针对水电机组作为低速旋转设备具有复杂的运行机理,在目前缺乏先验知识、故障样本较少的情况下,运用传统故障诊断方法很难对水电机组的运行状况做出正确判断的问题,提出一种基于集合经验模态分解法和长短期记忆神经网络相结合的水电机组劣化度预测方法。利用水电机组非故障运行期间的数据计算不同工况下的特征参数健康值标准,使用劣化度描述机组运行期间特征量偏离健康值的程度,并通过集合经验模态分解法将原本具有非平稳性的劣化度时间序列分解为若干个平稳的分量序列,最后使用长短期记忆神经网络预测算法对机组劣化度进行预测。预测结果表明,该方法具有较好的预测精度,能准确地预测水电机组的劣化趋势。
Abstract
As a low-speed rotating equipment, the hydroelectric generator has a complicated operating mechanism. In the absence of prior knowledge and few fault samples, it is difficult to make a correct judgment on the operating status of a hydroelectric generator using traditional fault diagnosis methods. In view of the above problems, a method for predicting the degradation degree of hydroelectric generators based on the combination of ensemble empirical mode decomposition （EEMD） and long short-term memory （LSTM） is proposed. Using the data of the hydroelectric generator during non-failure operation to calculate the standard of the health value of the characteristic parameters under different working conditions, using the degree of degradation to describe the degree to which the characteristic value deviates from the health value during the operation of the generator. Furthermore, the EEMD method is used to decompose the original non-stationary degradation time series into several stationary component sequences. Finally, the LSTM prediction algorithm is used to predict the deterioration degree of the generator. The prediction results show that the method has good prediction accuracy and can accurately predict the deterioration trend of hydroelectric generators.
关键词
水电机组 /
劣化 /
人工智能 /
预测 /
长短期记忆神经网络 /
集合经验模态分解
Key words
hydroelectric generators /
deterioration /
artificial intelligence /
prediction /
long short-term memory /
ensemble empirical mode decomposition
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 张炜博. 基于时频分析与非线性熵的水电机组智能故障诊断与状态趋势预测研究[D]. 武汉: 华中科技大学, 2019.
ZHANG W B.Study on intelligent fault diagnosis and state tendency prediction of hydroelectric generator units based on time-frequency analysis and nonlinear entropy[D]. Wuhan: Huazhong University of Science & Technology, 2019.
[2] 姜伟. 水电机组混合智能故障诊断与状态趋势预测方法研究[D]. 武汉: 华中科技大学, 2019.
JIANG W.Study on hybrid intelligent fault diagnosis and state tendency prediction for hydroelectric generator units[D]. Wuhan:Huazhong University of Science & Technology, 2019.
[3] 周叶. 基于新异类检测和支持向量机的水电机组诊断技术研究[D]. 北京: 中国水利水电科学研究院, 2015.
ZHOU Y.Research on hydroelectric generating unit diagnostic technology based on new heterogeneous detection and support vector machine[D]. Beijing: China Institute of Water Resources and Hydropower, 2015.
[4] 周叶, 潘罗平, 曹登峰. 基于概率统计的水电机组状态评估数据特性研究[J]. 水电站机电技术, 2017, 40(7): 22-25.
ZHOU Y, PAN L P, CAO D F.Research on condition evaluation data characteristics of hydropower unit based on probability statistics[J]. Mechanical & electrical technique of hydropower station, 2017, 40(7): 22-25.
[5] 安学利, 潘罗平, 张飞. 水电机组状态退化评估与非线性预测[J]. 电网技术, 2013, 37(5): 1379-1383.
AN X L, PAN L P, ZHANG F.Condition degradation assessment and nonlinear prediction of hydropower unit[J]. Power system technology, 2013, 37(5): 1379-1383.
[6] 田波, 朴在林, 郭丹, 等. 基于改进EEMD-SE-ARMA的超短期风功率组合预测模型[J]. 电力系统保护与控制, 2017, 45(4): 72-79.
TIAN B, PIAO Z L, GUO D, et al.Wind power ultra short-term model based on improved EEMD-SE-ARMA[J]. Power system protection and control, 2017, 45(4): 72-79.
[7] 陈畅, 李晓磊, 崔维玉. 基于LSTM网络预测的水轮机机组运行状态检测[J]. 山东大学学报(工学版), 2019, 49(3): 40-46.
CHEN C, LI X L, CUI W Y.Hydraulic turbine operation status detection based on LSTM network prediction[J]. Journal of Shandong University(engineering science), 2019, 49(3): 40-46.
[8] 雷若冰, 徐箭, 孙辉, 等. 基于相关性分析的风电场群风速分布预测方法[J]. 电力自动化设备, 2016, 36(5): 134-140.
LEI R B, XU J, SUN H, et al.Wind speed distribution forecasting based on correlation analysis for wind farm group[J]. Electric power automation equipment, 2016, 36(5): 134-140.
[9] WANG T, ZHANG M C, YU Q H, et al.Comparing the applications of EMD and EEMD on time-frequency analysis of seismic signal[J]. Journal of applied geophysics, 2012, 83: 29-34.
[10] 王军辉, 贾嵘, 谭泊. 基于EEMD和模糊C均值聚类的风电机组齿轮箱故障诊断[J]. 太阳能学报, 2015, 36(2): 320-324.
WANG J H, JIA R, TAN B.Fault diagnosis of wind turbine's gearbox based on EEMD and fuzzy C means clustering[J]. Acta energiae solaris sinica, 2015, 36(2):320-324.
[11] GREFF K, SRIVASTAVA R K, KOUTNÍK J, et al. LSTM: a search space Odyssey[J]. IEEE transactions on neural networks & learning systems, 2016, 28(10): 2222-2232.
[12] 陆继翔, 张琪培, 杨志宏. 基于CNN-LSTM混合神经网络模型的短期负荷预测方法[J]. 电力系统自动化, 2019, 43(8): 131-137.
LU J X, ZHANG Q P, YANG Z H.Short-term load forecasting method based on CNN-LSTM hybrid neural network model[J]. Automation of electric power system, 2019, 43(8): 131-137.
[13] 潘罗平. 基于健康评估和劣化趋势预测的水电机组故障诊断系统研究[D]. 北京: 中国水利水电科学研究院, 2013.
PAN L P.Study on hydroelectric generating unit fault diagnosis system based on health assessment and deterioration trend forecast[D]. Beijing: China Institute of Water Resources and Hydropower, 2013.
[14] 陆冰鉴, 周鹏, 王兴, 等. 基于EEMD和LSTM的短期风速预测模型研究[J]. 软件工程, 2020, 23(3): 44-48.
LU B J, ZHOU P, WANG X, et al.Research on short-term wind speed forecasting model based on EEMD and LSTM[J]. Software engineering, 2020, 23(3): 44-48.
基金
国家自然科学基金青年项目（51807051）; 江苏省自然科学基金青年项目（BK20180507）; 江苏省“六大人才高峰”资助项目（2014-XNY-008）
PDF(1827 KB)
