Dynamic optimization method and system for construction parameters of cemented riprap in wave-current environment

Abstract

The application provides a dynamic optimization method and system for cemented riprap construction parameters in a wave flow environment, and relates to the technical field of construction parameter determination. First, time sequence information of various environmental parameters in a specified construction area is extracted from multiple dimensions, and the various environmental parameters are subjected to spatiotemporal alignment processing. Second, construction parameter information is recorded in real time, and is associated with environmental parameter information and construction effect information according to construction rounds. Finally, a time sequence prediction model for representing construction conditions is obtained based on the above data, so that the best construction parameter information can be predicted based on environmental parameters and expected construction effect information in a future preset time interval. The technical scheme of the application can accurately predict cemented riprap construction parameters in a wave flow environment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of construction parameter determination, in particular to a dynamic optimization method and system for construction parameters of cemented riprap in a wave-current environment. BACKGROUND

[0002] In a strong current and wave-coupled marine environment, the traditional cemented riprap construction has problems such as difficulty in real-time matching of riprap particle size, throwing height, and cementing material pouring speed with flow field changes, resulting in unstable cementing effect, material waste, and performance degradation of the protection structure. The prior art lacks dynamic adjustment capability for construction parameters, and cannot realize intelligent construction. SUMMARY

[0003] The purpose of the present application is to provide a dynamic optimization method and system for construction parameters of cemented riprap in a wave-current environment, which can solve the technical problem of inaccurate prediction of construction parameters during the construction process of cemented riprap.

[0004] The present application provides a dynamic optimization method for construction parameters of cemented riprap in a wave-current environment, which comprises the following steps:

[0005] S1: Collecting at least one multi-source data sequence, performing data optimization extraction processing on the at least one multi-source data sequence to obtain at least one first flow field feature vector;

[0006] S2: Obtaining at least one construction parameter feature vector and at least one first construction effect information in the construction process, and determining a space-time correlation database according to the correlation between the at least one construction parameter feature vector, the at least one first construction effect information, and the at least one first flow field feature vector;

[0007] S3: Predicting target construction parameter information according to a target flow field feature vector and target construction effect information;

[0008] S4: After confirming the target construction parameter information, performing issuing and recording processing.

[0009] Preferably, the S1 comprises:

[0010] S11: Arranging at least one first multi-source sensor in a first ship and a first construction range to obtain a flow velocity data sequence, a wave data sequence, and a ship motion data sequence;

[0011] S12: Performing space-time alignment fusion processing on the flow velocity data sequence, the wave data sequence, and the ship motion data sequence to obtain a target flow velocity data sequence, a target wave data sequence, and a target ship motion data sequence;

[0012] S13: performing data quality optimization processing and feature extraction processing on the target flow velocity data sequence, the target wave data sequence and the target ship movement data sequence to obtain at least one first flow field feature vector.

[0013] Preferably, in each of the first flow field feature vectors, a combined vector of flow velocity data, wave data and ship movement data within a specified time interval is included.

[0014] Preferably, the S2 comprises:

[0015] S21: performing real-time data acquisition on construction parameters to obtain at least one construction parameter feature vector;

[0016] S22: determining at least one first construction effect information according to the first digital elevation model obtained after each construction;

[0017] S23: combining the at least one first flow field feature vector, the at least one construction parameter feature vector and the at least one first construction effect information into a space-time correlation database.

[0018] Preferably, the S22 comprises:

[0019] S221: after each construction is completed, performing full-coverage topographic survey on the construction area to obtain a first digital elevation model;

[0020] S222: obtaining first cemented body information according to the first digital elevation model and the original digital elevation model;

[0021] S223: obtaining first construction effect information according to the first cemented body information and first design blueprint information.

[0022] Preferably, at least one data record is included in the space-time correlation database.

[0023] Preferably, the S3 comprises:

[0024] S31: training a construction parameter prediction model according to the space-time correlation database;

[0025] S32: inputting a target flow field feature vector and target construction effect information into the construction parameter prediction model to obtain target construction parameter information;

[0026] S33: when the amount of construction records accumulated exceeds a first preset value, incrementally learning the construction parameter prediction model.

[0027] Preferably, in the training process of the construction parameter prediction model, the flow field feature vector and the construction effect information in the sample data are taken as input data, and the construction parameter feature vector is taken as output data.

[0028] Preferably, the S4 comprises:

[0029] S41: displaying the target construction parameter information on the digital board, and performing a delivery operation after a confirmation operation;

[0030] S42: recording the target construction parameter information and the parameter adjustment information into an operation log.

[0031] The application also proposes a dynamic optimization system for construction parameters of cemented riprap in a wave flow environment, which is used to implement the dynamic optimization method for construction parameters of cemented riprap in a wave flow environment.

[0032] The dynamic optimization method and system for construction parameters of cemented riprap in a wave flow environment proposed by the application relate to the technical field of construction parameter determination. Firstly, time sequence information of various environmental parameters in a specified construction area is extracted from multiple dimensions, and the various environmental parameters are subjected to spatio-temporal alignment processing. Secondly, construction parameter information is recorded in real time, and is associated with environmental parameter information and construction effect information according to a construction round as a unit. Finally, a time sequence prediction model for representing construction conditions is obtained based on the above data, so that the best construction parameter information can be predicted based on environmental parameters in a future preset time interval and expected construction effect information. The technical solution of the application can accurately predict construction parameters of cemented riprap in a wave flow environment. BRIEF DESCRIPTION OF DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the provided drawings.

[0034] Figure 1 is the execution flowchart of the dynamic optimization method for construction parameters of cemented riprap in a wave flow environment in the embodiments of the application.

[0035] Figure 2 is a layout schematic diagram of a flow velocity data acquisition sensor in the embodiments of the application. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the present application will be described clearly and completely in the embodiments of the present application in combination with the drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work belong to the scope of the present application.

[0037] The present application will be described in detail below in combination with the drawings and specific embodiments, and the schematic embodiments and the description are only used to explain the present application, but not to limit the present application.

[0038] The method and system for dynamically optimizing the construction parameters of cemented riprap in a wave flow environment will be described in detail below.

[0039] The method for dynamically optimizing the construction parameters of cemented riprap in a wave flow environment is proposed in the present embodiment, which aims to accurately predict the riprap construction parameters by combining big data and a machine learning model, and the specific process is as shown in Figure 1

[0040] S1: at least one multi-source data sequence is collected, and data optimization extraction processing is performed on the at least one multi-source data sequence to obtain at least one first flow field feature vector.

[0041] The present step aims to build a high-precision and high-frequency field environment perception system, which comprehensively and reliably captures the dynamic flow field information of the construction area by deploying multiple sensors and performing collaborative calibration and preprocessing, and provides a data basis for subsequent intelligent decision-making.

[0042] The data optimization extraction processing includes steps such as spatio-temporal alignment processing, data optimization and feature extraction.

[0043] The S1 specifically includes the following sub-steps:

[0044] S11: at least one first multi-source sensor is deployed in the first ship and the first construction range, so as to obtain a flow velocity data sequence, a wave data sequence and a ship motion data sequence.

[0045] In order to accurately match the subsequent riprap construction parameters with the environmental data and the riprap data, in the present step, the corresponding sensors need to be arranged on the specified positions in the construction range and the specified positions of the ship, so as to collect the flow velocity data, the wave data and the ship motion data, thereby preparing the data for the prediction of the subsequent riprap construction parameters.

[0046] The specific acquisition process of the above types of data is as follows:

[0047] 1. Flow velocity data collection

[0048] For example,​Figure 2 At least four Nortek Vectrino series point acoustic Doppler current profilers are arranged at 10 m upstream node A, 10 m downstream node B, and 5 m on both sides of nodes C and D of the construction foundation structure (such as a single pile), preferably with a sampling frequency of 16 Hz, to measure the three-dimensional instantaneous flow velocity at key points around the pile.

[0049] Meanwhile, a Nortek Signature 1000 ADCP is mounted on the bow of the construction ship to collect complete flow velocity profile data from the seabed to the water surface below the waterline at a frequency of 1 Hz. The complete flow velocity profile data can be selected by multiple data points at a specified distance interval, and the multiple data points are combined to form the complete flow velocity profile data.

[0050] The three-dimensional instantaneous flow velocity at key points around the pile and the complete flow velocity profile data are used to form a flow velocity data vector. Preferably, the two parts of flow velocity data are simply spliced to form the flow velocity data vector. Each flow velocity data vector corresponds to a time point.

[0051] 2. Wave data acquisition

[0052] Three Valeport laser wave direction meters are arranged in a triangular shape outside the construction area, with a sampling frequency of 2 Hz, to synchronously measure wave height, wave period, and wave direction. The influence of ship motion on wave measurement is eliminated by a triangulation method. The specific operation process of the triangulation method can be referred to the known operation method in the prior art.

[0053] After wave data acquisition, a wave data vector for representing wave data characteristics at a specified time point is obtained by combining wave height, wave period, and wave direction data at the specified time point.

[0054] 3. Ship motion data acquisition

[0055] An Applanix POS MV WaveMaster series high-precision integrated navigation system is installed at the center of gravity of the construction ship to output six degrees of freedom data (longitude, latitude, elevation, roll, pitch, and yaw) of the ship at a frequency of 100 Hz. The exemplary accuracy requirements are: plane positioning ≤2 cm, elevation ≤5 cm, and attitude angle ≤0.05°.

[0056] The ship motion data is also combined from the six degrees of freedom data to form a ship motion vector at a specific time point.

[0057] Through the above steps, the flow velocity data vector, the wave data vector, and the ship motion vector at different time points can be obtained.

[0058] After the combination of various data vectors at different time points, the flow rate data sequence, the wave data sequence and the ship motion data sequence can be obtained.

[0059] S12: Perform spatio-temporal alignment fusion processing on the flow rate data sequence, the wave data sequence and the ship motion data sequence to obtain a target flow rate data sequence, a target wave data sequence and a target ship motion data sequence.

[0060] In this step, spatio-temporal alignment fusion processing needs to be performed on the multiple data sequences obtained in S11, so that the processed data is more in line with the actual situation. The spatio-temporal alignment fusion processing includes two steps of time alignment and space alignment.

[0061] For the time alignment processing process, a time series data synchronization module needs to be deployed on an industrial-grade edge computing industrial computer. The module takes the PPS signal of GPS as an absolute time reference, synchronizes the internal clocks of all sensors through the PTP precise clock protocol, and ensures that the timestamp deviation of all data is less than a preset time interval, preferably 10 ms.

[0062] For the space alignment processing process, a coordinate unification conversion module needs to be developed to convert all sensor data to a local coordinate system of the construction area, preferably with a single pile center as the origin.

[0063] S13: Perform data quality optimization processing and feature extraction processing on the target flow rate data sequence, the target wave data sequence and the target ship motion data sequence to obtain at least one first flow field feature vector.

[0064] In S12, the spatio-temporal alignment processing of various data sequences has been completed. In this step, further data quality optimization processing and feature extraction need to be performed on all data, so as to serve as input data for subsequent steps.

[0065] The data quality optimization processing step includes: for each type of original data, applying the phase space threshold method to remove spikes, and then using a 4th order low-pass Butterworth filter to set a specified cutoff frequency to eliminate high-frequency noise.

[0066] The feature extraction step includes: for each type of processed time series data, calculating the flow field feature values within each window in real time with a 5-minute time window. Taking the flow rate data as an example, the flow field feature values can include: average flow rate U_mean, flow rate standard deviation U_std, maximum flow rate U_max, average wave height Hs, and main wave period Tp. These feature values will serve as input vectors for the machine learning model.

[0067] At least one first flow field feature vector is formed using the extracted features. In each of the first flow field feature vectors, a combination vector of various types of data values in a specified time interval is included. The specified time interval is preferably 5 minutes.

[0068] S2: Obtain at least one construction parameter feature vector and at least one first construction effect information in the construction process, and determine a space-time correlation database according to the correlation between at least one construction parameter feature vector, at least one first construction effect information, and at least one first flow field feature vector.

[0069] This step aims to create a structured, space-time correlated historical database, accurately correlate construction operations, environmental conditions, and final effects, and form a high-quality "problem-solution" sample library to prepare for subsequent model training.

[0070] The S2 includes the following sub-steps:

[0071] S21: Real-time data acquisition of construction parameters to obtain at least one construction parameter feature vector.

[0072] In this step, real-time acquisition of process parameters of construction machinery in the construction process is required.

[0073] The collected construction parameters include riprap particle size, throwing height (continuous value), and pouring rate (continuous value). The riprap particle size is classified as 0, 1, and 2 for classification, and the throwing height and pouring rate are both continuous values.

[0074] In the specific acquisition process, the above key parameters of the riprap machine are read and recorded in real time through the PLC controller of the construction machinery through the Modbus TCP protocol.

[0075] After the acquisition of the construction parameters is completed, at least one construction parameter feature vector is formed in a specified time interval. Preferably, the construction parameter feature vector and the specified time interval of the first flow field feature vector are the same to facilitate subsequent data alignment.

[0076] In each of the construction parameter feature vectors, a feature vector composed of riprap particle size, throwing height, and pouring rate is included, and the specific forms of the three types of data are as described above.

[0077] S22: Determine at least one first construction effect information according to the first digital elevation model obtained after each construction.

[0078] In the S21, real-time construction parameters have been collected. In this step, full-coverage topographic survey is needed to be conducted on the construction area after the construction according to the real-time construction parameters, and the construction effect is quantitatively evaluated after comparison with the design blueprint, so as to prepare for subsequent model training.

[0079] The S22 includes the following sub-steps:

[0080] S221: After each construction, full-coverage topographic survey is conducted on the construction area, so as to obtain a first digital elevation model.

[0081] After each construction section, Norbit iWBMS series multi-beam sounding system is used to conduct full-coverage topographic survey on the construction area with 200% overlap rate, so as to generate a digital elevation model with a resolution of 5cm x 5cm.

[0082] S222: Obtain first cemented body information according to the first digital elevation model and the original digital elevation model.

[0083] In this step, the DEM after construction and the DEM before construction are subjected to difference operation (DoD). The elevation change threshold (such as +0.1m) is set, the cemented body area is automatically identified, and the total volume, average thickness, and coverage area are calculated, and the above information is taken as the first cemented body information.

[0084] S223: Obtain first construction effect information according to the first cemented body information and the first design blueprint information.

[0085] In the first design blueprint information, construction effect parameters expected to be achieved after this construction are recorded, which can specifically include total volume, average thickness, coverage area, etc.

[0086] In this step, similarity comparison is conducted between the first cemented body information and the first design blueprint information, so as to obtain calculation coverage rate and volume compliance rate, which are taken as the first construction effect information of the construction effect.

[0087] The first construction effect information can be obtained by designated operation of various compliance rates.

[0088] Preferably, average value operation or weighted summation operation mode can be selected.

[0089] Preferably, the various compliance rates can not be weighted and averaged, but the compliance rates of various parameters are combined into a feature vector as the first construction effect information.

[0090] Each of the first construction effect information corresponds to at least one of the specified time intervals.

[0091] S23: Combining at least one first flow field feature vector, at least one construction parameter feature vector, and at least one first construction effect information into a spatio-temporal correlation database.

[0092] In order to obtain complete sample data for subsequent model training, at least one first flow field feature vector, at least one construction parameter feature vector, and the first construction effect information are combined into a spatio-temporal correlation database in this step.

[0093] In the spatio-temporal correlation database, at least one data record is included, and each data record includes a one-to-one or one-to-many relationship between each first construction effect information and the first flow field feature vector and the construction parameter feature vector.

[0094] Two core data tables are designed using a MySQL database:

[0095] Specifically, by using high-precision timestamps and spatial interpolation algorithms, environmental data, construction operations, and construction effect data within the same spatio-temporal range are correlated to form a complete sample record. For example, the spatial position corresponding to the construction operation can be calculated based on the GPS coordinates of the construction ship and the single pile coordinates, thereby establishing a correlation between the environmental data, construction data, and construction effect data within a specified time period at the corresponding spatial position.

[0096] S3: Predicting target construction parameter information based on target flow field feature vector and target construction effect information.

[0097] Since the environmental parameters in the same geographical area are relatively stable, a machine learning model that can predict optimal construction parameters can be trained using the information stored in the spatio-temporal correlation database in this step.

[0098] The S3 specifically includes the following sub-steps:

[0099] S31: Training a construction parameter prediction model based on the spatio-temporal correlation database.

[0100] In this step, each set of records in the spatio-temporal correlation database is used as a training sample to train a construction parameter prediction model.

[0101] During training, the environmental parameters and construction effect information are used as input, and the construction parameter information is used as output to train the construction parameter prediction model. The input features of the model are at least one first flow field feature vector corresponding to a construction time and the corresponding first construction effect information extracted in S13. The output of the model is three construction parameters that need to be optimized corresponding to the construction time: rock particle size, throwing height, and pouring rate.

[0102] Preferably, the construction parameter prediction model is an XGBoost regressor, thereby constructing a multi-output regression model.

[0103] In the specific training process of the model, the GridSearchCV can be used to cross-validate and optimize the model hyperparameters (such as max_depth, learning_rate, n_estimators) with mean squared error (MSE) and mean absolute error (MAE) as the loss function and evaluation index. The specific optimization process can refer to the optimization method in the prior art, which will not be described here.

[0104] Since the time series information of the environmental parameters, construction parameters and construction effect information is used in the training process of the construction parameter prediction model, the optimal construction parameter information in the future preset time interval can be predicted by the trained construction parameter prediction model.

[0105] S32: input the target flow field feature vector and the target construction effect information into the construction parameter prediction model to obtain the target construction parameter information.

[0106] In this step, the target flow field feature vector in the preset time interval and the target construction effect information to be achieved are input into the construction parameter prediction model to obtain the target construction parameter information.

[0107] Since the target flow field feature vector used to represent the environmental parameters usually does not change dramatically in a short time, the target construction parameter information in the future preset time interval can be predicted through this step.

[0108] S33: when the construction record accumulation amount exceeds the first preset value, incrementally learn the construction parameter prediction model.

[0109] Since the construction process is ongoing, the system automatically triggers the incremental learning process whenever a preset number of valid construction records are accumulated.

[0110] Preferably, the first preset value is 50.

[0111] In the specific implementation process, the partial_fit method of scikit-learn or the incremental training interface of XGBoost can be used to update the existing model online with new data, while important historical samples are retained to prevent catastrophic forgetting. After the updated model is verified by the test set, the old model is automatically replaced to realize the continuous evolution of the decision-making ability.

[0112] S4: After the target construction parameter information is confirmed, the issuing and recording process is performed.

[0113] After the target construction parameter information is obtained through S3, the intelligent decision of the model can be converted into actual construction instructions in this step, and through the man-machine interaction interface or the industrial control system, the real-time and accurate execution of the construction parameters is realized.

[0114] The S4 can specifically include the following sub-steps:

[0115] S41: Display the target construction parameter information on the digital board, and perform the issuing operation after the confirmation operation.

[0116] A Web-based real-time data board is developed, preferably using Grafana or Vue.js + ECharts framework. The board dynamically displays the optimal parameter setting value recommended by the model in the form of numbers and instrument panels, and displays the current actual value side by side, and the difference part is highlighted in color.

[0117] A one-key issuing button is integrated on the board. After the operator confirms the recommended parameter, the button is clicked to issue the setting value to the PLC.

[0118] S42: Record the target construction parameter information and the parameter adjustment information to the operation log.

[0119] In this step, any automatic or manual parameter adjustment will be recorded in the operation log table.

[0120] Exemplary fields can include timestamp, parameter_name, recommended_value, actual_set_value, operator_id.

[0121] The log is not only used for audit tracking, but its actual_set_value will be used as the real executed parameter to feed back to the database of S2 for subsequent model training and effect evaluation, ensuring the closure of the data chain.

[0122] The application also proposes a dynamic optimization system for cemented riprap construction parameters in wave-current environment, which is used to execute the dynamic optimization method for cemented riprap construction parameters in wave-current environment.

[0123] The application provides a dynamic optimization method and system for cemented riprap construction parameters in a wave flow environment, and relates to the technical field of construction parameter determination. First, time sequence information of various environmental parameters in a specified construction area is extracted from multiple dimensions, and various environmental parameters are subjected to spatiotemporal alignment processing. Second, construction parameter information is recorded in real time, and is associated with environmental parameter information and construction effect information according to construction rounds. Finally, a time sequence prediction model for representing construction conditions is obtained based on the above data, so that the best construction parameter information can be predicted through environmental parameters and expected construction effect information in a future preset time interval. The technical scheme of the application can accurately predict cemented riprap construction parameters in a wave flow environment.

[0124] The above description is only the preferred embodiment of the present application, and any equivalent changes or modifications made to the structure, features and principles described in the scope of the present application are included in the scope of the present application.

Claims

1. A method for dynamically optimizing construction parameters of cemented riprap under wave-current environment, characterized in that, The method comprises: S1: collecting at least one multi-source data sequence, performing data optimization extraction processing on at least one multi-source data sequence to obtain at least one first flow field feature vector; S2: obtaining at least one construction parameter feature vector and at least one first construction effect information in the construction process, determining a space-time correlation database according to the correlation of at least one construction parameter feature vector, at least one first construction effect information and at least one first flow field feature vector; at least one data record is included in the space-time correlation database, each data record includes one-to-one or one-to-many relationship between each first construction effect information and the first flow field feature vector and the construction parameter feature vector; through high-precision time stamp and space interpolation algorithm, the environment data, construction operation and construction effect data in the same space-time range are associated to form a complete sample record; S3: obtaining target construction parameter information according to target flow field feature vector and target construction effect information; S4: after confirming the target construction parameter information, executing issuing and recording processing; The S1 comprises: S11: at least one first multi-source sensor is arranged in the first ship and the first construction range, so as to obtain flow velocity data sequence, wave data sequence and ship movement data sequence; S12: performing space-time alignment fusion processing on the flow velocity data sequence, the wave data sequence and the ship movement data sequence to obtain target flow velocity data sequence, target wave data sequence and target ship movement data sequence; S13: performing data quality optimization processing and feature extraction processing on the target flow velocity data sequence, the target wave data sequence and the target ship movement data sequence to obtain at least one first flow field feature vector; The S3 comprises: S31: training a construction parameter prediction model according to the space-time correlation database; S32: inputting the target flow field feature vector and the target construction effect information into the construction parameter prediction model to obtain the target construction parameter information; S33: when the construction record accumulation amount exceeds a first preset value, incrementally learning the construction parameter prediction model.

2. The method according to claim 1, wherein, In each first flow field feature vector, a combined vector of flow velocity data, wave data and ship movement data in a specified time interval is included.

3. The method according to claim 1, wherein, The S2 comprises: S21: collecting real-time data of construction parameters to obtain at least one construction parameter feature vector; S22: determining at least one first construction effect information according to the first digital elevation model obtained after each construction; S23: combining at least one first flow field feature vector, at least one construction parameter feature vector and at least one first construction effect information into a space-time correlation database.

4. The method according to claim 3, wherein, The S22 comprises: S221: after each construction is completed, full-coverage topographic measurement is performed on the construction area to obtain a first digital elevation model; S222: obtaining first cementing body information according to the first digital elevation model and the original digital elevation model; S223: Obtain first construction effect information according to the first cementation body information and first design blueprint information.

5. The method according to claim 4, wherein, At least one data record is included in the spatio-temporal correlation database.

6. The method according to claim 5, wherein, In the training process of the construction parameter prediction model, the flow field feature vector and the construction effect information in the sample data are taken as input data, and the construction parameter feature vector is taken as output data.

7. The method according to claim 6, wherein, The S4 includes: S41: Display the target construction parameter information on the digital board, and perform the issuing operation after the confirmation operation; S42: Record the target construction parameter information and the parameter adjustment information into the operation log.

8. A dynamic optimization system for cemented riprap construction parameters in a wave flow environment, which is used to implement the dynamic optimization method for cemented riprap construction parameters in a wave flow environment according to any one of claims 1-7.

Images