基于IMSGP-WEDI的水电机组故障预警方法

PDF(2329 KB)

振动与冲击 ›› 2024, Vol. 43 ›› Issue (8) : 52-60.

论文

曹超凡1，李明亮2，蒋双云1，张广涛3，李中梁1，卢娜1

作者信息 +

Fault warning method of a hydropower unit based on IMSGP-WEDI

CAO Chaofan1，LI Mingliang2，JIANG Shuangyun1，ZHANG Guangtao3，LI Zhongliang1，LU Na1

Author information +

文章历史 +

摘要

水电机组故障预警指标对于机组早期故障预警时间影响较大，而当前预警指标多基于单传感器信息构建，且其特征信息单一，难以更全面地表征机组运行状态，针对此问题，提出了一种基于集成多传感器遗传规划（Integrated Multi-Sensor Genetic Programming, IMSGP）与权重欧式距离指标（Weighted Euclidean Distance Index, WEDI）的水电机组故障预警方法。首先，将多传感器信号进行预处理，剔除干扰信息；然后从预处理后的信号中提取多元特征，构建原始预警特征集；接下来利用复合检测指数（Composite Detection Index, CDI）进行特征选择，并利用IMSGP进行特征构造；最后结合主成分分析（Principal Component Analysis，PCA）与欧式距离构建WEDI，判别机组异常状态。通过对水电机组实测数据的分析，证明了提出的方法可及时发现早期故障，实现故障预警。

Abstract

The early warning of faults in hydropower units is greatly affected by the warning indicators. However, these indicators are mostly based on single sensor signal and information, and therefore limited in their abilities to comprehensively characterize the unit operating status. To address this issue, a method combining Integrated Multi-Sensor Genetic Programming (IMSGP) and Weighted Euclidean Distance Index (WEDI) is proposed. First, multiple sensor signals are preprocessed to eliminate interference. Next, multivariate features are extracted from the preprocessed signals to construct the original warning feature set. Then, the Composite Detection Index (CDI) is used for feature selection, and IMSGP is investigated for feature construction. Finally, Principal Component Analysis (PCA) and the Euclidean distance are used to construct WEDI for identifying abnormal states of the unit. Through analysis of hydropower unit data, the ability of the proposed method on detecting early faults and achieving effective fault warning were verified.

导出引用

曹超凡1，李明亮2，蒋双云1，张广涛3，李中梁1，卢娜1. 基于IMSGP-WEDI的水电机组故障预警方法[J]. 振动与冲击, 2024, 43(8): 52-60

CAO Chaofan1，LI Mingliang2，JIANG Shuangyun1，ZHANG Guangtao3，LI Zhongliang1，LU Na1. Fault warning method of a hydropower unit based on IMSGP-WEDI[J]. Journal of Vibration and Shock, 2024, 43(8): 52-60

参考文献

[1] 潘罗平, 安学利, 周叶. 基于大数据的多维度水电机组健康评估与诊断[J]. 水利学报, 2018, 49(9): 1178-1186. PAN luo-ping, AN xue-li, ZHOU ye. Multi-dimension health assessment and diagnosis of hydropower unit based on big data [J]. Journal of Hydraulic Engineering, 2018, 49(9): 1178-1186. [2] 张彬桥, 杨文娟, 葛苏叶, 等. 水电站运维本体知识库构建及应用[J]. 水力发电学报, 2022, 41(10): 86-98. ZHANG bin-qiao, YANG wen-juan, GE su-ye, et al. Construction and application of ontology knowledge base for hydropower plant operation and maintenance [J]. Journal of Hydroelectric Engineering, 2022, 41(10): 86-98. [3] 王继选, 胡润志, 管一, 等. 基于 RFOA 优化 GRNN 的水电机组振动预测[J]. 振动与冲击, 2021. WANG ji-xuan, HU run-zhi, GUAN yi, et al. Vibration prediction of hydropower unit based on RFOA-GRNN [J]. Journal of Vibration and Shark, 2021. [4] 贾春雷, 刘博, 谭小刚, 等. 基于 BP 神经网络的水电机组振动趋势预测研究[J]. 水电与新能源, 2020, 34(8): 40-43. JIA chun-lei, LIU bo, TAN xiao-gang, et al. Research on vibration trend prediction of hydroelectric unit based on BP neural network[J]. Hydropower and Energy Science, 2020,34(8):40-43. [5] 胡晓, 肖志怀, 刘东, 等. 基于 EEMD-SDCC Ⅰ-HMM 的水电机组振动故障识别方法[J]. 振动与冲击, 2022. HU xiao, XIAO zhi-huai, LIU dong, et al. Vibration fault identification method of hydropower unit based on EEMD-SDCC-HMM[J]. Journal of Vibration and Shock, 2022. [6] 江亚兰. 水电机组状态趋势预测与智能预警方法研究[D]. 武汉：华中科技大学, 2021. [7] 鹿卫国, 戴亚平, 高峰. 一种基于概率分布估计的水电机组故障预警方法[J]. 中国电机工程学报, 2005, 25(4): 94-98. LU wei-guo, DAI Ya-ping, GAO feng. A hydroelectric-cenerator unit fault early warning method based on distribution estimation[J]. Proceedings of the CSEE, 2005, 25(4): 94-98. [8] 安学利, 潘罗平, 张飞. 基于三维曲面的抽水蓄能电站机组故障预警模型[J]. 水力发电, 2013, 39(1): 71-74. AN xue-li, PAN luo-ping, ZHANG fei. Early fault warning model of pumped-storage power station unit based on three-dimensional surface[J]. Water Power, 2013, 39(1): 71-74. [9] 刘涛, 刘吉臻, 吕游, 等. 基于多元状态估计和偏离度的电厂风机故障预警[J]. 动力工程学报, 2016, 36(6): 454-460. LIU tao, LIU ji-zhen, LU you, et al. Early fault warning of power plant fans based on MSET and the deviation degree[J]. Journal of Chinese Society of Power Engineering, 2016, 36(6): 454-460. [10] 刘东, 赖旭, 胡晓, 等. 基于振动信号的水电机组状态劣化在线评估方法研究[J]. 水利学报, 2021, 52(4): 461-473. LIU dong, LAI xu, HU xiao, et al. Research on on-line evaluation method of state degradation of hydropower unit based on vibration signal[J]. Journal of Hydraulic Engineering, 2021, 52(4): 461-473. [11] Mao W, Wang Y, Kou L, et al. A New Deep Tensor Autoencoder Network for Unsupervised Health Indicator Construction and Degradation State Evaluation of Metro Wheel[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-15. [12] Liu X, Chen G, Wei X, et al. A rolling bearing fault evolution state indicator based on deep learning and its application[J]. Journal of Mechanical Science and Technology, 2023: 1-15. [13] Tsai J T, Chou P Y, Chou J H. Performance comparisons between PCA-EA-LBG and PCA-LBG-EA approaches in VQ codebook generation for image compression[J]. International Journal of Electronics, 2015, 102(11): 1831-1851. [14] Morin L, Gilormini P, Derrien K. Generalized Euclidean distances for elasticity tensors[J]. Journal of Elasticity, 2020, 138: 221-232. [15] Krawiec K. Genetic programming-based construction of features for machine learning and knowledge discovery tasks[J]. Genetic Programming and Evolvable Machines, 2002, 3: 329-343. [16] Song L, Wang H, Chen P. Intelligent diagnosis method for machinery by sequential auto-reorganization of histogram[J]. ISA transactions, 2019, 87: 154-162. [17] Zhang D, Wang H, Feng Y, et al. Fast Fourier Transform (FFT) Using Flash Arrays for Noise Signal Processing[J]. IEEE Electron Device Letters, 2022, 43(8): 1207-1210. [18] Li K, Chen P, Wang S. An intelligent diagnosis method for rotating machinery using least squares mapping and a fuzzy neural network[J]. Sensors, 2012, 12(5): 5919-5939. [19] 李龙,燕旭朦,张钰声等.小样本锂电池数据SOC估算方法[J/OL].西安交通大学学报：1-9[2023-08-07]. [20] Nielsen F. On a generalization of the Jensen–Shannon divergence and the Jensen–Shannon centroid[J]. Entropy, 2020, 22(2): 221. [21] Chen W, Li J, Wang Q, et al. Fault feature extraction and diagnosis of rolling bearings based on wavelet thresholding denoising with CEEMDAN energy entropy and PSO-LSSVM[J]. Measurement, 2021, 172: 108901. [22] 孙曙光, 庞毅, 王景芹, 等. 改进的 EEMD 去噪方法及其在谐波检测中的应用研究[J]. 电工电能新技术, 2016, 35(4): 67-74. SUN shu-guang, PANG Yi, WANG jing-qin. Study of improved EEMD denoising method and application in harmonic detection[J].Advanced Technology of Electrical Engineering and Energy, 2016, 35(4): 67-74.