Machine-Made Synthesis of Stabilization System by Modified Cartesian Genetic Programming

Diveev, Askhat; Shmalko, Elizaveta

doi:10.1109/tcyb.2020.3039693

Cited by 15 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Today, modern numerical machine learning methods of symbolic regression can be applied to fnd a solution for generic dynamic objects [36,37]. Further in the computational example, we use these symbolic regression methods for stabilization system synthesis.…”

Section: Synthesized Approach To the Solution Of The Extended Optimal...mentioning

confidence: 99%

Extended Statement of the Optimal Control Problem and Machine Learning Approach to Its Solution

Shmalko

Diveev

2022

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

Engineers strive to realize the goal of control in the best possible way based on a given quality criterion when developing control system. The well-known optimal control problem requires finding a solution as a function of time. Such a function cannot be directly used to control a real object because its application corresponds to an open-loop control system and engineers usually complete it with a feedback stabilization system. Hence, there is an obvious need to reformulate the optimal control problem so that its solution can be directly applied to real objects. The paper presents a new extended statement of the optimal control problem. An additional requirement for the control function is introduced to give the system describing the control object properties that will ensure the stability of solutions. The desired control function must provide for the optimal trajectory given the properties of the attractor in the neighbourhood. The solution to the extended optimal control problem can be directly used to control a real object. The paper presents a computational machine learning approach to solving the extended problem of optimal control based on the application of a synthesized optimal control technique. Examples of the practical solution to the stated problem are given to illustrate the efficiency of the approach, where the solution to the conventional optimal control problem is compared with the proposed extended one in the presence of perturbations in models and initial conditions.

show abstract

Section: Synthesized Approach To the Solution Of The Extended Optimal...mentioning

confidence: 99%

Extended Statement of the Optimal Control Problem and Machine Learning Approach to Its Solution

Shmalko

Diveev

2022

Mathematical Problems in Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…The operations of addition and multiplication were used as binary operations, and a set of 28 smooth elementary functions was used as unary operations. The description of these functions can be found in the supplementary material to [28].…”

Section: Computational Experimentsmentioning

confidence: 99%

Control Synthesis as Machine Learning Control by Symbolic Regression Methods

Shmalko

Diveev

2021

Applied Sciences

Self Cite

View full text Add to dashboard Cite

The problem of control synthesis is considered as machine learning control. The paper proposes a mathematical formulation of machine learning control, discusses approaches of supervised and unsupervised learning by symbolic regression methods. The principle of small variation of the basic solution is presented to set up the neighbourhood of the search and to increase search efficiency of symbolic regression methods. Different symbolic regression methods such as genetic programming, network operator, Cartesian and binary genetic programming are presented in details. It is shown on the computational example the possibilities of symbolic regression methods as unsupervised machine learning control technique to the solution of MLC problem of control synthesis for obtaining the stabilization system for a mobile robot.

show abstract

“…Update the position of population using Eq. (35) The main purpose of using LSA in this problem is to get optimal control parameters of the NL-PID controller which is responsible for stabilization and tracking control of the x-z pendulum as compared to other optimization techniques. Finding the optimal parameters would lead to fine tuning of the PID controller and simultaneously improvement in the transient as well as steady state response of the system under consideration.…”

Section: Lightning Search Algorithm (Lsa)mentioning

confidence: 99%

“…It is stated that optimal control and predictive control may produce quite well results but they may also suffer about stability in some cases. There are recently applied symbolic regression methods for the automatic synthesis of the stabilization system [34,35]. These symbolic regression methods are seemed as the further development of neural networks which can automate the process of synthesis of control systems.…”

Section: Introductionmentioning

confidence: 99%

Stabilization and tracking control of an x-z type inverted pendulum system using Lightning Search Algorithm tuned nonlinear PID controller

Özmen

Marul

2021

Robotica

View full text Add to dashboard Cite

Inverted pendulum systems (IPSs) are mostly used to demonstrate the control rules for keeping the pendulum at a balanced upright position due to a slight force applied to the cart system. This paper presents an application for nonlinear control of an x-z type IPS by using a proportional-integral-derivative (PID) controller with newly established evolutionary tuning method Lightning Search Algorithm (LSA). A single, double and triple PID controller system is tested with the conventional and the self-tuning controllers to get a better understanding of the performance of the given system. The mathematical modelling of the x-z type IPS, the theoretical explanation of the LSA and the simulation analysis of the x-z type IPS is put forward entirely. The LSA algorithm solves the optimization problem of PID controller in an evolutionary way. The most effective way of making comparisons is evaluating the performance results with a well-known optimization technique or with the previous accepted results. We have compared the system’s performance with particle swarm optimization and with a classical control study in the literature. According to the simulation results, LSA-tuned PID controller has the ability to decrease the overshoot better than the conventional-tuned controllers. Finally, it can be concluded that the LSA-supported PID can better stabilize the pendulum angle and track the reference better for non-disturbed and the slightly disturbed systems.

show abstract

Machine-Made Synthesis of Stabilization System by Modified Cartesian Genetic Programming

Cited by 15 publications

References 26 publications

Extended Statement of the Optimal Control Problem and Machine Learning Approach to Its Solution

Extended Statement of the Optimal Control Problem and Machine Learning Approach to Its Solution

Control Synthesis as Machine Learning Control by Symbolic Regression Methods

Stabilization and tracking control of an x-z type inverted pendulum system using Lightning Search Algorithm tuned nonlinear PID controller

Contact Info

Product

Resources

About