CN110046460B - Amphibious vehicle layout optimization method based on adaptive elite genetic algorithm - Google Patents
Amphibious vehicle layout optimization method based on adaptive elite genetic algorithm Download PDFInfo
- Publication number
- CN110046460B CN110046460B CN201910347970.1A CN201910347970A CN110046460B CN 110046460 B CN110046460 B CN 110046460B CN 201910347970 A CN201910347970 A CN 201910347970A CN 110046460 B CN110046460 B CN 110046460B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- arrangement
- individuals
- fitness
- elite
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 74
- 230000002068 genetic effect Effects 0.000 title claims abstract description 49
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000005457 optimization Methods 0.000 title claims description 21
- 230000035772 mutation Effects 0.000 claims abstract description 5
- 238000012248 genetic selection Methods 0.000 claims abstract description 4
- 210000000349 chromosome Anatomy 0.000 claims description 20
- 108090000623 proteins and genes Proteins 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000010187 selection method Methods 0.000 claims description 3
- 238000002922 simulated annealing Methods 0.000 description 11
- 230000008859 change Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 230000015556 catabolic process Effects 0.000 description 3
- 238000006731 degradation reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000010353 genetic engineering Methods 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 108091026890 Coding region Proteins 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007850 degeneration Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000010985 leather Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/30—Circuit design
- G06F30/39—Circuit design at the physical level
- G06F30/392—Floor-planning or layout, e.g. partitioning or placement
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Architecture (AREA)
- Feedback Control In General (AREA)
- Electrical Control Of Air Or Fuel Supplied To Internal-Combustion Engine (AREA)
Abstract
本发明涉及一种基于自适应精英遗传算法的两栖车辆布列优化方法。本发明包括：获取两栖车辆及布列空间尺寸；明确两栖车辆布列约束条件；确定两栖车辆布列目标函数；设定自适应精英遗传算法初始参数；随机产生第一代两栖车辆布列种群编码；解算当代个体适应度，保存最优个体作为精英个体；判断是否达到最大迭代次数或平均适应度达到预期值；所有个体与最差个体适应度的差作为所有个体新适应度；进行遗传选择、交叉和变异，产生新一代种群；精英个体替换新一代种群最差个体；对最后一代种群中的最优个体进行解码，得到车辆布列的最优顺序；利用最低水平线定位算法确定两栖车辆布列位置。
The invention relates to a method for optimizing the arrangement of amphibious vehicles based on an adaptive elite genetic algorithm. The invention includes: acquiring the amphibious vehicles and the space size of the arrangement; clarifying the constraints of the arrangement of the amphibious vehicles; determining the objective function of the arrangement of the amphibious vehicles; setting the initial parameters of the adaptive elite genetic algorithm; ; Calculate the fitness of contemporary individuals and save the best individual as an elite individual; judge whether the maximum number of iterations or the average fitness has reached the expected value; the difference between the fitness of all individuals and the worst individual is used as the new fitness of all individuals; genetic selection is performed , crossover and mutation to generate a new generation of populations; elite individuals replace the worst individuals of the new generation of populations; decode the optimal individuals in the last generation of populations to obtain the optimal order of vehicle layout; use the lowest horizontal line positioning algorithm to determine the layout of amphibious vehicles column position.
Description
(I) technical field
The invention relates to an amphibious vehicle layout optimization method based on a self-adaptive elite genetic algorithm.
(II) background of the invention
The amphibious battle is to throw own army and air force to the enemy coast or the designated beach through a surface naval vessel. In a non-combat loading mode, when the 'wasp-level' amphibious attacking ship executes tasks, the loading target is to maximize the utilization rate of the deck area of the vehicle cabin.
The essence of the vehicle layout problem of the amphibious attacking vessel is rectangular two-dimensional layout, and belongs to one of combination optimization problems. The arrangement aims to solve the optimal arrangement in a finite space, and an intelligent algorithm is generally used for solving an approximate optimal solution. Along with the development of the optimization algorithm, the speed, the precision and other performances of the algorithm are greatly improved. Applying new optimization algorithms to two-dimensional layout problems is a hot spot in research today. And C, Alves provides a variable-field-based search algorithm, and the optimal layout problem of irregular seat parts in the unprocessed leather is solved.
However, the conventional genetic algorithm has a long resolving time and a slow convergence rate, and may cause degradation. The genetic algorithm selects the current individuals according to the fitness, the difference value of the individual fitness in the current generation population is small along with the increase of the iteration times of the algorithm, more excellent individuals cannot occupy great advantages in the selection process, and finally the excellent degree of the solution is low. Therefore, the invention aims to provide an amphibious vehicle layout optimization method based on a self-adaptive elite genetic algorithm.
Disclosure of the invention
The invention aims to provide an amphibious vehicle layout optimization method based on a self-adaptive elite genetic algorithm.
The purpose of the invention is realized as follows:
(1) acquiring the size of the amphibious vehicle and the layout space;
(2) defining layout constraint conditions of the amphibious vehicle;
(3) determining a layout objective function of the amphibious vehicle;
(4) setting initial parameters of the adaptive elite genetic algorithm;
(5) randomly generating a first-generation amphibious vehicle arrangement population code;
(6) resolving the fitness of the current individual, and storing the optimal individual as an elite individual;
(7) judging whether the maximum iteration number is reached or the average fitness reaches an expected value, if so, turning to the step (11), otherwise, turning to the step (8);
(8) the difference between all the individuals and the worst individual fitness is used as the new fitness of all the individuals;
(9) genetic selection, crossing and variation are carried out to generate a new generation of population;
(10) replacing the worst individuals of the new generation of population with elite individuals, and turning to the step (6);
(11) decoding the optimal individuals in the population of the last generation to obtain the optimal sequence of vehicle arrangement;
(12) determining the arrangement position of the amphibious vehicle by using a lowest horizontal line positioning algorithm;
(13) and finishing the arrangement of the amphibious vehicle.
The invention has the advantages that: first, the conventional genetic algorithm has a long calculation time and a slow convergence rate, and may cause degeneration in an iterative process, i.e., the average fitness of children is lower than that of parents. The introduction of the elite strategy by the adaptive elite genetic algorithm improves the above problems. For a population of size n, the best shown individuals (elite individuals) were kept prior to the selection procedure. After each genetic manipulation is completed, the worst individual is replaced with the current elite individual. Ensures that the best individuals in each generation directly enter the next generation and are not affected by genetic manipulation. The elite strategy can accelerate the convergence speed of the genetic algorithm and weaken the population degradation phenomenon in the iterative process. Secondly, in the traditional genetic algorithm, excellent individuals are selected according to the fitness, and with the increase of the number of iterations, the individual fitness difference is small, so that the advantages of the excellent individuals are reduced, and finally the excellent degree of the solution is reduced. In order to solve the above problem, before the selection operation, the original fitness is replaced by the difference value between the fitness of all individuals and the minimum fitness. For each generation of population, the basis of selection operation is the current new environment, and the situation that the competitive power of excellent individuals is weakened after multiple iterations is effectively avoided. The traditional adaptive genetic algorithm is to change the cross probability and the variation, so that the algorithm is more adaptive to the current living environment. The adaptive strategy is to adaptively change the probability of each individual being selected, namely, adjust the living environment to be more suitable for the survival of excellent individuals, thereby improving the competitiveness of the excellent individuals. Compared with the traditional adaptive genetic algorithm, the provided adaptive genetic algorithm has simple operation process, does not need to solve complex functions, and can obviously reduce the calculated amount, thereby improving the calculation efficiency of the algorithm. The invention verifies the effectiveness of the adaptive elite genetic arrangement optimization algorithm through simulation experiments.
(IV) description of the drawings
FIG. 1 is a flow chart of an amphibious vehicle arrangement optimization method based on a self-adaptive elite genetic algorithm;
FIG. 2 is a layout diagram of an amphibious vehicle based on a conventional genetic algorithm;
FIG. 3 is a layout diagram of an amphibious vehicle based on a simulated annealing algorithm;
FIG. 4 is a layout diagram of an amphibious vehicle based on an adaptive elite genetic algorithm;
FIG. 5 is a fitness variation curve based on a conventional genetic algorithm;
FIG. 6 is a fitness variation curve based on a simulated annealing algorithm;
fig. 7 is a fitness variation curve based on the adaptive elite genetic algorithm.
(V) detailed description of the preferred embodiments
The invention is described in detail below with reference to the attached drawing figures:
as shown in FIG. 1, the invention discloses an amphibious vehicle layout optimization method based on a self-adaptive elite genetic algorithm. The implementation of the invention comprises the following steps:
(1) acquiring the size of the amphibious vehicle and the layout space;
the size of the related amphibious vehicle and the layout space is as follows: the rectangular arrangement space of the vehicle cabin is P, the length is L, the width is W, and n vehicles { P }existiI 1.. n }, and the length and width are liAnd wiIn the plan view of the vehicle cabin deck, the lower left corner is defined as the origin O (0,0), the upper left corner is defined as (0, L), the lower right corner is defined as (W, 0), and the rectangular vehicle PiThe top left corner vertex of (x)i1,yi1) Then P isiThe coordinate of the lower right corner is
(2) Defining layout constraint conditions of the amphibious vehicle;
the constraints involved are: two vehicles PiAnd Pj(i ≠ j) does not overlap, vehicles cannot be placed outside the arrangement space, and the height and the width of the vehicles are larger than 0, and each vehicleThere will be a maximum number limit, numrIs the number of r-th kind of vehicles arranged, NrIs the maximum number of the r-th vehicle, the constraint is as follows:
(3) determining a layout objective function of the amphibious vehicle;
the objective function involved is that the vehicle cabin deck is least unused, i.e. the sum of the layout areas occupied by the vehicle is maximum, expressed as:
(4) setting initial parameters of the adaptive elite genetic algorithm;
the initial parameters involved were: the iteration times are 100 times, the population size is 100, the cross probability is 0.9, and the variation probability is 0.15;
(5) randomly generating a first-generation amphibious vehicle arrangement population code;
the population generation involved is: the initial population is generated by using individuals corresponding to chromosomes formed by random numbers to form the initial population, the amphibious vehicle arrangement problem can be converted into a vehicle parking sequence combination optimization problem, a decimal vehicle number is selected as a coding mode, for example, the coding sequence is {1,5,2, 6,3,4}, and the vehicle is represented to park according to the sequence of numbers 1,5,2,6,3, 4;
(6) resolving the fitness of the current individual, and storing the optimal individual as an elite individual;
the involved fitness is as follows: selecting the unused rate of the deck as a fitness function;
(7) judging whether the maximum iteration number is reached or the average fitness reaches an expected value, if so, turning to the step (11), otherwise, turning to the step (8);
(8) the difference between all the individuals and the worst individual fitness is used as the new fitness of all the individuals;
(9) genetic selection, crossing and variation are carried out to generate a new generation of population;
the related selection operation adopts a roulette selection method to select individuals from parents to perform genetic operation and enter the next generation, the number of amphibious vehicles is n, and the fitness of the ith vehicle is fiThen the probability P that this vehicle is selectediComprises the following steps:
the related interleaving operation adopts a sequential interleaving method to avoid the encoding repetition, and the interleaving process of two parents is assumed as follows:
first, randomly selecting a crossover on the first parent chromosome,
secondly, the same genes on the second parent chromosome as the first chromosome are removed, and the remaining genes are arranged according to the original sequence,
thirdly, splicing the rest part of the second father chromosome and the cross part of the first father chromosome into a son chromosome according to the original sequence,
finally, a second daughter chromosome was obtained in the same manner;
the mutation operations involved are: for random chromosomes, randomly selecting two different genes on the chromosome for exchange;
(10) replacing the worst individuals of the new generation of population with elite individuals, and turning to the step (6);
(11) decoding the optimal individuals in the population of the last generation to obtain the optimal sequence of vehicle arrangement;
(12) determining the arrangement position of the amphibious vehicle by using a lowest horizontal line positioning algorithm;
(13) and finishing the arrangement of the amphibious vehicle.
Take a wasp-level amphibious aggressor ship in the United states as an example. The deck arrangement space has a length of 100 meters and a width of 20 meters. The vehicles participating in the arrangement are of four types, namely A type, B type, C type and D type, and the expansion size after considering the distance between the vehicles is as follows: the A type has the length of 6.40m and the width of 2.50m, the B type has the length of 11.00m and the width of 3.00m, the C type has the length of 9.77m and the width of 3.66m, and the D type has the length of 5.00m and the width of 4.00 m. The maximum arrangement number of the four types of vehicles is set to be 80, and the vehicles are numbered in sequence, namely A is 1-80, B is 81-160, C is 161-240, and D is 241-320.
Comparing the simulation results of the traditional genetic algorithm, the simulated annealing algorithm and the self-adaptive elite genetic algorithm. Initial parameters of two genetic algorithms are set: the iteration times are 100 times, the population size is 100, the cross probability is 0.9, and the variation probability is 0.15. Setting initial parameters of a simulated annealing algorithm: the initial temperature is 2000 ℃, the end temperature is 1 ℃, the iteration times at each temperature are 1000 times, and the temperature reduction coefficient is 0.95.
Amphibious vehicle layouts of a traditional genetic algorithm, a simulated annealing algorithm and an adaptive elite genetic algorithm are shown in fig. 2-4, respectively. The three optimization algorithms all realize automatic arrangement of the amphibious vehicle to obtain respective optimal arrangement results. A long and narrow unused deck space appears in both the middle of fig. 2 and the right side of fig. 3. Fig. 4 does not show significant unused space.
The fitness curves of the conventional genetic algorithm, the simulated annealing algorithm and the adaptive elite genetic algorithm are shown in fig. 5-7. In fig. 5-7, the fitness curve of the conventional genetic algorithm starts to decline slowly after the 10 th generation, and the fitness does not change significantly after the 10 th generation. The simulated annealing algorithm gave a better solution at the 75 th generation outer loop. The adaptive elite genetic algorithm has unobvious adaptability change after the 20 th generation, and the adaptability is slowly reduced. Theoretically, the larger the number of iterations, the better the algorithm results, but the more computation is increased. Compared with the two genetic algorithms, the simulated annealing algorithm has the advantages of higher non-utilization rate of the deck, poorer arrangement result and longest calculation time. One of the disadvantages of the simulated annealing algorithm is that the initial parameter setting is complex, and the problem solving is influenced. The two genetic algorithms can obtain better optimization performance than the simulated annealing algorithm by setting initial parameters for the first time.
The deck utilization rates of the traditional genetic algorithm, the simulated annealing algorithm and the adaptive elite genetic algorithm are 95.90%, 95.28% and 97.44% respectively, the calculation time is 140.07s, 295.29s and 136.5s respectively, and the numbers of amphibious vehicles of the type A, the type B, the type C and the type D are (56,21,7,4), (61,18,9,1) and (15,18,20,20) respectively. The deck utilization rate of the adaptive elite genetic algorithm is improved by 1.61 percent compared with that of the traditional genetic algorithm and is improved by 2.27 percent compared with that of the simulated degradation algorithm. The optimization time of the adaptive elite genetic algorithm is the shortest compared with the other two optimization algorithms. The number of vehicles in the arrangement of the three algorithms is 88, 89 and 73, respectively. The number of listings for the adaptive elite genetic algorithm is minimal because the optimization goal is to minimize the unused deck rate, rather than maximizing the number of listings. The arrangement quantity of each vehicle of the self-adaptive elite genetic algorithm is relatively close, and the actual loading requirement can be met. The arrangement quantity distribution of other two optimization algorithms is uneven and mainly focuses on the A-type vehicle, and the two optimization results are not in accordance with the actual requirements.
In conclusion, the adaptive elite genetic algorithm adopts the elite strategy to store the optimal individual of each generation, and replaces the worst individual in the population after genetic operation, so that the optimal individual can not be damaged. Meanwhile, a self-adaptive selection strategy is adopted, and the adaptability of the population is changed along with the change of the environment by making a difference with the lowest adaptability in the population, so that the adaptability of the population is improved, individuals with smaller adaptability difference are distinguished in the selection process, and the excellent degree of the solution can be improved.
Claims (1)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910347970.1A CN110046460B (en) | 2019-04-28 | 2019-04-28 | Amphibious vehicle layout optimization method based on adaptive elite genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910347970.1A CN110046460B (en) | 2019-04-28 | 2019-04-28 | Amphibious vehicle layout optimization method based on adaptive elite genetic algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110046460A CN110046460A (en) | 2019-07-23 |
| CN110046460B true CN110046460B (en) | 2022-03-29 |
Family
ID=67279831
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910347970.1A Active CN110046460B (en) | 2019-04-28 | 2019-04-28 | Amphibious vehicle layout optimization method based on adaptive elite genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110046460B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111291969B (en) * | 2020-01-14 | 2023-04-25 | 东南大学 | Automobile reordering method based on genetic algorithm |
| CN111461402B (en) * | 2020-03-06 | 2024-03-26 | 上海汽车集团股份有限公司 | Logistics scheduling optimization method and device, computer-readable storage medium and terminal |
| CN111553532B (en) * | 2020-04-28 | 2022-12-09 | 闽江学院 | Method and system for optimizing urban express vehicle path |
| CN112418528B (en) * | 2020-11-24 | 2021-09-14 | 哈尔滨理工大学 | Amphibious vehicle layout area utilization maximization method based on multi-strategy dynamic adjustment |
| CN113222272B (en) * | 2021-05-26 | 2022-09-20 | 合肥工业大学 | Emergency material transportation and loading cooperative optimization method based on double-layer genetic coding |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9708065B2 (en) * | 2015-04-07 | 2017-07-18 | The Boeing Company | Crown cabin configuration for an aircraft |
| US10019902B2 (en) * | 2015-11-06 | 2018-07-10 | Continental Automotive Systems, Inc. | Enhanced sound generation for quiet vehicles with vehicle-to-vehicle communication capabilities |
-
2019
- 2019-04-28 CN CN201910347970.1A patent/CN110046460B/en active Active
Non-Patent Citations (6)
| Title |
|---|
| 《Automatic interior space arrangement of mid-sized superyachts using a constraint-based genetic algorithm》;Jong-Ho Nam 等;《Journal of Marine Science and Technology volume 》;20120525;第481-492页 * |
| 基于GA算法的舰载机甲板布列方法;王保乳等;《海军航空工程学院学报》;20130920;第28卷(第05期);第571-576页 * |
| 基于多目标遗传算法的飞行甲板参数化设计优化方法;王健 等;《中国舰船研究》;20130116;第8卷(第0期);第7-12页 * |
| 基于小生境遗传算法的两栖车辆车轮收放装置的优化;包振明等;《汽车实用技术》;20150926(第09期);第41-45页 * |
| 基于模拟退火算法的舰载机布列方法研究;卞大鹏 等;《应用科技》;20150727;第42卷(第4期);第20-24页 * |
| 基于遗传算法的船体主甲板外展程度寻优;黄胜等;《海军工程大学学报》;20090815;第21卷(第04期);第34-39页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110046460A (en) | 2019-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110046460B (en) | Amphibious vehicle layout optimization method based on adaptive elite genetic algorithm | |
| KR102217761B1 (en) | Method and apparatus for adapting parameters of neural network | |
| CN113158580B (en) | One-dimensional layout method of solid wood panels | |
| Deng et al. | A novel hybrid genetic algorithm for solving Sudoku puzzles | |
| CN110490326A (en) | A kind of differential evolution method and system of adaptive multi-Vari strategy | |
| CN108830292A (en) | Data classification model optimization method and classification method | |
| CN111242281A (en) | Weight optimization method for deep convolutional neural network | |
| CN114722482A (en) | Method for predicting deformation of plateau tunnel and plateau tunnel health detection system | |
| US6766497B2 (en) | Method and system for reproduction in a genetic optimization process | |
| CN113792492B (en) | Optimal design method of Highway array antenna based on immune genetic algorithm | |
| CN114493090B (en) | Industrial park comprehensive energy intelligent control method and device | |
| CN117313634A (en) | Chip design layout splitting method, system and storage medium | |
| CN117313973A (en) | Container terminal outlet box position distribution method based on hybrid genetic algorithm | |
| CN115829425A (en) | Virtual unit scheduling method and system based on grouping technology and improved CS algorithm | |
| CN117495041A (en) | Multi-target flexible job shop scheduling method based on mixed wolf algorithm | |
| CN113141272B (en) | Network security situation analysis method based on iteration optimization RBF neural network | |
| CN118863307A (en) | Flexible job shop scheduling method based on improved genetic algorithm of discrete Levy flight | |
| CN115906352A (en) | A Dimensional Adaptive Lamp Arrangement Method Based on Particle Swarm Optimization | |
| CN113282089A (en) | Global path planning method for mobile robot in high-temperature scene | |
| CN113741482A (en) | Multi-agent path planning method based on asynchronous genetic algorithm | |
| CN114444388A (en) | Weapon Target Allocation Optimization Method Based on Improved Biogeography | |
| CN115187409B (en) | Method, device, electronic device and storage medium for determining energy investment strategy | |
| CN114118000A (en) | PCB splicing and blanking method based on deep intelligent genetic optimization algorithm | |
| CN113780651A (en) | Two-dimensional irregular layout method based on improved hybrid BL strategy | |
| CN113219986A (en) | Robot global path planning method based on genetic algorithm and cubic spline interpolation |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240711 Address after: 230000 Woye Garden Commercial Building B-1017, 81 Ganquan Road, Shushan District, Hefei City, Anhui Province Patentee after: HEFEI JINGLONG ENVIRONMENTAL PROTECTION TECHNOLOGY Co.,Ltd. Country or region after: China Address before: 150080 No. 52, Xuefu Road, Nangang District, Heilongjiang, Harbin Patentee before: HARBIN University OF SCIENCE AND TECHNOLOGY Country or region before: China |
|
| TR01 | Transfer of patent right |