Marine survey equipment layout planning method

Abstract

Along with continuous deepening of ocean exploration of human beings, an autonomous underwater vehicle (AUV) equipped with various detection sensors has important significance for carrying out ocean survey with rich information. According to different marine survey task requirements, optimization motion of a particle swarm in a multi-dimensional search space is simulated based on a particle swarm optimization algorithm, and an optimal layout planning strategy meeting the task requirements is calculated through interactive learning, so that the problems that a traditional AUV layout planning strategy is low in efficiency and wastes manpower and material resources are solved. The layout planning result comprises information such as the equipment number, the laying position, the detection path, the measurement end point, the underwater detection profile frequency and the data return frequency of the autonomous underwater vehicle. The method can be widely applied to deployment tasks of the autonomous underwater vehicle in the fields of marine resource exploration, underwater rescue, marine search and the like.

Description

Technical Field

[0001] The invention relates to the technical field of optimization algorithms and autonomous underwater vehicles, and in particular to a method for planning the layout of marine surveying equipment. Background Art

[0002] As human beings continue to explore the ocean, autonomous underwater vehicles (AUVs) equipped with various detection sensors are of great significance for conducting information-rich ocean surveys. With the advantages of strong autonomy, long range, low cost, small size, and long working time, autonomous underwater vehicles are widely used in marine resource exploration, underwater rescue, and ocean search. The layout planning of AUV directly affects the efficiency and quality of ocean measurement. However, due to the influence of ocean currents, the longitude and latitude information of AUV is difficult to obtain in real time during underwater detection, resulting in deviations between the measurement trajectory and expectations. The traditional AUV layout planning strategy is relatively subjective, and there are problems of low efficiency and waste of manpower and material resources. The particle swarm optimization algorithm simulates the optimization movement of a particle swarm in a multidimensional search space and finds the global optimal solution through interactive learning. This algorithm is widely used in various optimization problems. Combined with the marine environment and task requirements, the particle swarm optimization algorithm can well solve the problem of intelligent layout planning of marine measurement equipment. Summary of the invention

[0003] The purpose of the present invention is to optimize and calculate the optimal layout planning strategy that meets the task requirements according to different ocean measurement task requirements in view of the shortcomings of the above-mentioned background technology, so as to improve the efficiency of ocean measurement. The layout planning results include the number of equipment, deployment location, detection path, measurement end point, underwater detection profile frequency, data return frequency and other information of the autonomous underwater vehicle. The present invention adopts the following technical solutions: The present invention proposes a method for planning the layout of marine surveying equipment: (1) Delineate the sea area to be tested, complete spatiotemporal data screening based on ocean current characteristics, and establish an ocean current environment background field for the layout planning strategy; (2) Set three mission scenarios: maximum measurement coverage, key sea area key measurement, and optimal equipment recovery. In the mission scenario with the maximum measurement coverage, the mission requirement is to ensure that the measurement path of the measurement equipment is long enough, while ensuring that the mutual interference between devices is minimal, so as to fully detect the target sea area as much as possible and maximize the measurement efficiency. In the mission scenario of key sea area key measurement, the mission requirement is to achieve the maximum intersection of paths in key areas, and then complete repeated measurements of equipment in key areas, so as to fully obtain information on environmental elements of the sea area to be measured. In the mission scenario of optimal equipment recovery, the mission requirement is to facilitate the salvage and recovery of subsequent equipment after the equipment completes the ocean measurement mission; (3) Design appropriate evaluation functions and constraints according to different task scenarios; (4) Initialize the particle swarm parameters, such as the number of particles, inertia weight, learning coefficient, number of iterations, etc. During initialization, set the particle swarm size N = 100, and each particle contains M paths. Inertia weight w = 1, individual learning coefficient c1 = 3, global learning coefficient c2 = 1, and the number of iterations is 1000. X is the particle population, Xi represents the individual particles in the population, where i = 1, 2...N. Xij represents each path in each layout scheme, where j = 1, 2...M; (5) Iterate and calculate, adjust particle position and speed, evaluate fitness, and update individual optimal solutions and global optimal solutions. The particle speed indicates the direction and distance of movement in the next iteration, and the particle position is a layout planning scheme under the current task scenario. The algorithm includes the position of the i-th particle, the speed of the i-th particle, the optimal position searched by the i-th particle (individual optimal solution), the optimal position searched by the group (group optimal solution), the fitness value of the optimal position searched by the i-th particle, and the fitness value of the optimal position searched by the group; (6) Determine whether the termination conditions are met and output the global optimal solution as the optimal layout planning scheme. The advantages and positive effects of the present invention are: (1) The present invention extracts ocean current characteristic data, completes the temporal and spatial range screening of the data, and establishes the ocean current environment background field for the layout planning task. (2) The present invention is based on a particle swarm optimization algorithm, which has the advantages of fast convergence speed, few parameters, simple algorithm and easy code implementation. (3) The present invention provides fitness function designs for three mission scenarios: maximum measurement coverage, key sea area key measurement, and optimal equipment recovery. Different fitness functions can be called according to different mission requirements to achieve flexible application in multiple scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0004] Figure 1 The present invention provides a marine environment background field for measuring equipment layout planning; Figure 2 It is a schematic diagram of a layout planning process of ocean measurement equipment based on particle swarm optimization provided by the present invention; Figure 3 It is a layout planning diagram of three task scenarios provided by the present invention; DETAILED DESCRIPTION

[0005] This example takes layout planning strategy as the research object and describes the principles and features of the present invention in conjunction with the accompanying drawings. However, the examples given are only used to explain the present invention and are not used to limit the scope of the present invention. Changes can be made to the present invention without departing from the spirit and scope of the present invention. To make the technical solution of the present invention clearer, the present invention is further described below in conjunction with the accompanying drawings. The present invention is specifically implemented according to the following steps: 1. See Figure 1 Marine environment background field, longitude range 108°E-115°E, latitude range 16° N-20°N. In order to ensure the optimal deployment of marine environment measurement equipment, the historical measurement data is preprocessed, and the appropriate spatiotemporal data interpolation technology is selected to interpolate the data in view of the missing and discrete problems of some data sources in the obtained data. In addition, numerical calculation is used to build a high-precision and high-resolution three-dimensional marine environment background field model in combination with specific measurement requirements. This model can provide prior environmental information for the deployment of marine environment measurement equipment, ensure that the measurement equipment is deployed according to the specific characteristics of the marine environment, and realize efficient and accurate measurement of the marine environment. 2. See Figure 2 Flowchart of measurement equipment layout planning. In this algorithm, the speed and position update formulas of each particle are: v ij (t+1)=w*v ij (t)+c1*r1*[p ij (t)-x ij (t)]+c2*r2*[p gj (t)-x ij (t)] x ij (t+1)=x ij (t)+v ij (t+1) 3. In the scenario with maximum measurement coverage, the layout scheme uses Euclidean distance to calculate the distance length d(i,j) of each measurement path. The calculation formula is as follows: where s x (i,j) represents the starting point S of the measurement path (i,j) The horizontal coordinate of (x, y), that is, the longitude coordinate; s y (i,j) represents the starting point S of the measurement path (i,j) (x,y) is the vertical coordinate, i.e. the latitude coordinate; e x (i,j) represents the end point of the measurement path E (i,j) The horizontal coordinate of (x, y) is the longitude coordinate; e y (i,j) represents the end point of the measurement path E (i,j) The vertical coordinate (x, y) is the latitude coordinate. To ensure the minimum interference between devices, the generated layout solution requires the minimum number of intersections of each path to reduce the overlap of the measurement range. i =β·n i ·r2 , where β is the penalty term for the intersection of the path, which is required to be large enough; r is the measurement range radius of the device; n i is the total number of intersections of all paths in the i-th layout planning solution. The evaluation function in this task scenario is as follows: max f i =D i -L i Among them, D i The sum of the path distances for each layout planning solution. After the particle swarm optimization algorithm is iterated, when the evaluation function f i When the maximum value is reached, the corresponding layout planning scheme is the scheme with the largest measurement coverage. The measurement path length under this scheme is long enough to ensure sufficient measurement coverage, and the intersections between the paths are small enough to effectively avoid mutual interference between devices and improve detection efficiency. Figure 3 . 4. In the mission scenario of key sea area measurement, the more dispersed the path starting point is, the more it can ensure that the measurement equipment can complete the all-round measurement task of the target sea area from different detection directions and different attitude angles. In addition, dispersing the initial position of the equipment can effectively avoid the overlap of the measurement path, thereby improving the detection efficiency. This algorithm intends to use the variance of the starting point coordinates to measure the degree of dispersion of the equipment. The formula is as follows: in, and They are respectively the means of the longitude and latitude coordinates of the starting point in the scheme. In order to ensure that the measurement path can smoothly pass through the key sea area, and at the same time, each path in the scheme realizes cross-measurement in the key sea area, so as to maximize the measurement effect. Under this requirement, this algorithm intends to design an evaluation function and two constraints. The evaluation function is designed to measure the dispersion of the distance from the center of the sea area to each path. This algorithm intends to use variance to calculate. x ,O y ), the path p(i,j) in the layout plan, where i=1,2...N, j=1,2...M. Then the distance variance from the sea area center to each path is The calculation formula is: Where d(i,j) is the center of the sea area O(Ox ,O y ) to the path p(i,j) in the layout solution, and α, β, and γ are the general straight line equation coefficients of the path p(i,j). The constraints in this task scenario include two items: one is that the distance d(i, j) from the center of the key sea area to be measured to all paths is less than the radius r of the sea area, so as to avoid the path not passing through the sea area to be measured; the other is that the angle between the center of the sea area and the starting point and end point of the path is required to be an obtuse angle, that is: The evaluation function in this task scenario is as follows: std(i,j) <r After the particle swarm optimization algorithm is iterated, when the evaluation function f i When the maximum value is reached, the corresponding layout planning scheme is the best scheme for key sea area key measurement. Under this scheme, the coordinates of the equipment starting points are sufficiently dispersed, and all measurement paths effectively pass through the key sea area, which can ensure the full range of measurement tasks for the target sea area. Figure 3 . 5. In the task scenario of optimal equipment recovery, this algorithm also uses variance to measure the dispersion of the end point position. The formula is as follows: in, and are the means of the longitude and latitude coordinates of the endpoint in the scheme respectively. In order to avoid duplication of equipment starting points and considering that the measurement range will overlap when the distance between devices is too close, this algorithm intends to calculate the sum of the distances between the starting points of the measuring devices. When the sum of the distances is the largest, it can ensure that the starting points of the devices are sufficiently dispersed in every corner of the sea area to be measured, while keeping a certain distance between the devices. The calculation formula is as follows: This algorithm intends to use Euclidean distance to calculate the distance length d(i,j) of each measurement path. The calculation formula is as follows: where s x (i,j) represents the starting point S of the measurement path (i,j) The horizontal coordinate of (x, y), that is, the longitude coordinate; s y (i,j) represents the starting point S of the measurement path (i,j) (x,y) is the vertical coordinate, i.e. the latitude coordinate; e x(i,j) represents the end point of the measurement path E (i,j) The horizontal coordinate of (x, y) is the longitude coordinate; e y (i,j) represents the end point of the measurement path E (i,j) The ordinate (x, y) is the latitude coordinate. This algorithm intends to limit the measurement endpoint to the set recovery sea area, requiring the device endpoint E (i,j) (x,y) is O(O) from the center of the recovery area x ,O y ) is less than the sea area radius r. That is: The evaluation function in this task scenario is as follows: Expand the above formula to get: Among them, D i The sum of the path distances for each layout planning solution. After the particle swarm optimization algorithm is iterated, when the evaluation function f i When the maximum, the corresponding layout planning scheme is the best equipment recovery scheme. In this scheme, the coordinates of the starting point of the equipment are kept at a large enough distance, so that the equipment can measure from different directions and end in the set recovery area. At the same time, the measurement path distance is long enough. It can meet the basic measurement coverage requirements. See the scheme result diagram for details. Figure 3 . The above specific embodiments further describe the purpose, technical solutions and design features of the present invention. However, it should be emphasized that the present invention includes but is not limited to the embodiments described in the specific embodiments, and any changes, modifications, substitutions, combinations and simplifications made under the spirit and principle of the present invention should be included in the scope of protection of the claims of the present invention.

Claims

1. A method for planning the layout of marine survey equipment, characterized in that: (1) Delineate the sea area to be tested, complete spatiotemporal data screening based on ocean current characteristics, and establish a marine environment background field; (2) Set three mission scenarios in the ocean background field: maximum measurement coverage, key sea area key measurement, and optimal equipment recovery; (3) Design appropriate evaluation functions and constraints according to different task scenarios; (4) Initialize the particle swarm parameters in the algorithm, such as the number of particles, inertia weight, learning coefficient, number of iterations, etc.; (5) Iteratively calculate optimization parameters, adjust particle positions and velocities, evaluate fitness, and update individual optimal solutions and global optimal solutions; (6) Determine whether the termination conditions are met and output the global optimal solution as the optimal layout planning scheme.

2. A method for planning the layout of marine surveying equipment as claimed in claim 1, characterized in that: The establishment of the marine environment background field in step (1): Establishing the marine environment background field is an important preliminary work of this layout optimization method. First, it is necessary to control the quality and preprocess the marine environment data from different sensing platforms and methods, and use interpolation methods to unify the data into the same time and space resolution framework. Combined with specific measurement needs, select the time and space range, such as building a high-precision, high-resolution three-dimensional marine environment background field model. From January 1, 2016 to December 2, 2022, 20 areas with a size of 24×24 (3°E×3°N) in the South China Sea were selected as training and test data, and a prediction study based on the South China Sea current was planned to be carried out. Finally, the dimension of this ocean current spatiotemporal prediction dataset is (20, 2304, 24, 24, 51, 2), that is, 20 ocean current data units, a time span of 2304 days, including 576 24×24 spatial points, and 51 layer depths (from the sea surface to 9000 meters underwater) of ocean current vector fields, which provides the necessary environmental impact parameters for subsequent algorithms and strongly supports the implementation of layout optimization calculations.

3. A method for planning the layout of marine surveying equipment as claimed in claim 1, characterized in that: Design of evaluation functions and constraints for the three task scenarios in step (3): In the scenario with maximum measurement coverage, the evaluation function is as follows: max f i =D i -L i Among them, D i The sum of the path distances for each layout planning solution. After the particle swarm optimization algorithm is iterated, when the evaluation function f i When the value is the largest, the corresponding layout planning scheme at this time is the scheme with the largest measurement coverage. Under this scheme, the measurement path length is long enough to ensure sufficient measurement coverage, and the intersections between the paths are small enough to effectively avoid mutual interference between devices and improve detection efficiency. In the mission scenario of key measurements in key sea areas, the evaluation function is as follows: std(i,j) <r After the particle swarm optimization algorithm is iterated, when the evaluation function f i When the value is the largest, the corresponding layout planning scheme is the best scheme for key sea area measurement. Under this scheme, the starting coordinates of the equipment are sufficiently dispersed, and all measurement paths effectively pass through the key sea area, which can ensure the full range of measurement tasks in the target sea area. In the task scenario of optimal equipment recovery, the evaluation function is as follows: Expand the above formula to get: Among them, D i The sum of the path distances for each layout planning solution. After the particle swarm optimization algorithm is iterated, when the evaluation function f i When the maximum value is reached, the corresponding layout planning scheme is the best equipment recovery scheme. In this scheme, the coordinates of the starting point of the equipment are kept at a large enough distance so that the equipment can measure from different directions and end in the set recovery area. At the same time, the measurement path distance is long enough to ensure the basic measurement coverage requirements.

4. A method for planning the layout of marine surveying equipment as claimed in claim 1, characterized in that: The design of the particle swarm algorithm in step (4): At initialization, set the particle swarm size N = 100, each particle contains M paths. The inertia weight w = 1, the individual learning coefficient c1 = 3, the global learning coefficient c2 = 1, and the number of iterations is 1000. X is the particle population, Xi represents the individual particles in the population, where i = 1, 2...N. Xij represents each path in each layout scheme, where j = 1, 2...M. In this algorithm, the speed and position update formulas of each particle are: v ij (t+1)=w*v ij (t)+c1*r1*[p ij (t)-x ij (t)]+c2*r2*[p gj (t)-x ij (t)] x ij (t+1)=x ij (t)+v ij (t+1)。

Images