[1]方 涛,刘 涛,李 龙.基于自适应步长 FOA-SVM 算法的卡泵故障诊断[J].计算机技术与发展,2021,31(04):153-157.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 026]
　FANG Tao,LIU Tao,LI Long.Research on Fault Diagnosis of Stuck Pump Based on AdaptiveStep Size FOA-SVM Algorithm[J].,2021,31(04):153-157.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 026]
点击复制

基于自适应步长 FOA-SVM 算法的卡泵故障诊断()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年04期
页码:
153-157
栏目:
应用前沿与综合
出版日期:
2021-04-10

文章信息/Info

Title:
Research on Fault Diagnosis of Stuck Pump Based on AdaptiveStep Size FOA-SVM Algorithm
文章编号:
1673-629X(2021)04-0153-05
作者:
方 涛; 刘 涛; 李 龙
东北石油大学 计算机与信息技术学院,黑龙江 大庆 163318
Author(s):
FANG Tao; LIU Tao; LI Long
School of Computer and Information Technology,Northeast Petroleum University,Daqing 163318,China
关键词:
果蝇优化算法; 自适应步长; 支持向量机; 示功图; 机采井卡泵; 故障诊断
Keywords:
drosophila optimization algorithm;  adaptive step size;  support vector machine;  indicator diagram;  mechanical well stuckpump; fault diagnosis
分类号:
TP301. 6
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 04. 026
摘要:
为了提高机采井卡泵故障诊断精度,提出一种基于自适应步长 FOA-SVM 混合算法模型的机采井卡泵诊断方法。在支持向量机对示功图诊断分类的基础上,引入改进的自适应步长果蝇优化算法( AS_FOA) 对 SVM 的惩罚因子和核函数参数进行寻优,避免人为选择参数的盲目性。 为了实现果蝇优化算法的全局与局部寻优能力的平衡,应用自适应步长方法对其进行改进,使果蝇算法能够根据上一代的适应度值和当前迭代次数来自适应改变果蝇个体搜索步长。 通过采油厂真实示功图数据进行仿真实验,比较 AS_FOA、FOA、GA 三种算法在支持向量机参数寻优中的性能。 实验结果表明,AS_FOA 收敛速度更快,寻优能力更佳。 与其他算法相比,AS_FOA-SVM 混合算法模型在卡泵故障诊断中准确率更高,泛化能力更强。
Abstract:
In order to improve the fault diagnosis accuracy of stuck pump,a fault diagnosis method based on adaptive step size FOA-SVM hybrid algorithm model is proposed. Based on the classification of indicator diagram diagnosis by support vector machine,an improved adaptive step size drosophila optimization algorithm ( AS_FOA) is introduced to optimize the penalty factor and kernel function parameters of SVM,so as to avoid the blindness of artificial selection of parameters. In order to achieve? ? ?the balance of global and local optimization ability of drosophila optimization algorithm,the adaptive step method is used to improve it,so that the drosophila algorithm can adapt to change the individual search step according to the fitness value of the previous generation and the number of current iterations. Through the simulation experiment of the real indicator diagram data of oil production plant,the performance of AS_FOA,FOA and GA in the pa鄄rameter optimization of support vector machine is compared. The experiment shows that AS_FOA has faster convergence speed and better optimization ability. Compared with other algorithms, AS_FOA_SVM hybrid algorithm model has higher accuracy and stronger generalization ability in the fault diagnosis of stuck pump.

相似文献/References:

[1]刘立群[],韩俊英[],代永强[],等. 果蝇优化算法优化性能对比研究[J].计算机技术与发展,2015,25(08):94.
　LIU Li-qun[],HAN Jun-ying[],DAI Yong-qiang[],et al. Comparative Study on Optimization Performance of Fruit Fly Optimization Algorithm [J].,2015,25(04):94.
[2]江浩,阮奇. 基于变尺度法和自适应步长的布谷鸟搜索算法[J].计算机技术与发展,2015,25(10):38.
　JIANG Hao,RUAN Qi. A Cuckoo Search Algorithm Based on Variable Metric Method and Adaptive Step[J].,2015,25(04):38.
[3]牛勇力[],吴清[][],李平娜[],等. 自适应修改权重参数的果蝇优化算法[J].计算机技术与发展,2017,27(11):41.
　NIU Yong-li[],WU Qing[][],LI Ping-na[],et al. A Fruit Fly Optimization Algorithm with Adaptive Modifying Weight Parameters[J].,2017,27(04):41.
[4]王全民,杨晶,张帅帅,等.一种基于改进果蝇优化的K-mediods聚类算法[J].计算机技术与发展,2018,28(12):17.[doi:10．3969/j．issn．1673－629X．2018．12．004]
　WANG Quanmin,YANG Jing,ZHANG Shuaishuai.A New K－mediods Clustering Algorithm Based on Improved Fruit Fly Optimization Algorithm[J].,2018,28(04):17.[doi:10．3969/j．issn．1673－629X．2018．12．004]
[5]叶亚荣,贺兴时,张超.基于随机扰动的自适应布谷鸟算法[J].计算机技术与发展,2019,29(05):77.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 017]
　YE Ya-rong,HE Xing-shi,ZHANG Chao.An Adaptive Cuckoo Algorithm Based on Random Disturbance[J].,2019,29(04):77.[doi:10. 3969 / j. issn. 1673-629X. 2019. 05. 017]
[6]彭 铎,张 倩,张腾飞,等.基于坐标优化的 FOA-Amorphous 节点定位算法[J].计算机技术与发展,2023,33(07):91.[doi:10. 3969 / j. issn. 1673-629X. 2023. 07. 014]
　PENG Duo,ZHANG Qian,ZHANG Teng-fei,et al.FOA-Amorphous Node Localization Algorithm Based on Coordinate Optimization[J].,2023,33(04):91.[doi:10. 3969 / j. issn. 1673-629X. 2023. 07. 014]

更新日期/Last Update: 2020-04-10