A method and system for optimizing the layout of shore-based sensors considering coverage probability

Abstract

The present disclosure provides a shore-based sensor layout optimization method and system considering coverage probability, relating to the technical field of intelligent port perception, comprising: acquiring geographic environment data and meteorological condition data of a port monitoring area, determining target coverage area positions of sensor deployment and sensor types; constructing a coverage probability calculation model fusing geometric occlusion and meteorological attenuation; constructing a multi-objective layout optimization function; solving the multi-objective layout optimization objective function by using an improved non-dominated genetic algorithm, obtaining a Pareto optimal sensor deployment scheme set, selecting the scheme with the highest comprehensive score according to a user's preset preference weight as the final target layout scheme, and mapping it to the port physical space to output a structured deployment list containing sensor coordinates, types and orientations. The present disclosure realizes a global optimal balance between coverage rate, robustness and economy of the shore-based perception network, and significantly improves the safe operation level of the automated wharf.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent port sensing technology, specifically to a method and system for optimizing the layout of shore-based sensors considering coverage probability. Background Technology

[0002] The statements in this section are merely background information relating to this disclosure and do not necessarily constitute prior art.

[0003] With the deepening of automated terminal construction, shore-based sensing systems play a crucial role in ensuring the safe berthing of large ships. To achieve accurate monitoring of ship position, outline, and motion status, ports typically deploy multi-source heterogeneous sensor networks composed of LiDAR, high-definition visual cameras, millimeter-wave radar, and UWB base stations. However, the current deployment of shore-based sensors mainly relies on engineering experience or simple rules (such as equal spacing and uniform distribution along the shoreline), lacking scientific basis based on environmental physical characteristics and sensing effectiveness quantification. This extensive deployment model leads to a serious imbalance between sensing performance and resource investment, making it difficult to meet the stringent requirements of automated terminals for high precision, high reliability, and all-weather operation, and has become a key bottleneck restricting the upgrading of shore-based sensing networks.

[0004] Due to the highly complex structure, frequent dynamic interference, and variable weather conditions of port operations, existing sensor deployment methods still have the following technical limitations:

[0005] (1) The perception performance evaluation model is too simplified and lacks a fusion consideration of complex geometric occlusion and meteorological attenuation. Existing sensor layout models are generally based on the ideal free space assumption or only consider simple two-dimensional geometric occlusion, seriously ignoring the nonlinear cutting effect of three-dimensional static obstacles in the port on the field of view. In addition, existing models fail to integrate the nonlinear attenuation effect of dynamic meteorological conditions such as rain, fog, and haze on the detection performance of different modal sensors, resulting in a significant deviation between the simulated coverage range and the actual working conditions (the coverage range is overestimated), which cannot provide a high-confidence theoretical support for sensor layout under complex working conditions.

[0006] (2) The optimization objective is too singular, making it difficult to achieve a global balance between coverage, robustness, and economy. Existing layout optimization methods mostly adopt a single-objective greedy strategy, only pursuing "maximum coverage area" or "minimum deployment cost", lacking a multi-dimensional collaborative mechanism. When a single sensor fails or extreme weather causes a sharp drop in performance, this approach is prone to failure in critical areas due to the lack of effective backup sensors. Due to the lack of hard constraints on the redundancy of observations in critical areas, existing methods cannot automatically find the lowest cost and most fault-tolerant equilibrium solution while ensuring a safety baseline, leading to extreme situations such as excessive waste in non-critical areas or insufficient robustness in core areas.

[0007] (3) The planning methods have low intelligence levels, making it difficult to efficiently solve high-dimensional and complex problems involving the mixed deployment of heterogeneous sensors. In scenarios involving the mixed deployment of multiple heterogeneous sensors, decision variables exhibit a mixture of high-dimensional, discrete (location / type) and continuous (orientation) characteristics. Existing methods often rely on manual trial and error or traditional integer programming, lacking efficient intelligent search mechanisms, making it difficult to quickly converge to the global optimum in a massive combinatorial solution space. This not only leads to long planning cycles but also results in generated solutions that often lack structured details, making it difficult to directly guide engineering implementation. Existing technologies cannot meet the urgent needs of smart ports for refined planning, dynamic adjustment, and low-cost operation and maintenance throughout the entire lifecycle of shore-based sensing networks. Summary of the Invention

[0008] To address the aforementioned issues, this disclosure proposes a method and system for optimizing the layout of shore-based sensors that considers coverage probability. It deeply integrates the three-dimensional physical environment of the port, the atmospheric attenuation and occlusion characteristics of multi-source sensors, and constructs a multi-objective shore-based sensor layout optimization model that takes into account coverage, redundancy and cost. An improved non-dominated genetic algorithm is used to solve the model, thereby achieving the scientific, efficient and reliable deployment of shore-based sensing networks and providing technical support for the safe and efficient operation of automated terminals.

[0009] According to some embodiments, the present disclosure adopts the following technical solutions:

[0010] A method for optimizing the deployment of shore-based sensors considering coverage probability includes:

[0011] Acquire geographical and meteorological data of the port monitoring area to determine the target coverage area and sensor type for sensor deployment.

[0012] Based on the environmental model, the line-of-sight occlusion relationship between the candidate sensor locations and the target coverage area is analyzed, and atmospheric attenuation parameters are determined in combination with real-time or preset meteorological conditions to construct a coverage probability calculation model that integrates geometric occlusion and meteorological attenuation.

[0013] Based on the coverage probability model, mutual exclusion constraints for installation and service guarantee constraints for key areas are set. With the goals of maximizing average coverage, maximizing observation redundancy in key areas, and minimizing total deployment cost, a multi-objective layout optimization objective function is constructed.

[0014] The multi-objective layout optimization model is solved using a multi-objective optimization algorithm to obtain a Pareto-optimal set of sensor deployment schemes;

[0015] Based on the preset decision-making strategy, the target sensor layout scheme is determined from the Pareto optimal sensor deployment scheme set, and a deployment list containing sensor location, type and orientation information is output.

[0016] According to some embodiments, the present disclosure adopts the following technical solutions:

[0017] A shore-based sensor deployment optimization system considering coverage probability includes:

[0018] The data acquisition module is used to acquire geographical environmental data and meteorological condition data of the port monitoring area, and to determine the target coverage area location of the sensor deployment and the sensor type.

[0019] The factor determination module is used to analyze the line-of-sight occlusion relationship between candidate sensor locations and target coverage areas based on an environmental model, and to determine atmospheric attenuation parameters in conjunction with real-time or preset meteorological conditions, thereby constructing a coverage probability calculation model that integrates geometric occlusion and meteorological attenuation.

[0020] The objective function construction module is used to construct a multi-objective layout optimization objective function based on the coverage probability model, setting installation mutual exclusion constraints and key area service guarantee constraints, with the goal of maximizing average coverage, maximizing key area observation redundancy, and minimizing total deployment cost.

[0021] The optimization solution module is used to solve the multi-objective layout optimization model using a multi-objective optimization algorithm to obtain a Pareto optimal sensor deployment scheme set; according to a preset decision strategy, it determines the target sensor layout scheme from the Pareto optimal sensor deployment scheme set and outputs a deployment list containing sensor location, type and orientation information.

[0022] According to some embodiments, the present disclosure adopts the following technical solutions:

[0023] A computer program product includes a computer program that, when executed by a processor, implements the aforementioned method for optimizing the layout of shore-based sensors considering coverage probability.

[0024] According to some embodiments, the present disclosure adopts the following technical solutions:

[0025] A non-transitory computer-readable storage medium is provided for storing computer instructions, which, when executed by a processor, implement the aforementioned method for optimizing the layout of shore-based sensors considering coverage probability.

[0026] According to some embodiments, the present disclosure adopts the following technical solutions:

[0027] An electronic device includes a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the aforementioned method for optimizing the layout of shore-based sensors considering coverage probability.

[0028] Compared with the prior art, the beneficial effects of this disclosure are as follows:

[0029] 1. Significantly improves the accuracy and confidence of perception performance assessment in complex port environments. This disclosure breaks through the limitations of traditional layout methods that only consider ideal line-of-sight or simple geometric occlusion, and innovatively constructs a coverage probability calculation model that integrates geometric occlusion and meteorological attenuation. By deeply integrating high-precision three-dimensional physical environment data of the port with real-time / preset meteorological conditions, it can accurately quantify the line-of-sight occlusion effect of static obstacles such as gantry cranes and container yards, as well as the attenuation effect of dynamic meteorological factors such as rain, fog, and haze on the detection performance of multi-source sensors such as lidar and visual cameras. It effectively solves the problems of inaccurate prediction of perception blind spots and inflated coverage estimation under complex working conditions, and provides a high-confidence theoretical basis for sensor layout.

[0030] 2. Achieving a globally optimal balance between sensing network coverage, robustness, and economy. This disclosure abandons the one-sided optimization strategy of solely pursuing maximum coverage or minimum cost, and proposes a multi-objective collaborative optimization mechanism that takes into account average coverage, observation redundancy in key areas, and total deployment cost. "Average observation redundancy in key areas" serves as a core indicator, quantifying the multiple coverage capabilities of key areas such as ship berthing, significantly enhancing the system's fault tolerance and robustness under single-point sensor failures or extreme weather conditions. By constructing a multi-objective optimization model under multi-dimensional constraints, this disclosure can automatically find the equilibrium solution with the lowest cost and highest efficiency while ensuring seamless sensing of key operational areas, avoiding resource waste caused by excessive redundant deployment or safety hazards caused by insufficient coverage.

[0031] 3. Improved scientific rigor, intelligence, and execution efficiency in heterogeneous sensor network planning. This disclosure employs an improved non-dominated sorting genetic algorithm, capable of efficiently traversing massive discrete combinatorial solution spaces and rapidly converging to the Pareto optimal front. This method is not only applicable to hybrid deployment scenarios involving multiple heterogeneous sensors but also automatically generates a structured deployment list containing coordinates, type, and orientation. This significantly shortens the planning cycle of port sensing networks and reduces the total lifecycle cost of operation and maintenance, providing implementable and replicable intelligent technical support for the refined planning and dynamic adjustment of shore-based sensing networks in smart ports. Attached Figure Description

[0032] The accompanying drawings, which form part of this disclosure, are used to provide a further understanding of this disclosure. The illustrative embodiments of this disclosure and their descriptions are used to explain this disclosure and do not constitute an undue limitation of this disclosure.

[0033] Figure 1 This is a schematic diagram of sensor layout optimization considering line-of-sight obstruction and atmospheric attenuation in an embodiment of this disclosure.

[0034] Figure 2 This is a flowchart illustrating the implementation of the improved non-dominated genetic algorithm according to an embodiment of this disclosure. Detailed Implementation

[0035] The present disclosure will be further described below with reference to the accompanying drawings and embodiments.

[0036] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of this disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure pertains.

[0037] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments according to this disclosure. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms “comprising” and / or “including” are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0038] Example 1

[0039] One embodiment of this disclosure provides a method for optimizing the layout of shore-based sensors considering coverage probability, the method steps including:

[0040] Step 1: Obtain geographical environment data and meteorological condition data of the port monitoring area to determine the target coverage area location of the sensor deployment and the sensor type;

[0041] Step 2: Based on the environmental model, analyze the line-of-sight occlusion relationship between the candidate sensor locations and the target coverage area, and determine the atmospheric attenuation parameters in combination with real-time or preset meteorological conditions to construct a coverage probability calculation model that integrates geometric occlusion and meteorological attenuation.

[0042] Step 3: Based on the coverage probability model, set installation mutual exclusion constraints and key area service guarantee constraints, and construct a multi-objective layout optimization objective function with the goals of maximizing average coverage, maximizing observation redundancy in key areas, and minimizing total deployment cost;

[0043] Step 4: Solve the multi-objective layout optimization model using a multi-objective optimization algorithm to obtain a Pareto optimal sensor deployment scheme set; determine the target sensor layout scheme from the Pareto optimal sensor deployment scheme set according to the preset decision strategy, and output a deployment list containing sensor location, type and orientation information.

[0044] As one embodiment, this disclosure discloses a shore-based sensor layout optimization method considering coverage probability. This method deeply integrates the port's three-dimensional physical environment, atmospheric attenuation and occlusion characteristics of multi-source sensors, and balances coverage, redundancy, and cost. It constructs a multi-objective objective function for shore-based sensor layout optimization and employs an improved non-dominated genetic algorithm to solve for the optimal deployment scheme, achieving a scientific, efficient, and reliable deployment of the shore-based sensing network. The specific implementation process includes:

[0045] Step 1: Obtain geographical environment data and meteorological condition data of the port monitoring area to determine the target coverage area location of the sensor deployment and the sensor type.

[0046] This disclosure involves modeling the port environment and target area. The specific implementation steps are as follows:

[0047] (1) Obtain a three-dimensional model of the port environment: Use airborne / ground laser scanning or BIM system to obtain high-precision three-dimensional point cloud data of the port and construct a static obstacle set. This includes the metal structure of the bridge crane, container yard, warehouse walls, etc.

[0048] (2) Define the target coverage area According to port operation procedures, the projected area of ​​the hull of a large vessel on the quay plane when it berths is defined as the target coverage area, and it is discretized into a two-dimensional ground grid.

[0049]

[0050] in, For target coverage area G The first in j Each discrete grid cell is the basic spatial unit that makes up the entire coverage area. It corresponds to a specific geographical location coordinate; For the first j The horizontal coordinate of each grid cell in the wharf plane coordinate system (east-west direction or along the wharf shoreline direction). For the first j The vertical coordinate of each grid cell in the wharf plane coordinate system (north-south direction or perpendicular to the wharf shoreline). The elevation of the dock surface (if the dock surface is the reference surface, then) ), The target is the total number of grid cells, with a grid resolution of 1m × 1m.

[0051] (3) Define the set of candidate sensor installation locations:

[0052]

[0053] in, For feasible installation heights of light poles, quay bridge columns, etc. This represents the number of candidate points.

[0054] (4) Define the set of sensor types and the set of parameter sensor types as follows:

[0055]

[0056] Among them, each type of sensor It has the following preset physical parameters: maximum effective detection range Atmospheric attenuation coefficient Horizontal field of view Vertical field of view and equipment costs .

[0057] Step 2: Based on the environmental model built in Step 1, analyze the line-of-sight occlusion relationship between the candidate sensor locations and the target grid points, and combine real-time or preset meteorological conditions to determine atmospheric attenuation parameters and construct an effective coverage probability calculation model.

[0058] This disclosure relates to sensor candidate locations. Target point and sensor type Calculate its effective coverage probability The effective coverage probability reflects the reliable point-to-point sensing capability of sensors in a real port environment. The calculation process involves constructing a line-of-sight occlusion constraint function and a geometric constraint function. By introducing these two functions and comprehensively considering geometric occlusion and weather attenuation, an effective coverage probability model is obtained. The specific implementation steps are as follows:

[0059] (1) Line-of-sight occlusion determination. Use Open3D or PCL library for raycasting to determine the line-of-sight occlusion from the candidate sensor position. To the target point Does the line connect to the set of obstacles? Intersection, generating a line-of-sight occlusion indicator function (Line-of-Sight Indicator):

[0060]

[0061] (2) Geometric constraint determination. Calculate the Euclidean distance. If any of the following conditions are met, then :

[0062] ① ;

[0063] ② The azimuth angle exceeds the horizontal field of view ;

[0064] ③ The pitch angle exceeds the vertical field of view .

[0065] (3) Atmospheric attenuation and detection effectiveness modeling. Based on the above geometric and line-of-sight constraints, the impact of meteorological conditions on signal transmission is further considered. Define the sensor. s The minimum detectable signal threshold is (Determined by sensor sensitivity). First, calculate the theoretical received signal strength. :

[0066]

[0067] in, The initial intensity of the sensor's emission; No. s The signal strength attenuation rate of this type of sensor per unit distance under current meteorological conditions, measured in dB / km, can be dynamically updated based on real-time rain and fog data from the port meteorological monitoring system. For sensor position i Distance to grid point j The Euclidean distance between them.

[0068] Then the effective coverage probability for:

[0069]

[0070] Among them, when When the probability value is normalized to reflect the detection confidence, when the received signal is below the threshold, it is considered as not being covered (probability is 0).

[0071] Step 3: Based on the coverage probability model in Step 2, set installation mutual exclusion constraints and key area service guarantee constraints, and construct a multi-objective layout optimization objective function with the goals of maximizing average coverage, maximizing key area observation redundancy, and minimizing total deployment cost.

[0072] This disclosure constructs a multi-objective mixed-integer nonlinear programming model, defines binary decision variables and optimization objectives, including maximizing average coverage, maximizing observation redundancy in key areas, and minimizing total deployment cost. The specific process is as follows:

[0073] (1) Define binary decision variables: ,in Indicates the location Deployment sensor types s Otherwise, it is 0.

[0074] (2) Optimization objective:

[0075] 1) Maximize average coverage:

[0076] Target point The probability of being covered by at least one effective sensor is:

[0077]

[0078] To transform the maximization objective into a minimization input for an improved non-dominated genetic algorithm, we define:

[0079]

[0080] in, The fitness function is the first optimization objective, and the value is the negative of the average coverage rate. The smaller the value, the better the overall coverage performance of the current deployment scheme.

[0081] 2) Maximize observation redundancy in key areas:

[0082] Redundancy is a core indicator of system robustness, reflecting the degree to which critical berthing areas in a port are effectively covered simultaneously by multiple sensors. Let the critical area consist of sub-regions within the target coverage area that play a decisive role in berthing safety, and its corresponding ground grid point index set be... Then, the average observation redundancy of the critical region is defined as the average number of times each grid point in that sub-region is effectively covered:

[0083]

[0084] in, The fitness function is the second optimization objective, and the negative value of the average observation redundancy in the key area is the smaller the value. The smaller the value, the more reliable the coverage of the key area is by sensors, and the stronger the system robustness. This represents the total number of grid cells in the critical area.

[0085] 3) Minimize total deployment cost:

[0086]

[0087] in, Let be the fitness function for the third optimization objective, and be the total deployment cost. The smaller the value, the more economical and efficient the system construction. The unit deployment cost for the s-th type of sensor.

[0088] (3) Constraints:

[0089] 1) Install mutual exclusion constraints. At most one device can be deployed at each candidate location:

[0090]

[0091] 2) Coverage Guarantee Constraints. To ensure that target points within critical areas can be reliably sensed, arbitrary target points are defined... j Overall coverage probability Not less than :

[0092]

[0093] 3) Robustness Constraint. To prevent sensing failure due to single-point failure or extreme weather, this embodiment further introduces an effective coverage redundancy constraint. This constraint requires that each target point in the critical area must be covered by at least [missing information]. K Multiple sensors cover simultaneously:

[0094]

[0095] (4) The final multi-objective layout optimization objective function is:

[0096]

[0097] Step 4: Use an improved non-dominated genetic algorithm to solve the multi-objective layout optimization objective function, obtain the Pareto sensor deployment scheme set, select the scheme with the highest comprehensive score from the Pareto solution set as the final target layout scheme according to the user's preset preference weights and decision-making strategy, and map it to the port physical space, outputting a structured deployment list containing sensor coordinates, type and orientation.

[0098] like Figure 2 As shown, the specific implementation process of the improved non-dominated genetic algorithm disclosed herein includes:

[0099] (1) Define the sensor layout encoding method. In the genetic algorithm disclosed herein, an individual refers to each sensor layout, and a chromosome refers to the different coordinates of each sensor. The population refers to the solution set composed of multiple sensor layouts. The encoding method selected in this disclosure is real number encoding, which directly represents the chromosome with the original data. Compared with the traditional binary encoding, this encoding method does not require converting the original data into binary numbers, avoiding frequent encoding and decoding operations and reducing the computational load of the algorithm. The specific encoding is set as follows: These correspond to "no deployment, LiDAR, Camera, Radar, UWB" respectively. Mapping the coordinates obtained by the algorithm to the site layout yields the corresponding shore-based sensor layout.

[0100] (2) Initialize sensor layout set: Set chromosome length to and gene value of initial population size The initial population consisted of A feasible sensor layout scheme is constituted, denoted as [Scheme Name]. :

[0101]

[0102] Each of the following schemes It is a length of an integer vector, whose ... i dimension Indicates the first i Sensor types to be deployed at candidate locations (0: no deployment, 1: LiDAR, 2: Camera, 3: Radar, 4: UWB).

[0103] Furthermore, to improve the quality of the initial solution, this disclosure adopts a greedy starting strategy, prioritizing the deployment of high-reliability sensors (such as Radar + LiDAR combination) near key areas, generating a set of initial sensor layout solutions within the constraints, and mapping the coordinates obtained by the algorithm to the shore-based wharf layout, which is the corresponding multi-source sensor layout.

[0104] (3) Sensor layout fitness calculation. For each shore-based sensor layout in the solution set, its fitness value is calculated according to the objective function to quantify the comprehensive performance of the layout scheme on multiple objectives such as coverage, monitoring accuracy and deployment cost.

[0105] (4) Sensor layout selection operation. The tournament selection operator is used to select individuals with better fitness from the current shore-based sensor layout solution set and enter the subsequent genetic operation stage to retain high-quality sensor layout features.

[0106] (5) Sensor layout crossover operation. In genetic operations, crossover is performed at a single point, and its crossover probability is... Determined by the adaptive mechanism shown in the following equation:

[0107]

[0108] in, The overall fitness of individuals in the current population. For maximum fitness, For average fitness, , This is an empirical parameter for the crossover probability. When the individual fitness is high, the crossover probability is increased to promote the recombination of superior genes.

[0109] Crossover operations generate new layout schemes that combine the advantages of both parents by exchanging chromosome segments of high-quality shore-based sensor layout individuals, thereby enhancing the diversity and optimization potential of the solution set.

[0110] (6) Sensor layout mutation operation. The mutation operation is achieved by randomly replacing chromosome gene loci, and the mutation probability is shown in the following formula:

[0111]

[0112] in, , This is an empirical parameter for the mutation probability. When the fitness is low, increasing the mutation probability can enhance population diversity.

[0113] This disclosure further enriches the diversity of shore-based sensor deployment by introducing new sensor types or deployment locations, and reduces the risk of algorithms getting trapped in local optima.

[0114] (7) Individual repair of shore-based sensor layout. This includes addressing violations of installation mutual exclusion constraints (i.e., the same location). Heuristic repair of individuals (assigned multiple sensor types): Calculate the candidate sensor types at that location. s The marginal contribution rate of the current objective function (i.e., the ratio of coverage gain to cost brought by deploying this sensor) is used to retain the gene locus corresponding to the sensor type with the largest marginal contribution rate, and the gene loci of other sensor types at that position are forced to zero.

[0115] This strategy ensures that, while meeting physical constraints, the deployment scheme that maximizes system performance is retained as much as possible, avoiding solution quality degradation caused by random repairs.

[0116] (8) Generation and decision-making of Pareto optimal solution set. Determine if the iteration meets the termination condition: maximum number of iterations. The Pareto front remains unchanged for 30 consecutive generations. If any termination condition is met, the algorithm stops running and outputs the current Pareto optimal solution set. Each solution All of them satisfy the constraints. m Each feasible sensor layout scheme (individual) is considered, and the three objectives of coverage, redundancy, and cost are independent of each other. Based on the user's preset preference weights or decision-making strategy, the scheme with the highest comprehensive score is selected from the Pareto solution set as the final target layout scheme.

[0117] (9) Output of results. Map the optimal solution back to the port physical coordinate system to generate a structured deployment list, which includes: the unique ID of each sensor, three-dimensional coordinates, sensor type, installation orientation (azimuth angle, pitch angle) and a visualization layer of the expected coverage area.

[0118] Example 2

[0119] One embodiment of this disclosure provides a shore-based sensor layout optimization system that considers coverage probability, including:

[0120] The data acquisition module is used to acquire geographical environmental data and meteorological condition data of the port monitoring area, and to determine the target coverage area location of the sensor deployment and the sensor type.

[0121] The factor determination module is used to analyze the line-of-sight occlusion relationship between candidate sensor locations and target coverage areas based on an environmental model, and to determine atmospheric attenuation parameters in conjunction with real-time or preset meteorological conditions, thereby constructing a coverage probability calculation model that integrates geometric occlusion and meteorological attenuation.

[0122] The objective function construction module is used to construct a multi-objective layout optimization objective function based on the coverage probability model, setting installation mutual exclusion constraints and key area service guarantee constraints, with the goal of maximizing average coverage, maximizing key area observation redundancy, and minimizing total deployment cost.

[0123] The optimization solution module is used to solve the multi-objective layout optimization model using a multi-objective optimization algorithm to obtain a Pareto optimal sensor deployment scheme set; according to a preset decision strategy, it determines the target sensor layout scheme from the Pareto optimal sensor deployment scheme set and outputs a deployment list containing sensor location, type and orientation information.

[0124] Example 3

[0125] One embodiment of this disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned method for optimizing the layout of shore-based sensors considering coverage probability.

[0126] Example 4

[0127] One embodiment of this disclosure provides a non-transitory computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the aforementioned method for optimizing the layout of shore-based sensors considering coverage probability.

[0128] Example 5

[0129] One embodiment of this disclosure provides an electronic device, including a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the aforementioned method for optimizing the layout of shore-based sensors considering coverage probability.

[0130] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0131] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0132] While the specific embodiments of this disclosure have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of this disclosure. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of this disclosure are still within the scope of protection of this disclosure.

Claims

1. A method for optimizing the layout of shore-based sensors considering coverage probability, characterized in that, include: Acquire geographical and meteorological data of the port monitoring area to determine the target coverage area and sensor type for sensor deployment. Based on an environmental model, the line-of-sight occlusion relationship between candidate sensor locations and the target coverage area is analyzed. Atmospheric attenuation parameters are determined by combining real-time or preset meteorological conditions. A coverage probability calculation model integrating geometric occlusion and meteorological attenuation is constructed, including: For any candidate sensor installation location and any grid point within the target coverage area, construct a line-of-sight occlusion determination function. If the line connecting the two passes through a set of static obstacles, then the geometric coverage probability is determined to be zero. If the sensor does not pass through a static obstacle, the probability of weather coverage is calculated using a signal attenuation model based on the detection performance parameters corresponding to the sensor type and the atmospheric attenuation parameters. The effective coverage probability of the sensor for that grid point is obtained by multiplying or weighting the geometric coverage probability with the meteorological coverage probability. Based on the coverage probability model, mutual exclusion constraints for installation and service guarantee constraints for key areas are set. A multi-objective layout optimization objective function is constructed with the goals of maximizing average coverage, maximizing observation redundancy in key areas, and minimizing total deployment cost. Based on the coverage probability model, the constraints are determined, including: Installation mutual exclusion constraint: Only one type of sensor or no sensor is allowed to be deployed at the same candidate sensor installation location; Key area coverage guarantee constraint: In the key sub-regions within the target coverage area, the comprehensive coverage probability of each grid point is not lower than a preset threshold; Redundancy constraint: The total cost of deploying sensors shall not exceed the preset budget limit; The construction of the multi-objective layout optimization objective function includes: Define binary decision variables and optimization objectives. The optimization objectives include maximizing average coverage, maximizing observation redundancy in key areas, and minimizing total deployment cost. Observation redundancy is a core indicator for measuring system robustness and is used to reflect the degree to which key berthing areas of the port are effectively covered by multiple sensors simultaneously. Assume that the key area consists of sub-areas within the target coverage area that play a decisive role in berthing safety. Set a corresponding ground grid point index set and define the average observation redundancy of the key area as the average of the sum of probabilities that each grid point in the sub-area is effectively covered. A multi-objective optimization algorithm is used to solve the multi-objective layout optimization model to obtain a Pareto optimal set of sensor deployment schemes; An improved non-dominated genetic algorithm is used to solve the multi-objective layout optimization objective function, obtaining the coordinates of each sensor deployment point. The improvement strategy includes: Integer encoding is used to map gene bits to sensor type or sensorless state; A greedy strategy is introduced to generate the initial population in order to improve the quality of the initial solution; For each individual shore-based sensor deployment in the solution set, its fitness value is calculated to quantify the overall performance of the deployment scheme in terms of multiple objectives such as coverage, monitoring accuracy, and deployment cost. The tournament selection operator is used to select individuals with better fitness from the current solution set of shore-based sensor layouts and enter the subsequent genetic operation stage to preserve the high-quality sensor layout features. Sensor layout crossover operation is performed. The crossover adopts a single-point crossover method. By exchanging chromosome segments of high-quality shore-based sensor layout individuals, a new layout scheme that combines the advantages of both parents is generated. Sensor layout variation operations are performed by randomly replacing chromosome gene loci to introduce new sensor types or deployment locations; Construct a heuristic repair mechanism: After genetic operations, detect whether an individual violates the installation mutual exclusion constraint. If it does, randomly remove or replace the sensor at the conflicting location based on the marginal coverage contribution rate of the grid point until the constraint is satisfied. Determine whether the termination condition is met, and finally generate the Pareto optimal solution set; Based on the preset decision-making strategy, the target sensor layout scheme is determined from the Pareto optimal sensor deployment scheme set, and a deployment list containing sensor location, type and orientation information is output.

2. The shore-based sensor layout optimization method considering coverage probability as described in claim 1, characterized in that, The acquisition of geographical environmental data and meteorological condition data of the port monitoring area, and the determination of the target coverage area location and sensor type for sensor deployment, include: High-precision three-dimensional point cloud data of the port is acquired through airborne, ground-based laser scanning or BIM systems, and a set of static obstacles is extracted from it. The static obstacles include the metal structure of the bridge crane, the container yard, and the warehouse walls. According to port operation procedures, the area projected onto the dock plane by the hull of a large vessel when it is berthed is defined as the target coverage area. A three-dimensional mesh model is constructed based on the three-dimensional point cloud data, and the points on the port shore-based facilities that meet the installation conditions are determined as the set of candidate sensor installation locations.

3. A shore-based sensor layout optimization system considering coverage probability, characterized in that, Specifically, the method for optimizing the layout of shore-based sensors considering coverage probability as described in any one of claims 1-2 includes: The data acquisition module is used to acquire geographical environmental data and meteorological condition data of the port monitoring area, and to determine the target coverage area location of the sensor deployment and the sensor type. The factor determination module is used to analyze the line-of-sight occlusion relationship between candidate sensor locations and target coverage areas based on an environmental model, and to determine atmospheric attenuation parameters in conjunction with real-time or preset meteorological conditions, thereby constructing a coverage probability calculation model that integrates geometric occlusion and meteorological attenuation. The objective function construction module is used to construct a multi-objective layout optimization objective function based on the coverage probability model, setting installation mutual exclusion constraints and key area service guarantee constraints, with the goal of maximizing average coverage, maximizing key area observation redundancy, and minimizing total deployment cost. The optimization solution module is used to solve the multi-objective layout optimization model using a multi-objective optimization algorithm to obtain a Pareto optimal sensor deployment scheme set; according to a preset decision strategy, it determines the target sensor layout scheme from the Pareto optimal sensor deployment scheme set and outputs a deployment list containing sensor location, type and orientation information.

4. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the shore-based sensor layout optimization method considering coverage probability as described in any one of claims 1-2.

5. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium is used to store computer instructions, which, when executed by a processor, implement a shore-based sensor layout optimization method considering coverage probability as described in any one of claims 1-2.

6. An electronic device, characterized in that, include: The device includes a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to perform a method for optimizing the layout of shore-based sensors considering coverage probability as described in any one of claims 1-2.

Images