论文中文题名: | 基于PSO-SVM的煤矿物资计划管理系统的研究 |
姓名: | |
学号: | 201107328 |
保密级别: | 公开 |
学科代码: | 085208 |
学科名称: | 电子与通信工程 |
学生类型: | 工程硕士 |
学位年度: | 2014 |
院系: | |
专业: | |
第一导师姓名: | |
论文外文题名: | Research of Mine Materials Planning Management System Based on PSO-SVM |
论文中文关键词: | |
论文外文关键词: | Materials Planning ; Particle Swarm ; SVM ; DDC ; Materials Forecast ; Workflow |
论文中文摘要: |
煤炭作为我国能源消耗的主要来源之一,在经济发展当中具有举足轻重的地位。随着信息技术的不断发展,互联网技术和移动互联网技术的广泛应用,以及经济全球化进程的加剧,使得市场竞争更加激烈。国内的煤炭企业物资计划管理信息化水平整体还比较低,随之带来的问题是库存积压严重,占用大量资金,企业生产成本增大。为实现“零库存”的管理思想,延伸供应链到采煤工作面,做好煤炭企业物资计划的精细化管理,利用信息技术科学有效地对煤矿生产所消耗的物资进行动态预测、建立物资计划提报的智能化管理系统是降低企业库存成本,提高物资供应链的精细化管理水平的关键手段。
本文首先分析了当前煤炭企业物资计划管理存在的一些问题,然后阐述了物资计划管理的相关内容,根据已经分类好的物资,通过提取煤矿井下生产作业所需的这类物资的影响因素,设计关键指标进行分析,确立了物资需求预测关键指标体系。同时针对支持向量机模型在参数选取时具有一定的主观性和参数优化程度不够的问题,采用粒子群优化算法对支持向量机模型的最佳参数进行最优选取,然后将最优选取的参数结果应用于支持向量机对物资需求预测,以实际的物资采煤机截齿为例进行预测,预测结果表明通过粒子群算法对参数优化后的支持向量机预测模型提高了预测精度。
本论文以实际参与的企业课题“山东能源淄矿集团供应链电子商务系统”为背景,通过分析淄矿集团当前计划管理的业务需求,提出了煤矿企业物资计划管理系统的整体架构,探讨了系统的技术实现方案。对其中的物资预测进行数据建模,选择粒子群优化的支持向量机作为物资需求的预测模型,基于J2EE开发平台,并采用Oracle10g数据库作为底层数据支撑平台,同时以Activiti5流程引擎设计并开发了一套符合淄矿集团实际业务的基于PSO-SVM(Particle Swarm Optimization- Support Vector Machine,PSO-SVM)的物资计划管理平台,实现了淄矿集团物资计划管理的信息化,最后对论文的研究工作做以总结,并对系统的进一步研究做以展望。
﹀
|
论文外文摘要: |
As one of the main sources of China's energy consumption, coal is of great importance in our country’s economy development, the extensive use of the Internet technology and mobile Internet technology, and the quickened proceeding of economy globalization, the market competition becomes more and more ardent. Over all informatization level of China’s coal mine enterprise material plan management is relatively low, which causes the subsequent problems of excess inventory, large amount of capital occupation and the increase of production costs. In order to achieve the management philosophy of “Zero inventory”, the supply chain should be extended to the coalface, fine management of the coal mine enterprise material plan needs to be made, information technical science should be employed to make valid dynamic predication of the materials consumed in the production, intelligent management system for the material plan report also needs to be built. All the above methods also act as the critical measures of minimizing inventory costs and improving the fine management level of the material supply chain.
This thesis first analyzes the problems in the present material plan management of the coal mine enterprise, and then demonstrates the relevant content of the material plan management. Based on the classified materials and the influential factors extracted from these materials needed by the underground mine operations as well as the analysis of the key indicators, the key indicator system of the material demand forecast is worked out. As to the problems of subjectivity and insufficient optimization of the parameters in the process of parameter selection by the support vector machine model ( SVM model), particle swarm optimization method is adopted in optimal selection of the optimal parameters of the SVM model. According to the parameter results of the optimal selection, the SVM forecasts the material demand, for example,forecast shearer with the actual materials, and the forecast results indicate that particle swarm optimization method optimizes the parameters of the support vector machine forecast model and improves its predicting accuracy.
Based on the background of the author’s actual participation of the enterprise project topic “Supply chain e-commerce system of Shandong energy Zi mining group” and the analysis of the business requirements of the Zi mining group’s plan management, this thesis works out the whole framework of the mine’s enterprise material plan management system and discusses the technology realization scheme. Data modeling is done based on the relevant material demand forecast, particle swarm optimized SVM is chosen as the prediction model for the material demand forecast, based on J2EE development platform, Oracle10g data base is adopted as the underlying data support platform, meanwhile, Activiti5 process engine design is applied, therefore, a set of material plan management platform based on PSO—SVM according with the actual business of Zi mining group is developed. Finally, the research work of the dissertation has been summarized and the prospect of the further study of the system has been opened up.
﹀
|
中图分类号: | TP311.52 |
开放日期: | 2014-06-12 |