Neural Network Designs for Partially Known Dynamic Systems

1994 ◽  
Vol 116 (3) ◽  
pp. 407-409 ◽  
Author(s):  
S. I. Mistry ◽  
S. S. Nair
Keyword(s):  
Dynamic Systems ◽  
Machine Tools ◽  
Hardware Implementation ◽  
Back Propagation ◽  
Neural Dynamic ◽  
Modeling And Control ◽  
Training Scheme ◽  
Network Training ◽  
On Line ◽  
And Control

Algorithms are investigated for system identification and control using neural networks and validated using on-line hardware implementation. Such algorithms require very little knowledge about the system which, together with their capability of learning, make them attractive for the modeling and control of nonlinear partially known dynamic systems. An implementation architecture for neural dynamic back propagation suitable for application to other machine tools and manufacturing processes, and a network training scheme with more general features are proposed.

NEURAL MODELING AND CONTROL OF DYNAMIC SYSTEMS WITH HYSTERESIS

2007 ◽  
Vol 31 (1) ◽  
pp. 127-141
Author(s):  
Yonghong Tan ◽  
Xinlong Zhao
Keyword(s):  
Dynamic Systems ◽  
Control Strategy ◽  
Neural Modeling ◽  
Modeling And Control ◽  
Control Scheme ◽  
The Neural Networks ◽  
Adaptive Control Strategy ◽  
Set Up ◽  
Modeling Strategy ◽  
And Control

A hysteretic operator is proposed to set up an expanded input space so as to transform the multi-valued mapping of hysteresis to a one-to-one mapping so that the neural networks can be applied to model of the behavior of hysteresis. Based on the proposed neural modeling strategy for hysteresis, a pseudo control scheme is developed to handle the control of nonlinear dynamic systems with hysteresis. A neural estimator is constructed to predict the system residual so that it avoids constructing the inverse model of hysteresis. Thus, the control strategy can be used for the case where the output of hysteresis is unmeasurable directly. Then, the corresponding adaptive control strategy is presented. The application of the novel modeling approach to hysteresis in a piezoelectric actuator is illustrated. Then a numerical example of using the proposed control strategy for a nonlinear system with hysteresis is presented.

Modeling and Control of SMT Manufacturing Lines Using Hybrid Dynamic Systems

2003 ◽  
pp. 66-80 ◽  
Author(s):  
L. G. Barajas ◽  
A. Kansal ◽  
A. Saxena ◽  
M. Egerstedt ◽  
A. Goldstein ◽  
...  
Keyword(s):  
Dynamic Systems ◽  
Modeling And Control ◽  
And Control

Modeling and Control of Interconnected Dimensionless Dynamic Systems

2009 ◽  
Author(s):  
Scott Manwaring ◽  
Andrew Alleyne
Keyword(s):  
Dimensional Analysis ◽  
Dynamic Systems ◽  
Controller Design ◽  
Fluid Power ◽  
Modeling And Control ◽  
Initial Investigation ◽  
And Control ◽  
Insight Into ◽  
Original Dynamic

Previous work has found benefit in using dimensional analysis in the modeling and control of dynamic systems. What has not been explored is how multiple dimensionless dynamic systems would interconnect and interact with one another. This work presents an initial investigation into the interconnection of dimensionless dynamic systems, including an analysis of the differences between interconnecting dimensioned and dimensionless systems. A strategy is developed to interconnect dimensionless dynamic systems and explored using models of multiple fluid power components. The interconnection strategy is tested through controller design and simulation, which reveals insight into the dimensionless transformation of the original dynamic systems.

On-Line Thermal Control for Injection Moulding Process

2013 ◽  
Author(s):  
Jaho Seo ◽  
Amir Khajepour ◽  
Jan P. Huissoon ◽  
Young-Jun Park
Keyword(s):  
Injection Moulding ◽  
Thermal Control ◽  
Production Quality ◽  
Modeling And Control ◽  
Moulding Process ◽  
Cycle Times ◽  
Plastic Injection Moulding ◽  
Injection Moulding Process ◽  
On Line ◽  
And Control

Thermal control is a key issue for injection moulding process due to its effects on production quality and rate. In this study, an on-line thermal control strategy is provided for effective thermal management in plastic injection moulding process. The strategy covers for methods in determining sensor locations as a prerequisite step for modeling and control, identifying a thermal dynamic model of a mould with uncertainties and designing a cavity wall temperature controller. A verification of the designed controller’s performance is carried out from the viewpoints of accuracy in on-line temperature tacking and response time under different injection moulding process with various cycle-times.

Modeling and Control of a Refrigerant Evaporator

1985 ◽  
Vol 107 (4) ◽  
pp. 235-240 ◽  
Author(s):  
W.-D. Gruhle ◽  
R. Isermann
Keyword(s):  
Control Variable ◽  
Modeling And Control ◽  
Lumped Parameter ◽  
Lumped Parameter Models ◽  
Expansion Valve ◽  
On Line ◽  
Process Computer ◽  
Dry Out ◽  
Random Fluctuations ◽  
And Control

Based on the balance equations for enthalpy, mass, and momentum a theoretical model of a refrigerant evaporator has been developed. The distributed parameter process is approximated by several lumped parameter models. The model is completed by equations for the expansion valve, the compressor and the superheater. Various effects, e.g., the random fluctuations of the liquid-dry-out-point can be explained by the model. The dynamic behavior of the evaporator is investigated as a function of the manipulating signal UEV (position of the expansion valve) and various disturbances (air temperature ϑA, condenser pressure pCd and compressor rotation speed nc), considering the superheating temperature ϑs as control variable and the evaporator performance Q˙E, which has to be optimized. Two controllers are considered. First, the control behavior with a conventional thermostatic expansion valve is shown, which often operates unstable. The control performance can be considerably improved by a controller whose structure and parameters are better adapted to the evaporation process. For the experiments a process computer is connected on-line to the process. It will be demonstrated that the performance of the evaporator and therefore its efficiency can be increased by at least 5 percent.

Incorporating Practical Laboratory Experiments to Reinforce Dynamic Systems and Control Concepts

2009 ◽  
Author(s):  
Melody L. Baglione
Keyword(s):  
Dynamic Systems ◽  
Laboratory Experiments ◽  
Pressure Control ◽  
Lessons Learned ◽  
Student Groups ◽  
Modeling And Control ◽  
Faculty Interaction ◽  
Hands On ◽  
Systems And Control ◽  
And Control

The Cooper Union is developing a new simultaneous lecture and laboratory approach to address the pedagogical challenge of finding the appropriate balance between theory and hands-on experimentation in teaching dynamic systems and control concepts. The new approach dedicates one hour each week to laboratory experiments with the class subdivided into small student groups having greater faculty interaction. Bench top experiments from National Instruments and Quanser include DC motor and inverted pendulum modeling and control workstations. Process control test rigs from Feedback Inc. include level, flow, temperature, and pressure control trainers. Devoting significant time to laboratory experiments gives students the opportunities to fully appreciate feedback control concepts and to acquire valuable practical skills. This paper discusses the new instructional approach, preliminary results, lessons learned, and future plans for improving the systems and control curriculum.

scholarly journals Neural networks on-line optimized PID controller with wind gust rejection for a quad-rotor

2021 ◽  
Author(s):  
Chiraz Ben Jabeur ◽  
Hassene Seddik
Keyword(s):  
Neural Networks ◽  
Experimental Results ◽  
Wind Gust ◽  
Pd Controller ◽  
Hostile Environment ◽  
Modeling And Control ◽  
Self Tuning ◽  
On Line ◽  
Hostile Environments ◽  
And Control

Abstract In this paper a complete methodology of modeling and control of quad-rotor aircraft is exposed. In fact, a PD on-line optimized Neural Networks Approach (PD-NN) is developed and applied to control the attitude of a quad-rotor that is evolving in hostile environment with wind gust disturbances and should maintain its position despite of these troubles. Whereas PD classical controllers are dedicated for the positions, altitude and speed control. The main objective of this work is to develop a smart Self-Tuning PD controller for attitude angles control, based on neural networks capable of controlling the quad-rotor for an optimized performance thus following a desired trajectory. Many problems could arise if the quad-rotor is evolving in hostile environments presenting irregular troubles such as wind gusts modeled and applied to the overall system. The quad-rotor has to rapidly achieve tasks while guaranteeing stability and precision and must behave quickly with regards to decision making fronting turbulences. This technique offers some advantages over conventional control methods such as PD controllers. Simulation results are achieved with the use of Matlab/Simulink environment and are established on a comparative study between PD and PD-NN controllers founded on wind disturbances application. These obstacles are applied with numerous degrees of strength to test the quad-rotor comportment. Experimental results are reached with the use of the V-REP environment with which some trajectories are tracked and then applied on a BLADE Inductrix FPV+. These simulations and experimental results are acceptable and have confirmed the efficiency of the proposed PD-NN approach. In fact, this controller has fairly smaller errors than the PD controller and has an improved ability to reject troubles. Moreover, it has confirmed to be extremely vigorous and efficient fronting disturbances in the form of wind disturbances.

Sign in / Sign up

Export Citation Format

Share Document