Abstract
The reliability of many industrial processes depends on the sensor system. However, these sensors can be affected by noise, perturbations and failures. Hence, sensor monitoring and diagnosis are fundamental to guarantee the quality of an industrial process. Nowadays, artificial neural networks (ANN) are widely used in sensor signal processing and diagnosis. However, those ANNs usually require many artificial neurons, being difficult to implement in software and hardware due to their high computational costs. This paper presents an optimized implementation of artificial neurons in ANNs for sensor data analysis using a Genetic Algorithm (GA). The objective of GA is to find an adequate segmentation to reduce the activation function approximation error. One of the advantages of the proposed approach is that the cost function used in GA considers the effect of factors such as the ANN architecture or the number of bits used in arithmetic operations. The proposed ANN implementation technique aims to get the best possible approximation for a specific ANN architecture, making easier its implementation in software and hardware. Simulation and experimental results using FPGA (Field Programmable Gate Array) prove the advantages of the proposed approach for implementing sensor data analysis systems based on ANNs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Fan X, Zhang S, Gemmeke T (2020) Approximation of transcendental functions with guaranteed algorithmic QoS by multilayer Pareto optimization. IEEE Trans Very Large Scale Integr (VLSI) Syst 28:2495–2508
Obla S, Gong X, Aloufi A, Hu P, Takabi D (2020) Effective activation functions for homomorphic evaluation of deep neural networks. IEEE Access 8:153098–153112
Dong H et al. (2020) PLAC: Piecewise linear approximation computation for all nonlinear unary functions. IEEE Trans Very Large Scale Integr (VLSI) Syst 28:2014–2027
Chandwani A, Dey S, Mallik A (2020) Cybersecurity of onboard charging systems for electric vehicles—review, challenges and countermeasures. IEEE Access 8:226982–226998
Li Y, Yin G, Zhuang W, Zhang N, Wang J, Geng K (2020) Compensating delays and noises in motion control of autonomous electric vehicles by using deep learning and unscented Kalman predictor. IEEE Trans Syst Man Cyber Syst 50:4326–4338
Ortega-Zamorano F, Jerez JM, Muñoz DU, Luque-Baena RM, Franco L (2016) Efficient implementation of the backpropagation algorithm in FPGAs and microcontrollers. IEEE Trans Neural Netw Learn Syst 27:1840–1850
Sai CH, Chih YT, Wong WH, Lee CY (2015) A hardware-efficient sigmoid function with adjustable precision for a neural network system. IEEE Trans Circ Syst II Exp Briefs 62:1073–1077
Youssefi B, Leigh AJ, Mirhassani M, Wu J (2019) Tunable neuron with PWL approximation based on the minimum operator. IEEE Trans Circ Syst II Exp Briefs 66:387–391
Qin Z et al (2020) A novel approximation methodology and its efficient VSLI implementation for the sigmoid function. IEEE Trans Circuits Syst, II, Exp Briefs 67:3422–3426
Sun H et al (2020) A universal method of linear approximation with controllable error for the efficient implementation of transcendental functions. IEEE Trans Circ Syst I Reg Papers 67:177–188
Zamanlooy B, Mirhassani M (2014) Efficient VLSI implementation of neural networks with hyperbolic tangent activation function. IEEE Trans Very Large Scale Integr (VLSI) Syst 22:39–48
Soares AM, Pinto JOP, Bose BK, Leite LC, da Silva LEB, Romero M. Field Programmable Gate Array (FPGA) based neural network implementation of stator flux oriented vector control of induction motor drive. In: Proceedings of 2006 IEEE International Conference on Industrial Technology (ISIE), Mumbai, India, 15–17 December 2006, 31–34
Jupp DLB (1978) Approximation to data by SPLINES with free knots. SIAM J Numer Anal 15:328–343
Goldberg DE (1989) Genetic Algorithm in Search Optimization & Machine Learning. Addison-Wesley Longman Publishing Co., Boston
Rafiei M, Khooban MH, Igder MA, Boudjadar J (2019) A novel approach to overcome the limitations of reliability centered maintenance implementation on the smart grid distance protection system. IEEE Trans Circuits Syst II Exp Briefs 67:320–324
Acknowledgments
Authors want to thank the BATLAB Laboratory and the Graduation Program in Electrical Engineering of Federal University of Mato Grosso do Sul – UFMS, for the support to this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
D’Estefani, A., Cordero, R., Onofre, J. (2022). Efficient Implementation of Artificial Neural Networks for Sensor Data Analysis Based on a Genetic Algorithm. In: Pinto, J.O.P., Kimpara, M.L.M., Reis, R.R., Seecharan, T., Upadhyaya, B.R., Amadi-Echendu, J. (eds) 15th WCEAM Proceedings. WCEAM 2021. Lecture Notes in Mechanical Engineering. Springer, Cham. https://doi.org/10.1007/978-3-030-96794-9_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-96794-9_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-96793-2
Online ISBN: 978-3-030-96794-9
eBook Packages: EngineeringEngineering (R0)