Structural Engineering and Mechanics

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Optimal deep machine learning framework for vibration mitigation of seismically-excited uncertain building structures

  • Received : 2023.06.28
  • Accepted : 2023.11.23
  • Published : 2023.12.25
⟨ Previous Next ⟩

Abstract

Deep extreme learning machine (DELM) and multi-verse optimization algorithms (MVO) are hybridized for designing an optimal and adaptive control framework for uncertain buildings. In this approach, first, a robust model predictive control (RMPC) scheme is developed to handle the problem uncertainty. The optimality and adaptivity of the proposed controller are provided by the optimal determination of the tunning weights of the linear programming (LP) cost function for clustered external loads using the MVO. The final control policy is achieved by collecting the clustered data and training them by DELM. The efficiency of the introduced control scheme is demonstrated by the numerical simulation of a ten-story benchmark building subjected to earthquake excitations. The results represent the capability of the proposed framework compared to robust MPC (RMPC), conventional MPC (CMPC), and conventional DELM algorithms in structural motion control.

Keywords

References

  1. Ackermann, J. (1985), Design of Robust Control Systems. In Sampled-Data Control Systems, Springer, Berlin, Heidelberg.
  2. Afram, A., Janabi-Sharifi, F., Fung, A.S. and Raahemifar, K. (2017), "Artificial neural network (ANN) based model predictive control (MPC) and optimization of HVAC systems: A state of the art review and case study of a residential HVAC system", Energy Build., 141, 96-113. https://doi.org/10.1016/j.enbuild.2017.02.012.
  3. Akinosho, T.D., Oyedele, L.O., Bilal, M., Ajayi, A.O., Delgado, M.D., Akinade, O.O. and Ahmed, A.A. (2020), "Deep learning in the construction industry: A review of present status and future innovations", J. Build. Eng., 32, 101827. https://doi.org/10.1016/j.jobe.2020.101827.
  4. Al-Fahdawi, O.A. and Barroso, L.R. (2021), "Adaptive neuro-fuzzy and simple adaptive control methods for full three-dimensional coupled buildings subjected to bi-directional seismic excitations", Eng. Struct., 232, 111798. https://doi.org/10.1016/j.engstruct.2020.111798.
  5. Arfiadi, Y. and Hadi, M.N.S. (2001), "Optimal direct (static) output feedback controller using real coded genetic algorithms", Comput. Struct., 79(17), 1625-1634. https://doi.org/10.1016/S0045-7949(01)00041-4.
  6. Bahrami Rad, A., Katebi, J. and Yaghmaei-Sabegh, S. (2023), "Covariance tracking method for designing a robust receding horizon controller", J. Vib. Control, 10775463231195221. https://doi.org/10.1177/10775463231195221.
  7. Bahrami Rad, A., Nouri, M., Katebi, J. and Mousavi Ghasemi, S.A. (2021), "A developed model predictive control scheme for vibration attenuation of building structures", Smart Struct. Syst., 27(4), 691-703. http://doi.org/10.12989/sss.2021.27.4.691.
  8. Berradia, M., Azab, M., Ahmad, Z., Accouche, O., Raza, A. and Alashker, Y. (2022), "Data-driven prediction of compressive strength of FRP-confined concrete members: An application of machine learning models", Struct. Eng. Mech., 83(4), 515-535. https://doi.org/10.12989/sem.2022.83.4.515 .
  9. Botchkarev, A. (2019), "A new typology design of performance metrics to measure errors in machine learning regression algorithms", Interdisc. J. Inform., Knowl Manage, 14, 045-076. https://doi.org/10.28945/4184.
  10. Caicedo, D., Lara-Valencia, L., Blandon, J. and Graciano, C. (2021), "Seismic response of high-rise buildings through metaheuristic-based optimization using tuned mass dampers and tuned mass dampers inerter", J. Build. Eng., 34, 101927. https://doi.org/10.1016/j.jobe.2020.101927.
  11. Calanca, A. and Fiorini, P. (2018), "A rationale for acceleration feedback in force control of series elastic actuators", IEEE Trans. Robot., 34(1), 48-61. https://doi.org/10.1109/TRO.2017.2765667.
  12. Camacho, E.F. and Alba, C.B. (2013), Model Predictive Control, Springer Science & Business Media.
  13. Chen, Y., Sato, D., Miyamoto, K. and She, J. (2020), "Estimating the maximum response and maximum control force for high-rise base-isolated buildings with active structural control in along-wind direction", Eng. Struct., 216, 110712. https://doi.org/10.1016/j.engstruct.2020.110712.
  14. Chen, Y., Zhang, S., Peng, H., Chen, B. and Zhang, H. (2017), "A novel fast model predictive control for large-scale structures", J. Vib. Control, 23(13), 2190-2205. https://doi.org/10.1177/1077546315610033.
  15. Chen, Z.Y., Peng, S.H., Wang, R.Y., Meng, Y., Fu, Q. and Chen, T. (2022), "Stochastic intelligent GA controller design for active TMD shear building", Struct. Eng. Mech., 81(1), 51-57. https://doi.org/10.12989/sem.2022.81.1.051.
  16. Ding, F., Luo, X., Cai, Y. and Chang, W. (2020), "Acceleration feedback control for enhancing dynamic stiffness of fast tool servo system considering the sensor imperfections", Mech. Syst. Signal Pr., 141, 106429. https://doi.org/10.1016/j.ymssp.2019.106429.
  17. Dogan, A. and Birant, D. (2021), "Machine learning and data mining in manufacturing", Exp. Syst. Appl., 166, 114060. https://doi.org/10.1016/j.eswa.2020.114060.
  18. Eliasi, H., Yazdani, H., Khatibinia, M. and Mahmoudi, M. (2022), "Optimum design of a sliding mode control for seismic mitigation of structures equipped with active tuned mass dampers", Struct. Eng. Mech., 81(5), 633-645. https://doi.org/10.12989/sem.2022.81.5.633 .
  19. Esfahani, P.S. and Pieper, J.K. (2019), "Robust model predictive control for switched linear systems", ISA Trans., 89, 1-11. https://doi.org/10.1016/j.isatra.2018.12.006
  20. Gu, Y., Chen, Y., Liu, J. and Jiang, X. (2015), "Semi-supervised deep extreme learning machine for Wi-Fi based localization", Neurocomput., 166, 282-293. https://doi.org/10.1016/j.neucom.2015.04.011.
  21. Hamandi, M., Tognon, M. and Franchi, A. (2020), "Direct acceleration feedback control of quadrotor aerial vehicles", 2020 IEEE International Conference on Robotics and Automation (ICRA), 5335-5341. https://doi.org/10.1109/ICRA40945.2020.9196557.
  22. Heirung, T.A.N., Paulson, J.A., O'Leary, J. and Mesbah, A. (2018), "Stochastic model predictive control-how does it work?", Comput. Chem. Eng., 114, 158-170. https://doi.org/10.1016/j.compchemeng.2017.10.026.
  23. Huang, G.B., Zhu, Q.Y. and Siew, C.K. (2004), "Extreme learning machine: A new learning scheme of feedforward neural networks", 2004 IEEE International Joint Conference on Neural Networks, IEEE Cat. No. 04CH37541, 2, 985-990. https://doi.org/10.1109/IJCNN.2004.1380068.
  24. Isaia, F., Fiorentini, M., Serra, V. and Capozzoli, A. (2021), "Enhancing energy efficiency and comfort in buildings through model predictive control for dynamic facades with electrochromic glazing", J. Build. Eng., 43, 102535. https://doi.org/10.1016/j.jobe.2021.102535.
  25. Janakiraman, V.M., Nguyen, X. and Assanis, D. (2016), "An ELM based predictive control method for HCCI engines", Eng. Appl. Artif. Intell., 48, 106-118. https://doi.org/10.1016/j.engappai.2015.10.007.
  26. Kalita, K., Ghadai, R.K. and Chakraborty, S. (2021), "A comparative study on the metaheuristic-based optimization of skew composite laminates", Eng. Comput., 38(4), 3549-3566. https://doi.org/10.1007/s00366-021-01401-y.
  27. Katebi, J., Rad, A.B. and Zand, J.P. (2022), "A novel multi-feature model predictive control framework for seismically excited high-rise buildings", Struct. Eng. Mech., 83(4), 537-549. https://doi.org/10.12989/sem.2022.83.4.537.
  28. Katebi, J., Shoaei-parchin, M., Shariati, M., Trung, N.T. and Khorami, M. (2019), "Developed comparative analysis of metaheuristic optimization algorithms for optimal active control of structures", Eng. Comput., 1, 1-20. https://doi.org/10.1007/s00366-019-00780-7.
  29. Kayabekir, A.E., Nigdeli, S.M. and Bekdas, G. (2020), "Robustness of structures with active tuned mass dampers optimized via modified harmony search for time delay", Proceedings of 6th International Conference on Harmony Search, Soft Computing and Applications: ICHSA 2020, Istanbul, Springer Singapore. https://doi.org/10.1007/978-981-15-8603-3_6.
  30. Lana, C. and Rotea, M. (2008), "Desensitized model predictive control applied to a structural benchmark problem", IFAC Proc. Vol., 41(2), 13188-13193. https://doi.org/10.3182/20080706-5-KR-1001.02234.
  31. Lee, J.H. (2014), "From robust model predictive control to stochastic optimal control and approximate dynamic programming: A perspective gained from a personal journey", Comput. Chem. Eng., 70, 114-121. https://doi.org/10.1016/j.compchemeng.2013.10.014.
  32. Luo, J., Jin, K., Wang, M., Yuan, J. and Li, G. (2017), "Robust entry guidance using linear covariance-based model predictive control", Int. J. Adv. Robot. Syst., 14(1), 1729881416687503. https://doi.org/10.1177%2F1729881416687503. https://doi.org/10.1177%2F1729881416687503
  33. Mei, G., Kareem, A. and Kantor, J.C. (2001), "Real-time model predictive control of structures under earthquakes", Earthq. Eng. Struct. Dyn., 30(7), 995-1019. https://doi.org/10.1002/eqe.49.
  34. Mei, G., Kareem, A. and Kantor, J.C. (2002), "Model predictive control of structures under earthquakes using acceleration feedback", J. Eng. Mech., 128(5), 574-585. https://doi.org/10.1061/(ASCE)0733-9399(2002)128:5(574).
  35. Mei, G., Kareem, A. and Kantor, J.C. (2004), "Model predictive control of wind-excited building: Benchmark study", J. Eng. Mech., 130(4), 459-465. https://doi.org/10.1061/(ASCE)0733-9399(2004)130:4(459).
  36. Mesbah, A. (2016), "Stochastic model predictive control: An overview and perspectives for future research", IEEE Control Syst. Mag., 36(6), 30-44. https://doi.org/10.1109/MCS.2016.2602087.
  37. Mirjalili, S., Mirjalili, S.M. and Hatamlou, A. (2016), "Multi-verse optimizer: a nature-inspired algorithm for global optimization", Neur. Comput. Appl., 27(2), 495-513. https://doi.org/10.1007/s00521-015-1870-7.
  38. Moradi, S., Azam, S.E. and Mofid, M. (2021), "On Bayesian active vibration control of structures subjected to moving inertial loads", Eng. Struct., 239, 112313. https://doi.org/10.1016/j.engstruct.2021.112313.
  39. Morari, M. and Lee, J.H. (1999), "Model predictive control: past, present and future", Comput. Chem. Eng., 23(4-5), 667-682. https://doi.org/10.1016/S0098-1354(98)00301-9.
  40. Mtibaa, F., Nguyen, K.K., Dermardiros, V. and Cheriet, M. (2021), "Context-aware model predictive control framework for multi-zone buildings", J. Build. Eng., 42, 102340. https://doi.org/10.1016/j.jobe.2021.102340.
  41. Naser, M.Z. (2023), Machine Learning for Civil and Environmental Engineers: A Practical Approach to Data-Driven Analysis, Explainability, and Causality, John Wiley & Sons.
  42. Naser, M.Z. and Alavi, A.H. (2021), "Error metrics and performance fitness indicators for artificial intelligence and machine learning in engineering and sciences", Arch. Struct. Constr., 1-19. https://doi.org/10.1007/s44150-021-00015-8.
  43. Ohtori, Y., Christenson, R.E., Spencer, Jr. B.F. and Dyke, S.J. (2004), "Benchmark control problems for seismically excited nonlinear buildings", J. Eng. Mech., 130(4), 366-385. https://doi.org/10.1061/(ASCE)0733-9399(2004)130:4(366).
  44. Park, W., Park, K.S. and Koh, H.M. (2008), "Active control of large structures using a bilinear pole shifting transform with H∞ control method", Eng. Struct., 30(11), 3336-3344. https://doi.org/10.1016/j.engstruct.2008.05.009.
  45. Patan, K. (2018), "Two stage neural network modelling for robust model predictive control", ISA Trans., 72, 56-65. https://doi.org/10.1016/j.isatra.2017.10.011.
  46. Peng, H., Chen, Y., Li, E., Zhang, S. and Chen, B. (2018), "Explicit expression-based practical model predictive control implementation for large-scale structures with multi-input delays", J. Vib. Control, 24(12), 2605-2620. https://doi.org/10.1177/1077546316689341.
  47. Peng, H., Li, F., Zhang, S. and Chen, B. (2017), "A novel fast model predictive control with actuator saturation for large-scale structures", Comput. Struct., 187, 35-49. https://doi.org/10.1016/j.compstruc.2017.03.014.
  48. Pnevmatikos, G.N. and Gantes, J.C. (2011), "The influence of time delay and saturation capacity in control of structures under seismic excitations", Smart Struct. Syst., 8(5), 479-490. https://doi.org/10.12989/sss.2011.8.5.449.
  49. Rahmani, H.R., Chase, G., Wiering, M. and Konke, C. (2019), "A framework for brain learning-based control of smart structures", Adv. Eng. Inf., 42, 100986. https://doi.org/10.1016/j.aei.2019.100986.
  50. Reynolds, J., Rezgui, Y., Kwan, A. and Piriou, S. (2018), "A zonelevel, building energy optimisation combining an artificial neural network, a genetic algorithm, and model predictive control", Energy, 151, 729-739. https://doi.org/10.1016/j.energy.2018.03.113.
  51. Seron, M.M., Goodwin, G.C. and Carrasco, D.S. (2019), "Stochastic model predictive control: Insights and performance comparisons for linear systems", Int. J. Robust. Nonlin. Control, 29(15), 5038-5057. https://doi.org/10.1002/rnc.4106.
  52. Smarra, F., Jain, A., de Rubeis, T., Ambrosini, D., D'Innocenzo, A. and Mangharam, R. (2018), "Data-driven model predictive control using random forests for building energy optimization and climate control", Appl. Energy, 226, 1252-1272. https://doi.org/10.1016/j.apenergy.2018.02.126.
  53. Song, Y., Fang, X. and Diao, Q. (2016), "Mixed H 2/H∞ distributed robust model predictive control for polytopic uncertain systems subject to actuator saturation and missing measurements", Int. J. Syst. Sci., 47(4), 777-790. https://doi.org/10.1080/00207721.2014.905647.
  54. Tapeh, A.T.G. and Naser, M.Z. (2023), "Artificial intelligence, machine learning, and deep learning in structural engineering: A scientometrics review of trends and best practices", Arch. Comput. Meth. Eng., 30(1), 115-159. https://doi.org/10.1007/s11831-022-09793-w.
  55. Ulusoy, S., Bekdas, G., Nigdeli, S.M., Kim, S. and Geem, Z.W. (2021), "Performance of optimum tuned PID controller with different feedback strategies on active-controlled structures", Appl. Sci., 11(4), 1682. https://doi.org/10.3390/app11041682.
  56. Ulusoy, S., Nigdeli, S.M. and Bekdas, G. (2021), "Novel metaheuristic-based tuning of PID controllers for seismic structures and verification of robustness", J. Build. Eng., 33, 101647. https://doi.org/10.1016/j.jobe.2020.101647.
  57. Wang, L. (2009), Model Predictive Control System Design and Implementation using MATLAB® , Springer Science & Business Media.
  58. Yang, C.S.W., Chung, L.L., Wu, L.Y. and Chung, N.H. (2011), "Modified predictive control of structures with direct output feedback", Struct. Control Hlth. Monit., 18(8), 922-940. https://doi.org/10.1002/stc.411.
  59. Yang, S., Wan, M.P., Chen, W., Ng, B.F. and Dubey, S. (2021), "Experiment study of machine-learning-based approximate model predictive control for energy-efficient building control", Appl. Energy, 288, 116648. https://doi.org/10.1016/j.apenergy.2021.116648.
  60. Yucel, M., Bekdas, G., Nigdeli, S.M. and Sevgen, S. (2019), "Estimation of optimum tuned mass damper parameters via machine learning", J. Build. Eng., 26, 100847. https://doi.org/10.1016/j.jobe.2019.100847
  61. Zafarani, M.M. and Halabian, A.M. (2020), "A new supervisory adaptive strategy for the control of hysteretic multi-story irregular buildings equipped with MR-dampers", Eng. Struct., 217, 110786. https://doi.org/10.1016/j.engstruct.2020.110786.
  62. Zand, J.P., Katebi, J. and Yaghmaei-Sabegh, S. (2023), "A hybrid clustering-based type-2 adaptive neuro-fuzzy forecasting model for smart control systems", Exp. Syst. Appl., 239, 122445. https://doi.org/10.1016/j.eswa.2023.122445.
  63. Zand, J.P., Sabouri, J., Katebi, J. and Nouri, M. (2021), "A new time-domain robust anti-windup PID control scheme for vibration suppression of building structure", Eng. Struct., 244, 112819. https://doi.org/10.1016/j.engstruct.2021.112819.
  64. Zand, J.P., Katebi, J. and Yaghmaei-Sabeghb, S. (2023), "A generalized ANFIS controller for vibration mitigation of uncertain building structure", Struct. Eng. Mech., 87(3), 231-242. https://doi.org/10.12989/sem.2023.87.3.231.
  65. Zhang, Y., Huang, Y., Chen, Z., Li, G. and Liu, Y. (2021), "A novel learning based model predictive control strategy for plugin hybrid electric vehicle", IEEE Trans. Transp. Electrif., 8(1), 23-35. https://doi.org/10.1109/TTE.2021.3069924.