Modeling MCSRM with artificial neural network

Karaçor, Mevlüt; Yilmaz, K.; Kuyumcu, Feriha Erfan

doi:10.1109/acemp.2007.4510569

Cited by 7 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Authors in [62] and [73] used feed-forward artificial neural network (FF-ANN) to model the mutual coupling with reduced FEA steps for CSRM and SL-FP-MCSRM, respectively. In [73], FEA results were for 2-phase excitation with keeping one phase current as a constant and assuming linear mutual effect of the constant phase current on the other phase. Results obtained from FEA are applied to ANN through a back-projective training.…”

Section: ) Other Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Mutually Coupled Switched Reluctance Motor: Fundamentals, Control, Modeling, State of the Art Review and Future Trends

2019

View full text Add to dashboard Cite

Switched reluctance motor (SRM) is gaining more interest in the last decades due to its simple and robust structure. SRMs are classified into conventional SRMs (CSRMs) and mutually coupled SRMs (MCSRMs). CSRMs are based on single-phase excitation and torque is generated by the variation of selfinductance with rotor position. MCSRMs are based on multi-phase excitation and torque is produced by the rate of change of both self-and mutual inductances. MCSRM has the advantages of using the standard voltage source inverter at balanced current operation, when the sum of the phase currents is zero, while CSRM requires an asymmetrical converter. This paper presents the state-of-the-art review of MCSRMs, including operating concept, winding, and pole configurations, control methods by using different current waveforms, performance comparison of MCSRM configurations, modeling methods, and future work for improving MCSRM performance. INDEX TERMS Double/single layer winding, motor control, mutually coupled switched reluctance motor, modeling, short/full pitched winding, state-of-the-art review.

show abstract

Section: ) Other Methodsmentioning

confidence: 99%

“…Keeping one phase current constant value reduced the FEA steps significantly. However, the results did not account for saturation and an experimental validation was not provided [73].…”

Section: ) Other Methodsmentioning

confidence: 99%

Mutually Coupled Switched Reluctance Motor: Fundamentals, Control, Modeling, State of the Art Review and Future Trends

2019

View full text Add to dashboard Cite

show abstract

“…It is worth mentioning that the methods introduced in [17], [18], [21]- [25] are for 3-phase FP MCSRM since that winding configuration simplifies the modeling of the mutual inductance. In FP MCSRM, the two excited phases magnetize a single stator pole which makes the FP MCSRM operation with two-phase excitation similar to the short pitched CSRM with single-phase excitation [3].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Vector Modeling of Three-Phase Mutually Coupled Switched Reluctance Machines with Single dq-Quadrant Look-up Tables

Azer

Nalakath

Howey

et al. 2020

IEEE Open J. Ind. Electron. Soc.

View full text Add to dashboard Cite

This paper presents a dynamic modeling method for a 3-phase mutually coupled switched reluctance machine (MCSRM) considering spatial harmonics and saturation. The conventional modeling methods of MCSRMs are based on 3D look-up tables (LUTs), where the phase flux linkages are considered as state variables. These 3D LUTs describe the phase currents with respect to phase flux linkages and rotor position. The 3D LUTs represent two dq quadrants and are obtained from finite element analysis (FEA) by multi-phase excitation where the excitation currents cover two quadrants in the dq synchronous reference frame. The LUTs used in the proposed method represent the phase current and electromagnetic torque as vectors. The magnitude and the angle of these vectors are represented by the sine and cosine Fourier coefficients. Hence, rotor position is not an input to the LUTs and the proposed method uses 2D LUTs. Additionally, the flux linkages in the four dq quadrants possess symmetry for MCSRMs. Therefore, LUTs corresponding to only one dq quadrant are required. The single-quadrant based LUTs reduces the number of FEA steps and the size of the LUTs by 50% compared to the two-quadrant LUT based models. Finally, the proposed method is validated using FEA and experiments for a 12/8 MCSRM.

show abstract

“…Thus, many studies focus on using novel heuristic optimization methods or evolutionary algorithms to resolve the problems of MLP learning algorithms [14]. Classical applied approaches are Particle Swarm Optimization (PSO) algorithms [15,16], Ant Colony Optimization (ACO) [17], and Artificial Bee Colony (ABC) [18]. However, the No Free Lunch (NFL) theorem [19,20] states that no heuristic algorithm is best suited for solving all optimization problems.…”

Section: Introductionmentioning

confidence: 99%

Developing a Novel Hybrid Biogeography-Based Optimization Algorithm for Multilayer Perceptron Training under Big Data Challenge

Chen

et al. 2018

Scientific Programming

View full text Add to dashboard Cite

A Multilayer Perceptron (MLP) is a feedforward neural network model consisting of one or more hidden layers between the input and output layers. MLPs have been successfully applied to solve a wide range of problems in the fields of neuroscience, computational linguistics, and parallel distributed processing. While MLPs are highly successful in solving problems which are not linearly separable, two of the biggest challenges in their development and application are the local-minima problem and the problem of slow convergence under big data challenge. In order to tackle these problems, this study proposes a Hybrid Chaotic Biogeography-Based Optimization (HCBBO) algorithm for training MLPs for big data analysis and processing. Four benchmark datasets are employed to investigate the effectiveness of HCBBO in training MLPs. The accuracy of the results and the convergence of HCBBO are compared to three well-known heuristic algorithms: (a) Biogeography-Based Optimization (BBO), (b) Particle Swarm Optimization (PSO), and (c) Genetic Algorithms (GA). The experimental results show that training MLPs by using HCBBO is better than the other three heuristic learning approaches for big data processing.

show abstract

Modeling MCSRM with artificial neural network

Cited by 7 publications

References 5 publications

Mutually Coupled Switched Reluctance Motor: Fundamentals, Control, Modeling, State of the Art Review and Future Trends

Mutually Coupled Switched Reluctance Motor: Fundamentals, Control, Modeling, State of the Art Review and Future Trends

Dynamic Vector Modeling of Three-Phase Mutually Coupled Switched Reluctance Machines with Single dq-Quadrant Look-up Tables

Developing a Novel Hybrid Biogeography-Based Optimization Algorithm for Multilayer Perceptron Training under Big Data Challenge

Contact Info

Product

Resources

About