Method and system for improving construction efficiency of pile-driving boat based on artificial intelligence

Abstract

The present invention discloses a method and system for improving the construction efficiency of a pile-driving ship based on artificial intelligence. The method includes sensor monitoring, data preprocessing, construction path optimization, multi-ship collaborative optimization and construction efficiency improvement. The present invention relates to the field of intelligent construction technology for pile-driving ships, and specifically refers to a method and system for improving the construction efficiency of pile-driving ships based on artificial intelligence. This solution adopts a dual-path integrated optimization solution that combines construction path planning and multi-ship collaborative optimization to comprehensively improve the construction efficiency of pile-driving ships. By combining environmental factors and multi-objective factors in the process of construction path optimization, the data representation capability of the pile-driving ship construction process is also enhanced, thereby improving the overall improvement rate and intelligence level of the pile-driving ship construction efficiency. The improved search algorithm adopts multi-structure global search optimization, and effectively improves the basic performance of the search algorithm through the combination of chaos initialization, benchmark weight strategy adjustment and Gaussian adjustment cosine factor.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent construction of piling vessels, and in particular to a method and system for improving the construction efficiency of piling vessels based on artificial intelligence. Background Art

[0002] This AI-based method and system for improving the construction efficiency of pile-driving vessels aims to monitor and optimize the operation of pile-driving vessels in real time through advanced technologies such as deep learning, machine vision, and reinforcement learning. The system automatically adjusts the vessel's operating parameters based on multi-dimensional data, including the construction site environment, vessel status, and operational tasks, improving construction accuracy and efficiency. Specific functions include intelligent operation scheduling, real-time fault diagnosis and prediction, operation path optimization, and energy consumption analysis. This method enables pile-driving vessels to achieve higher efficiency, reduce human error, and enhance operational safety. Furthermore, the system can automatically adapt to different construction environments, reducing manual intervention and increasing productivity.

[0003] However, among the existing methods for improving the construction efficiency of pile-driving ships, there are existing intelligent construction efficiency optimization methods, which mainly optimize and improve from the perspective of intelligent path planning. However, in reality, pile-driving ship construction usually involves more complex environmental problems, multi-ship scheduling problems and collaborative operation problems. Simple ship construction path planning is difficult to meet the actual technical needs of improving the efficiency of pile-driving ships. In the existing methods for optimizing the construction path of pile-driving ships, there is an existing search algorithm that is inevitably limited in the path search population of the search algorithm itself when applied to the optimization of the construction path of pile-driving ships. The construction path of pile-driving ships is a complex problem with a long time span. This further The step makes it difficult to control the balance between local optimization and overall optimization. At the same time, the pile-driving ship construction process involves multiple objectives, multiple parameters and multiple types of data, and the existing technology is difficult to meet the flexibility requirements of such results. Among the existing multi-vessel collaborative optimization methods, there is an existing intelligent technology solution that mainly adopts a single-stage multi-vessel collaborative optimization. This method skips the construction path optimization process of a single pile-driving ship. Although it improves the overall efficiency, it also ignores the various complex factors that may exist in the construction process of a single pile-driving ship and the influence of inter-vessel communication scheduling. As a result, the existing solution is not fine-grained enough for the collaborative optimization of multiple pile-driving ships, and it is difficult to meet the objective needs. Summary of the Invention

[0004] In view of the above situation, in order to overcome the defects of the existing technology, the present invention provides a method and system for improving the construction efficiency of pile-driving ships based on artificial intelligence. Among the existing methods for improving the construction efficiency of pile-driving ships, there are existing intelligent construction efficiency optimization methods, which are mainly optimized and improved from the perspective of intelligent path planning. However, pile-driving ship construction in reality usually involves more complex environmental problems, multi-ship scheduling problems and collaborative operation problems. Simple ship construction path planning is difficult to meet the actual technical needs of improving the efficiency of pile-driving ships. This solution creatively adopts a dual-path integrated optimization solution that combines construction path planning and multi-ship collaborative optimization to improve the overall construction efficiency of pile-driving ships. By optimizing the construction path, The combination of environmental factors and multi-objective factors in the process also enhances the data representation capability of the pile-driving ship construction process, and overall improves the improvement rate and intelligence level of the pile-driving ship construction efficiency. In the existing pile-driving ship construction path optimization method, there is an existing search algorithm that is inevitably limited in the path search population of the search algorithm itself when applied to the pile-driving ship construction path optimization. The pile-driving ship construction path is a complex and time-long solution problem, which further leads to the difficulty in controlling the balance between local optimization and overall optimization. At the same time, the pile-driving ship construction process involves multiple objectives, multiple parameters and multiple types of data. The existing technology is also difficult to meet the flexibility requirements of such results. To solve the problem, this solution creatively adopts a search algorithm improved by multi-structure global search optimization. Through the combination of chaos initialization, baseline weight strategy adjustment and Gaussian adjustment cosine factor, the basic performance of the search algorithm is effectively improved, ensuring the search convergence speed suitable for the construction path of pile-driving ships. At the same time, global search enhancement, local search optimization, environmental adaptability improvement and multi-objective improvement are further introduced. Through these four integrated improvements, the performance of the construction path optimization of pile-driving ships is improved as a whole, and good data guarantee is provided for the subsequent multi-ship collaborative optimization. In view of the fact that in the existing multi-ship collaborative optimization methods, the existing intelligent technology solutions mainly adopt single-stage multi-ship collaborative optimization, which skips the single-stage multi-ship collaborative optimization. Although the construction path optimization process of a pile-driving ship improves the overall efficiency, it also ignores the various complex factors that may exist in the construction process of a single pile-driving ship and the influence of inter-ship communication scheduling, which leads to the fact that the existing scheme is not fine-grained enough for the collaborative optimization of multiple pile-driving ships, and it is difficult to meet the technical problems of objective needs. This scheme creatively adopts the method of combining the construction path optimization of pile-driving ships with reinforcement learning for multi-ship collaborative optimization. By combining the improved construction path optimization results of pile-driving ships, it effectively further conducts reinforcement learning training, improves the effect of multi-ship collaborative optimization, and can provide comprehensive operation scheduling and optimization reference, ensuring that pile-driving ships collaborate efficiently in complex environments and improving construction efficiency.

[0005] The technical solution adopted by the present invention is as follows: The method for improving the construction efficiency of a pile-driving ship based on artificial intelligence provided by the present invention comprises the following steps:

[0006] Step S1: sensor monitoring;

[0007] Step S2: data preprocessing;

[0008] Step S3: construction path optimization;

[0009] Step S4: multi-ship collaborative optimization;

[0010] Step S5: Improve construction efficiency.

[0011] Furthermore, in step S1, the sensor monitoring is used to arrange sensors and collect vessel, construction and environmental data, specifically to collect data through sensor arrangement to obtain an original data set for improving the construction efficiency of the piling vessel;

[0012] The original data set for improving the construction efficiency of the piling vessel specifically includes vessel status data, environmental status data, and construction process data.

[0013] Furthermore, in step S2, the data preprocessing is used to optimize the original data, specifically, basic data enhancement is performed on the original data set for improving the construction efficiency of the piling ship to obtain an optimized data set for improving the construction efficiency of the piling ship;

[0014] The basic data enhancement specifically includes data cleaning, data normalization, data standardization, filtering and denoising, missing value processing and manual feature extraction;

[0015] The pile-driving ship construction efficiency improvement optimization data set specifically includes optimizing ship status data, optimizing environmental status data, optimizing construction task data, optimizing ship operation data, optimizing multi-ship collaboration data and optimizing construction data.

[0016] Furthermore, in step S3, the construction path optimization is used to optimize the construction path of the piling ship. Specifically, based on the piling ship construction efficiency improvement optimization data set, a search algorithm improved by multi-structure global search optimization is used to optimize the construction path to obtain reference data for the piling ship construction path optimization.

[0017] The improved search algorithm of the multi-structure global search optimization specifically includes a chaos initialization operator, a benchmark weight optimization operator, a dynamic adjustment convergence operator, a global search enhancement operator, a local search fine-tuning operator, a pile-driving ship environmental adaptability dynamic adjustment operator, and a pile-driving ship construction path multi-objective optimization operator;

[0018] The chaos initialization operator is used to generate the initial population parameters of the search algorithm by using a mixed advantage set and a chaotic map during the initialization phase of the search algorithm;

[0019] The benchmark weight optimization operator is used to dynamically adjust the optimization weight and improve search stability;

[0020] The dynamic adjustment convergence operator is used to balance the collaborative optimization of global search and local search;

[0021] The global search enhancement operator is used to introduce global search enhancement to enhance the parameter diversity of the construction path of the pile-driving ship in the early stage of construction path optimization and to switch to precise search and optimization in the later stage;

[0022] The local search fine-tuning operator is used to introduce a mutation operation to fine-tune the local search path and improve its accuracy;

[0023] The piling vessel environmental adaptability dynamic adjustment operator is used to introduce analysis of the piling vessel environmental data and perform dynamic adjustment of the environmental adaptability construction path planning;

[0024] The multi-objective optimization operator for the construction path of the pile-driving ship is used to construct a multi-objective optimization structure for the construction path of the pile-driving ship and comprehensively optimize various construction parameters of the pile-driving ship;

[0025] The step of using the improved search algorithm of multi-structure global search optimization to optimize the construction path and obtain the optimized reference data of the construction path of the piling ship includes:

[0026] Step S31: initializing search parameters, specifically setting an initial parameter set of the search algorithm, and improving and executing the search algorithm based on the initial parameter set;

[0027] Step S32: chaos initialization, specifically using chaos advantage set initialization and chaos mapping to generate an initial search population and obtain optimized search initial position parameters;

[0028] Step S33: Benchmark weight optimization, specifically, calculating the fitness value through the benchmark weight strategy, constructing the optimal search individual combination, performing path update, and obtaining benchmark weight optimization update individual data;

[0029] The optimal search individual combination specifically includes exploration individuals, surrounding individuals, chasing individuals and propulsion individuals; the exploration individuals are used to explore new solutions, and the new solutions are used to represent new construction paths for pile-driving ships; the surrounding individuals are used to search around the optimal solution of the current number of iterations; the chasing individuals are used to follow and optimize the optimal solution of the current number of iterations; and the propulsion individuals are used to advance the overall process of the search algorithm;

[0030] Step S34: Dynamically adjust convergence, specifically using a Gaussian adjusted cosine factor to dynamically adjust the search convergence process, and through the dynamic adjustment, balance the global search degree and local search degree of the search algorithm. The calculation formula of the Gaussian adjusted cosine factor is:

[0031] ;

[0032] Where f is the Gaussian adjusted cosine factor, which is used as the convergence factor for balancing the global search degree and local search degree of the search algorithm. start is the starting value of the convergence factor, f end is the final value of the convergence factor, t is the iteration index, T is the maximum number of iterations, is the standard deviation parameter of the Gaussian function;

[0033] Step S35: Global search enhancement, specifically, by combining the dynamic adversarial learning algorithm and the sine-cosine algorithm to construct a global search enhancement operator. Specifically, in the early stage of the search algorithm, the dynamic adversarial learning algorithm is used as the search strategy, and in the middle stage of the search algorithm, the dynamic adversarial learning algorithm and the sine-cosine algorithm are used as the search strategy in a balanced manner. In the late stage of the search algorithm, the sine-cosine algorithm is used as the search strategy, and by constructing a dynamically adjusted learning rate parameter, the individual position of the search algorithm is updated to obtain global search enhancement individual data;

[0034] Step S36: local search fine-tuning, specifically, applying a mutation operation to fine-tune the local search after each iteration of the search algorithm to obtain local tuning path data;

[0035] The calculation formula of the local tuning path data is:

[0036] ;

[0037] Where, is the local tuning path data, is the optimal search individual position at the tth iteration, is the coefficient of variation parameter, is a randomly selected local search individual position;

[0038] Step S37: Dynamically adjust the environmental adaptability of the piling vessel, specifically, dynamically adjust the environmental adaptability of the piling vessel based on the optimized environmental state data in the piling vessel construction efficiency improvement optimization data set to obtain environmental adaptability tuning path data. The calculation formula is:

[0039] ;

[0040] Where, is the environmental adaptability tuning path data, is the local tuning path data, is the environmental adaptability coefficient, enadjust(·) is the environmental data adjustment function, and env is the environmental characteristic data;

[0041] Step S38: multi-objective optimization of the construction path of the piling ship, specifically introducing a multi-objective path optimization mechanism, setting a multi-objective optimal path output, performing multi-objective optimization of the construction path of the piling ship, and obtaining multi-objective construction path optimization output data;

[0042] The multi-objective path optimization specifically includes the construction vessel coordinate optimization goal, the construction path length optimization goal, the total construction time optimization goal, the construction energy consumption optimization goal and the construction environment adjustment optimization goal;

[0043] Step S39: Optimizing the construction path of the piling ship, specifically setting the maximum number of iterations and the convergence condition of the search algorithm, and iteratively executing the operations from Step S31 to Step S38 to optimize the construction path of the piling ship, thereby obtaining reference data for optimizing the construction path of the piling ship;

[0044] The pile-driving ship construction path optimization reference data specifically includes construction vessel coordinate data, construction path length optimization data, total construction time optimization data, construction energy consumption optimization data and construction environment adjustment optimization data.

[0045] Furthermore, in step S4, the multi-vessel collaborative optimization is used to optimize the collaborative operation of multiple vessels. Specifically, based on the piling vessel construction efficiency improvement optimization data set and the piling vessel construction path optimization reference data, a reinforcement learning method is used to perform multi-vessel collaborative optimization to obtain the piling vessel construction multi-vessel optimization scheduling reference data, which specifically includes the following steps:

[0046] Step S41: Initializing the reinforcement learning model, specifically extracting multi-vessel initial state data, vessel working data, vessel position data, vessel relative distance data, and construction target data from the piling vessel construction efficiency improvement optimization dataset and the piling vessel construction path optimization reference data, and using these as raw data input for multi-vessel collaborative optimization to construct a standard reinforcement learning model;

[0047] The standard reinforcement learning model, including action space, state space and reward function;

[0048] Step S42: multi-ship collaborative scheduling and allocation, specifically, applying deep Q learning based on the multi-ship collaborative optimization raw data input and the standard reinforcement learning model to perform multi-ship task allocation reinforcement learning training to obtain a multi-ship collaborative scheduling allocation model, and obtaining multi-ship collaborative scheduling allocation reference solution data by applying the multi-ship collaborative scheduling allocation model;

[0049] Step S43: Dynamic collaborative optimization, specifically, maximizing operational efficiency by continuously adjusting the multi-vessel collaboration mode during the piling barge construction process, and updating and maintaining the multi-vessel collaborative scheduling allocation model through real-time feedback;

[0050] Step S44: multi-vessel collaborative optimization, specifically, performing reinforcement learning optimization of multi-vessel collaborative operation through the reinforcement learning model initialization, the multi-vessel collaborative scheduling allocation and the dynamic collaborative optimization, and obtaining multi-vessel optimized scheduling reference data for pile driving vessel construction;

[0051] The multi-vessel optimized scheduling reference data for pile-driving ship construction specifically includes vessel identification data, multi-vessel task allocation data, vessel position data, vessel path planning data, vessel speed data, vessel operation load data, vessel collaboration information data and operation scheduling efficiency reference data.

[0052] Furthermore, in step S5, the construction efficiency is improved, and is used to comprehensively improve the efficiency of pile-driving ship construction by combining the comprehensive optimization results of the construction path and multi-ship collaboration. Specifically, by combining the pile-driving ship construction path optimization reference data, the optimal construction path of a single pile-driving ship is predicted, and by combining the pile-driving ship construction multi-ship optimization scheduling reference data, the parallel construction and joint operation scheduling of the pile-driving ships are optimized to obtain the reference data for improving the comprehensive construction efficiency of the pile-driving ship.

[0053] The artificial intelligence-based piling ship construction efficiency improvement system provided by the present invention includes a sensor monitoring module, a data preprocessing module, a construction path optimization module, a multi-ship collaborative optimization module and a construction efficiency improvement module;

[0054] The sensor monitoring module is used for sensor monitoring, obtaining an original data set of the pile driving ship construction efficiency improvement through sensor monitoring, and sending the original data set of the pile driving ship construction efficiency improvement to the data preprocessing module;

[0055] The data preprocessing module is used for data preprocessing, obtaining a data set for optimizing the construction efficiency of a pile-driving vessel through data preprocessing, and sending the data set for optimizing the construction efficiency of a pile-driving vessel to the construction path optimization module and the multi-vessel collaborative optimization module;

[0056] The construction path optimization module is used for construction path optimization, obtains construction path optimization reference data of the pile-driving ship through construction path optimization, and sends the construction path optimization reference data of the pile-driving ship to the multi-vessel collaborative optimization module and the construction efficiency improvement module;

[0057] The multi-vessel collaborative optimization module is used for multi-vessel collaborative optimization, obtains multi-vessel optimization scheduling reference data for pile driving vessel construction through multi-vessel collaborative optimization, and sends the multi-vessel optimization scheduling reference data for pile driving vessel construction to the construction efficiency improvement module;

[0058] The construction efficiency improvement module is used to improve construction efficiency. By improving construction efficiency, reference data for improving the comprehensive construction efficiency of the piling vessel is obtained.

[0059] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0060] (1) Among the existing methods for improving the construction efficiency of pile-driving ships, there are existing intelligent construction efficiency optimization methods, which are mainly optimized and improved from the perspective of intelligent path planning. However, in reality, pile-driving ship construction usually involves more complex environmental problems, multi-ship scheduling problems and collaborative operation problems. Simple ship construction path planning is difficult to meet the actual technical needs of improving the efficiency of pile-driving ships. This solution creatively adopts a dual-path integrated optimization solution that combines construction path planning and multi-ship collaborative optimization to improve the overall construction efficiency of pile-driving ships. By combining environmental factors and multi-objective factors in the process of construction path optimization, it also enhances the data representation capability of the pile-driving ship construction process, and overall improves the improvement rate and intelligence level of pile-driving ship construction efficiency.

[0061] (2) In the existing methods for optimizing the construction path of pile-driving ships, there is an inevitable problem of path search population limitation in the existing search algorithm itself when it is applied to the optimization of the construction path of pile-driving ships. The construction path of pile-driving ships is a complex problem with a long time span, which further leads to the difficulty in controlling the balance between local optimization and overall optimization. At the same time, the construction process of pile-driving ships involves multiple objectives, multiple parameters and multiple types of data. The existing technology is also difficult to meet the technical problem of the flexibility of the results. This scheme creatively adopts a search algorithm improved by multi-structure global search optimization. Through the combination of chaos initialization, benchmark weight strategy adjustment and Gaussian adjustment cosine factor, the basic performance of the search algorithm is effectively improved, ensuring the search convergence speed suitable for the construction path of pile-driving ships. At the same time, global search enhancement, local search optimization, environmental adaptability improvement and multi-objective improvement are further introduced. Through these four integrated improvements, the performance of the optimization of the construction path of pile-driving ships is improved as a whole, and good data guarantee is provided for the subsequent multi-ship collaborative optimization.

[0062] (3) In view of the fact that among the existing multi-vessel collaborative optimization methods, the existing intelligent technology solutions mainly adopt a single-stage multi-vessel collaborative optimization. This method skips the construction path optimization process of a single pile-driving ship. Although it improves the overall efficiency, it also ignores the various complex factors that may exist in the construction process of a single pile-driving ship and the influence of inter-vessel communication scheduling. As a result, the existing solutions are not fine-grained enough for the multi-vessel collaborative optimization of pile-driving ships, and it is difficult to meet the technical problems of objective needs. This solution creatively adopts a method of combining the construction path optimization of pile-driving ships with reinforcement learning multi-vessel collaborative optimization. By combining the improved pile-driving ship construction path optimization results, it effectively further conducts reinforcement learning training, improves the effect of multi-vessel collaborative optimization, and can provide a comprehensive operation scheduling and optimization reference, ensuring that pile-driving ships can collaborate efficiently in complex environments and improve construction efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A schematic diagram of the process of improving the construction efficiency of a pile-driving ship based on artificial intelligence provided by the present invention;

[0064] Figure 2 A schematic diagram of the artificial intelligence-based piling vessel construction efficiency improvement system provided by the present invention;

[0065] Figure 3 This is a flow chart of construction path optimization in step S3;

[0066] Figure 4 Schematic diagram of the multi-vessel collaborative optimization process in step S4.

[0067] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0068] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0069] In the description of the present invention, it should be understood that terms such as "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limiting the present invention.

[0070] Example 1, see Figure 1 The present invention provides a method for improving the construction efficiency of a pile-driving ship based on artificial intelligence, which comprises the following steps:

[0071] Step S1: sensor monitoring;

[0072] Step S2: data preprocessing;

[0073] Step S3: construction path optimization;

[0074] Step S4: multi-ship collaborative optimization;

[0075] Step S5: Improve construction efficiency.

[0076] By performing the above operations, in the existing methods for improving the construction efficiency of pile-driving ships, there are existing intelligent construction efficiency optimization methods, which are mainly optimized and improved from the perspective of intelligent path planning. However, in reality, pile-driving ship construction usually involves more complex environmental problems, multi-ship scheduling problems and collaborative operation problems. Simple ship construction path planning is difficult to meet the actual technical needs of improving the efficiency of pile-driving ships. This solution creatively adopts a dual-path integrated optimization solution that combines construction path planning and multi-ship collaborative optimization to improve the overall construction efficiency of pile-driving ships. By combining environmental factors and multi-objective factors in the process of construction path optimization, the data representation capability of the pile-driving ship construction process is also enhanced, and the overall improvement of the construction efficiency and the degree of intelligence of the pile-driving ship are improved.

[0077] Example 2, see Figure 1 and Figure 2 In step S1, the sensor monitoring is used to arrange sensors and collect vessel, construction and environmental data. Specifically, data is collected through sensor arrangement to obtain an original data set for improving the construction efficiency of the pile driving vessel;

[0078] The original data set for improving the construction efficiency of the piling vessel specifically includes vessel status data, environmental status data, and construction process data;

[0079] The vessel status data specifically includes vessel position data, speed data, direction data, and vessel mechanical equipment operating status data;

[0080] The environmental status data specifically includes weather condition data, tidal condition data, ocean current condition data, wind speed data and temperature data;

[0081] The construction process data specifically includes pile driving task progress data, pile driving depth data, pile driving pressure data and pile driving vibration signal data.

[0082] Example 3, see Figure 1 、 Figure 2 This embodiment is based on the above embodiment. In step S2, the data preprocessing is used to optimize the original data, specifically, basic data enhancement is performed on the original data set for improving the construction efficiency of the piling ship to obtain an optimized data set for improving the construction efficiency of the piling ship;

[0083] The basic data enhancement specifically includes data cleaning, data normalization, data standardization, filtering and denoising, missing value processing and manual feature extraction;

[0084] The said pile driving vessel construction efficiency improvement optimization data set specifically includes optimization of vessel status data, optimization of environmental status data, optimization of construction task data, optimization of vessel operation data, optimization of multi-vessel coordination data and optimization of construction data;

[0085] The optimized ship status data specifically includes positioning position data, speed and heading data, ship equipment working status data, ship equipment load status data, and ship fuel and power consumption data;

[0086] The optimized environmental status data specifically includes optimized weather data, optimized tidal data, optimized water depth and ocean current data, and optimized marine geological reference data;

[0087] The optimized construction task data specifically includes pile foundation position data, pile foundation depth requirement data, construction progress data, construction time data and optimized piling parameter data;

[0088] The optimized vessel operation data specifically includes operator information data and vessel collaborative task allocation data;

[0089] The optimized multi-vessel collaboration data specifically includes vessel spacing data, vessel relative position data, collaborative operation information data, and vessel communication information data;

[0090] The optimized construction data specifically includes construction efficiency data, construction obstacle data and resource allocation efficiency data.

[0091] Example 4, see Figure 1 、 Figure 2 、 Figure 3 This embodiment is based on the above embodiment. In step S3, the construction path optimization is used to optimize the construction path of the piling ship. Specifically, based on the piling ship construction efficiency improvement optimization data set, an improved search algorithm of multi-structure global search optimization is used to optimize the construction path, thereby obtaining the piling ship construction path optimization reference data.

[0092] The improved search algorithm of the multi-structure global search optimization specifically includes a chaos initialization operator, a benchmark weight optimization operator, a dynamic adjustment convergence operator, a global search enhancement operator, a local search fine-tuning operator, a pile-driving ship environmental adaptability dynamic adjustment operator, and a pile-driving ship construction path multi-objective optimization operator;

[0093] The chaos initialization operator is used to generate the initial population parameters of the search algorithm by using a mixed advantage set and a chaotic map during the initialization phase of the search algorithm;

[0094] The benchmark weight optimization operator is used to dynamically adjust the optimization weight and improve search stability;

[0095] The dynamic adjustment convergence operator is used to balance the collaborative optimization of global search and local search;

[0096] The global search enhancement operator is used to introduce global search enhancement to enhance the parameter diversity of the construction path of the pile-driving ship in the early stage of construction path optimization and to switch to precise search and optimization in the later stage;

[0097] The local search fine-tuning operator is used to introduce a mutation operation to fine-tune the local search path and improve its accuracy;

[0098] The piling vessel environmental adaptability dynamic adjustment operator is used to introduce analysis of the piling vessel environmental data and perform dynamic adjustment of the environmental adaptability construction path planning;

[0099] The multi-objective optimization operator for the construction path of the pile-driving ship is used to construct a multi-objective optimization structure for the construction path of the pile-driving ship and comprehensively optimize various construction parameters of the pile-driving ship;

[0100] The step of using the improved search algorithm of multi-structure global search optimization to optimize the construction path and obtain the optimized reference data of the construction path of the piling ship includes:

[0101] Step S31: initializing search parameters, specifically setting an initial parameter set of the search algorithm, and improving and executing the search algorithm based on the initial parameter set;

[0102] The initial parameter set includes search space scale, search dimension, search boundary, maximum number of iterations, pile driving vessel construction environment parameters and multi-objective weights;

[0103] Step S32: chaos initialization, specifically using chaos advantage set initialization and chaos mapping to generate an initial search population and obtain optimized search initial position parameters;

[0104] The calculation formula for the chaos initialization is:

[0105] ;

[0106] Where, is the position of the i-th search individual at the 0th iteration, which is used to represent the initial position of the search individual. The search individual is used to represent the solution element of the search algorithm. ChaosMap(·) is the chaos mapping function, i is the search individual index, and low bound is the search boundary lower limit parameter, up bound is the search boundary upper limit parameter;

[0107] Step S33: Benchmark weight optimization, specifically, calculating the fitness value through the benchmark weight strategy, constructing the optimal search individual combination, performing path update, and obtaining benchmark weight optimization update individual data;

[0108] The optimal search individual combination specifically includes exploration individuals, surrounding individuals, chasing individuals and propulsion individuals; the exploration individuals are used to explore new solutions, and the new solutions are used to represent new construction paths for pile-driving ships; the surrounding individuals are used to search around the optimal solution of the current number of iterations; the chasing individuals are used to follow and optimize the optimal solution of the current number of iterations; and the propulsion individuals are used to advance the overall process of the search algorithm;

[0109] The calculation formula for the benchmark weight optimization and update of individual data is:

[0110] ;

[0111] Where, is the individual data of the benchmark weight optimization update, which is used to indicate the position of the i-th search individual at the t+1th iteration after the weighted update, t is the iteration number index, W A is the exploration individual weight, W B is the individual weight, W C is the pursuit individual weight, W D is the weight of the individual, X A is the location of the exploration individual, X B is the position around the individual, X C is the position of the chasing individual, X D It is the position of advancing the individual;

[0112] Step S34: Dynamically adjust convergence, specifically using a Gaussian adjusted cosine factor to dynamically adjust the search convergence process, and through the dynamic adjustment, balance the global search degree and local search degree of the search algorithm. The calculation formula of the Gaussian adjusted cosine factor is:

[0113] ;

[0114] Where f is the Gaussian adjusted cosine factor, which is used as the convergence factor for balancing the global search degree and local search degree of the search algorithm. start is the starting value of the convergence factor, f end is the final value of the convergence factor, t is the iteration index, T is the maximum number of iterations, is the standard deviation parameter of the Gaussian function;

[0115] Step S35: Global search enhancement, specifically, by combining the dynamic adversarial learning algorithm and the sine-cosine algorithm to construct a global search enhancement operator. Specifically, in the early stage of the search algorithm, the dynamic adversarial learning algorithm is used as the search strategy, and in the middle stage of the search algorithm, the dynamic adversarial learning algorithm and the sine-cosine algorithm are used as the search strategy in a balanced manner. In the late stage of the search algorithm, the sine-cosine algorithm is used as the search strategy, and by constructing a dynamically adjusted learning rate parameter, the individual position of the search algorithm is updated to obtain global search enhancement individual data;

[0116] The calculation formula for the global search enhanced individual data is:

[0117] ;

[0118] Where, It is a global search to enhance individual data, is the current search individual position before global enhancement, which is used to represent the position of the i-th search individual at the t-th iteration. G is a dynamically adjusted learning rate parameter used to balance the use strategy of the dynamic adversarial learning algorithm and the sine-cosine algorithm. is the optimal search individual position at the tth iteration, which is used to represent the optimal result of the pile-driving ship construction path optimization;

[0119] Step S36: local search fine-tuning, specifically, applying a mutation operation to fine-tune the local search after each iteration of the search algorithm to obtain local tuning path data;

[0120] The calculation formula of the local tuning path data is:

[0121] ;

[0122] Where, is the local tuning path data, is the optimal search individual position at the tth iteration, is the coefficient of variation parameter, is a randomly selected local search individual position;

[0123] Step S37: Dynamically adjust the environmental adaptability of the piling vessel, specifically, dynamically adjust the environmental adaptability of the piling vessel based on the optimized environmental state data in the piling vessel construction efficiency improvement optimization data set to obtain environmental adaptability tuning path data. The calculation formula is:

[0124] ;

[0125] Where, is the environmental adaptability tuning path data, is the local tuning path data, is the environmental adaptability coefficient, enadjust(·) is the environmental data adjustment function, and env is the environmental characteristic data;

[0126] Step S38: multi-objective optimization of the construction path of the piling ship, specifically introducing a multi-objective path optimization mechanism, setting a multi-objective optimal path output, performing multi-objective optimization of the construction path of the piling ship, and obtaining multi-objective construction path optimization output data;

[0127] The multi-objective path optimization specifically includes the construction vessel coordinate optimization goal, the construction path length optimization goal, the total construction time optimization goal, the construction energy consumption optimization goal and the construction environment adjustment optimization goal;

[0128] Step S39: Optimizing the construction path of the piling ship, specifically setting the maximum number of iterations and the convergence condition of the search algorithm, and iteratively executing the operations from Step S31 to Step S38 to optimize the construction path of the piling ship, thereby obtaining reference data for optimizing the construction path of the piling ship;

[0129] The pile-driving ship construction path optimization reference data specifically includes construction vessel coordinate data, construction path length optimization data, total construction time optimization data, construction energy consumption optimization data and construction environment adjustment optimization data.

[0130] By performing the above operations, the existing search algorithm in the existing pile-driving ship construction path optimization method will inevitably have the problem of path search population limitation when applied to the pile-driving ship construction path optimization. The pile-driving ship construction path is a complex and time-consuming problem to solve, which further leads to the difficulty in controlling the balance between local optimization and overall optimization. At the same time, the pile-driving ship construction process involves multiple objectives, multiple parameters, and multiple types of data. The existing technology is also difficult to meet the technical problem of the flexibility required for such results. This scheme creatively adopts a search algorithm improved by multi-structure global search optimization. By combining chaotic initialization, benchmark weight strategy adjustment, and Gaussian adjusted cosine factor, the basic performance of the search algorithm is effectively improved, ensuring the search convergence speed suitable for the pile-driving ship construction path. At the same time, global search enhancement, local search optimization, environmental adaptability improvement, and multi-objective improvement are further introduced. Through these four integrated improvements, the performance of the pile-driving ship construction path optimization is improved as a whole, and good data guarantee is provided for subsequent multi-vessel collaborative optimization.

[0131] Example 5, see Figure 1 、 Figure 2 and Figure 4 This embodiment is based on the above embodiment. In step S4, the multi-vessel collaborative optimization is used to optimize the collaborative operation of multiple vessels. Specifically, based on the piling vessel construction efficiency improvement optimization data set and the piling vessel construction path optimization reference data, a reinforcement learning method is used to perform multi-vessel collaborative optimization to obtain the piling vessel construction multi-vessel optimization scheduling reference data. Specifically, the steps include:

[0132] Step S41: Initializing the reinforcement learning model, specifically extracting multi-vessel initial state data, vessel working data, vessel position data, vessel relative distance data, and construction target data from the piling vessel construction efficiency improvement optimization dataset and the piling vessel construction path optimization reference data, and using these as raw data input for multi-vessel collaborative optimization to construct a standard reinforcement learning model;

[0133] The standard reinforcement learning model, including action space, state space and reward function;

[0134] Step S42: multi-ship collaborative scheduling and allocation, specifically, applying deep Q learning based on the multi-ship collaborative optimization raw data input and the standard reinforcement learning model to perform multi-ship task allocation reinforcement learning training to obtain a multi-ship collaborative scheduling allocation model, and obtaining multi-ship collaborative scheduling allocation reference solution data by applying the multi-ship collaborative scheduling allocation model;

[0135] Step S43: Dynamic collaborative optimization, specifically, maximizing operational efficiency by continuously adjusting the multi-vessel collaboration mode during the piling barge construction process, and updating and maintaining the multi-vessel collaborative scheduling allocation model through real-time feedback;

[0136] Step S44: multi-vessel collaborative optimization, specifically, performing reinforcement learning optimization of multi-vessel collaborative operation through the reinforcement learning model initialization, the multi-vessel collaborative scheduling allocation and the dynamic collaborative optimization, and obtaining multi-vessel optimized scheduling reference data for pile driving vessel construction;

[0137] The multi-vessel optimized scheduling reference data for pile-driving ship construction specifically includes vessel identification data, multi-vessel task allocation data, vessel position data, vessel path planning data, vessel speed data, vessel operation load data, vessel collaboration information data and operation scheduling efficiency reference data.

[0138] By performing the above operations, in the existing multi-ship collaborative optimization methods, there is an existing intelligent technology solution that mainly adopts a single-stage multi-ship collaborative optimization. This method skips the construction path optimization process of a single pile-driving ship. Although it improves the overall efficiency, it also ignores the various complex factors that may exist in the construction process of a single pile-driving ship and the influence of inter-ship communication scheduling, which leads to the existing solution for the multi-ship collaborative optimization of pile-driving ships not being fine-grained enough, and it is also difficult to meet the objective technical needs. This solution creatively adopts a method of combining the construction path optimization of pile-driving ships with reinforcement learning for multi-ship collaborative optimization. By combining the improved pile-driving ship construction path optimization results, it effectively further performs reinforcement learning training, improves the effect of multi-ship collaborative optimization, and can provide a comprehensive operation scheduling and optimization reference to ensure that pile-driving ships collaborate efficiently in complex environments and improve construction efficiency.

[0139] Example 6, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. In step S5, the construction efficiency is improved by combining the comprehensive optimization results of the construction path and multi-vessel collaboration to comprehensively improve the efficiency of the pile-driving ship construction. Specifically, by combining the pile-driving ship construction path optimization reference data, the optimal construction path of a single pile-driving ship is predicted, and by combining the pile-driving ship construction multi-vessel optimization scheduling reference data, the parallel construction and joint operation scheduling of the pile-driving ships are optimized to obtain the reference data for improving the comprehensive construction efficiency of the pile-driving ship.

[0140] Example 7, see Figure 1 and Figure 2 This embodiment is based on the above embodiment. The artificial intelligence-based piling ship construction efficiency improvement system provided by the present invention includes a sensor monitoring module, a data preprocessing module, a construction path optimization module, a multi-ship collaborative optimization module and a construction efficiency improvement module;

[0141] The sensor monitoring module is used for sensor monitoring, obtaining an original data set of the pile driving ship construction efficiency improvement through sensor monitoring, and sending the original data set of the pile driving ship construction efficiency improvement to the data preprocessing module;

[0142] The data preprocessing module is used for data preprocessing, obtaining a data set for optimizing the construction efficiency of a pile-driving vessel through data preprocessing, and sending the data set for optimizing the construction efficiency of a pile-driving vessel to the construction path optimization module and the multi-vessel collaborative optimization module;

[0143] The construction path optimization module is used for construction path optimization, obtains construction path optimization reference data of the pile-driving ship through construction path optimization, and sends the construction path optimization reference data of the pile-driving ship to the multi-vessel collaborative optimization module and the construction efficiency improvement module;

[0144] The multi-vessel collaborative optimization module is used for multi-vessel collaborative optimization, obtains multi-vessel optimization scheduling reference data for pile driving vessel construction through multi-vessel collaborative optimization, and sends the multi-vessel optimization scheduling reference data for pile driving vessel construction to the construction efficiency improvement module;

[0145] The construction efficiency improvement module is used to improve construction efficiency. Through the improvement of construction efficiency, reference data for improvement of the comprehensive construction efficiency of the piling vessel is obtained.

[0146] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0147] While the embodiments of the present invention have been shown and described, it will be apparent to those skilled in the art that various changes, modifications, substitutions, and alterations can be made to the embodiments without departing from the principles and spirit of the invention.

[0148] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. A method for improving the construction efficiency of a pile-driving ship based on artificial intelligence, characterized by: The method comprises the following steps: Step S1: sensor monitoring to obtain the original data set for improving the construction efficiency of the pile-driving ship; Step S2: Data preprocessing to obtain an optimized data set for improving the construction efficiency of pile-driving vessels; Step S3: Construction path optimization, which is used to optimize the construction path of the piling ship. Specifically, based on the piling ship construction efficiency improvement optimization data set, an improved search algorithm of multi-structure global search optimization is used to optimize the construction path, and obtain reference data for the construction path optimization of the piling ship. The improved search algorithm of the multi-structure global search optimization specifically includes a chaos initialization operator, a benchmark weight optimization operator, a dynamic adjustment convergence operator, a global search enhancement operator, a local search fine-tuning operator, a pile-driving ship environmental adaptability dynamic adjustment operator, and a pile-driving ship construction path multi-objective optimization operator; Step S4: multi-vessel collaborative optimization, which is used to optimize the collaborative operation of multiple vessels. Specifically, based on the optimization dataset for improving the construction efficiency of the pile-driving vessel and the reference data for optimizing the construction path of the pile-driving vessel, a reinforcement learning method is used to perform multi-vessel collaborative optimization to obtain reference data for optimizing the scheduling of multiple vessels for pile-driving vessel construction. Step S5: Construction efficiency is improved, and reference data on improvement of the comprehensive construction efficiency of the piling vessel is obtained.

2. The method for improving construction efficiency of a pile-driving ship based on artificial intelligence according to claim 1, characterized in that: In step S1, the sensor monitoring is used to arrange sensors and collect vessel, construction and environmental data, specifically to collect data through sensor arrangement to obtain an original data set for improving the construction efficiency of the piling vessel; The original data set for improving the construction efficiency of the piling vessel specifically includes vessel status data, environmental status data, and construction process data.

3. The method for improving construction efficiency of a pile-driving ship based on artificial intelligence according to claim 2, characterized in that: In step S2, the data preprocessing is used to optimize the original data, specifically to perform basic data enhancement on the original data set for improving the construction efficiency of the piling ship to obtain an optimized data set for improving the construction efficiency of the piling ship; The basic data enhancement specifically includes data cleaning, data normalization, data standardization, filtering and denoising, missing value processing and manual feature extraction; The pile-driving ship construction efficiency improvement optimization data set specifically includes optimizing ship status data, optimizing environmental status data, optimizing construction task data, optimizing ship operation data, optimizing multi-ship collaboration data and optimizing construction data.

4. The method for improving construction efficiency of a pile-driving ship based on artificial intelligence according to claim 3, characterized in that: In step S3, the construction path optimization is used to optimize the construction path of the piling ship. Specifically, based on the piling ship construction efficiency improvement optimization data set, a search algorithm improved by multi-structure global search optimization is used to optimize the construction path to obtain the piling ship construction path optimization reference data; The improved search algorithm of the multi-structure global search optimization specifically includes a chaos initialization operator, a benchmark weight optimization operator, a dynamic adjustment convergence operator, a global search enhancement operator, a local search fine-tuning operator, a pile-driving ship environmental adaptability dynamic adjustment operator, and a pile-driving ship construction path multi-objective optimization operator; The chaos initialization operator is used to generate the initial population parameters of the search algorithm by using a mixed advantage set and a chaotic map during the initialization phase of the search algorithm; The benchmark weight optimization operator is used to dynamically adjust the optimization weight and improve search stability; The dynamic adjustment convergence operator is used to balance the collaborative optimization of global search and local search; The global search enhancement operator is used to introduce global search enhancement to enhance the parameter diversity of the construction path of the pile-driving ship in the early stage of construction path optimization and to switch to precise search and optimization in the later stage; The local search fine-tuning operator is used to introduce a mutation operation to fine-tune the local search path and improve its accuracy; The piling vessel environmental adaptability dynamic adjustment operator is used to introduce analysis of the piling vessel environmental data and perform dynamic adjustment of the environmental adaptability construction path planning; The multi-objective optimization operator for the construction path of the pile-driving ship is used to construct a multi-objective optimization structure for the construction path of the pile-driving ship and comprehensively optimize various construction parameters of the pile-driving ship.

5. The method for improving construction efficiency of a pile-driving ship based on artificial intelligence according to claim 4, characterized in that: In step S3, the step of using the improved search algorithm of multi-structure global search optimization to optimize the construction path and obtain the optimized reference data of the construction path of the piling ship includes: Step S31: initializing search parameters, specifically setting an initial parameter set of the search algorithm, and improving and executing the search algorithm based on the initial parameter set; Step S32: chaos initialization, specifically using chaos advantage set initialization and chaos mapping to generate an initial search population and obtain optimized search initial position parameters; Step S33: Benchmark weight optimization, specifically, calculating the fitness value through the benchmark weight strategy, constructing the optimal search individual combination, performing path update, and obtaining benchmark weight optimization update individual data; The optimal search individual combination specifically includes exploration individuals, surrounding individuals, chasing individuals and propulsion individuals; the exploration individuals are used to explore new solutions, and the new solutions are used to represent new construction paths for pile-driving ships; the surrounding individuals are used to search around the optimal solution of the current number of iterations; the chasing individuals are used to follow and optimize the optimal solution of the current number of iterations; and the propulsion individuals are used to advance the overall process of the search algorithm; Step S34: Dynamically adjust convergence, specifically using a Gaussian adjusted cosine factor to dynamically adjust the search convergence process, and through the dynamic adjustment, balance the global search degree and local search degree of the search algorithm. The calculation formula of the Gaussian adjusted cosine factor is: ； Where f is the Gaussian adjusted cosine factor, which is used as the convergence factor for balancing the global search degree and local search degree of the search algorithm. start is the starting value of the convergence factor, f end is the final value of the convergence factor, t is the iteration index, T is the maximum number of iterations, is the standard deviation parameter of the Gaussian function; Step S35: Global search enhancement, specifically, by combining the dynamic adversarial learning algorithm and the sine-cosine algorithm to construct a global search enhancement operator. Specifically, in the early stage of the search algorithm, the dynamic adversarial learning algorithm is used as the search strategy, and in the middle stage of the search algorithm, the dynamic adversarial learning algorithm and the sine-cosine algorithm are used as the search strategy in a balanced manner. In the late stage of the search algorithm, the sine-cosine algorithm is used as the search strategy, and by constructing a dynamically adjusted learning rate parameter, the individual position of the search algorithm is updated to obtain global search enhancement individual data; Step S36: local search fine-tuning, specifically, applying a mutation operation to fine-tune the local search after each iteration of the search algorithm to obtain local tuning path data; The calculation formula of the local tuning path data is: ； Where, is the local tuning path data, is the optimal search individual position at the tth iteration, is the coefficient of variation parameter, is a randomly selected local search individual position; Step S37: Dynamically adjust the environmental adaptability of the piling vessel, specifically, dynamically adjust the environmental adaptability of the piling vessel based on the optimized environmental state data in the piling vessel construction efficiency improvement optimization data set to obtain environmental adaptability tuning path data. The calculation formula is: ； Where, is the environmental adaptability tuning path data, is the local tuning path data, is the environmental adaptability coefficient, enadjust(·) is the environmental data adjustment function, and env is the environmental characteristic data; Step S38: multi-objective optimization of the construction path of the piling ship, specifically introducing a multi-objective path optimization mechanism, setting a multi-objective optimal path output, performing multi-objective optimization of the construction path of the piling ship, and obtaining multi-objective construction path optimization output data; The multi-objective path optimization specifically includes the construction vessel coordinate optimization goal, the construction path length optimization goal, the total construction time optimization goal, the construction energy consumption optimization goal and the construction environment adjustment optimization goal; Step S39: Optimizing the construction path of the piling ship, specifically setting the maximum number of iterations and the convergence condition of the search algorithm, and iteratively executing the operations from Step S31 to Step S38 to optimize the construction path of the piling ship, thereby obtaining reference data for optimizing the construction path of the piling ship; The pile-driving ship construction path optimization reference data specifically includes construction vessel coordinate data, construction path length optimization data, total construction time optimization data, construction energy consumption optimization data and construction environment adjustment optimization data.

6. The method for improving construction efficiency of a pile-driving ship based on artificial intelligence according to claim 5, characterized in that: In step S4, the multi-vessel collaborative optimization is used to optimize the collaborative operation of multiple vessels. Specifically, based on the piling vessel construction efficiency improvement optimization data set and the piling vessel construction path optimization reference data, a reinforcement learning method is used to perform multi-vessel collaborative optimization to obtain the piling vessel construction multi-vessel optimization scheduling reference data, which specifically includes the following steps: Step S41: Initializing the reinforcement learning model, specifically extracting multi-vessel initial state data, vessel working data, vessel position data, vessel relative distance data, and construction target data from the piling vessel construction efficiency improvement optimization dataset and the piling vessel construction path optimization reference data, and using these as raw data input for multi-vessel collaborative optimization to construct a standard reinforcement learning model; The standard reinforcement learning model, including action space, state space and reward function; Step S42: multi-ship collaborative scheduling and allocation, specifically, applying deep Q learning based on the multi-ship collaborative optimization raw data input and the standard reinforcement learning model to perform multi-ship task allocation reinforcement learning training to obtain a multi-ship collaborative scheduling allocation model, and obtaining multi-ship collaborative scheduling allocation reference solution data by applying the multi-ship collaborative scheduling allocation model; Step S43: Dynamic collaborative optimization, specifically, maximizing operational efficiency by continuously adjusting the multi-vessel collaboration mode during the piling barge construction process, and updating and maintaining the multi-vessel collaborative scheduling allocation model through real-time feedback; Step S44: multi-vessel collaborative optimization, specifically, performing reinforcement learning optimization of multi-vessel collaborative operation through the reinforcement learning model initialization, the multi-vessel collaborative scheduling allocation and the dynamic collaborative optimization, and obtaining multi-vessel optimized scheduling reference data for pile driving vessel construction; The multi-vessel optimized scheduling reference data for pile-driving ship construction specifically includes vessel identification data, multi-vessel task allocation data, vessel position data, vessel path planning data, vessel speed data, vessel operation load data, vessel collaboration information data and operation scheduling efficiency reference data.

7. The method for improving construction efficiency of a pile-driving ship based on artificial intelligence according to claim 6, characterized in that: In step S5, the construction efficiency is improved, and is used to comprehensively improve the efficiency of pile-driving ship construction by combining the comprehensive optimization results of the construction path and multi-ship collaboration. Specifically, by combining the pile-driving ship construction path optimization reference data, the optimal construction path of a single pile-driving ship is predicted, and by combining the pile-driving ship construction multi-ship optimization scheduling reference data, the parallel construction and joint operation scheduling of the pile-driving ships are optimized to obtain the reference data for improving the comprehensive construction efficiency of the pile-driving ship.

8. An artificial intelligence-based system for improving the construction efficiency of a pile-driving vessel, for implementing the artificial intelligence-based method for improving the construction efficiency of a pile-driving vessel as claimed in any one of claims 1 to 7, characterized in that: It includes sensor monitoring module, data preprocessing module, construction path optimization module, multi-ship collaborative optimization module and construction efficiency improvement module.

9. The artificial intelligence-based piling vessel construction efficiency improvement system according to claim 8, characterized in that: The sensor monitoring module is used for sensor monitoring, obtaining an original data set of the pile driving ship construction efficiency improvement through sensor monitoring, and sending the original data set of the pile driving ship construction efficiency improvement to the data preprocessing module; The data preprocessing module is used for data preprocessing, obtaining a data set for optimizing the construction efficiency of a pile-driving vessel through data preprocessing, and sending the data set for optimizing the construction efficiency of a pile-driving vessel to the construction path optimization module and the multi-vessel collaborative optimization module; The construction path optimization module is used for construction path optimization, obtains construction path optimization reference data of the pile-driving ship through construction path optimization, and sends the construction path optimization reference data of the pile-driving ship to the multi-vessel collaborative optimization module and the construction efficiency improvement module; The multi-vessel collaborative optimization module is used for multi-vessel collaborative optimization, obtains multi-vessel optimization scheduling reference data for pile driving vessel construction through multi-vessel collaborative optimization, and sends the multi-vessel optimization scheduling reference data for pile driving vessel construction to the construction efficiency improvement module; The construction efficiency improvement module is used to improve construction efficiency. Through the improvement of construction efficiency, reference data for improvement of the comprehensive construction efficiency of the piling vessel is obtained.

Images