Artificial intelligence based power consumption estimation of two-phase brushless DC motor according to FEA parametric simulation

Abstract In this study, Artificial Neural Networks, Extreme Machine Learning and Support Vector Machine (SVM) are used to estimate power consumption of Brushless DC motor in Unmanned Aerial Vehicle (UAV). Durafly 3648 Brushless DC motor of UAV is modelled with the Finite Element Analysis software. Then it is simulated with Ansys-Rmxprt according to pulse degree, speed and battery voltage of the UAV. The training times and Mean Absolute Percentage Errors (MAPE) of the Artificial Intelligence Techniques (AITs) are calculated for motor input power estimation. The best result among the implemented AITs is achieved with the MAPE of 0.269% by the SVM model. Then the graphical user interface (GUI) is developed to easily obtain information about how efficient the battery can be used, and the flight time of UAVs. Thanks to the proposed GUI software, the input power of the motor can be estimated via input parameters without the long-time consuming simulations.

[1]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[2]  M. M. Beharie,et al.  Design of a quadrotor flight test stand for system identification , 2015 .

[3]  Rogelio Lozano,et al.  Hovering Flight Improvement of a Quad-rotor Mini UAV Using Brushless DC Motors , 2011, J. Intell. Robotic Syst..

[4]  Devendra K. Chaturvedi,et al.  Parameters Estimation of an Electric Fan Using ANN , 2010, J. Intell. Learn. Syst. Appl..

[5]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[6]  Ali Sinan Çabuk,et al.  Investigation of different slot-pole combinations of an in-wheel BLDC motor for light electric vehicle propulsion , 2016, 2016 National Conference on Electrical, Electronics and Biomedical Engineering (ELECO).

[7]  T. J. E. Miller,et al.  Design of Brushless Permanent-Magnet Machines , 2010 .

[8]  Kristen Bell DeTienne,et al.  Neural Networks as Statistical Tools for Business Researchers , 2003 .

[9]  Weiming Ma,et al.  Research on a New Control Strategy of Three Phase Inverter for Unbalanced Loads , 2010 .

[10]  Fabrice Rossi,et al.  Mean Absolute Percentage Error for regression models , 2016, Neurocomputing.

[11]  Nisai H. Fuengwarodsakul,et al.  Dynamic model of brushless DC drive using FE method based characteristics , 2011, 2011 IEEE Ninth International Conference on Power Electronics and Drive Systems.

[12]  Duane C. Hanselman,et al.  Brushless Permanent-Magnet Motor Design , 1994 .

[13]  Johan Meyer,et al.  Brushless DC motor characterisation and selection for a fixed wing UAV , 2011, IEEE Africon '11.

[14]  Kadir Sabanci,et al.  A study on visual features of leaves in plant identification using artificial intelligence techniques , 2019, Comput. Electron. Agric..

[15]  Mustafa Turkmen,et al.  Neural models for quasi-static analysis of conventional and supported coplanar waveguides , 2007 .

[16]  Ebrahim Farjah,et al.  An Efficient Regenerative Braking System Based on Battery/Supercapacitor for Electric, Hybrid, and Plug-In Hybrid Electric Vehicles With BLDC Motor , 2017, IEEE Transactions on Vehicular Technology.

[17]  Ibrahim Sefa,et al.  A static exciter with interleaved buck converter for synchronous generators , 2017 .

[18]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..

[19]  Kacem Gargouri.  Electronic Commutator Direct Current (ECDC) machine , 2012 .

[20]  Kadir Sabanci,et al.  A parametric simulation of the wireless power transfer with inductive coupling for electric vehicles, and modelling with artificial bee colony algorithm , 2020 .

[21]  Atif Iqbal,et al.  Direct Torque Control Based on Artificial Neural Network of a Five-Phase PMSM Drive , 2017 .

[22]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[23]  Đorđe Lekić,et al.  Split ratio optimization of high torque density PM BLDC machines considering copper loss density limitation and stator slot leakage , 2018, International Journal of Electrical Power & Energy Systems.

[24]  Akif Durdu,et al.  Human action recognition with bag of visual words using different machine learning methods and hyperparameter optimization , 2019, Neural Computing and Applications.

[25]  Durmus Uygun,et al.  A new topology for dual rotor/stator BLDC motors applied to marine thrusters , 2015, 2015 IEEE 5th International Conference on Power Engineering, Energy and Electrical Drives (POWERENG).

[26]  Ahmet Kayabasi.  Soft computing-based synthesis model for equilateral triangular ring printed antenna , 2018 .

[27]  N. Altin,et al.  Thermal Behavior of a Medium-Frequency Ferrite-Core Power Transformer , 2016, Journal of Electronic Materials.

[28]  Akif Durdu,et al.  Breast Cancer Diagnosis by Different Machine Learning Methods Using Blood Analysis Data , 2018, International Journal of Intelligent Systems and Applications in Engineering.

[29]  Jafar Milimonfared,et al.  Optimum Design of Tubular Permanent-Magnet Motors for Thrust Characteristics Improvement by Combined Taguchi–Neural Network Approach , 2010, IEEE Transactions on Magnetics.

[30]  E. Yiğit,et al.  Automatic Classification of Agricultural Grains: Comparison of Neural Networks , 2018 .

[31]  G. R. Bindu,et al.  Optimal design of a surface mounted permanent-magnet BLDC motor for spacecraft applications , 2011, 2011 International Conference on Emerging Trends in Electrical and Computer Technology.

[32]  Siddhartha Datta,et al.  Development of an artificial neural network model for adsorption and photocatalysis of reactive dye on TiO2 surface , 2010, Expert Syst. Appl..

[33]  C. Carunaiselvane,et al.  Generalized procedure for BLDC motor design and substantiation in MagNet 7.1.1 software , 2012, 2012 International Conference on Computing, Electronics and Electrical Technologies (ICCEET).

[34]  Piotr Bilski,et al.  Application of Support Vector Machines to the induction motor parameters identification , 2014 .

[35]  Ömer Faruk Ertugrul,et al.  Detecting fault type and fault location in power transmission lines by extreme learning machines , 2015, 2015 23nd Signal Processing and Communications Applications Conference (SIU).

[36]  Adi Ben-Israel,et al.  Generalized inverses: theory and applications , 1974 .