Abstract
This paper addresses the identification problem of feedback nonlinear system with time delay (FNTD). A data-driven identification method for the FNTD system based on bidirectional long short-term memory (BiLSTM) networks is proposed. First, considering the long input and output data sequence and the existence of bidirectional features, the BiLSTM network is chosen for identification. In addition, in order to mine the complex nonlinear mapping relationship between input and output, the attention mechanism is introduced into the BiLSTM algorithm to highlight the influence of key factors. The Gaussian kernel function selects the optimal complexity model to enhance the extrapolation performance, and further improves the identification accuracy. Then, the attention-BiLSTM algorithm is proposed. In the simulation, a numerical example and two application examples are implemented. The results show that the attention-BiLSTM method can effectively identify the FNTD system, and is superior to LSTM and BiLSTM in terms of identification accuracy and speed. The proposed attention-BiLSTM method has the highest identification accuracy, and the RMSE is \(5.57\%\) and \(1.05\%\) lower than the LSTM and BiLSTM models, respectively. The \(R^2\) value reaches 0.9997, which is \(16.17\%\) and \(0.77\%\) higher than LSTM and BiLSTM, respectively.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Data availability and access
The data used to support the results of this study are available from the corresponding author upon request.
References
Lu Y, Tang YG, Zhang XG, Wang SE (2020) Parameter identification of fractional order systems with nonzero initial conditions based on block pulse functions. Measurement 158:107684
Guan W, Dong LL, Zhou JM, Han Y, Zhou J (2019) Data-driven methods for operational modal parameters identification: A comparison and application. Measurement 132:238–251
Yang CY, Bu LC, Chen B (2021) Energy modeling and online parameter identification for permanent magnet synchronous motor driven belt conveyors. Measurement 178:109342
Guo J, Jia RZ, Su RN, Zhao YL (2023) Identification of FIR systems with Binary-Valued observations against data tampering attacks. IEEE Transactions on Systems, Man, and Cybernetics: Systems. https://doi.org/10.1109/TSMC.2023.3276352
Li JH, Zong TC, Gu JP (2020) Parameter estimation of Wiener systems based on the particle swarm iteration and gradient search principle. Circ Syst Sig Process 39:3470–3495
Li F, Jia L (2019) Parameter estimation of Hammerstein-Wiener nonlinear system with noise using special test signals. Neurocomputing 344:37–48
Ding S, Wang Z, Zhang J, Fang H, Gu XC (2022) Time delay system identification using controlled recurrent neural network and discrete bayesian optimization. Appl Intell 52:8351–8371
Kou J, Zhang W, Yin M (2016) Novel Wiener models with a time-delayed nonlinear block and their identification. Nonlinear Dyn 85:2389–2404
Ma JX, Ding F, Xiong WL, Yang EF (2017) Combined state and parameter estimation for Hammerstein systems with time delay using the Kalman filtering. Int J Adapt Control Signal Process 31(8):1139–1151
Ma JX, Xiong WL, Chen J, Ding F (2017) Hierarchical identification for multivariate Hammerstein systems by using the modified Kalman filter. IET Control Theory Appl 11(6):857–869
Dong SJ, Yu L, Zhang WA, Chen B (2020) Robust extended recursive least squares identification algorithm for Hammerstein systems with dynamic disturbances. Digit Sig Process 101:102716
Liu HX, Feng YX, Li JH, Luo JC (2022) Robust Petri net controllers for flexible manufacturing systems with multi-type and multi-unit unreliable resources. IEEE Transactions on System Man and Cybernetics. https://doi.org/10.1109/TSMC.2022.3201826
Ding F, Liu XM, Hayat T (2020) Hierarchical least squares identification for feedback nonlinear equation-error systems. J Franklin Inst 357(5):2958–2977
Li JH, Ding F (2011) Maximum likelihood stochastic gradient estimation for Hammerstein systems with colored noise based on the key term separation technique. Comput Math Appl 62(11):4170–4177
Li JH, Zong TC, Lu GP (2022) Parameter identification of Hammerstein-Wiener nonlinear systems with unknown time delay based on the linear variable weight particle swarm optimization. ISA Trans 120:89–98
Mete S, Ozer S, Zorlu H (2016) System identification using Hammerstein model optimized with differential evolution algorithm. Aeu-international J Electron Commun 70(12):1667–1675
Cui T, Xu L, Ding F, Alsaedi A, Hayat T (2020) Maximum likelihood-based adaptive differential evolution identification algorithm for multivariable systems in the state-space form. Int J Adapt Control Signal Process 34(11):1658–1676
Ren G, Yang RH, Yang RY, Zhang P, Yang XZ, Xu CB, Hu BG, Zhang HT, Lu YS, Cai YN (2019) A parameter estimation method for fractional-order nonlinear systems based on improved whale optimization algorithm. Mod Phys Lett B 33(7)
Ghosh S, Maka S (2011) Genetic algorithm based NARX model identification for evaluation of insulin sensitivity. Appl Soft Comput 11(1):221–226
Lu YZ, Yan DP, Levy D (2015) Friction coefficient estimation in servo systems using neural dynamic programming inspired particle swarm search. Appl Intell 43:1–14
Sun H, Luş H, Betti R (2013) Identification of structural models using a modified Artificial Bee Colony algorithm. Comput Struct 116:59–74
Rahmani MR, Farrokhi M (2020) Fractional-order Hammerstein state-space modeling of nonlinear dynamic systems from input-output measurements. ISA Trans 96:177–184
Chang WD (2022) Identification of nonlinear discrete systems using a new Hammerstein model with Volterra neural network. Soft Comput 26:6765–6775
Mehmood A, Zameer A, Chaudhary NI (2020) Design of meta-heuristic computing paradigms for Hammerstein identification systems in electrically stimulated muscle models. Neural Comput Appl 32:12469–12497
Li YR, Chen WX, Chen J, Chen X, Liang J, Du M (2019) Neural network based modeling and control of elbow joint motion under functional electrical stimulation. Neurocomputing 340:171–179
Wang HY, Luo C, Wang XY (2019) Synchronization and identification of nonlinear systems by using a novel self-evolving interval type-2 fuzzy LSTM-neural network. Eng Appl Artif Intell 81:79–93
Ren JC, Liu D, Wan Y (2021) Modeling and application of Czochralski silicon single crystal growth process using hybrid model of data-driven and mechanism-based methodologies. J Process Control 104:74–85
An H, Zhang S, Cui C (2022) Dynamic model identification for adaptive polishing system. Int J Control Autom Syst 20:3110–3120
Xu ZC, Zhang BL, Li DF, Yip WS, To S (2024) Digital-twin-driven intelligent tracking error compensation of ultra-precision machining. Mech Syst Signal Process 219:111630
Zhang CY, Zhang WD, Ying GG, Ying LQ, Hu JL, Chen WM (2024) A deep learning method for heavy vehicle load identification using structural dynamic response. Comput Struct 297:107341
Sun J, Shi W, Yang Z, Yang J, Gui G (2019) Behavioral Modeling and Linearization of Wideband RF Power Amplifiers Using BiLSTM Networks for 5G Wireless Systems. IEEE Trans Veh Technol 68(11):10348–10356
Astroza R, Ebrahimian H, Li Y, Conte JP (2017) Bayesian nonlinear structural FE model and seismic input identification for damage assessment of civil structures. Mech Syst Signal Process 93:661–687
Ding ZH, Yu Y, Xia Y (2023) Nonlinear hysteretic parameter identification using an attention-based long short-term memory network and principal component analysis. 111:4559–4576
Abbasimehr H, Paki R (2022) Improving time series forecasting using LSTM and attention models. J Ambient Intell Human Comput 13:673–691
Lin MQ, Wu J, Meng JH, Wang W, Wu J (2023) State of health estimation with attentional long short-term memory network for lithium-ion batteries. Energy 268:126706
Su LY, Xiong L, Yang JL (2023) Multi-Attn BLS: Multi-head attention mechanism with broad learning system for chaotic time series prediction. Appl Soft Comput 132:109831
Chemali E, Kollmeyer PJ, Preindl M, Ahmed R, Emadi A (2018) Long short-term memory networks for accurate state-of-charge estimation of Li-ion batteries. IEEE Trans Ind Electron 65:6730–6739
Alkadi O, Moustafa N, Turnbull B, Choo KKR (2021) A deep blockchain framework-enabled collaborative intrusion detection for protecting IoT and cloud networks. IEEE Internet Things J 8:9463–9472
Yao H, Liu C, Zhang P, Wu S, Jiang C, Yu S (2022) Identification of encrypted traffic through attention mechanism based long short term memory. IEEE Trans on Big Data 8:241–252
Zhang J, Zhang K, An Y, Luo H, Yin S (2024) An integrated multitasking intelligent bearing fault diagnosis scheme based on representation learning under imbalanced sample condition. IEEE Trans Neural Netw Learn Syst 35:6231–6242
Dong Z, Ji X, Wang J, Gu Y, Wang J, Qi D (2024) ICNCS: Internal cascaded neuromorphic computing system for fast electric vehicle state-of-charge estimation. IEEE Trans Consum Electron 70:4311–4320
Yang GC, Yao JY (2020) High-precision motion servo control of double-rod electro-hydraulic actuators with exact tracking performance. ISA Trans 103:266–279
Ruffa F, De Capua C, Morello R, Liu ZZ (2019) Temperature sensing and evaluation of thermal effects on battery packs for automotive applications. IEEE Sensors J 19:11634–11645
Funding
This work was supported in part by the National Natural Science Foundation of China (61973176,61973178,U2066203).
Author information
Authors and Affiliations
Contributions
Jun Yan: Data curation, Writing - original draft, Visualization, Investigation. Junhong Li: Conceptualization, Methodology, Software, Funding acquisition. Guixiang Bai: Software, Validation. Yanan Li: Writing - review & editing.
Corresponding author
Ethics declarations
Ethical and informed consent for data used
The data used in this paper conform to ethical and informed conset.
Conflicts of interests
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yan, J., Li, J., Bai, G. et al. An Attention-BiLSTM network identification method for time-delay feedback nonlinear system. Appl Intell 55, 29 (2025). https://doi.org/10.1007/s10489-024-06067-9
Accepted:
Published:
DOI: https://doi.org/10.1007/s10489-024-06067-9