Multifunctional auxiliary ship space arrangement method and system based on industrial requirements
By constructing a rule base for aquaculture auxiliary vessels and employing a multi-objective particle swarm optimization algorithm, the spatial layout of multi-functional auxiliary vessels is optimized, solving the problems of low space utilization and high modification costs in traditional designs, and achieving synergistic optimization of function and performance.
Patent Information
- Application Number
- CN202511476543.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-16
- Publication Date
- 2026-02-27
AI Technical Summary
The spatial layout design of traditional multi-functional auxiliary vessels is difficult to cope with the complex and ever-changing needs of industrial scenarios, resulting in low space utilization, frequent functional conflicts or high modification costs, and lack of systematic consideration of dynamic task switching, equipment compatibility and human-machine ergonomics.
By constructing a rule base for aquaculture auxiliary vessels, analyzing the correlation between the characteristics of marine aquaculture ranches, aquaculture operation requirements, and vessel functional characteristics, a multi-objective particle swarm optimization algorithm is used to generate layout schemes, and multi-dimensional data mining and decision tree algorithms are combined to optimize the spatial layout of vessels.
It achieves synergistic optimization of the functions, performance and cost of the multi-functional auxiliary vessel throughout its entire life cycle, improving space utilization and operational efficiency while reducing conversion costs.
Smart Images

Figure CN121581173A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of aquaculture auxiliary ship, and particularly relates to a multifunctional auxiliary ship space arrangement method and system based on industrial demand. BACKGROUND
[0002] With the rapid development of global marine economy and offshore operation activities, the application demand of multifunctional auxiliary ships in the fields of marine resource development and fishery support is increasing. Such ships need to have multiple functions such as material transportation, equipment loading, personnel residence and dynamic positioning, and the rationality and adaptability of the space layout directly determine the operation efficiency and economic benefit of the ship. Traditional ship design usually plans the space based on a single task, and the function areas of cabins and decks are relatively fixed, which is difficult to meet the needs of complex and variable industrial scenarios. For example, multifunctional aquaculture auxiliary ships need to balance the relationship between bait transportation and feeding, net replacement, fish transportation and crew life, etc. The existing design methods mostly rely on experiential layout and static partitioning, and lack of systematic consideration of task dynamic switching, equipment compatibility and human-machine ergonomics, resulting in low space utilization, frequent functional conflicts or high modification costs. At the same time, with the popularization of intelligent equipment and green energy technology, the ship needs to reserve power system expansion interfaces, unmanned equipment loading areas and new energy storage spaces, which further aggravates the complexity of space planning.
[0003] Under the current industrial background, there is an urgent need for a space arrangement method that integrates multi-objective optimization, modular design and dynamic adaptability evaluation, to realize the whole life cycle collaborative optimization of ship function, performance and cost. SUMMARY
[0004] The present application overcomes the defects of the prior art and provides a multifunctional auxiliary ship space arrangement method and system based on industrial demand.
[0005] To achieve the above purpose, the first aspect of the present application provides a multifunctional auxiliary ship space arrangement method based on industrial demand, comprising: Obtaining historical usage instances of different single-function type aquaculture auxiliary ships, analyzing the correlation between marine aquaculture pasture characteristics, aquaculture operation demand and aquaculture auxiliary ship function characteristics, and constructing a first aquaculture auxiliary ship rule base; Extracting ship structure characteristics and historical ship navigation characteristics of each single-function type aquaculture auxiliary ship through historical usage instances, judging the correlation between ship space and ship performance, and constructing a second aquaculture auxiliary ship rule base; Analyzing the economic characteristics of each single-function aquaculture auxiliary ship, and correlating the correlation rules in the first aquaculture auxiliary ship rule base and the second aquaculture auxiliary ship rule base, to construct a coupled correlation rule base; The current mariculture operation demand is acquired, a multi-objective particle swarm optimization algorithm is used for arrangement scheme analysis in combination with the constructed coupling association rule library, and an arrangement scheme is generated for recommendation.
[0006] In the scheme, the association relationship among the characteristics of the marine mariculture farm, the mariculture operation demand and the function characteristics of the mariculture auxiliary ship is analyzed, and a first mariculture auxiliary ship rule library is constructed, specifically including: Based on data retrieval, historical use instances of different single function type mariculture auxiliary ships are acquired, and feature extraction is performed to acquire mariculture auxiliary ship function characteristics, mariculture operation demand characteristics and historical mariculture farm characteristics, to obtain historical use instance feature information; According to the mariculture operation demand characteristics extracted from the historical use instance feature information, mariculture demand labels are generated based on mariculture characteristics demand, and corresponding mariculture auxiliary ship function characteristics are associated to obtain first association information; A preset membership function is used to calculate the membership value between the mariculture operation demand and the mariculture auxiliary ship function characteristics, and the historical use instance data set is generated in combination with the first association information; The Apriority algorithm is introduced to mine frequent item sets according to the historical use instance data set, and a plurality of frequent item subsets are obtained through layer-by-layer search, and a plurality of association rules of mariculture demand and mariculture auxiliary ship function characteristics are generated using each frequent item subset; A preset confidence threshold is set, the confidence of the association rule corresponding to each mariculture demand event is calculated, and the confidence threshold is judged, the association rule greater than the preset confidence threshold is defined as an effective association rule, the association rule is screened, and an association rule data set is generated.
[0007] In the scheme, the association relationship among the characteristics of the marine mariculture farm, the mariculture operation demand and the function characteristics of the mariculture auxiliary ship is analyzed, and a first mariculture auxiliary ship rule library is constructed, specifically including: The historical use instance feature information is acquired, and the historical marine mariculture farm characteristics of each historical use instance are extracted through the historical use instance feature information, including mariculture area, mariculture water body, mariculture type and farm voyage, to obtain historical marine mariculture farm characteristic information; The mariculture auxiliary ship function characteristics are extracted through the historical use instance feature information, and a decision tree algorithm is introduced, the characteristics of the marine mariculture farm are taken as the decision attribute, and the function characteristics of the mariculture auxiliary ship are taken as the target attribute, and the root node is initialized; The initialized root node is acquired, and the different marine mariculture farm characteristics are used for classification to obtain a plurality of root node branches and construct the hierarchical structure of the decision tree, the judgment basis of the information gain best split node is defined to construct the decision tree, and the first topological structure diagram is generated through the constructed decision tree; obtain an association rule dataset, extract an association rule between a function feature of the aquaculture auxiliary ship and the aquaculture operation demand based on the association rule dataset, define the function feature of the aquaculture auxiliary ship as a target attribute, and define the aquaculture operation demand as a decision attribute, and construct a second topological structure diagram; take the function feature node of the aquaculture auxiliary ship as a connection node, construct an association rule with the marine aquaculture pasture feature, the aquaculture operation demand and the function feature of the aquaculture auxiliary ship as a path by using the first topological structure diagram and the second topological structure diagram, and generate a first aquaculture auxiliary ship rule library.
[0008] In the scheme, the ship structure features and the historical ship navigation features of each function type of the aquaculture auxiliary ship are extracted through historical use instances, the association relationship between the ship space and the ship performance is judged, and a second aquaculture auxiliary ship rule library is constructed, which specifically includes: obtain historical use instances of different function types of the aquaculture auxiliary ship, extract ship structure features and historical ship navigation features of each function type of the aquaculture auxiliary ship through the historical use instances, and obtain aquaculture auxiliary ship feature information; extract the ship structure features based on the aquaculture auxiliary ship feature information, calculate the limited three-dimensional space and the limited deck space through the ship structure features, and divide the ship internal area through the regional function type through the ship structure features to obtain first analysis information; based on the first analysis information, a cabin topological relationship modeling is performed by using a graph theory method, each cabin is defined as a single node, and the function features corresponding to the cabin nodes and the distance features of the adjacent nodes are taken as node merging bases to establish a cabin topological structure diagram; extract the historical ship navigation features through the aquaculture auxiliary ship feature information, generate the historical navigation sea area wave spectrum of each type of the aquaculture auxiliary ship according to the historical ship navigation features, and extract the wave height features and the spectral peak period features; construct a roll motion equation by using a linear potential flow theory through the historical ship navigation features, analyze the historical navigation roll response amplitude of each type of the aquaculture auxiliary ship, and combine the extracted wave height features and the spectral peak period features as ship performance representations to obtain second analysis information; based on the cabin topological structure diagram, obtain a plurality of adjacency matrices representing the spatial topological connection relationship of each type of the aquaculture auxiliary ship, associate the second analysis information, construct an association rule with space-performance as a path, and generate a second aquaculture auxiliary ship rule library.
[0009] In the scheme, the economic features of each single function type of the aquaculture auxiliary ship are analyzed, and the association rules in the first aquaculture auxiliary ship rule library and the second aquaculture auxiliary ship rule library are associated to construct a coupled association rule library, which specifically includes: Obtaining a first aquaculture auxiliary ship rule base and a second aquaculture auxiliary ship rule base, and extracting aquaculture auxiliary ship function characteristics and aquaculture auxiliary ship structure characteristics through the first aquaculture auxiliary ship rule base and the second aquaculture auxiliary ship rule base; Based on the aquaculture auxiliary ship function characteristics, the function device type corresponding to each aquaculture auxiliary ship function and the device value are obtained by using a data retrieval means, the aquaculture auxiliary ship structure characteristics are used to obtain the structure material type and the material scale of each type of aquaculture auxiliary ship, and the second analysis information is generated; The association rules in the first aquaculture auxiliary ship rule base and the second aquaculture auxiliary ship rule base are coupled, the second analysis information is taken as an auxiliary feature, the coupled association rules with the path of aquaculture pasture characteristics, aquaculture operation demand, aquaculture auxiliary ship function and aquaculture auxiliary ship performance are generated, and a coupled association rule base is obtained.
[0010] In the scheme, the current marine pasture aquaculture operation demand is obtained, a multi-objective particle swarm optimization algorithm is used for arrangement scheme analysis in combination with the constructed coupled association rule base, an arrangement scheme is generated for recommendation, and specifically includes the following steps: The current marine pasture aquaculture operation demand is obtained, three-dimensional target space is constructed in combination with the coupled association rule database by defining three-dimensional targets of function completeness, navigation performance and cost economy; A multi-objective particle swarm optimization algorithm is introduced for arrangement scheme analysis, a target function is established according to the three-dimensional targets of function completeness, navigation performance and cost economy, and constraint conditions and a penalty function are generated through the current marine pasture aquaculture operation demand; An initial population is obtained by initializing the population using the constructed three-dimensional target space, the fitness values of individuals in the initial population are calculated based on the target function, if the constraint conditions are violated, the fitness is modified through the penalty function, and an initial optimal population individual is obtained; Non-dominated solutions are obtained by performing non-dominated solution screening on the initial population based on the calculated fitness values, an external population is generated according to the obtained non-dominated solutions, and a guide solution is selected based on the external population to perform particle updating operation in combination with the initial optimal population individual; The non-dominated solution set of the final external population is output when the iteration number reaches a preset threshold or meets the convergence standard through repeated iteration analysis of the updated population, and a multi-functional aquaculture auxiliary ship arrangement scheme for the current marine pasture aquaculture operation demand is generated according to the non-dominated solution set of the final external population.
[0011] The second aspect of the present application provides a multi-functional auxiliary ship space arrangement system based on industrial demand, which comprises a memory and a processor, the memory contains a multi-functional auxiliary ship space arrangement method program based on industrial demand, and the multi-functional auxiliary ship space arrangement method program based on industrial demand is executed by the processor to realize the following steps: Obtaining historical use examples of different single function type aquaculture auxiliary ships, analyzing the correlation between the characteristics of the marine aquaculture pasture, the aquaculture operation demand and the function characteristics of the aquaculture auxiliary ship, and constructing a first aquaculture auxiliary ship rule base; Extracting the ship structure characteristics and historical ship navigation characteristics of each single function type aquaculture auxiliary ship through historical use examples, judging the correlation between the ship space and the ship performance, and constructing a second aquaculture auxiliary ship rule base; Analyzing the economic characteristics of each single function aquaculture auxiliary ship, and correlating the correlation rules in the first aquaculture auxiliary ship rule base and the second aquaculture auxiliary ship rule base, and constructing a coupled correlation rule base; Obtaining the current marine pasture aquaculture operation demand, combining the coupled correlation rule base, and using a multi-objective particle swarm optimization algorithm to analyze the arrangement scheme, and generating an arrangement scheme for recommendation.
[0012] The application discloses a multifunctional auxiliary ship space arrangement method and system based on industrial demand, which comprises the following steps: obtaining historical use examples of different function type aquaculture auxiliary ships, analyzing the correlation between the characteristics of the marine aquaculture pasture, the aquaculture operation demand and the function characteristics of the aquaculture auxiliary ship, and constructing a first aquaculture auxiliary ship rule base; extracting the ship structure characteristics and historical ship navigation characteristics of each function type aquaculture auxiliary ship, judging the correlation between the ship space and the ship performance, and constructing a second aquaculture auxiliary ship rule base; analyzing the economic characteristics of each single function aquaculture auxiliary ship, and correlating the correlation rules in the first aquaculture auxiliary ship rule base and the second aquaculture auxiliary ship rule base, and constructing a coupled correlation rule base; obtaining the current marine pasture aquaculture operation demand, combining the coupled correlation rule base, and using a multi-objective particle swarm optimization algorithm to analyze the arrangement scheme, and generating an arrangement scheme for recommendation. The whole life cycle collaborative optimization of the ship body function, performance and cost is realized according to the operation demand. ACCURATE DESCRIPTION OF DRAWINGS
[0013] In order to more clearly illustrate the technical solutions in the embodiments or examples of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or examples. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained according to the drawings shown by those skilled in the art without creating any creative labor.
[0014] Figure 1 A multifunctional auxiliary ship space arrangement method flow chart based on industrial demand is provided for an embodiment of the present application; Figure 2 A multifunctional auxiliary ship space arrangement optimization method flow chart based on industrial demand is provided for an embodiment of the present application; Figure 3 A multifunctional auxiliary ship space arrangement system block diagram based on industrial demand is provided for an embodiment of the present application; The objectives, functional characteristics and advantages of the present application will be further described with reference to the embodiments and in conjunction with the accompanying drawings. DETAILED DESCRIPTION
[0015] In order to enable a more complete understanding of the above-mentioned objects, features and advantages of the present application, the present application will be further described below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.
[0016] In the following description, a large number of specific details are set forth in order to facilitate a thorough understanding of the present application, however, the present application can also be implemented in other manners different from those described herein, and therefore, the protective scope of the present application is not limited by the specific embodiments disclosed below.
[0017] Figure 1 A multifunctional auxiliary ship space arrangement method based on industrial demand provided by an embodiment of the present application is shown in a flow chart; As Figure 1 shown, the present application provides a multifunctional auxiliary ship space arrangement method based on industrial demand flow chart, comprising: S102, obtaining historical usage instances of different single-function type aquaculture auxiliary ships, analyzing the correlation between the characteristics of the marine aquaculture ranch, the aquaculture operation demand and the functional characteristics of the aquaculture auxiliary ship, and constructing a first aquaculture auxiliary ship rule base; S104, extracting the ship structure characteristics and historical ship navigation characteristics of each single-function type aquaculture auxiliary ship through the historical usage instances, judging the correlation between the ship space and the ship performance, and constructing a second aquaculture auxiliary ship rule base; S106, analyzing the economic characteristics of each single-function aquaculture auxiliary ship, and correlating the first aquaculture auxiliary ship rule base and the second aquaculture auxiliary ship rule base, and constructing a coupled correlation rule base; S108, obtaining the current marine ranch aquaculture operation demand, combining the constructed coupled correlation rule base, and using a multi-objective particle swarm optimization algorithm to analyze the arrangement scheme, and generating the arrangement scheme for recommendation.
[0018] Further, in a preferred embodiment of the present application, the analysis of the correlation between the characteristics of the marine aquaculture ranch, the aquaculture operation demand and the functional characteristics of the aquaculture auxiliary ship, and the construction of the first aquaculture auxiliary ship rule base specifically comprises: Based on data retrieval, historical usage instances of different single-function type aquaculture auxiliary ships are obtained, feature extraction is performed to obtain aquaculture auxiliary ship functional characteristics, aquaculture operation demand characteristics and historical aquaculture ranch characteristics, and historical usage instance feature information is obtained; According to the historical use instance feature information, breeding operation demand features are extracted, breeding demand labels are generated based on breeding feature demands, corresponding breeding auxiliary ship function features are associated, and first association information is obtained; A preset membership function is used to calculate the membership value between the breeding operation demand and the breeding auxiliary ship function feature, and the historical use instance dataset is generated in combination with the first association information; The Apriority algorithm is introduced to perform frequent item set mining on the historical use instance dataset, and a plurality of frequent item subsets are obtained through layer-by-layer search, and a plurality of association rules between breeding demands and breeding auxiliary ship function features are generated by using the frequent item subsets; A preset confidence threshold is set, the confidence of the association rule corresponding to each breeding demand event is calculated, and the confidence threshold is judged, the association rule greater than the preset confidence threshold is defined as an effective association rule, the association rule is screened, and an association rule dataset is generated.
[0019] It should be noted that the relevant information is retrieved from the historical use data of the breeding auxiliary ship of different functional types, which covers multi-dimensional data such as the functional configuration of the ship itself, the specific breeding operation demand, and the environmental and operation features of the historical breeding pasture. The original data is converted into structured feature information through feature extraction technology. These features include functional attributes such as the deck layout, equipment carrying capacity, and energy supply mode of the ship, and demand attributes such as the fry release frequency, feed transportation volume, and water quality monitoring requirements in the breeding operation. At the same time, environmental parameters such as the sea area conditions, breeding varieties, and production scale of the historical breeding pasture are integrated to form a comprehensive feature dataset covering the ship, the task, and the environment.
[0020] It should be noted that after obtaining the historical use instance feature information, the discrete job tasks are converted into standardized aquaculture demand labels, such as “high-frequency fry transportation”, “large-scale feed feeding” or “real-time water quality monitoring” and the like through classification and clustering of the job demand features, and these labels are associated and mapped with the corresponding aquaculture auxiliary ship function features to establish an initial association relationship database. The explicit correspondence between the identified demand and function in this stage, for example, the high-frequency fry transportation demand may be associated with the cold chain storage capacity of the ship, the quick loading and unloading equipment and the like, forming a preliminary association rule basic data. In order to quantify the matching degree between the demand and the function, the membership function in fuzzy mathematics is introduced to convert the unstructured association relationship into a numerical membership value. For example, for the “real-time water quality monitoring” demand and the “multi-parameter sensor carrying” function, a triangular or trapezoidal membership function can be designed, and the matching degree thereof is calculated according to the frequency and conditional probability of the simultaneous occurrence of the two in the historical data. Further, a multi-dimensional data set containing demand labels, function features and membership values is constructed to provide standardized input for subsequent association rule mining. Subsequently, the Apriori algorithm is used for frequent item set mining, and the demand-function combination frequently co-occurring is identified through a layer-by-layer search and pruning strategy. The algorithm first scans the historical data set to count the frequency of occurrence of a single demand or function item, and selects the single item set that meets the minimum support; then, based on the a priori principle, the candidate item set containing multiple items is generated through connection and pruning operation, and the support thereof is verified again to determine the frequent item set. This process is iterated until no higher-order frequent item set can be generated. Through this method, frequent item subsets reflecting the strong association between demand and function, such as “high-density aquaculture, oxygenation equipment demand-powerful oxygen supply system” or “deep-sea aquaculture, harsh sea conditions-high stability ship design” and the like can be mined. Finally, the generated association rules are screened for effectiveness by pre-setting a confidence threshold. The confidence calculation is the conditional probability of the simultaneous occurrence of the rule antecedent and the consequent, i.e. confidence = support (antecedent ∪ consequent) / support (antecedent), which is used to measure the confidence degree of the rule. For example, if the confidence of “fry survival rate requirement ≥95%-closed temperature control cargo hold” is 0.85, and the pre-set threshold is 0.75, then the rule is retained as an effective association rule.
[0021] It should be noted that the pre-set membership function can use a binary matching enhancement function to analyze the membership between the aquaculture job demand and the aquaculture auxiliary ship function feature, for example, the demand type is feed transportation and the associated function is storage capacity, and the association times of various aquaculture job demands and aquaculture auxiliary ship functions are counted to obtain the membership value.
[0022] The binary matching enhancement function is as follows:
[0023] The function indicates that when the breeding auxiliary ship function features and the breeding operation demand features completely match, the membership degree is 1; when they completely do not match, the membership degree is 0; and when they partially match, the membership degree takes the average of the normalized values.
[0024] Further, in a preferred embodiment of the present application, the analysis of the correlation between the marine aquaculture farm features, the breeding operation demand and the breeding auxiliary ship function features to construct the first breeding auxiliary ship rule base further comprises: Obtaining historical use instance feature information, extracting historical marine aquaculture farm features of each historical use instance from the historical use instance feature information, including breeding area, breeding water body, breeding type and farm voyage, to obtain historical marine aquaculture farm feature information; Extracting the breeding auxiliary ship function features from the historical use instance feature information, introducing a decision tree algorithm, taking the marine aquaculture farm features as decision attributes and the breeding auxiliary ship function features as target attributes to initialize the root node; Obtaining the initialized root node, classifying and obtaining a plurality of root node branches and constructing the hierarchical structure of the decision tree by using different marine aquaculture farm features, defining the judgment basis of the best split node of information gain for decision tree construction, and generating a first topological structure diagram through the constructed decision tree; Obtaining an association rule data set, extracting the association rules of the breeding auxiliary ship function features and the breeding operation demand based on the association rule data set, defining the breeding auxiliary ship function features as target attributes and the breeding operation demand as decision attributes, and constructing a second topological structure diagram; Taking the breeding auxiliary ship function feature node as a connection node, constructing the association rules with the marine aquaculture farm features, the breeding operation demand and the breeding auxiliary ship function features as the path by using the first topological structure diagram and the second topological structure diagram, and generating the first breeding auxiliary ship rule base.
[0025] It should be noted that, first, the basic features of the marine aquaculture farm are extracted from the historical use instance, including breeding area, water volume, breeding type (such as fish, shellfish or algae) and farm voyage (i.e. typical round trip distance between breeding area and port), forming a key parameter set describing the breeding scene. These parameters directly affect the functional requirements of the auxiliary ship, for example, large-scale deep-water breeding may require the ship to have large cargo capacity, wind and wave resistance and long-range endurance characteristics, while high-density breeding requires the ability to strengthen the carrying capacity of water quality monitoring and oxygen supply equipment. The structured extraction of historical aquaculture farm feature information provides a data basis for the subsequent analysis of the environment and task dimensions.
[0026] It should be noted that after the characteristics of the marine culture pasture are determined, the functional characteristics of the culture auxiliary ship are further extracted, covering technical indicators such as deck layout, equipment configuration, energy system, and cabin partition, and a decision tree algorithm is introduced to establish a mapping relationship between the characteristics of the marine culture pasture and the ship function. Specifically, the culture area, water type, type and voyage are taken as decision attributes, and the ship function characteristics are taken as target attributes to initialize the root node of the decision tree. By traversing the historical data, the information gain of each decision attribute is calculated, and the feature with the highest gain is selected as the node splitting basis. For example, if the information gain of “culture type” to “oxygen supply equipment necessity” is the highest, then the splitting condition is generated based on this, and the data set is recursively divided until a complete decision tree hierarchy structure is formed. Finally, the first topology structure diagram is generated, which directly shows the priority and combination rules of the ship function configuration under different culture scenarios. At the same time, based on the association rule data set, strong association rules between the functional characteristics of the culture auxiliary ship and the culture operation requirements (such as fry release frequency, feed feeding amount, disease monitoring intensity, etc.) are extracted, and a second topology structure diagram is constructed. In this diagram, the functional characteristics are taken as target attributes, and the operation requirements are taken as decision attributes, forming rule chains such as “real-time water quality monitoring requirement → multi-parameter sensor + data control system”. In order to realize the collaborative optimization of multi-dimensional characteristics, the two types of topology structure diagrams are bridged through the ship function characteristic nodes, and the association paths of the culture pasture characteristics, operation requirements and function configuration are integrated. For example, when a certain culture pasture characteristic (such as “large-scale algae culture + long-distance voyage”) in the historical data derives the “large deck area + solar panel configuration” function requirement through the decision tree, and the association rule shows that “large deck area” is often strongly related to “mechanized harvesting equipment” requirement, the system will generate a composite rule: “large-scale algae culture + long-distance voyage + mechanized harvesting requirement → large deck area + solar panel + harvesting equipment interface”. Such rules not only reflect the influence of single characteristics, but also capture the coupling effect of multiple factors, enhancing the scene adaptability and decision completeness of the rule base.
[0027] Further, in a preferred embodiment of the present application, the ship structure characteristics and historical ship navigation characteristics of each single function type culture auxiliary ship are extracted through historical use instances, the association relationship between ship space and ship performance is judged, and a second culture auxiliary ship rule base is constructed, specifically including: Obtaining historical use instances of different single function type culture auxiliary ships, extracting ship structure characteristics and historical ship navigation characteristics of each function type culture auxiliary ship through the historical use instances, and obtaining culture auxiliary ship characteristic information; Based on the culture auxiliary ship characteristic information, the ship structure characteristics are extracted, the limited three-dimensional space and the limited deck space are calculated through the ship structure characteristics, and the ship internal area is divided through the regional function type through the ship structure characteristics, to obtain first analysis information; Based on the first analysis information, a cabin topology relationship modeling is performed by using a graph theory method, each cabin is defined as a single node, and a function feature corresponding to the cabin node and a distance feature of adjacent nodes are combined as a node to establish a cabin topology structure graph; By extracting the historical ship navigation features from the aquaculture auxiliary ship feature information, generating the historical navigation sea area wave spectrum of various types of aquaculture auxiliary ships according to the historical ship navigation features, and extracting the wave height feature and the spectral peak period feature; By using the linear potential flow theory to construct the roll motion equation through the historical ship navigation features, analyzing the historical navigation roll response amplitude of various types of aquaculture auxiliary ships, and combining the extracted wave height feature and the spectral peak period feature as the ship performance representation, the second analysis information is obtained; Based on the cabin topology structure graph, a plurality of adjacency matrices representing the spatial topology connection relationship of various types of aquaculture auxiliary ships are obtained, the second analysis information is associated, the association rules with space-performance as the path are constructed, and the second aquaculture auxiliary ship rule library is generated.
[0028] It should be noted that first, the ship structure features are extracted from the historical operation data of different functional types of aquaculture auxiliary ships, including static parameters such as ship main dimensions (length, width, depth), deck functional zoning, cabin layout topology, and dynamic navigation features such as speed trajectory, load state, and operation sea area, forming a feature information library covering structure, function and environment. For example, the baiting ship may have an open rear deck and a through-type layout of the feed storage and transportation cabin, while the monitoring ship is equipped with a modular structure of multi-level laboratory and equipment cabin, which directly affects the space utilization efficiency and operation adaptability of the ship. Based on the structure feature data, the spatial constraints of the ship are further quantified. Through three-dimensional modeling, the limited cubic space (cargo hold volume, vertical net height) and deck effective area of the ship are calculated, and the internal space is grid divided according to the regional function type (such as power area, living area, operation area). For example, for cold chain transport type auxiliary ships, priority should be given to the space proportion of refrigerated cargo hold and deck loading and unloading area, while coordinating the layout of engine room equipment and the topology of personnel passage, forming the first analysis information describing the priority and compatibility rules of space allocation. Based on the analysis of spatial features, the graph theory method is introduced to construct the cabin topology relationship model. Each cabin is abstracted as an independent node, and the node attributes include function type (such as storage, power, residence, etc.), space volume and distance threshold of adjacent cabins. Based on the principles of "function complementation priority proximity" (such as power distribution cabin needs to be close to power equipment area) and "safety isolation constraint" (such as the minimum distance between fuel cabin and living area), the node merging rules are established, and the topological structure graph representing the connection relationship of cabins is generated. At the same time, the ship performance data is extracted from the historical navigation features. By analyzing the wave statistical data of the operation sea area, the wave energy spectrum (such as JONSWAP spectrum or Pierson-Moskowitz spectrum) of typical sea conditions is constructed, and the characteristic wave height and spectral peak period are extracted as environmental excitation parameters. Combined with the ship load condition and speed data, the roll motion equation is established by using linear potential flow theory, the roll response amplitude operator (RAO) in different sea conditions is calculated, the ship's seakeeping performance is quantified, and the second analysis information evaluating the ship's performance is constructed. Finally, the cabin topology structure graph and navigation performance data are cross-domain associated. The cabin space connection strength is encoded through adjacency matrix, and the corresponding performance indicators such as roll amplitude and speed maintenance ability are matched, to excavate the implicit correlation between space layout and ship stability. For example, the isolation distance between engine room and living area in the topological graph is negatively correlated with the roll amplitude, and the through-type cargo cabin layout may cause the center of gravity to rise and thus reduce the initial stability height. Such rules are abstracted as "power area front + low position layout of living area → roll amplitude reduction of 15%" and other space-performance correlation rules, generating the second aquaculture auxiliary ship rule library, providing a multi-dimensional rule engine for intelligent ship design.
[0029] Further, in a preferred embodiment of the present application, the economic characteristics of each single function aquaculture auxiliary ship are analyzed, and the associated rules in the first aquaculture auxiliary ship rule base and the second aquaculture auxiliary ship rule base are associated to construct a coupled associated rule base, specifically comprising: obtaining the first aquaculture auxiliary ship rule base and the second aquaculture auxiliary ship rule base, and extracting the aquaculture auxiliary ship function characteristics and the aquaculture auxiliary ship structure characteristics through the first aquaculture auxiliary ship rule base and the second aquaculture auxiliary ship rule base; based on the aquaculture auxiliary ship function characteristics, using data retrieval means to obtain the function equipment type and equipment value corresponding to each aquaculture auxiliary ship function, and through the aquaculture auxiliary ship structure characteristics to obtain the structure material type and material scale of each type of aquaculture auxiliary ship, to generate the second analysis information; coupling the associated rules in the first aquaculture auxiliary ship rule base and the second aquaculture auxiliary ship rule base, and taking the second analysis information as an accessory characteristic, to generate the coupled associated rules with the aquaculture pasture characteristics, the aquaculture operation demand, the aquaculture auxiliary ship function and the aquaculture auxiliary ship performance as the path, to obtain the coupled associated rule base.
[0030] It should be noted that firstly the functional features and the structural features are extracted from the first aquaculture auxiliary ship rule base and the second aquaculture auxiliary ship rule base. The functional features include the equipment type (such as baiting machine, water quality sensor, hoisting crane) carried by the ship and its operation ability parameters, and the structural features cover the ship body material (such as steel, aluminum alloy, composite material), cabin layout topology and main dimension parameters. Both of them define the design boundary from the aspects of task adaptability and engineering feasibility. After the functional and structural features are defined, the second analysis information is further generated through data retrieval and economic modeling. Specifically, based on the equipment type (such as automatic baiting system, cold chain storage equipment) in the functional features, the equipment procurement cost, energy consumption parameter and maintenance cycle data are obtained by combining market research or supplier database; at the same time, according to the material type (such as ship steel plate, glass steel) and the amount of scale (such as tonnage, plate area) in the structural features, the material cost and processing fee are calculated, and such economic data provides a quantitative basis for subsequent cost-benefit analysis. Then, the association rules of the two rule bases are coupled in multiple dimensions. Through the rule matching algorithm, the intersection and dependency relationship of the functional-demand rules and the structural-performance rules are identified. For example, the demand of "offshore aquaculture → remote navigation + anti-wave ability" in the first rule base may be associated with the performance rule of "high bulwark design + stabilizer fin configuration → 20% reduction of roll amplitude" in the second rule base, forming a compound rule "offshore aquaculture + anti-wave demand → high bulwark design + stabilizer fin + satellite navigation equipment". In this process, the equipment value and material cost in the second analysis information are embedded as auxiliary features in the rule chain, forming a cost-performance trade-off path such as "high bulwark design (steel cost + 15%) + stabilizer fin (equipment value 800,000 yuan) → anti-wave performance meets the standard". Such coupled rules not only describe the technical feasibility, but also quantify the relationship between economic investment and performance gain. Finally, the coupled association rule base is generated, taking the aquaculture pasture features, operation demand, ship function, structural performance and economic cost as the association path, to build a knowledge network covering technology, environment and economy. The rule base provides decision support for designers from demand analysis, function configuration, structure design to cost estimation by integrating multi-source data and cross-field rules, and realizes the global optimal balance between technical performance, task adaptability and economic feasibility of ship design.
[0031] Figure 2 A flow chart of a multifunctional auxiliary ship space layout optimization method based on industrial demand is provided for an embodiment of the application. As Figure 2 shown, the application provides a flow chart of a multifunctional auxiliary ship space layout optimization method based on industrial demand, which includes: S202, acquiring the current marine pasture aquaculture operation demand, defining three-dimensional target space of functional completeness, navigation performance and cost economy, and combining the coupled association rule database to build the three-dimensional target space; S204, a multi-objective particle swarm optimization algorithm is introduced for arrangement scheme analysis, a target function is established according to three-dimensional target of function completeness, navigation performance and cost economy, constraint conditions and penalty function are generated through current marine ranching operation demand; S206, the initial population is obtained by initializing the population in the three-dimensional target space, the fitness value of each individual in the initial population is calculated based on the target function, if the constraint condition is violated, the fitness is modified through the penalty function, and the initial optimal population individual is obtained; S208, the non-dominated solution is obtained by non-dominated solution screening of the initial population based on the calculated fitness value, the external population is generated according to the obtained non-dominated solution, and the particle update operation is performed based on the external population selected guide solution combined with the initial optimal population individual; S210, the non-dominated solution set of the final external population is output when the iteration number reaches the preset threshold or meets the convergence standard, and the multi-functional marine ranching auxiliary ship arrangement scheme of the current marine ranching operation demand is generated according to the non-dominated solution set of the final external population.
[0032] It should be noted that first, the operation demand is extracted from the actual marine ranching scene of the current marine ranching, such as fry transportation frequency, feed feeding scale, water quality monitoring accuracy and operation sea area environmental conditions (such as wave height, flow rate), and these demands are converted into optimization targets of three dimensions of function completeness (device configuration integrity), navigation performance (stability, speed) and cost economy (construction cost, operation cost). Combined with the coupling correlation rule base constructed in the early stage, the demand characteristics are mapped to the three-dimensional target space: the function completeness is determined by the device type and quantity, the navigation performance is quantified by the stability-layout correlation rule in the historical rule base, and the cost economy is calculated by the material cost, device value and energy consumption index, forming a multi-objective optimization problem with the direction of "maximizing function, performance and minimizing cost". On the basis of the definition of target space, a multi-objective particle swarm optimization algorithm (MOPSO) is introduced, and a target function and a constraint system are constructed. The function completeness target function can be designed as the weighted sum of device configuration coverage (actual configuration device number / demand device number), the navigation performance target function is based on the performance prediction model (such as roll amplitude calculation, speed-power curve) in the coupling rule base, and the cost economy target function integrates material consumption unit price, device procurement cost and energy consumption cost. At the same time, according to the operation demand, hard constraints are set, such as the minimum deck area needs to meet the device installation demand, the maximum construction cost cannot exceed the budget threshold, or the stability height must meet the lower limit of the specification. For the candidate scheme that violates the constraint, a penalty term is introduced in the fitness calculation through the penalty function method, for example, if the stability height of a scheme is lower than the safety value, the target function value will be significantly enlarged, so that such infeasible solution is naturally eliminated in the iteration process.
[0033] It should be noted that the initial population is randomly generated in the three-dimensional target space, each particle represents a ship arrangement scheme, and the encoding parameters include cabin layout topology, equipment selection list, material type and quantity, etc. The fitness value of each particle is calculated by the objective function, and the fitness of the illegal scheme is modified by the penalty function. The high-quality individuals in the initial population are selected as the initial optimal population. Then, the non-dominated solution screening is performed on the population using the Pareto dominance relationship, and the schemes that are not fully superior to other solutions are stored in the external population (i.e. the Pareto front candidate set). In the particle updating process, the high diversity solutions in the external population (selected by the crowding distance or reference point method) and the initial optimal individuals are used as guide solutions to drive the particle swarm to move to the better region in the target space. In the iteration process, the particle swarm continuously updates the position and velocity, and the dynamic optimal solution set distribution is maintained through fitness calculation, non-dominated solution screening and external population maintenance. When the maximum number of iterations is reached or the hyper volume change rate of the external population is lower than the convergence threshold, the algorithm terminates and outputs the non-dominated solution set of the final external population. These solution sets form a Pareto front curve in the three-dimensional target space, which intuitively shows the trade-off relationship between function, performance and cost. The final arrangement scheme defines the function configuration (such as the number of bait machines, sensor types), construction parameters (such as cabin layout topology, material specifications) and performance indicators (such as roll amplitude, speed range) of the ship in detail, and verifies its technical feasibility and economic rationality through the coupling rule base. Through the multi-objective collaborative optimization of MOPSO, the complex design decision is transformed into a data-driven intelligent search process, which significantly improves the scheme generation efficiency and decision-making scientificity, and provides an efficient tool for customized design of marine ranching auxiliary ships.
[0034] Further, the objective function is established according to the three-dimensional target of maximum functional completeness, optimal navigation performance and economic cost, and the constraint conditions and penalty function are generated according to the current marine ranching operation demand, which is specifically expressed as follows: , Among them, the maximum functional completeness is: , It should be noted that is the decision variable vector, such as ship type parameters, equipment configuration, etc. is the kth feature of the breeding operation demand, such as feed transportation capacity, net cage maintenance frequency, etc. is the kth feature of the breeding auxiliary ship, such as carrying capacity, number of mechanical arms, etc. is the membership function, which is obtained based on the matching degree calculation of the historical association rule database.
[0035] Among them, the optimal navigation performance is: , It should be noted that V is the speed of the ship; Stability, such as the standard deviation of the roll angle, needs to be minimized, which can be converted to negative value maximization; Endurance needs to be maximized; W is the weight coefficient, and the sum of the addition is equal to 1.
[0036] Among them, the cost economy is: , It should be noted that, The construction cost is C.
[0037] Among them, the penalty function is: , It should be noted that, The constraint condition number is determined by the number of set constraint conditions; The first constraint function is The penalty coefficient of the first constraint is The second constraint function is The penalty coefficient of the second constraint is
[0038] It is worth mentioning that the setting of the constraint condition can be set from the physical constraint, the operation demand constraint and the environmental constraint, that is, the constraint threshold is set, for example, the ship length and the ship width of the physical constraint, the feed transportation capacity of the operation demand constraint, and the expected draft depth less than the pasture water depth of the environmental constraint.
[0039] Figure 3 A multifunctional auxiliary ship space arrangement system based on industrial demand provided by an embodiment of the application 3, the system comprises: a memory 31, a processor 32, the memory 31 contains a multifunctional auxiliary ship space arrangement method based on industrial demand program, the multifunctional auxiliary ship space arrangement method based on industrial demand program is executed by the processor 32, the following steps are realized: Obtain historical usage instances of different function type aquaculture auxiliary ships, analyze the correlation between the characteristics of the marine aquaculture pasture, the aquaculture operation demand and the functional characteristics of the aquaculture auxiliary ship, and construct a first aquaculture auxiliary ship rule base; Extract the ship structure characteristics and historical ship navigation characteristics of each single function type aquaculture auxiliary ship through the historical usage instances, judge the correlation between the ship space and the ship performance, and construct a second aquaculture auxiliary ship rule base; Analyze the economic characteristics of each single function aquaculture auxiliary ship, and correlate the first aquaculture auxiliary ship rule base and the second aquaculture auxiliary ship rule base, and construct a coupled correlation rule base; The current marine ranching operation demand is acquired, a multi-objective particle swarm optimization algorithm is used for arrangement scheme analysis in combination with the constructed coupling correlation rule library, and an arrangement scheme is generated and recommended.
[0040] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The above described device embodiments are merely schematic, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling, or direct coupling, or communication connection between the components can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.
[0041] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units; they can be located in one place, or distributed on multiple network units; and part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.
[0042] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; and the integrated unit can be implemented in the form of hardware or hardware plus software functional unit.
[0043] Those skilled in the art can understand that all or part of the steps of the above method embodiments can be completed by program instruction related hardware, and the foregoing program can be stored in a computer readable storage medium, and the program is executed to perform the steps of the above method embodiments; and the foregoing storage medium includes mobile storage equipment, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and various storage medium capable of storing program codes.
[0044] Alternatively, the above-mentioned integrated unit of the present application, if realized in the form of a software function module and sold or used as an independent product, can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product in essence or in the form of a part of the prior art that contributes to the present application. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the method described in the embodiments of the present application. The aforementioned storage medium includes mobile storage devices, ROM, RAM, magnetic discs or optical discs, and various media that can store program codes.
[0045] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
Claims
1. A method for spatial arrangement of a multifunctional auxiliary vessel based on industry needs, characterized in that, include: Obtain historical usage examples of aquaculture auxiliary vessels of different single-function types, analyze the correlation between marine aquaculture ranch characteristics, aquaculture operation requirements and aquaculture auxiliary vessel functional characteristics, and construct the first aquaculture auxiliary vessel rule base; By extracting the ship structure features and historical ship navigation features of each single-function type of aquaculture auxiliary vessel from historical usage examples, the correlation between ship space and ship performance is determined, and a second aquaculture auxiliary vessel rule base is constructed. Analyze the economic characteristics of each single-function aquaculture auxiliary vessel, and associate the association rules in the first aquaculture auxiliary vessel rule base and the second aquaculture auxiliary vessel rule base to construct a coupled association rule base; The system obtains the current aquaculture operation requirements of marine ranching, and uses a multi-objective particle swarm optimization algorithm to analyze the layout schemes based on the constructed coupled association rule base, generating layout schemes for recommendation.
2. The spatial arrangement method for a multi-functional auxiliary vessel based on industry needs according to claim 1, characterized in that, The analysis establishes a correlation between the characteristics of marine aquaculture ranches, aquaculture operation requirements, and the functional characteristics of aquaculture support vessels, and constructs a first aquaculture support vessel rule base, specifically including: Based on data retrieval, historical usage examples of aquaculture auxiliary vessels of different single-function types are obtained. Feature extraction is performed to obtain the functional characteristics of aquaculture auxiliary vessels, aquaculture operation requirements, and historical aquaculture ranch characteristics, thereby obtaining the feature information of historical usage examples. Based on the historical usage instance feature information, aquaculture operation demand features are extracted, aquaculture demand tags are generated based on aquaculture feature requirements, and the corresponding aquaculture auxiliary vessel function features are associated to obtain the first association information; A membership function is preset, and the membership value between the aquaculture operation requirements and the functional characteristics of the aquaculture auxiliary vessel is calculated through the membership function. The historical usage instance dataset is generated by combining the first association information. The Apriority algorithm is introduced to mine frequent itemsets based on the historical usage instance dataset. Several frequent item subsets are obtained through layer-by-layer search, and several association rules between aquaculture demand and aquaculture auxiliary vessel functional characteristics are generated using each frequent item subset. A confidence threshold is preset, the confidence of the association rules corresponding to each aquaculture demand event is calculated, and the confidence is compared with the confidence threshold. Association rules with a confidence threshold greater than the preset confidence threshold are defined as valid association rules. Association rules are then filtered to generate an association rule dataset.
3. The spatial arrangement method for a multi-functional auxiliary vessel based on industry needs according to claim 1, characterized in that, The analysis of the correlation between the characteristics of marine aquaculture ranches, aquaculture operation requirements, and the functional characteristics of aquaculture support vessels, and the construction of the first aquaculture support vessel rule base, also includes: Obtain historical usage instance feature information, and extract historical marine aquaculture ranch features for each historical usage instance through the historical usage instance feature information, including aquaculture area, aquaculture water body, aquaculture type and ranch voyage, to obtain historical marine aquaculture ranch feature information; The functional features of the aquaculture auxiliary vessel are extracted from the historical usage instance feature information. A decision tree algorithm is introduced, with the marine aquaculture ranch features as decision attributes and the functional features of the aquaculture auxiliary vessel as target attributes, and the root node is initialized. Obtain the root node after initialization, classify and obtain several root node branches using the characteristics of different marine aquaculture ranches, and construct the hierarchical structure of the decision tree. Define the judgment criteria for the best split node with information gain to construct the decision tree, and generate the first topology diagram through the constructed decision tree. Obtain the association rule dataset, extract the association rules between the functional features of the aquaculture auxiliary vessel and the aquaculture operation requirements based on the association rule dataset, define the functional features of the aquaculture auxiliary vessel as the target attribute and the aquaculture operation requirements as the decision attribute, and construct the second topology graph. Using the functional feature nodes of aquaculture auxiliary vessels as connection nodes, and utilizing the first and second topology diagrams, association rules are constructed with the characteristics of marine aquaculture ranches, aquaculture operation requirements, and functional features of aquaculture auxiliary vessels as paths, thereby generating the first aquaculture auxiliary vessel rule base.
4. The spatial arrangement method for a multi-functional auxiliary vessel based on industry needs according to claim 1, characterized in that, The process involves extracting the structural features and historical navigation characteristics of aquaculture auxiliary vessels of various functional types from historical usage examples, determining the correlation between vessel space and vessel performance, and constructing a second aquaculture auxiliary vessel rule base. Specifically, this includes: Historical usage examples of aquaculture auxiliary vessels of different single-function types are obtained. The ship structure characteristics and historical ship navigation characteristics of each functional type of aquaculture auxiliary vessel are extracted from the historical usage examples to obtain aquaculture auxiliary vessel characteristic information. Based on the aquaculture auxiliary vessel's characteristic information, ship structural features are extracted. The finite three-dimensional space and finite deck space are calculated using the ship structural features. The internal regions of the ship are then divided by regional functional types based on the ship structural features to obtain the first analysis information. Based on the first analysis information, the topological relationship of the cabin is modeled using graph theory. Each cabin is defined as a single node, and the functional characteristics of the cabin node and the distance characteristics of the neighboring nodes are used as the basis for merging nodes to establish the cabin topological structure diagram. Historical vessel navigation features are extracted using the aforementioned aquaculture auxiliary vessel feature information. Based on these historical vessel navigation features, wave spectra of the historical navigation sea areas for various types of aquaculture auxiliary vessels are generated, and wave height features and peak period features are extracted. By constructing the roll motion equation using linear potential flow theory based on historical ship navigation characteristics, the roll response amplitude of various aquaculture auxiliary vessels during historical navigation is analyzed. Combined with the extracted wave height characteristics and spectral peak period characteristics as ship performance characteristics, the second analysis information is obtained. Based on the cabin topology diagram, several adjacency matrices are obtained to represent the spatial topological connection relationships of various aquaculture auxiliary vessels. The second analysis information is then associated to construct association rules with space-performance as the path, generating a second aquaculture auxiliary vessel rule base.
5. The spatial arrangement method for a multi-functional auxiliary vessel based on industry needs according to claim 1, characterized in that, The analysis of the economic characteristics of each single-function aquaculture auxiliary vessel, and the association rules in the first and second aquaculture auxiliary vessel rule bases, are used to construct a coupled association rule base, specifically including: Obtain the first and second aquaculture auxiliary vessel rule bases, and extract the functional and structural features of the aquaculture auxiliary vessels from the first and second aquaculture auxiliary vessel rule bases. Based on the functional characteristics of aquaculture auxiliary vessels, data retrieval methods are used to obtain the types and values of functional equipment corresponding to each aquaculture auxiliary vessel's functions. By using the structural characteristics of aquaculture auxiliary vessels, the types and scales of structural materials for various aquaculture auxiliary vessels are obtained, generating secondary analysis information. The association rules in the first and second aquaculture auxiliary vessel rule bases are coupled, and the second analysis information is used as an auxiliary feature to generate coupled association rules with aquaculture farm characteristics, aquaculture operation requirements, aquaculture auxiliary vessel functions, and aquaculture auxiliary vessel performance as paths, thus obtaining a coupled association rule base.
6. The spatial arrangement method for a multi-functional auxiliary vessel based on industry needs according to claim 1, characterized in that, The process of obtaining current marine ranching operation requirements, combining the constructed coupled association rule base, and using a multi-objective particle swarm optimization algorithm to analyze layout schemes and generate recommended layout schemes specifically includes: The current marine ranching operation requirements are obtained, and three dimensions of objectives are defined: functional completeness, navigation performance, and cost economy. A three-dimensional target space is constructed by combining the coupled association rule database. A multi-objective particle swarm optimization algorithm is introduced to analyze the layout scheme. An objective function is established based on three dimensions: functional completeness, navigation performance, and cost economy. Constraints and penalty functions are generated based on the current marine ranching operation requirements. The initial population is obtained by initializing the population using the constructed three-dimensional target space. The fitness value of each individual in the initial population is calculated based on the objective function. If the constraints are violated, the fitness is corrected through the penalty function to obtain the initial optimal population individuals. Based on the calculated fitness value, the initial population is screened for non-dominated solutions to obtain non-dominated solutions. An external population is generated based on the obtained non-dominated solutions. Based on the external population, a guiding solution is selected and combined with the initial optimal population individuals to perform particle update operations. The updated population is subjected to repeated iterative analysis. When the number of iterations reaches a preset threshold or meets the convergence criteria, the non-dominated solution set of the final external population is output. Based on the non-dominated solution set of the final external population, a multi-functional aquaculture auxiliary vessel layout scheme is generated to meet the current marine ranching operation requirements.
7. A multifunctional auxiliary vessel space arrangement system based on industry needs, characterized in that, The system includes: a memory and a processor. The memory contains a program for a multi-functional auxiliary vessel space arrangement method based on industry needs. When the processor executes the program for the multi-functional auxiliary vessel space arrangement method based on industry needs, it performs the following steps: Obtain historical usage examples of aquaculture auxiliary vessels of different single-function types, analyze the correlation between marine aquaculture ranch characteristics, aquaculture operation requirements and aquaculture auxiliary vessel functional characteristics, and construct the first aquaculture auxiliary vessel rule base; By extracting the ship structure features and historical ship navigation features of each single-function type of aquaculture auxiliary vessel from historical usage examples, the correlation between ship space and ship performance is determined, and a second aquaculture auxiliary vessel rule base is constructed. Analyze the economic characteristics of each single-function aquaculture auxiliary vessel, and associate the association rules in the first aquaculture auxiliary vessel rule base and the second aquaculture auxiliary vessel rule base to construct a coupled association rule base; The system obtains the current aquaculture operation requirements of marine ranching, and uses a multi-objective particle swarm optimization algorithm to analyze the layout schemes based on the constructed coupled association rule base, generating layout schemes for recommendation.
