请专业人士翻译论文摘要，超高分相送！

Posted 2023-02-15

因为是硕士论文的摘要，因此一定要求翻译专业，严禁机器自动翻译，否则不但不给分还举报扣分！一些翻译的基本原则比如多用被动句等一定要把握好，超高分相送！翻译的好额外加多多分数。

近些年来，人们对遗传算法(GA，Genetic Algorithm)的关注程度越来越大，对它的应用越来越广泛，但有关它收敛速度方面的理论研究还不是很多，本文在最优保存遗传算法的收敛速度方面做了理论分析，并在分析的基础上对传统的遗传算法进行了优化，它通过在进化的每一代中提高全局最优解出现的概率来提高算法的效率。此外遗传算法还存在早熟收敛的问题，本文介绍了一种解决早熟收敛的方法，在搜索最优解的过程中连续多次运行遗传算法来得到多个不同的局部最优解，然后再从这些被选解中求得全局最优解。本文还研究了应用遗传算法学习神经网络权值的问题，提出了一种优化的网络结构，使用多个单一输出的网络替换多输出的BP网络，该种网络结构更简单，更适合使用遗传算法优化。此外，可以证明这种优化的网络结构具有更优的最优解。
0-1规划是重要的整数线性规划模型之一，本文在将遗传算法应用于实际项目《航运船舶配载系统》中时，将选择可用船建立为0-1规划模型。在实际问题中可用船的数量多达上百艘，全枚举的方法在这里显然不适用。为此本文首先引入了分支限界法的思想，大大减少了问题的计算次数，在大多数情况下可以在很短时间内计算出问题的最优解。然后本文针对那些使用分支限界法无法在较短时间内计算出最优解的情况，提出了一种改进的遗传算法进行求解。其实使用目前所知的任何方法求解这些少部分情况都是困难的，使用遗传算法计算满意解是比较好的选择，实验结果也证明了本文方法的有效性。

近些年来，人们对遗传算法(GA，Genetic Algorithm)的关注程度越来越大，对它的应用越来越广泛，但有关它收敛速度方面的理论研究还不是很多，本文在最优保存遗传算法的收敛速度方面做了理论分析，并在分析的基础上对传统的遗传算法进行了优化，它通过在进化的每一代中提高全局最优解出现的概率来提高算法的效率。In recent years Genetic Algorithm is paid more and more attention, and its application is getting more and more extensive, however there is less theoretical research on its convergence speed. Consequently, the theoretical analysis for the convergence speed of Saving Best Result Genetic Algorithm is conducted in this paper, and on the basis of the analysis the traditional algorithm is optimized, which is to enhance the efficiency of the algorithm through enhancing the appearing probability of global optimal solution. 此外遗传算法还存在早熟收敛的问题，本文介绍了一种解决早熟收敛的方法，在搜索最优解的过程中连续多次运行遗传算法来得到多个不同的局部最优解，然后再从这些被选解中求得全局最优解。In addition there is still an issue of premature convergence for Genetic Algorithm, so a method for overcoming premature convergence is proposed. This method successively runs Genetic Algorithm to obtain multiple different local optimal solutions in the process of searching optimal solution, then obtains global optimal solution from these solutions to be chosen.本文还研究了应用遗传算法学习神经网络权值的问题，提出了一种优化的网络结构，使用多个单一输出的网络替换多输出的BP网络，该种网络结构更简单，更适合使用遗传算法优化。此外，可以证明这种优化的网络结构具有更优的最优解。In this paper the issue of using Genetic Algorithm to learn the weight of neural network is also studied, and an optimized network architecture is proposed, which uses a network with multiple single outputs to replace a BP network with multiple outputs, so that features simple in structure, and is more suitable to use Genetic Algorithm optimization. In addition, this optimized network architecture can be proved to have more superior optimal solution.
0-1规划是重要的整数线性规划模型之一，本文在将遗传算法应用于实际项目《航运船舶配载系统》中时，将选择可用船建立为0-1规划模型。0-1 programming is one of the most important integer linear programming. In the paper when Genetic Algorithm is adopted in a practical project of “Stowage System for Shipping Ships”, available ships will be chosen to establish 0-1 programming model. 在实际问题中可用船的数量多达上百艘，全枚举的方法在这里显然不适用。In practical problems the number of available ships may be up to hundred, so the method of all enumeration is obviously not suitable here. 为此本文首先引入了分支限界法的思想，大大减少了问题的计算次数，在大多数情况下可以在很短时间内计算出问题的最优解。Therefore the idea of embranchment delimitation is introduced first in the paper so that the times of calculation are reduced dramatically, and the optimal solution can be obtained in a very short time in most cases.然后本文针对那些使用分支限界法无法在较短时间内计算出最优解的情况，提出了一种改进的遗传算法进行求解。Then an improved Genetic Algorithm is proposed to solve the optimal solution against the situation that embranchment delimitation method can not obtain optimal solution in a shorter time. 其实使用目前所知的任何方法求解这些少部分情况都是困难的，使用遗传算法计算满意解是比较好的选择，实验结果也证明了本文方法的有效性。In fact it is difficult to solve such minority situations using any methods now known, and it is a better choice to use Genetic Algorithm obtaining a satisfactory solution. The experimental result has proved the effectiveness of the proposed method. 参考技术A People inherits algorithm (GA face to face during the past in recent year, Genetic Algorithm) attention degree is more and more big , the application to it is more and more broad , that theory about its convergence speed aspect studies is not many but , the main body of a book is analysed in having made theory give the aspect preserving inheritance algorithm convergence speed preferential treatment most , improves and algorithmic efficiency during the past probability appearing in the optimum solution having carried out optimization , its on tradition inheritance algorithm on analytical basis passing improving an overall situation in evolutionary every generation. There exists precocity convergence's problem in inheritance algorithm besides , one kind of convergence method resolving precocity the main body of a book has been introduced, continues getting the part different muchly come running inheritance algorithm many times give a solution preferential treatment most in the process searching for the optimum solution , unties and then again give preferential treatment most from asking for an overall situation in these selected solutions. The problem the main body of a book has been studied applying inheritance algorithm studying neural networks right value's, has brought forward one kind of the network structure optimizing , is put into use being unitary output network more replacing the BP network outputing muchly, that kind network structure is simpler , is fit to be put into use inheriting the algorithm optimization more. Besides, can testify the network structure that this optimizes having the optimum more excellent solution. That 0-1 plans is one of important integer linear program model , "shipping boat and ship matches for the main body of a book in applying inheritance algorithm to the actual project when in being loaded with system ", with the plan model choosing boat building-up available as 0-1. Problem is hit by boat available quantity in reality as many as mounting hundred , the entire enumeration method evidently does not apply to in here. For this purpose the main body of a book the thought having led into branch limit boundary law first , the calculation number of times having decreased by a problem greatly, can calculate the optimum solution going wrong within very short time in most of the cases. Then the main body of a book have suggested that one kind of the inheritance algorithm go along improving finds the solution specifically for those use the branch limit boundary to follow the condition having no way to calculate out the optimum solution within shorter time. Use any method that the institute knows at present to find the solution in fact that these are part condition short has all been difficult , using inheritance algorithm to calculate satisfied solution has been to choose comparatively well , the experiment bear fruit has also testified the main body of a book the method validity.
我只是中学英语老师，就会这么多，对不起啊 参考技术B In recent years, people have the genetic algorithms (GA, Genetic Algorithm) the degree of concern increases, it becomes more widespread, but the convergence speed is not a lot of theoretical research, this paper, the optimal preservation of genetic speed of convergence of the algorithm has done a theoretical analysis, and based on the analysis of the traditional genetic algorithm optimization, it evolved through each generation to improve the global optimal solution appears to increase the probability of algorithm efficiency. In addition, there are still premature convergence of genetic algorithm for the problem, this paper describes a solution to premature convergence of the method, the optimal solution in the search process has repeatedly run the genetic algorithm to get a number of different local optimal solution, and then from these selected solution obtained in the global optimal solution. This paper also studied the application of genetic algorithm for learning neural network weight problems, and propose an optimized network structure, using the network to replace multiple single-output multi-output BP network, the kinds of network structure is more simple and more suitable for the use of genetic algorithms optimization. In addition, the network can be shown that the optimized structure has better optimal solution.
0-1 programming is an important one integer linear programming model, this paper genetic algorithm is applied to the actual project, "Maritime ship stowage System", it will select the best available for the 0-1 programming model boat building. In practical problems the number of available boats up on the 100, full enumeration methods in here, obviously does not apply. This paper first introduces the idea of the branch and bound method, greatly reducing the problem of calculating the number of, in most cases, problems within a very short period of time calculating the optimal solution. Then this paper, those who use branch and bound method can not be in a relatively short period of time to calculate the optimal solution, putting forward an improved genetic algorithm to solve it. In fact, the use of any of the methods now known for solving such a small number of cases are difficult, and satisfactory solution using genetic algorithm is a better choice, experimental results also proved the effectiveness of this method. 参考技术C 一楼的开头有错误哦！我打的辛苦的。
Recent year, people to genetic algorithm (GA, Genetic Algorithm) the attention degree is getting bigger and bigger, is getting more and more widespread to its application, but concerns its convergence rate aspect fundamental research is not many, this article has made the theoretical analysis in the most superior preservation genetic algorithm's convergence rate aspect, and has carried on the optimization in the analysis foundation to the traditional genetic algorithm, it through raises the probability which in evolution each generation the globally optimal solution appears to enhance the algorithm the efficiency. In addition the genetic algorithm also had precocious restraining the question, this article introduced one solution precocious restraining method, moved in the search optimal solution's process the genetic algorithm to obtain many different partial optimal solutions many times continuously, is elected from these in the solution to obtain again the globally optimal solution. This article has also studied the application genetic algorithm study neural network weight question, proposed one kind of optimization's network architecture, uses many sole outputs the networks to replace the multi-outputs the BP network, this kind of network architecture is simpler, more suitable use genetic algorithm optimization. In addition, may prove that this kind of optimized the network architecture has a more superior optimal solution. the 0-1 plan is one of important integer linear programming models, this article will apply when the genetic algorithm "Shipping Ships Loads System" in the actual project, will choose the available ship establishment will be 0-1 planning models. Available ship's quantity reaches over a hundred much in the actual problem, the entire enumeration's method is not obviously suitable in here. Therefore this article has first introduced the branch limit method thought that reduced the question computation number of times greatly, may calculate the optimal solution which in the majority situations in the very short time has problems. Then this article is unable in view of these use branch limit law to calculate the optimal solution in a short time the situation, proposed one kind of improvement's genetic algorithm carries on the solution. Actually the use present knows any method solves this a little partial situations is difficult, the use genetic algorithm computation satisfaction solution was the quite good choice, the experimental result has also proven this article method validity.

参考资料：如果您的回答是从其他地方引用，请表明出处

参考技术D Google翻译.
谢谢.