Method and system for predicting scouring trend of full-hall high-pile wharf

Abstract

The invention discloses a method and system for predicting the scouring trend of a full-hall long-piled wharf, and belongs to the field of port engineering monitoring. The method comprises the following steps: firstly, constructing an embedded ultrasonic array monitoring system, arranging probes according to regions to realize accurate deployment and control, and synchronously acquiring acoustic data and environmental parameters; noise reduction, inversion and fusion processing are carried out on the data, and normal deposition fluctuation and abnormal scouring events are distinguished by combining shallow water acoustic modeling and a scouring mechanism recognition algorithm; and finally, predicting the current siltation state through an improved DWMA model, predicting the scouring trend by means of an improved LSTM physical hybrid model, and realizing risk visualization based on a grading early warning mechanism. The system can adapt to the dense pile foundation environment of the full-space high-pile wharf, effectively solves the problems of large blind area and high error in traditional monitoring, remarkably improves the monitoring precision and early warning timeliness, and provides powerful support for safe operation and maintenance of the wharf.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of port engineering monitoring, in particular to a full-bay high-pile wharf scouring trend prediction method and system. BACKGROUND

[0002] In recent years, full-bay high-pile wharfs are widely used in port engineering construction due to their stable structure and strong adaptability. The safety operation of the wharf is closely related to the scouring and deposition state of the seabed. Scouring of the seabed can lead to insufficient depth of the pile foundation, causing structural instability, while deposition can affect the navigation capacity of the wharf and the stress balance of the structure. Therefore, continuous monitoring and trend prediction of the scouring and deposition state of the seabed around the pile foundation are crucial to ensure the long-term safe operation of the wharf.

[0003] Currently, there are two major difficulties in the scouring and deposition monitoring and prediction of full-bay high-pile wharfs. On the one hand, there are significant limitations in equipment deployment. Traditional monitoring relies on an array of rigid sensors, but the dense pile foundation of full-bay high-pile wharfs and the narrow underwater space make it difficult to arrange sensors reasonably, resulting in large blind areas. At the same time, the strong turbulence in the underwater environment of the wharf can cause sensor drift, poor data stability, and an inability to accurately capture dynamic evolution details such as instantaneous scouring caused by local vortices, making it difficult to meet the seamless monitoring needs of the entire cross-section.

[0004] On the other hand, existing prediction models have obvious defects. Current prediction methods are mostly based on historical statistical data or simplified hydrodynamic equations, without fully considering the riverbed-flow coupling effect and without integrating real-time monitoring data, resulting in large fluctuations in prediction errors, usually exceeding 20%. In addition, the model parameter update cycle is long, and it cannot quickly respond to short-term extreme hydrological events such as tidal mutations, making it difficult to accurately predict short-term scouring and deposition trends and providing timely and effective decision support for wharf operation and maintenance.

[0005] To solve the above problems, related fields have tried to optimize sensor deployment or improve prediction models, but neither has formed a systematic solution for the structural characteristics of full-bay high-pile wharfs. Sensor deployment still faces space limitations due to dense pile foundations, and the monitoring accuracy and coverage are insufficient; the prediction model has not effectively integrated real-time data and physical mechanisms, and the short-term prediction accuracy and dynamic response capability need to be improved, making it difficult to meet the actual needs of accurate monitoring, reliable prediction, and timely warning of scouring and deposition state for wharf safety operation. SUMMARY

[0006] Therefore, the present application proposes a full-bay high-pile wharf scouring trend prediction method, characterized by the following steps: Step (1), build an embedded ultrasonic array monitoring system, arrange ultrasonic probes according to the scouring risk distribution zoning of the underwater structure of the wharf, and optimize the installation parameters and array topology of the probes; Step (2), collecting multi-dimensional monitoring data, including acoustic data and environmental parameters, the acoustic data being acquired by the ultrasonic probe; Step (3), processing the monitoring data in the whole process to improve the data quality through time delay window dynamic control, wavelet threshold denoising, echo path discrimination, acoustic impedance inversion and data fusion optimization; Step (4), using an improved dynamic weighted moving average (DWMA) model, combining time decay weight and Kalman filter residual correction term, predicting the current sedimentation state based on the monitoring data processed in the whole process; Step (5), constructing an improved LSTM physical hybrid model, fusing hydrodynamic terms and data-driven terms, setting adaptive weights and sliding time windows for incremental training, predicting risk indexes based on the current sedimentation state to realize graded early warning, and connecting to a digital twin platform for visual presentation.

[0007] Further, in step (1), the ultrasonic probe is arranged at the front and rear capping tables of each bent pile and the junction of adjacent bent piles, and the array topology is optimized by finite element simulation; the optimized array topology specifically includes optimizing the probe working frequency, layout spacing and pointing angle through water tank simulation and numerical analysis; the embedded ultrasonic array works in a multi-unit cooperative scanning mode.

[0008] Further, in step (2), the acoustic data includes echo time delay, amplitude decay rate and frequency shift, and the environmental parameters include hydrological data and meteorological correlation parameters; the hydrological data includes flow rate, flow direction, tidal level and sediment concentration, and the meteorological correlation parameters include wind speed and wave height.

[0009] Further, in step (3), the time delay window width calculation formula is where D(t) is the real-time water depth, c is the sound speed, is the standard deviation of environmental noise, and k is the noise constant; the echo path discrimination separates the cross-correlation algorithm formula of the reflected wave as where is the time delay, x(t) is the original ultrasonic pulse signal transmitted, and y(t+τ) is the mixed echo signal received; the acoustic impedance inversion is realized by calculating the reflection coefficient, and the calculation formula of the reflection coefficient is where , is the medium density, , is the acoustic impedance of the adjacent medium.

[0010] Further, the monitoring data is transmitted to the shore-based data processing module for waveform analysis, noise suppression and echo peak identification, and then combined with the historical monitoring sequence to construct the erosion evolution trend curve.

[0011] Further, in the step (4), the dynamic weighted moving average (DWMA) model calculation formula is: , wherein, is the local erosion depth at time t, is the model calibration coefficient, is the number of ultrasonic probes participating in the calculation, is the time decay weight, is the echo time delay variation of the i-th probe, is the spatial adaptation coefficient, is the sound speed of the i-th probe after temperature and salinity compensation correction, is the initial erosion depth, is a random error term.

[0012] Further, in the step (4), the time decay weight calculation formula is: , wherein , t is the time, is the time of the i-th event or data point; the beta coefficient is optimized to adapt to the spatial distribution of multiple probes, and the local erosion rate difference is combined with the multi-probe collaborative inversion, and the sensor drift error is corrected by Kalman filtering.

[0013] Further, in the step (5), the LSTM physical hybrid model calculation formula is: , wherein, is the hydrodynamic term, u is the flow velocity vector, H is the erosion depth, is the hydrodynamic term weight coefficient, is the feature mapping function of the LSTM model, is the sediment concentration, is the pile foundation vibration spectrum, is the dynamic noise suppression term weight, is the dynamic noise suppression term.

[0014] Further, in the step (5), the LSTM physical hybrid model adopts an incremental training mechanism, and based on the classification results of normal sediment fluctuations and abnormal erosion events, a hierarchical early warning threshold is drawn, and the seabed morphology changes are presented in a three-dimensional visual form through a digital twin platform.

[0015] The application further provides a full-bay high-pile wharf scouring trend prediction system for implementing the full-bay high-pile wharf scouring trend prediction method, and has the characteristics that the system comprises an embedded ultrasonic array monitoring unit, a multi-dimensional data acquisition unit, a monitoring data processing unit, a siltation state prediction unit and a scouring trend prediction and early warning unit. The embedded ultrasonic array monitoring unit is used to construct an embedded ultrasonic array monitoring system, arrange ultrasonic probes according to the scouring risk distribution zoning of the underwater structure of the wharf, and optimize the installation parameters and array topology of the probes. The multi-dimensional data acquisition unit is used to acquire multi-dimensional monitoring data, wherein the multi-dimensional monitoring data comprises acoustic data and environmental parameters, and the acoustic data is acquired by the ultrasonic probes. The monitoring data processing unit is used to perform full-process processing on the monitoring data, and improve the data quality through time delay window dynamic control, wavelet threshold denoising, echo path discrimination, acoustic impedance inversion and data fusion optimization. The siltation state prediction unit is used to predict the siltation state at the current time based on the monitoring data processed by the full-process processing, by using an improved dynamic weighted moving average (DWMA) model, combining a time attenuation weight and a Kalman filter residual correction term. The scouring trend prediction and early warning unit is used to construct an improved LSTM physical hybrid model, fuse a hydrodynamic term and a data-driven term, set adaptive weights and a sliding time window for incremental training, realize graded early warning based on the risk index predicted based on the siltation state at the current time, and visually present on a digital twin platform.

[0016] The above description is only a summary of the technical solutions of the application, in order to more clearly understand the technical means of the application, the application can be implemented according to the content of the specification, and in order to make the above and other purposes, characteristics and advantages of the application more obvious and easy to understand, the following will specifically describe the embodiments of the application. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the specific embodiments of the application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or the prior art description. Obviously, the drawings in the following description are some embodiments of the application, and those skilled in the art can also obtain other drawings according to these drawings without creating any creative labor.

[0018] Figure 1 The flowchart of the full-bay high-pile wharf scouring trend prediction method.

[0019] Figure 2 The schematic diagram of the architecture of the full-bay high-pile wharf scouring trend prediction system. DETAILED DESCRIPTION

[0020] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work belong to the scope of protection of the present application.

[0021] As shown in the accompanying Figure 1 and the accompanying Figure 2 The present application discloses a full-bank high-pile wharf scouring trend prediction method, characterized in that it comprises the following steps: Step (1), an embedded ultrasonic array monitoring system is constructed, ultrasonic probes are arranged according to the scouring risk distribution zoning of the underwater structure of the wharf, and the probe installation parameters and array topology are optimized. The ultrasonic probes are arranged at the front and rear pile caps of each bent and the junctions of adjacent bents, and the array topology is optimized through finite element simulation. The optimization of the array topology specifically includes optimizing the probe working frequency, layout spacing and pointing angle through water channel simulation and numerical analysis. The embedded ultrasonic array works in a multi-unit cooperative scanning mode.

[0022] Specifically, the zoning layout scheme is arranged as follows: For the front pile cap (upstream face): 53 main probes are arranged according to the bent unit, 26 auxiliary probes are additionally arranged at the junctions of adjacent bents, and the gap between pile groups (which is prone to vortex area) is mainly covered, the probe spacing is 1.2 m, and a "main-auxiliary" cross monitoring network is formed; For the rear pile cap (downstream face): due to the gentle change of siltation, one main probe is arranged every two bent units, a total of 27, and no auxiliary probe is additionally arranged at the junctions, the probe spacing is 2.4 m; For the corner of the wharf (area where the flow direction changes suddenly): 8 wide-angle probes (pointing angle 150°) are additionally arranged to cover the blind area of the traditional probe monitoring.

[0023] The optimization of the array topology through finite element simulation specifically includes joint simulation of ANSYS Fluent and ANSYS APDL, first simulating the underwater flow field distribution (flow velocity, vortex intensity) of the wharf to determine 12 high-risk scouring points; then establishing a three-dimensional model of the ultrasonic array, setting the water sound speed to 1500 m / s and the riverbed sediment sound speed to 1800 m / s, and simulating the sound wave propagation path and reflection signal intensity; Based on the optimization results, the probe spacing is adjusted from 1.5 m to 1.2 m (front pile cap), and the monitoring blind area coverage rate is reduced from the initial 6.8% to 2.9%; by increasing the wide-angle probe, the blind area at the corner of the wharf is completely eliminated, and the final monitoring blind area coverage rate of the whole wharf is controlled at 2.1%, meeting the design requirement of ≤5%.

[0024] Step (2), collecting multi-dimensional monitoring data, including acoustic data and environmental parameters, the acoustic data being obtained by the ultrasonic probe. Further, in step (2), the acoustic data includes echo time delay, amplitude decay rate and frequency offset, and the environmental parameters include hydrological data and meteorological correlation parameters; the hydrological data includes flow rate, flow direction, tidal level and sediment concentration, and the meteorological correlation parameters include wind speed and wave height.

[0025] In order to realize effective collection of multi-dimensional monitoring data, each monitoring unit is configured with one data acquisition terminal (integrated with the array control module), and the acquisition frequency can be dynamically adjusted: 1 time / minute under normal working conditions, 1 time / 10 seconds in typhoon season (wind speed ≥10 m / s), to ensure the timeliness of data in extreme environment.

[0026] The data transmission link adopts a three-level transmission architecture of "edge node-land-based base station-cloud platform". Specifically, the edge node acquisition terminal aggregates the probe data in the unit through the RS485 bus, and completes the preliminary noise reduction based on mean filtering. The land-based base station is deployed with several 4G / 5G base stations, which receive edge node data through LoRa wireless communication and store them synchronously to the local server. The cloud platform uses Ali Cloud servers, and the land-based base station pushes complete data to the cloud once every preset time for remote access and data analysis by the cloud platform.

[0027] Step (3), processing the monitoring data in the whole process, and improving the data quality through time delay window dynamic control, wavelet threshold denoising, echo path discrimination, acoustic impedance inversion and data fusion optimization; Further, in step (3), the time delay window width calculation formula is where D(t) is the real-time water depth, c is the sound speed, is the standard deviation of environmental noise, k is the noise constant; the standard deviation of environmental noise The standard deviation of environmental noise is obtained by 10 times of continuous no-signal measurement (shielding the probe transmitting end).

[0028] The 1. wavelet threshold denoising adopts Symlet5 basis function to perform 5-layer wavelet decomposition on the echo signal, and the coefficients of each layer after decomposition are processed by heuristic threshold (Heuristic SURE), and the threshold calculation is wherein N is the signal length; wherein σ is the noise standard deviation; The echo path discrimination separation reflected wave cross-correlation algorithm formula is wherein is the time delay, x(t) is the transmitted original ultrasonic pulse signal (such as the sound wave emitted by the probe), y(t+τ) is the received mixed echo signal (containing direct wave, pile foundation reflected wave, riverbed reflected wave); the cross-correlation algorithm is used to calculate the cross-correlation coefficient of the original signal and the reference signal, i.e. the mixed echo signal, the cross-correlation coefficient range is set, the direct wave, the pile foundation reflected wave and the riverbed reflected wave are distinguished, and the accurate separation of the three types of echoes is realized.

[0029] The acoustic impedance inversion is realized by the reflection coefficient calculation, and the calculation formula of the reflection coefficient is wherein , is the medium density, , is the acoustic impedance of the adjacent medium; specifically, the sound pressure distribution under different deposition thicknesses is simulated, the riverbed reflected wave sound pressure amplitude is extracted, and the deposition thickness is inverted in combination with the reflection coefficient formula.

[0030] Further, the monitoring data is classified by using the shallow water acoustic modeling and scour mechanism identification algorithm, the normal deposition fluctuation and the abnormal scour event are distinguished, the monitoring data is first transmitted to the shore-based data processing module for waveform analysis, noise suppression and echo peak identification, and then the scour evolution trend curve is constructed in combination with the historical monitoring sequence.

[0031] The shallow water acoustic modeling specifically includes building a three-dimensional layered model for the shallow water environment, inputting real-time parameters to correct the sound speed and attenuation coefficient, setting the pile foundation (hard boundary), the pile cap (gradual boundary), the riverbed (layered boundary) and correcting the multi-path error; the finite difference time domain (FDTD) method is used to solve the acoustic wave equation, and the simulation results show that only a single riverbed interface echo peak appears under the normal deposition state, and the abnormal scour event is manifested as a missing section of echo or a multi-interface disorder echo, which provides a characteristic basis for subsequent mechanism identification.

[0032] The scour mechanism identification algorithm specifically includes distinguishing the event by “feature extraction + two-level classification”: extracting three types of features including interface stability, sound field distribution and dynamic change, the two-level classification includes the first level using 1000+ sample random forest (accuracy > 95%) for preliminary judgment, and the second level according to the historical threshold to eliminate false anomalies, and outputting an event report containing the basis.

[0033] Step (4), an improved dynamic weighted moving average (DWMA) model is used, combined with the time attenuation weight and the Kalman filter residual correction term, to predict the deposition state at the current time based on the monitoring data processed by the whole process. Further, in the step (4), the dynamic weighted moving average DWMA model calculation formula is: , wherein, is the local scour depth at time t, is the model calibration coefficient, is the number of ultrasonic probes participating in the calculation, is the time decay weight, is the echo time delay variation of the i-th probe, is the spatial adaptation coefficient, is the sound speed of the i-th probe after the temperature and salinity compensation correction, is the initial scour depth (reference depth), is a random error term.

[0034] Further, in the step (4), the time decay weight calculation formula is: , wherein , t is the time, is the time of the i-th event or data point, and is the historical time; the spatial distribution of multiple probes is adapted by optimizing the spatial adaptation coefficient, and the local scour rate difference is combined with the multi-probe collaborative inversion, and the sensor drift error is corrected by means of Kalman filtering.

[0035] Step (5), an improved LSTM physical hybrid model is constructed, a water dynamic term and a data driven term are fused, an adaptive weight and a sliding time window are set for incremental training, a risk index is predicted based on the current time siltation state to realize graded early warning, and a digital twin platform is accessed to realize visual presentation.

[0036] Further, in the step (5), the LSTM physical hybrid model calculation formula is: , wherein, is the water dynamic term, u is the flow velocity vector (real-time monitoring input), and H is the scour depth, is the water dynamic term weight coefficient, is the feature mapping function of the LSTM model, is the sediment concentration, is the pile foundation vibration spectrum, is the dynamic noise suppression term weight, is the dynamic noise suppression term, the noise suppression term is dynamically adjusted based on the Kalman filtering residual error, and the interference of environmental noise on the prediction is suppressed.

[0037] The LSTM network, the input layer is the sediment concentration, the pile foundation vibration spectrum (set frequency range, extract a certain number of characteristic values), and the silt thickness sequence in the past set time length, the hidden layer is set to a certain number of layers (each layer is set to a certain number of neurons), and the output layer is the scour rate prediction value, and the weight is adjusted by an adaptive algorithm Further, in step (5), the LSTM physical mixing model adopts an incremental training mechanism, and a hierarchical warning threshold is determined based on normal deposition fluctuations and abnormal scour event classification results, and seabed morphology changes are presented in a three-dimensional visual form through a digital twin platform.

[0038] Real-time calculation of risk index, formula Calculation, wherein Determine according to the safety standard of the pier pile foundation (the scour depth exceeding this value is easy to lead to the instability of the pile foundation), k is the trend sensitivity coefficient, The scour rate is set; the threshold range corresponding to different risk levels is set, which corresponds to the safe, attention and warning state respectively; when the risk index reaches the warning threshold, the corresponding warning is triggered.

[0039] In the digital twin platform, real-time monitoring data and prediction results are accessed, and scour risk areas are marked with different colors in a three-dimensional interface corresponding to different risk levels. Clicking on any monitoring point can view real-time data and historical trend curves, including deposition thickness, flow rate, risk index, etc. When the warning is triggered, the platform automatically sends an SMS and a push notification to the mobile APP of the operation and maintenance personnel, including the warning location, risk level, recommended measures, such as riprap protection, flow rate monitoring encryption, etc., and the control response time is within the set range.

[0040] Embodiment two The application also provides a full-bay high-pile wharf scour trend prediction system for realizing the full-bay high-pile wharf scour trend prediction method. The embedded ultrasonic array monitoring unit is used to construct an embedded ultrasonic array monitoring system, arrange ultrasonic probes according to the scour risk distribution zoning of the underwater structure of the wharf, and optimize the probe installation parameters and array topology. The multi-dimensional data acquisition unit is used to acquire multi-dimensional monitoring data, and the multi-dimensional monitoring data includes acoustic data and environmental parameters, and the acoustic data is obtained by the ultrasonic probe.

[0041] The monitoring data processing unit is used for full-process processing of monitoring data, and the data quality is improved through time delay window dynamic control, wavelet threshold denoising, echo path discrimination, acoustic impedance inversion and data fusion optimization. The deposition state prediction unit is used to predict the current deposition state based on the full-process processed monitoring data by using an improved dynamic weighted moving average (DWMA) model combined with a time decay weight and a Kalman filter residual correction term. The scouring trend prediction and early warning unit is configured to build an improved LSTM physical hybrid model, fuse a hydrodynamic term and a data-driven term, set adaptive weights and a sliding time window for incremental training, realize graded early warning based on a current time point siltation state prediction risk index, and access a digital twin platform to realize visual presentation.

[0042] It can be understood that the system and unit provided by the embodiment can also be used to implement each step in the method provided by other embodiments of the application.

[0043] The application also provides a computer device. The computer device is in the form of a general-purpose computing device. The components of the computer device can include, but are not limited to, one or more processors or processing units, system memory, and a bus connecting different system components.

[0044] The computer device typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device and includes both volatile and nonvolatile media, removable and non-removable media.

[0045] The system memory can include computer system readable media in the form of volatile memory, and the memory can include at least one program product having a set (for example, at least one) of program modules configured to perform the functions of the embodiments of the application.

[0046] The processing unit performs various functional applications and data processing by running the programs stored in the system memory, for example, implements the method provided by other embodiments of the application.

[0047] The application also provides a storage medium containing computer executable instructions, and a computer program is stored on the storage medium, and the program is executed by a processor to implement the method provided by other embodiments of the application.

[0048] Note that the above is only the preferred embodiment of the application and the technical principles applied. Those skilled in the art will understand that the application is not limited to the specific embodiments described herein, and those skilled in the art can make various obvious changes, readjustments and substitutions without departing from the scope of the application. Therefore, although the application has been described in more detail through the above embodiments, the application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the application, and the scope of the application is determined by the scope of the appended claims.

Claims

1. A method for predicting scouring trend of a full-pile wharf, characterized in that, The method comprises the following steps: Step (1), constructing an embedded ultrasonic array monitoring system, arranging ultrasonic probes according to the risk distribution partition of the scour of the underwater structure of the wharf, and optimizing the installation parameters and array topology of the probes; Step (2), collecting multi-dimensional monitoring data, including acoustic data and environmental parameters, wherein the acoustic data is obtained by the ultrasonic probe; Step (3), processing the monitoring data in the whole process, and improving the data quality through time delay window dynamic control, wavelet threshold denoising, echo path discrimination, acoustic impedance inversion and data fusion optimization; Step (4), using an improved dynamic weighted moving average (DWMA) model, combining time attenuation weight and Kalman filter residual correction term, and predicting the current deposition state based on the monitoring data processed in the whole process; Step (5), constructing an improved LSTM physical hybrid model, fusing hydrodynamic terms and data-driven terms, setting adaptive weights and sliding time windows for incremental training, predicting the risk index based on the current deposition state to realize graded warning, and connecting to a digital twin platform for visual presentation. 2.The method according to claim 1, wherein, In step (1), the ultrasonic probes are arranged at the front and rear pile caps of each bent and the junction of adjacent bents, and the array topology is optimized through finite element simulation; the optimized array topology specifically includes optimizing the probe working frequency, arrangement spacing and pointing angle through water tank simulation and numerical analysis; the embedded ultrasonic array works in a multi-unit cooperative scanning mode. 3.The method according to claim 1, wherein, In step (2), the acoustic data includes echo time delay, amplitude decay rate and frequency shift, and the environmental parameters include hydrological data and meteorological related parameters; the hydrological data includes flow rate, flow direction, tidal level and sediment concentration, and the meteorological related parameters include wind speed and wave height. 4.The method according to claim 1, wherein, In the step (3), the time delay window width calculation formula is: Wherein, D(t) is real-time water depth, c is sound speed, is standard deviation of environmental noise, k is noise constant; the echo path discrimination separation reflection wave cross-correlation algorithm formula is: Wherein is time delay, x(t) is transmitted original ultrasonic pulse signal, y(t+τ) is received mixed echo signal; the acoustic impedance inversion is realized by reflection coefficient calculation, the reflection coefficient calculation formula is Wherein , is medium density, , is acoustic impedance of adjacent medium.

5. The method according to claim 4, wherein, The monitoring data is classified by shallow water acoustic modeling and scour mechanism identification algorithm to distinguish normal deposition fluctuations from abnormal scour events; the monitoring data is first transmitted to a shore-based data processing module for waveform analysis, noise suppression and echo peak identification, and then a scour evolution trend curve is constructed based on the historical monitoring sequence. 6.The method according to claim 1, wherein, In the step (4), the dynamic weighted moving average DWMA model calculation formula is: wherein, is a local scouring depth at time t, is a model calibration coefficient, is a number of ultrasonic probes participating in calculation, is a time decay weight, is an echo time delay variation of the i-th probe, is a spatial adaptation coefficient, is a sound speed of the i-th probe after temperature-salinity compensation correction, is an initial scouring depth, is a random error term.

7. The method according to claim 6, wherein, In the step (4), the time decay weight calculation formula is: , wherein t is the time at that time, is the time of the i th event or data point; the multiple probe spatial distribution is optimized and adapted through the β coefficient, the local scour rate difference is combined with the multiple probe collaborative inversion, and the sensor drift error is corrected by means of Kalman filtering. 8.The method according to claim 1, wherein, In the step (5), the LSTM physical mixing model calculation formula is: wherein, is a hydrodynamic term, u is a flow velocity vector, H is a scouring depth, is a hydrodynamic term weight coefficient, is a feature mapping function of the LSTM model, is a sediment concentration, is a pile foundation vibration frequency spectrum, is a dynamic noise suppression term weight, is a dynamic noise suppression term. 9.The method according to claim 8, wherein, In step (5), the LSTM physical hybrid model adopts an incremental training mechanism, sets graded warning thresholds based on the classification results of normal deposition fluctuations and abnormal scour events, and presents the seabed morphology changes in a three-dimensional visual form through a digital twin platform.

10. A system for predicting scouring tendency of a full-piled wharf, for implementing the method for predicting scouring tendency of a full-piled wharf according to any one of claims 1 to 9, characterized in that, It comprises: an embedded ultrasonic array monitoring unit, a multi-dimensional data acquisition unit, a monitoring data processing unit, a deposition state prediction unit and a scour trend prediction and warning unit; the embedded ultrasonic array monitoring unit is used to construct an embedded ultrasonic array monitoring system, arrange ultrasonic probes according to the risk distribution partition of the scour of the underwater structure of the wharf, and optimize the installation parameters and array topology of the probes; the multi-dimensional data acquisition unit is used to collect multi-dimensional monitoring data, wherein the multi-dimensional monitoring data includes acoustic data and environmental parameters, and the acoustic data is obtained by the ultrasonic probe; the monitoring data processing unit is used to process the monitoring data in the whole process, and improve the data quality through time delay window dynamic control, wavelet threshold denoising, echo path discrimination, acoustic impedance inversion and data fusion optimization; The siltation state prediction unit is configured to predict the siltation state at the current time based on the monitoring data after the whole process treatment by using an improved dynamic weighted moving average (DWMA) model, combining a time attenuation weight and a Kalman filter residual correction term. The scour trend prediction and early warning unit is configured to construct an improved LSTM physical hybrid model, fuse a hydrodynamic term and a data-driven term, set adaptive weights and a sliding time window for incremental training, realize graded early warning based on a risk index predicted by the siltation state at the current time, and access a digital twin platform for visual presentation.

Images