【作者】 张涛；

【导师】 李敬花；

【作者基本信息】 哈尔滨工程大学 ， 船舶与海洋结构物设计制造， 2016， 硕士

【摘要】 海工项目计划是项目实施的依据,必须在项目开工之前编制完成,这样项目才能在进度计划的指导下高效有序的进行。通过调研发现国内的海工项目普遍存在计划无法指导执行而流于形式的问题,一个重要原因是海洋工程项目具有周期长,单件或小批量生产,EPC总承包合同,项目工作跨专业、跨部门甚至跨企业等特点,因此项目计划编制难度极大,往往项目已经开工而计划编制尚未完成。计划的编制可以看作一种决策问题,而人工神经网络在智能决策系统的应用中有良好的表现。为解决制约海工项目计划编制效率的关键问题,本文研究了基于人工神经网络技术的海工项目计划编制关键技术,开发了海工项目计划编制原型系统。本研究有利于我国海工企业计划管理的科学化和规范化。论文分析了国内外项目计划编制技术以及海工项目计划编制技术研究现状,阐述了人工神经网络技术的原理;深入研究了海工项目计划编制技术,并找出了制约海工项目计划编制效率的关键点;在此基础上,本文提出了两个需要解决的关键问题:工作分解结构(WBS, Work Breakdown Structure)分解和活动排序。针对WBS分解问题,建立海工项目工作分解结构模型,提出基于模块化神经网络的WBS分解方法;针对活动排序问题,建立海工项目作业排序模型,提出基于BP神经网络的作业排序方法。最后,将上述研究成果应用于实践,采用基于Spring的开发框架和B/S结构,设计并开发海工项目计划编制原型系统,验证方法的可行性和有效性。更多还原

【Abstract】 Offshore project planning is the basis of project implementation,which should be accomplished before the start of the project so that the project can be carried out effectively under the guidance of the schedule. Study found that there is a common problem in domestic enterprises that the plan cannot be used to guide implementation and become a mere formality.The most important reason for this is that offshore equipment project planning is quite difficult because of its characters such as long duration,single or small batch production,EPC general contract,cross-professional,cross-departments and even cross-enterprise project work etc. As a result, the plan usually cannot be finished before starting construction. The planning of project can be considered as a kind of decision-making problem. As is known that artificial neural network has a good performance in the application of intelligent decision system.Hence, the key issues which restrict the efficiency of the project planning are studied in this paper, and a method of offshore project planning based on artificial neural network has been proposed, which can promote the construction enterprise to improve the level of planning management.Firstly, the research on the project planning technology and its application in the field of offshore project both at home and abroad are analyzed and summarized; Secondly, the principle of artificial neural network is introduced briefly; Thirdly, the key issues which restrict the efficiency of the project planning are found through detail analysis of the techniques of offshore project planning; Fourthly, two of the key issues: WBS and sequence the activities are proposed. Aimed at solving the WBS problem, the WBS model of offshore project is built and a modular neural network model used to solve this problem is proposed;Aimed at solving the project activities sequencing problem, the sequence model of offshore project activities is built and a method based on BP neural network is proposed; Last, by adopting the Spring development framework and B/S structure, the prototype system of the project planning management system is designed and developed, which prove the feasibility and validity of the approach.更多还原