Document Type : SI: ADLRTCA

Authors

Department of Electrical Engineering, South Tehran Branch, Islamic Azad University, Tehran, Iran.

Abstract

This paper describes a new technique for implementing an Artificial Neural Network (ANN) using Field Programmable Gate Array (FPGA). The goal is design the Low Drop Output (LDO) voltage-regulator circuit with the desired features depending on the application. (The first novelty is designing an LDO with variable features). Voltage regulators bring voltage changes to a stable and acceptable level, especially for products using portable devices. The fragmentary neural network algorithm is modeled using the Xilinx generator system and it can be implemented in Xilinx FPGA (the second novelty is implanting fragmentary ANN in FPGA for parallel computations and real time design). The neural network is trained using the levenberg-Marquardt algorithm which is the data collected from HSPICE software. In Matlab, the tangent-sigmoid function is used as a neuron activation function, but the block set provided by the Xilinx generator system does not have a tangent-sigmoid operator, so the tan-sigmoid operator is modeled on the Maclaurin expansion (the third novelty is using Maclaurin series for approximation function along with the reduction of connections in the neural network to reduce many blocks in FPGA). In this paper, the similarity of the tangent-sigmoid function produced using Matlab and the approximation of the performance of this function using the Maclaurin series are shown. When the inputs are between -0.5 to +0.5, the simulated results show that the absolute error between the values of tan-sigmoid function based on Matlab and Xilinx System Generator using Maclaurin power series are not more than 0.17%. The performance modeling of the system generator with 0.996515% accuracy of Matlab modeling.

Keywords

Main Subjects

Torres, J., El-Nozahi, M., Amer, A., Gopalraju, S., Abdullah, R., Entesari, K., & Sanchez-Sinencio, E. (2014). Low drop-out voltage regulators: Capacitor-less architecture comparison. IEEE circuits and systems magazine14(2), 6-26. DOI:1109/MCAS.2014.2314263
Mohamed, A. R., Qi, L., & Wang, G. (2021). A power-efficient and re-configurable analog artificial neural network classifier. Microelectronics journal111, 105022. https://doi.org/10.1016/j.mejo.2021.105022
Zhang, L., Zheng, C., Li, T., Xing, L., Zeng, H., Li, T., ... & Zhou, Z. (2017). Building up a robust risk mathematical platform to predict colorectal cancer. Complexity2017. https://doi.org/10.1155/2017/8917258
Sahani, M., & Dash, P. K. (2020). FPGA-based semisupervised multifusion RDCNN of process robust VMD data with online kernel RVFLN for power quality events recognition. IEEE transactions on neural networks and learning systems, 1-13. DOI:1109/TNNLS.2020.3027984
Ma, Y., Suda, N., Cao, Y., Seo, J. S., & Vrudhula, S. (2016, August). Scalable and modularized RTL compilation of convolutional neural networks onto FPGA. 2016 26th international conference on field programmable logic and applications (FPL)(pp. 1-8). IEEE. DOI: 1109/FPL.2016.7577356
Zhu, J., & Sutton, P. (2003, September). FPGA implementations of neural networks–a survey of a decade of progress. International conference on field programmable logic and applications (pp. 1062-1066). Berlin, Heidelberg: Springer. https://doi.org/10.1007/978-3-540-45234-8_120
Malathi, S., & Jayachandran, J. (2020). FPGA implementation of NN based LMS–LMF control algorithm in DSTATCOM for power quality improvement. Control engineering practice98, 104378. https://doi.org/10.1016/j.conengprac.2020.104378
Sanabria-Borbon, A. C., & Tlelo-Cuautle, E. (2014, August). Sizing analog integrated circuits by combining g m/I D technique and evolutionary algorithms. 2014 IEEE 57th international midwest symposium on circuits and systems (MWSCAS)(pp. 234-237). IEEE. DOI: 1109/MWSCAS.2014.6908395
Chinchore, J. B., & Thakker, R. A. (2015, March). Design of low dropout regulator using artificial bee colony evolutionary algorithm. 2015 international conference on circuits, power and computing technologies [ICCPCT-2015](pp. 1-8). IEEE. DOI: 1109/ICCPCT.2015.7159280
Lopez-Arredondo, J., Tlelo-Cuautle, E., & Trejo-Guerra, R. (2015, March). Optimizing an LDO voltage regulator by evolutionary algorithms considering tolerances of the circuit elements. 2015 16th latin-american test symposium (LATS)(pp. 1-5). IEEE. DOI: 1109/LATW.2015.7102506
Ho, M., Leung, K. N., & Mak, K. L. (2010). A low-power fast-transient 90-nm low-dropout regulator with multiple small-gain stages. IEEE journal of solid-state circuits45(11), 2466-2475. IEEE. DOI: 1109/JSSC.2010.2072611
Tang, J., Lee, J., & Roh, J. (2018). Low-power fast-transient capacitor-less LDO regulator with high slew-rate class-AB amplifier. IEEE transactions on circuits and systems II: express briefs66(3), 462-466. IEEE. DOI:1109/TCSII.2018.2865254
Lim, C. C., Lai, N. S., Tan, G. H., & Ramiah, H. (2015). A low-power fast transient output capacitor-free adaptively biased LDO based on slew rate enhancement for SoC applications. Microelectronics journal46(8), 740-749. https://doi.org/10.1016/j.mejo.2015.06.002
Qu, X., Zhou, Z. K., & Zhang, B. (2015). Ultralow‐power fast‐transient output‐capacitor‐less low‐dropout regulator with advanced adaptive biasing circuit. IET circuits, devices & systems9(3), 172-180. DOI: 1049/iet-cds.2014.0162
Fathipour, R., Saberkari, A., Martinez, H., & Alarcón, E. (2014). High slew rate current mode transconductance error amplifier for low quiescent current output-capacitorless CMOS LDO regulator. Integration47(2), 204-212. https://doi.org/10.1016/j.vlsi.2013.10.005
Lee, Y. H., & Chen, K. H. (2010, August). A 65nm sub-1V multi-stage low-dropout (LDO) regulator design for SoC systems. 2010 53rd IEEE international midwest symposium on circuits and systems(pp. 584-587). IEEE. DOI: 1109/MWSCAS.2010.5548893
Milliken, R. J., Silva-Martínez, J., & Sánchez-Sinencio, E. (2007). Full on-chip CMOS low-dropout voltage regulator. IEEE transactions on circuits and systems I: regular papers54(9), 1879-1890. IEEE. DOI:1109/TCSI.2007.902615
Guo, J., & Leung, K. N. (2010). A 6-$mu $ W Chip-area-efficient output-capacitorless LDO in 90-nm CMOS technology. IEEE journal of solid-state circuits45(9), 1896-1905. IEEE. DOI:1109/JSSC.2010.2053859
Saberkari, A., Alarcón, E., & Shokouhi, S. B. (2013). Fast transient current-steering CMOS LDO regulator based on current feedback amplifier. Integration46(2), 165-171. https://doi.org/10.1016/j.vlsi.2012.02.001
Jahangiri, M., & Farrokhi, A. (2019). Fast transient capacitor-less low-dropout regulator based on output voltage spike reduction circuits for SOC applications. Journal of Circuits, Systems and Computers28(03), 1950043. https://doi.org/10.1142/S0218126619500439
Mathews, V. J. (1991). Adaptive polynomial filters. Jul1, 8(3) 10-26. IEEE. DOI: 1109/79.127998
Wen, H., Li, T., Chen, D., Yang, J., & Che, Y. (2021). An optimized neural network classification method based on kernel holistic learning and division. Mathematical problems in engineering2021. https://doi.org/10.1155/2021/8857818
Rigatos, G. G. (2011). A derivative-free Kalman filtering approach to state estimation-based control of nonlinear systems. IEEE transactions on industrial electronics59(10), 3987-3997. IEEE. DOI: 1109/TIE.2011.2159954
Kshirsagar, P., & Rathod, N. (2012). Artificial neural network. International journal of computer applications2, 12-16.
Reynaldi, A., Lukas, S., & Margaretha, H. (2012, November). Backpropagation and Levenberg-Marquardt algorithm for training finite element neural network. 2012 sixth UKSim/AMSS european symposium on computer modeling and simulation(pp. 89-94). IEEE. DOI: 1109/EMS.2012.56
Wang, S., Ling, X., Zhang, F., & Tong, J. (2010, March). Speech emotion recognition based on principal component analysis and back propagation neural network. 2010 international conference on measuring technology and mechatronics automation (Vol. 3, pp. 437-440). IEEE.
Haykin, S. S. (2008). Adaptive filter theory. Pearson Education India.
Mercorelli, P. (2016). A motion-sensorless control for intake valves in combustion engines. IEEE transactions on industrial electronics64(4), 3402-3412. IEEE. DOI:1109/TIE.2016.2598314
Li, S. (2001, July). Comparative analysis of backpropagation and extended Kalman filter in pattern and batch forms for training neural networks. IJCNN'01. international joint conference on neural networks. proceedings (Cat. No. 01CH37222)(Vol. 1, pp. 144-149). IEEE. DOI: 1109/IJCNN.2001.939007
Young, K. D., Utkin, V. I., & Ozguner, U. (1999). A control engineer's guide to sliding mode control. IEEE transactions on control systems technology7(3), 328-342. IEEE. DOI:1109/87.761053
Ahmed, R., El Sayed, M., Gadsden, S. A., Tjong, J., & Habibi, S. (2016). Artificial neural network training utilizing the smooth variable structure filter estimation strategy. Neural computing and applications27(3), 537-548. https://doi.org/10.1007/s00521-015-1875-2
Mercorelli, P. (2014). An adaptive and optimized switching observer for sensorless control of an electromagnetic valve actuator in camless internal combustion engines. asian journal of control16(4), 959-973. https://doi.org/10.1002/asjc.772
Jahangiri, M., & Razaghian, F. (2014). Fault detection in analogue circuits using hybrid evolutionary algorithm and neural network. Analog integrated circuits and signal processing80(3), 551-556. https://doi.org/10.1007/s10470-014-0352-7