基于关联规则和多元状态估计的汽轮机故障预警算法

doi:10.13229/j.cnki.jdxbgxb.20230667

摘要/Abstract

摘要：

为准确实现汽轮机故障预警，提出一种基于关联规则和多元状态估计的汽轮机故障预警算法。利用关联规则从历史数据中挖掘不同类型的汽轮机故障特征，构建原始决策表；对关联规则挖掘结果展开属性约简，提取最佳故障特征约简集合；采用最佳属性集合组合的约简决策表，对不同类型汽轮机故障信息展开分类。基于汽轮机故障历史数据和实时监测数据组建动态记忆矩阵，使用多元状态估计方法计算汽轮机故障状态，利用非线性欧氏距离计算故障特征向量与观测数据估计偏离距离。利用相似度函数对汽轮机的状态展开预估，设定故障报警阈值，实现汽轮机故障预警。测试结果证明，采用本文算法可准确划分汽轮机故障类型，预估值与实际值基本吻合，可精准实现汽轮机故障预警。

关键词: 关联规则, 多元状态估计, 汽轮机故障预警

Abstract:

In order to accurately achieve steam turbine fault warning， a steam turbine fault warning algorithm based on association rules and multivariate state estimation is proposed. Mining different types of turbine fault features from historical data using association rules to construct original decision tables； Conduct attribute reduction on the results of association rule mining and extract the optimal set of fault feature reduction； Using the optimal attribute set combination reduction decision table to classify different types of turbine fault information. Based on historical data of steam turbine faults and real-time monitoring data， a dynamic memory matrix is constructed， and the fault state of the steam turbine is calculated using multivariate state estimation method. The fault feature vector is calculated using nonlinear Euclidean distance to estimate the deviation distance from the observed data. Use similarity function to estimate the state of the steam turbine， set fault alarm threshold， and achieve steam turbine fault warning. The test results show that the proposed algorithm can accurately classify the types of steam turbine faults， and the estimated values are basically consistent with the actual values， which can accurately achieve steam turbine fault warning.

Key words: association rules, multivariate state estimation, steam turbine fault warning

中图分类号:

TK267

邹红波,张馨煜,李奇隆. 基于关联规则和多元状态估计的汽轮机故障预警算法[J]. 吉林大学学报(工学版), 2024, 54(11): 3283-3288.

Hong-bo ZOU,Xin-yu ZHANG,Qi-long LI. Turbine fault warning algorithm based on association rules and multivariate state estimation[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(11): 3283-3288.

图/表 6

表1

图1

表2

图2

图3

表3

参考文献 10

1	向玲, 朱浩伟, 丁显,等. 基于CAE与BiLSTM结合的风电机组齿轮箱故障预警方法研究[J]. 动力工程学报, 2022, 42(6): 514-521.
	Xiang Ling, Zhu Hao-wei, Ding Xian, et al. Research on fault warning method of wind turbine gearbox based on CAE and BiLSTM[J]. Journal of Chinese Society of Power Engineering, 2022, 42(6): 514-521.
2	杨锡运, 邓子琦, 康宁. 融合集合经验模态分解与宽度学习的齿轮箱故障预警方法[J]. 计算机集成制造系统, 2022, 28(6): 1835-1843.
	Yang Xi-yun, Deng Zi-qi, Kang Ning. Early warning method of gearbox fault based on EEMD and broad learning algorithm[J]. Computer Integrated Manufacturing Systems, 2022, 28(6): 1835-1843.
3	谢天, 覃子珍, 杨如意, 等. 基于常模式提取的火电机组通流故障早期预警方法研究[J]. 汽轮机技术, 2023, 65(2): 122-126.
	Xie Tian, Qin Zi-zhen, Yang Ru-yi, et al. Study on early warning method for through-flow faults in thermal power units based on constant pattern extraction[J]. Turbine Technology, 2023, 65(2): 122-126.
4	刘朋印, 谢小荣, 马宁宁,等. 风电次/超同步振荡激发汽轮机组轴系扭振风险的在线评估与预警技术[J]. 中国电机工程学报, 2021, 41(): 52-58.
	Liu Peng-yin, Xie Xiao-rong, Ma Ning-ning, et al. Online assessment and early warning of torsional vibration risk for turbine generators stimulated by sub-/super-synchronous oscillations associated with wind power[J]. Proceedings of the CSEE, 2021, 41(Sup.1): 52-58.
5	王宇飞, 李俊娥, 刘艳丽, 等. 容忍阶段性故障的协同网络攻击引发电网级联故障预警方法[J]. 电力系统自动化, 2021, 45(3): 24-32.
	Wang Yu-fei, Li Jun-e, Liu Yan-li, et al. Staged failure tolerance based early warning method for cascading failures in power grid caused by coordinated cyber attacks[J]. Automation of Electric Power Systems, 2021, 45(3): 24-32.
6	辛春花, 郭艳光, 鲁晓波. 大型数据库中利用强化学习改进treap的关联规则挖掘算法[J]. 计算机应用研究, 2021, 38(1): 88-92.
	Xin Chun-hua, Guo Yan-guang, Lu Xiao-bo. Association rule mining algorithm using improving treap with interpolation algorithm in large database[J]. Application Research of Computers, 2021, 38(1): 88-92.
7	李鑫, 史天运, 常宝,等. 基于优化的MsEclat算法的铁路机车事故故障关联规则挖掘[J]. 中国铁道科学, 2021, 42(4): 155-165.
	Li Xin, Shi Tian-yun, Chang Bao, et al. Association rule mining for railway locomotive accident and fault based on optimized MsEclat algorithm[J]. China Railway Science, 2021, 42(4): 155-165.
8	钟倩漪, 钱谦, 伏云发, 等. 粒子群优化算法在关联规则挖掘中的研究综述[J]. 计算机科学与探索, 2021, 15(5): 777-793.
	Zhong Qian-yi, Qian Qian, Fu Yun-fa, et al. Survey of particle swarm optimization algorithm for association rule mining[J]. Computer Science and Exploration, 2021, 15(5): 777-793.
9	王培培, 孟芸. 多段支持度数据频繁模式关联规则挖掘仿真[J]. 计算机仿真, 2021, 38(5): 282-286.
	Wang Pei-pei, Meng Yun. Simulation of mining frequent pattern association rules of multi-segment support data[J]. Computer Simulation, 2021, 38(5): 282-286.
10	胡杰, 唐静, 谢仕义. 基于实时动态基线的运行设备多元状态估计方法[J]. 热力发电, 2021, 50(2): 125-131.
	Hu Jie, Tang Jing, Xie Shi-yi. Multivariate state estimation technique for equipment running condition using real-time dynamic baseline[J]. Thermal Power Generation, 2021, 50(2): 125-131.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

名称	配置参数
硬件环境	Intel i7 八核CPU
网络环境	DDR 20 GB Infiniband
操作系统	Win l0
节点连接网络	天河-1A
数据集样本大小	35GB
编译器	Ifort V10
仿真平台	MATLAB 2019c
Hadoop	Cloudera Hadop 5.0

故障类型序号	汽轮机故障类型
01	机组主汽压力故障
02	机组高压缸排汽压力故障
03	轴承盖振动故障
04	机组轴向振动故障
05	机组抗燃油总管压力故障
06	机组主蒸汽压力故障
07	低旁入口蒸汽压力故障
08	机组冷油器出口压力故障
09	机组中压缸压力故障
10	机组低压缸压力故障

汽轮机故障类型	均方根误差/%
汽轮机故障类型	本文算法	文献［3］算法	文献［4］算法
01	6.384	7.251	7.652
02	5.221	6.558	6.995
03	6.013	6.420	6.784
04	5.447	6.003	6.357
05	6.852	7.123	7.358
06	6.774	7.018	7.280
07	6.890	7.356	7.474
08	6.113	6.458	7.113
09	6.541	6.779	7.056
10	6.101	6.425	6.716

[1]	马琨,王喆,范文波. 基于改进Apriori算法的学生资助系统精准资助方法[J]. 吉林大学学报(工学版), 2023, 53(11): 3246-3252.
[2]	梁泉,翁剑成,周伟,荣建. 基于关联规则的公共交通通勤稳定性人群辨识[J]. 吉林大学学报(工学版), 2019, 49(5): 1484-1491.
[3]	张君维, 杨静, 张健沛, 张乐君. 基于滑动窗口的敏感关联规则隐藏[J]. 吉林大学学报(工学版), 2013, 43(01): 172-178.
[4]	李松生, 赵燕伟, 顾熙仁. 改进的FUP算法在五金产品质量分析系统中的应用[J]. 吉林大学学报(工学版), 2012, 42(增刊1): 251-254.
[5]	张日明，孙大文 . 数控装备故障模式分析[J]. 吉林大学学报(工学版), 2008, 38(增刊): 123-0125.
[6]	段海滨, 王道波, 于秀芬 . 基于云模型的小生境MAX-MIN相遇蚁群算法[J]. 吉林大学学报(工学版), 2006, 36(05): 803-0808.
[7]	程晓青, 苑森淼. 关联规则试验数据的人工合成[J]. 吉林大学学报(工学版), 2000, (3): 47-50.