改进遗传算法及其在钻井液设计中的运用
|
摘要
在深井、超深井以及地层复杂等条件下,为了避免或减少钻井事故的发生,达到优质快速钻井的目的,选择合适的钻井液体系至关重要。基于案例推理(CBR,Case-Based Reasoning)的钻井液设计中,钻井液体系由岩性、井型和井深等属性推理得出,但属性权重的分配会对推理结果产生显著的影响;遗传算法在优化属性权重时,存在收敛速度慢、收敛精度低的缺点。针对上述问题,提出一种解决CBR中属性权重分配问题的改进遗传算法。首先,对遗传算子进行改进:选择算子方面,利用指数尺度变换法优化个体选择;交叉算子方面,对算术交叉中的比例因子进行自适应调整;变异算子方面,改进个体变异方向,保持种群多样性。其次,从个体适.应度和交叉个体的差异程度两方面实现交叉概率自适应调整。最后,通过对UCI数据集的对比实验,证明了改进后的遗传算法能改善全局收敛性能,提高CBR的准确率。将该算法运用到基于CBR的钻井液设计中,实验结果表明,所提方法能够优化属性权重的分配,进而提高钻井液设计的质量。
The selection of a proper drilling fluid system is the key to enabling fast and high-quality drilling operations while avoiding or reducing the occurrence of drilling accidents when working in deep wells, ultra-deep wells, and complex formations.When designing the drilling fluid using case-based reasoning(CBR), the drilling fluid system can be derived from multiple attributes such as lithology, well type, and well depth. However, the derivation results can be substantially affected by each attribute's weight assignment. The genetic algorithm suffers from slow convergence and low convergence precision when used for optimization of the attribute weights. Considering this issue, this study proposes an improved genetic algorithm to address the issue of attribute weight assignment in CBR. Initially, the genetic operator is improved using the following techniques. An exponential scale transformation method is used to optimize the selection of the individual operator. A self-adaptive adjustment is performed on the scale factors in the arithmetic crossover. With reference to the mutation operator, the mutation direction of each individual is modified to maintain the diversity of the population. Next, the self-adaptive adjustment of the crossover probability is realized from two aspects, namely the individual fitness and the level of variation between crossover individuals.Finally, by performing comparative experiments on the UCI dataset, we proved that the improved genetic algorithm can enhance the global convergence performance and increase the accuracy of CBR. Experimental results demonstrate that applying the improved genetic algorithm to the CBR-based drilling fluid design can effectively optimize the weight assignments of each attribute and therefore improve the quality of drilling fluid.
The selection of a proper drilling fluid system is the key to enabling fast and high-quality drilling operations while avoiding or reducing the occurrence of drilling accidents when working in deep wells, ultra-deep wells, and complex formations.When designing the drilling fluid using case-based reasoning(CBR), the drilling fluid system can be derived from multiple attributes such as lithology, well type, and well depth. However, the derivation results can be substantially affected by each attribute's weight assignment. The genetic algorithm suffers from slow convergence and low convergence precision when used for optimization of the attribute weights. Considering this issue, this study proposes an improved genetic algorithm to address the issue of attribute weight assignment in CBR. Initially, the genetic operator is improved using the following techniques. An exponential scale transformation method is used to optimize the selection of the individual operator. A self-adaptive adjustment is performed on the scale factors in the arithmetic crossover. With reference to the mutation operator, the mutation direction of each individual is modified to maintain the diversity of the population. Next, the self-adaptive adjustment of the crossover probability is realized from two aspects, namely the individual fitness and the level of variation between crossover individuals.Finally, by performing comparative experiments on the UCI dataset, we proved that the improved genetic algorithm can enhance the global convergence performance and increase the accuracy of CBR. Experimental results demonstrate that applying the improved genetic algorithm to the CBR-based drilling fluid design can effectively optimize the weight assignments of each attribute and therefore improve the quality of drilling fluid.
引文
[1]胡庆辉,赵正文,陆玉靖.钻井液专家系统的研究与设计[J].钻井液与完井液,2007, 24(3):60-63. doi:10.-3969/j.issn.1001-5620.2007.03.019HU Qinghui, ZHAO ZhengwenL LU Yujing. Studies and design of drilling fluid expert system[J]. Drilling Fluid&Completion Fluid. 2007,24(3):60-63. doi:10.-3969/j.issn.1001-5620.2007.03.019
[2] SHOKOUHI S V, SKALLE P, AAMODT A. An overview of case-based reasoning applications in drilling engineering[J]. Artificial Intelligence Review, 2014, 41(3):317-329.
[3]王宝毅,张宝生,费沿光,等.基于案例推理的钻井复杂情况专家系统[J].石油大学学报(自然科学版),2005,29(6):123-126. doi:10.3321/j.issn:1000-5870.-2005.06.029WANG Baoyi.ZHANG Baosheng,FEI Yanguang,et al.A drilling troubles expert system based on case-based reasoning[J]. Journal of the University of Petroleum, China, 2005.29(6):123-126. doi:10.3321/j.issn:1000-5870.-2005.06.029
[4]安丽娜,张士杰.专家系统研究现状及展望[J].计算机应用研究,2007, 24(12):1-5, 19. doi:10.3969/j.issn.-1001-3695.2007.12.001AN Lina, ZHANG Shijie. Progress and prospects of expert system[J]. Application Research of Computers, 2007,24(12):1-5, 19. doi:10.3969/j.issn.1001-3695.2007.-12.001
[5]袁勇,董书杰,刘文梅.基于实例推理的钻井液配方设计系统[J].钻井液与完井液,2005, 22(1):31-34. doi:10.3969/j.issn.1001-5620.2005.01.010YUAN Yong, DONG Shujie, LIU Wenmei. Case based reasoning designing system for drilling fluid formulation[J]. Drilling Fluid&Completion Fluld, 2005, 22(1):31-34. doi:10.3969/j.issn.1001-5620.2005.01.010
[6] PLA A,LOPEZ B,GAY P,et al. eXiT*CBR.v2:Distributed case-based reasoning tool for medical prognosis[J]. Decision Support Systems, 2013, 54(3):1499-1510. doi:10.1016/j.dss.2012.12.033
[7] YAN Aijun, WANG Weixian, ZHANG Chunxiao, et al.A fault prediction method that uses improved case-based reasoning to continuously predict the status of a shaft furnace[J]. Information Sciences, 2014, 259(20):269-281.doi:10.1016/j.ins.2013.04.025
[8]顾东晓,李兴国,梁昌勇,等.案例检索及权重优化方法研究及应用[J].系统工程学报,2009, 24(6):764-768.doi:10.3969/j.issn.1000-5781.2009.06.020GU Dongxiao,LI Xingguo,LIANG Changyong,et al.Research on case retrieval with weight optimizing and its application[J]. Journal of Systems Engineering, 2009,24(6):764-768. doi:10.3969/j.issn.1000-5781.2009.-06.020
[9] PARK C S, HAN I. A case-based reasoning with the feature weights derived by analytic hierarchy process for bankruptcy prediction[J]. Expert Systems with Applications, 2002, 23(3):255-264. doi:10.1016/S0957-4174(02)00045-3
[10] JI Aimin, ZHU Kun, HUANG Quansheng. Methods determining the weights of characteristics in mechanical products design on case-base reasoning[J]. Applied Mechanics&Materials, 2011, 138-139:315-320. doi:10.-4028/www.scientific.net/AMM. 138-139.315
[11]吴登生,李建平,孙晓蕾.基于加权案例推理模型族的软件成本SVR组合估算[J].管理工程学报,2015,29(2):210-216. doi:10.13587/j.cnki.jieem.2015.02.023WU Dengsheng, LI Jianping, SUN Xiaolei. Combination estimation of software effort by support vector regression based on multiple case-based reasoning with optimizedweight[J]. Journal of Industrial Engineering and Engineering Management, 2015,29(2):210-216. doi:10.13587/j.-cnki.j ieem.2015.02.023
[12] YAN Aijun, SHAO Hongshan, GUO Zhen. Weight optimization for case-based reasoning using membrane computing[J], Information Sciences, 2014, 287:109-120.
[13]付雅芳,刘晓东,李延杰,等.基于遗传算法和案例推理的软件费用估算方法[J].计算机工程与应用,2012,48(8):86-91. doi:10.3778/j.issn.1002-8331-2012.08.024FU Yafang,LIU Xiaodong,LI Yanjie,et al. Software cost estimation method based on genetic algorithm and casebased reasoning[J]. Computer Engineering and Applications, 2012,48(8):86-91. doi:10.3778/j.issn.1002-8331.-2012.08.024
[14]王丽敏,乔玲玲,魏霖静.结合遗传算法的优化卷积神经网络学习方法[J].计算机工程与设计,2017, 38(7):1945-1950. doi:10.16208/j.issn1000-7024.2017.07.044WANG Limin, QIAO Lingling, WEI Linjing. Optimal convolutional neural networks learning method combined with genetic algorithm[J]. Computer Engineering and Design, 2017, 38(7):1945-1950. doi:10.16208/j.issn1000-7024.2017.07.044
[15]李海芳,樊海亮,金辉.基于遗传算法的全局优化检索策略研究[J].计算机应用研究,2009, 26(5):1667-1669. doi:10.3969/j.issn.1001-3695.2009.05.018LI Haifang, FAN Hailiang, JIN Hui. Strategy research of global optimization based on genetic algorithm[J]. Application Research of Computers, 2009, 26(5):1667-1669.doi:10.3969/j.issn. 1001-3695.2009.05.018
[16]孟庆宽,张漫,仇瑞承,等.基于改进遗传算法的农机具视觉导航线检测[J].农业机械学报,2014, 45(10):39-46. doi:10.6041/j.issn.1000-1298.2014.10.007MENG Qingkuan, ZHANG Man, QIU Ruicheng, et al.Navigation line detection for farm machinery based on improved genetic algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2014,45(10):39-46.doi:10.6041/j.issn. 1000-1298.2014.10.007
[17]万碧君,罗健旭.一种改进的基于案例推理的建模算法[J].华东理工大学学报(自然科学版),2014, 40(5):107-111. doi:10.3969/j.issn.1006-3080.2014.05.019WAN Bijun, LUO Jianxu. An improved case-based reasoning modeling algorithm[J]. Journal of East China University of Science and Technology(Natural Science Edition), 2014, 40(5):107-111. doi:10.3969/j.issn. 1006-3080.2014.05.019
[18] BAX E. Validation of nearest neighbor classifiers[J].IEEE Transactions on Information Theory, 2004, 46(7):2746-2752. doi:10.1109/18.887892
[19]边霞,米良.遗传算法理论及其应用研究进展[J].计算机应用研究,2010, 27(7):2425-2429, 2434. doi:10.-3969/j.issn.1001-3695.2010.07.006BIAN Xia, MI Liang. Development genetic algorithm theory and its applications[J]. Application Research of Computers.2010. 27(7):2425-2429, 2434. doi:10.-3969/j.issn.1001-3695.2010.07.006
[20]葛继科,邱玉辉,吴春明,等.遗传算法研究综述[J].计算机应用研究,2008, 25(10):2911-2916. doi:10.-3969/j.issn.1001-3695.2008.10.008GE Jike.QIU,Yuhui,Wu Chunming,et al. Summary of genetic algorithms research[J]. Application Research of Computers, 2008. 25(10):2911-2916. doi:10.3969/j.-issn.1001-3695.2008.10.008
[21]徐岩,郅静.基于改进自适应遗传算法的PMU优化配置[J].电力系统保护与控制.2015, 43(2):55-62.XU Yan, ZHI Jing. Optimal PMU configuration based on improved adaptive genetic algorithm[J]. Power System Protection and Control, 2015,43(2):55-62.
[22]陈乐亮.我国钻井液体系分类的探讨[J].天然气工业,1991.11(4):64-68.CHEN Leliang. A discussion on the classification of drilling fluid system in our country[J]. Natural Gas Indus-try.1991.11(4):64—68.
[2] SHOKOUHI S V, SKALLE P, AAMODT A. An overview of case-based reasoning applications in drilling engineering[J]. Artificial Intelligence Review, 2014, 41(3):317-329.
[3]王宝毅,张宝生,费沿光,等.基于案例推理的钻井复杂情况专家系统[J].石油大学学报(自然科学版),2005,29(6):123-126. doi:10.3321/j.issn:1000-5870.-2005.06.029WANG Baoyi.ZHANG Baosheng,FEI Yanguang,et al.A drilling troubles expert system based on case-based reasoning[J]. Journal of the University of Petroleum, China, 2005.29(6):123-126. doi:10.3321/j.issn:1000-5870.-2005.06.029
[4]安丽娜,张士杰.专家系统研究现状及展望[J].计算机应用研究,2007, 24(12):1-5, 19. doi:10.3969/j.issn.-1001-3695.2007.12.001AN Lina, ZHANG Shijie. Progress and prospects of expert system[J]. Application Research of Computers, 2007,24(12):1-5, 19. doi:10.3969/j.issn.1001-3695.2007.-12.001
[5]袁勇,董书杰,刘文梅.基于实例推理的钻井液配方设计系统[J].钻井液与完井液,2005, 22(1):31-34. doi:10.3969/j.issn.1001-5620.2005.01.010YUAN Yong, DONG Shujie, LIU Wenmei. Case based reasoning designing system for drilling fluid formulation[J]. Drilling Fluid&Completion Fluld, 2005, 22(1):31-34. doi:10.3969/j.issn.1001-5620.2005.01.010
[6] PLA A,LOPEZ B,GAY P,et al. eXiT*CBR.v2:Distributed case-based reasoning tool for medical prognosis[J]. Decision Support Systems, 2013, 54(3):1499-1510. doi:10.1016/j.dss.2012.12.033
[7] YAN Aijun, WANG Weixian, ZHANG Chunxiao, et al.A fault prediction method that uses improved case-based reasoning to continuously predict the status of a shaft furnace[J]. Information Sciences, 2014, 259(20):269-281.doi:10.1016/j.ins.2013.04.025
[8]顾东晓,李兴国,梁昌勇,等.案例检索及权重优化方法研究及应用[J].系统工程学报,2009, 24(6):764-768.doi:10.3969/j.issn.1000-5781.2009.06.020GU Dongxiao,LI Xingguo,LIANG Changyong,et al.Research on case retrieval with weight optimizing and its application[J]. Journal of Systems Engineering, 2009,24(6):764-768. doi:10.3969/j.issn.1000-5781.2009.-06.020
[9] PARK C S, HAN I. A case-based reasoning with the feature weights derived by analytic hierarchy process for bankruptcy prediction[J]. Expert Systems with Applications, 2002, 23(3):255-264. doi:10.1016/S0957-4174(02)00045-3
[10] JI Aimin, ZHU Kun, HUANG Quansheng. Methods determining the weights of characteristics in mechanical products design on case-base reasoning[J]. Applied Mechanics&Materials, 2011, 138-139:315-320. doi:10.-4028/www.scientific.net/AMM. 138-139.315
[11]吴登生,李建平,孙晓蕾.基于加权案例推理模型族的软件成本SVR组合估算[J].管理工程学报,2015,29(2):210-216. doi:10.13587/j.cnki.jieem.2015.02.023WU Dengsheng, LI Jianping, SUN Xiaolei. Combination estimation of software effort by support vector regression based on multiple case-based reasoning with optimizedweight[J]. Journal of Industrial Engineering and Engineering Management, 2015,29(2):210-216. doi:10.13587/j.-cnki.j ieem.2015.02.023
[12] YAN Aijun, SHAO Hongshan, GUO Zhen. Weight optimization for case-based reasoning using membrane computing[J], Information Sciences, 2014, 287:109-120.
[13]付雅芳,刘晓东,李延杰,等.基于遗传算法和案例推理的软件费用估算方法[J].计算机工程与应用,2012,48(8):86-91. doi:10.3778/j.issn.1002-8331-2012.08.024FU Yafang,LIU Xiaodong,LI Yanjie,et al. Software cost estimation method based on genetic algorithm and casebased reasoning[J]. Computer Engineering and Applications, 2012,48(8):86-91. doi:10.3778/j.issn.1002-8331.-2012.08.024
[14]王丽敏,乔玲玲,魏霖静.结合遗传算法的优化卷积神经网络学习方法[J].计算机工程与设计,2017, 38(7):1945-1950. doi:10.16208/j.issn1000-7024.2017.07.044WANG Limin, QIAO Lingling, WEI Linjing. Optimal convolutional neural networks learning method combined with genetic algorithm[J]. Computer Engineering and Design, 2017, 38(7):1945-1950. doi:10.16208/j.issn1000-7024.2017.07.044
[15]李海芳,樊海亮,金辉.基于遗传算法的全局优化检索策略研究[J].计算机应用研究,2009, 26(5):1667-1669. doi:10.3969/j.issn.1001-3695.2009.05.018LI Haifang, FAN Hailiang, JIN Hui. Strategy research of global optimization based on genetic algorithm[J]. Application Research of Computers, 2009, 26(5):1667-1669.doi:10.3969/j.issn. 1001-3695.2009.05.018
[16]孟庆宽,张漫,仇瑞承,等.基于改进遗传算法的农机具视觉导航线检测[J].农业机械学报,2014, 45(10):39-46. doi:10.6041/j.issn.1000-1298.2014.10.007MENG Qingkuan, ZHANG Man, QIU Ruicheng, et al.Navigation line detection for farm machinery based on improved genetic algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2014,45(10):39-46.doi:10.6041/j.issn. 1000-1298.2014.10.007
[17]万碧君,罗健旭.一种改进的基于案例推理的建模算法[J].华东理工大学学报(自然科学版),2014, 40(5):107-111. doi:10.3969/j.issn.1006-3080.2014.05.019WAN Bijun, LUO Jianxu. An improved case-based reasoning modeling algorithm[J]. Journal of East China University of Science and Technology(Natural Science Edition), 2014, 40(5):107-111. doi:10.3969/j.issn. 1006-3080.2014.05.019
[18] BAX E. Validation of nearest neighbor classifiers[J].IEEE Transactions on Information Theory, 2004, 46(7):2746-2752. doi:10.1109/18.887892
[19]边霞,米良.遗传算法理论及其应用研究进展[J].计算机应用研究,2010, 27(7):2425-2429, 2434. doi:10.-3969/j.issn.1001-3695.2010.07.006BIAN Xia, MI Liang. Development genetic algorithm theory and its applications[J]. Application Research of Computers.2010. 27(7):2425-2429, 2434. doi:10.-3969/j.issn.1001-3695.2010.07.006
[20]葛继科,邱玉辉,吴春明,等.遗传算法研究综述[J].计算机应用研究,2008, 25(10):2911-2916. doi:10.-3969/j.issn.1001-3695.2008.10.008GE Jike.QIU,Yuhui,Wu Chunming,et al. Summary of genetic algorithms research[J]. Application Research of Computers, 2008. 25(10):2911-2916. doi:10.3969/j.-issn.1001-3695.2008.10.008
[21]徐岩,郅静.基于改进自适应遗传算法的PMU优化配置[J].电力系统保护与控制.2015, 43(2):55-62.XU Yan, ZHI Jing. Optimal PMU configuration based on improved adaptive genetic algorithm[J]. Power System Protection and Control, 2015,43(2):55-62.
[22]陈乐亮.我国钻井液体系分类的探讨[J].天然气工业,1991.11(4):64-68.CHEN Leliang. A discussion on the classification of drilling fluid system in our country[J]. Natural Gas Indus-try.1991.11(4):64—68.