An adaptive predictive control based on a quasi-ARX neural network model

Jami'in, Mohammad Abu; Sutrisno, Imam; Hu, Jinglu; Mariun, Norman; Marhaban, Mohammad Hamiruce

doi:10.1109/icarcv.2014.7064314

Cited by 14 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is difficult for the control signal calculated based on a nonlinear estimator to guarantee the stability of the closed‐loop controller. Therefore, a linear estimator is used to keep the closed‐loop stability . Thus, the switching line is introduced between the linear part θ and the nonlinear part δ ( ξ ( t )) of an SDPE, described as follows:

\begin{matrix} eqnarrayleft center right \\ eqnarray-1 \hat{ℵ} (ξ (t)) & eqnarray-2 = & eqnarray-3 \hat{θ} + χ (t) \hat{δ} \end{matrix}

\begin{matrix} eqnarrayleft center right \\ eqnarray-1 & eqnarray-2 & eqnarray-3 \\ eqnarray-1 u (t) & eqnarray-2 = & eqnarray-3 χ (t) u_{n} + (1 - χ (t)) u_{l} (t) \end{matrix}

where u l is a control signal calculated by the linear robust control that uses the parameters of the linear estimator

\overset{θ}{true}

, and u n is a control signal from the nonlinear robust control that uses the parameters of the nonlinear estimator by summing

\overset{θ}{true}

and

\overset{δ}{true} (ξ (t))

.…”

Section: Control Strategymentioning

confidence: 99%

See 1 more Smart Citation

Quasi‐ARX neural network based adaptive predictive control for nonlinear systems

Jami'in

Marhaban

et al. 2015

IEEJ Transactions Elec Engng

Self Cite

View full text Add to dashboard Cite

In this paper, a new switching mechanism is proposed based on the state of dynamic tracking error so that more information will be provided –not only the error but also a one up to pth differential error will be available as the switching variable. The switching index is based on the Lyapunov stability theory. Thus the switching mechanism can work more effectively and efficiently. A simplified quasi‐ARX neural‐network (QARXNN) model presented by a state‐dependent parameter estimation (SDPE) is used to derive the controller formulation to deal with its computational complexity. The switching works inside the model by utilizing the linear and nonlinear parts of an SDPE. First, a QARXNN is used as an estimator to estimate an SDPE. Second, by using SDPE, the state of dynamic tracking error is calculated to derive the switching index. Additionally, the switching formula can use an SDPE as the switching variable more easily. Finally, numerical simulations reveal that the proposed control gives satisfactory tracking and disturbance‐rejection performances. Experimental results demonstrate its effectiveness. © 2015 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

show abstract

\begin{matrix} eqnarrayleft center right \\ eqnarray-1 \hat{ℵ} (ξ (t)) & eqnarray-2 = & eqnarray-3 \hat{θ} + χ (t) \hat{δ} \end{matrix}

\begin{matrix} eqnarrayleft center right \\ eqnarray-1 & eqnarray-2 & eqnarray-3 \\ eqnarray-1 u (t) & eqnarray-2 = & eqnarray-3 χ (t) u_{n} + (1 - χ (t)) u_{l} (t) \end{matrix}

where u l is a control signal calculated by the linear robust control that uses the parameters of the linear estimator

\overset{θ}{true}

, and u n is a control signal from the nonlinear robust control that uses the parameters of the nonlinear estimator by summing

\overset{θ}{true}

and

\overset{δ}{true} (ξ (t))

.…”

Section: Control Strategymentioning

confidence: 99%

“…The switching index between the linear and nonlinear controller was proposed by some researchers . The switching rule is based on the convergence index of error, which is a function of the estimation error of the linear and nonlinear adaptive controllers.…”

Section: Introductionmentioning

confidence: 99%

Quasi‐ARX neural network based adaptive predictive control for nonlinear systems

Jami'in

Marhaban

et al. 2015

IEEJ Transactions Elec Engng

Self Cite

View full text Add to dashboard Cite

show abstract

Detection of Oil and Filter Feasibility in Ship Gearbox with SVM (Support Vector Machine) Method Based on Microcontroller

Santosa

Saputra²,

Sutrisno³

et al. 2020

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Lubrication systems on ships are vital for a ship to operate while sailing. Lubrication serves to prevent direct friction between components on the ship engine, especially the gearbox. Gearbox is one of the components of the ship crane that acts as the propeller of the ship. Obviously related to friction between components, therefore a lubrication system is needed. Some lubrication systems on Indonesian warships still use manual systems to monitor oil and filter change schedules. This can make the operator forget about the oil and filter change schedule. With the development of technology that is now the author makes a prototype with an oil and filter feasibility detection system on a ship gearbox. The author uses the SVM method that is able to classify properly or not like an oil. By using a viscosity sensor and a temperature sensor to be processed by the SVM method and a color sensor to detect a color in the oil filter. The results of the SVM method are quite accurate with 100% accuracy can distinguish good and bad oil from the samples used are new oil and used oil. There is a change in the intensity of the light that causes the color sensor readings in conditions of 100%, conditions of 30%, conditions of 40%, and conditions of 50%.

show abstract

Determination of the requirement resistant for Ship-RUV trust power to maneuvering and performance

Rahmad¹,

Sutrisno²,

Budianto³

et al. 2021

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

The resistance requirement of Ship-RUV is very much needed for the maneuvering process by placing the motor and the propeller as the driving force. In this case the propeller and motor components in the Ship-RUV component are installed with a KV 1000 KV motor with 12000 RPM with a number of 6 Motor-propellers. Propeller conditions are installed in the rear and bottom conditions of the Ship-RUV. This function is used for operational movement when the hull of the ship. Where the design of the motor propeller selection is based on the calculation of resistance obtained from the empirical calculation formula. In the calculation of resistance, the amount of resistance of the Ship-RUV is 16 N to be able to move and operate. The condition of the speed of the Ship-RUV in its operation is planned to be able to move in the air reaching a service speed of 5 knots.

show abstract

An adaptive predictive control based on a quasi-ARX neural network model

Cited by 14 publications

References 15 publications

Quasi‐ARX neural network based adaptive predictive control for nonlinear systems

Quasi‐ARX neural network based adaptive predictive control for nonlinear systems

Detection of Oil and Filter Feasibility in Ship Gearbox with SVM (Support Vector Machine) Method Based on Microcontroller

Determination of the requirement resistant for Ship-RUV trust power to maneuvering and performance

Contact Info

Product

Resources

About