深井底板突水判别和预测系统开发研究-矿业信息工程专业论文.docx

摘要随着煤炭开采逐步向深部发展，在复杂的水文地质环境下，深井底板突水危险性将 更加突出，安全回采深部煤炭资源的控制难度大大增加。本文从因素分析、数学模型和 系统程序为一体的研究方法，对深井底板突水的主控因素、判别模型和预测系统进行了 研究。计算了深井临界深度，分析了各因素在深井底板突水中的作用，建立了深井底板突 水评价指标体系。运用层次分析法选出深井底板突水的主控因素，建立了层次分析法自动调整模型程 序解决动态判断矩阵的整体一致性难以满足的难题。通过建立隶属度和隶属函数实现了 各因素信息数据的归一处理，构建了基于模糊神经网络的深井底板突水判别模型，选择 合适的网络结构参数规避了神经网络自身的缺点，选取工程实例验证了模糊神经判别模 型的可靠程度。通过灰色关联分析验证了层次分析法得到的主控因素，应用熵值调整法确定了各主 控因素在突水过程中的贡献权重。依据肖芳淳教授的灰色物元分析理论，分别构建了深 井煤层底板突水最优灰色物元和线性灰色物元判别模型，通过工程样本验证模型确定了 危险区、脆弱区和安全区的阈值。以最优灰色物元和线性灰色物元判别模型为基础，采用 VB6.0 开发了深井底板突水 组合灰色物元判别系统。系统分为信息管理、突水评判、系统维护和系统服务四个模块。 系统功能相对完善，且具有简易性、实用性和可靠性，从而使深井底板突水的预测结果 相对科学和客观。 关键词：深井底板突水；临界深度；自动调整模型；模糊神经；灰色关联分析；熵值调整；灰色物元分析；判别系统ABSTRACTWith the gradua l development of deep coal, the hazard of deep seam mining floor water- burst ing is more sigificia nt in a complex hydrogeologica l environment and to mine the deep coal seam safely is much more difficult then before. In this paper, the integrated approaches of factoria l analysis, mathematica l model and system program were adopted to study the ma in factors, discr imina nt model and predict ion system.The critica l depth of deep mine was calculated and each factoria l funct ion of water-burst ing was analysed, then assessment index system was derived.By AHP(analytic hierarchy process), it got the ma in factors of deep-well floor water burst ing. The AHP automa tical adjust ing model program was built to solve the quest ion that the dynamica l judgement matrix’s globe consistece is usua lly hard to satisfy. Every factor ’s information data were norma lized by the membership funct ion or membership grade, the FNN (fuzzy neura l network) dist inguish ment model was taken out. Choosing the proper network ’s paramater was used to avoid ing neura l network its weakness, its reliability was tested by the engineer ing projects.The chosen ma in factors were verified by the grey releva nce analysis, the contributionweights was ascertained by the entropy adjust ing the ancient. According to professor Xiao Fangchun’s grey mat