Abstract
Spintronic memristors have received significant attention as a potential building block for control systems, and particularly, it can be laid out in a high-density grid known as a crossbar array. Meanwhile, radial basis function (RBF) neural network control algorithm can effectively improve the control performance against large uncertain systems. But choosing reasonable parameters for RBF neural network to save convergence time and reduce the amplitude of the initial step is very important and difficult. Therefore, based on the study of characteristics of RBF neural network and spintronic memristors, this paper proposes a RBF neural network control algorithm based on spintronic memristor crossbar array; that is to say, the RBF neural network is divided into two parts of hardware and software. Hardware completes the updated parameters’ storage and extraction by spintronic memristor crossbar array, and software accomplishes the parameters updating process from the traditional RBF neural network. With a multiple-input multiple-output data sample training as the research object, simulation results show that the typical RBF neural network control algorithm needs 24 steps to fulfill the convergence requirements and the amplitude of the initial step is close to 2e−4. However, the proposed algorithm only needs 18 steps and the amplitude of the initial step is just about 8.6e−9. The comparison of these results indicates evidently the effectiveness of proposed algorithm.
Similar content being viewed by others
References
Chua L (1971) Memristor—the missing circuit element. IEEE Trans Circuit Theory 18(5):507–519
Chen Y, Wang X (2009) Compact modeling and corner analysis of spintronic memristor, 2013 IEEE/ACM international symposium on nanoscale architectures (NANOARCH), pp 7–12
Chen Y, Li H, Sun Z (2014) Spintronic memristor as interface between DNA and solid state devices, memristors and memristive systems. Springer, New York, pp 281–298
Wang X, Chen Y, Xi H, Li H, Dimitrov D (2009) Spintronic memristor through spin-torque-induced magnetization motion. IEEE Electron Device Lett 30(3):294–297
Li S, Zheng J (2010) Adaptive controller design for a class of nonlinear time-delay systems based on RBF neural networks. J Syst Sci Math Sci 5(2):577–592
Wang Z, Zhang Y, Fang H (2008) Neural adaptive control for a class of nonlinear systems with unknown deadzone. Neural Comput Appl 17(4):339–345
Zhao J, Wei H, Zhang C, Li W, Guo W, Zhang K (2015) Natural gradient learning algorithms for RBF networks. Neural Comput 27(2):481–505
Fasshauer GE, Zhang JG (2007) On choosing “optimal” shape parameters for RBF approximation. Numer Algorithms 45(1–4):345–368
Chen W, Jiao LC, Wu J (2012) Globally stable adaptive robust tracking control using RBF neural networks as feedforward compensators. Neural Comput Appl 21(2):351–363
Gao S, Dong H, Ning B, Chen Y, Sun X (2015) Adaptive fault-tolerant automatic train operation using RBF neural networks. Neural Comput Appl 26(1):141–149
Golbabai A, Mohebianfar E, Rabiei H (2015) On the new variable shape parameter strategies for radial basis functions. Comput Appl Math 34(2):691–704
Liu J (2013) Radial basis function (RBF) neural network control for mechanical systems. Springer, Berlin, pp 133–191
Prado RNA, Oliveira JAN, Melo JD, Neto AD (2014) Takagi Hayashi fuzzy neural system in hardware: an application for embedding in industrial sensors, making them intelligent. J Control Autom Electr Syst 25(5):585–596
Li MM, Verma B, Fan X, Tickle K (2008) RBF neural networks for solving the inverse problem of backscattering spectra. Neural Comput Appl 17(4):391–397
Zhang S, Qiu X, Liu C (2014) Neural adaptive compensation control for a class of MIMO uncertain nonlinear systems with actuator failures. Circuits Syst Signal Process 33(6):1971–1984
Wang M, Liu X, Shi P (2011) Adaptive neural control of pure-feedback nonlinear time-delay systems via dynamic surface technique, systems. IEEE Trans Syst Man Cybern B Cybern 41(6):1681–1692
Wang H, Liu X, Liu K, Chen B, Lin C (2014) Adaptive neural control for a general class of pure-feedback stochastic nonlinear systems. Neurocomputing 135(8):348–356
Huang J, Li C, He X (2013) Stabilization of a memristor-based chaotic system by intermittent control and fuzzy processing. Int J Control Autom Syst 11(3):643–647
Kim H, Sah MP, Yang C, Roska T, Chua LO (2012) Neural synaptic weighting with a pulse-based memristor circuit. IEEE Trans Circuits Syst I Regul Pap 59(1):148–158
Bi X, Zhang C, Li H, Chen Y, Pino RE (2012) Spintronic memristor based temperature sensor design with CMOS current reference. IEEE design, automation and test in Europe conference and exhibition (DATE), pp 1301–1306
Fang Y, Dumas RK, Nguyen TN, Mohseni SM, Chung S, Miller CW, Åkerman J (2013) A nonvolatile spintronic memory element with a continuum of resistance states. Adv Funct Mater 23(15):1919–1922
Qureshi MS, Pickett M, Miao F, Strachan JP (2011) CMOS interface circuits for reading and writing memristor crossbar array, circuits and systems (ISCAS), IEEE international symposium, pp 2954–2957
Wu A, Zeng Z (2015) Improved conditions for global exponential stability of a general class of memristive neural networks. Commun Nonlinear Sci 20(3):975–985
Duan S, Hu W, Li C, Wu S (2012) Exponential stability of discrete-time delayed Hopfield neural networks with stochastic perturbations and impulses. Results Math 62(1-2):73–87
Hu X, Duan S, Wang L, Liao X (2012) Memristive crossbar array with applications in image processing. Sci China Inform Sci 55(2):461–472
Hu M, Li HH, Chen Y, Wang X (2011) spintronic memristor: compact model and statistical analysis. J Low Power Electron 7(2):234–244
Chen L, Li C, Huang T, Chen Y, Wang X (2013) Memristor crossbar-based unsupervised image learning. Neural Comput Appl 25(2):393–400
Chen Y, Huang T, Huang Y (2014) Complex dynamics of a delayed discrete neural network of two nonidentical neurons, chaos: an interdisciplinary. J Nonlinear Sci 24(1):013108
Wen S, Bao G, Zeng Z, Chen Y, Huang T (2013) Global exponential synchronization of memristor-based recurrent neural networks with time-varying delays. Neural Netw 48:195–203
Mirebrahimi SN, Merrikh-Bayat F (2014) Programmable discrete-time type I and type II FIR filter design on the memristor crossbar structure. Analog Integr Circuits Signal Process 79(3):529–541
Duan S, Hu X, Wang L, Gao S, Li C (2014) Hybrid memristor/RTD structure-based cellular neural networks with applications in image processing. Neural Comput Appl 25(2):291–296
Querlioz D, Bichler O, Dollfus P, Gamrat C (2013) Immunity to device variations in a spiking neural network with memristive nanodevices. IEEE Trans Nanotechnol 12(3):288–295
Duan S, Zhang Y, Hu X, Wang L, Li C (2014) Memristor-based chaotic neural networks for associative memory. Neural Comput Appl 25(6):1437–1445
Huang T, Li C, Duan S, Starzyk JA (2012) Robust exponential stability of uncertain delayed neural networks with stochastic perturbation and impulse effects. IEEE Trans Neural Netw Learn Syst 23(6):866–875
Gao S, Dong H, Ning B, Chen Y, Sun X (2015) Adaptive fault-tolerant automatic train operation using RBF neural networks. Neural Comput Appl 26(1):141–149
Acknowledgements
The work was supported by Program for New Century Excellent Talents in University (Grant No. [2013]47), National Natural Science Foundation of China (Grant Nos. 61372139, 61101233, 60972155), “Spring Sunshine Plan” Research Project of Ministry of Education of China (Grant No. z2011148), Technology Foundation for Selected Overseas Chinese Scholars, Ministry of Personnel in China (Grant No. 2012-186), University Excellent Talents Supporting Foundations in of Chongqing (Grant No. 2011-65), Research Project of Basic Science and Cutting-edge Technology of Chongqing (Grant No. cstc2016jcyjA0573), Research Project of Basic Science and Cutting-edge Technology of Chongqing (Grant No. cstc2016jcyjA0573), Fundamental Research Funds for the Central Universities (Grant Nos. XDJK2014A009, XDJK2013B011, XDJK2015C009, XDJK2016C027).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, T., Duan, S., Liu, J. et al. An improved design of RBF neural network control algorithm based on spintronic memristor crossbar array. Neural Comput & Applic 30, 1939–1946 (2018). https://doi.org/10.1007/s00521-016-2715-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2715-8