Prediction of equipment performance index based on improved chaotic lion swarm optimization–LSTM

  • Zhe Yang
  • Chunwu WeiEmail author
Methodologies and Application


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.


Long 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.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.


  1. 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
  2. Fischer T, Krauss C (2018) Deep learning with long short-term memory networks for financial market predictions. Eur J Oper Res 270(2):654–669MathSciNetCrossRefGoogle Scholar
  3. Gandomi AH, Yang X-S (2014) Chaotic bat algorithm. J Comput Sci 5(2):224–232MathSciNetCrossRefGoogle Scholar
  4. Graves A (2012) Supervised sequence labelling with recurrent neural networks. Springer, Berlin, pp 39–45CrossRefGoogle Scholar
  5. He D, He C, Jiang L-G, Zhu H-W, Hu G-R (2001) Chaotic characteristics of a one-dimensional iterative map with infinite collapses. IEEE Trans Circuits Syst I Fundam Theory Appl 48(7):900–906MathSciNetCrossRefGoogle Scholar
  6. Hou MZ, Han XL (2003) Application of neural network based on MATLAB in stock market prediction. Syst Eng 02:112–115Google Scholar
  7. 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
  8. Li Y, Cao H (2018) Prediction for tourism flow based on LSTM neural network. Procedia Comput Sci 129:277–283CrossRefGoogle Scholar
  9. 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
  10. 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
  11. Liu SJ, Yang Y, Zhou YQ (2018) A kind of Swarm Intelligence Algorithm—Lion Group Algorithm. Pattern Recognit AI 31(05):431–441Google Scholar
  12. Ma B, Liu Z, Jiang F, Yan Y, Yuan J, Bu S (2019) Vehicle detection in aerial images using rotation-invariant cascaded forest. IEEE Access 7:59613–59623CrossRefGoogle Scholar
  13. Patan K (2008) Stability and stabilization of locally recurrent networks, p 377.
  14. Sangaiah AK, Medhane DV, Han T, Hossain MS, Muhammad G (2019) Enforcing position-based confidentiality with machine learning paradigm through mobile edge computing in real-time industrial informatics. IEEE Trans Ind Inform. CrossRefGoogle Scholar
  15. 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
  16. 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
  17. 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
  18. 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
  19. 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
  20. 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
  21. 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
  22. 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
  23. Zhou FY, Jin LP, Dong J (2017) A review of convolution neural networks. J Comput Sci 40(06):1229–1251Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of Computer ScienceUniversity of ManchesterManchesterUK
  2. 2.Graduate School of Information and Computer ScienceTaiyuan University of TechnologyTaiyuanChina

Personalised recommendations