Method and device for monitoring deformation of ship pipeline, electronic equipment and medium
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA STATE SHIPBUILDING CORP LTD RESEARCH INSTITUTE 719
- Filing Date
- 2026-03-10
- Publication Date
- 2026-06-30
AI Technical Summary
In existing technologies, deformation monitoring of pipeline sections through the sea is difficult to simultaneously meet the requirements of accuracy and comprehensiveness. Structured light surface cameras have insufficient accuracy and are environmentally dependent, while strain sensors have a limited number of monitoring points.
By combining optical and contact sensors, and by traversing various lens flatness values, the error between optical and contact measurement values is calculated. The target lens flatness with the smallest error is then selected for use in the optical sensor calculation, achieving high-precision full-area monitoring.
This improved monitoring accuracy and full-area coverage, ensuring the reliability and quality of large-scale pipeline docking installations on ships.
Smart Images
Figure CN122305953A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of ship pipeline safety technology, and in particular to a method, device, electronic equipment, and medium for monitoring the deformation of ship pipelines. Background Technology
[0002] Monitoring the installation status of the subsea tunnel section is a major challenge during the docking process between the module and the hull. This is primarily because the subsea tunnel section is large and heavy after the module is pushed into the hull, and its installation space is extremely limited as one end connects to the module and the other to the hull. Currently, the installation status of the subsea tunnel section is monitored mainly through two methods: structured light surface cameras and strain sensors.
[0003] However, the deformation calculation process of structured light surface cameras involves the flatness of the lenses, which generally changes with environmental factors such as temperature and humidity. Therefore, a value is typically set empirically during the calculation, resulting in insufficient accuracy for structured light surface camera measurements. While strain sensors, installed in fixed locations, can achieve relatively accurate deformation measurement, the number of monitorable locations is very limited due to installation limitations and space constraints. Consequently, current deformation monitoring of the Tonghai pipeline section cannot meet both accuracy and comprehensiveness requirements. Summary of the Invention
[0004] This invention provides a method, device, electronic equipment, and medium for monitoring the deformation of ship pipelines, in order to solve the shortcomings of existing technologies in monitoring the deformation of sea-crossing pipeline sections, which are difficult to achieve both accuracy and comprehensiveness.
[0005] This invention provides a method for monitoring the deformation of ship pipelines, comprising: Acquire optical monitoring data based on optical sensors and reference deformation at the target monitoring point obtained based on contact sensors; the optical monitoring data and the reference deformation are obtained based on monitoring of the same ship's pipeline. The monitoring data to be calculated at the target monitoring point is extracted from the optical monitoring data; Based on the flatness of each candidate lens of the optical sensor, the monitoring data to be solved is calculated to obtain the candidate deformation under the flatness of each candidate lens; Based on each candidate deformation and the reference deformation, the candidate measurement error under the flatness of each candidate lens is calculated respectively; Based on the candidate measurement error, the target lens flatness is selected from the candidate lens flatness to perform deformation monitoring based on the target lens flatness.
[0006] According to the present invention, a method for monitoring the deformation of a ship's pipeline includes multiple target monitoring points; The calculation of the candidate measurement error for the flatness of each candidate lens, based on each candidate deformation and the reference deformation, includes: For each candidate flatness, calculate the single-point error between the candidate deformation and the corresponding reference deformation at each target monitoring point; The single-point errors corresponding to multiple target monitoring points are summed to obtain the candidate measurement error for each candidate flatness.
[0007] According to the present invention, a method for monitoring the deformation of a ship's pipeline includes calculating the single-point error between the candidate deformation and the corresponding reference deformation at each target monitoring point, comprising: For each target monitoring point, calculate the absolute value of the difference between the candidate deformable variable and the corresponding reference deformable variable at each target monitoring point; Calculate the ratio of the absolute value of the difference to the absolute value of the reference deformation, and determine the ratio as the single-point error at each target monitoring point.
[0008] According to the present invention, a method for monitoring the deformation of a ship's pipeline, wherein selecting the target lens flatness from the candidate lens flatness based on the candidate measurement error includes: Compare the candidate measurement errors corresponding to the flatness of each candidate lens; The flatness of the candidate lens corresponding to the smallest candidate measurement error is determined as the flatness of the target lens.
[0009] According to the deformation monitoring method for ship pipelines provided by the present invention, the step of determining the flatness of candidate lenses includes: Obtain the reference flatness range under the preset environment; The reference flatness range is divided according to a preset step size to obtain multiple candidate lens flatnesses; Alternatively, a specified number of candidate lens flatnesses may be randomly generated within the range of the reference flatness.
[0010] According to the present invention, a method for monitoring the deformation of a ship's pipeline includes an optical sensor comprising a structured light surface camera and a contact sensor comprising a strain sensor. The deformation monitoring based on the flatness of the target lens includes: Using the flatness of the target lens as an intrinsic parameter of the structured light surface camera, the optical monitoring data is calculated globally to obtain the global deformation of the ship's pipeline.
[0011] The present invention also provides a deformation monitoring device for ship pipelines, comprising: The acquisition unit acquires optical monitoring data collected by an optical sensor and reference deformation at the target monitoring point obtained by a contact sensor; the optical monitoring data and the reference deformation are obtained based on monitoring of the same ship pipeline to be monitored; The extraction unit extracts the monitoring data to be solved at the target monitoring point from the optical monitoring data; The calculation unit calculates the monitoring data to be calculated based on the flatness of each candidate lens of the optical sensor to obtain the candidate deformation under the flatness of each candidate lens; The error calculation unit calculates the candidate measurement error of the flatness of each candidate lens based on each candidate deformation and the reference deformation, respectively. The optimized monitoring unit selects the target lens flatness from the candidate lens flatness based on the candidate measurement error, and performs deformation monitoring based on the target lens flatness.
[0012] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the deformation monitoring method for ship pipelines as described above.
[0013] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the deformation monitoring method for ship pipelines as described above.
[0014] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the deformation monitoring method for ship pipelines as described above.
[0015] The present invention provides a method, device, electronic equipment, and medium for monitoring the deformation of ship pipelines. By traversing multiple candidate lens flatnesses within a preset range and calculating the error between their respective optical measurement values and contact measurement values, the flatness of the target lens with the smallest error under the current environment is selected. This improves the monitoring accuracy of deformation monitoring based on optical sensors, while also overcoming the limitation of the limited deployment points of contact sensors. Thus, it can ensure the high accuracy of monitoring data and achieve full-area coverage monitoring of the installation status of ship-to-sea pipelines, greatly improving the reliability and quality of docking and installation of large ship pipelines in complex environments. Attached Figure Description
[0016] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0017] Figure 1 This is a flowchart illustrating the deformation monitoring method for ship pipelines provided by the present invention; Figure 2 This is a schematic diagram of the deformation monitoring system for ship pipelines provided by the present invention; Figure 3 This is a schematic diagram of the deformation monitoring device for ship pipelines provided by the present invention; Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this 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 this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0019] It should be noted that as ships gradually develop towards higher power and larger tonnage, the ship assembly process generally adopts a modular construction mode. This involves high-precision modular assembly outside the hull, followed by docking between the modules and the hull. This effectively improves the assembly quality and efficiency of the modules. However, during the docking process between the modules and the hull, monitoring the installation status of the sea passage pipe section is a major challenge in the entire installation process. This is mainly because after the module is pushed into the hull, the sea passage pipe section is large in size and weight, with one end connecting to the module and the other end connecting to the hull, and the installation space is extremely limited.
[0020] Currently, the installation status of subsea pipeline sections is mainly monitored using two methods: structured light surface cameras and strain sensors. Structured light surface cameras scan the pipeline section using structured light, constructing a global coordinate system. Within this system, point cloud maps and depth maps are fitted to calculate the global deformation of the pipeline section. This method offers a large monitoring range and high efficiency. However, the deformation calculation process for structured light surface cameras involves the flatness of the lenses, which generally changes with external environmental factors such as temperature and humidity. Therefore, a value is typically set empirically during the calculation process, resulting in insufficient accuracy for this method. Strain sensors, on the other hand, can achieve relatively accurate deformation measurement by being installed at fixed locations. However, due to limitations in installation technology and space, the number of locations that can be monitored is very limited.
[0021] To address the aforementioned problems, this invention provides a method for monitoring the deformation of ship pipelines, thereby achieving high-precision monitoring of pipeline deformation. Figure 1 This is a flowchart illustrating the deformation monitoring method for ship pipelines provided by the present invention, as shown below. Figure 1 As shown, the method includes: Step 110: Obtain optical monitoring data collected by optical sensors and reference deformation at the target monitoring point obtained by contact sensors.
[0022] The optical monitoring data and the reference deformation are obtained based on monitoring of the same ship's pipeline.
[0023] Here, the pipelines to be monitored on the ship refer to sea passage sections or other critical pipelines that require high-precision docking and installation during the modular construction of the ship. Due to the large size and weight of these pipelines, and the extremely limited installation space, their deformation directly affects the docking quality. Furthermore, the optical sensor here refers to a device employing a non-contact measurement principle. In this embodiment, it can specifically be a structured light surface camera, which can construct a global coordinate system by projecting structured light and acquiring reflected images, thereby covering a large monitoring range. Here, the optical monitoring data refers to the raw image data, point cloud data, or depth map data acquired by the optical sensor scanning and capturing images of the pipelines on the ship to be monitored.
[0024] Furthermore, the contact sensor here refers to a device that is directly attached to the surface of an object to sense deformation; in this embodiment, a strain sensor is preferred. Since the contact sensor is directly fixed to the pipe surface, its measurement results are less affected by environmental factors such as light, temperature, and refractive index. Therefore, its measurement value is considered a highly reliable benchmark value, i.e., a reference deformation. Here, the target monitoring point refers to the specific physical location on the ship's pipeline where the contact sensor is actually deployed.
[0025] Specifically, firstly, k contact sensors, such as strain sensors, can be deployed at key locations on the pipeline to be monitored to collect real-time deformation values at these specific locations as reference deformation values. Simultaneously, optical sensors, such as structured light cameras, mounted at appropriate viewing angles, are used to perform a comprehensive scan of the pipeline, acquiring optical monitoring data containing information about the entire pipeline's morphology. It should be noted that the acquisition of these two types of data is synchronized or nearly synchronized in time to ensure that they reflect the deformation of the pipeline under the same condition.
[0026] Step 120: Extract the monitoring data to be solved at the target monitoring point from the optical monitoring data.
[0027] Here, the monitoring data to be calculated refers to the local data in the optical monitoring data corresponding to the target monitoring point where the contact sensor is deployed in physical space. It is understandable that since the optical sensor collects global data, such as the entire point cloud map, while the contact sensor only provides data for a few discrete points, it is necessary to establish a spatial mapping relationship between the two.
[0028] Specifically, pixel coordinates or point cloud coordinates corresponding to the location of the contact sensor in physical space can be found in the coordinate system constructed by the optical sensor through pre-calibration or feature point recognition. Then, the optical monitoring data at this coordinate location is extracted and used as input data for subsequent targeted calculations. This allows for point-to-point alignment between the optical measurement results and the contact measurement results in space, providing a basis for comparison in subsequent parameter calibration.
[0029] Step 130: Based on the flatness of each candidate lens of the optical sensor, the monitoring data to be solved is calculated to obtain the candidate deformation under the flatness of each candidate lens.
[0030] Here, candidate lens flatness refers to the various flatness values that an optical sensor lens may have under the current environment. It is understood that since lens flatness is not a constant value, directly using factory settings or empirical values will lead to calculation errors. Therefore, this embodiment of the invention treats it as a variable and sets a series of possible values as candidates. Furthermore, candidate deformation here refers to the deformation value at the target monitoring point calculated using the monitoring data to be calculated, by substituting a specific candidate lens flatness as a parameter into the optical calculation algorithm.
[0031] Specifically, first, it is necessary to determine the range of values for the lens flatness. For example, this can be done by simulating the typical marine environment of a pipeline installation site in an environmental laboratory to determine the threshold range of lens flatness variation under these conditions. Then, within this threshold range, multiple values are generated according to certain rules. For instance, the range can be divided into n equal segments, and n+1 values can be selected in a stepwise manner. Alternatively, a geometric sequence can be used, or a certain number of values can be randomly generated within the range.
[0032] Furthermore, for each generated candidate lens flatness, it is used as a known input parameter and input into the optical sensor's solution model to process the data extracted in step 120, thereby obtaining a set of candidate deformation variables corresponding to each candidate lens flatness. It can be understood that if n+1 candidate lens flatnesses are selected, then n+1 sets of candidate deformation variables will be calculated accordingly.
[0033] Step 140: Calculate the candidate measurement error for the flatness of each candidate lens based on each candidate deformation and the reference deformation.
[0034] Here, the candidate measurement error is used to quantify the deviation between the optical measurement result and the true value when using the flatness of a specific candidate lens. Since the reference deformation measured by the contact sensor is considered a high-precision benchmark, this error is the difference between the candidate deformation and the reference deformation.
[0035] Specifically, for each candidate lens flatness, the difference or distance between its calculated candidate deformation and the reference deformation actually measured at that location can be calculated. If there are k target monitoring points, i.e., k contact sensors are deployed, then it is necessary to calculate the total difference between the optical measurements and contact measurements at all k locations for the flatness of the candidate lens. For example, statistical methods such as the sum of absolute values or root mean square error can be used to characterize the overall error level for the flatness of the candidate lens. Through this step, the abstract lens parameter selection problem can be transformed into a specific numerical error minimization problem.
[0036] Step 150: Based on the candidate measurement error, select the target lens flatness from the candidate lens flatness to perform deformation monitoring based on the target lens flatness.
[0037] Specifically, by comparing the candidate measurement errors calculated in step 140, a minimum value comparator or sorting algorithm is used to find the candidate measurement error with the smallest value. The candidate lens flatness corresponding to this minimum error is considered the optimal setting value under the current environment, and is thus taken as the target lens flatness. It can be understood that using the value corresponding to the target lens flatness means that the measurement results of the optical sensor are closest to the measurement results of the high-precision contact sensor.
[0038] Furthermore, once the flatness of the target lens is determined, it can be fixed as the current operating parameter of the optical sensor. Subsequently, using the flatness of the target lens, the full-area optical monitoring data collected by the optical sensor, covering the entire pipeline of the ship under monitoring, is calculated. The resulting full-area deformation result at this point possesses the advantages of the optical sensor's large field of view and high efficiency, while also correcting for accuracy errors caused by environmental factors through the calibration of the contact sensor.
[0039] The deformation monitoring method for ship pipelines provided in this invention improves the monitoring accuracy of deformation monitoring based on optical sensors by traversing multiple candidate lens flatnesses within a preset range and calculating the error between their corresponding optical measurement values and contact measurement values. This method selects the target lens flatness with the smallest error under the current environment, thereby overcoming the limitation of the limited deployment points of contact sensors. It ensures high accuracy of monitoring data and achieves full-area coverage monitoring of the installation status of ship-to-sea pipelines, greatly improving the reliability and quality of docking and installation of large ship pipelines in complex environments.
[0040] Based on any of the above embodiments, the target monitoring points include multiple points; Here, there are multiple target monitoring points, and contact sensors can be deployed in different critical stress areas of the sea-crossing pipeline, such as flange connections, bends, and intermediate suspended sections. In this embodiment, the number of target monitoring points is set to k.
[0041] Accordingly, step 140 includes: For each candidate flatness, calculate the single-point error between the candidate deformation and the corresponding reference deformation at each target monitoring point; The single-point errors corresponding to multiple target monitoring points are summed to obtain the candidate measurement error for each candidate flatness.
[0042] Specifically, firstly, for each candidate flatness, i.e., for each assumed lens flatness value, the data from all k target monitoring points can be processed in parallel or serially. This means that for the current candidate flatness, k corresponding candidate deformation variables have already been calculated. At this point, the difference between the candidate deformation variable at each of these k locations and the reference deformation variable actually measured at that location can be defined as the single-point error. It can be understood that the single-point error here characterizes the measurement accuracy of the optical sensor at a specific local location under the current lens flatness setting.
[0043] Then, to evaluate the suitability of the candidate flatness for the entire pipeline, these local evaluation indicators need to be aggregated. For example, the single-point errors corresponding to these k target monitoring points can be summed. By accumulating the errors at all key locations, a value that comprehensively reflects the overall degree of fit is obtained, namely, the candidate measurement error for each candidate flatness.
[0044] In one embodiment, assuming three contact sensors are deployed, candidate deformation variables are calculated at the three target monitoring points for candidate flatness A. Then, the single-point errors at target monitoring points 1, 2, and 3 can be calculated by separately calculating the differences between the candidate deformation variables and the corresponding reference deformation variables at each target monitoring point. Then, the candidate measurement error under the candidate flatness A. = Therefore, subsequent processes can compare the total candidate measurement errors for each candidate flatness, rather than comparing the performance of a single target measurement point, thereby improving the accuracy of lens flatness correction.
[0045] The method provided in this invention, by introducing multiple target monitoring points and employing an error summation evaluation strategy, ensures that the flatness of the ultimately selected target lens is accurate not only at a single point but also maintains high measurement consistency across all critical areas of the pipeline. Understandably, this global optimization approach effectively avoids parameter calibration deviations caused by fluctuations in individual point readings or local deformation anomalies—i.e., overfitting—thereby significantly improving the overall reliability of full-area deformation monitoring for large ship pipelines.
[0046] Based on any of the above embodiments, the step of calculating the single-point error between the candidate deformation variable and the corresponding reference deformation variable at each target monitoring point includes: For each target monitoring point, calculate the absolute value of the difference between the candidate deformable variable and the corresponding reference deformable variable at each target monitoring point; Calculate the ratio of the absolute value of the difference to the absolute value of the reference deformation, and determine the ratio as the single-point error at each target monitoring point.
[0047] Specifically, for any candidate flatness, for each target monitoring point, the absolute value of the difference between the candidate deformation and the corresponding reference deformation at that target monitoring point is calculated. It should be noted that this absolute value of the difference directly reflects the magnitude of the numerical deviation between the two monitoring sensors at that target monitoring point, i.e., the absolute error.
[0048] Then, considering that the deformation baseline at different locations in a ship's pipeline may vary greatly—for example, some areas with concentrated stress may have large deformations, while some areas with higher rigidity may have small deformations—simply summing the absolute errors could lead to the evaluation system being dominated by errors in areas of large deformation, thus neglecting the accuracy requirements in areas of small deformation. Therefore, this invention introduces a normalization method: calculating the ratio of the absolute value of the aforementioned difference to the absolute value of the reference deformation at that point. Finally, this ratio can be determined as the single-point error at each target monitoring point. Thus, the final summarized candidate measurement error is actually the sum of the relative errors at each point.
[0049] In one embodiment, the candidate measurement error under any candidate flatness A can be calculated by the following formula, as shown below: In the formula, This represents the candidate measurement error under candidate flatness A; , … These represent the candidate deformation variables at the 1st, 2nd, ..., and kth target monitoring points, respectively. , … These represent the reference deformations at the 1st, 2nd, ..., and kth target monitoring points, respectively.
[0050] The method provided in this invention calculates the absolute value of the difference between the candidate deformation and the corresponding reference deformation at each target monitoring point; then, it calculates the ratio of the absolute value of the difference to the absolute value of the reference deformation, and determines the ratio as the single-point error at each target monitoring point. This eliminates the weight imbalance problem caused by the different magnitudes of deformation at different parts of the pipeline, so that each monitoring point, regardless of the size of the deformation, has relatively equal decision-making power in the optimal decision of the mirror flatness, and the final determined target mirror flatness can better take into account the measurement accuracy at various parts of the pipeline.
[0051] Based on any of the above embodiments, in step 150, selecting the target lens flatness from the candidate lens flatnesses based on the candidate measurement error includes: Compare the candidate measurement errors corresponding to the flatness of each candidate lens; The flatness of the candidate lens corresponding to the smallest candidate measurement error is determined as the flatness of the target lens.
[0052] Specifically, first, the candidate measurement errors corresponding to the flatness of each candidate lens are compared. That is, each set of candidate lens flatness corresponds to a calculated candidate measurement error, which characterizes the degree of deviation between the optical measurement and the contact reference under that setting. By iterating through this set of error data, a minimum value comparator or sorting algorithm can be used to find the minimum value among all the calculated error values.
[0053] Subsequently, the flatness of the candidate lens corresponding to the smallest candidate measurement error can be determined as the flatness of the target lens. It should be noted that the smallest error means that, under this flatness value setting, the measurement results of the optical sensor at key points best match the actual measured values of the high-precision contact sensor. Therefore, this flatness value can be considered to be closest to the true physical state of the lens under the current specific temperature and humidity conditions, i.e., the optimal solution under the current environment.
[0054] This invention achieves adaptive calibration of optical sensor parameters through an automated error comparison and minimum value optimization mechanism. It can lock the lens flatness that best matches the current actual measurement environment based on real-time calculation feedback, thereby ensuring that the subsequent deformation calculation based on this parameter has the highest confidence level and effectively solving the problem of optical measurement parameter drift caused by environmental factors.
[0055] Based on any of the above embodiments, the step of determining the flatness of the candidate lens includes: Obtain the reference flatness range under the preset environment; The reference flatness range is divided according to a preset step size to obtain multiple candidate lens flatnesses; Alternatively, a specified number of candidate lens flatnesses may be randomly generated within the range of the reference flatness.
[0056] It should be noted that the step of determining the flatness of candidate lenses usually occurs before the formal monitoring and calculation, and belongs to the parameter setting stage of system initialization.
[0057] Specifically, the first step is to determine the flatness of the candidate lenses, which includes obtaining the reference flatness range under a preset environment. Understandably, since the flatness of lenses changes with external environmental factors such as temperature and humidity, the characteristics of the lens flatness variation can be tested in advance in an environmental laboratory, simulating the general marine environmental conditions of a ship's sea-crossing pipeline installation site, to determine the upper and lower threshold ranges of its variation, i.e., the reference flatness range, denoted as […]. , ].
[0058] Based on this, the reference flatness range can be divided according to a preset step size to obtain multiple candidate lens flatness values. For example, the reference flatness range can be divided into n segments, and the lens flatness in the input conditions can be adjusted stepwise to obtain the desired flatness values. , , … .
[0059] Alternatively, in scenarios where computational efficiency is critical or the variation pattern is nonlinear, a specified number of candidate lens flatnesses can be randomly generated within the reference flatness range.
[0060] The embodiments of the present invention determine the benchmark range through preset environmental testing, and construct a candidate parameter set by combining step-by-step partitioning or random generation. This ensures that the parameter optimization process has both clear physical boundaries and sufficient search density, providing a sufficient data foundation for subsequently selecting high-precision target lens flatness and guaranteeing the effectiveness of calibration.
[0061] Based on any of the above embodiments, the optical sensor includes a structured light surface camera; the contact sensor includes a strain sensor. The deformation monitoring based on the flatness of the target lens includes: Using the flatness of the target lens as an intrinsic parameter of the structured light surface camera, the optical monitoring data is calculated globally to obtain the global deformation of the ship's pipeline.
[0062] Specifically, the optical sensor includes a structured light surface camera; the contact sensor includes a strain sensor. In one embodiment, Figure 2 This is a schematic diagram of the deformation monitoring system for ship pipelines provided by the present invention, as shown below. Figure 2 As shown, the monitoring system includes a structured surface camera, stress sensors, and a sea-crossing pipeline. The structured surface camera is used for comprehensive monitoring of the sea-crossing pipeline, while the stress sensors can be deployed at multiple target monitoring points along the pipeline.
[0063] Lens flatness is a crucial internal parameter in the imaging model of a structured light surface camera, directly impacting the accuracy of optical path calculations and 3D reconstruction. Therefore, the target lens flatness selected in the preceding steps can be updated in the camera's solution algorithm, replacing factory default values or empirical values.
[0064] Then, using the target lens flatness obtained through environmental calibration, the optical monitoring data covering the entire pipeline is reprocessed and subjected to 3D fitting. The final output global deformation not only includes information on the location of the contact sensors, but also the deformation information of all sensor-free areas on the pipeline, such as continuous surface deformation.
[0065] This invention combines a structured light surface camera with a strain sensor to form a complementary monitoring system. The point accuracy of the strain sensor is used to calibrate the surface parameters of the structured light camera, ultimately enabling high-precision, full-area measurement using the calibrated camera. This perfectly solves the problems of insufficient coverage of single-contact measurement and poor environmental adaptability of single-optical measurement in marine pipeline installation, achieving efficient, accurate, and comprehensive control over the pipeline installation status.
[0066] Based on any of the above embodiments Figure 3 This is a schematic diagram of the deformation monitoring device for ship pipelines provided by the present invention, as shown below. Figure 3 As shown, the device includes: The acquisition unit 310 acquires optical monitoring data collected by an optical sensor and reference deformation at the target monitoring point obtained by a contact sensor; the optical monitoring data and the reference deformation are obtained based on monitoring of the same ship pipeline to be monitored; Extraction unit 320 extracts the monitoring data to be solved at the target monitoring point from the optical monitoring data; The calculation unit 330 calculates the monitoring data to be calculated based on the flatness of each candidate lens of the optical sensor to obtain the candidate deformation under the flatness of each candidate lens. The error calculation unit 340 calculates the candidate measurement error of the flatness of each candidate lens based on each candidate deformation and the reference deformation, respectively. The optimized monitoring unit 350 selects the target lens flatness from the candidate lens flatness based on the candidate measurement error, and performs deformation monitoring based on the target lens flatness.
[0067] The deformation monitoring device for ship pipelines provided in this invention improves the monitoring accuracy of deformation monitoring based on optical sensors by traversing multiple candidate lens flatnesses within a preset range and calculating the error between their corresponding optical measurement values and contact measurement values. This also overcomes the limitation of limited deployment points of contact sensors, thereby ensuring high accuracy of monitoring data and achieving full-area coverage monitoring of the installation status of ship-to-sea pipelines. This greatly improves the reliability and quality of docking and installation of large ship pipelines in complex environments.
[0068] Based on any of the above embodiments, the target monitoring points include multiple points; The error calculation unit is specifically used for: For each candidate flatness, calculate the single-point error between the candidate deformation and the corresponding reference deformation at each target monitoring point; The single-point errors corresponding to multiple target monitoring points are summed to obtain the candidate measurement error for each candidate flatness.
[0069] Based on any of the above embodiments, the error calculation unit is further specifically used for: For each target monitoring point, calculate the absolute value of the difference between the candidate deformable variable and the corresponding reference deformable variable at each target monitoring point; Calculate the ratio of the absolute value of the difference to the absolute value of the reference deformation, and determine the ratio as the single-point error at each target monitoring point.
[0070] Based on any of the above embodiments, the optimized monitoring unit is specifically used for: Compare the candidate measurement errors corresponding to the flatness of each candidate lens; The flatness of the candidate lens corresponding to the smallest candidate measurement error is determined as the flatness of the target lens.
[0071] Based on any of the above embodiments, the device further includes a flatness determination unit, which is specifically used for: Obtain the reference flatness range under the preset environment; The reference flatness range is divided according to a preset step size to obtain multiple candidate lens flatnesses; Alternatively, a specified number of candidate lens flatnesses may be randomly generated within the range of the reference flatness.
[0072] Based on any of the above embodiments, the optical sensor includes a structured light surface camera; the contact sensor includes a strain sensor; The optimized monitoring unit is specifically used for: Using the flatness of the target lens as an intrinsic parameter of the structured light surface camera, the optical monitoring data is calculated globally to obtain the global deformation of the ship's pipeline.
[0073] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4As shown, the electronic device may include a processor 410, a communication interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute a deformation monitoring method for ship pipelines. This method includes: acquiring optical monitoring data collected by an optical sensor and a reference deformation at a target monitoring point obtained by a contact sensor; the optical monitoring data and the reference deformation are obtained based on monitoring of the same ship pipeline; extracting the monitoring data to be calculated at the target monitoring point from the optical monitoring data; calculating the monitoring data to be calculated based on the flatness of each candidate lens of the optical sensor to obtain candidate deformations under each candidate lens flatness; calculating candidate measurement errors under each candidate lens flatness based on each candidate deformation and the reference deformation; and selecting the target lens flatness from the candidate lens flatness based on the candidate measurement errors, and performing deformation monitoring based on the target lens flatness.
[0074] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0075] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the deformation monitoring method for ship pipelines provided by the above methods. The method includes: acquiring optical monitoring data collected based on optical sensors and reference deformation at a target monitoring point obtained based on contact sensors; the optical monitoring data and the reference deformation are obtained based on monitoring the same ship pipeline to be monitored; extracting monitoring data to be calculated at the target monitoring point from the optical monitoring data; calculating the monitoring data to be calculated based on the flatness of each candidate lens of the optical sensor to obtain candidate deformation under the flatness of each candidate lens; calculating candidate measurement errors under the flatness of each candidate lens based on each candidate deformation and the reference deformation; and selecting the flatness of a target lens from the candidate lens flatness based on the candidate measurement errors, so as to perform deformation monitoring based on the flatness of the target lens.
[0076] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements a method for monitoring the deformation of a ship's pipeline provided by the methods described above. This method includes: acquiring optical monitoring data collected by an optical sensor and a reference deformation at a target monitoring point obtained by a contact sensor; the optical monitoring data and the reference deformation are obtained based on monitoring of the same ship's pipeline to be monitored; extracting monitoring data to be calculated at the target monitoring point from the optical monitoring data; calculating the monitoring data to be calculated based on the flatness of each candidate lens of the optical sensor to obtain candidate deformations under the flatness of each candidate lens; calculating candidate measurement errors under the flatness of each candidate lens based on each candidate deformation and the reference deformation; and selecting a target lens flatness from the candidate lens flatness based on the candidate measurement errors, and performing deformation monitoring based on the target lens flatness.
[0077] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0078] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A method for monitoring the deformation of ship pipelines, characterized in that, include: Acquire optical monitoring data based on optical sensors and reference deformation at the target monitoring point obtained based on contact sensors; The optical monitoring data and the reference deformation are obtained based on monitoring of the same ship's pipelines. The monitoring data to be calculated at the target monitoring point is extracted from the optical monitoring data; Based on the flatness of each candidate lens of the optical sensor, the monitoring data to be solved is calculated to obtain the candidate deformation under the flatness of each candidate lens; Based on each candidate deformation and the reference deformation, the candidate measurement error under the flatness of each candidate lens is calculated respectively; Based on the candidate measurement error, the target lens flatness is selected from the candidate lens flatness to perform deformation monitoring based on the target lens flatness.
2. The method for monitoring the deformation of ship pipelines according to claim 1, characterized in that, The target monitoring points include multiple points; The calculation of the candidate measurement error for the flatness of each candidate lens, based on each candidate deformation and the reference deformation, includes: For each candidate flatness, calculate the single-point error between the candidate deformation and the corresponding reference deformation at each target monitoring point; The single-point errors corresponding to multiple target monitoring points are summed to obtain the candidate measurement error for each candidate flatness.
3. The method for monitoring the deformation of ship pipelines according to claim 2, characterized in that, The calculation of the single-point error between the candidate deformation variable and the corresponding reference deformation variable at each target monitoring point includes: For each target monitoring point, calculate the absolute value of the difference between the candidate deformable variable and the corresponding reference deformable variable at each target monitoring point; Calculate the ratio of the absolute value of the difference to the absolute value of the reference deformation, and determine the ratio as the single-point error at each target monitoring point.
4. The method for monitoring the deformation of ship pipelines according to any one of claims 1 to 3, characterized in that, The step of selecting the target lens flatness from the candidate lens flatnesses based on the candidate measurement error includes: Compare the candidate measurement errors corresponding to the flatness of each candidate lens; The flatness of the candidate lens corresponding to the smallest candidate measurement error is determined as the flatness of the target lens.
5. The method for monitoring the deformation of ship pipelines according to any one of claims 1 to 3, characterized in that, The steps for determining the flatness of candidate lenses include: Obtain the reference flatness range under the preset environment; The reference flatness range is divided according to a preset step size to obtain multiple candidate lens flatnesses; Alternatively, a specified number of candidate lens flatnesses may be randomly generated within the range of the reference flatness.
6. The method for monitoring the deformation of ship pipelines according to any one of claims 1 to 3, characterized in that, The optical sensor includes a structured light surface camera; the contact sensor includes a strain sensor. The deformation monitoring based on the flatness of the target lens includes: Using the flatness of the target lens as an intrinsic parameter of the structured light surface camera, the optical monitoring data is calculated globally to obtain the global deformation of the ship's pipeline.
7. A deformation monitoring device for ship pipelines, characterized in that, include: The acquisition unit acquires optical monitoring data collected by optical sensors and reference deformation at the target monitoring point obtained by contact sensors. The optical monitoring data and the reference deformation are obtained based on monitoring of the same ship's pipelines. The extraction unit extracts the monitoring data to be solved at the target monitoring point from the optical monitoring data; The calculation unit calculates the monitoring data to be calculated based on the flatness of each candidate lens of the optical sensor to obtain the candidate deformation under the flatness of each candidate lens; The error calculation unit calculates the candidate measurement error of the flatness of each candidate lens based on each candidate deformation and the reference deformation, respectively. The optimized monitoring unit selects the target lens flatness from the candidate lens flatness based on the candidate measurement error, and performs deformation monitoring based on the target lens flatness.
8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the deformation monitoring method for ship pipelines as described in any one of claims 1 to 6.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the deformation monitoring method for ship pipelines as described in any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the deformation monitoring method for ship pipelines as described in any one of claims 1 to 6.