment, the first pulse information triggered by the first end of the pipe to be detected on the conveying platform is obtained through a laser sensor, and the first pulse signal is sent to the server. The first image information of the pipe to be detected on the conveying platform is obtained through a camera, and the first image information is sent to the server. The second pulse information triggered by the second end of the pipe to be detected on the conveying platform is obtained through the laser sensor, and the second pulse signal is sent to the server, so that the server uses a preset length detection model and determines the length information of the pipe to be detected according to the first pulse signal, the first image information, the second pulse signal and the conveying speed of the conveying platform, thereby significantly improving the detection accuracy and efficiency, reducing the labor cost, and enhancing the quality control in the production process at the same time.

[0103] Figure 2 It is a schematic flowchart of a pipe length detection method shown by this application according to an exemplary embodiment. As Figure 2 shown, the method provided in this embodiment includes:

[0104] S201. At a first moment, the first pulse information triggered by the first end of the pipe to be detected on the conveying platform is obtained through a laser sensor, and the first pulse signal is sent to the server.

[0105] First, ensure that the pipe length detection device has been started and is ready. The device should include a conveying platform, a camera, a laser sensor and a server, and all components need to establish a communication connection with the server.

[0106] When the pipe to be detected is placed on the conveying platform and moves under the laser sensor, the laser sensor will detect the first end of the pipe and trigger the first pulse information. This pulse information is then transmitted to the server for recording, which marks the start of the detection process.

[0107] S202. At a second moment, the first image information of the pipe to be detected on the conveying platform is obtained through a camera, and the first image information is sent to the server.

[0108] Immediately afterwards, the camera captures the image of the pipe to be detected on the conveying platform, that is, the first image information. This step occurs after the first pulse signal is collected. The first image is then sent to the server for analysis.

[0109] S203. At a third moment, the second pulse information triggered by the second end of the pipe to be detected on the conveying platform is obtained through a laser sensor, and the second pulse signal is sent to the server.

[0110] As the pipe continues to move, when its second end passes through the laser sensor, the second pulse signal is triggered, indicating that the other end of the pipe has reached the detection position. This signal is also sent to the server. At this time, the time interval between the first pulse signal and the second pulse signal has been determined.

[0111] S204. The server uses a preset length detection model and determines the length information of the pipe to be detected based on the first pulse signal, the first image information, the second pulse signal, and the conveying speed of the conveying platform.

[0112] After receiving all the signals, the server will process these data using the preset length detection model. First, based on the time difference between the first pulse signal and the second pulse signal and the constant speed of the conveying platform, the characteristic distance that the pipe is conveyed on the conveying platform is calculated. Second, using the first image information, the axial contour of the pipe is determined through a contour extraction model, and then the first boundary feature vector is obtained. Finally, combining the conveying characteristic distance, the first boundary feature vector, and the preset unit vector, the actual length information of the pipe is calculated using a specific formula.

[0113] In a possible implementation manner, for the above-mentioned preset length detection model, specifically, the server uses Formula 1 and determines the conveying characteristic distance s of the pipe to be detected in the conveying direction of the conveying platform according to the time difference Δt between the first pulse signal and the second pulse signal and the conveying speed v c to determine the conveying characteristic distance s of the pipe to be detected in the conveying direction of the conveying platform c , and Formula 1 is:

[0114] s c = v c ·Δt

[0115] The server uses a contour extraction model and determines the first boundary contour of the pipe to be detected according to the first image information, so as to determine the first boundary feature vector according to the first boundary contour The first boundary contour is the contour line along the axial direction of the pipe to be detected. It is worth noting that the above-mentioned contour extraction model can be based on an edge detection algorithm, and can use technologies such as the Sobel operator and Canny edge detection to identify the regions with significant intensity changes in the image, so as to determine the boundary contour of the pipe. And in this embodiment, for the recognition of the first boundary contour of the pipe to be detected, it is not required to recognize the complete outer contour of the pipe to be detected, but only to recognize at least two feature points on the contour along the axial direction, so that the first boundary feature vector can be determined according to the feature points That's it. In addition, since the first boundary contour is a straight line, it can also be to identify two end points on one side of the pipe to be detected, and then determine the first boundary feature vector according to the two end points

[0116] The server uses Formula 2 and determines the length information L of the pipe to be detected according to the conveying characteristic distance s c , the first boundary feature vector and the preset feature vector to determine the length information L of the pipe to be detected, and the preset feature vector is the unit vector in the conveying direction of the conveying platform, and Formula 2 is as follows:

[0117]

[0118] Among them, is the first boundary feature vector of the modulus length, is the preset feature vector of the modulus length.

[0119] It should be noted that if only a laser sensor is used for length detection, for the case where the pipe to be detected is placed obliquely on the conveying platform, the length of the pipe cannot be accurately measured. If only a camera is used for image processing and then length calculation, the calculation amount is relatively large, and the contour accuracy of the acquired image is required to be relatively high. In addition, the method of length measurement through image processing has relatively high requirements for the algorithm. In the above steps, by combining a laser sensor and a camera, length detection with relatively high accuracy can be achieved with a relatively low amount of computation, which is suitable for high-speed detection scenarios on the production line.

[0120] Furthermore, after determining the first boundary contour of the pipe to be detected according to the first image information, the server can also use Formula 3 and update the length information of the pipe to be detected based on the conveying feature distance s c , the first boundary feature vector and the preset feature vector to generate the first updated length information L ′ , the formula

[0121] 3 is as follows:

[0122]

[0123] Among them, D is the preset diameter of the pipe to be detected.

[0124] In addition, a weight sensor is also set on the conveying platform, and the weight sensor is communicatively connected to the server. At the second moment, the first weight information of the pipe to be detected can also be obtained through the weight sensor and sent to the server.

[0125] After updating the first updated length information L c of the pipe to be detected based on the conveying feature distance s , the first boundary feature vector and the preset feature vector ′ , if the server determines the length information L ′If it is within the preset length range and it is determined that the first weight in the first weight information exceeds the preset weight range, then it is determined that the steel pipe to be detected is in an abnormal cutting state. The abnormal cutting state includes abnormal end cutting. The minimum value of the preset weight range is the first weight threshold, and the maximum value is the second weight threshold. The ratio between the first weight threshold and the calibrated weight of the steel pipe to be detected is between 0.95 and 0.99, and the ratio between the second weight threshold and the calibrated weight of the steel pipe to be detected is between 1.01 and 1.05.

[0126] On the conveying platform, the weight sensor measures the weight of the steel pipe at the second moment to generate the first weight information, which is sent to the server. The server compares the length information and the weight information of the steel pipe. If the length of the steel pipe is within the preset range but the weight exceeds the preset weight range, that is, the weight is less than 95% of the calibrated weight or higher than 105%, it is determined as abnormal cutting, and there may be a problem with inaccurate end cutting.

[0127] Further, after obtaining the first image information of the steel pipe to be detected on the conveying platform through the camera, it further includes:

[0128] The server uses the contour extraction model and determines the second boundary contour of the steel pipe to be detected according to the first image information, so as to determine the second boundary feature vector according to the second boundary contour. The second boundary contour is the contour line along the radial direction of the steel pipe to be detected. The server uses formula 4 and according to the first boundary feature vector. And the second boundary feature vector. Determine the end angle feature value k of the steel pipe to be detected. Formula 4 is:

[0129]

[0130] Wherein, is the modulus of the second boundary feature vector. ;

[0131] If the server determines that the end angle feature value k is less than the preset angle feature threshold, it is determined that the abnormal state of the steel pipe to be detected is that there is an abnormality in the end cutting angle.

[0132] In addition, if the server determines that the length information L of the steel pipe to be detected ′ is within the preset length range and it is determined that the first weight in the first weight information exceeds the third weight threshold, it is determined that the steel pipe to be detected is in an abnormal quantity state. The ratio between the third weight threshold and the calibrated weight of the steel pipe to be detected is between 1.5 and 1.9.

[0133] If the length of the rolled tube is still within the preset range, but the weight far exceeds the normal range, that is, 1.5 to 1.9 times the calibrated weight, the system will identify it as an abnormal quantity, which may mean that multiple rolled tubes are stuck together and placed on the conveyor platform.

[0134] Once the server identifies the abnormal end cutting, it will generate an abnormal prompt image according to the first image information. The position and type of the abnormal rolled tube will be marked on the image, and it will be sent to the display for display at the same time, so as to facilitate the operator to discover and handle the problem in time.

[0135] Furthermore, the server generates a first abnormal prompt image according to the first image information and the abnormal state, and sends the first abnormal prompt image to the display. The first abnormal image includes the rolled tube to be detected, an abnormal identification frame displayed on the end of the rolled tube to be detected, and prompt information for prompting the tool maintenance of the cutting device. Thus, the first image information is displayed on the display.

[0136] Figure 3 It is a schematic structural diagram of an electronic device shown according to an exemplary embodiment of the present application. As Figure 3 shown, an electronic device 300 provided in this embodiment includes: a processor 301 and a memory 302; wherein:

[0137] The memory 302 is used to store computer programs, and this memory can also be flash (flash memory).

[0138] The processor 301 is used to execute the execution instructions stored in the memory to implement each step in the above method. For details, please refer to the relevant descriptions in the foregoing method embodiments.

[0139] Optionally, the memory 302 can be either independent or integrated with the processor 301.

[0140] When the memory 302 is a device independent of the processor 301, the electronic device 300 may further include:

[0141] A bus 303 for connecting the memory 302 and the processor 301.

[0142] This embodiment also provides a readable storage medium. The readable storage medium stores a computer program. When at least one processor of the electronic device executes this computer program, the electronic device executes the methods provided by the above various embodiments.

[0143] This embodiment also provides a program product, which includes a computer program stored in a readable storage medium. At least one processor of the electronic device can read the computer program from the readable storage medium, and the execution of the computer program by the at least one processor enables the electronic device to implement the methods provided by the above various embodiments.

[0144] Those skilled in the art will readily conceive of other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include common general knowledge or conventional technical means in the technical field not disclosed in the present application. The specification and embodiments are only to be considered as exemplary, and the true scope and spirit of the present application are pointed out by the claims.

[0145] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. A tube length detection device, characterized in that: include: A transmission platform, a camera, a laser sensor and a server, wherein the transmission platform, the camera and the laser sensor are respectively connected to the server for communication; At a first moment, a first pulse signal triggered by a first end of the rolled tube to be inspected on the conveying platform is acquired by the laser sensor, and the first pulse signal is sent to the server; At the second moment, the first image information of the rolled tube to be inspected on the conveying platform is obtained by the camera, and the first image information is sent to the server; At a third moment, a second pulse signal triggered by the second end of the rolled tube to be inspected on the conveying platform is acquired by the laser sensor, and the second pulse signal is sent to the server, wherein the second moment is between the first moment and the third moment; The server uses a preset length detection model and determines the length information of the to-be-detected rolled tube according to the first pulse signal, the first image information, the second pulse signal and the transmission speed of the transmission platform; The server uses a preset length detection model and determines the length information of the to-be-detected rolled tube according to the first pulse signal, the first image information, the second pulse signal and the transmission speed of the transmission platform, including: The server uses Formula 1, and the server calculates the time difference Δt between the first pulse signal and the second pulse signal and the transmission speed v c Determine the transmission characteristic distance s of the rolled tube to be inspected in the transmission direction of the transmission platform c , the formula 1 is: s c =v c ·Δt The server uses a contour extraction model and determines a first boundary contour of the to-be-detected rolled tube according to the first image information, so as to determine a first boundary feature vector according to the first boundary contour. The first boundary contour is a contour line along the axial direction of the rolling tube to be inspected; The server uses formula 3 according to the transmission characteristic distance s c , the first boundary feature vector And the preset feature vector Update the length information of the rolled tube to be detected, the preset feature vector is a unit vector in the transmission direction of the transmission platform to generate the first updated length information L′, and the formula 3 is: in, is the first boundary feature vector The module length, The preset feature vector The mold length is , and D is the preset diameter of the rolled tube to be tested.

2. The tube length detection device according to claim 1, characterized in that: A weight sensor is also arranged on the conveying platform, and the weight sensor is in communication with the server; after the first pulse signal triggered by the first end of the rolled tube to be inspected on the conveying platform is obtained by the laser sensor, the method further includes: At the second moment, first weight information of the rolled tube to be inspected is obtained through the weight sensor, and the first weight information is sent to the server; Correspondingly, after updating the length information of the to-be-detected rolled tube according to the transmission characteristic distance, the first boundary characteristic vector and the preset characteristic vector to generate the first updated length information, the method further includes: If the server determines that the length information of the rolled pipe to be detected is within a preset length range, and determines that the first weight in the first weight information exceeds the preset weight range, then the rolled pipe to be detected is determined to be in a cutting abnormality state, and the cutting abnormality state includes an abnormality in end cutting. The minimum value of the preset weight range is a first weight threshold, and the maximum value is a second weight threshold. The ratio of the first weight threshold to the calibrated weight of the rolled pipe to be detected is between 0.95 and 0.99, and the ratio of the second weight threshold to the calibrated weight of the rolled pipe to be detected is between 1.01 and 1.

05.

3. The tube length detection device according to claim 2, characterized in that: After the length information of the to-be-detected rolled tube is updated according to the transmission characteristic distance, the first boundary characteristic vector and the preset characteristic vector to generate the first updated length information, the method further includes: If the server determines that the length information of the rolled pipe to be detected is within a preset length range, and determines that the first weight in the first weight information exceeds a third weight threshold, it is determined that the rolled pipe to be detected is in an abnormal quantity state, and the ratio between the third weight threshold and the calibrated weight of the rolled pipe to be detected is between 1.5 and 1.

9.

4. The tube length detection device according to any one of claims 1 to 3, characterized in that: After the first image information of the rolled tube to be inspected on the conveying platform is obtained by the camera, the method further includes: The server uses the contour extraction model and determines a second boundary contour of the to-be-detected rolled tube according to the first image information, so as to determine a second boundary feature vector according to the second boundary contour. The second boundary contour is a contour line along the radial direction of the rolling tube to be inspected; The server determines the end angle feature value of the to-be-detected rolled tube according to the first boundary feature vector and the second boundary feature vector; If the server determines that the end angle characteristic value is less than a preset angle characteristic threshold, it determines that the abnormal state of the rolled pipe to be detected is that there is an abnormality in the end cutting angle.

5. The tube length detection device according to claim 4, characterized in that: Also includes: a display, the server being communicatively connected to the display; After determining that the abnormal state of the rolled tube to be inspected is abnormality in end cutting, the method further includes: The server generates a first abnormality prompt image according to the first image information and the abnormal state, and sends the first abnormality prompt image to the display, wherein the first abnormality prompt image includes the rolled tube to be inspected, an abnormality identification frame displayed on the end of the rolled tube to be inspected, and prompt information for prompting the cutting equipment tool to be repaired; The display displays the first image information.

6. A method for detecting the length of a rolled tube, characterized in that: Applied to a tube length detection device, the tube length detection device comprises: a transmission platform, a camera, a laser sensor and a server, the transmission platform, the camera and the laser sensor are respectively connected to the server for communication; the method comprises: At a first moment, a first pulse signal triggered by a first end of the rolled tube to be inspected on the conveying platform is acquired by the laser sensor, and the first pulse signal is sent to the server; At the second moment, the first image information of the rolled tube to be inspected on the conveying platform is obtained by the camera, and the first image information is sent to the server; At a third moment, a second pulse signal triggered by the second end of the rolled tube to be inspected on the conveying platform is acquired by the laser sensor, and the second pulse signal is sent to the server, wherein the second moment is between the first moment and the third moment; The server uses a preset length detection model and determines the length information of the to-be-detected rolled tube according to the first pulse signal, the first image information, the second pulse signal and the transmission speed of the transmission platform; The server uses a preset length detection model and determines the length information of the to-be-detected rolled tube according to the first pulse signal, the first image information, the second pulse signal and the transmission speed of the transmission platform, including: The server uses Formula 1, and the server calculates the time difference Δt between the first pulse signal and the second pulse signal and the transmission speed v c Determine the transmission characteristic distance s of the rolled tube to be inspected in the transmission direction of the transmission platform c , the formula 1 is: s c =v c ·Δt The server uses a contour extraction model and determines a first boundary contour of the to-be-detected rolled tube according to the first image information, so as to determine a first boundary feature vector according to the first boundary contour. The first boundary contour is a contour line along the axial direction of the rolling tube to be inspected; After determining the first boundary contour of the to-be-detected rolled tube according to the first image information, the method further includes: The server uses formula 3 according to the transmission characteristic distance s c , the first boundary feature vector And the preset feature vector Update the length information of the rolled tube to be detected, the preset feature vector is a unit vector in the transmission direction of the transmission platform to generate the first updated length information L′, and the formula 3 is: in, is the first boundary feature vector The module length, The preset feature vector The mold length is , and D is the preset diameter of the rolled tube to be tested.

Images