A pipeline deposit thickness prediction method, device, equipment, medium and product

Abstract

This invention relates to the field of pipeline drainage inspection technology, and discloses a method, device, equipment, medium, and product for predicting pipeline sediment thickness. By deploying temperature sensors in different cross-sections of the pipeline and collecting long-term data series, this invention achieves long-term dynamic monitoring of sediment layers in long pipe sections. It overcomes the limitations of single-point, short-term measurements with limited applicability. Furthermore, the temperature sensors are unaffected by complex environments such as stagnant water and obstacles within the pipeline, and there is no need to install equipment that would affect pipeline operation. They can be deployed within the system for extended periods. Therefore, by measuring temperature time-series data and using dynamic harmonic regression methods, spatiotemporal dynamic monitoring of the sediment layer is achieved. Moreover, instead of assuming uniform sediment layer thickness, it predicts the thickness variation of the sediment layer along the water flow direction based on the sediment layer thickness at different cross-sections, accurately reflecting the non-uniform variations of the sediment layer.

Description

Technical Field

[0001] This invention relates to the field of pipeline drainage detection technology, specifically to a method, apparatus, equipment, medium, and product for predicting pipeline sediment thickness. Background Technology

[0002] Existing sediment thickness measurement technologies mainly include pressure sensor thickness measurement, laser ranging, and hydraulic estimation. However, pressure sensor thickness measurement, which determines the pipe diameter and sediment location through infrared ranging and then uses a transmission mechanism to bring the pressure sensor into contact with the sediment surface to measure the thickness, is only suitable for single-point, short-term measurements. It cannot achieve long-term dynamic monitoring of sediment layer development in long pipe sections, and it is difficult to operate in high water or full water level environments, thus limiting its applicability. This limitation is essentially the same as that of manual measurement and cannot support the analysis of the overall sedimentation trend of a pipeline.

[0003] Laser ranging technology directly measures the thickness of sediments using a laser rangefinder. However, the complex internal environment of pipelines, such as silt and obstacles, can hinder laser penetration, leading to a significant decrease in measurement accuracy. Furthermore, the installation of laser equipment requires interference with the normal operation of the pipeline, making it impossible to deploy it within the system for extended periods. This makes it difficult to achieve spatiotemporal dynamic monitoring of sediment layers, and it cannot operate effectively under conditions of high or full water levels, thus failing to meet the requirements for continuous monitoring.

[0004] Hydraulic estimation techniques use liquid level monitoring data combined with hydraulic formulas to estimate sediment thickness. While this method enables long-term monitoring and is applicable to high and full water levels, its core assumption—that "the thickness of the sediment layer at the bottom of the pipe varies uniformly from the beginning to the end"—does not reflect reality. Due to differences in sediment particle size, foreign objects, and obstacles, sediment layer development exhibits non-uniform variations, leading to significant discrepancies between predicted and actual thicknesses and failing to accurately reflect the true morphology of the sediment layer along the water flow direction. Summary of the Invention

[0005] In view of this, the present invention provides a method, apparatus, equipment, medium and product for predicting pipeline sediment thickness, in order to solve the problem that existing sediment thickness measurement technologies have many limitations and are difficult to meet the needs of long-term, accurate and multi-scenario monitoring of drainage systems.

[0006] In a first aspect, the present invention provides a method for predicting the thickness of pipe deposits, the method comprising:

[0007] The process involves acquiring multiple first sediment layer thicknesses at a first cross-section within the pipeline to be predicted, first temperature time-series data from multiple first temperature sensors within the first cross-section, and second temperature time-series data from multiple second temperature sensors within multiple second cross-sections of the pipeline. The first and multiple second cross-sections are determined according to the water flow direction within the pipeline to be predicted. Based on the first temperature time-series data and the multiple first sediment layer thicknesses, a temperature conductivity coefficient is obtained through dynamic harmonic regression. Based on the second temperature time-series data and the temperature conductivity coefficient, multiple second sediment layer thicknesses at the multiple second cross-sections are obtained through dynamic harmonic regression. Based on the multiple first and multiple second sediment layer thicknesses, the thickness variation of the sediment layer within the pipeline to be predicted along the water flow direction is predicted to obtain the sediment thickness prediction result for the pipeline to be predicted.

[0008] The pipeline sediment thickness prediction method provided by this invention achieves long-term dynamic monitoring of sediment layers in long pipe sections by setting up a first pipe section and multiple second pipe sections in the direction of water flow within the pipe to be predicted, and deploying temperature sensors to collect long-term series data. Furthermore, the deployment of temperature sensors and data acquisition are unaffected by high or full water levels, overcoming the limitations of pressure sensor thickness measurement technology, which is limited to single-point, short-term measurements and has a limited scope of application. Moreover, the temperature sensors are unaffected by complex environments such as stagnant water and obstacles within the pipeline, and do not require the installation of equipment that would affect pipeline operation; they can be deployed within the system for extended periods. Therefore, by measuring temperature time-series data and using dynamic harmonic regression methods, spatiotemporal dynamic monitoring of sediment layers is achieved, overcoming the shortcomings of laser ranging technology, which is susceptible to environmental interference and cannot be deployed for long periods. Furthermore, instead of assuming a uniform variation in sediment thickness, the method obtains a temperature conductivity coefficient that reflects the thermal conductivity characteristics of the actual sedimentary medium by using multiple first sediment thickness and temperature time series data of the first pipe section. Then, it calculates the second sediment thickness of each section by combining the temperature time series data of multiple second pipe sections. Finally, it predicts the thickness variation of the sediment layer along the water flow direction by combining multiple first sediment thicknesses. This method can accurately reflect the non-uniform variation of the sediment layer and solves the problem of large deviations between prediction results and reality caused by unreasonable assumptions in hydraulic calculation technology. It provides data support for pipeline operation and maintenance and dredging schemes.

[0009] In one optional implementation, based on first temperature time-series data and multiple first deposition layer thicknesses, a temperature conductivity coefficient is obtained through dynamic harmonic regression, including:

[0010] The first water temperature sequence data in the first temperature time series data is processed using a dynamic regression model and Fourier series to obtain multiple first water temperature amplitudes of the first pipe cross-section. The first sedimentary layer temperature sequence data in the first temperature time series data is processed using an asymmetric cyclic sequence analysis method to obtain multiple first sedimentary layer temperature amplitudes of the first pipe cross-section. Based on the first water temperature sequence data and the first sedimentary layer temperature sequence data, multiple first phase lags of the first pipe cross-section are determined. Based on the multiple first water temperature amplitudes, multiple first sedimentary layer temperature amplitudes, multiple first phase lags, and multiple first sedimentary layer thicknesses, the temperature conductivity coefficient is obtained by fitting a preset functional relationship.

[0011] The pipeline sediment thickness prediction method provided by this invention uses Fourier series decomposition of water temperature time-series data and combines it with a dynamic regression model to capture harmonic components of different frequencies. This accurately extracts water temperature amplitude, solving the signal distortion problem caused by siltation and obstruction in laser ranging technology, and ensuring the integrity and reliability of water temperature reference data. Furthermore, through asymmetric cyclic sequence analysis, the temperature amplitude of sediments at different depths can be effectively extracted, overcoming the disturbance problem caused by contact measurement in pressure sensor thickness measurement technology. It is also unaffected by high or full water levels and adapts to the complex temperature changes of the first pipeline cross-section. Simultaneously, by addressing the asymmetry of sediment temperature changes, the homogeneity assumption error of hydraulic estimation techniques is avoided, thus accurately characterizing the temperature fluctuation features of sediments at different depths. Furthermore, by combining the first water temperature sequence data and the first sediment layer temperature sequence data to determine the phase lag, the method reflects the lag characteristics of temperature transmission between the water body and the sediment layer, solving the phase information loss problem caused by the inability of laser ranging technology to penetrate the medium. Finally, using the known deposition layer thickness of the first pipe section and combining characteristics such as amplitude and phase hysteresis, a pre-defined functional relationship was used to fit the temperature conductivity coefficient. This solved the parameter distortion problem caused by the assumption of homogeneity in hydraulic estimation techniques, thus enabling the temperature conductivity coefficient to accurately reflect the actual thermal conductivity characteristics of the deposition medium. Furthermore, the fitted temperature conductivity coefficient provides a unified benchmark for the subsequent thickness calculation of the second pipe section, overcoming the shortcomings of pressure sensor methods and laser methods in cross-section calibration, and ensuring the consistency of thickness measurements across different sections.

[0012] In one optional implementation, the first water temperature sequence data in the first temperature time series data is processed using a dynamic regression model and Fourier series to obtain multiple first water temperature amplitudes of the first pipe cross-section, including:

[0013] The first temperature time series data is decomposed using Fourier series to obtain multiple harmonic components; based on the multiple harmonic components, the first water temperature sequence data is processed using a dynamic regression model to obtain multiple first water temperature amplitudes.

[0014] The pipeline sediment thickness prediction method provided by this invention decomposes the first temperature time series data into multiple harmonic components using Fourier series, effectively capturing the periodic changes in water temperature over time. This solves the signal distortion problem caused by siltation and obstructions in laser ranging technology, ensuring the integrity and reliability of the water temperature reference data. Furthermore, by combining the harmonic components with a dynamic regression model, the water temperature amplitude can be accurately extracted, providing data support for the subsequent fitting of the temperature conduction coefficient.

[0015] In one optional implementation, an asymmetric cyclic sequence analysis method is used to process the temperature sequence data of the first sedimentary layer in the first temperature time series data to obtain multiple first sediment temperature amplitudes of the first pipe cross-section, including:

[0016] The first temperature time series data is simplified and denoised to obtain the third temperature time series data, which includes the temperature sequence data of the second sedimentary layer. The second sedimentary layer temperature sequence data is analyzed to obtain multiple local maximum values ​​and multiple local minimum values ​​of sediment temperature. Based on the multiple local maximum values ​​and multiple local minimum values ​​of sediment temperature, multiple first sediment temperature amplitudes are determined.

[0017] The pipeline sediment thickness prediction method provided by this invention reduces interference signals in the first temperature time series data through simplification and noise reduction, solving the data fluctuation problem caused by environmental disturbances in pressure sensor thickness measurement technology and ensuring the stability of the sediment temperature sequence. Furthermore, by extracting local maximum and minimum values, the fluctuation range of sediment temperature can be accurately calculated, overcoming the feature extraction bias caused by the assumption of uniform sediment layers in hydraulic extrapolation techniques, thus accurately reflecting the true temperature changes of sediments at different depths.

[0018] In one optional implementation, based on second temperature time-series data and temperature conductivity coefficients, and processed using a dynamic harmonic regression method, multiple second deposition layer thicknesses for multiple second pipe cross-sections are obtained, including:

[0019] The second water temperature sequence data in the second temperature time series data were processed using a dynamic regression model and Fourier series to obtain multiple second water temperature amplitudes for multiple second pipe sections. The third sedimentary layer temperature sequence data in the second temperature time series data were processed using an asymmetric cyclic sequence analysis method to obtain multiple second sedimentary temperature amplitudes for multiple second pipe sections. Based on the second water temperature sequence data and the third sedimentary layer temperature sequence data, multiple second phase lags for multiple second pipe sections were determined. Based on the temperature conductivity coefficient, multiple second water temperature amplitudes, multiple second sedimentary layer temperature amplitudes, and multiple second phase lags, multiple second sedimentary layer thicknesses for multiple second pipe sections were obtained after processing using a preset functional relationship.

[0020] The pipeline sediment thickness prediction method provided by this invention uses Fourier series decomposition of water temperature time-series data and combines it with a dynamic regression model to capture harmonic components of different frequencies. This accurately extracts water temperature amplitude, solving the signal distortion problem caused by siltation and obstruction in laser ranging technology, and ensuring the integrity and reliability of water temperature reference data. Furthermore, through asymmetric cyclic sequence analysis, the temperature amplitude of sediments at different depths can be effectively extracted, overcoming the disturbance problem caused by contact measurement in pressure sensor thickness measurement technology. It is also unaffected by high or full water levels and adapts to the complex temperature changes of the first pipeline cross-section. Simultaneously, by addressing the asymmetry of sediment temperature changes, the uniformity assumption error of hydraulic estimation techniques is avoided, thus accurately characterizing the temperature fluctuation characteristics of sediments at different depths. Furthermore, based on a preset functional relationship and combined with the fitted temperature conductivity coefficient, the thickness of multiple second sediment layers at multiple second pipeline cross-sections can be accurately calculated, achieving multi-temporal and spatial monitoring along the water flow direction with centimeter-level accuracy. This clearly characterizes the non-uniform changes in sediment layers, providing data support for pipeline operation and maintenance and dredging schemes.

[0021] In a second aspect, the present invention provides a pipe deposit thickness prediction device, the device comprising:

[0022] The acquisition module is used to acquire multiple first sediment layer thicknesses in a first pipe cross-section within the pipe to be predicted, first temperature time-series data from multiple first temperature sensors within the first pipe cross-section, and second temperature time-series data from multiple second temperature sensors within multiple second pipe cross-sections. The first pipe cross-section and multiple second pipe cross-sections are determined according to the water flow direction within the pipe to be predicted. The first processing module is used to obtain a temperature conductivity coefficient based on the first temperature time-series data and multiple first sediment layer thicknesses using a dynamic harmonic regression method. The second processing module is used to obtain multiple second sediment layer thicknesses in multiple second pipe cross-sections based on the second temperature time-series data and the temperature conductivity coefficient using a dynamic harmonic regression method. The prediction module is used to predict the thickness change of the sediment layer along the water flow direction within the pipe to be predicted based on the multiple first sediment layer thicknesses and multiple second sediment layer thicknesses, and obtain the sediment thickness prediction result for the pipe to be predicted.

[0023] In one optional implementation, the first processing module includes:

[0024] The first processing submodule is used to process the first water temperature sequence data in the first temperature time series data using a dynamic regression model and Fourier series to obtain multiple first water temperature amplitudes of the first pipe cross-section; the second processing submodule is used to process the first sedimentary layer temperature sequence data in the first temperature time series data using an asymmetric cyclic sequence analysis method to obtain multiple first sedimentary layer temperature amplitudes of the first pipe cross-section; the first determination submodule is used to determine multiple first phase lags of the first pipe cross-section based on the first water temperature sequence data and the first sedimentary layer temperature sequence data; the fitting submodule is used to obtain the temperature conductivity coefficient by fitting multiple first water temperature amplitudes, multiple first sedimentary layer temperature amplitudes, multiple first phase lags, and multiple first sedimentary layer thicknesses through a preset functional relationship.

[0025] Thirdly, the present invention provides a computer 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 pipe deposition thickness prediction method of the first aspect or any corresponding embodiment described above.

[0026] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform the pipe deposit thickness prediction method of the first aspect or any corresponding embodiment described above.

[0027] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the pipe deposit thickness prediction method of the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0028] 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.

[0029] Figure 1 This is a schematic flowchart of a pipeline deposition thickness prediction method according to an embodiment of the present invention;

[0030] Figure 2 This is a schematic diagram of the installation of a temperature sensor along the water flow direction in a pipeline according to an embodiment of the present invention;

[0031] Figure 3 This is a schematic diagram of the temperature sensor mounting section according to an embodiment of the present invention;

[0032] Figure 4 This is a schematic diagram of the first temperature time series data according to an embodiment of the present invention;

[0033] Figure 5 This is a schematic diagram of the second temperature time series data according to an embodiment of the present invention;

[0034] Figure 6 This is a schematic diagram of deposition thickness prediction according to an embodiment of the present invention;

[0035] Figure 7 This is a schematic flowchart of another pipeline deposit thickness prediction method according to an embodiment of the present invention;

[0036] Figure 8 This is a flowchart illustrating another method for predicting pipeline deposit thickness according to an embodiment of the present invention;

[0037] Figure 9 This is a structural block diagram of a pipe deposit thickness prediction device according to an embodiment of the present invention;

[0038] Figure 10 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0039] 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.

[0040] This invention provides a method for predicting pipeline sediment thickness. By setting up a first pipeline cross-section and multiple second pipeline cross-sections in the direction of water flow within the pipeline to be predicted, and combining different temperature time series data collected by different sensors, the dynamic harmonic regression method is used to process the data to achieve accurate prediction of pipeline sediment thickness.

[0041] According to an embodiment of the present invention, a method for predicting the thickness of pipe deposits 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 method for predicting pipeline deposit thickness, which can be used in electronic devices such as computers, mobile phones, and tablets. Figure 1This is a flowchart of a pipeline deposition thickness prediction method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0043] Step S101: Obtain the thickness of multiple first deposited layers in the first pipe section of the pipe to be predicted, the first temperature time series data of multiple first temperature sensors in the first pipe section, and the second temperature time series data of multiple second temperature sensors in multiple second pipe sections.

[0044] The first pipe cross-section and multiple second pipe cross-sections are determined according to the direction of water flow in the pipe to be predicted.

[0045] Furthermore, the first pipe section refers to the section near the pipe inlet. Within this section, the sediment thickness is generally relatively large. This is because long-term field data shows that the sediment thickness typically decreases with the direction of water flow. In other words, the first pipe section appears only once within the same pipe. Figure 2 Section AA.

[0046] Furthermore, the second pipe section represents the section following the first pipe section, and can be divided into n sections as needed based on the pipe length and diameter, such as... Figure 2 Section Bn-Bn.

[0047] Specifically, the installation methods of temperature sensors on different types of pipe cross-sections.

[0048] Among them, such as Figure 3 As shown in section AA, the arrangement of multiple first temperature sensors is as follows: 1) A temperature sensor is installed at the bottom of the pipe, marked as T. D-A 1) Used to record changes in the temperature of the bottom sediment; 2) Starting from the bottom, temperature sensors are installed on the side wall of the pipe at vertical intervals of 5 cm, upwards, until half the pipe diameter is reached, marked as T. W-A1 T W-A2 T W-A3 , ..., T W-An .

[0049] Furthermore, such as Figure 3 As shown in the Bn-Bn section, the arrangement of multiple second temperature sensors is as follows: 1) A temperature sensor is installed at the bottom of the pipe, marked as T. D-Bn Used to record temperature changes in the bottom sediments, with section B being closer to section AA. 1-B1 1) Install a cross-section every 5-25 meters, with the last cross-section being Bn-Bn; 2) Install temperature sensors on the sidewall of the pipeline near the normal water level, marked as T. W-Bn .

[0050] Furthermore, such as Figure 3As shown, both the first and second temperature sensors are pancake-shaped sensors, with cables running along the pipe for power supply and data transmission.

[0051] Furthermore, the thickness of the multiple first deposition layers in the first pipe cross section can be determined based on the positions of the multiple first temperature sensors obtained from the deployment.

[0052] Furthermore, the first temperature time series data is as follows: Figure 4 As shown, it can include water temperature sequence data, sediment layer temperature sequence data, and sediment layer temperature sequence data.

[0053] Furthermore, the second temperature time series data is as follows: Figure 5 As shown, it can include water temperature sequence data and sediment layer temperature sequence data.

[0054] Furthermore, in section AA, T W-A4 The standard for judging water temperature is T. W-A4 T and above W-A5 , TW-A6 Until T W-An The temperature amplitude and hysteresis are very small, consistent with temperature changes within the same medium after thorough mixing. However, when significant changes occur in temperature amplitude and hysteresis (e.g., T...),... W-A2 T W-A1 T D-A This reflects the temperature changes in the sedimentary layer.

[0055] Furthermore, the periodic changes in water temperature are gradually transmitted to the sedimentary layer. Due to the time lag in temperature transmission, this is manifested in… Figure 4 and Figure 5 The trend in.

[0056] Step S102: Based on the first temperature time series data and multiple first deposition layer thicknesses, the temperature conductivity coefficient is obtained by processing with the dynamic harmonic regression method.

[0057] Among them, the dynamic harmonic regression method represents a technique applicable to the analysis, modeling, and prediction of non-stationary time series.

[0058] Furthermore, the temperature conductivity coefficient represents a physical parameter characterizing the thermal conductivity of a deposition medium (such as sediments in a pipe), and is used to reflect the rate characteristics of temperature transfer in the sediment.

[0059] Specifically, based on the first temperature time series data (including water temperature and temperature time series data of sediments at different depths) of the first pipe section and the known thicknesses of multiple first sedimentary layers of the section, the dynamic harmonic regression method is used to analyze and process these data, and the temperature conductivity coefficient of the sedimentary medium can be finally fitted.

[0060] Step S103: Based on the second temperature time series data and temperature conduction coefficient, the thickness of multiple second deposition layers for multiple second pipe sections is obtained through dynamic harmonic regression.

[0061] Specifically, based on the second temperature time series data (including water temperature and temperature time series data of sediments at different depths at each section) of multiple second pipe sections and the determined temperature conductivity coefficient, the dynamic harmonic regression method is used to analyze and process these data, which can accurately calculate the thickness of multiple second sedimentary layers corresponding to multiple second pipe sections.

[0062] Step S104: Based on the thicknesses of multiple first sedimentary layers and multiple second sedimentary layers, predict the thickness variation of the sedimentary layers in the pipeline to be predicted along the water flow direction, and obtain the predicted sedimentary thickness of the pipeline to be predicted.

[0063] Specifically, based on the obtained thicknesses of multiple first sedimentary layers and multiple second sedimentary layers, a diagram showing the variation of sediment thickness along the water flow direction inside the pipe can be drawn, i.e., a schematic diagram of sediment thickness prediction.

[0064] In some optional embodiments, a schematic diagram of deposition thickness prediction is shown below. Figure 6 As shown.

[0065] Furthermore, according to Figure 6 It can be seen that the thickness of the sediment at the initial position AA section is 0.5m, and the thickness of the sediment at the subsequent Bn-Bn section gradually decreases along the direction of water flow, reflecting the characteristics of bedload movement. This indicates that in addition to organic matter in domestic sewage, inorganic matter such as sand and gravel also accounts for a certain proportion inside the pipe.

[0066] Furthermore, according to Figure 6 It can also guide the analysis of pipeline deposition risks and the formulation of pipeline operation and maintenance dredging plans. For example, when the deposition thickness accounts for more than 50% of the pipeline diameter, dredging measures should be taken as soon as possible. If the deposition thickness accounts for no more than 20% of the pipeline diameter, it means that the pipeline is operating relatively normally and no additional attention is needed to the deposition development phenomenon.

[0067] The pipeline sediment thickness prediction method provided in this embodiment achieves long-term dynamic monitoring of sediment layers in long pipe sections by setting up a first pipe section and multiple second pipe sections in the direction of water flow within the pipe to be predicted, and deploying temperature sensors to collect long-term series data. Furthermore, the deployment of temperature sensors and data acquisition are unaffected by high or full water levels, overcoming the limitations of pressure sensor thickness measurement technology, which can only perform single-point, short-term measurements and has a limited scope of application. Moreover, the temperature sensors are unaffected by complex environments such as stagnant water and obstacles within the pipeline, and do not require the installation of equipment that would affect pipeline operation; they can be deployed within the system for extended periods. Therefore, by measuring using time-series temperature data and dynamic harmonic regression methods, spatiotemporal dynamic monitoring of the sediment layer is achieved, overcoming the shortcomings of laser ranging technology, which is susceptible to environmental interference and cannot be deployed for long periods. Furthermore, instead of assuming a uniform variation in sediment thickness, the method obtains a temperature conductivity coefficient that reflects the thermal conductivity characteristics of the actual sedimentary medium by using multiple time-series data of the first sediment thickness and temperature at the first pipe cross-section. This coefficient is then combined with time-series data of the temperature at multiple second pipe cross-sections to calculate the second sediment thickness at each cross-section. This allows for the prediction of sediment thickness variations along the water flow direction, accurately reflecting the non-uniform variation of the sediment layer. This solves the problem of large discrepancies between predictions and actual results caused by unreasonable assumptions in hydraulic calculation techniques, providing data support for pipeline operation and maintenance and dredging schemes.

[0068] This embodiment provides a method for predicting pipeline deposit thickness, which can be used in electronic devices such as computers, mobile phones, and tablets. Figure 7 This is a flowchart of a pipeline deposition thickness prediction method according to an embodiment of the present invention, such as... Figure 7 As shown, the process includes the following steps:

[0069] Step S701: Obtain the thickness of multiple first deposition layers in the first pipe cross-section to be predicted, the first temperature time-series data of multiple first temperature sensors in the first pipe cross-section, and the second temperature time-series data of multiple second temperature sensors in multiple second pipe cross-sections. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0070] Step S702: Based on the first temperature time series data and multiple first deposition layer thicknesses, the temperature conductivity coefficient is obtained through dynamic harmonic regression.

[0071] Specifically, step S702 includes:

[0072] Step S7021: The first water temperature sequence data in the first temperature time series data is processed using a dynamic regression model and Fourier series to obtain multiple first water temperature amplitudes of the first pipe cross section.

[0073] Fourier series is a mathematical tool used to decompose raw temperature time series data into a combination of sine and cosine functions (harmonic components) of different frequencies, which is used to extract periodic variation information contained in the time series.

[0074] Furthermore, the dynamic regression model represents a model used to analyze time series data. It can capture the trends and complex patterns of temperature time series by utilizing extracted harmonic components. At the same time, by optimizing the model parameters, the fitting and prediction capabilities of temperature series variation patterns can be improved.

[0075] Specifically, for the first water temperature sequence data (e.g., T) in the first temperature time series data of the first pipe section (e.g., section AA), W-A4 The water temperature data collected by the above sensors is first extracted by Fourier series decomposition to obtain the periodic harmonic components contained therein. Then, these components are input into a dynamic regression model. Through model analysis and processing, multiple amplitudes of water temperature fluctuation at this cross section can be obtained, namely multiple first water temperature amplitudes.

[0076] In some optional implementations, step S7021 above includes:

[0077] Step a1: Decompose the first temperature time series data using Fourier series to obtain multiple harmonic components.

[0078] Step a2: Based on multiple harmonic components, the first water temperature sequence data is processed using a dynamic regression model to obtain multiple first water temperature amplitudes.

[0079] Specifically, Fourier transform is performed on the first temperature time series data (including the time series of water temperature and sediment temperature) collected from the first pipe section, decomposing the original data into a combination of sine and cosine functions of different frequencies, i.e., multiple harmonic components.

[0080] Each harmonic component corresponds to the fluctuation characteristics of different periods in the data.

[0081] Furthermore, from the multiple harmonic components obtained by decomposition, the harmonic components related to the first water temperature sequence data (water temperature time series) can be screened out and used as input features of the dynamic regression model.

[0082] Furthermore, the input harmonic components are fitted and analyzed using a dynamic regression model, and the periodic fluctuation pattern of the water temperature sequence is captured. Finally, the fluctuation amplitude of the water temperature under different periods is calculated, i.e., multiple first water temperature amplitudes.

[0083] Step S7022: Using the asymmetric cyclic sequence analysis method, the temperature sequence data of the first sediment layer in the first temperature time series data is processed to obtain multiple first sediment temperature amplitudes of the first pipe cross section.

[0084] Among them, the asymmetric cyclic sequence analysis method refers to an analytical technique for processing asymmetric cyclic temperature time series data, which is mainly used to extract amplitude and phase characteristic information in the fundamental frequency of sediment temperature time series.

[0085] Specifically, for the first deposition layer temperature sequence data (such as T) in the first temperature time series data of the first pipe section... W-A1 T W-A2 T D-A Using sediment temperature data collected by sensors, and employing asymmetric cyclic sequence analysis, the temperature fluctuation amplitudes of sediments at different depths can be extracted through data simplification, noise reduction, and extreme value identification. This results in multiple first sediment temperature amplitudes.

[0086] In some optional implementations, step S7022 above includes:

[0087] Step b1 involves simplifying and denoising the first temperature time series data to obtain the third temperature time series data, which includes the temperature sequence data of the second deposition layer.

[0088] Step b2 involves analyzing the temperature sequence data of the second sedimentary layer to obtain multiple local maximum and minimum sediment temperatures.

[0089] Step b3: Determine multiple first sediment temperature amplitudes based on multiple local maximum and multiple local minimum sediment temperatures.

[0090] Specifically, a 24-hour time period can be selected, and 12 samples can be chosen each day from the first temperature time series data to simplify the data volume. At the same time, a low-pass filter can be used to process the simplified data to reduce noise interference and obtain the third temperature time series data.

[0091] Furthermore, the third temperature time series data includes the first sedimentary layer temperature series data, i.e., the second sedimentary layer temperature series data, which is a simplified and noise-reduced preprocessed sediment temperature time series that can be used for analysis.

[0092] Furthermore, by analyzing the second sedimentary layer temperature sequence data (sediment temperature time series) in the third temperature time series data, and by using signal processing tools, the local maximum values ​​(temperature peaks) and local minimum values ​​(temperature valleys) of the sequence in each time period can be identified, thus obtaining multiple local maximum values ​​and multiple local minimum values ​​of sediment temperature.

[0093] Furthermore, for each time period, the difference between the local maximum and local minimum values ​​of sediment temperature within that period is calculated. This difference is the fluctuation range of sediment temperature within that period, i.e., the first sediment temperature amplitude.

[0094] Furthermore, by organizing the fluctuation amplitudes of multiple cycles, the temperature fluctuation amplitudes of sediments at different depths in the first pipe section can be obtained, i.e., multiple temperature amplitudes of the first sediments.

[0095] Step S7023: Based on the first water temperature sequence data and the first sedimentation layer temperature sequence data, determine multiple first phase lags of the first pipe cross-section.

[0096] Phase lag refers to the time difference between the water temperature and the sediment temperature reaching their peak (local maximum) within the same time period. It is usually measured in radians (2π radians for 24 hours) and is used to reflect the lag characteristics of temperature transfer between the water body and the sediment layer.

[0097] Specifically, the first water temperature sequence data (water temperature time series) and the first sedimentary layer temperature sequence data (sediment temperature time series) in the first pipe section are compared, and the time when the temperature peak (local maximum) of both occurs in each time period is identified.

[0098] Furthermore, the time difference between the peak water temperature and the peak sediment temperature within the same cycle is calculated, and this time difference is converted into a value in radians (24 hours corresponds to 2π radians), resulting in multiple time lag values, i.e. multiple first phase lags of the first pipe section.

[0099] Step S7024: Based on multiple first water temperature amplitudes, multiple first sediment temperature amplitudes, multiple first phase hysteresis, and multiple first sediment layer thicknesses, the temperature conductivity coefficient is obtained by fitting a preset function relationship.

[0100] Specifically, the preset functional relationship is shown in the following relation (1):

[0101] (1)

[0102] In the formula: Indicates the thickness of the sedimentary layer; Indicates phase lag; Indicates the thermal conductivity coefficient; The characteristic information representing the fundamental frequency of two time series is shown in the following relationship (2):

[0103] (2)

[0104] In the formula: Indicates the amplitude of water temperature fluctuation; This indicates the temperature amplitude of the sediment.

[0105] Furthermore, by substituting the obtained multiple first water temperature amplitudes, multiple first sediment temperature amplitudes, multiple first phase hysteresis, and multiple first sediment layer thicknesses into the above relationships (1) and (2), the corresponding temperature conductivity coefficients can be obtained by fitting. .

[0106] Step S703: Based on the second temperature time series data and temperature conductivity coefficient, the thickness of multiple second deposition layers for multiple second pipe cross-sections is obtained through dynamic harmonic regression. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0107] Step S704: Based on multiple first sediment layer thicknesses and multiple second sediment layer thicknesses, the thickness variation of the sediment layer along the water flow direction within the pipe to be predicted is predicted, thus obtaining the predicted sediment thickness of the pipe. For details, please refer to [link to relevant documentation]. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0108] The pipeline sediment thickness prediction method provided in this embodiment decomposes the first temperature time series data into multiple harmonic components using Fourier series, effectively capturing the periodic changes in water temperature over time. This solves the signal distortion problem caused by siltation and obstruction in laser ranging technology, ensuring the integrity and reliability of the water temperature reference data. Furthermore, by processing the harmonic components using a dynamic regression model, the water temperature amplitude can be accurately extracted. Further, through simplification and noise reduction, interference signals in the first temperature time series data can be reduced, solving the data fluctuation problem caused by environmental disturbances in pressure sensor thickness measurement technology, ensuring the stability of the sediment temperature sequence. Furthermore, by extracting local maximum and minimum values, the fluctuation amplitude of sediment temperature can be accurately calculated, overcoming the feature extraction bias caused by the assumption of uniform sediment layers in hydraulic extrapolation technology, thus accurately reflecting the true temperature changes of sediments at different depths. Furthermore, by combining the first water temperature sequence data and the first sediment layer temperature sequence data to determine the phase lag, the transmission lag characteristics of temperature between the water body and the sediment layer can be reflected, solving the phase information loss problem caused by the inability of laser ranging technology to penetrate the medium. Finally, using the known deposition layer thickness of the first pipe section and combining characteristics such as amplitude and phase hysteresis, a pre-defined functional relationship was used to fit the temperature conductivity coefficient. This solved the parameter distortion problem caused by the assumption of homogeneity in hydraulic estimation techniques, thus enabling the temperature conductivity coefficient to accurately reflect the actual thermal conductivity characteristics of the deposition medium. Furthermore, the fitted temperature conductivity coefficient provides a unified benchmark for the subsequent thickness calculation of the second pipe section, overcoming the shortcomings of pressure sensor methods and laser methods in cross-section calibration, and ensuring the consistency of thickness measurements across different sections.

[0109] This embodiment provides a method for predicting pipeline deposit thickness, which can be used in electronic devices such as computers, mobile phones, and tablets. Figure 8 This is a flowchart of a pipeline deposition thickness prediction method according to an embodiment of the present invention, such as... Figure 8 As shown, the process includes the following steps:

[0110] Step S801: Obtain the thickness of multiple first deposition layers in the first pipe cross-section to be predicted, the first temperature time-series data of multiple first temperature sensors in the first pipe cross-section, and the second temperature time-series data of multiple second temperature sensors in multiple second pipe cross-sections. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0111] Step S802: Based on the first temperature time series data and multiple first deposition layer thicknesses, the temperature conductivity coefficient is obtained through dynamic harmonic regression. For details, please refer to [link to relevant documentation]. Figure 7 Step S702 of the illustrated embodiment will not be described again here.

[0112] Step S803: Based on the second temperature time series data and temperature conductivity coefficient, the thickness of multiple second deposition layers for multiple second pipe sections is obtained through dynamic harmonic regression.

[0113] Specifically, step S803 includes:

[0114] Step S8031: The second water temperature sequence data in the second temperature time series data is processed using a dynamic regression model and Fourier series to obtain multiple second water temperature amplitudes for multiple second pipe sections.

[0115] The specific process can be found in the description of step S7021 above, and will not be repeated here.

[0116] Step S8032: Using the asymmetric cyclic sequence analysis method, the temperature sequence data of the third sedimentary layer in the second temperature time series data is processed to obtain multiple second sediment temperature amplitudes for multiple second pipe cross sections.

[0117] The specific process can be found in the description of step S7022 above, and will not be repeated here.

[0118] Step S8033: Based on the second water temperature sequence data and the third sedimentation layer temperature sequence data, determine multiple second phase lags for multiple second pipe sections.

[0119] The specific process can be found in the description of step S7023 above, and will not be repeated here.

[0120] Step S8034: Based on the temperature conductivity coefficient, multiple second water temperature amplitudes, multiple second sediment temperature amplitudes, and multiple second phase hysteresis, the thickness of multiple second sediment layers for multiple second pipe sections is obtained through processing with a preset function relationship.

[0121] Specifically, by substituting the obtained multiple second water temperature amplitudes, multiple second sediment temperature amplitudes, multiple second phase hysteresis, and the fitted temperature conductivity coefficient into the above relationships (1) and (2), the thicknesses of multiple second sedimentary layers at multiple second pipe sections can be calculated. )

[0122] Step S804: Based on multiple first sediment layer thicknesses and multiple second sediment layer thicknesses, the thickness variation of the sediment layer along the water flow direction within the pipeline to be predicted is predicted, thus obtaining the predicted sediment thickness of the pipeline. For details, please refer to [link to relevant documentation]. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0123] The pipeline sediment thickness prediction method provided in this embodiment uses Fourier series decomposition of water temperature time-series data and combines it with a dynamic regression model to capture harmonic components of different frequencies. This accurately extracts water temperature amplitude, solving the signal distortion problem caused by siltation and obstruction in laser ranging technology, and ensuring the integrity and reliability of water temperature reference data. Furthermore, through asymmetric cyclic sequence analysis, the temperature amplitude of sediments at different depths can be effectively extracted, overcoming the disturbance problem caused by contact measurement in pressure sensor thickness measurement technology. It is also unaffected by high or full water levels and adapts to the complex temperature changes of the first pipeline cross-section. Simultaneously, the asymmetry of sediment temperature changes is addressed, avoiding the uniformity assumption errors of hydraulic estimation techniques, thus accurately characterizing the temperature fluctuation characteristics of sediments at different depths. Furthermore, based on a preset functional relationship and combined with the fitted temperature conductivity coefficient, the thickness of multiple second sediment layers at multiple second pipeline cross-sections can be accurately calculated, achieving multi-temporal and spatial monitoring along the water flow direction with centimeter-level accuracy. This clearly characterizes the non-uniform changes in sediment layers, providing data support for pipeline operation and maintenance and dredging schemes.

[0124] This embodiment also provides a pipe deposit thickness prediction device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that implements 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.

[0125] This embodiment provides a device for predicting the thickness of pipe deposits, such as... Figure 9 As shown, the device includes:

[0126] The acquisition module 901 is used to acquire the thickness of multiple first deposit layers in the first pipe section of the pipe to be predicted, the first temperature time series data of multiple first temperature sensors in the first pipe section, and the second temperature time series data of multiple second temperature sensors in multiple second pipe sections. The first pipe section and multiple second pipe sections are determined according to the water flow direction in the pipe to be predicted.

[0127] The first processing module 902 is used to obtain the temperature conductivity coefficient based on the first temperature time series data and multiple first deposition layer thicknesses through a dynamic harmonic regression method.

[0128] The second processing module 903 is used to obtain the thickness of multiple second deposited layers for multiple second pipe sections by processing the second temperature time series data and temperature conductivity coefficient through a dynamic harmonic regression method.

[0129] The prediction module 904 is used to predict the thickness variation of the sediment layer in the pipeline to be predicted along the water flow direction based on multiple first sediment layer thicknesses and multiple second sediment layer thicknesses, and to obtain the sediment thickness prediction result of the pipeline to be predicted.

[0130] In some alternative implementations, the first processing module 902 includes:

[0131] The first processing submodule is used to process the first water temperature sequence data in the first temperature time series data using a dynamic regression model and Fourier series to obtain multiple first water temperature amplitudes of the first pipe cross section.

[0132] The second processing submodule is used to process the temperature sequence data of the first sediment layer in the first temperature time series data using the asymmetric cyclic sequence analysis method to obtain multiple first sediment temperature amplitudes of the first pipe section.

[0133] The first determining submodule is used to determine multiple first phase lags of the first pipe cross-section based on the first water temperature sequence data and the first sedimentation layer temperature sequence data.

[0134] The fitting submodule is used to obtain the temperature conductivity coefficient by fitting multiple first water temperature amplitudes, multiple first sediment temperature amplitudes, multiple first phase hysteresis, and multiple first sediment layer thicknesses through a preset functional relationship.

[0135] In some alternative implementations, the first processing submodule includes:

[0136] The decomposition unit is used to decompose the first temperature time series data using Fourier series to obtain multiple harmonic components.

[0137] The first processing unit is used to process the first water temperature sequence data based on multiple harmonic components using a dynamic regression model to obtain multiple first water temperature amplitudes.

[0138] In some optional implementations, the second processing submodule includes:

[0139] The second processing unit is used to simplify and reduce noise in the first temperature time series data to obtain third temperature time series data containing the temperature sequence data of the second deposition layer.

[0140] The analysis unit is used to analyze the temperature sequence data of the second sedimentary layer to obtain multiple local maximum values ​​and multiple local minimum values ​​of sediment temperature.

[0141] The determination unit is used to determine multiple first sediment temperature amplitudes based on multiple local maximum values ​​and multiple local minimum values ​​of sediment temperature.

[0142] In some alternative implementations, the second processing module 903 includes:

[0143] The third processing submodule is used to process the second water temperature sequence data in the second temperature time series data using dynamic regression model and Fourier series to obtain multiple second water temperature amplitudes of multiple second pipe sections.

[0144] The fourth processing submodule is used to process the temperature sequence data of the third sediment layer in the second temperature time series data using the asymmetric cyclic sequence analysis method, so as to obtain multiple second sediment temperature amplitudes of multiple second pipe sections.

[0145] The second determination submodule is used to determine multiple second phase lags of multiple second pipe sections based on the second water temperature sequence data and the third sedimentation layer temperature sequence data.

[0146] The fifth processing submodule is used to obtain the thickness of multiple second sediment layers for multiple second pipe sections by processing the temperature conductivity coefficient, multiple second water temperature amplitudes, multiple second sediment temperature amplitudes, and multiple second phase hysteresis through a preset function relationship.

[0147] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0148] In this embodiment, the pipeline deposit thickness prediction device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0149] This invention also provides a computer device having the above-described features. Figure 9 The pipe deposit thickness prediction device shown.

[0150] Please see Figure 10 , Figure 10 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 10 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 10 Take a processor 10 as an example.

[0151] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0152] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0153] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0154] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0155] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0156] 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, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0157] 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.

[0158] 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 all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for predicting the thickness of pipeline sediments, characterized in that, The method includes: The thickness of multiple first sediment layers in a first pipe section of the pipe to be predicted, the first temperature time series data of multiple first temperature sensors in the first pipe section, and the second temperature time series data of multiple second temperature sensors in multiple second pipe sections are obtained. The first pipe section and the multiple second pipe sections are determined according to the water flow direction in the pipe to be predicted. The first pipe section represents the section near the pipe inlet where the sediment thickness is large. The multiple second pipe sections are determined according to the pipe length and diameter. Based on the first temperature time series data and the thickness of the multiple first deposition layers, the temperature conductivity coefficient is obtained by processing with the dynamic harmonic regression method. The temperature conductivity coefficient represents a physical parameter characterizing the thermal conductivity of the deposits in the pipe and is used to reflect the rate characteristics of temperature transfer in the deposits. Based on the second temperature time series data and the temperature conductivity coefficient, the thickness of the second deposition layer of the multiple second pipe sections is obtained by processing with the dynamic harmonic regression method. The thickness variation of the sediment layer in the pipeline to be predicted along the water flow direction is predicted based on the thickness of the plurality of first sediment layers and the thickness of the plurality of second sediment layers, and the sediment thickness prediction result of the pipeline to be predicted is obtained. The sediment thickness prediction result is used to reflect the non-uniform variation of the sediment layer. The arrangement of the plurality of first temperature sensors is as follows: a temperature sensor is installed at the bottom of the pipe to record the temperature change of the bottom sediment; starting from the bottom, temperature sensors are installed on the side wall of the pipe at vertical intervals of 5 cm, until half the pipe diameter is reached. The arrangement of the multiple second temperature sensors is as follows: a temperature sensor is installed at the bottom of the pipe to record the temperature change of the bottom sediment; and temperature sensors are installed on the side wall of the pipe near the normal water level. Specifically, based on the first temperature time-series data and the thicknesses of the plurality of first deposition layers, the temperature conductivity coefficient is obtained through dynamic harmonic regression, including: The first water temperature sequence data in the first temperature time series data is processed using a dynamic regression model and Fourier series to obtain multiple first water temperature amplitudes of the first pipe cross section. The dynamic regression model represents a model for analyzing time series data, which can capture the trend and complex patterns of temperature time series by using the extracted harmonic components. The asymmetric cyclic sequence analysis method is used to process the temperature sequence data of the first sedimentary layer in the first temperature time series data to obtain multiple first sediment temperature amplitudes of the first pipe cross section. The asymmetric cyclic sequence analysis method is used to extract the amplitude and phase feature information of the fundamental frequency of the sediment temperature time series. Based on the first water temperature sequence data and the first sediment layer temperature sequence data, multiple first phase lags of the first pipe cross-section are determined. The phase lag represents the time difference between the water temperature and the sediment temperature reaching their peak values ​​within the same time period, and is used to reflect the lag characteristics of temperature transfer between the water body and the sediment layer. The temperature conductivity coefficient is obtained by fitting a preset function relationship based on the plurality of first water temperature amplitudes, the plurality of first sediment temperature amplitudes, the plurality of first phase hysteresis, and the plurality of first sediment layer thicknesses.

2. The method according to claim 1, characterized in that, The first water temperature sequence data in the first temperature time series data is processed using a dynamic regression model and Fourier series to obtain multiple first water temperature amplitudes of the first pipe cross-section, including: The first temperature time series data is decomposed using the Fourier series to obtain multiple harmonic components; Based on the multiple harmonic components, the first water temperature sequence data is processed using the dynamic regression model to obtain the multiple first water temperature amplitudes.

3. The method according to claim 1, characterized in that, Using an asymmetric cyclic sequence analysis method, the temperature sequence data of the first sedimentary layer in the first temperature time series data is processed to obtain multiple first sediment temperature amplitudes of the first pipe cross-section, including: The first temperature time series data is simplified and denoised to obtain a third temperature time series data that includes the temperature sequence data of the second deposition layer. Analysis of the temperature sequence data of the second sedimentary layer yielded multiple local maxima and multiple local minima of sediment temperature. The amplitudes of the first sediment temperature are determined based on the local maximum and local minimum values ​​of the multiple sediment temperatures.

4. The method according to claim 1, characterized in that, Based on the second temperature time series data and the temperature conductivity coefficient, and processed by the dynamic harmonic regression method, the thicknesses of multiple second deposition layers in the multiple second pipe cross sections are obtained, including: The dynamic regression model and the Fourier series are used to process the second water temperature sequence data in the second temperature time series data to obtain multiple second water temperature amplitudes of the multiple second pipe sections; Using the asymmetric cyclic sequence analysis method, the temperature sequence data of the third sedimentary layer in the second temperature time series data is processed to obtain multiple second sediment temperature amplitudes of the multiple second pipe sections; Based on the second water temperature sequence data and the third sediment layer temperature sequence data, multiple second phase lags of the multiple second pipe cross sections are determined; Based on the temperature conductivity coefficient, the plurality of second water temperature amplitudes, the plurality of second sediment temperature amplitudes, and the plurality of second phase hysteresis, the plurality of second sediment layer thicknesses of the plurality of second pipe cross sections are obtained through the preset function relationship processing.

5. A device for predicting the thickness of sediment deposits in a pipeline, characterized in that, The device includes: The acquisition module is used to acquire the thickness of multiple first deposit layers in a first pipe section of the pipe to be predicted, the first temperature time series data of multiple first temperature sensors in the first pipe section, and the second temperature time series data of multiple second temperature sensors in multiple second pipe sections. The first pipe section and the multiple second pipe sections are determined according to the water flow direction in the pipe to be predicted. The first pipe section represents the section near the pipe inlet where the deposit thickness is relatively large. The multiple second pipe sections are determined according to the pipe length and diameter. The first processing module is used to obtain the temperature conductivity coefficient based on the first temperature time series data and the thickness of the multiple first deposition layers through a dynamic harmonic regression method. The second processing module is used to obtain the thickness of multiple second deposition layers of the multiple second pipe sections by processing the second temperature time series data and the temperature conductivity coefficient through the dynamic harmonic regression method. The prediction module is used to predict the thickness variation of the sediment layer in the pipeline to be predicted along the water flow direction based on the thickness of the plurality of first sediment layers and the thickness of the plurality of second sediment layers, so as to obtain the sediment thickness prediction result of the pipeline to be predicted. The arrangement of the plurality of first temperature sensors is as follows: a temperature sensor is installed at the bottom of the pipe to record the temperature change of the bottom sediment; starting from the bottom, temperature sensors are installed on the side wall of the pipe at vertical intervals of 5 cm, until half the pipe diameter is reached. The arrangement of the multiple second temperature sensors is as follows: a temperature sensor is installed at the bottom of the pipe to record the temperature change of the bottom sediment; and temperature sensors are installed on the side wall of the pipe near the normal water level. The first processing module includes: The first processing submodule is used to process the first water temperature sequence data in the first temperature time series data using a dynamic regression model and Fourier series to obtain multiple first water temperature amplitudes of the first pipe cross section. The dynamic regression model represents a model for analyzing time series data, which can capture the trend and complex patterns of temperature time series using the extracted harmonic components. The second processing submodule is used to process the temperature sequence data of the first sediment layer in the first temperature time series data using an asymmetric cyclic sequence analysis method to obtain multiple first sediment temperature amplitudes of the first pipe cross section. The asymmetric cyclic sequence analysis method is used to extract amplitude and phase feature information in the fundamental frequency of the sediment temperature time series. The first determining submodule is used to determine multiple first phase lags of the first pipe cross-section based on the first water temperature sequence data and the first sediment layer temperature sequence data. The phase lag represents the time difference between the water temperature and the sediment temperature reaching their peak values ​​within the same time period, and is used to reflect the lag characteristics of temperature transfer between the water body and the sediment layer. The fitting submodule is used to obtain the temperature conductivity coefficient by fitting the plurality of first water temperature amplitudes, the plurality of first sediment temperature amplitudes, the plurality of first phase hysteresis and the plurality of first sediment layer thicknesses through a preset functional relationship.

6. A computer 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 pipe deposit thickness prediction method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the pipe deposit thickness prediction method according to any one of claims 1 to 4.

8. A computer program product, characterized in that, Includes computer instructions for causing a computer to perform the pipe deposit thickness prediction method according to any one of claims 1 to 4.

Images