CN118095089B - Underwater vehicle magnetic stealth high-dimensional multi-objective optimization method based on cf-MODE algorithm - Google Patents
Underwater vehicle magnetic stealth high-dimensional multi-objective optimization method based on cf-MODE algorithm Download PDFInfo
- Publication number
- CN118095089B CN118095089B CN202410260202.3A CN202410260202A CN118095089B CN 118095089 B CN118095089 B CN 118095089B CN 202410260202 A CN202410260202 A CN 202410260202A CN 118095089 B CN118095089 B CN 118095089B
- Authority
- CN
- China
- Prior art keywords
- underwater vehicle
- solution
- individual
- algorithm
- magnetic field
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000005457 optimization Methods 0.000 title abstract description 17
- 238000004804 winding Methods 0.000 claims abstract description 6
- 238000001514 detection method Methods 0.000 claims abstract description 3
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000035772 mutation Effects 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000013178 mathematical model Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 239000002245 particle Substances 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000009826 distribution Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000006698 induction Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005358 geomagnetic field Effects 0.000 description 1
- 230000005389 magnetism Effects 0.000 description 1
- 230000005415 magnetization Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- Genetics & Genomics (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Automation & Control Theory (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computing Systems (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a cf-MODE algorithm-based underwater vehicle magnetic stealth high-dimensional multi-objective optimization method, which comprises the following steps: firstly, combining a method for evaluating an individual by using a cost function with a search strategy of differential evolution, wherein the cost function method can enable each demagnetizing current value to be evaluated mutually, so that a dominant solution and a non-dominant solution can be easily identified, the convergence and diversity contribution of each candidate solution in a solution set can be evaluated, and further, when the problem of high-dimensional multi-objective optimization is faced, the selection pressure in the process of keeping the dominant demagnetizing current value is smaller. The differential evolution method has strong convergence capacity, and the combination of the differential evolution method and the convergence capacity can realize an effective algorithm suitable for being applied to the high-dimensional multi-objective problem. Secondly, inputting target magnetic field data of the underwater vehicle and demagnetizing winding efficiency, and rapidly calculating by using a cf-MODE algorithm to obtain a group of optimized demagnetizing current solution. And selecting an optimal scheme from the solution set to execute according to the different magnetic detection forms.
Description
Technical Field
The invention belongs to the technical field of underwater vehicle degaussing optimization algorithms, and particularly relates to a method for estimating individual multi-target differential evolutionary algorithm by adopting a cost function and applying the method to magnetic stealth high-dimensional multi-target optimization design of an underwater vehicle.
Background
Under the influence of geomagnetic field magnetization and electronic and electrical equipment, various magnetic fields are generated by the underwater vehicle, and the underwater vehicle mainly comprises a fixed magnetic field, an induced magnetic field, an eddy magnetic field, a corrosion current magnetic field, a stray magnetic field and the like, and the underwater vehicle is a ship body magnetic field. The fixed magnetic field and the induction magnetic field account for 80% -90% of the ship magnetic field, and are main focuses of the ship ship magnetism stealth control at present, wherein the fixed magnetic field is restrained by adopting a measure of periodically demagnetizing the station for magnetic treatment, and the induction magnetic field is compensated by installing a demagnetizing system. The research on degaussing systems is very important in all countries, and the advanced underwater vehicles in the united states almost all adopt an internal degaussing technology, so that the DEGS-type carrier-based degaussing system is considered as the most advanced and effective degaussing system in the world. The Germany has the world first-class ship manufacturing technology, is very important to the magnetic stealth of the ship, and is mainly used as a novel degaussing system model DEG-COMP1. The new generation of naval vessel demagnetizing system of Russian naval is called as a KDS type system, and has better anti-interference capability and reliability.
The reasonable configuration of the demagnetizing current in the demagnetizing system is extremely critical, and the demagnetizing current is mainly calculated through a demagnetizing optimization algorithm. Most of the existing underwater vehicle degaussing optimization adopts a low-dimensional multi-objective optimization algorithm, so that optimization of certain objective functions is ignored, and the common high-dimensional optimization algorithm has high dependence on initial parameters and high calculation complexity.
Disclosure of Invention
The invention aims to provide an effective method for high-dimensional multi-objective degaussing optimization of an underwater vehicle so as to solve the problems.
The cost function evaluation method can efficiently evaluate the quality (i.e. convergence and distribution) of one solution, and is measured by mutual evaluation of other solutions in the current population, so that the method is very suitable for the high-dimensional multi-objective problem. The differential evolution search strategy has stronger global search capability and better robustness, and is suitable for processing various complex high-dimensional multi-objective optimization problems. In order to achieve the above purpose, the present invention provides the following technical solutions: a method for acquiring a Pareto solution set of an optimal underwater vehicle degaussing current value by adopting a differential evolution algorithm and based on a cost function evaluation multi-objective comprises the following steps:
1. The method for optimizing the magnetic stealth high-dimensional multi-target of the underwater vehicle based on the cf-MODE algorithm is characterized by adopting a differential evolution algorithm and evaluating a Pareto solution set for acquiring the demagnetizing current value of the underwater vehicle by multiple targets based on a cost function, and comprises the following steps:
(1) Preprocessing magnetic field data of the underwater vehicle, and respectively integrating the measured original magnetic field data of the underwater vehicle and efficiency data of the degaussing winding into a data matrix AndAnd initializing the population (i.e., degaussing the current solution set);
(2) The individual (namely, demagnetizing current solution) of the uncomputed area is obtained by adopting a variation function of a differential evolution algorithm, and the variation function has the following formula:
xi,g+1＝xr1,g+F×(xr3,g-xr2,g) (1)
Wherein x r1,g、xr2,g、xr3,g is different vectors in the population, x i,g+1 is the mutated individual, and F is the search step size;
(3) And (3) adopting a cross function of a differential evolution algorithm in the solution value obtained in the step (2), randomly selecting individuals from the father to cross to obtain offspring, wherein the formula of the cross function is as follows:
Wherein NP is population size; d is the dimension of each particle; c R is a crossover operator, typically between [0,1 ]; m is a random number between [1, D ] in order to ensure that the mutated intermediate individuals at least have one-dimensional participation in a crossing strategy, x ij is an initialized individual, x 'ij,g+1 is a g+1st generation of individuals after mutation operation, and x' ij,g+1 is a g+1st generation of intermediate individuals after mutation and crossing operation;
(4) The individual in the population is subjected to fitness assignment by using a cost function, the convergence and diversity of each individual are evaluated, whether the individual is reserved or not is determined, one solution is measured by using the cost function, the loss of the candidate solution in the candidate solution set, which is evaluated relative to other individuals, is evaluated, the individuals are mutually evaluated, the dominant individual is reserved, and the specific calculation process is as follows:
if the de-centralized individuals x i and x j are taken out, set For the objective function vector of the individual x i, the solution x j obtained from x i is defined as:
in the candidate solution set X, the mutual evaluation among all individuals is calculated as:
wherein N * is the number of solutions in the candidate solution set X;
(5) Calculating a target dimension function value: after the decision variable parameters of the population demagnetizing current solution values are obtained, the objective function values of all individuals in the current population are obtained through calculation, and the calculation functions are as follows:
wherein f PM Upper part ,fPM Lower part(s) ,fRMS Upper part and f RMS Lower part(s) are respectively the peak value and the root mean square value of the magnetic field above and below the underwater vehicle, AndThe magnetic fields are respectively the upper magnetic field and the lower magnetic field of the underwater vehicle,AndThe efficiency of demagnetizing windings on the upper side and the lower side of the underwater vehicle is respectively;
2. According to the magnetic stealth high-dimensional multi-target optimization method for the underwater vehicle based on the cf-MODE algorithm, the optimal demagnetizing current value Pareto solution set of the underwater vehicle is calculated, and the mathematical model of the optimized target function is as follows:
Wherein the method comprises the steps of The objective function vector, I is a degaussing current solution, and I min and I max are the upper and lower limits of the solution constraint condition respectively;
3. According to the magnetic stealth high-dimensional multi-target optimization method for the underwater vehicle based on the cf-MODE algorithm, the optimal demagnetizing current value Pareto solution set of the underwater vehicle is output, and the algorithm control terminal selects a proper solution from the optimal demagnetizing current value Pareto solution set according to different magnetic detection forms faced by the underwater vehicle for demagnetizing the underwater vehicle.
[ Advantages and positive effects of the invention ]
According to the invention, the differential evolution algorithm is introduced to perform optimization, and the differential evolution algorithm reserves global searching capability, real number coding, mutation operators, crossover operators and one-to-one selection operators, so that the method is simple to operate, has few parameters, has high-efficiency searching capability, and is more suitable for processing the high-dimensional multi-target problem.
The method for evaluating each demagnetizing current value by combining the cost function enables individuals in the solution set to evaluate each other and conduct fitness assignment, can calculate the convergence and diversity contribution of each demagnetizing current value in the solution set at the same time, has smaller selection pressure when facing high-dimensional problems, and further retains the dominant solution value.
Drawings
FIG. 1 is a flow chart of the cf-MODE algorithm of the present invention.
FIG. 2 is a schematic diagram of an underwater vehicle degaussing system, and ① is a process of generating corresponding degaussing current by an optimization algorithm terminal control degaussing current distribution box; ② The process is that a degaussing current distribution box transmits current to each degaussing winding to generate a compensating magnetic field to compensate magnetic anomalies of the underwater vehicle; ③ Is a process for realizing magnetic stealth of an underwater vehicle.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Referring to fig. 1, the algorithm flow of the present invention is described as follows:
s1: initializing: input parameters are set and population P 0 is initialized to let the number of evolution iterations = 0.
S2: mutation and crossover operations: searching for unsearched areas through mutation, and randomly selecting individuals from the father through crossover operation to cross to obtain offspring.
S3: calculating objective function values of each dimension: and calculating the function value of each dimension of the demagnetizing current value in the high-dimensional target.
S4: the cost function method estimates individuals: by using the method, individuals are mutually evaluated, and fitness assignment is carried out on the individuals.
S5: preserving dominant amperometric values: and sequencing the solution sets by using the individual fitness values, and reserving dominant current solution values for optimizing.
S6: termination rule judgment: judging whether a termination condition is reached or whether the current iteration number reaches the maximum iteration number G max, and stopping iteration if so.
S7: outputting an optimal solution set of demagnetizing current: and outputting the obtained Pareto solution set, and selecting a proper solution from the Pareto solution set by the algorithm control terminal according to different state potentials for demagnetizing the underwater vehicle.
Claims (2)
1. The method for optimizing the magnetic stealth high-dimensional multi-target of the underwater vehicle based on the cf-MODE algorithm is characterized by adopting a differential evolution algorithm and evaluating a Pareto solution set for acquiring the demagnetizing current value of the underwater vehicle by multiple targets based on a cost function, and comprises the following steps:
(1) Preprocessing magnetic field data of the underwater vehicle, and respectively integrating the measured original magnetic field data of the underwater vehicle and efficiency data of the degaussing winding into a data matrix AndInitializing a population, namely degaussing current solution sets;
(2) And obtaining an individual of the uncomputed area, namely a degaussing current solution by adopting a variation function of a differential evolution algorithm, wherein the variation function has the following formula:
xi,g+1＝xr1,g+F×(xr3,g-xr2,g) (1)
Wherein x r1,g、xr2,g、xr3,g is different vectors in the population, x i,g+1 is the mutated individual, and F is the search step size;
(3) And (3) adopting a cross function of a differential evolution algorithm in the solution value obtained in the step (2), randomly selecting individuals from the father to cross to obtain offspring, wherein the formula of the cross function is as follows:
Wherein NP is population size; d is the dimension of each particle; c R is a crossover operator, m is a random number between [0,1] and [1, D ] in order to ensure that a mutated intermediate subject has at least one-dimensional participation in a crossover strategy, x ij is an initialized subject, x 'ij,g+1 is a g+1st-generation subject after mutation operation, and x' ij,g+1 is a g+1st-generation intermediate subject after mutation and crossover operation;
(4) The individual in the population is subjected to fitness assignment by using a cost function, the convergence and diversity of each individual are evaluated, whether the individual is reserved or not is determined, one solution is measured by using the cost function, the loss obtained by evaluating the solution in the candidate solution set relative to other solutions is evaluated, the individuals are mutually evaluated, the dominant individual is reserved, and the specific calculation process is as follows:
if the de-centralized individuals x i and x j are taken out, set For the objective function vector of the individual x i, the solution x j obtained from x i is defined as:
in the candidate solution set X, the mutual evaluation among all individuals is calculated as:
wherein N * is the number of solutions in the candidate solution set X;
(5) Calculating objective function values of each dimension: after the decision variable parameters of the population demagnetizing current solution values are obtained, the objective function values of all individuals in the population are obtained through calculation, and the calculation functions are as follows:
wherein f PM Upper part ,fPM Lower part(s) ,fRMS Upper part and f RMS Lower part(s) are respectively the peak value and the root mean square value of the magnetic field above and below the underwater vehicle, AndThe magnetic fields are respectively the upper magnetic field and the lower magnetic field of the underwater vehicle,AndThe efficiency of demagnetizing windings on the upper side and the lower side of the underwater vehicle is respectively;
calculating a Pareto solution set of an optimal underwater vehicle demagnetizing current value, and optimizing a mathematical model of an objective function as follows:
Wherein the method comprises the steps of The objective function vector, I is the degaussing current solution, and I min and I max are the upper and lower limits of the solution constraint, respectively.
2. The method for optimizing the magnetic stealth and high-dimensional targets of the underwater vehicle based on the cf-MODE algorithm, which is disclosed in claim 1, comprises the steps of outputting an optimal underwater vehicle degaussing current value Pareto solution set, and selecting a proper solution from the solution set by an algorithm control terminal according to different magnetic detection forms faced by the underwater vehicle for degaussing the underwater vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410260202.3A CN118095089B (en) | 2024-03-07 | 2024-03-07 | Underwater vehicle magnetic stealth high-dimensional multi-objective optimization method based on cf-MODE algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410260202.3A CN118095089B (en) | 2024-03-07 | 2024-03-07 | Underwater vehicle magnetic stealth high-dimensional multi-objective optimization method based on cf-MODE algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118095089A CN118095089A (en) | 2024-05-28 |
| CN118095089B true CN118095089B (en) | 2024-08-06 |
Family
ID=91145230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410260202.3A Active CN118095089B (en) | 2024-03-07 | 2024-03-07 | Underwater vehicle magnetic stealth high-dimensional multi-objective optimization method based on cf-MODE algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118095089B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440377A (en) * | 2013-08-27 | 2013-12-11 | 北京航空航天大学 | Aircraft aerodynamic configuration optimum design method based on improved parallel DE algorithm |
| CN106130792A (en) * | 2016-08-22 | 2016-11-16 | 扬州华鼎电器有限公司 | Photovoltaic microgrid control system integral, flexible optimization method, Apparatus and system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016134258A1 (en) * | 2015-02-20 | 2016-08-25 | Ibis Biosciences, Inc. | SYSTEMS AND METHODS FOR IDENTIFICATION AND USE OF SMALL RNAs |
| CN110641475B (en) * | 2019-10-29 | 2020-10-16 | 重庆大学 | Hierarchical fault-tolerant control method for four-wheel independent drive electric vehicle based on cooperative game |
| CN112396132B (en) * | 2021-01-19 | 2022-04-08 | 国网江苏省电力有限公司南京供电分公司 | SVM-based wireless terminal secure access method |
| CN115238762A (en) * | 2022-06-06 | 2022-10-25 | 哈尔滨工业大学 | Satellite telemetry data feature selection method, device and medium based on multi-objective optimization algorithm |
| CN115983174A (en) * | 2022-12-30 | 2023-04-18 | 福州大学 | High-dimensional multi-target evolution method based on improved domination criterion |
| CN117371328A (en) * | 2023-10-27 | 2024-01-09 | 同济大学 | Multi-objective optimization method based on dominant relationship selection and distribution evaluation |
-
2024
- 2024-03-07 CN CN202410260202.3A patent/CN118095089B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440377A (en) * | 2013-08-27 | 2013-12-11 | 北京航空航天大学 | Aircraft aerodynamic configuration optimum design method based on improved parallel DE algorithm |
| CN106130792A (en) * | 2016-08-22 | 2016-11-16 | 扬州华鼎电器有限公司 | Photovoltaic microgrid control system integral, flexible optimization method, Apparatus and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118095089A (en) | 2024-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112269134B (en) | Battery SOC and SOH joint estimation method based on deep learning | |
| CN110609200B (en) | Power distribution network earth fault protection method based on fuzzy metric fusion criterion | |
| CN113904786B (en) | False data injection attack identification method based on line topology analysis and tide characteristics | |
| CN111082401B (en) | Self-learning mechanism-based power distribution network fault recovery method | |
| CN111159638A (en) | Power distribution network load missing data recovery method based on approximate low-rank matrix completion | |
| CN111582542B (en) | Power load prediction method and system based on anomaly repair | |
| CN113486078A (en) | Distributed power distribution network operation monitoring method and system | |
| CN110837915B (en) | Low-voltage load point prediction and probability prediction method for power system based on hybrid integrated deep learning | |
| CN106503846A (en) | Route calculation algorithm patrolled and examined by a kind of power equipment | |
| CN111797974A (en) | Power system state estimation method combining particle filtering and convolutional neural network | |
| CN116008714B (en) | Anti-electricity-stealing analysis method based on intelligent measurement terminal | |
| CN110766190A (en) | Power distribution network load prediction method | |
| CN114742123B (en) | Industrial control abnormality detection method for industrial control system with insufficient samples | |
| CN118095089B (en) | Underwater vehicle magnetic stealth high-dimensional multi-objective optimization method based on cf-MODE algorithm | |
| CN109346787A (en) | A kind of electric automobile power battery adaptive optimization charging method | |
| CN112215279A (en) | Power grid fault diagnosis method based on immune RBF neural network | |
| CN115345297A (en) | Platform area sample generation method and system based on generation countermeasure network | |
| CN117131341A (en) | Electric meter operation error estimation method, and out-of-tolerance electric meter judgment method and system | |
| CN114865673B (en) | Micro-grid load storage collaborative optimization method, device, equipment and storage medium | |
| CN113344410B (en) | Multi-dimensional evaluation method, system, terminal and storage medium for energy conservation transformation of power distribution network | |
| CN115619028A (en) | Clustering algorithm fusion-based power load accurate prediction method | |
| CN111027017A (en) | Comprehensive evaluation system for power distribution network management state | |
| CN114139810B (en) | Green flexible job shop scheduling method based on improved electromagnetic mechanism algorithm | |
| Wang et al. | A locating method of ev fast charging stations based on the conditional generative adversarial networks | |
| CN113221465B (en) | Photovoltaic power generation operation and maintenance oriented component model parameter identification method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |