Abstract：In view of the non-stationary and nonlinear characteristics of the vibration of hydropower units, the revised fruit fly algorithm (RFOA) was used to optimize the generalized regression neural network model (RFOA-GRNN).By improving the searching step size and odor concentration determination formula of Drosophila algorithm, the local searching ability and convergence speed of Drosophila algorithm are enhanced. The simulation test of FOA algorithm, DSFOA algorithm and RFOA algorithm is carried out by 8 commonly used benchmark functions. The test results verify the effectiveness of RFOA algorithm. Three optimization algorithms were used to optimize the smoothing factor of GRNN, and the smoothing factor after optimization was substituted into the GRNN model to predict the vibration of hydropower units. The results show that, compared with FOA-GRNN and DSFOA-GRNN, the maximum relative error of RFOA-GRNN prediction model is reduced by 99.96% and 99.28%, respectively. It can be concluded that the prediction accuracy and stability of RFOA-GRNN model are better than the other two models, which verifies the effectiveness of this model. The application of the method in the research of state trend prediction of hydroelectric units can help the maintenance personnel to detect the faults of hydroelectric units in advance and repair them in time so as to ensure the safe and stable operation of the hydroelectric units.
王继选，胡润志，管一，张少恺，曹庆皎，王利英. 基于RFOA优化GRNN的水电机组振动预测[J]. 振动与冲击, 2021, 40(21): 120-126.
WANG Jixuan, HU Runzhi, GUAN Yi, ZHANG Shaokai, CAO Qingjiao, WANG Liying. Vibration prediction of hydropower unit based on RFOA-GRNN. JOURNAL OF VIBRATION AND SHOCK, 2021, 40(21): 120-126.
[1] 徐永干， 冉恒， 苟鑫， 等． 基于广义S变换和QPSO-SVM的水电机组振动故障诊断方法［J］． 智慧电力， 2020，48（02)： 38-44．
Xu Yonggan， Ran Heng， Gou Xin， et al． Vibration Fault Diagnosis Method of Hydroelectric Unit Based on Generalized S-Transform and QPSO-SVM ［J］． Smart Electricity， 2020， 48（02)： 38-44．
[2] 罗兴锜，朱国俊，冯建军．水轮机技术进展与发展趋势[J] ．水力发电学报，2020，39(08)：1-18．
Luo Xingqi， Zhu Guojun， Feng Jianjun．Progress and Development Trend of Hydraulic Turbine Technology [J] ．Journal of Hydroelectric Engineering， 2020， 39 (08) ：1-18．
[3] 罗萌．水电机组振动故障诊断与趋势预测研究[D] ．华中科技大学，2017．
LUO Meng． Research on Vibration Fault Diagnosis and Trend Prediction of Hydroelectric Unit [D] ．Huazhong University of Science and Technology，2017．
[4] 李辉， 范智超， 李华， 等． 基于SVD和DBN的水电机组故障诊断［J］． 水力发电学报， 2020 ， 39（12）：104-112．
Li Hui， Fan Zhichao， Li Hua， et al． Fault Diagnosis of Hydroelectric Unit Based on SVD and DBN［J］． Journal of Hydroelectric Engineering， 2020，39 (12) ： 104-112．
[5] 李辉， 范智超， 李华， 等．基于奇异值分解和深度置信网络的水电机组故障诊断[J/OL].水力发电学报:1-9[2021-03-17].http://kns.cnki.net/kcms/detail/11.2241.TV.20201028.1653.006.html.
Li Hui, Fan Zhichao, Li Hua, et al.Fault Diagnosis of Hydropower Units Based on Singular Value Decomposition and Deep Confidence Network [J/OL]. Journal of hydroelectric power: 1-9 [2021-03-17]. http://kns.cnki.net/kcms/detail/11.2241.TV.20201028.1653.006.html.
[6] Chen H W， Yu Z M， Zhang T， et al． Advances and Challenges of Optical Neural Networks［J］． Chinese Journal of Lasers， 2020， 47（5）： 0500004．
[7] Aslam Bilal， Zafar Adeel， Qureshi Umar Azam et al． Seismic investigation of the northern part of Pakistan using the statistical and neural network algorithms［J］． Environmental Earth Sciences， 2021， 80（2）
[8] Melahat Sevgül Bakay a， B M A． Electricity production based forecasting of greenhouse gas emissions in Turkey with deep learning，support vector machine and artificial neural network algorithms［J］． Journal of Cleaner Production， 2020， (285)：1-18
[9] Wang X． Research on inversion of ecosystem dynamics model parameters based on improved Neural Network algorithm［J］． Microprocessors and Microsystems， 2021，(80)： 103605．
[10] Wu Y， Zheng B， Feng Z， et al．The Vibration Prediction of Hydro-generating Units based Grey Relational Analysis and Fuzzy Support Vector Regression[C]// 2019 4th International Conference on Intelligent Green Building and Smart Grid (IGBSG) ．IEEE，2019．
[11] 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（08）： 40-43．
Jia Chunlei， Liu Bo， Tan Xiaogang， et al． Research on Vibration Trend Prediction of Hydroelectric Unit Based on BP Neural Network［J］． Hydropower and New Energy， 2020， 34（08）： 40-43．
[12] 田源，张彼德，刘代伟，等．基于果蝇优化算法的GRNN水电机组状态趋势预测[J] ． 水电能源科学，2012，30(12)：127-129．
Tian Yuan， Zhang Peide， Liu Daiwei，et al．State Trend Prediction of GRNN Hydropower Units Based on Drosophila Optimization Algorithm [J] ．Hydropower and Energy Science, 2012，30 (12) ：127-129．
[13] 戈涛， 张馨． 一种新型的改进果蝇优化算法［J］． 现代计算机， 2019（29）： 16-20．
Ge Tao， Zhang Xin． A Novel Improved Drosophila Optimization Algorithm ［J］． Modern Computers， 2019 (29)： 16-20．
[14] Xue Pei． Application of GRNN Neural Network in Grain Yield Prediction． 2020， 10（04）： 247-253．
[15] A． Saravanakumar， L． Rajeshkumar， D． Balaji, et al． Prediction of Wear Characteristics of AA2219-Gr Matrix Composites Using GRNN and Taguchi-Based Approach． 2020： 1-9．
[16] Ling Qiao， ZiboWang， Jing chuan Zhu． Application of improved GRNN model to predict interlamellar spacing and mechanical properties of hypereutectoid steel． 2020， 792（C）．
[17] Pan W C． A new Fruit Fly Optimization Algorithm： Taking the financial distress model as an example［J］． Knowledge-Based Systems， 2012， 26（3）： 69-74．
[18] 皮骏， 马圣， 张奇奇，等． 基于改进果蝇算法优化的GRNN航空发动机排气温度预测模型［J］． 航空动力学报， 2019， 34（01）：8-17．
Pi Jun， Ma Sheng， Zhang Qiqi， et al． Exhaust Temperature Prediction Model of GRNN Aero-engine Based on Improved Fruit Fly Algorithm ［J］．Journal of Aerospace Power， 2019，34 (01)： 8-17．
[19] Wang L F， Deng L， Liu P． Improved Fruit Fly Optimization based Hysteresis Bouc-Wen Model identification of piezoelectric precision positioning stages［J］． Computer Engineering and Applications， 2020， 56(02)： 242-272．
[20] 南敬昌，曹馨元，高明明，等． 改进果蝇算法优化GRNN的双陷波超宽带天线建模[J/OL] ． 激光与光电子学进展:1-17[2021-05-21].http://kns.cnki.net/kcms/detail/31.1690.TN.20200828.0941.002.html.
Nan Jingchang, Cao Xinyuan, Gao Mingming, et al.Improved Drosophila Algorithm for Optimizing GRNN Dual Bitch UWB Antenna Modeling [J/OL].Advances in lasers and optoelectronics:1-17[2021-05-21].http://kns.cnki.net/kcms/detail/31.1690.TN.20200828.0941.002.html.
