Abstract
Neural-Network (NN)-based controllers have the potential to achieve better control performance than classical PID controllers. Yet NN deployment on tiny microcontrollers, which are used in DC motor control due to strict cost requirements, is challenging as NNs are computationally intensive and memory demanding. We propose a lightweight direct inverse NN-based control approach for controlling the angular speed of a permanent magnet DC motor, which runs on a tiny Arm Cortex-M0 microcontroller with only 4 kB of RAM. Moreover, the NN-based controller can self-adapt to the DC motor characteristics without the need of any external machine learning frameworks such as TensorFlow. For this, we are not deploying a pre-trained network for inference but implement a fully automated training process on the microcontroller, which also includes the dataset collection.
The result is a self-adaptive control algorithm that is able to drive the motor at the desired speed after it learned the motor characteristics in an initial training phase. Furthermore, the approach is extended such that it enables the controller to constantly self-adapt to later changes in the motor characteristics caused by heating or wear-out while it is operating in standard control mode.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
TensorFlow lite for microcontrollers (2020). https://www.tensorflow.org/lite/microcontrollers
Abadi, M., et. al.: TensorFlow: Large-scale machine learning on heterogeneous systems (2015). http://tensorflow.org/, software available from tensorflow.org
Cotton, N.J., Wilamowski, B.M., Dundar, G.: A neural network implementation on an inexpensive eight bit microcontroller. In: 2008 International Conference on Intelligent Engineering Systems, pp. 109–114 (2008)
Fedorov, I., Adams, R.P., Mattina, M., Whatmough, P.: Sparse: sparse architecture search for CNNs on resource-constrained microcontrollers. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 4977–4989. Curran Associates, Inc. (2019)
Hafner, R., Riedmiller, M.: Neural reinforcement learning controllers for a real robot application. In: Proceedings 2007 IEEE International Conference on Robotics and Automation, pp. 2098–2103 (2007)
ARM Inc.: CMSIS DSP software library (2020). http://www.keil.com/pack/doc/CMSIS/DSP/html/index.html
Infineon Technologies AG: Infineon TLE9855QX microcontroller (2020). https://www.infineon.com/cms/en/product/microcontroller/embedded-power-ics-system-on-chip-/h-bridge-driver-ic-integrated-arm-cortex-m0/tle9855qx/
Infineon Technologies AG: Infineon TLE985X evaluation board (2020). https://www.infineon.com/cms/en/product/evaluation-boards/tle985x-evalboard/
Khalid, M., Omatu, S.: A neural network controller for a temperature control system. IEEE Control Syst. Mag. 12(3), 58–64 (1992)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015, Conference Track Proceedings (2015)
Lai, L., Suda, N., Chandra, V.: CMSIS-NN: efficient neural network kernels for Arm Cortex-M CPUs. arXiv e-prints, January 2018. http://arxiv.org/abs/1801.06601
Liu, K., Tokar, R.L., McVey, B.D.: An integrated architecture of adaptive neural network control for dynamic systems. In: Tesauro, G., Touretzky, D.S., Leen, T.K. (eds.) Advances in Neural Information Processing Systems, vol. 7, pp. 1031–1038. MIT Press (1995)
Psaltis, D., Sideris, A., Yamamura, A.A.: A multilayered neural network controller. IEEE Control Syst. Mag. 8(2), 17–21 (1988)
Schley, C., Chauvin, Y., Henkle, V., Golden, R.: Neural networks structured for control application to aircraft landing. In: Lippmann, R.P., Moody, J.E., Touretzky, D.S. (eds.) Advances in Neural Information Processing Systems 3, pp. 415–421. Morgan-Kaufmann (1991)
Weerasooriya, S., El-Sharkawi, M.A.: Identification and control of a dc motor using back-propagation neural networks. IEEE Trans. Energy Convers. 6(4), 663–669 (1991)
Zhang, Y., Suda, N., Lai, L., Chandra, V.: Hello edge: keyword spotting on microcontrollers. CoRR abs/1711.07128 (2017). http://arxiv.org/abs/1711.07128
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Funk, F., Bucksch, T., Mueller-Gritschneder, D. (2020). ML Training on a Tiny Microcontroller for a Self-adaptive Neural Network-Based DC Motor Speed Controller. In: Gama, J., et al. IoT Streams for Data-Driven Predictive Maintenance and IoT, Edge, and Mobile for Embedded Machine Learning. ITEM IoT Streams 2020 2020. Communications in Computer and Information Science, vol 1325. Springer, Cham. https://doi.org/10.1007/978-3-030-66770-2_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-66770-2_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-66769-6
Online ISBN: 978-3-030-66770-2
eBook Packages: Computer ScienceComputer Science (R0)