A combined multi-objective optimization model for degradation trend prediction of pumped storage unit

Abstract Pumped storage unit (PSU) operated under the combination of different condition, which may cause equipment wear, fatigue and fault issues. It is difficult to achieve accurate and stable degradation trend prediction (DTP) considering only either the accuracy or stability. In this paper, a combined multi-objective optimization model is proposed for DTP of PSU. Firstly, the health model of PSU is constructed with back propagation neural network (BPNN) and condition parameters of active power, working head and guide vane opening. Subsequently, the performance degradation index (PDI) is developed to characterize degradation level of PSU. Then, considering high accuracy and strong stability in predicted model, kernel extreme learning machine (KELM) is optimized by multi-objective particle swarm optimization (MOPSO) to achieve DTP. To validate the effectiveness of the proposed model, the monitoring data collected from PSU in China is taken as case studies. The results demonstrate that the proposed model outperforms other comparison models in terms of predicting accuracy and stability.

[1]  M. Ehyaei,et al.  Optimization of parabolic through collector (PTC) with multi objective swarm optimization (MOPSO) and energy, exergy and economic analyses , 2019, Journal of Cleaner Production.

[2]  Mozhde Heydarianasl,et al.  Design optimization of electrostatic sensor electrodes via MOPSO , 2020 .

[3]  Jianzhou Wang,et al.  A novel hybrid system based on a new proposed algorithm-Multi-Objective Whale Optimization Algorithm for wind speed forecasting , 2017 .

[4]  Yi Shang,et al.  Deep learning for prognostics and health management: State of the art, challenges, and opportunities , 2020 .

[5]  Bin Ran,et al.  Day-ahead traffic flow forecasting based on a deep belief network optimized by the multi-objective particle swarm algorithm , 2019, Knowl. Based Syst..

[6]  Xin Hu,et al.  A Hybrid Model For Predicting The Degradation Trend Of Hydropower Units Based On Deep Learning , 2019, 2019 Prognostics and System Health Management Conference (PHM-Qingdao).

[7]  Allan J. Volponi,et al.  Gas Turbine Engine Health Management: Past, Present, and Future Trends , 2014 .

[8]  Diego Cabrera,et al.  A review on data-driven fault severity assessment in rolling bearings , 2018 .

[9]  Nor Ashidi Mat Isa,et al.  A constrained multi-swarm particle swarm optimization without velocity for constrained optimization problems , 2020, Expert Syst. Appl..

[10]  Dawei Zhao,et al.  Multi-label learning with kernel extreme learning machine autoencoder , 2019, Knowl. Based Syst..

[11]  Yang Zheng,et al.  Adaptive condition predictive-fuzzy PID optimal control of start-up process for pumped storage unit at low head area , 2018, Energy Conversion and Management.

[12]  Qiang Miao,et al.  A parameter-adaptive VMD method based on grasshopper optimization algorithm to analyze vibration signals from rotating machinery , 2018, Mechanical Systems and Signal Processing.

[13]  Chen Wang,et al.  Research and application of a combined model based on multi-objective optimization for multi-step ahead wind speed forecasting , 2017 .

[14]  Hongmin Li,et al.  Multi-objective algorithm for the design of prediction intervals for wind power forecasting model , 2019, Applied Mathematical Modelling.

[15]  Xiangdong Wang,et al.  Multiscale local features learning based on BP neural network for rolling bearing intelligent fault diagnosis , 2020, Measurement.

[16]  Jack Chin Pang Cheng,et al.  Data-driven predictive maintenance planning framework for MEP components based on BIM and IoT using machine learning algorithms , 2020 .

[17]  Chen Wang,et al.  Research and application of a hybrid model based on multi-objective optimization for electrical load forecasting , 2016 .

[18]  Hao Zhong,et al.  Vibration trend measurement for a hydropower generator based on optimal variational mode decomposition and an LSSVM improved with chaotic sine cosine algorithm optimization , 2018, Measurement Science and Technology.

[19]  Alibakhsh Kasaeian,et al.  Optimizing a hybrid wind-PV-battery system using GA-PSO and MOPSO for reducing cost and increasing reliability , 2017, Energy.

[20]  Lazaros G. Papageorgiou,et al.  A regression tree approach using mathematical programming , 2017, Expert Syst. Appl..

[21]  Rob J Hyndman,et al.  Another look at measures of forecast accuracy , 2006 .

[22]  Wenlong Fu,et al.  A state tendency measurement for a hydro-turbine generating unit based on aggregated EEMD and SVR , 2015 .

[23]  Li Bai,et al.  Performance predictions of ground source heat pump system based on random forest and back propagation neural network models , 2019, Energy Conversion and Management.

[24]  Wei Jiang,et al.  Multistep Degradation Tendency Prediction for Aircraft Engines Based on CEEMDAN Permutation Entropy and Improved Grey-Markov Model , 2019, Complex..

[25]  Yaguo Lei,et al.  Machinery health prognostics: A systematic review from data acquisition to RUL prediction , 2018 .

[26]  Zhihao Shang,et al.  A novel wind speed forecasting model based on moving window and multi-objective particle swarm optimization algorithm , 2019 .

[27]  Chu Zhang,et al.  Multi-Objective Optimization for Flood Interval Prediction Based on Orthogonal Chaotic NSGA-II and Kernel Extreme Learning Machine , 2019, Water Resources Management.

[28]  Xinyu Shao,et al.  Data-driven remaining useful life prediction via multiple sensor signals and deep long short-term memory neural network. , 2020, ISA transactions.

[29]  Jie Liu,et al.  Vibration Tendency Prediction of Hydroelectric Generator Unit Based on Fast Ensemble Empirical Mode Decomposition and Kernel Extreme Learning Machine with Parameters Optimization , 2018, 2018 11th International Symposium on Computational Intelligence and Design (ISCID).

[30]  Li Yang,et al.  Condition parameter degradation assessment and prediction for hydropower units using Shepard surface and ITD , 2014 .

[31]  Liang Guo,et al.  Machinery health indicator construction based on convolutional neural networks considering trend burr , 2018, Neurocomputing.

[32]  M.N.S. Swamy,et al.  An improved scheme for digital mammogram classification using weighted chaotic salp swarm algorithm-based kernel extreme learning machine , 2020, Appl. Soft Comput..

[33]  Khanh T.P. Nguyen,et al.  Health monitoring of bearing and gear faults by using a new health indicator extracted from current signals , 2019, Measurement.

[34]  X. An,et al.  Characteristic parameter degradation prediction of hydropower unit based on radial basis function surface and empirical mode decomposition , 2015 .

[35]  Inés María Galván,et al.  Multi-objective evolutionary optimization of prediction intervals for solar energy forecasting with neural networks , 2017, Inf. Sci..

[36]  R. Sivaranjani,et al.  Speckle noise removal in SAR images using Multi-Objective PSO (MOPSO) algorithm , 2019, Appl. Soft Comput..

[37]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[38]  Jiakai Ding,et al.  Gear Fault Diagnosis Based on Genetic Mutation Particle Swarm Optimization VMD and Probabilistic Neural Network Algorithm , 2020, IEEE Access.

[39]  Weijia Yang,et al.  A coordinated optimization framework for flexible operation of pumped storage hydropower system: Nonlinear modeling, strategy optimization and decision making , 2019, Energy Conversion and Management.

[40]  Hooshang Jazayeri-Rad,et al.  Enhancing the performance of a parallel nitrogen expansion liquefaction process (NELP) using the multi-objective particle swarm optimization (MOPSO) algorithm , 2019, Energy.

[41]  Jia Minping,et al.  Application of CSA-VMD and optimal scale morphological slice bispectrum in enhancing outer race fault detection of rolling element bearings , 2019, Mechanical Systems and Signal Processing.

[42]  Haiping Wu,et al.  Multi-step wind speed forecasting using EWT decomposition, LSTM principal computing, RELM subordinate computing and IEWT reconstruction , 2018, Energy Conversion and Management.

[43]  Harwinder Singh,et al.  Evaluation and analysis of occupational ride comfort in rotary soil tillage operation , 2019, Measurement.

[44]  Li Yang,et al.  Nonlinear prediction of condition parameter degradation trend for hydropower unit based on radial basis function interpolation and wavelet transform , 2015 .

[45]  Jiakai Ding,et al.  GMPSO-VMD Algorithm and Its Application to Rolling Bearing Fault Feature Extraction , 2020, Sensors.

[46]  Q. Xiao,et al.  Modeling heat transfer properties in an ORC direct contact evaporator using RBF neural network combined with EMD , 2019, Energy.

[47]  Mohammad Nazri Mohd. Jaafar,et al.  Multi-objective particle swarm optimization of flat plate solar collector using constructal theory , 2020 .

[48]  Jianhua Gu,et al.  Evolving an optimal kernel extreme learning machine by using an enhanced grey wolf optimization strategy , 2019, Expert Syst. Appl..

[49]  Wennian Yu,et al.  Remaining useful life estimation using a bidirectional recurrent neural network based autoencoder scheme , 2019, Mechanical Systems and Signal Processing.