A torque testing device and method for spiral wound pipes

Abstract

This invention discloses a torque testing device and method for spiral wound tubing, belonging to the field of profile performance testing technology. The device includes a fixture, a torque wrench, a cage, a die head, a torque tester, a vision sensor, and a control system. This invention achieves uniform torque transmission through the precise installation of the fixture. Combined with the coordinated detection of the torque wrench, torque tester, and vision sensor, it effectively solves the problems of large installation deviations and high measurement errors in traditional testing, significantly improving testing accuracy and reliability. Furthermore, by integrating the vision sensor and control system, this invention can collect and analyze the displacement data of the spiral tube in real time, and perform synchronous data analysis through the control system, achieving efficient and accurate detection of the profile's torque performance and automatically optimizing process parameters to achieve the best production spiral tube quality.

Description

Technical Field

[0001] This invention belongs to the field of profile performance testing technology, and is mainly applied to the quality control of profile production. Specifically, it relates to the field of torque testing in material mechanical property testing technology, and more specifically, to a torque testing device and method for wound-formed pipes. This device and method integrate mechanical fixation, precise measurement, and intelligent analysis functions to achieve standardized testing of the torque performance of profiles, providing reliable technical support for quality control and process optimization of profile products. Background Technology

[0002] In pipeline laying projects, spiral wound pipe technology is used for convenient transportation. Profiles are fabricated on-site using a spiral wound pipe-making machine (such as the spiral wound equipment disclosed in CN212004760U). During on-site construction, torque performance testing is a crucial step in ensuring product quality for the spirally wound pipes. Traditional torque testing methods rely mainly on manual operation of simple torque wrenches, which has several technical shortcomings. First, due to the lack of standardized fixing devices, the profiles are prone to displacement or slippage during testing, leading to distorted measurement data. Second, traditional methods cannot guarantee the stability of the torque application direction during each test, resulting in poor repeatability of measurement results. More importantly, this type of testing lacks a real-time data acquisition system; the testing process relies entirely on the operator's subjective judgment, making it difficult to form objective and traceable quality records. This crude testing method can no longer meet the high standards of product quality control required by modern manufacturing. Moreover, this type of profile performance testing is a destructive test, posing certain safety risks; improper manual operation may cause accidental injury.

[0003] Existing torque testing devices generally suffer from structural design deficiencies. The fixing devices often employ simple clamping methods, failing to ensure precise concentric positioning with the profile, leading to uneven torque transmission and systematic deviations in measurement data. During testing, the profile's fixation stability is insufficient, easily resulting in micro-displacement under torque loading, severely impacting measurement accuracy. Furthermore, conventional testing devices lack effective limiting mechanisms, failing to guarantee the standard test length of the profile and control the torque wrench's force trajectory. These structural defects cause significant fluctuations in measurement results, making data from different operators or batches incomparable and hindering product quality assessment. While some automated testing equipment exists on the market, its high cost and complex operating procedures limit its widespread application on production lines.

[0004] With the advancement of intelligent manufacturing technology, the industry has placed higher demands on torque testing. On the one hand, it requires standardization and automation of the testing process to reduce human interference; on the other hand, it requires the testing system to have data acquisition and analysis capabilities to provide data support for process optimization. Most existing testing devices lack intelligent monitoring modules and cannot record the deformation characteristics and mechanical response of profiles under torque in real time. Especially in the research and development of new composite profiles, traditional testing methods struggle to accurately capture the nonlinear deformation characteristics of materials. Therefore, developing a novel torque testing device for wound-formed pipes that integrates mechanical fixing, precise measurement, and intelligent analysis has become a key technological breakthrough for improving the quality control level of profile products. Summary of the Invention

[0005] (a) Purpose of the invention

[0006] To address the problems of inaccurate torque data acquisition during the construction and testing phase in existing technologies, the reliance on skilled workers to visually assess pipe deformation to determine if the destructive torque has been reached, the lack of specific implementation standards, significant human error, and the inherent risks of such destructive material mechanical property testing, this invention aims to provide an intelligent device for detecting the maximum torsional capacity of wound-formed pipes. This device solves the problems of low measurement accuracy, incomplete data acquisition, insufficient standardization of operation, and safety risks in existing profile torque testing.

[0007] (II) Technical Solution

[0008] To achieve the objective of this invention and solve its technical problems, the present invention adopts the following technical solution:

[0009] On one hand, the present invention provides a torque detection device for wound-formed tubing, comprising:

[0010] The machine head has a cage installed on one side. The cage is used to wind the profiles fed in by the machine head into a spiral tube. A torque tester is also installed on the machine head.

[0011] Fixture, installed on the spiral tube;

[0012] A torque wrench, one end of which is fitted with the fixed end of a retainer, and equipped with a torque sensor to sense the torque of the torque wrench;

[0013] A vision sensor, installed on one side of the spiral tube, is used to acquire image data of the spiral tube in real time;

[0014] The control system consists of field control devices and a cloud server. The field control devices are communicatively connected to vision sensors, torque sensors, and torque testers. The control system also includes an image recognition module, a deformation detection module, and a process parameter adjustment module.

[0015] The image data acquired by the vision sensor is analyzed by the image recognition module and the deformation discrimination module to calculate the cumulative strain value, global deformation acceleration, and local strain gradient of the sample area. A three-level state discrimination mechanism is used to determine whether the spiral tube has undergone irreversible plastic deformation. The real-time data of the torque tester and torque wrench acquired when plastic deformation occurs are used as the basis for judging whether the spiral tube meets the standards. The process parameters are improved and optimized according to the deep learning model of the process parameter adjustment module.

[0016] On the other hand, the present invention also provides a torque detection method for wound-formed pipes, which employs the aforementioned torque detection device for wound-formed pipes, and the method includes the following steps:

[0017] S1. Test preparation: The profile is continuously fed into the machine head and sent into the matching cage to be wound into a spiral tube of a fixed length;

[0018] S2. Torque wrench installation: Drill a hole in the spiral tube to install the retainer, ensuring that the retainer is concentric with the spiral tube. Assemble the torque wrench onto the retainer and limit the torque wrench installation.

[0019] S3. Torque Test: The vision sensor is activated to acquire images in real time. The die head begins to apply a uniformly accelerating feed pressure. The real-time image data acquired by the vision sensor is continuously uploaded to the cloud server. The cumulative strain value, overall deformation acceleration, and local strain gradient of the sample area are calculated and analyzed by the image recognition module and deformation discrimination module and fed back to the field control device. The field control device uses a three-level state discrimination mechanism to determine whether the spiral tube has undergone irreversible plastic deformation. When plastic deformation is determined to have occurred, the die head is immediately stopped from applying force and the force is slowly released. At the same time, the real-time data of the torque tester and torque wrench are captured as the destructive torque.

[0020] S4. Parameter Adjustment: The on-site control device determines whether the strength of the spiral tube meets the engineering requirements. If it does not meet the requirements, the process parameters and breaking torque of the spiral tube can be uploaded to the cloud server. The cloud server provides suggestions for improving the process parameters through the deep learning model of the process parameter adjustment module. Based on the suggestions, the process parameters are improved and optimized, a new spiral tube is remade, and the above steps are repeated until the strength of the spiral tube meets the engineering requirements.

[0021] (III) Beneficial Effects

[0022] Compared with the prior art, the present invention has the following beneficial effects:

[0023] (1) The torque wrench of the present invention is connected to the spiral tube through a retainer, so that the torque applied by the torque wrench can be evenly transmitted to the spiral tube, avoiding local stress concentration, thereby improving the accuracy of the measurement data. Through the coordinated work of the torque wrench and the torque tester, the dual detection and comparison of torque data can be realized, effectively reducing the systematic error of a single measuring device.

[0024] (2) This invention uses a cross-shaped drilling installation method between the fixture and the spiral tube, combined with the fastening structure of the screw and nut, to ensure a high-precision concentric connection between the fixture and the spiral tube, effectively avoiding torque measurement errors caused by installation deviations. The setting of the limiting plate can precisely limit the feeding length of the spiral tube, ensuring consistent initial conditions for each test, reducing human error, and improving the reliability of the test. The limiting effect of the bracket on the torque wrench can prevent it from deviating during the test, ensuring the stability of the torque application direction, thereby improving the measurement accuracy.

[0025] (3) This invention integrates a vision sensor and a control system to collect and analyze the displacement data of the spiral tube in real time. The control system performs synchronous data analysis to achieve automated monitoring of the detection process, reduce human intervention, and improve detection efficiency and objectivity. By setting up an image recognition module, a deformation discrimination module, and a process parameter adjustment module in the control system, the image data collected by the vision sensor is transmitted to the control system. The image recognition module and the deformation discrimination module calculate and analyze the cumulative strain value, the overall deformation acceleration, and the local strain gradient of the sample area. The three-level state discrimination mechanism can accurately capture the small displacement changes of the spiral tube under torque. The deep learning model of the process parameter adjustment module realizes the automatic adjustment of process parameters. The system automatically completes data statistics, analysis, and recording, significantly reducing the errors introduced by human operation, achieving efficient and accurate detection of profile torque performance, and automatically optimizing process parameters to achieve the best production spiral tube quality. Attached Figure Description

[0026] Figure 1 This is a front view of a torque detection device for spiral wound tubing according to an embodiment of the present invention;

[0027] Figure 2 This is a side view of a torque detection device for spiral wound tubing according to an embodiment of the present invention;

[0028] Figure 3 This is a structural diagram of the fixator according to an embodiment of the present invention;

[0029] Figure 4 This is a schematic diagram of the installation of the bracket and torque sensor according to an embodiment of the present invention;

[0030] Figure 5 This is a flowchart of a torque detection method for spiral wound pipes according to an embodiment of the present invention;

[0031] Explanation of reference numerals in the attached diagram: 1-Spiral tube; 2-Torque wrench; 3-Fixer; 4-Cage; 5-Head; 6-Torque tester; 7-Limit plate; 8-Vision sensor; 9-Bracket; 10-Lead screw; 11-Nut; 12-Torque sensor; 13-Control system. Detailed Implementation

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention.

[0033] Example 1: Torque Detection Device

[0034] like Figures 1 to 4 In the embodiment of the torque testing device for spiral wound tubing shown in the present invention, the device mainly includes a torque wrench 2, a retainer 3, a cage 4, a machine head 5, and a torque tester 6. The retainer 3 is installed on the spiral tube 1, the torque wrench 2 is connected to the spiral tube 1 through the retainer 3, the cage 4 is installed on one side of the machine head 5, and the torque tester 6 is installed on the machine head 5.

[0035] The torque wrench 2 is connected to the spiral tube 1 via the retainer 3, ensuring that the torque applied by the torque wrench 2 is evenly transmitted to the spiral tube 1, avoiding localized stress concentration and thus improving the accuracy of the measurement data. The cage 4 is used to wind the fed profile into the spiral tube 1. The cage 4's limiting effect on the spiral tube 1 also enhances the stability of the testing process, preventing the spiral tube 1 from shifting during torque loading. The main body of the retainer 3 is a disc with four screws 10 and several nuts 11 symmetrically arranged around its perimeter. A hexagonal head is located at the center of the disc. The screws 10 of the retainer 3 are connected to the outer end of the spiral tube 1 through cross-shaped drill holes. The retainer 3 uses a fastening structure of screws 10 and nuts 11 to achieve a reliable connection with the spiral tube 1. The retainer 3 is preferably set with high-precision concentricity with the spiral tube 1, effectively avoiding torque measurement errors caused by installation deviations. The fixed end of the retainer 3 is installed in conjunction with the torque wrench 2, ensuring that the torque applied by the torque wrench 2 is evenly transmitted to the spiral tube 1, ensuring the accuracy of the measurement data. The torque wrench 2 preferably has a hexagonal socket at its connecting end, which matches the hexagonal head at the center of the disc of the retainer 3. The two are installed by inserting the hexagonal head and the hexagonal socket together.

[0036] A limiting plate 7 is provided on one side of the spiral tube 1 to limit the feeding length of the spiral tube 1, ensuring that the initial position of the spiral tube 1 is consistent during each test, reducing human error and improving the reliability of the test. The cage 4 includes a guide rail frame, forming rollers, and guide rollers. The profile is folded and spirally wound into a tubular shape on the forming rollers inside the cage 4. The male and female locking buckles on both sides of the profile are self-locking, and the tubular spiral tube 1 moves forward under the action of the guide groove. The structure of the cage 4 also enhances the limiting effect on the spiral tube 1, preventing the spiral tube 1 from deviating during torque loading and ensuring accurate measurement results.

[0037] In addition, the detection device also includes a bracket 9, which is disposed on one side of the spiral tube 1 to limit the torque wrench 2. The bracket 9 can effectively prevent the torque wrench 2 from deviating during the detection process, ensuring the stability of the torque application direction, thereby improving the measurement accuracy. Preferably, a torque sensor 12 is disposed on the bracket 9 to collect the torque of the torque wrench 2 and transmit the information synchronously to the control system. In other embodiments, the torque sensor can also be disposed at the connection end that mates with the fixing device.

[0038] Furthermore, the detection device preferably includes a vision sensor 8, which is mounted on one side of the spiral tube 1 via a bracket, near the detection area, for real-time acquisition of image data from the spiral tube 1. The vision sensor 8 can accurately capture minute displacement changes of the spiral tube 1 under torque, and the data is transmitted to the control system via a high-speed data interface. Specifically, the vision sensor mentioned in this embodiment consists of a high-resolution industrial camera and a polarizing filter. The filter reduces interference from metallic reflections from the profile. A vibration-damping gimbal is also installed between the industrial camera and the bracket to reduce disturbances caused by on-site construction, personnel operation, etc. An external light source is also provided on the bracket to ensure stable brightness in the sampling area. The image data acquisition rate is greater than or equal to 30fps to ensure sufficient sampling.

[0039] In one embodiment, the system further includes a control system 13, which consists of a field control device and a cloud server. The field control device is communicatively connected to a vision sensor, a torque sensor, and a torque tester to achieve real-time acquisition, storage, and analysis of detection data. The field control device is connected to the machine head 5 to control the feeding force. Furthermore, the control system includes an image recognition module, a deformation discrimination module, and a process parameter adjustment module, wherein:

[0040] The image recognition module transmits the image data acquired by the vision sensor 8 to the image recognition module. In the image recognition module, dimensionality reduction is performed through pooling operations, and the dimensionality-reduced data is uploaded to the cloud server in real time. The cloud server performs polarization denoising processing on the dimensionality-reduced data through a polarization response layer to obtain denoised data. The denoised data is then convolved to extract speckle features to obtain a speckle feature set, thereby determining the tracking marker. The displacement field is calculated based on the pixel displacement and edge brightness changes of the tracking marker. The displacement field is plotted into 10 consecutive frames of strain field data with a resolution of 128×128 for each frame, according to the time-space relationship, for further analysis by the deformation discrimination module.

[0041] The image recognition module determines the displacement field by tracking changes in speckle brightness, exhibiting high accuracy under stable light conditions. To improve algorithm response speed, the algorithm employs a layered deployment: a basic preprocessing layer is deployed locally, while the core algorithm layer is deployed on a cloud server. Raw data undergoes local pooling preprocessing before being transmitted to the cloud server. The cloud server's high computing power then rapidly processes the displacement field information, rendering it into 10 consecutive frames of strain field data with a resolution of 128×128, which are then sent to the deformation discrimination module for further analysis. The image recognition module also includes a polarized light response layer to enhance texture recognition in reflective metal areas and further eliminate the influence of metal reflections.

[0042] The deformation discrimination module, comprising a 3D convolutional layer, an LSTM neural network layer, and a fully connected layer, inputs 128×128×10 strain field data into the 3D convolutional layer to simultaneously discriminate the temporal and spatial variation characteristics of the displacement field, obtaining a spatiotemporal feature sequence. The LSTM neural network layer receives the spatiotemporal feature sequence extracted from the 3D convolutional layer and analyzes the dynamic evolution path of the strain field. After forgetting and state updates, it inputs the feature vector of the evolution information into the fully connected layer. The fully connected layer, as the output layer, maps the feature vector of the evolution information to three deformation indices through weighted summation and nonlinear transformation: the cumulative strain value of the sample region, the overall deformation acceleration, and the local strain gradient.

[0043] The cumulative strain value of the sample area directly reflects the degree of plastic deformation in that area; the global deformation acceleration predicts the trend of deformation rate (acceleration) throughout the strain field during the observation period, determining whether deformation is accelerating and serving as an important early warning signal for instability risk; the local strain gradient predicts the spatial rate of change of strain (gradient) near a specific location or region. High strain gradients usually indicate stress concentration and are dangerous areas for crack initiation or propagation.

[0044] The cloud server packages the three deformation indices and their corresponding time and spatial coordinates into a data packet and feeds it back to the field control device. This data packet enters the field control device's deformation discrimination mechanism, which controls the growth rate of the feed thrust of the die head 5 based on the returned data. When the cumulative strain value in a region is less than 50% of the material's ultimate strain, it indicates that the structure is in the elastic deformation stage and has not reached the material's limit. This stage is considered low-risk, and the preset growth rate of the feed thrust of the die head 5 can be maintained unchanged. If a sudden change occurs in the local strain gradient exceeding 200% (e.g., from 0.01 / mm to 0.03 / mm), it is determined to be a stress concentration phenomenon, indicating the onset of potential damage. During the initial stage, it is crucial to monitor the microcrack propagation trend in this area. This stage is considered a medium-risk stage, and the growth rate of the preset feed thrust of the die head 5 should be gradually reduced. When the deformation acceleration continuously exceeds 0.1% / ms (i.e., the strain rate increases by 0.001 per millisecond) or microcracks are observed, this state indicates the initiation of necking or macroscopic fracture, marking the material entering an irreversible unstable failure stage. This stage is considered a high-risk stage, and the force applied by the die head 5 should be stopped immediately and the force slowly released to prevent further collapse of the sample spiral tube and subsequent safety accidents. The real-time data from the torque tester 6 and torque wrench 2 should be saved as the destructive torque, and the feed thrust failure value of the die head 5 should be recorded.

[0045] In the process parameter adjustment module, the on-site control device will initially determine whether the strength of the batch of spiral tubes meets the engineering requirements based on the breaking torque. If it does not meet the standard, the data such as the feed rate, feed pressure, hot melt adhesive output rate and breaking torque of the sample spiral tube can be uploaded to the cloud server. The cloud server provides process parameter improvement suggestions through the deep learning model of the process parameter adjustment module. After fine-tuning, a new sample spiral tube is remade and the test is repeated until the strength of the spiral tube meets the engineering requirements.

[0046] Specifically, the pre-training samples of the overall control system, comprising three modules, were collected in the materials laboratory. This model can also be further optimized based on real-time data uploaded to the cloud server during past construction. Using vision sensors, torque sensors, and torque testers, key data such as the displacement and stress of the spiral tube are collected in real time. The system automatically completes data statistics, analysis, and recording, significantly reducing errors introduced by human operation, achieving efficient and accurate detection of the profile's torque performance, and automatically optimizing process parameters to achieve the best production quality of the spiral tube.

[0047] Example 2: Torque Detection Method

[0048] Based on Embodiment 1 above, Embodiment 2 of the present invention further proposes a torque detection method for wound-formed pipes, and a torque detection device for wound-formed pipes based on the present invention, such as... Figure 5 As shown, the method mainly includes the following steps when implemented:

[0049] S1. Test Preparation:

[0050] The profile is continuously fed into the die head 5 and into the matching cage 4 to be wound into a spiral tube 1 of a fixed length. To ensure consistent winding length, a limit plate 7 is installed to restrict the feeding length;

[0051] S2. Torque wrench installation:

[0052] Drill a hole in the cross direction at the outer end of the spiral tube 1 to install the retainer 3, and complete the secure connection through the screw 10 and nut 11. During the installation process, strictly calibrate the length of the screw 10 and the distance between the nut 11 and the screw 10 to ensure that the retainer 3 and the spiral tube 1 are concentric; insert the hexagonal socket of the torque wrench 2 into the hexagonal head at the center of the disc of the retainer 3 to complete the installation, and limit the installation of the torque wrench 2 and the bracket 9;

[0053] S3. Torque Test:

[0054] The vision sensor 8 is activated to acquire image data in real time. After a period of image acquisition and confirmation of the tracked sample area, the preprocessed data is uploaded to the cloud server. Testing begins after the cloud server confirms normal real-time transmission. The die head 5 begins to apply a uniformly accelerating feed pressure, and the field control device continuously uploads the real-time image data acquired by the vision sensor 8 to the cloud server. The cloud server calculates and analyzes the stress deformation of the sample area using the image recognition module and deformation discrimination module, and feeds back three deformation indicators to the field control device in real time. The field control device uses a three-level state discrimination mechanism to determine whether irreversible plastic deformation has occurred in the spiral tube. When plastic deformation is determined to have occurred, the force applied to the die head 5 is immediately stopped and the force is slowly released. Simultaneously, the real-time data from the torque tester 6 and torque wrench 2 are captured as the breaking torque, and the feed thrust of the die head 5 is recorded as the breaking thrust value.

[0055] S4. Parameter Adjustment:

[0056] The on-site control device determines whether the strength of the batch of spiral tubes meets the engineering requirements. If it does not meet the requirements, it can upload data such as the feed rate, feed pressure, hot melt adhesive discharge rate and breaking torque of the sample spiral tubes to the cloud server. The cloud server provides suggestions for improving the process parameters through the deep learning model of the process parameter adjustment module. After adjusting according to the suggestions, a new sample spiral tube is remade, and the above testing steps are repeated until the strength of the spiral tubes meets the engineering requirements.

[0057] Preferably, step S3, when performing the torque test, specifically includes the following sub-steps:

[0058] SS31. The image data acquired by the vision sensor is transmitted to the image recognition module. In the image recognition module, dimensionality reduction is performed through pooling operations, and the dimensionality-reduced data is uploaded to the cloud server in real time. The cloud server performs polarization denoising processing on the dimensionality-reduced data through the polarization response layer to obtain denoised data. The denoised data is convolved to extract speckle features to obtain a speckle feature set, thereby determining the tracking marker. The displacement field is calculated based on the pixel displacement and edge brightness change of the tracking marker. The displacement field is plotted into strain field data of 10 consecutive frames with a resolution of 128×128 for each frame according to the time-space relationship.

[0059] SS32. The strain field data is input into the deformation discrimination module. The convolutional layer in the deformation discrimination module determines the temporal and spatial variation characteristics of the displacement field, and obtains the spatiotemporal feature sequence. The LSTM neural network layer receives the spatiotemporal feature sequence and analyzes the dynamic evolution path of the strain field. After forgetting gate filtering and state update, the feature vector of the evolution information is input into the fully connected layer. The fully connected layer, as the output layer, maps the feature vector of the evolution information to three deformation indices: cumulative strain value of the sample region, global deformation acceleration, and local strain gradient through weighted summation and nonlinear transformation.

[0060] The SS33 cloud server packages the three deformation indices and their corresponding time and spatial coordinates into a data packet and feeds it back to the field control device. This data packet enters the deformation discrimination mechanism of the field control device, which controls the growth rate of the feed thrust of the die head based on the returned data. When the cumulative strain value in the region is lower than 50% of the material's ultimate strain, the growth rate of the preset feed thrust of the die head remains unchanged. If a sudden change occurs in the local strain gradient, the growth rate of the preset feed thrust of the die head is gradually slowed down. When the deformation acceleration continuously exceeds 0.1% / ms or a microcrack is observed, the die head force application is stopped immediately and the force is slowly released. The real-time data from the torque tester and torque wrench are saved as the destructive torque, and the feed thrust of the die head is recorded as the destructive thrust value.

[0061] This invention provides a torque testing technology for spiral wound tubing. By integrating a torque testing device with an automated monitoring system, a high-precision profile performance testing system is constructed. Through the precise installation of the retainer 3, the coordinated detection of the torque wrench 2 and torque tester 6, the real-time monitoring of the vision sensor 8, and the intelligent analysis of the control system, accurate measurement of the profile's torque performance is achieved. The coordinated operation of each component, from the precise positioning of the spiral tube 1 and the uniform application of torque to the real-time acquisition and analysis of data, effectively solves the problems of large installation deviations, high measurement errors, and incomplete data acquisition in traditional torque testing, providing reliable technical support for the quality control of profile products.

[0062] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A torque detection device for spiral wound tubing, characterized in that, include: The machine head has a cage installed on one side. The cage is used to wind the profile fed into the machine head into a spiral tube, and a torque tester is installed on the machine head. Fixture, installed on the spiral tube; A torque wrench is installed in conjunction with the center fixed end of a retainer and is equipped with a torque sensor to detect the torque of the torque wrench. A vision sensor, installed on one side of the spiral tube, is used to acquire image data of the spiral tube in real time; The control system consists of field control devices and a cloud server. The field control devices are communicatively connected to vision sensors, torque sensors, and torque testers, and among them: The control system is equipped with an image recognition module, a deformation discrimination module, and a process parameter adjustment module. The image data collected by the vision sensor is used by the image recognition module and the deformation discrimination module to calculate and analyze the cumulative strain value, the overall deformation acceleration, and the local strain gradient of the sample area. A three-level state discrimination mechanism is used to determine whether the spiral tube has undergone irreversible plastic deformation. The real-time data of the torque tester and torque wrench obtained when plastic deformation occurs are used as the basis for judging whether the spiral tube meets the standards. The process parameters are improved and optimized based on the deep learning model of the process parameter adjustment module.

2. The torque detection device for wound-formed pipes according to claim 1, characterized in that: The main body of the fixture is a disc, with four screws and several nuts symmetrically arranged around the disc. A hexagonal head is located at the center of the disc. The screws of the fixture are connected to the outer end of the spiral tube through cross-shaped drill holes.

3. The torque detection device for wound-formed pipes according to claim 1, characterized in that: The vision sensor consists of a high-resolution industrial camera and a polarizing filter.

4. The torque detection device for spiral wound tubing according to claim 1, characterized in that: The image recognition module transmits the image data collected by the visual sensor to the image recognition module, performs dimensionality reduction processing through pooling operation in the image recognition module, and uploads the dimensionality-reduced data to the cloud server in real time; The cloud server performs polarization denoising on the dimensionality-reduced data through a polarization response layer to obtain denoised data; the denoised data is then convolved to extract speckle features to obtain a speckle feature set, thereby determining the tracking marker; the displacement field is calculated based on the pixel displacement and edge brightness change of the tracking marker; the displacement field is plotted into 10 consecutive frames of strain field data with a resolution of 128×128 for each frame, according to the time-space relationship.

5. The torque detection device for wound-formed pipes according to claim 4, characterized in that: The deformation discrimination module includes a 3D convolutional layer, an LSTM neural network layer, and a fully connected layer. The strain field data is input into the 3D convolutional layer to simultaneously discriminate the temporal and spatial variation characteristics of the displacement field, thereby obtaining a spatiotemporal feature sequence. After receiving the spatiotemporal feature sequence extracted from the 3D convolutional layer, the LSTM neural network layer analyzes the dynamic evolution path of the strain field and inputs the feature vector of the evolution information into the fully connected layer after forget gate filtering and state update. The fully connected layer, as the output layer, maps the feature vectors of evolutionary information to three deformation indices: cumulative strain value, global deformation acceleration, and local strain gradient, through weighted summation and nonlinear transformation.

6. The torque detection device for wound-formed tubing according to claim 5, characterized in that, The three-level state discrimination mechanism of the deformation discrimination module is as follows: The cloud server packages the three deformation indices and their corresponding time and spatial coordinates into a data packet and feeds it back to the field control device. This data packet enters the deformation discrimination mechanism of the field control device, which controls the growth rate of the feed thrust of the die head based on the returned data. When the cumulative strain value in the region is lower than 50% of the material's ultimate strain, the growth rate of the preset feed thrust of the die head remains unchanged. If a sudden change occurs in the local strain gradient, the growth rate of the preset feed thrust of the die head is gradually slowed down. When the deformation acceleration continuously exceeds 0.1% / ms or a microcrack is observed, the die head force application is stopped immediately and the force is slowly released. The real-time data from the torque tester and torque wrench is saved as the destructive torque.

7. The torque detection device for wound-formed tubing according to claim 1, characterized in that: A limit plate is provided on one side of the spiral tube to limit the feeding length of the spiral tube.

8. The torque detection device for spiral wound tubing according to claim 1, characterized in that: It also includes a bracket, which is set on one side of the spiral tube, for limiting the torque wrench.

9. A method for detecting torque in wound pipes, comprising using the torque detection device for wound pipes as described in any one of claims 1-8, characterized in that, Includes the following steps: S1. Test preparation: The profile is continuously fed into the machine head and sent into the matching cage to be wound into a spiral tube of a fixed length; S2. Torque wrench installation: Drill a hole in the spiral tube to install the retainer, ensuring that the retainer is concentric with the spiral tube. Assemble the torque wrench onto the retainer and limit the torque wrench installation. S3. Torque Test: The vision sensor is activated to acquire images in real time. The die head begins to apply a uniformly accelerating feed pressure. The real-time image data acquired by the vision sensor is continuously uploaded to the cloud server. The cumulative strain value, overall deformation acceleration, and local strain gradient of the sample area are calculated and analyzed by the image recognition module and deformation discrimination module and fed back to the field control device. The field control device uses a three-level state discrimination mechanism to determine whether the spiral tube has undergone irreversible plastic deformation. When plastic deformation is determined to have occurred, the die head is immediately stopped from applying force and the force is slowly released. At the same time, the real-time data of the torque tester and torque wrench are captured as the destructive torque. S4. Parameter adjustment; The on-site control device determines whether the strength of the spiral tube meets the engineering requirements. If it does not meet the requirements, the process parameters and breaking torque of the spiral tube are uploaded to the cloud server. The cloud server provides suggestions for improving the process parameters through the deep learning model of the process parameter adjustment module. Based on the suggestions, the process parameters are improved and optimized, a new spiral tube is remade, and the above steps are repeated until the strength of the spiral tube meets the engineering requirements.

10. The torque detection method for wound-formed pipes according to claim 9, characterized in that: Step S3 includes the following sub-steps when implemented: SS31. The image data collected by the vision sensor is transmitted to the image recognition module. In the image recognition module, dimensionality reduction is performed through pooling operation, and the dimensionality-reduced data is uploaded to the cloud server in real time. The cloud server performs polarization denoising on the dimensionality-reduced data through a polarization response layer to obtain denoised data. The denoised data is then convolved to extract speckle features, resulting in a speckle feature set, which is used to determine the tracking markers. The displacement field is calculated based on the pixel displacement and edge brightness changes of the tracking markers. Finally, the displacement field is plotted as strain field data according to the time-space relationship. SS32. Input the strain field data into the deformation discrimination module. The convolutional layer in the deformation discrimination module determines the temporal and spatial variation characteristics of the displacement field and obtains the spatiotemporal feature sequence. The LSTM neural network layer receives the spatiotemporal feature sequence and analyzes the dynamic evolution path of the strain field. After forgetting gate filtering and state update, the feature vector of the evolution information is input into the fully connected layer. The fully connected layer, as the output layer, maps the feature vectors of evolutionary information to three deformation indices: cumulative strain value, full-field deformation acceleration, and local strain gradient in the sample region through weighted summation and nonlinear transformation. The SS33 cloud server packages the three deformation indices and their corresponding time and spatial coordinates into a data packet and feeds it back to the field control device. This data packet enters the deformation discrimination mechanism of the field control device, which controls the growth rate of the feed thrust of the die head based on the returned data. When the cumulative strain value in the region is lower than 50% of the material's ultimate strain, the growth rate of the preset feed thrust of the die head remains unchanged. If a sudden change occurs in the local strain gradient, the growth rate of the preset feed thrust of the die head is gradually slowed down. When the deformation acceleration continuously exceeds 0.1% / ms or a microcrack is observed, the die head force application is stopped immediately and the force is slowly released. The real-time data from the torque tester and torque wrench is saved as the destructive torque.

Images