Pressure prediction on a variable-speed pump controlled hydraulic system using structured recurrent neural networks

2014-05-01
This paper presents a study to predict the pressures in the cylinder chambers of a variable-speed pump controlled hydraulic system using structured recurrent neural network topologies where the rotational speed of the pumps, the position and the average velocity of the hydraulic actuator are used as their inputs. The paper elaborates the properties of such networks in extended time periods through detailed simulation- and experimental studies where black-box modeling approaches generally fail to yield acceptable performance. As alternative estimation techniques, both linear- and extended Kalman filters are considered in this paper. The estimation properties of the devised network models are comparatively evaluated and their potential application areas are discussed in detail.
CONTROL ENGINEERING PRACTICE

Suggestions

Optimum geometry for torque ripple minimization of switched reluctance motors
Sahin, F; Ertan, HB; Leblebicioğlu, Mehmet Kemal (Emerald, 1995-12-01)
This paper briefly describes an approach to determine the optimum magnetic circuit parameters to minimize low speed torque ripple for switched reluctance (SR) motors. For prediction of the torque ripple, normalized data obtained from field solution and a neural network approach is used. Comparison of experimental results with computations illustrates the accuracy of the method. The optimization method is briefly described and some results are presented.
Nonlinear time-varying dynamic analysis of a spiral bevel geared system
Yavuz, Siar Deniz; Sarıbay, Zihni Burcay; Ciğeroğlu, Ender (Springer Science and Business Media LLC, 2018-06-01)
In this paper, a nonlinear time-varying dynamic model of a drivetrain composed of a spiral bevel gear pair, shafts and bearings is developed. Gear shafts are modeled by utilizing Timoshenko beam finite elements, and the mesh model of a spiral bevel gear pair is used to couple them. The dynamic model includes the flexibilities of shaft bearings as well. Gear backlash and time variation of mesh stiffness are incorporated into the dynamic model. Clearance nonlinearity of bearings is assumed to be negligible, w...
Nonlinear dynamic analysis of a drivetrain composed of spur, helical and spiral bevel gears
Yavuz, Siar Deniz; Saribay, Zihni Burcay; Ciğeroğlu, Ender (Springer Science and Business Media LLC, 2020-06-01)
This paper proposes a dynamic model for the first time in order to investigate nonlinear time-varying dynamic behavior of a drivetrain including parallel axis gears (such as spur and helical gears) and intersecting axis gears (such as spiral bevel gears). Flexibilities of shafts and bearings are included in the dynamic model by the use of finite element modeling. Finite element models of shafts are coupled with each other by the mesh models of gear pairs including backlash nonlinearity and fluctuating mesh ...
Simple derivative-free nonlinear state observer for sensorless AC drives
Akin, Bilal; Orguner, Umut; Ersak, Aydin; Ehsani, Mehrdad (Institute of Electrical and Electronics Engineers (IEEE), 2006-10-01)
In this paper, a new Kalman filtering technique, unscented Kalman filter (UKF), is utilized both experimentally and theoretically as a state estimation tool in field-oriented control (FOC) of sensorless ac drives. Using the advantages of this recent derivative-free nonlinear estimation tool, rotor speed and dq-axis fluxes of an induction motor are estimated only with the sensed stator currents and voltages information. In order to compare the estimation performances of the extended Kalman filter (EKF) and U...
A Mathematical Model for Simulation of Flow Rate and Chamber Pressures in Spool Valves
Afatsun, Ahmet C.; Balkan, Raif Tuna (ASME International, 2019-02-01)
In this paper, a mathematical model to simulate the pressure and flow rate characteristics of a spool valve is derived. To improve the simulation accuracy, the discharge coefficient through the spool valve ports is assumed to be a function of both the Reynolds number and the orifice geometry rather than treating it as a constant. Parameters of the model are determined using the data obtained by computational fluid dynamics (CFD) analyses conducted on two-dimensional axisymmetric domains using ANSYS FLUENT 1...
Citation Formats
E. KILIÇ, M. Dölen, H. Çalışkan, A. B. Koku, and R. T. Balkan, “Pressure prediction on a variable-speed pump controlled hydraulic system using structured recurrent neural networks,” CONTROL ENGINEERING PRACTICE, pp. 51–71, 2014, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/37207.