Surrogate Modeling of Electrical Machine Torque Using Artificial Neural Networks

Tahkola, Mikko; Keränen, Janne; Sedov, Denis; Far, Mehrnaz Farzam; Kortelainen, Juha

doi:10.1109/access.2020.3042834

Cited by 30 publications

(11 citation statements)

References 68 publications

(68 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning is used for electrical machines optimization through automating surrogate model building within the optimization loop [216]. Using surrogate models reduces the ON\OFF or GA-based topology optimization time.…”

Section: Topology Optimization Based On Deep Learningmentioning

confidence: 99%

Geometry and Topology Optimization of Switched Reluctance Machines: A Review

Abdalmagid

Sayed²,

Bakr

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Switched reluctance machines (SRMs) have recently attracted more interest in many applications due to the volatile prices of rare-earth permanent magnets (PMs) used in permanent magnet synchronous machines (PMSMs). They also have rugged construction and can operate at high speeds and high temperatures. However, acoustic noise and high torque ripples, in addition to the relatively low torque density, present significant challenges. Geometry and topology optimization are applied to overcome these challenges and enable SRMs to compete with PMSMs. Key geometric design parameters are optimized to minimize various objective functions within geometry optimization. On the other hand, the material distribution in a particular design space within the machine domain may be optimized using topology optimization. We discuss how these techniques are applied to optimize the geometries and topologies of SRMs to enhance machine performance. As optimizing the machine geometry and material distribution at the design phase is of substantial significance, this work offers a comprehensive literature review on the current state of the art and the possible trends in the optimization techniques of SRMs. The paper also reviews different configurations of SRMs and stochastic and deterministic optimization techniques utilized in optimizing different configurations of the machine.

show abstract

Section: Topology Optimization Based On Deep Learningmentioning

confidence: 99%

Geometry and Topology Optimization of Switched Reluctance Machines: A Review

Abdalmagid

Sayed²,

Bakr

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The resulting input, z, is subject to a transfer function computing the neural network's output. A non-linear activation function, the sigmoid function, is adopted in (5).…”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…Different methods for data reduction based on machine learning allow obtaining quickly high-accuracy models. Such an example is presented in [5], where a comparison of various data sampling and their effect on the accuracy of an ANN for torque estimation is discussed.…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Network and Data Dimensionality Reduction Based on Machine Learning Methods for PMSM Model Order Reduction

et al. 2021

View full text Add to dashboard Cite

The present paper targets a solution for permanent motor synchronous machine (PMSM) model order reduction (MOR) using artificial neural networks and machine learning techniques for data dimensionality reduction. The neural networks are trained using data obtained from a series of electromagnetic Finite Element Analysis (FEA), conducted in conditions imposed by the data dimensionality reduction method. The workflow proposed to build the PMSM MOR, starts with data generation, goes further to its post-processing, and finishes with the model training and experimental validation. In the study, data dimensionality reduction procedure (adaptive data generation) is performed to increase the computational efficiency, also maintaining the model accuracy. Different data reduction approaches are compared from the computational cost's point of view and their ease of use. The obtained results are compared to those obtained from FEA seeking the best solution for building the dynamic model. The resulting ROM is included in a real-time control prototyping platform to characterize machine's performances. The model accuracy and its usability are proved in a comparative analysis with simulated versus experimental measurements.INDEX TERMS artificial neural networks, adaptive data generation, machine learning, permanent magnet synchronous machine, dynamic simulation, real-time.

show abstract

“…In order to simulate system-level behavior of PMSMs, highfidelity reduced-order models [20] are needed that include saturation, cross-saturation and slotting effect. A series of magnetostatic FEA that sweep through the current (i dq ) and rotor position (θ m ) range are performed and the resulting electromagnetic torque (T em ), flux-linkages (λ dq ) and airgap forces (F rad/tan ) are post-processeed and stored in LUTs as shown in [21].…”

Section: Look-up Table Based Nonlinear Pmsm Modelmentioning

confidence: 99%

PMSM Current Shaping for Minimum Joule Losses While Reducing Torque Ripple and Vibrations

et al. 2021

View full text Add to dashboard Cite

This paper presents a current shaping method for torque ripple and mean air-gap radial forceshape harmonics reduction, under minimum Joule losses, used for air-born and structure-born vibration reduction in 3-phase PMSM electric drives. The main source for structure-born noise in electric powertrains is the torque ripple, while the main source for air-born noise are the radial air-gap forces. The proposed method uses a Fourier-decomposed LUT model obtained from updating the 2D electromagnetic FE model using test-bench results. Modal testing is used to update the structural model, and the vibration response on the machine full RPM range is determined using the vibration-synthesis method. The proposed current shaping algorithm is deterministic and can be used on any topology of 3-phase PMSMs. The torque and mean air-gap force harmonics that are intended for reduction can be arbitrary selected and their minimization can be fully completed if the maximum current and voltage constraint are respected. On the machine under test, vibration reduction is accomplished, especially for the mechanical orders that interact with the second mode-shape.

show abstract

Surrogate Modeling of Electrical Machine Torque Using Artificial Neural Networks

Cited by 30 publications

References 68 publications

Geometry and Topology Optimization of Switched Reluctance Machines: A Review

Geometry and Topology Optimization of Switched Reluctance Machines: A Review

Artificial Neural Network and Data Dimensionality Reduction Based on Machine Learning Methods for PMSM Model Order Reduction

PMSM Current Shaping for Minimum Joule Losses While Reducing Torque Ripple and Vibrations

Contact Info

Product

Resources

About