%0 Journal Article %1 MELLAH_2016 %A MELLAH, Hacene %A Eddine, Kamel %A TALEB, Rachid %D 2016 %I The Science and Information Organization %J International Journal of Advanced Computer Science and Applications %K Bayesian DC and backpropagation, cascade-forward estimations, modeling, motor, myown network neural parameter regulation, state thermal %N 7 %R 10.14569/ijacsa.2016.070731 %T Intelligent Sensor Based Bayesian Neural Network for Combined Parameters and States Estimation of a Brushed DC Motor %U https://doi.org/10.14569%2Fijacsa.2016.070731 %V 7 %X The objective of this paper is to develop an Artificial Neural Network (ANN) model to estimate simultaneously, parameters and state of a brushed DC machine. The proposed ANN estimator is novel in the sense that his estimates simultaneously temperature, speed and rotor resistance based only on the measurement of the voltage and current inputs. Many types of ANN estimators have been designed by a lot of researchers during the last two decades. Each type is designed for a specific application. The thermal behavior of the motor is very slow, which leads to large amounts of data sets. The standard ANN use often Multi-Layer Perceptron (MLP) with Levenberg-Marquardt Backpropagation (LMBP), among the limits of LMBP in the case of large number of data, so the use of MLP based on LMBP is no longer valid in our case. As solution, we propose the use of Cascade-Forward Neural Network (CFNN) based Bayesian Regulation backpropagation (BRBP). To test our estimator robustness a random white-Gaussian noise has been added to the sets. The proposed estimator is in our viewpoint accurate and robust.

@article{MELLAH_2016, abstract = {The objective of this paper is to develop an Artificial Neural Network (ANN) model to estimate simultaneously, parameters and state of a brushed DC machine. The proposed ANN estimator is novel in the sense that his estimates simultaneously temperature, speed and rotor resistance based only on the measurement of the voltage and current inputs. Many types of ANN estimators have been designed by a lot of researchers during the last two decades. Each type is designed for a specific application. The thermal behavior of the motor is very slow, which leads to large amounts of data sets. The standard ANN use often Multi-Layer Perceptron (MLP) with Levenberg-Marquardt Backpropagation (LMBP), among the limits of LMBP in the case of large number of data, so the use of MLP based on LMBP is no longer valid in our case. As solution, we propose the use of Cascade-Forward Neural Network (CFNN) based Bayesian Regulation backpropagation (BRBP). To test our estimator robustness a random white-Gaussian noise has been added to the sets. The proposed estimator is in our viewpoint accurate and robust.}, added-at = {2018-07-12T15:16:21.000+0200}, author = {MELLAH, Hacene and Eddine, Kamel and TALEB, Rachid}, biburl = {https://www.bibsonomy.org/bibtex/260d9b11e71d7469cab291447aeef0e96/mellah}, doi = {10.14569/ijacsa.2016.070731}, interhash = {843283f504430b4f04ae3f628c1ac7dc}, intrahash = {60d9b11e71d7469cab291447aeef0e96}, journal = {International Journal of Advanced Computer Science and Applications}, keywords = {Bayesian DC and backpropagation, cascade-forward estimations, modeling, motor, myown network neural parameter regulation, state thermal}, number = 7, publisher = {The Science and Information Organization}, timestamp = {2018-07-12T15:19:02.000+0200}, title = {Intelligent Sensor Based Bayesian Neural Network for Combined Parameters and States Estimation of a Brushed {DC} Motor}, url = {https://doi.org/10.14569%2Fijacsa.2016.070731}, volume = 7, year = 2016 }