吉林大学学报(工学版) ›› 2021, Vol. 51 ›› Issue (3): 1017-1025.doi: 10.13229/j.cnki.jdxbgxb20200059

• 计算机科学与技术 • 上一篇    

故障响应指导下基于测试集的故障诊断方法

欧阳丹彤1,2(),刘扬3,刘杰1,2()   

  1. 1.吉林大学 计算机科学与技术学院,长春 130012
    2.吉林大学 符号计算与知识工程教育部重点实验室,长春 130012
    3.吉林大学 软件学院,长春 130012
  • 收稿日期:2020-01-31 出版日期:2021-05-01 发布日期:2021-05-07
  • 通讯作者: 刘杰 E-mail:ouyangdantong@163.com;liu_jie@jlu.edu.cn
  • 作者简介:欧阳丹彤(1968-),女,教授,博士生导师. 研究方向:人工智能,基于模型诊断.E-mail:ouyangdantong@163.com
  • 基金资助:
    国家自然科学基金项目(61672261)

Fault diagnosis method based on test set under fault response guidance

Dan-tong OUYANG1,2(),Yang LIU3,Jie LIU1,2()   

  1. 1.College of Computer Science and Technology,Jilin University,Changchun 130012,China
    2.Key Laboratory of Symbolic Computation and Knowledge Engineering,Ministry of Education,Jilin University,Changchun 130012,China
    3.College of Software,Jilin University,Changchun 130012,China
  • Received:2020-01-31 Online:2021-05-01 Published:2021-05-07
  • Contact: Jie LIU E-mail:ouyangdantong@163.com;liu_jie@jlu.edu.cn

摘要:

通过对电路中故障输出特征进行研究,结合增强故障诊断(ADD)测试候选诊断求解方法,提出了故障响应指导下的候选诊断求解方法ALFDD。依据当前测试激励下实际输出响应与预期输出响应不相同的单故障更可能是故障诊断解的原理,提出了候选单故障集合的概念。针对ADD方法中需对电路的所有单故障求解Fsame的问题,给出仅对候选单故障集合求解Fsame的方法。该方法一方面避免了对所有单故障都进行对比并求解Fsame的问题,提高了诊断求解效率;另一方面有效删除了Fsame中包含的冗余候选诊断解,提高了候选诊断解的分辨率;此外,还增加了候选故障集中所包含的真实诊断解的数量,提高了候选诊断解的准确率。实验结果表明,与ADD方法相比,ALFDD方法候选诊断分辨率和准确率明显提高,求解效率也有较大提高。

关键词: 计算机应用, 模型故障, 故障诊断, 候选单故障集合, 诊断准确性, 诊断分辨率

Abstract:

In this paper, having deeply studied the fault output characteristics in circuits and the ADD candidate diagnosis solution method, we propose a candidate diagnosis solution method under the guidance of fault response, ALFDD, namely. We also put forward the concept of candidate single fault set, which is based on the principle that a single fault with different actual output response and expected output response under current test excitations is more likely to be a fault diagnosis solution. To overcome the problem that in ADD method to obtain Fsame all single faults of circuit should be compared, we give the method which only considers the faults of the candidate single fault set to obtain Fsame. This method has three merits. Firstly, it does not need to compare all single faults and improves the efficiency of solving problems. Secondly, it eliminates the reluctant candidate solutions concluded in Fsame effectively, so it improves the resolution of candidate diagnostic solutions. In addition, this method improves the accuracy of candidate diagnostic solutions, namely, increasing the number of real diagnostic solutions in the candidate fault sets. The test results show that,, compared with ADD, the proposed ALFDD method increases the resolution, accuracy and solution efficiency for selecting candidate diagnoses.

Key words: computer application, model fault, fault diagnosis, candidate single fault set, accuracy of diagnosis, resolution of diagnosis

中图分类号: 

  • TP391

表1

s27部分Rk和Robs对照表"

iRobsR0R1
0010100010111
1101010001100
2010110101110
3110100010001
4010101010101
5011011101110
6100110001000
7101110101010
8111111101110
9010100011100

表2

部分故障分数"

fkf8f27f4f5f20f21f26f30
s(fk)3131303030303029

表3

ISCAS—85实例故障诊断结果"

电路名称实际故障模型故障OverlapResoPrecrtime
ADDALFDDADDALFDDdvalADDALFDDdval
c175142.34.20.670.800.130.460.840.380.88
c43220865.17.20.290.320.030.260.360.100.86
c499201467.88.00.350.440.090.390.400.010.53
c8802016515.117.30.600.610.010.760.870.110.64
c13552014611.211.20.560.700.140.560.560.000.52
c1908201168.815.60.420.450.030.440.780.340.57
c26702058917.319.40.680.700.020.870.970.100.70
c35402014413.015.10.370.400.030.650.760.110.69
c53152059619.619.80.940.990.050.980.990.010.64
c62882012812.613.80.410.500.090.630.690.060.52

表4

ISCAS—89实例故障诊断结果"

电路

名称

实际

故障

模型

故障

OverlapResoPrecrtime
ADDALFDDADDALFDDdvalADDALFDDdval
s2710323.53.60.430.600.170.350.360.010.71
s208_1202178.69.80.270.280.010.430.490.060.98
s2982030812.214.70.200.240.040.610.740.130.76
s344203427.28.40.330.380.050.360.420.060.74
s349203508.214.20.260.280.020.410.710.300.71
s3822039912.313.10.220.240.020.620.660.040.75
s386203849.615.40.100.110.010.480.770.290.88
s400204246.811.80.090.100.010.340.590.250.76
s4202043012.012.40.290.340.050.600.620.020.83
s420_1204559.610.00.320.26-0.060.480.500.020.77
s4442047413.415.70.280.290.010.670.790.120.77
s510205644.69.90.060.060.000.230.500.270.80
s526205559.311.40.180.200.020.470.570.100.76
s526n205539.110.10.170.200.030.460.510.050.75
s641204638.511.60.500.520.020.430.580.150.72
s7132058116.216.50.210.220.010.810.830.020.72
s820208506.08.00.040.050.010.300.400.100.81
s8322087010.010.10.060.070.010.500.510.010.81
s838208577.18.00.290.330.040.360.400.040.83
s838_1209319.514.60.190.210.020.480.730.260.79
s9532010339.012.10.160.170.010.450.610.160.82
s11962012408.513.40.150.170.020.430.670.240.84
s12382013538.712.30.070.080.010.440.620.180.81
s142320151518.119.60.200.220.020.910.980.080.71
s14882014866.78.90.020.020.000.340.450.110.79
s14942015069.011.30.040.050.010.450.570.120.80
1 Liu Meng, Ouyang Dan-tong, Cai Shao-wei, et al. Efficient zonal diagnosis with maximum satisfiability[J]. Science China Information Sciences, 2018, 61(11):17-30.
2 Liu Meng, Ouyang Dan-tong, Zhang Li-ming. A novel approach for improving quality of health state with difference degree in circuit diagnosis[J]. Applied Intelligence, 2018, 48(11): 4371-4381.
3 刘梦,欧阳丹彤,刘伯文,等. 结合问题特征的分组式诊断方法[J]. 电子学报, 2018, 46(3): 589-594.
Liu Meng, Ouyang Dan-tong, Liu Bo-wen, et al. Grouped diagnosis approach using the feature of problem[J]. Acta Electronica Sinica, 2018, 46(3): 589-594.
4 Wang Yi-yuan, Li Rui-zhi, Zhou Yu-peng, et al. A path cost-based GRASP for minimum independent dominating set problem[J]. Neural Computing & Applications, 2018, 28(1): 143-151.
5 刘思光,欧阳丹彤,张立明. 极小碰集求解中候选解极小性判定方法[J]. 软件学报, 2018, 29(12): 3733-3746.
Liu Si-guang, Ouyang Dan-tong, Zhang Li-ming. Method of minimality-checking of candidate solution for minimal hitting set algorithm[J]. Journal of software, 2018, 29(12): 3733-3746.
6 赵剑,欧阳丹彤,王晓宇,等. 基于模型的混杂系统中控制器故障诊断方法[J]. 吉林大学学报:工学版, 2011, 41(1):155-159.
Zhao Jian, Ouyang Dan-tong, Wang Xiao-yu, et al. Model-based diagnosis of controller fault in hybrid system[J]. Journal of Jilin University(Engineering and Technology Edition), 2011, 41(1):155-159.
7 Adapa R, Tragoudas S, Michael M K. Accelerating diagnosis via dominance relations between sets of faults[C]∥IEEE Vlsi Test Symposium, Berkeley, 2007: 219-224.
8 刘红,孙爽滋,王庆元,等. 基于PSO的模拟电路故障信息特征提取[J]. 吉林大学学报:工学版, 2015, 45(2): 675-680.
Liu Hong, Sun Shuang-zi, Wang Qing-yuan, et al. PSO based feature extraction method for analog circuit fault information[J]. Journal of Jilin University(Engineering and Technology Edition), 2015, 45(2): 675-680.
9 Lavo D B, Chess B, Larrabee T, et al. Probabilistic mixed-model fault diagnosis[C]∥IEEE International Test Conference, Washington, 1998:1084-1093.
10 Venkataraman S, Drummonds S B. POIROT: a logic fault diagnosis tool and its applications[C]∥International Test Conference, Atlantic City, 2002:253-262.
11 Holst S, Wunderlich H J. Adaptive debug and diagnosis without fault dictionaries[J]. Journal of Electronic Testing, 2009, 25(4/5): 259-268.
12 Tang X, Cheng W T, Guo R, et al. Diagnosis of multiple physical defects using logic fault models[C]∥IEEE Asian Test Symposium, Shanghai, China, 2010:94-99.
13 Pomeranz I. OBO: an output-by-output scoring algorithm for fault diagnosis[C]∥IEEE Computer Society Annual Symposium on VLSI, Tampa, 2014:314-319.
14 Pomeranz I. Improving the accuracy of defect diagnosis by considering fewer tests[J]. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2014, 33(12): 2010-2014.
15 Brglez F, Bryan D, Kozminski K. Combinational profiles of sequential benchmark circuits[C]∥Proceedings of IEEE International Symposium on Circuits and Systems, Portland, 1989: 1929-1934.
16 Brglez F, Fujiwara H. A neutral netlist of 10 combinational benchmark circuits and a target translator in fortran[C]∥Proceedings of IEEE International Symposium on Circuits and Systems, Kyoto, 1985:695-698.
[1] 朱小龙,谢忠. 基于机器学习的地理空间数据抽取算法[J]. 吉林大学学报(工学版), 2021, 51(3): 1011-1016.
[2] 魏晓辉,周长宝,沈笑先,刘圆圆,童群超. 机器学习加速CALYPSO结构预测的可行性[J]. 吉林大学学报(工学版), 2021, 51(2): 667-676.
[3] 潘凤文,弓栋梁,高莹,徐明伟,麻斌. 基于锂离子电池线性化模型的电流传感器故障诊断[J]. 吉林大学学报(工学版), 2021, 51(2): 435-441.
[4] 周炳海,吴琼. 基于多目标的机器人装配线平衡算法[J]. 吉林大学学报(工学版), 2021, 51(2): 720-727.
[5] 顾天奇,胡晨捷,涂毅,林述温. 基于移动最小二乘法的稳健重构方法[J]. 吉林大学学报(工学版), 2021, 51(2): 685-691.
[6] 许骞艺,秦贵和,孙铭会,孟诚训. 基于改进的ResNeSt驾驶员头部状态分类算法[J]. 吉林大学学报(工学版), 2021, 51(2): 704-711.
[7] 王小玉,胡鑫豪,韩昌林. 基于生成对抗网络的人脸铅笔画算法[J]. 吉林大学学报(工学版), 2021, 51(1): 285-292.
[8] 方明,陈文强. 结合残差网络及目标掩膜的人脸微表情识别[J]. 吉林大学学报(工学版), 2021, 51(1): 303-313.
[9] 宋元,周丹媛,石文昌. 增强OpenStack Swift云存储系统安全功能的方法[J]. 吉林大学学报(工学版), 2021, 51(1): 314-322.
[10] 赵宏伟,刘晓涵,张媛,范丽丽,龙曼丽,臧雪柏. 基于关键点注意力和通道注意力的服装分类算法[J]. 吉林大学学报(工学版), 2020, 50(5): 1765-1770.
[11] 管乃彦,郭娟利. 基于姿态估计算法的组件感知自适应模型[J]. 吉林大学学报(工学版), 2020, 50(5): 1850-1855.
[12] 李阳,李硕,井丽巍. 基于贝叶斯模型与机器学习算法的金融风险网络评估模型[J]. 吉林大学学报(工学版), 2020, 50(5): 1862-1869.
[13] 周炳海,何朝旭. 基于线边集成超市的混流装配线动态物料配送调度[J]. 吉林大学学报(工学版), 2020, 50(5): 1809-1817.
[14] 蒋磊,管仁初. 基于多目标进化算法的人才质量模糊综合评价系统设计[J]. 吉林大学学报(工学版), 2020, 50(5): 1856-1861.
[15] 张根保,李浩,冉琰,李裘进. 一种用于轴承故障诊断的迁移学习模型[J]. 吉林大学学报(工学版), 2020, 50(5): 1617-1626.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!