CN-122021335-A - Marine emission guarantee equipment layout optimization method based on multi-objective genetic algorithm

CN122021335ACN 122021335 ACN122021335 ACN 122021335ACN-122021335-A

Abstract

The invention discloses a marine emission guarantee equipment layout optimization method based on a multi-objective genetic algorithm, which comprises the steps of S1, collecting multi-source data of a marine emission platform, a guarantee equipment and an emission task, processing four-dimensional associated data sets in real time for the collected data, S2, constructing a marine emission guarantee equipment layout optimization model, S3, carrying out iterative optimization on the marine emission guarantee equipment layout optimization model by adopting the multi-objective genetic algorithm to obtain an optimized parameter combination, S4, applying the optimized parameter combination to the marine emission guarantee equipment layout optimization model, outputting a pareto optimal solution set, S5, selecting an optimal layout scheme from the pareto solution set based on weight, outputting a coordinate table, a list and a map, S6, monitoring four-dimensional parameters in real time, triggering dynamic optimization based on a history solution set, and outputting a dynamic adjustment scheme, and realizing the overall improvement of the multi-objective and significant emission guarantee under complex constraint by combining the pareto optimal solution set and an analysis method.

Inventors

GONG QINGTAO
TENG YAO
ZHANG SHUNING
HE SHILONG
HU XIN
LI KANGQIANG
SHEN KECHANG
GUO YANLI
HAN YANQING

Assignees

鲁东大学

Dates

Publication Date: 20260512
Application Date: 20260210

Claims (7)

1. The marine launching guarantee equipment layout optimization method based on the multi-objective genetic algorithm is characterized by comprising the following steps of; S1, collecting multi-source data of an offshore launching platform, guaranteeing equipment and launching tasks, sequentially carrying out moving average filtering on the collected data to eliminate short-time noise of dynamic environment data, and adopting The rule eliminates abnormal values of equipment attribute data, processes abnormal data through linear normalization, and finally generates a four-dimensional associated data set based on Bayesian network fusion ; S2, constructing an offshore emission guarantee equipment layout optimization model, and relating the four-dimensional associated data set The offshore launching support equipment layout optimization model comprises a decision variable vector definition module, a constraint condition set setting module and a multi-objective optimization function construction module; S3, performing iterative optimization on an offshore emission guarantee equipment layout optimization model by adopting a multi-objective genetic algorithm, and encoding each population individual into a group of parameter combinations comprising equipment quantity proportion, a space coordinate threshold value and constraint weight coefficients to obtain optimized parameter combinations; s4, applying the optimized parameter combination to an offshore launching guarantee equipment layout optimization model, and using the optimized model to perform four-dimensional correlation data set Performing solution processing to output pareto optimal solution set ; S5, screening candidate equipment layout schemes with optimal comprehensive performance from the pareto optimal solution set by combining the target weight calculated by the analytic hierarchy process, and synchronously outputting an equipment coordinate configuration table, a quantity list and a four-dimensional balance visual map; And S6, monitoring the space attitude of the platform, dynamic environment parameters, equipment running and deployment states, task flow and priority four-dimensional parameters in real time, when the parameter variation of any dimension exceeds a preset threshold, rapidly initializing the population based on a historical pareto optimal solution set, injecting current real-time data to execute iterative optimization, and outputting an equipment layout dynamic adjustment scheme.
2. The marine launch assurance equipment layout optimization method based on the multi-objective genetic algorithm of claim 1, wherein the S1 specifically comprises: s11, acquiring functional partition boundary parameters of a platform through a sensor network deployed in a key area of an offshore launching platform Distribution matrix of bearing capacity And a set of dangerous area locations ; S12, collecting dynamic environment parameters including wind speed Sea wave height And air temperature Noise removal is performed through moving average filtering, and the specific formula is as follows: ; S13, collecting and guaranteeing equipment geometric dimension Weight of the container Cost of And is based on Detecting and eliminating abnormal values according to criteria; S14, collecting operation flow parameters of the emission task The method comprises the steps of task priority, a job time window and equipment cooperative relationship; S15, carrying out linear normalization processing on the multi-source heterogeneous data, wherein the specific formula is as follows: ; s16, constructing a four-dimensional association model based on a Bayesian network, and generating a four-dimensional association data set of platform-equipment-task-environment 。
3. The marine launch assurance equipment layout optimization method based on the multi-objective genetic algorithm of claim 1, wherein the S2 specifically comprises: S21, setting four-dimensional associated data set For input matrix , wherein, As a set of real numbers, Representing the number of samples to be taken, Representing a characteristic dimension of each sample; S22, constructing a decision variable vector definition module, and adopting a multi-dimensional coding structure comprising equipment quantity proportioning vectors Spatial coordinate threshold vector Constrained weight coefficient vector Wherein Indicating the number of types of equipment, Indicating the number of placement positions of the equipment, Representing the number of constraints, the decision variable vector being defined as ; S23, constructing a constraint condition set setting module, and defining a hard constraint set based on platform space constraint, equipment physical constraint, task safety constraint and environment dynamic constraint And soft constraint set Wherein the hard constraint comprises a platform boundary insurmountable condition and an inter-equipment minimum safe distance condition, the soft constraint comprises a cost upper limit condition and a task response time condition, and the constraint is relaxed by a factor Dynamically adjusting violation tolerance of soft constraints; s24, constructing a multi-objective optimization function construction module, and defining multi-objective function vectors Wherein: Representing the overall cost minimization goal, Representing a task response time minimization goal, Representing safety redundancy maximization targets and introducing target weight vectors ; S25, introducing an adaptive constraint coordination unit between the decision variable vector definition module and the constraint condition set setting module, monitoring constraint conflict conditions in real time, and dynamically adjusting constraint weight coefficient vectors according to platform space attitude change ; S26, integrating a pareto dominant relationship evaluation mechanism in a multi-objective optimization function construction module, generating an initial pareto solution set by calculating non-dominant ordering and crowding distance of the solution set, and providing a diversity maintaining strategy for a genetic algorithm; S27, defining a structural parameter set of an offshore launching support equipment layout optimization model, wherein the structural parameter set comprises a decision variable dimension Number of constraint conditions Number of objective functions Constraint relaxation factor And a target weight vector ; And S28, finishing structural initialization of the layout optimization model of the offshore launching guarantee equipment, and loading the current parameter configuration to perform model verification and pre-optimization.
4. The marine launch assurance equipment layout optimization method based on the multi-objective genetic algorithm of claim 1, wherein the S3 specifically comprises: s31, initializing population scale of multi-target genetic algorithm Setting the maximum iteration number Probability of crossover Probability of variation ; S32, representing each genetic individual by adopting a structure-parameter joint coding mode, and coding the genetic individual as The specific formula is as follows: Wherein, the Representing decision variable vectors , Representing corresponding combinations of algorithm parameters, including crossover probabilities Probability of variation Selecting a pressure factor Constraint relaxation factor ; S33, vector decision variables corresponding to each genetic individual Inputting an offshore emission guarantee equipment layout optimization model, and calculating multiple objective function vectors And evaluate the degree of constraint violation ; S34, defining an fitness evaluation function of the genetic individuals Combining multiple target performance indexes Degree of constraint violation And solution set distribution index The specific formula is as follows: Wherein, the For non-dominant ranking based on pareto dominant relationship, , , Are all weighting coefficients; S35, calculating the solution set distribution entropy of the current generation population The method is used for measuring the distribution uniformity of the pareto front edge, and the specific formula is as follows: Wherein: is the first The non-dominant solution set of the generation, To solve the problem of A crowding distance from adjacent solutions; S36, adopting a self-adaptive cross variation adjustment mechanism based on distribution entropy according to the following steps Dynamically adjusting crossover probabilities Probability of variation The specific formula is as follows: Wherein, the 、 As a reference probability of being a reference probability, 、 In order to adjust the coefficient of the power supply, Is a distributed entropy reference value; S37, performing tournament selection operation based on crowdedness sequencing on the population, and preferentially selecting individuals with high non-dominant grades and large crowdedness distances to enter a mating pool; S38, performing adaptive arithmetic crossover and Gaussian variation operation on individuals in the mating pool to generate a child population, and according to constraint relaxation factors Dynamically adjusting the variation amplitude; s39, merging parent and offspring population, executing rapid non-dominant sorting and congestion degree calculation, and selecting the parent and offspring population before Individuals constitute a new generation population; S310, judging whether an iteration termination condition is met or not, wherein the iteration termination condition comprises that the maximum iteration times or the pareto front convergence index is lower than a set threshold; S311, if the termination condition is not met, returning to the step S33; S312, if the termination condition is satisfied, outputting an optimal parameter combination set Wherein: In order to optimize the decision variable vector after the optimization, And combining the corresponding optimal algorithm parameters.
5. The marine launch assurance equipment layout optimization method based on the multi-objective genetic algorithm of claim 1, wherein the S4 specifically comprises: s41, combining the optimal parameters obtained in claim 4 Layout optimization model applied to offshore emission guarantee equipment, wherein In order to optimize the decision variable vector after the optimization, Combining the corresponding optimal algorithm parameters; S42, based on the optimized decision variable vector Deconstructing equipment quantity proportioning vector Spatial coordinate threshold vector Constrained weight coefficient vector Generating basic configuration parameters of equipment layout; S43, associating four dimensions with the data set Inputting the configured marine launching support equipment layout optimization model, executing multi-objective optimization solution, and outputting a pareto optimal solution set containing a plurality of non-dominant solutions Wherein each solution A possible equipment layout scheme is shown.
6. The marine launch assurance equipment layout optimization method based on the multi-objective genetic algorithm of claim 1, wherein the S5 specifically comprises: S51, constructing a target weight decision matrix by adopting an analytic hierarchy process, and determining the relative importance weight of each target function based on expert evaluation Wherein: in correspondence with the weight of the total cost, In response to the weight of the response time, Corresponding to the safety redundancy weight; S52, based on the target weight vector Computing pareto optimal solution sets Each solution of (1) Is a comprehensive evaluation value of (2) The specific formula is as follows: Wherein, the , And Are normalized objective function values; S53, selecting the solution with the highest comprehensive evaluation value As a candidate equipment layout scheme with optimal comprehensive performance, the specific formula is as follows: S54, based on optimal layout scheme Generating an equipment coordinate configuration table, an equipment quantity list and a four-dimensional balance visual map, wherein the equipment coordinate configuration table is used for defining specific position coordinates of each equipment in a platform space, and the equipment quantity list is used for listing the optimal configuration quantity of each type of equipment in detail.
7. The marine launch assurance equipment layout optimization method based on the multi-objective genetic algorithm of claim 1, wherein the S6 specifically comprises: S61, real-time monitoring of platform space attitude, dynamic environment parameters, equipment running and deployment states, task flows and priority four-dimensional parameters, and establishing a parameter variation evaluation mechanism; s62, setting dynamic thresholds of parameters of all dimensions, and triggering a dynamic optimization flow when the parameter variation of any dimension exceeds a preset threshold; S63, optimal solution set based on history pareto Quickly initializing a genetic algorithm population, injecting current real-time data and performing iterative optimization; S64, outputting a dynamic adjustment scheme of the equipment layout according to the dynamic optimization result.

Description

Marine emission guarantee equipment layout optimization method based on multi-objective genetic algorithm Technical Field The invention relates to the technical field of offshore space launching guarantee, intelligent optimization algorithm and equipment layout planning intersection, in particular to an offshore launching guarantee equipment layout optimization method based on a multi-objective genetic algorithm. Background Along with the normalized promotion of the offshore aerospace launching task, the layout rationality of the equipment is guaranteed to directly determine the safety, efficiency and economy of the launching task. The offshore launching scene has the characteristics of limited platform space, complex equipment types (high-risk fuel equipment, precise measurement and control equipment, emergency rescue equipment and the like are covered), high coupling degree of operation flow, dynamic environment interference (sea wave jolt, meteorological change) and the like, and strict requirements are put on equipment layout. The current mainstream offshore launching support equipment layout method is dependent on engineering experience or a single-target optimization model, and has the obvious defects that firstly, the traditional experience layout does not quantitatively consider multi-target constraint, response delay is easy to cause, cost is low, safety redundancy is too high, efficiency is insufficient and other contradictory scenes, secondly, the traditional single-target optimization method (taking response time minimization as a target) ignores cost controllability and operation safety, is difficult to adapt to complex constraint of offshore launching, and thirdly, a part of optimization algorithm (such as a single genetic algorithm and a particle swarm algorithm) does not design an adaptation mechanism aiming at multi-constraint characteristics of offshore layout, and the problems of convergence, partial optimum and insufficient solution diversity exist. Therefore, a marine emission guarantee equipment layout optimization method based on a multi-objective genetic algorithm is provided. Disclosure of Invention The invention aims to provide a marine launching guarantee equipment layout optimization method based on a multi-objective genetic algorithm so as to solve the problems in the background technology. In order to achieve the aim, the invention provides the technical scheme that the marine launching guarantee equipment layout optimization method based on the multi-objective genetic algorithm comprises the following steps of; s1, collecting multi-source data of an offshore launching platform, guaranteeing equipment and launching tasks, and eliminating short-time noise of dynamic environment data by moving average filtering the collected data in real time, Rule eliminating abnormal value of equipment attribute data, linear normalization of abnormal dimension data, generating four-dimensional association data set of platform-equipment-task-environment based on Bayesian network fusion; S2, constructing an offshore launching guarantee equipment layout optimization model, and relating the platform-equipment-task-environment four-dimensional related data setThe offshore launching support equipment layout optimization model comprises a decision variable vector definition module, a constraint condition set setting module and a multi-objective optimization function construction module; S3, performing iterative optimization on an offshore emission guarantee equipment layout optimization model by adopting a multi-objective genetic algorithm, and encoding each population individual into a group of parameter combinations comprising equipment quantity proportion, a space coordinate threshold value and constraint weight coefficients to obtain optimized parameter combinations; S4, applying the optimized parameter combination to an offshore launching guarantee equipment layout optimization model, and using the optimized model to perform four-dimensional association data set of platform-equipment-task-environment Performing solution processing to output pareto optimal solution set; S5, screening candidate equipment layout schemes with optimal comprehensive performance from the pareto optimal solution set by combining the target weight calculated by the analytic hierarchy process, and synchronously outputting an equipment coordinate configuration table, a quantity list and a four-dimensional balance visual map; And S6, monitoring the space attitude of the platform, dynamic environment parameters, equipment running and deployment states, task flow and priority four-dimensional parameters in real time, and when the parameter variation of any dimension exceeds a preset threshold, rapidly initializing the population based on a historical pareto optimal solution set and injecting current real-time data to execute iterative optimization so as to output an equipment layout dynamic adjustment scheme. Preferably, the S