A sensor system, pipe deposition assessment method, apparatus and device

Abstract

The present application relates to the technical field of pipeline deposition monitoring, and discloses a sensor system, a pipeline deposition evaluation method, device and equipment. In the method, first, six-axis motion data of the water surface position collected by a first sensor is smoothed to obtain a water surface line trajectory along the pipeline direction; on this basis, six-axis motion data and pressure data of the pipeline bottom collected by a second sensor are fused, and physical baseline data of multiple positions of the pipeline bottom are inversely calculated in combination with the water surface line trajectory to realize quantitative characterization of the actual state of the pipeline bottom; subsequently, the working condition characteristic parameters are jointly input into a trained random forest model, the random forest model is used to quantitatively estimate the deviation of the physical baseline from the non-deposition state, and a residual prediction value of the deposition thickness in the pipeline is obtained; finally, the physical baseline data and the residual prediction value are summed according to the positions to obtain a deposition thickness evaluation result with a clear spatial position, thereby significantly improving the efficiency and accuracy of pipeline deposition detection.

Description

Technical Field

[0001] This invention relates to the field of pipeline deposition monitoring technology, specifically to a sensor system, pipeline deposition assessment method, apparatus, and equipment. Background Technology

[0002] Drainage pipes play a crucial role in urban drainage systems, carrying water through various channels. As these pipes age, sediment inevitably accumulates at their bottoms. This sediment buildup not only reduces the pipe's cross-sectional area and water transport capacity but also accelerates corrosion and can even cause blockages, leading to sewage overflows and flooding. Therefore, accurately assessing the sediment levels within pipes is of paramount importance for the operation, maintenance, and disaster prevention and mitigation of drainage networks.

[0003] Among the pipeline deposition assessment methods disclosed in related technologies is a pipeline condition assessment method that utilizes sensor motion trajectories. This method involves releasing a detection device equipped with a microelectromechanical sensor inside the pipeline and using the microelectromechanical sensor to record multi-dimensional data such as acceleration and angular velocity during the movement process inside the pipeline, thereby determining the state of siltation, damage, etc. inside the pipeline.

[0004] However, the pipeline condition assessment methods disclosed in related technologies are limited by the cumulative error of sensor data, making it difficult to accurately predict the deposition thickness of the sediment layer inside the pipeline, and thus failing to meet the current requirements for refined operation and maintenance management of drainage pipelines. Summary of the Invention

[0005] This invention provides a sensor system, pipeline deposition assessment method, apparatus, and equipment to solve the problem that pipeline condition assessment methods disclosed in related technologies are difficult to accurately predict the deposition thickness of the deposition layer inside the pipeline.

[0006] In a first aspect, the present invention provides a sensor system, the system comprising: At least two pulleys are installed at the inspection wells at both ends of the target pipeline; The flexible track is connected at both ends by two pulleys, and a traction head is fixedly connected to the middle of the flexible track. The traction head is fixedly connected to a plurality of flexible connecting ropes for connecting the first sensor or the second sensor. The first sensor, connected to a flexible connecting rope, is used to collect six-axis motion data of the water surface position inside the target pipe; Multiple second sensors, each connected to a flexible connecting rope, are used to collect six-axis motion data and pressure data at the bottom of the target pipe.

[0007] By adopting the above-described implementation method, a track spanning both ends of the target pipeline is constructed using pulleys and a flexible track. The flexible track drives the traction head to reciprocate along the track, enabling the first and second sensors to move stably from downstream to upstream. This solves the technical problems of underwater robots and other equipment being difficult to move, easily lost, and time-consuming in narrow pipelines. The traction head simultaneously suspends the first sensor and multiple second sensors via a flexible connecting rope, synchronously collecting data on the water surface and bottom of the target pipeline. This provides a time-aligned data basis for subsequent cross-validation. Furthermore, the parallel layout of multiple second sensors allows for the acquisition of multiple trajectory data in a single operation, facilitating subsequent trajectory fusion and anomaly removal. The system can operate with water without pumping out sewage, and the traction speed is controllable, significantly improving the convenience and efficiency of pipeline inspection.

[0008] Secondly, the present invention provides a method for evaluating pipeline deposition, the method comprising: Based on the first sensing data collected inside the target pipeline, a smoothing method is used to obtain the water surface trajectory data along the pipeline; the first sensing data includes six-axis motion data of the water surface position inside the pipeline collected by the first sensor; Based on the second sensing data collected inside the target pipeline, combined with the water surface trajectory data, the physical baseline data of multiple positions along the pipeline direction is obtained using the trajectory inverse calculation method; the second sensing data includes six-axis motion data and pressure data at the bottom of the pipeline collected by the second sensor; Based on the physical baseline data at each location at the bottom of the pipeline, and combined with the corresponding operating condition characteristic parameters within the target pipeline, a trained random forest model is used to make predictions to obtain the residual prediction values ​​for the corresponding locations within the pipeline. The operating condition characteristic parameters include Reynolds number, Froude number, dimensionless sediment particle size, and the ratio of physical baseline to water depth. By combining the physical baseline data and the corresponding residual prediction values ​​at each location within the target pipeline, and using the summation method based on the same location, the deposition thickness assessment results at the corresponding locations within the target pipeline are obtained.

[0009] By adopting the above implementation method, firstly, the six-axis motion data of the water surface position collected by the first sensor is smoothed to obtain the water surface trajectory along the pipeline. On this basis, the six-axis motion data and pressure data of the bottom of the pipeline collected by the second sensor are fused together, and the physical baseline data of multiple positions at the bottom of the pipeline are calculated by combining the water surface trajectory, so as to realize the quantitative characterization of the actual state of the bottom of the pipeline. Then, the operating condition characteristic parameters are input into the trained random forest model, and the random forest model is used to quantitatively estimate the deviation of the physical baseline from the non-deposition state, and obtain the residual prediction value of the deposition thickness in the pipeline. Finally, the physical baseline data and the residual prediction value are summed according to the position to obtain the deposition thickness assessment result with clear spatial location, which significantly improves the efficiency and accuracy of pipeline deposition detection.

[0010] In one optional implementation, the second sensing data collected within the target pipeline, combined with the water surface trajectory data, is used to obtain physical baseline data for multiple locations along the pipeline's direction using a trajectory inverse calculation method, including: Based on the six-axis motion data of the bottom position of the pipe collected by multiple second sensors, coordinate transformation is performed using coordinate transformation methods to obtain the acceleration data and angular velocity data of each second sensor in the global coordinate system; Based on the acceleration data of each second sensor in the global coordinate system, the original motion trajectory of each second sensor is obtained by using the quadratic integration method. Based on the pressure data of each second sensor, combined with the water surface trajectory data, the real-time water depth at the location of the corresponding second sensor is calculated using the water depth conversion method and corrected accordingly, so as to obtain the corrected motion trajectory data of each second sensor. By combining the motion trajectory data corrected by multiple second sensors, a trajectory fusion method is used to obtain physical baseline data for multiple locations along the pipeline.

[0011] By adopting the above implementation method, the six-axis motion data collected by each second sensor is first converted into acceleration and angular velocity data in the global coordinate system through coordinate transformation, eliminating the influence of sensor attitude changes on motion information; then, the acceleration data is integrated twice to obtain the original motion trajectory of each sensor, and the real-time water depth is calculated and corrected using pressure data combined with the water surface trajectory, with the water surface line used as an absolute elevation reference to constrain the integral drift; finally, the corrected motion trajectories of multiple sensors are fused to obtain physical baseline data for multiple locations along the pipeline, improving the accuracy and reliability of the physical baseline data.

[0012] In one optional implementation, the motion trajectory data corrected by multiple second sensors is integrated using a trajectory fusion method to obtain physical baseline data for multiple locations along the pipeline, including: By combining the corrected motion trajectory data from multiple second sensors at the same location, outlier data removal methods are used to remove abnormal data with deviations exceeding a preset threshold, thus obtaining the filtered valid trajectory data. Based on the filtered valid trajectory data, the moving average method is used to smooth the data along the pipeline route, resulting in physical baseline data for multiple locations along the pipeline route.

[0013] By adopting the above implementation method, for the corrected motion trajectory data of multiple second sensors at the same location, firstly, outlier data removal method is used to screen out abnormal data with deviations exceeding a preset threshold, effectively eliminating isolated outliers introduced by the sensors due to factors such as local slippage, signal abrupt changes, or poor contact, and improving the reliability of fused data; then, based on the screened effective trajectory data, the moving average method is used to smooth the data along the pipeline direction, further suppressing random fluctuations caused by the inherent noise and residual integral error of different second sensors, making the physical baseline data continuous and stable along the pipeline direction, and providing a continuous and reliable position reference for subsequent deposition assessment.

[0014] In one optional implementation, the step of obtaining water surface trajectory data along the pipe direction based on the first sensing data collected within the target pipe using a smoothing method includes: Based on the six-axis motion data collected at multiple moments during the movement of the first sensor along the target pipeline, the position data of the first sensor at each moment is obtained by using the time series analysis method. Based on the first sensor position data corresponding to each time moment, the position coordinates in the global coordinate system at each time moment are obtained by using the coordinate transformation method; Based on the position coordinates in the global coordinate system at each moment, the water surface trajectory data along the pipeline direction is obtained using a time-series smoothing method.

[0015] By adopting the above implementation method, firstly, the six-axis motion data collected by the first sensor during its movement within the pipeline is used to extract the position data corresponding to each moment using a time-series analysis method, converting the sensor's time-series motion information into spatial position information; then, a coordinate transformation method is used to unify the position coordinates at each moment to a global coordinate system, eliminating the influence of the first sensor's attitude changes and local coordinate offsets, making the trajectory data spatially comparable; finally, a time-series smoothing method is used to smooth the global coordinate sequence, suppressing trajectory fluctuations caused by noise and integral drift from the first sensor, obtaining continuous and stable water surface trajectory data along the pipeline's direction, providing a reliable geometric reference benchmark for subsequent back-calculation of the physical baseline at the bottom of the pipeline.

[0016] In one optional implementation, the step of using a trained random forest model to predict the residual prediction value at each location within the pipe, based on the physical baseline data at each position at the bottom of the pipe and combined with the corresponding operating condition characteristic parameters within the target pipe, includes: Based on the physical baseline data at each location at the bottom of the pipeline, combined with the water depth data at the corresponding location, the ratio of the physical baseline to the water depth at the corresponding location is obtained using the ratio calculation method of physical baseline to water depth. Based on the ratio of physical baseline to water depth at each location, and combined with the Reynolds number, Froude number, and dimensionless sediment particle size at the corresponding location within the pipe, input feature vectors for the corresponding locations are constructed respectively. Based on the input feature vector at each location, the trained random forest model is used to make predictions to obtain the residual prediction value at the corresponding location.

[0017] By adopting the above implementation method, firstly, based on the physical baseline data at each location at the bottom of the pipeline and combined with the water depth data at the corresponding location, the ratio of the physical baseline to the water depth is calculated to achieve dimensionless physical baseline data, eliminate differences in factors such as pipeline burial depth, and make the physical baseline data at different locations comparable in sedimentation assessment. Then, an input feature vector is constructed using this ratio, Reynolds number, Froude number, and dimensionless sedimentary grain size to ensure that the random forest model can comprehensively judge the degree of sedimentation from multiple dimensions such as hydrodynamic conditions, flow state, sediment characteristics, and spatial morphology. Finally, the trained random forest model is used to predict the input feature vector at each location and output the residual prediction value at the corresponding location, capturing the complex nonlinear relationship between multi-condition characteristics and sediment thickness, facilitating sedimentation identification based on data-driven quantitative prediction, and overcoming the limitations of using a single threshold for judgment.

[0018] In one alternative implementation, training the random forest model includes: Acquire multiple sets of physical baseline data and corresponding measured deposition thickness data at various locations along the pipeline under multiple deposition thickness scenarios; Based on the difference between the physical baseline data and the measured deposition thickness data at each location, the residual data at the corresponding location is obtained, and a residual data sequence at the corresponding location along the pipeline direction is constructed. The residual data at each location is used as the output feature, and the corresponding working condition feature parameters are used as the input feature. The random forest algorithm is used for training to obtain the trained random forest model.

[0019] By adopting the above implementation method, firstly, physical baseline data and corresponding measured deposition thickness data at various locations along the pipeline under multiple deposition thickness scenarios are acquired, providing multi-sample support for the training of the random forest model; then, the difference between the physical baseline and the measured deposition thickness is used as residual data to transform the deposition thickness information into a residual data sequence, so that the model training objective is directly aligned with the deposition assessment task; finally, the random forest model is trained with the residual data as output and the operating condition feature parameters as input, thereby establishing a mapping relationship between operating conditions and deposition degree, enabling the trained model to output residual prediction values ​​based on online input features, providing a reliable data-driven basis for quantitative assessment of deposition thickness, and ensuring the applicability and prediction reliability of the random forest model in pipeline deposition assessment scenarios.

[0020] Thirdly, the present invention provides a pipeline deposition assessment device, the device comprising: The first processing module is used to obtain water surface trajectory data inside the pipe based on the first sensing data collected inside the target pipe using a smoothing processing method; the first sensing data includes six-axis motion data of the water surface position inside the pipe collected by a floating sensor; The second processing module is used to obtain physical baseline data at multiple locations at the bottom of the pipe based on the second sensing data collected inside the target pipe and the water surface trajectory data, using a trajectory inverse calculation method; the second sensing data includes six-axis motion data and pressure data at the bottom of the pipe collected by a sliding sensor. The residual prediction module is used to predict the residual values ​​at each position in the pipeline based on the physical baseline data at each position at the bottom of the pipeline and the corresponding operating condition characteristic parameters in the target pipeline, using a trained random forest model. The operating condition characteristic parameters include Reynolds number, Froude number, dimensionless sediment particle size, and the ratio of physical baseline to water depth. The results output module integrates the physical baseline data and corresponding residual prediction values ​​at each location within the target pipeline, and uses a summation method based on the same location to obtain the deposition thickness assessment results at the corresponding location within the target pipeline.

[0021] Fourthly, the present invention provides an electronic device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the pipeline deposition evaluation method of the first aspect or any corresponding embodiment described above.

[0022] Fifthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the pipeline deposition assessment method of the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0023] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the structure of a sensor system according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first process of the pipeline deposition assessment method according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the second process of the pipeline deposition assessment method according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the third process of the pipeline deposition assessment method according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the fourth process of the pipeline deposition assessment method according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the fifth process of the pipeline deposition assessment method according to an embodiment of the present invention; Figure 7 This is a deposition profile of a pipeline generated by the pipeline deposition assessment method according to an embodiment of the present invention. Figure 8 This is a structural block diagram of a pipeline deposition assessment device according to an embodiment of the present invention; Figure 9 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention.

[0025] Explanation of reference numerals in the attached drawings: 11. Pulley; 12. Flexible track; 121. Traction head; 122. Flexible connecting rope; 13. First sensor; 14. Second sensor; 15. Winder. Detailed Implementation

[0026] 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 embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0028] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0029] The pipeline deposition assessment methods disclosed in related technologies include: 1. A pipeline condition assessment method based on sensor motion trajectory: By releasing a detection device equipped with a microelectromechanical sensor inside the pipeline, the microelectromechanical sensor records multi-dimensional data such as acceleration and angular velocity during the movement process inside the pipeline, thereby determining the condition of the pipeline, such as siltation and damage.

[0030] 2. A physical model-based sediment simulation method simulates the transport and deposition process of sediments within a pipe by constructing physical equations of sediment movement.

[0031] However, the pipeline sedimentation status assessment methods disclosed in related technologies are mainly aimed at stormwater pipelines. The sediment source of stormwater pipelines is mainly surface runoff, which does not involve long-term sediment input scenarios. Therefore, they cannot be directly applied to sediment assessment of sewage systems. Furthermore, it is difficult to obtain sediment input conditions for sewage systems, which depends on monitoring sewage discharge patterns. However, the cost of related monitoring equipment is high and the operation and maintenance requirements are large, making it difficult to meet the current demand for precise monitoring of drainage pipelines.

[0032] To overcome the shortcomings of existing pipeline deposition assessment methods, this invention provides a pipeline deposition assessment method. First, six-axis motion data of the water surface position collected by a first sensor is smoothed to obtain the water surface trajectory along the pipeline. Then, six-axis motion data and pressure data of the pipeline bottom collected by a second sensor are fused together with the water surface trajectory to calculate physical baseline data for multiple locations at the pipeline bottom, thus quantitatively representing the actual state of the pipeline bottom. Subsequently, these data, along with operating condition characteristic parameters, are input into a trained random forest model. The random forest model quantitatively estimates the deviation of the physical baseline from the non-depositional state and obtains the residual prediction value of the deposition thickness within the pipeline. Finally, the physical baseline data and the residual prediction value are summed according to location to obtain a spatially defined deposition thickness assessment result, significantly improving the efficiency and accuracy of pipeline deposition detection.

[0033] First, this embodiment of the invention provides a sensor system for collecting first and second sensing data of a target pipeline, thereby facilitating subsequent pipeline deposition assessment methods. The system provided in this embodiment includes: At least two pulleys 11 are installed at the inspection wells at both ends of the target pipeline; The flexible track 12 is sequentially wound around and passes through two pulleys 11, and a traction head 121 is fixedly connected to the middle of the flexible track 12. The traction head 121 is fixedly connected to a plurality of flexible connecting ropes 122 for connecting the first sensor 13 or the second sensor 14. The first sensor 13 is connected to a flexible connecting rope 122 and is used to collect six-axis motion data of the water surface position inside the target pipe. Multiple second sensors 14 are each connected to a flexible connecting rope 122 to collect six-axis motion data and pressure data at the bottom of the target pipe.

[0034] The pulley 11 is connected to the manholes at both ends of the target pipeline via manhole fixers.

[0035] The flexible track 12 can be implemented as a lightweight track rope, which is used to connect a floating object carrying a small propeller to one end, thereby driving the flexible track 12 from the upstream of the target pipe through the target pipe to the downstream. If the water flow velocity in the target pipe is low, the small propeller is activated to assist the flexible track 12 in passing through the target pipe. The end of the flexible track 12 passes through the pulley 11 installed in the inspection well and extends to the outside of the inspection well.

[0036] The traction head 121 is connected to the middle of the flexible track 12 by binding and fixing. Meanwhile, there can be 5 flexible connecting ropes 122, one of which is used to connect to the first sensor 13, and the other 4 flexible connecting ropes 122 are used to connect to a second sensor 14 respectively.

[0037] The first sensor 13 can be implemented as a floating sensor with a density less than water, which has a built-in micro-motor chip, lithium battery, memory card and plastic shell, and is used to move along the water flow in the pipe under the traction of the flexible connecting rope 122.

[0038] The second sensor 14 can be implemented as a sliding sensor with a density greater than that of water. It has a built-in micro-motor chip, lithium battery, memory card, counterweight, pressure sensor and plastic shell, and is used to slide along the bottom of the pipe under the traction of the flexible connecting rope 122. In this embodiment, four second sensors 14 are provided.

[0039] In this embodiment, a winder 15 is also provided at the end of the flexible track 12, which is used to drive the flexible track 12 to move at a constant speed by rotating itself, thereby ensuring the uniformity of the acquired first sensing data and second sensing data.

[0040] In the sensor system provided by this invention, a track spanning both ends of the target pipeline is constructed using pulleys 11 and flexible track 12. The flexible track 12 drives the traction head 121 to reciprocate along the flexible track 12, enabling the first sensor 13 and the second sensor 14 to move stably from downstream to upstream. This solves the technical problems of underwater robots and other equipment being difficult to move, easily lost, and time-consuming in narrow pipelines. The traction head 121 simultaneously suspends the first sensor 13 and multiple second sensors 14 through a flexible connecting rope 122, synchronously collecting data on the water surface and bottom of the target pipeline. This provides a time-aligned data basis for subsequent cross-validation. At the same time, the parallel layout of multiple second sensors 14 can acquire multiple trajectory data in a single operation, facilitating subsequent trajectory fusion and anomaly removal. It can operate with water without pumping sewage, and the traction speed is controllable, significantly improving the convenience and efficiency of pipeline inspection.

[0041] According to an embodiment of the present invention, a method for evaluating pipeline deposition is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0042] This embodiment provides a pipeline deposition assessment method, which can be used in pipeline monitoring server terminals. Figure 2 This is a flowchart of a pipeline deposition assessment method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: S201, based on the first sensing data collected inside the target pipe, a smoothing method is used to obtain the water surface trajectory data along the pipe direction; the first sensing data includes six-axis motion data of the water surface position inside the pipe collected by the first sensor.

[0043] The first sensing data refers to the six-axis motion data of the water surface position inside the pipe collected by the first sensor. It can be implemented by using a reel to drive a lightweight rope between two adjacent pipe wells, and then pulling the three-axis acceleration and three-axis angular velocity of the water surface position inside the pipe collected by the floating sensor, which is used to calculate the motion trajectory of the first sensor on the water surface.

[0044] The first sensor can be implemented as a floating sensor, specifically a spherical sensor with a density less than water, with a built-in microelectromechanical chip, battery, memory card, or wireless communication device for monitoring six-axis motion data.

[0045] Six-axis motion data refers to three-axis acceleration data and three-axis angular velocity data collected using a microelectromechanical chip, which can be used to inversely calculate the spatial motion trajectory of the sensor through coordinate transformation and quadratic integration.

[0046] Smoothing is a method of applying a moving average to the raw position trajectory data collected by the sensor along the pipeline to eliminate random noise during the data acquisition process.

[0047] Water surface trajectory data is a smoothed water surface position trajectory that is continuously distributed along the pipeline direction, used to reflect the spatial morphology of the water flow surface inside the pipeline.

[0048] By using the first sensor to acquire the water surface position trajectory and smoothing it, water surface line data is obtained, which can be used to construct the vertical constraint boundary for the subsequent constraint of the motion trajectory of the second sensor. This can effectively suppress the cumulative drift error generated by inertial navigation integration, and at the same time provide a reference benchmark for cross-validation of water depth data from the pressure sensor.

[0049] S202, based on the second sensor data collected inside the target pipeline and combined with the water surface trajectory data, the physical baseline data of multiple positions along the pipeline direction is obtained by using the trajectory inverse calculation method; the second sensor data includes six-axis motion data and pressure data of the bottom position of the pipeline collected by the second sensor.

[0050] The second sensing data refers to the six-axis motion data and pressure data at the bottom of the pipe collected using the second sensor.

[0051] The second sensor is a spherical sensor with a density slightly greater than that of water. It can slide along the bottom of the pipe or the surface of the sediment. It has a built-in microelectromechanical chip, battery, pressure sensor, counterweight, memory card or wireless communication device to monitor six-axis motion data. The second sensor can be implemented as a sliding sensor. Multiple second sensors are set up and the multiple sliding sensors are flexibly connected by lightweight ropes.

[0052] Pressure data refers to the real-time water pressure value collected by the pressure sensor built into the second sensor, which can be converted into the real-time water depth at the location of the second sensor through a water depth conversion method.

[0053] The trajectory inverse calculation method refers to using the six-axis motion data of each second sensor, transforming the data in the local coordinate system of the sensor to the global coordinate system through coordinate transformation, and then performing a second integration on the acceleration data to obtain the motion trajectory; at the same time, the real-time water depth and water surface trajectory data converted from pressure data are used as vertical constraints to correct the trajectory.

[0054] The physical baseline data is the trajectory line at each position along the pipe bottom after trajectory back calculation and smoothing. It is used to represent the curve of the actual height of the sensor at the bottom of the pipe or the surface of the deposit as a function of the pipe direction during operation. It serves as the benchmark reference line for subsequent residual prediction and deposition thickness calculation.

[0055] Multiple locations refer to multiple spatial location points that are continuously distributed along the pipeline route. Each location corresponds to a set of physical baseline data, which are used to form a continuous data sequence along the pipeline route.

[0056] By combining the six-axis motion data of the bottom of the pipe collected by the second sensor with the pressure data, and using the water surface trajectory data as a vertical constraint to perform trajectory back calculation, physical baseline data is obtained. Multiple second sensors collect the trajectories of the bottom of multiple pipes in parallel. Data robustness is improved through data filtering and smoothing. Using the water surface trajectory data as a constraint effectively reduces the impact of integral drift on trajectory accuracy.

[0057] S203, based on the physical baseline data at each location at the bottom of the pipeline, combined with the corresponding operating condition characteristic parameters within the target pipeline, uses a trained random forest model to make predictions and obtain the residual prediction values ​​for the corresponding locations within the pipeline; the operating condition characteristic parameters include Reynolds number, Froude number, dimensionless sediment particle size, and the ratio of physical baseline to water depth.

[0058] Operating condition characteristic parameters refer to physical characteristic quantities used to describe the state of water and solid two-phase flow in the pipeline. They are used as input features for the random forest model to give the residual prediction physical constraints. These include the Reynolds number, which reflects the ratio of water flow inertial force to viscous force; the Froude number, which reflects the ratio of water flow inertial force to gravity; the dimensionless sediment particle size, which is a dimensionless parameter representing the particle size of sediments; and the ratio of the physical baseline to the water depth, which reflects the relative position of the sensor in the pipeline cross-section.

[0059] The trained random forest model refers to a random forest model pre-trained based on bench test data. The difference between the physical baseline data during training and the measured deposition thickness is used as the output label, and the corresponding working condition feature parameters are used as the input features. The random forest model makes predictions by constructing multiple decision trees and integrating the prediction results of each decision tree.

[0060] The residual prediction value refers to the predicted residual value at the corresponding location output by the random forest model, which is the difference between the physical baseline and the actual deposition thickness.

[0061] By using the characteristic parameters of the working conditions as input parameters for the trained random forest model, the random forest model is used to predict the residual between the physical baseline and the actual deposition thickness, ensuring that the data-driven prediction is constrained by the laws of hydrodynamics and improving the interpretability and accuracy of the residual prediction.

[0062] S204. By combining the physical baseline data and the corresponding residual prediction values ​​at each location within the target pipeline, and using the summation method based on the same location, the deposition thickness assessment results at the corresponding locations within the target pipeline are obtained.

[0063] The summation method at the same location involves adding the physical baseline data at each location along the pipeline route to the corresponding residual prediction value.

[0064] The deposition thickness assessment result refers to the final output of the deposition thickness value at each location along the pipeline.

[0065] By summing the physical baselines at each location with the corresponding residual predictions, the deposition thickness assessment results are obtained, upgrading the deposition assessment from qualitative judgment to quantitative prediction. The output continuous deposition profile provides specific quantitative basis for pipeline operation and maintenance.

[0066] This embodiment provides a pipeline deposition assessment method. First, six-axis motion data of the water surface position collected by a first sensor is smoothed to obtain the water surface trajectory along the pipeline. Then, six-axis motion data and pressure data of the pipeline bottom collected by a second sensor are fused together with the water surface trajectory to calculate physical baseline data for multiple locations at the pipeline bottom, thus quantitatively representing the actual state of the pipeline bottom. Subsequently, operating condition characteristic parameters are input into a trained random forest model. The random forest model quantitatively estimates the deviation of the physical baseline from the non-deposition state and obtains the residual prediction value of the deposition thickness within the pipeline. Finally, the physical baseline data and the residual prediction value are summed according to location to obtain a spatially defined deposition thickness assessment result, significantly improving the efficiency and accuracy of pipeline deposition detection.

[0067] This embodiment provides a pipeline deposition assessment method, which can be used in pipeline monitoring server terminals. Figure 3 This is a flowchart of a pipeline deposition assessment method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps: S301, based on the first sensing data collected inside the target pipe, a smoothing method is used to obtain the water surface trajectory data along the pipe direction; the first sensing data includes six-axis motion data of the water surface position inside the pipe collected by the first sensor.

[0068] Specifically, S301 includes: S3011, based on the six-axis motion data collected by the first sensor at multiple moments during its movement along the target pipeline, the position data of the first sensor at each moment is obtained using a time-series analysis method.

[0069] The temporal analysis method refers to the method of analyzing the six-axis motion data continuously collected by the sensor in the time dimension in chronological order. This includes integrating the acceleration data over time to obtain the velocity, integrating the velocity again to obtain the displacement, thereby obtaining the spatial position information corresponding to each moment.

[0070] S3012, based on the position data of the first sensor at each time moment, uses a coordinate transformation method to obtain the position coordinates in the global coordinate system at each time moment.

[0071] Coordinate transformation refers to the mathematical method of converting the position and orientation data of a sensor in its local coordinate system to a global coordinate system. Since the sensor's attitude constantly changes during movement, the collected data is based on a local coordinate system with the sensor's own orientation. It is necessary to determine the real-time attitude angle using angular velocity data, and then use a rotation matrix to transform the local coordinates to a global coordinate system with the pipe as a reference.

[0072] The global coordinate system is a three-dimensional spatial coordinate system established with the target pipeline as a reference, using the pipeline direction as the X-axis, the horizontal direction of the pipeline cross-section as the Y-axis, and the vertical direction as the Z-axis.

[0073] The position coordinates in the global coordinate system refer to the spatial position coordinates in the global coordinate system obtained by transforming the sensor's local coordinate system data. They are the basic data for subsequent trajectory smoothing and modeling analysis.

[0074] S3013, based on the position coordinates in the global coordinate system at each moment, uses a time-series smoothing method to obtain the water surface trajectory data along the pipeline.

[0075] Time-series smoothing methods refer to methods that perform moving average or filtering on position coordinate data along a time series. These methods are used to eliminate random fluctuations caused by factors such as sensor noise, vibration, and water flow fluctuations during data acquisition, making the water surface trajectory curve smoother and reflecting the true water surface morphology.

[0076] Along the pipeline direction refers to the direction along the axis of the target pipeline, used to indicate that the trajectory of the water surface changes continuously along the length of the pipeline.

[0077] Water surface trajectory data refers to the spatial position data of the water surface at each position along the pipeline after coordinate transformation and time-series smoothing. It is used to reflect the shape of the water flow surface inside the pipeline and is an important vertical constraint boundary for subsequent back-calculation of the bottom sensor trajectory.

[0078] First, using the six-axis motion data collected by the first sensor during its movement within the pipeline, position data at each moment is extracted using a time-series analysis method, converting the sensor's time-series motion information into spatial position information. Then, a coordinate transformation method is used to unify the position coordinates at each moment into a global coordinate system, eliminating the influence of the first sensor's attitude changes and local coordinate offsets, thus making the trajectory data spatially comparable. Finally, a time-series smoothing method is used to smooth the global coordinate sequence, suppressing trajectory fluctuations caused by noise from the first sensor and integral drift, obtaining continuous and stable water surface trajectory data along the pipeline's direction, providing a reliable geometric reference benchmark for subsequent back-calculation of the physical baseline at the bottom of the pipeline.

[0079] S302, based on the second sensor data collected inside the target pipeline and combined with the water surface trajectory data, uses a trajectory inverse calculation method to obtain physical baseline data for multiple locations along the pipeline's direction; the second sensor data includes six-axis motion data and pressure data at the bottom of the pipeline collected by the second sensor. For details, please refer to [link to details]. Figure 2 S202 of the illustrated embodiment will not be described again here.

[0080] S303, based on the physical baseline data at each location at the bottom of the pipe, combined with the corresponding operational characteristic parameters within the target pipe, uses a trained random forest model to predict the residual prediction values ​​for the corresponding locations within the pipe. The operational characteristic parameters include Reynolds number, Froude number, dimensionless sedimentary grain size, and the ratio of physical baseline to water depth. For details, please refer to [link to relevant documentation]. Figure 2 S203 of the illustrated embodiment will not be described again here.

[0081] S304, combining the physical baseline data and corresponding residual predictions at each location within the target pipeline, and using a summation method based on the same location, yields the deposition thickness assessment result at the corresponding location within the target pipeline. For details, please refer to [link to relevant documentation]. Figure 2 S204 of the illustrated embodiment will not be described again here.

[0082] This embodiment provides a pipeline deposition assessment method, which can be used in pipeline monitoring server terminals. Figure 4 This is a flowchart of a pipeline deposition assessment method according to an embodiment of the present invention, such as... Figure 4 As shown, the process includes the following steps: S401, based on the first sensor data collected inside the target pipe, a smoothing method is used to obtain the water surface trajectory data along the pipe's direction; the first sensor data includes six-axis motion data of the water surface position inside the pipe collected by the first sensor. For details, please refer to [link to details]. Figure 2 S201 of the illustrated embodiment will not be described again here.

[0083] S402, based on the second sensor data collected inside the target pipeline and combined with the water surface trajectory data, the physical baseline data of multiple positions along the pipeline direction is obtained by using the trajectory inverse calculation method; the second sensor data includes six-axis motion data and pressure data of the bottom position of the pipeline collected by the second sensor.

[0084] Specifically, S402 above includes: S4021, based on the six-axis motion data of the bottom position of the pipe collected by multiple second sensors, coordinate transformation is performed using coordinate transformation methods to obtain the acceleration data and angular velocity data of each second sensor in the global coordinate system; S4022, Based on the acceleration data of each second sensor in the global coordinate system, the original motion trajectory of each second sensor is obtained by using the quadratic integration method; S4023, Based on the pressure data of each second sensor and combined with the water surface trajectory data, the real-time water depth at the location of the corresponding second sensor is calculated using the water depth conversion method and corrected to obtain the corrected motion trajectory data of each second sensor. S4024 integrates the motion trajectory data corrected by multiple second sensors and uses a trajectory fusion method to obtain physical baseline data for multiple locations along the pipeline.

[0085] Specifically, S4024 above includes: a1 integrates the corrected motion trajectory data from multiple second sensors at the same location, and uses an outlier removal method to remove abnormal data with deviations exceeding a preset threshold, thus obtaining the filtered valid trajectory data.

[0086] Outlier removal methods refer to methods that identify and remove data sets that deviate significantly from the normal trajectory from the trajectory data of multiple pipelines collected by multiple second sensors, which are generated by abnormal situations such as sensor jamming, collision, overturning or data drift, thereby ensuring the quality of subsequent physical baseline data.

[0087] Reference Figure 5 , Figure 5 The trajectory projection of second sensing data collected by multiple second sensors in a certain pipeline onto the ZOX plane. Figure 5 The waveform of sensor 1 is different from that of sensors 2, 3, and 4. There is a significant lag in the peaks and troughs. As sensors connected in parallel, there should be no significant lag when moving in the same cross section. Therefore, the data from sensor 1 needs to be discarded.

[0088] a2, based on the filtered valid trajectory data, uses the moving average method to smooth the data along the pipeline direction, and obtains physical baseline data for multiple locations along the pipeline direction.

[0089] By analyzing the corrected motion trajectory data from multiple second sensors at the same location, outlier data exceeding a preset threshold is first filtered out using an outlier removal method. This effectively eliminates isolated outliers introduced by the sensors due to factors such as local slippage, signal abrupt changes, or poor contact, thus improving the reliability of the fused data. Then, based on the filtered effective trajectory data, a moving average method is used to smooth the data along the pipeline direction. This further suppresses random fluctuations caused by the inherent noise and residual integral errors of different second sensors, ensuring that the physical baseline data is continuous and stable along the pipeline direction, providing a continuous and reliable positional reference for subsequent deposition assessment.

[0090] First, the six-axis motion data collected by each second sensor is converted into acceleration and angular velocity data in the global coordinate system through coordinate transformation to eliminate the influence of sensor attitude changes on motion information. Then, the acceleration data is integrated twice to obtain the original motion trajectory of each sensor. At the same time, the pressure data is combined with the water surface trajectory to calculate the real-time water depth and perform correction. The water surface line is used as the absolute elevation reference to constrain the integral drift. Finally, the corrected motion trajectories of multiple sensors are fused to obtain physical baseline data at multiple locations along the pipeline, improving the accuracy and reliability of the physical baseline data.

[0091] S403, based on the physical baseline data at each location at the bottom of the pipe, combined with the corresponding operational characteristic parameters within the target pipe, uses a trained random forest model to predict the residual prediction values ​​for the corresponding locations within the pipe. The operational characteristic parameters include Reynolds number, Froude number, dimensionless sediment particle size, and the ratio of physical baseline to water depth. For details, please refer to [link to relevant documentation]. Figure 2 S203 of the illustrated embodiment will not be described again here.

[0092] S404, combining the physical baseline data and corresponding residual predictions at each location within the target pipeline, and using a summation method based on the same location, yields the deposition thickness assessment result at the corresponding location within the target pipeline. For details, please refer to [link to relevant documentation]. Figure 1 S204 of the illustrated embodiment will not be described again here.

[0093] This embodiment provides a pipeline deposition assessment method, which can be used in pipeline monitoring server terminals. Figure 6 This is a flowchart of a pipeline deposition assessment method according to an embodiment of the present invention, such as... Figure 6 As shown, the process includes the following steps: S601, based on the first sensor data collected inside the target pipe, uses a smoothing method to obtain the water surface trajectory data along the pipe's direction; the first sensor data includes six-axis motion data of the water surface position inside the pipe collected by the first sensor. For details, please refer to [link to details]. Figure 2 S201 of the illustrated embodiment will not be described again here.

[0094] S602, based on the second sensor data collected inside the target pipeline and combined with the water surface trajectory data, uses a trajectory inverse calculation method to obtain physical baseline data at multiple locations along the pipeline's direction; the second sensor data includes six-axis motion data and pressure data at the bottom of the pipeline collected by the second sensor. For details, please refer to [link to details]. Figure 2 S202 of the illustrated embodiment will not be described again here.

[0095] S603, based on the physical baseline data at each location at the bottom of the pipeline, combined with the corresponding operating condition characteristic parameters within the target pipeline, uses a trained random forest model to make predictions and obtain the residual prediction values ​​for the corresponding locations within the pipeline; the operating condition characteristic parameters include Reynolds number, Froude number, dimensionless sediment particle size, and the ratio of physical baseline to water depth.

[0096] Specifically, the aforementioned S603 includes: S6031, based on the physical baseline data at each location at the bottom of the pipe, combined with the water depth data at the corresponding location, the ratio of the physical baseline to the water depth at the corresponding location is obtained using the ratio calculation method of physical baseline to water depth. S6032, based on the ratio of physical baseline to water depth at each location, combined with the Reynolds number, Froude number and dimensionless sediment particle size at the corresponding location in the pipe, respectively, constructs the input feature vector for the corresponding location; S6033 uses the trained random forest model to make predictions based on the input feature vector at each position, and obtains the residual prediction value at the corresponding position.

[0097] Specifically, the training of the random forest model in S6033 above includes: b1, acquire multiple sets of physical baseline data and corresponding measured deposition thickness data at various locations along the pipeline under multiple deposition thickness scenarios; b2, based on the difference between the physical baseline data and the measured deposition thickness data at each location, the residual data at the corresponding location is obtained, and a residual data sequence at the corresponding location along the pipeline direction is constructed; b3 uses the residual data at each location as the output feature and the corresponding working condition feature parameters as the input feature, and trains the random forest algorithm to obtain the trained random forest model.

[0098] For example, a trained random forest model includes:

[0099]

[0100] in, This represents the output features of the random forest model; This represents the input features of the random forest model; Indicates the total number of decision trees; Indicates the first The prediction results generated by the decision tree; Indicates the total number of leaf nodes; Indicates the first The residual value corresponding to the leaf; This indicates an indicator function; the value is 1 if the condition within the parentheses is met, and 0 otherwise. Indicates the total number of leaf nodes; Indicates the first The area corresponding to the leaf.

[0101] By acquiring physical baseline data and corresponding measured deposition thickness data at various locations along the pipeline under multiple deposition thickness scenarios, multi-sample support is provided for the training of the random forest model. Then, the difference between the physical baseline and the measured deposition thickness is used as residual data to transform the deposition thickness information into a residual data sequence, directly aligning the model training objective with the deposition assessment task. Finally, the random forest model is trained with the residual data as output and the operating condition feature parameters as input, thereby establishing a mapping relationship between operating conditions and deposition degree. This enables the trained model to output residual prediction values ​​based on online input features, providing a reliable data-driven basis for quantitative deposition thickness assessment and ensuring the applicability and predictive reliability of the random forest model in pipeline deposition assessment scenarios.

[0102] First, based on the physical baseline data at each location at the bottom of the pipeline, combined with the corresponding water depth data, the ratio of the physical baseline to the water depth is calculated. This achieves dimensionless representation of the physical baseline data, eliminating differences caused by factors such as pipeline burial depth, and ensuring comparability of physical baseline data at different locations in sedimentation assessment. Then, an input feature vector is constructed using this ratio, Reynolds number, Froude number, and dimensionless sedimentary grain size. This ensures that the random forest model can comprehensively judge the degree of sedimentation from multiple dimensions, including hydrodynamic conditions, flow state, sediment characteristics, and spatial morphology. Finally, the trained random forest model is used to predict the input feature vector at each location, outputting the corresponding residual prediction value. This captures the complex nonlinear relationship between multi-condition characteristics and sediment thickness, facilitating sedimentation identification based on data-driven quantitative prediction and overcoming the limitations of using a single threshold for judgment.

[0103] S604, combining the physical baseline data and corresponding residual predictions at each location within the target pipeline, and using a summation method based on the same location, yields the deposition thickness assessment result at the corresponding location within the target pipeline. For details, please refer to [link to relevant documentation]. Figure 1 S204 of the illustrated embodiment will not be described again here.

[0104] In some optional implementations, the method provided in this embodiment further includes: S605, by combining the assessment results of the deposition thickness at each location within the target pipeline with the water surface trajectory data, a deposition profile map of the target pipeline is generated; the deposition profile map is used to display the water surface line, deposition thickness line and pipeline bottom reference line along the pipeline route.

[0105] Reference Figure 7 As shown, Figure 7 This represents a sedimentation profile of a pipeline generated by the pipeline sedimentation assessment method according to an embodiment of the present invention. Based on the sedimentation thickness assessment results at each location and the water surface trajectory data, a sedimentation profile along the pipeline direction is generated. The water surface line reflects the spatial distribution of the free surface of water flow inside the pipe, the pipeline bottom reference line reflects the original pipe bottom position in the absence of sedimentation, and the sedimentation thickness line visually indicates the spatial distribution and thickness variation of sediments. The constructed sedimentation profile provides an intuitive and quantifiable visualization basis for pipeline maintenance decisions, facilitating maintenance personnel to quickly locate severely sedimented sections and assess dredging needs.

[0106] This embodiment also provides a pipeline deposition assessment device for implementing the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0107] This embodiment provides a pipeline deposition assessment device, such as... Figure 8 As shown, it includes: The first processing module 810 is used to obtain water surface trajectory data inside the pipe based on the first sensing data collected inside the target pipe using a smoothing processing method; the first sensing data includes six-axis motion data of the water surface position inside the pipe collected by a floating sensor. The second processing module 820 is used to obtain physical baseline data at multiple positions at the bottom of the pipe based on the second sensing data collected inside the target pipe and the water surface trajectory data, using a trajectory inverse calculation method; the second sensing data includes six-axis motion data and pressure data at the bottom position inside the pipe collected by a sliding sensor; The residual prediction module 830 is used to predict the residual prediction value of the corresponding position in the pipeline based on the physical baseline data at each position at the bottom of the pipeline and the corresponding operating condition characteristic parameters in the target pipeline, using the trained random forest model. The operating condition characteristic parameters include Reynolds number, Froude number, dimensionless sediment particle size, and the ratio of physical baseline to water depth. The result output module 840 is used to integrate the physical baseline data and the corresponding residual prediction value at each location within the target pipeline, and obtain the deposition thickness assessment result at the corresponding location within the target pipeline by using the summation method based on the same location.

[0108] In some alternative implementations, the first processing module 810 includes: The timing analysis unit is used to obtain the position data of the first sensor at each moment based on the six-axis motion data collected by the first sensor at multiple moments during its movement along the target pipeline using the timing analysis method. The coordinate transformation unit is used to obtain the position coordinates in the global coordinate system at each time based on the first sensor position data corresponding to each time moment using the coordinate transformation method; The temporal smoothing unit is used to obtain water surface trajectory data along the pipeline direction based on the position coordinates in the global coordinate system at each time point using the temporal smoothing method.

[0109] In some alternative implementations, the second processing module 820 includes: The coordinate transformation unit is used to perform coordinate transformation based on the six-axis motion data of the bottom position of the pipe collected by multiple second sensors, and obtain the acceleration data and angular velocity data of each second sensor in the global coordinate system. The trajectory conversion unit is used to obtain the original motion trajectory of each second sensor based on the acceleration data of each second sensor in the global coordinate system using the quadratic integration method. The data correction unit is used to calculate and correct the real-time water depth at the location of the corresponding second sensor based on the pressure data of each second sensor and the water surface trajectory data, using the water depth conversion method, so as to obtain the corrected motion trajectory data of each second sensor. The trajectory fusion unit is used to integrate the motion trajectory data corrected by multiple second sensors and obtain the physical baseline data of multiple positions along the pipeline using the trajectory fusion method.

[0110] In some alternative implementations, the trajectory fusion unit is specifically used for: By combining the corrected motion trajectory data from multiple second sensors at the same location, outlier data removal methods are used to remove abnormal data with deviations exceeding a preset threshold, thus obtaining the filtered valid trajectory data. Based on the filtered valid trajectory data, the moving average method is used to smooth the data along the pipeline route, resulting in physical baseline data for multiple locations along the pipeline route.

[0111] In some alternative implementations, the residual prediction module 830 includes: The parameter acquisition unit is used to obtain the ratio of the physical baseline to the water depth at each location on the bottom of the pipe, based on the physical baseline data and the water depth data at the corresponding location, using the ratio calculation method of physical baseline to water depth. The input building unit is used to construct the corresponding input feature vector based on the ratio of physical baseline to water depth at each location, combined with the Reynolds number, Froude number and dimensionless sediment particle size at the corresponding location in the pipe. The residual prediction unit is used to make predictions based on the input feature vector at each location using the trained random forest model, and obtain the residual prediction value at the corresponding location.

[0112] In some alternative implementations, it also includes: The model training unit is specifically used to acquire multiple sets of physical baseline data and corresponding measured deposition thickness data at various locations along the pipeline under multiple deposition thickness scenarios. Based on the difference between the physical baseline data and the measured deposition thickness data at each location, the residual data at the corresponding location is obtained, and a residual data sequence at the corresponding location along the pipeline direction is constructed. The residual data at each location is used as the output feature, and the corresponding working condition feature parameters are used as the input feature. The random forest algorithm is used for training to obtain the trained random forest model.

[0113] The pipeline deposition assessment device provided in this embodiment of the invention can execute the pipeline deposition assessment method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units described above are the same as in the corresponding embodiments described above, and will not be repeated here.

[0114] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0115] The following is a detailed reference. Figure 9 This diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 901, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 902 or a program loaded from memory 908 into random access memory (RAM) 903. The RAM 903 also stores various programs and data required for the operation of the electronic device. The processor 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0116] Typically, the following devices can be connected to I / O interface 905: input devices 906 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 907 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 908 including, for example, magnetic tapes, hard disks, etc.; and communication devices 909. Communication device 909 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 9 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0117] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 909, or installed from a memory 908, or installed from a ROM 902. When the computer program is executed by the processor 901, it performs the functions defined in the pipeline deposition evaluation method of the embodiments of the present invention.

[0118] Figure 9 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0119] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the pipeline deposition evaluation method shown in the above embodiments is implemented.

[0120] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0121] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A sensor system, characterized in that, The system includes: At least two pulleys (11) are installed at the inspection wells at both ends of the target pipeline; The flexible track (12) is connected at both ends by two pulleys (11), and a traction head (121) is fixedly connected to the middle of the flexible track (12). The traction head (121) is fixedly connected to a plurality of flexible connecting ropes (122) for connecting the first sensor (13) or the second sensor (14). The first sensor (13) is connected to a flexible connecting rope (122) for collecting six-axis motion data of the water surface position inside the target pipe; Multiple second sensors (14) are connected to a flexible connecting rope (122) to collect six-axis motion data and pressure data at the bottom of the target pipe.

2. A method for assessing pipeline deposition, characterized in that, The method using the sensor system as described in claim 1 includes: Based on the first sensing data collected inside the target pipeline, a smoothing method is used to obtain the water surface trajectory data along the pipeline; the first sensing data includes six-axis motion data of the water surface position inside the pipeline collected by the first sensor; Based on the second sensing data collected inside the target pipeline, combined with the water surface trajectory data, the physical baseline data of multiple positions along the pipeline direction is obtained using the trajectory inverse calculation method; the second sensing data includes six-axis motion data and pressure data at the bottom of the pipeline collected by the second sensor; Based on the physical baseline data at each location at the bottom of the pipeline, and combined with the corresponding operating condition characteristic parameters within the target pipeline, a trained random forest model is used to make predictions to obtain the residual prediction values ​​for the corresponding locations within the pipeline. The operating condition characteristic parameters include Reynolds number, Froude number, dimensionless sediment particle size, and the ratio of physical baseline to water depth. By combining the physical baseline data and the corresponding residual prediction values ​​at each location within the target pipeline, and using the summation method based on the same location, the deposition thickness assessment results at the corresponding locations within the target pipeline are obtained.

3. The method according to claim 2, characterized in that, The second sensor data collected within the target pipeline, combined with the water surface trajectory data, is used to obtain physical baseline data for multiple locations along the pipeline using a trajectory inverse calculation method, including: Based on the six-axis motion data of the bottom position of the pipe collected by multiple second sensors, coordinate transformation is performed using coordinate transformation methods to obtain the acceleration data and angular velocity data of each second sensor in the global coordinate system; Based on the acceleration data of each second sensor in the global coordinate system, the original motion trajectory of each second sensor is obtained by using the quadratic integration method. Based on the pressure data of each second sensor, combined with the water surface trajectory data, the real-time water depth at the location of the corresponding second sensor is calculated using the water depth conversion method and corrected accordingly, so as to obtain the corrected motion trajectory data of each second sensor. By combining the motion trajectory data corrected by multiple second sensors, a trajectory fusion method is used to obtain physical baseline data for multiple locations along the pipeline.

4. The method according to claim 3, characterized in that, The motion trajectory data, after being corrected by multiple second sensors, is used to obtain physical baseline data for multiple locations along the pipeline using a trajectory fusion method, including: By combining the corrected motion trajectory data from multiple second sensors at the same location, outlier data removal methods are used to remove abnormal data with deviations exceeding a preset threshold, thus obtaining the filtered valid trajectory data. Based on the filtered valid trajectory data, the moving average method is used to smooth the data along the pipeline route, resulting in physical baseline data for multiple locations along the pipeline route.

5. The method according to claim 2, characterized in that, The water surface trajectory data along the pipeline direction is obtained by using a smoothing method based on the first sensor data collected inside the target pipeline, including: Based on the six-axis motion data collected at multiple moments during the movement of the first sensor along the target pipeline, the position data of the first sensor at each moment is obtained by using the time series analysis method. Based on the first sensor position data corresponding to each time moment, the position coordinates in the global coordinate system at each time moment are obtained by using the coordinate transformation method; Based on the position coordinates in the global coordinate system at each moment, the water surface trajectory data along the pipeline direction is obtained using a time-series smoothing method.

6. The method according to claim 2, characterized in that, The method involves using physical baseline data at each location at the bottom of the pipe, combined with corresponding operating condition characteristic parameters within the target pipe, to predict the residual prediction values ​​at the corresponding locations within the pipe using a trained random forest model. This includes: Based on the physical baseline data at each location at the bottom of the pipeline, combined with the water depth data at the corresponding location, the ratio of the physical baseline to the water depth at the corresponding location is obtained using the ratio calculation method of physical baseline to water depth. Based on the ratio of physical baseline to water depth at each location, and combined with the Reynolds number, Froude number, and dimensionless sediment particle size at the corresponding location within the pipe, input feature vectors for the corresponding locations are constructed respectively. Based on the input feature vector at each location, the trained random forest model is used to make predictions to obtain the residual prediction value at the corresponding location.

7. The method according to claim 2, characterized in that, The training of the random forest model includes: Acquire multiple sets of physical baseline data and corresponding measured deposition thickness data at various locations along the pipeline under multiple deposition thickness scenarios; Based on the difference between the physical baseline data and the measured deposition thickness data at each location, the residual data at the corresponding location is obtained, and a residual data sequence at the corresponding location along the pipeline direction is constructed. The residual data at each location is used as the output feature, and the corresponding working condition feature parameters are used as the input feature. The random forest algorithm is used for training to obtain the trained random forest model.

8. A pipe deposition assessment device, characterized in that, Employing the sensor system as described in claim 1, the device comprises: The first processing module is used to obtain water surface trajectory data inside the pipe based on the first sensing data collected inside the target pipe using a smoothing processing method; the first sensing data includes six-axis motion data of the water surface position inside the pipe collected by a floating sensor. The second processing module is used to obtain physical baseline data at multiple locations at the bottom of the pipe based on the second sensing data collected inside the target pipe and the water surface trajectory data, using a trajectory inverse calculation method; the second sensing data includes six-axis motion data and pressure data at the bottom of the pipe collected by a sliding sensor. The residual prediction module is used to predict the residual values ​​at each position in the pipeline based on the physical baseline data at each position at the bottom of the pipeline and the corresponding operating condition characteristic parameters in the target pipeline, using a trained random forest model. The operating condition characteristic parameters include Reynolds number, Froude number, dimensionless sediment particle size, and the ratio of physical baseline to water depth. The results output module integrates the physical baseline data and corresponding residual prediction values ​​at each location within the target pipeline, and uses a summation method based on the same location to obtain the deposition thickness assessment results at the corresponding location within the target pipeline.

9. An electronic device, characterized in that, include: A memory and a processor are communicatively connected, the memory storing computer instructions, and the processor executing the computer instructions to perform the pipeline deposition assessment method according to any one of claims 2 to 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the pipeline deposition assessment method according to any one of claims 2 to 8.

Images