A Fast Processing Method for Multibeam Data in Dredging Projects Based on AI

Abstract

The present invention proposes a fast processing method for multi-beam data of dredging projects based on AI, belonging to the field of dredging projects; when extracting the feature matrix X α , the data information of the beams at the same angle is directly extracted to form the feature matrix X α , and multiple feature matrices X are formed through the data information of the beams at different angles α ; the RNN neural network is trained through multiple feature matrices X α , and the output result of each matrix can intuitively reflect the water depth and geological information of the reflection points at the same angle; the matrices at different angles increase the difference between independent variables, accelerate the training speed of the RNN network, and enable the RNN network model to be trained more quickly; at the same time, the setting of each element parameter in the output matrix facilitates the subsequent batch mapping of the reflection points to the GPS and the production of the seabed geological distribution map through 3D software.

Description

Technical Field

[0001] The present invention relates to the field of dredging engineering, and more particularly, to a method for rapidly processing multi-beam data of dredging engineering based on AI. Background Art

[0002] Dredging engineering refers to the operations of artificial excavation, silt removal, widening, etc. of water bodies such as rivers, lakes, reservoirs, and ports, aiming to improve water flow smoothness, increase navigation capacity, prevent floods, improve water quality, etc.; with the acceleration of the global urbanization process and the increase in transportation demands, dredging engineering plays an increasingly important role in the construction of waterways, ports, and water conservancy facilities, etc.; at present, domestic and foreign dredging technologies are constantly updated and developed, and the equipment and methods adopted are becoming more and more advanced, such as hydraulic dredging, mechanical dredging, and combined dredging technologies, etc.; however, no matter what method is adopted, it is necessary to detect the topographic conditions of the seabed.

[0003] The current technologies for detecting the seabed mainly include: sonar detection technology, laser scanning technology, remote sensing technology, etc.; among them, sonar detection technology is even the main technology for seabed detection in dredging engineering. Sonar detection technology includes single-beam detection and multi-beam detection. Since single-beam detection is inefficient when detecting the topographic distribution of a large seabed area, multi-beam detection is usually used to detect the seabed topography. Multi-beam detection uses a transducer array to form a fan-shaped array of hundreds of acoustic waves to detect the seabed topography and analyze the seabed depth and geological distribution; however, the obtained data usually needs to be processed manually, with a very large workload and very time-consuming; therefore, how to improve the processing efficiency and accuracy of multi-beam detection data is an important task in dredging engineering projects. Summary of the Invention

[0004] The purpose of the present invention is to overcome the above problems existing in the prior art and greatly improve its technical effect on the basis of the original technology; the present invention provides a method for rapidly processing multi-beam data of dredging engineering based on AI, and the method includes:

[0005] First, obtain a feature set: perform multiple multi-beam measurements on the target dredging area through a multi-beam sounding system. The multiple multi-beam measurements refer to respectively scanning the entire target dredging area multiple times according to different fan-shaped angle ranges formed by the transducer array; after each completion of a scan of the entire target dredging area, respectively extract the data information of the same-angle beams received by the receiving end to form a feature matrix X α =[X1, X2,..., X i ,..., X n ; where X α refers to the matrix composed of beams with an angle of α after one scan, X i is a vertical vector, X iThe elements in it include: the angle of the corresponding beam, the reflection velocity, the reflection intensity, and the reflection time; and based on the obtained data, the water depth, the horizontal distance to the emission point, and the geological distribution at the time of reflection of the corresponding beam are obtained, constituting the characteristic matrix Y corresponding to the matrix X α =[Y1, Y2, …, Y α , …, Y i , …, Y n ; where Y i is a vertical vector, and the elements in Y i include: water depth, the horizontal distance to the emission point, and geological classification;

[0006] Taking all the characteristic matrices X α as inputs and the corresponding Y α as outputs to train the recurrent neural network RNN, obtaining the trained RNN model;

[0007] When it is necessary to detect the target dredging area, a suitable angular range is formed through the transducer array to scan the target detection area, obtaining the scanned data; according to the received data, the characteristic matrices X β , X β and the matrix X α have the same matrix form; inputting X β into the trained RNN model to obtain the output result Y β ;

[0008] According to the water depth, the horizontal distance to the emission point, and the geological classification measured by the corresponding beam in the output result Y β , combined with the emission source position when emitting the corresponding beam, calculate and map the position information corresponding to each vertical vector of the matrix Y β , and the entire matrix Y β forms the position scatter points of all vertical vectors; obtaining the position scatter points of all matrices Y β , and making a seabed geological distribution map according to the water depth and geological information in the matrix Y β corresponding to the position scatter points.

[0009] In addition, the multi-beam sounding system includes: the multi-beam sounding system can simultaneously emit multiple acoustic waves through the transducer array, and the multiple emitted acoustic waves are arranged in a fan shape, the fan-shaped plane is perpendicular to the sailing direction of the ship carrying the multi-beam sounding system, and the multiple emitted acoustic waves are respectively arranged at different angles with respect to the vertically downward direction, and the size of the angle ≤ half of the fan angle; multiple multi-beam measurements mean that for each fan-shaped arrangement set by the transducer array, the corresponding fan-shaped arrangement needs to complete multiple scans of the target dredging area, and as the number of completions increases, the obtained feature set will increase, and the trained AI model will be more reliable.

[0010] In addition, the feature matrix X α includes: The vectors in the feature matrix X α are column vectors, and the elements of the column vectors include: angle, reflection velocity, reflection intensity, and reflection time information. The expression of the column vector is:

[0011] where X i is the i-th column vector in the feature matrix X α , α i is the acoustic wave reflection angle corresponding to X i , v i is the acoustic wave reflection velocity corresponding to X i , σ i is the acoustic wave reflection intensity corresponding to X i , △t i is the time difference from acoustic wave emission to reception; all the acoustic wave reflection angles in X α are the same, so α1 = α2 = … α i … = α n ;

[0012] In addition, the water depth, horizontal distance to the emission point, and geological distribution at the corresponding beam reflection are obtained based on the acquired data, including: The formula for obtaining the water depth at the corresponding beam reflection is: ; The formula for obtaining the horizontal distance from the corresponding beam reflection point to the emission point is: ; The method for obtaining the geological distribution is: determining the geological classification of the corresponding beam through the empirical threshold classification method; The expression of Y α in the feature matrix Y i is:

[0013] where H i represents the water depth information corresponding to the acoustic wave X i , L i is the horizontal distance from the beam reflection point to the emission point, and C represents the geological classification at the reflection of the acoustic wave X i , and the classification of C is determined by the empirical threshold classification method.

[0014] In addition, scanning the target detection area by forming an appropriate angle range through the transducer array includes: The appropriate angle range refers to the angle of the fan-shaped beam formed by the transducer array; The appropriate angle range is determined according to the shape and area of the target detection area. Without affecting the detection accuracy, the angle of the fan-shaped beam formed by the transducer array is determined by analyzing the shape and area of the target detection area, and the determined angle is used to scan the entire target detection area.

[0015] In addition, calculate and map the matrix Y βThe position information corresponding to each vertical vector includes: β is the angle formed by the light beam and the vertically downward direction; the position information corresponding to each vertical vector refers to the position information of the light beam reflection point; the steps to determine the corresponding position information are as follows: First, obtain the position information of the light beam emission point and map the emission point position information to the GPS map; subsequently, through the matrix Y β obtain the vertical vector corresponding to the light beam, and obtain the water depth at the corresponding light beam reflection position and the horizontal distance to the emission point through the vertical vector; finally, based on the position information of the emission point, combine the water depth at the corresponding light beam reflection position and the triangular relationship formed by the horizontal distance to the emission point to determine the position information of the light beam emission point, map the position information to the GPS map, and mark the water depth information.

[0016] In addition, obtaining the position scatter points of all matrices Y β includes: obtaining the matrices Y of all light beams β and obtaining the position scatter points of all vertical vectors in each matrix Y β ; according to the water depth and geological information in the matrix Y corresponding to the position scatter points β produce a seabed geological distribution map through 3D software.

[0017] The beneficial effects of the present invention are:

[0018] The present invention provides a fast processing method for multi-beam data of dredging projects based on AI; it has the following advantages:

[0019] 1. In this method, the feature matrix X α and the feature matrix Y α are used as input and output pairs to train the recurrent neural network RNN. After obtaining the trained model, the feature matrix X of the target dredging area is obtained in real time β and input into the trained model; directly obtain the water depth of the acoustic wave reflection point in the target dredging area, the horizontal distance to the emission point, and the geological distribution situation according to the output of the model; greatly improve the efficiency of multi-beam data processing.

[0020] 2. When extracting the feature matrix X α in this method, directly extract the data information of the beams at the same angle to form the feature matrix X α , then the data information of the beams at different angles forms multiple feature matrices X α ; through multiple feature matrices X αThe RNN neural network is trained. When the trained network detects the target area to be detected, the output result of each matrix can intuitively reflect the water depth and geological information of the reflection points at the same angle; the matrices at different angles increase the difference between independent variables, accelerate the training speed of the RNN network, and improve the efficiency of data processing; at the same time, the setting of each element parameter in the output matrix facilitates the subsequent batch mapping of the reflection points to the GPS and the production of the seabed geological distribution map through 3D software. Brief Description of the Drawings

[0021] Figure 1 It is a flowchart of a method for quickly processing multi-beam data of a dredging project based on AI according to the present invention. Detailed Embodiments

[0022] The following details the specific embodiments of the present invention with reference to the accompanying drawings; it should be understood that the specific embodiments given here are only used to illustrate and explain the present invention and cannot be used to limit the present invention.

[0023] It should be noted that many specific details are set forth in the following description to facilitate a full understanding of the present invention. However, the present invention may have other embodiments and variations, and therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0024] As Figure 1 shown, it is a flowchart of a method for quickly processing multi-beam data of a dredging project based on AI according to an embodiment of the present invention; the flowchart includes: Step S1. First, obtain the feature set: perform multiple multi-beam measurements on the target dredging area through a multi-beam sounding system. The multiple multi-beam measurements refer to scanning the entire target dredging area multiple times respectively according to different fan angle ranges formed by the transducer array; after each complete scan of the entire target dredging area, extract the data information of the same-angle beams received by the receiving end to form a feature matrix X α =[X1, X2,..., X i ,..., X n ; where X α refers to the matrix composed of the beams with an angle of α after one scan, X i is a vertical vector, and the elements in X i include: the angle, reflection speed, reflection intensity, and reflection time of the corresponding beam; and calculate the water depth, horizontal distance to the emission point, and geological distribution situation at the time of reflection of the corresponding beam according to the obtained data, and form a feature matrix Y α corresponding to the matrix X α =[Y1, Y2,..., Y i ,..., Y n ; where Y i is a vertical vector, Y iThe elements in it include: water depth, horizontal distance to the emission point, and geological classification; Step S2: Take all the feature matrices X α as inputs, and the corresponding Y α as outputs to train the recurrent neural network (RNN) to obtain the trained RNN model; Step S3: When it is necessary to detect the target dredging area, use the transducer array to form an appropriate angular range to scan the target detection area and obtain the scanned data; According to the received data, respectively extract the feature matrices X β , X β and the matrix X α with the same matrix form; Input X β into the trained RNN model to obtain the output result Y β ; Step S4: According to the water depth, horizontal distance to the emission point, and geological classification conditions measured by the corresponding beams in the output result Y β , combined with the position of the emission source when the corresponding beam is emitted, calculate and map the position information corresponding to each vertical vector of the matrix Y β , and the entire matrix Y β forms the position scatter points of all vertical vectors; Obtain the position scatter points of all matrices Y β , and based on the water depth and geological information in the matrix Y β corresponding to the position scatter points, produce a seabed geological distribution map.

[0025] Specifically, in Step S1, the multi-beam sounding system can simultaneously emit multiple acoustic waves through the transducer array. The emitted multiple acoustic waves are arranged in a fan shape, and the fan-shaped plane is perpendicular to the sailing direction of the ship carrying the multi-beam sounding system. The multiple acoustic waves emitted are respectively arranged at different angles with respect to the vertically downward direction, and the size of the angle ≤ half of the fan angle; Multiple multi-beam measurements mean that for each fan-shaped arrangement set by the transducer array, the corresponding fan-shaped arrangement needs to complete multiple scans of the target dredging area. As the number of scans increases, the obtained feature set will increase, and the trained AI model will be more reliable.

[0026] The vectors in the feature matrix X α are vertical vectors. The elements of the vertical vector include: angle, reflection speed, reflection intensity, and reflection time information. The expression of the vertical vector is:

[0027] where X i is the i-th vertical vector in the feature matrix X α , α i is the acoustic wave reflection angle corresponding to X i , v i is the acoustic wave reflection speed corresponding to X i , σ i is the acoustic wave reflection intensity corresponding to X iThe corresponding acoustic wave reflection intensity, △t i is the time difference from acoustic wave emission to reception; X α All the acoustic wave reflection angles in are the same, so α1 = α2 = … α i … = α n .

[0028] Specifically, the water depth, horizontal distance to the emission point, and geological distribution corresponding to the beam reflection include: The formula for obtaining the water depth corresponding to the beam reflection is: ; The formula for obtaining the horizontal distance from the beam reflection point to the emission point is: ; The method for obtaining the geological distribution is: determining the geological classification of the corresponding beam through the empirical threshold classification method; Feature matrix Y α The Y in i The expression of is:

[0029] Among them, H i represents the water depth information corresponding to the acoustic wave X i , L i is the horizontal distance from the beam reflection point to the emission point, and C represents the geological classification when the acoustic wave X i is reflected. The classification of C is determined by the empirical threshold classification method.

[0030] In step S2, the recurrent neural network RNN is a neural network model with memory characteristics, suitable for processing sequence data, and can process the data of the feature matrix; Therefore, the feature matrix X α is trained by RNN, and the weights during the RNN training process are adjusted with the output Y α as the standard, and the trained RNN model can be obtained.

[0031] In step S3, the appropriate angle range refers to the angle of the fan-shaped beam formed by the transducer array; The appropriate angle range is determined according to the shape and area of the target detection area. Without affecting the detection accuracy, the angle of the fan-shaped beam formed by the transducer array is determined by analyzing the shape and area of the target detection area, and the determined angle is used to scan the entire target detection area.

[0032] In step S4, calculating and mapping the position information corresponding to each vertical vector of the matrix Y β includes: β is the angle formed by the beam and the vertically downward direction; The position information corresponding to each vertical vector refers to the position information of the beam reflection point; The steps for determining the corresponding position information are: First, obtain the position information of the beam emission point and map the emission point position information to the GPS map; Subsequently, through the matrix Y βObtain the vertical vector corresponding to the light beam, and obtain the water depth of the corresponding light beam reflection position and the horizontal distance to the launch point through the vertical vector; finally, according to the position information of the launch point, through the trigonometric relationship: combine the horizontal distance from the corresponding light beam reflection position to the launch point to determine the plane position information of the reflection point, and then determine the position information of the light beam reflection point through the plane position information combined with the water depth information; and map the position information to the GPS map and mark the water depth information.

[0033] Specifically, the method of obtaining all matrices Y β The position scattering includes: obtaining the matrix Y of all beams at different angles β , and find each matrix Y β The position scatter points of all vertical vectors in ; according to the matrix Y corresponding to the position scatter points β The water depth and geological information are collected and three-dimensional software is used to create a seabed geological distribution map.

Claims

1. A fast processing method for multi-beam data of dredging engineering based on AI, characterized in that: The method comprises: First, obtain the feature set: perform multiple multi-beam measurements on the target dredging area through the multi-beam bathymetry system. The multiple multi-beam measurements refer to scanning the entire target dredging area multiple times according to different fan-shaped angle ranges formed by the transducer array; after each scan of the entire target dredging area is completed, extract the data information of the same angle beam received by the receiving end to form a feature matrix X α =[X1, X2, …, X i , …, X n ]; where X α Refers to the matrix composed of beams with an angle of α, X i is the vertical vector, X i The elements in include: the angle of the corresponding beam, the reflection speed, the reflection intensity and the reflection time; and according to X i Obtain the water depth corresponding to the beam reflection point, the horizontal distance to the launch point, and the geological classification, which is composed of X α The corresponding feature matrix Y α =[Y1, Y2, ..., Y i , …, Y n ]; among them, Y i is the vertical vector, Y i The elements in refer to water depth, horizontal distance to the launch point, and geological classification; All feature matrices X α and Y α Train the recurrent neural network RNN ​​as input and output to obtain a trained RNN model; The target dredging area is detected in real time, and the target detection area is scanned by forming a suitable angle through the transducer array; according to the received data, the characteristic matrix X of the same angle beam is extracted respectively. β , β is the angle between the light beam and the vertical downward direction, X β and the matrix X α have the same matrix form; X β Input into the trained RNN model to get the output result Y β ; The appropriate angle refers to the angle of the fan-shaped beam formed by the transducer array; the appropriate angle is determined according to the shape and area of ​​the target detection area. Without affecting the detection accuracy, the angle of the fan-shaped beam formed by the transducer array is determined by analyzing the shape and area of ​​the target detection area, and the determined angle is maintained to scan the entire target detection area; According to the output result Y β The water depth of the corresponding beam, the horizontal distance to the launch point and the geological classification are combined with the position of the launch source when the corresponding beam is launched to calculate and map the matrix Y β The position information corresponding to each vertical vector, the entire matrix Y β That is, the position scatter points of all vertical vectors are formed; all matrices Y are obtained β The position scatter points, according to the matrix Y corresponding to the position scatter points β The water depth and geological information in the seabed are used to produce a seabed geological distribution map.

2. According to the AI-based fast processing method for multi-beam data of dredging engineering according to claim 1, it is characterized in that: The multi-beam bathymetry system includes: the multi-beam bathymetry system can emit multiple sound waves simultaneously through a transducer array, the emitted multiple sound waves are arranged in a fan shape, the fan plane is perpendicular to the navigation direction of the ship carrying the multi-beam bathymetry system, and the emitted multiple sound waves are arranged at different angles to the vertical downward direction, and the angle is ≤ half of the fan angle; multiple multi-beam measurements refer to each setting of a fan arrangement of the transducer array, and the corresponding fan arrangement is required to complete multiple scans of the target dredging area. As the number of completions increases, the acquired feature set will also increase, and the trained AI model will be more reliable.

3. According to the AI-based fast processing method for multi-beam data of dredging engineering in claim 1, it is characterized in that: The feature matrix X α Includes: feature matrix X α The vector in is a vertical vector. The elements of the vertical vector include: angle, reflection speed, reflection intensity and reflection time information. The expression of the vertical vector is: Among them, X i is the feature matrix X α The i-th vertical vector in i For X i The corresponding sound wave reflection angle, v i For X i The corresponding sound wave reflection velocity, σ i For X i The corresponding sound wave reflection intensity, △t i X is the time difference between the transmission and reception of sound waves; α All sound waves in the same reflection angle, so α1 = α2 = ... α i …=α n ; Said and according to X i The water depth at the corresponding beam reflection point, the horizontal distance to the launch point, and the geological classification are obtained: The formula for obtaining the water depth at the corresponding beam reflection point is: ; The formula for obtaining the horizontal distance from the corresponding beam reflection point to the transmitting point is: ; The method for obtaining the geological distribution is: determining the geological classification of the corresponding beam by the empirical threshold classification method; the characteristic matrix Y α Y i The expression is: Among them, H i Represents Sound Wave X i Corresponding water depth information, L i is the horizontal distance from the beam reflection point to the emission point, C represents the sound wave X i The geological classification at the time of reflection, the classification of C is determined by the empirical threshold classification method.

4. According to the AI-based fast processing method for multi-beam data of dredging engineering in claim 1, it is characterized in that: The calculation and mapping of the matrix Y β The position information corresponding to each vertical vector includes: β is the angle between the light beam and the vertical downward direction; the position information corresponding to each vertical vector refers to the position information of the light beam reflection point; the steps for determining the corresponding position information are: first, obtain the position information of the light beam emission point, and map the emission point position information to the GPS map; then, through the matrix Y β Obtain the vertical vector corresponding to the light beam, and obtain the water depth of the corresponding light beam reflection position and the horizontal distance to the launch point through the vertical vector; finally, according to the position information of the launch point, combined with the triangular relationship formed by the water depth of the corresponding light beam reflection position and the horizontal distance to the launch point, determine the position information of the light beam launch point, map the position information to the GPS map, and mark the water depth information.

5. According to the AI-based fast processing method for multi-beam data of dredging engineering in claim 1, it is characterized in that: Get all matrices Y β The position scattering includes: Get the matrix Y of all beams β , and find each matrix Y β The position scatter points of all vertical vectors in ; according to the matrix Y corresponding to the position scatter points β The water depth and geological information are collected and three-dimensional software is used to create a seabed geological distribution map.

Images