Parameter Tuning of MLP, RBF, and ANFIS Models Using Genetic Algorithm in Modeling and Classification Applications

Ansari, Sam; Alnajjar, Khawla A.; Abdallah, Saeed; Saad, Mohamed; El-Moursy, Ali A.

doi:10.1109/icit52682.2021.9491682

Cited by 10 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, boundary constraints of the training samples can also be utilized during the training of the network to further improve the accuracy of the RBFNN model [6]. The parameters of RBFNN can be optimized through multiple tests or using particle swarm optimization or genetic algorithm [7,8].…”

Section: Introductionmentioning

confidence: 99%

Modeling of nonlinear characteristics of switched reluctance motor based on optimized RBF neuron network

Li,

Ma,

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The strong nonlinearity of switched reluctance motor (SRM) makes it difficult to establish an accurate mathematical model of its electromagnetic characteristics. In this paper, an artificial neural network modeling method is adopted to estimate the nonlinear flux linkage characteristics of a four-phase SRM. Based on the samples obtained by experimental measurement, a radial basis function neural network is trained and further optimized using the K-Means algorithm. The modeling accuracy of the optimized flux linkage model is analyzed in detail and also verified by dynamic simulation of a direct instantaneous torque control system of the motor.

show abstract

Section: Introductionmentioning

confidence: 99%

Modeling of nonlinear characteristics of switched reluctance motor based on optimized RBF neuron network

Li,

Ma,

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…This can be done empirically, by varying the parameters in turn [31], [34]. Sensitivity analysis methods such as Morris' method [35], genetic algorithms (GA) or Tagushi's experimental design [36], [37] can also be used to select the parameters to be adjusted. Once the relevant hyperparameters have been selected, two tools developed in the scikit-learn Python librairy can be used:…”

mentioning

confidence: 99%