Prediction of equipment performance index based on improved chaotic lion swarm optimization–LSTM
- 1 Downloads
The lion swarm optimizer (LSO) algorithm is a novel meta-heuristic, inspired from the social behavior of lions. This paper introduces the chaos theory into the LSO algorithm with the aim of accelerating its global convergence speed. First, detailed studies are carried out on standard constrained benchmark problems with ten different chaotic maps to find out the most efficient one. Then, the improved chaotic lion swarm optimization algorithm is compared with the traditional LSO and some other popular meta-heuristics algorithms. Lastly, this paper uses the improved chaotic lion swarm algorithm to further optimize the LSTM super-parameters for the problem of equipment life prediction. In addition, for the validity of the analysis method, the comparative experiments of several typical time series prediction models and different parameter optimization algorithms are carried out to verify the proposed methods in each part, which proves that the improved chaotic lion group–LSTM model has strong generalization ability and higher accuracy in equipment life prediction.
KeywordsLong short-term memory (LSTM) recurrent neural network Chaotic mapping Hyperparameter optimization Improved chaotic lion swarm optimization algorithm Deep learning
This study was not funded by any other organization.
Compliance with ethical standards
Conflict of interest
Chunwu Wei and Zhe Yang declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- Chen DJ, Gong QW, Jin CY, Zhang J, Wang DM (2013) Short-term wind power prediction using support vector regression based on parameter optimization of adaptive perturbed quantum particle swarm optimization. Power Grid Technol 37(04):974–980Google Scholar
- Hou MZ, Han XL (2003) Application of neural network based on MATLAB in stock market prediction. Syst Eng 02:112–115Google Scholar
- Jia ZQ, Liang YY (2008) Application of GM (1,1) model in life prediction of electronic equipment. Fire Control Command Control 33(11):134–136Google Scholar
- Li S, Luo Y, Zhang MR (2011) Chaotic time series prediction based on BP neural network optimized by genetic algorithm. Comput Eng Appl 47(29):52–55Google Scholar
- Liu HR, Zhao CX, Li X, Wang YX, Guo CJ (2016) A neural network optimization algorithm based on improved genetic algorithm. J Instrum Instrum 37(07):1573–1580Google Scholar
- Liu SJ, Yang Y, Zhou YQ (2018) A kind of Swarm Intelligence Algorithm—Lion Group Algorithm. Pattern Recognit AI 31(05):431–441Google Scholar
- Patan K (2008) Stability and stabilization of locally recurrent networks, p 377. https://doi.org/10.1007/978-3-540-79872-9_5
- Tan MM (2017) Short term traffic flow forecasting based on LSTM and grey model integration. Nanjing University of Posts and Telecommunications, Nanjing, pp 18–36Google Scholar
- Wang LJ, Li H, Fang SB (2016) Short term wind power forecasting model based on artificial fish swarm optimization algorithm and support vector machine. J Electr Eng 11(10):7–12Google Scholar
- Wang RY, Bia HW, Liu WC (2017) Analysis of the influence of random error on inertial navigation system based on RMSE. J Nav Eng Univ 29(06):18–23+27Google Scholar
- Wang X, Wu J, Liu C, Yang H, Du Y, Niu W (2018) Fault time series prediction based on LSTM recurrent neural network. J Beihang Univ 44(4):772–784Google Scholar
- Wen BW, Dong WH, Xie WJ, Ma J (2018) Optimization of random forest parameters based on improved grid search algorithm. Comput Eng Appl 54(10):154–157Google Scholar
- Xiong ZB (2008) Research on forecasting model of RMB exchange rate based on ARIMA fusion neural network. Res Quant Econ Technol Econ 33(11):134–136Google Scholar
- Yi Z, Liao Y, Xiao Feng H, Xue Hui D, Zhu F (2018) Cooperative combat action recognition based on deep space time recurrent neural network. J Syst Simul 30(03):793–800Google Scholar
- Zhang QB, Wang WH, He X (2018) Nonlinear time series prediction of gas turbine monitoring parameters based on RBF neural network. J Nav Eng Univ 30(02):96–99Google Scholar
- Zhou FY, Jin LP, Dong J (2017) A review of convolution neural networks. J Comput Sci 40(06):1229–1251Google Scholar