用户名: 密码: 验证码:
基于人工智能的硬化层深预测系统
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
金属表面硬化层深的检测一直是机械工业部门急需解决的问题,涡流法作为一种无损检测方法相较于以往的破坏性检测有更高的可靠性和经济效益。然而用涡流法对它进行检测的最大难度在于检测信号的处理。由于涡流的检测层深和灵敏度受频率影响很大,单一频率检测不能满足不同层深的需要,本文采用多频涡流检测的方法,以使信号中充分包含有用信息。
     信息融合作为信息领域的一项高新技术,目前主要用于多传感器融合中。它是把多个信息源所得到的冗余或互补信息,依据某种准则进行组合,以获得对被检测目标的一致性解释或描述。信息融合对于多信息的处理能力已得到了广泛应用,本文对于它在多频涡流信号处理中的应用作了系统的研究,首次提出了不同数量级信号融合的方法。
     本文利用信息融合将多个频率下测得的涡流信号进行融合。采用模糊-遗传算法,信息融合过程中的推理由模糊聚合函数完成,模糊聚合比传统的集合论中的并和交操作能更好地模仿人的推理。模糊聚合函数的连接参数由遗传算法确定。该算法的优点是在信息源的可靠性、信息的冗余性/互补性不确定的情况下能够以近似最优的方法对信息进行融合。
     通过信息融合,本文最后得出了一个硬化层深的预测系统,并通过待测试件验证了预测的可靠性。
Nondestructive testing of metal hardened-depth is an important problem to be solved in machinery industry. Eddy current is an effective method in which the most difficult task is the processing of the signal. Since the penetrative depth and the testing sensitiveness are influenced seriously with the testing frequency. So multi-frequency eddy current is used in place of single-frequency eddy current to involve full information of the objects.
    Data fusion is a method to combine the redundant and complemented data of the multi-source by some rules. As a result, the consistency interpretation and description is obtained. This paper presents a method to fusion the signal of the eight-frequency eddy current. A fuzzy-genetic data fusion algorithm is utilized. The reasoning is performed by means of fuzzy aggregation functions, the fuzzy aggregation being capable of better set theories. The parameters of the connectives are found by genetic algorithms. The distinctive feature of this algorithm is its capability of fusing data in a near-optimal manner when there exists no information about the reliability of information sources, the degree of redundancy/ complementarities of the information sources, and the structure of the hierarchy.
    At the end, an example is given to test the reliability of the forecasting system.
引文
[1] M Mina, S S Udpa, L Udpa and J Yim. A New Approach for Practical Two Dimensional Data Fusion Utilizing a Single Eddy Current Probe, Review of Progress in Quantitative Nondestructive Evaluation, 1997. Vol 16: 749-754
    [2] M Mina, J Yim, S S Udpa and L Udpa. Two Dimensional Multi-frequency Eddy Current Data Fusion. Review of Progress in Quantitative Nondestructive Evaluation, 1996. Vol 15: 2125-2132
    [3] K A Bartels and J L Fisher. Optimal Multidimensional Multi-frequency Eddy Current Mixing Techniques. Review of Progress in Quantitative Nondestructive Evaluation, 1996. Vol 15: 393-400,
    [4] R Krishnapuram and J Lee. Fuzzy-connective-based hierarchical aggregation networks for decision-making. Fuzzy Sets and Syst , 1992. 46: 11-27.
    [5] H Dyckhoff and W pedrycz . Generalized means of model compensative connectives. Fuzzy Sets and Syst, 1984. 14
    [6] Radcliffe N J, Surry P D. The Reproductive Plan Language RPL2: Motivation and Applications. Amsterdam: IOS Press, 1994: 65-94
    [7] Ajun An,Christine Chan. Applying Knowledge Discovery to Predict Water-Supply Consumption. IEEE EXPERT 1997 JULY/AUGUST 72-77
    [8] Bui T N, Moon B R. Genetic Algorithm and Graph Partitioning. IEEE Trans on Computer. 1996,45(7) : 841-855
    [9] Liotopoulos Th K, Antonopoulos C.S., and Kriezis E.E. Kiw-frequency generalized solution for the shielding effectiveness of a multicoated system of coaxial cylindrical shells. IEE Pro. 1993. 140(4)
    [10] Clark R and Bond L J. An investigation of horizontal axis coils for eddy current inspection. NDT international, 1989. 22(6)
    [11] Martin Witkowski L, Marty P,and walker J S. Multidomain
    
    analytical-numerical solution for a rotating magnetic field with a finite-length conducting cylinder. IEEE Trains, 36(2)
    [12] Dodd C.D, and Deeds W.E. Analytical solutions to eddy-current probe-coil problem. Appl. Phys, 1991.39(6) : 4360~4365
    [13] Homaifar A, Lai S H Y, Qi X. Constrained Optimization via Genetic Algorithms. Simulation, 1994.62(4):242~254
    [14] Schoenauer M, Xanthakis S. Constrained G A Optimization. Proceedings of the 5th International Conference on Genetic Algorithms, Los Altos, 1993
    [15] Srinivas V, Deb K. Multi-objective Optimization Using Non-dominated Sorting in Genetic Algorithms. Evolutionary Computation, 1994.2(3): 221~248
    [16] 游凤荷,曹令俊.基于有限元法的涡流检测数值仿真.全国电磁(涡流)检测学术会议论文集,2000:21—26
    [17] 任吉林.电磁无损检测.北京:航空工业出版社,1989
    [18] 刘本田,雷银照,磁导率变化的平板导体上方的线圈阻抗的解析式,全国电磁(涡流)检测学术会议论文集,2000:86~97
    [19] 孙晓云,路灿.涡流无损检测中的定量分析.无损检测,2000.22(5):194~199
    [20] 吴前驱,贺潜源等.表面无损检测.北京:水利电力出版社.1991
    [21] 梁玉红,吴步宁,神经网络在涡流检测信号处理中的应用.无损检测.2000.22(12):545~547
    [22] 林介东.用于电站热交换管检测的四频涡流检测仪.热能动力工程,2002.17(3):189~190
    [23] 魏莉.涡流测试信号处理系统研究:[硕士学位论文].武汉:武汉理工大学机电学院,2002
    [24] 李洪志.信息融合技术.北京:国防工业出版社,2001
    [25] 何友,彭应宁等.多传感器数据融合模型综述.清华大学学报自然科学版,1996,36(9):14~20
    [26] 刘登第,傅惠民等.一种新的数据融合方法.中国安全科学学报,1998,8(6):1~4
    
    
    [27] 许军,罗飞路等,多传感器信息融合技术在无损检测中的应用研究.无损检测,2000.22(8):342~344
    [28] 王建海,方振和.多传感器数据融合浅析.上海大学学报(自然科学版),1997.3(4):454~461
    [29] 唐义平,李卫,多传感器系统的数据融合技术.上海航天,1997.4:39~44
    [30] 李国栋,陈维南.一种新的数据融合算法研究,机器人,1997.7:290~293
    [31] 吴陈.一种数据融合仿真系统的数据生成.造船技术,1998.9:31~38
    [32] 李卫星,李志民.基于信息融合理论的电力系统预测研究.继电器.2001.29(10):16~18
    [33] 杨杰,沈利等.结合数据融合和数据挖掘的医疗监护报警.计算机仿真,2000.17(6):39~41
    [34] 路勇,姚英学.基于多参量状态信息融合的刀具磨损状态智能识别.航空精密制造技术,1999.35(6):26~30
    [35] 王洪强,孙即祥.随机信号多尺度分析的数据融合.工程数学学报,2000.17(2):127~130
    [36] 李冰,罗雪山等.条件随机变量与条件数据融合.国防科技大学学报,1999.21(1):109~112
    [37] 刘莹,王宝树等.模糊聚合及遗传算法在多传感器数据融合中的应用.电子科技,1998.1:28~34
    [38] 刘莹,刘三阳等.基于遗传算法的多传感器数据融合.微电子学与计算机,1999.2:22~27
    [39] 吴超仲,严新平等.基于遗传算法的信息融合在摩擦学组合故障诊断中的应用.摩擦学学报,2001.21(4):301~304.
    [40] 潘正君,康立山等.演化计算.北京:清华大学出版社,广西科学技术出版社,1998
    [41] 郑宏兴,姚纪欢等.Matlab 5.x工具箱使用技巧与实例.武汉:华中科技大学出版社,2000
    [42] 汪秉文等,遗传算法在MATLAB环境中的实现,武汉汽车工业大学学报,1999.21(6):25~28
    [43] 刘国华,包宏等.用MATLAB实现遗传算法程序.计算机应用研究,
    
    2001(8):80~82
    [44] 周明,孙树栋.遗传算法原理及其应用.北京:国防工业出版社,1999
    [45] 姚东,王爱民等.matlab命令大全.北京:人民邮电出版社,2000
    [46] 龚剑,朱亮.matlab5.x入门与提高.北京:清华大学出版社 1999.
    [47] 阮达,黄崇福.模糊集与模糊信息粒理论.北京:北京师范大学出版社,2000

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700