A hybrid Neural Network-Genetic Programming Intelligent Control approach

Francesco Marchetti; Edmondo Minisci

doi:10.1007/978-3-030-63710-1_19

A hybrid Neural Network-Genetic Programming Intelligent Control approach

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

Abstract

The proposed work aims to introduce a novel approach to Intelligent Control (IC), based on the combined use of Genetic Programming (GP) and feedforward Neural Network (NN). Both techniques have been successfully used in the literature for regression and control applications, but, while a NN creates a black box model, GP allows for a greater interpretability of the created model, which is a key feature in control applications. The main idea behind the hybrid approach proposed in this paper is to combine the speed and flexibility of a NN with the interpretability of GP. Moreover, to improve the robustness of the GP control law against unforeseen environmental changes, a new selection and crossover mechanisms, called Inclusive Tournament and Inclusive Crossover, are also introduced. The proposed IC approach is tested on the guidance control of a space transportation system and results, showing the potentialities for real applications, are shown and discussed.

Original language	English
Title of host publication	Bioinspired Optimization Methods and Their Applications
Editors	Bogdan Filipič, Edmondo Minisci, Massimiliano Vasile
Place of Publication	Cham, Switzerland
Publisher	Springer
Pages	240-254
Number of pages	15
ISBN (Print)	9783030637101
DOIs	https://doi.org/10.1007/978-3-030-63710-1_19
Publication status	Published - 16 Nov 2020
Event	Bioinspired Optimization Methods and their Applications 2020 - Université Libre de Bruxelles (Virtual), Bruxelles, Belgium Duration: 19 Nov 2020 → 20 Nov 2020 http://utopiae.eu/bioma-2020/

Conference

Conference	Bioinspired Optimization Methods and their Applications 2020
Abbreviated title	BIOMA 2020
Country	Belgium
City	Bruxelles
Period	19/11/20 → 20/11/20
Internet address	http://utopiae.eu/bioma-2020/

Keywords

Genetic Programming
Intelligent Control
Neural Networks
optimal control
space transportation system

Access to Document

10.1007/978-3-030-63710-1_19

Embargoed Document

Marchetti-Minisci-BIOMA2020-A-hybrid-Neural-Network-Genetic-Programming
Accepted author manuscript, 859 KB
Embargo ends: 16/11/21

Fingerprint Dive into the research topics of 'A hybrid Neural Network-Genetic Programming Intelligent Control approach'. Together they form a unique fingerprint.

1 Participation in conference

Bioinspired Optimization Methods and their Applications 2020
Francesco Marchetti (Participant)
19 Nov 2020 → 20 Nov 2020
Activity: Participating in or organising an event types › Participation in conference

Cite this

@inproceedings{45f91495103d4fb7b3196afd0695180e,

title = "A hybrid Neural Network-Genetic Programming Intelligent Control approach",

abstract = "The proposed work aims to introduce a novel approach to Intelligent Control (IC), based on the combined use of Genetic Programming (GP) and feedforward Neural Network (NN). Both techniques have been successfully used in the literature for regression and control applications, but, while a NN creates a black box model, GP allows for a greater interpretability of the created model, which is a key feature in control applications. The main idea behind the hybrid approach proposed in this paper is to combine the speed and flexibility of a NN with the interpretability of GP. Moreover, to improve the robustness of the GP control law against unforeseen environmental changes, a new selection and crossover mechanisms, called Inclusive Tournament and Inclusive Crossover, are also introduced. The proposed IC approach is tested on the guidance control of a space transportation system and results, showing the potentialities for real applications, are shown and discussed.",

keywords = "Genetic Programming, Intelligent Control, Neural Networks, optimal control, space transportation system",

author = "Francesco Marchetti and Edmondo Minisci",

year = "2020",

month = nov,

day = "16",

doi = "10.1007/978-3-030-63710-1_19",

language = "English",

isbn = "9783030637101",

pages = "240--254",

editor = "Bogdan Filipi{\v c} and Edmondo Minisci and Massimiliano Vasile",

booktitle = "Bioinspired Optimization Methods and Their Applications",

publisher = "Springer",

note = "Bioinspired Optimization Methods and their Applications 2020, BIOMA 2020 ; Conference date: 19-11-2020 Through 20-11-2020",

url = "http://utopiae.eu/bioma-2020/",

}

Marchetti, F & Minisci, E 2020, A hybrid Neural Network-Genetic Programming Intelligent Control approach. in B Filipič, E Minisci & M Vasile (eds), Bioinspired Optimization Methods and Their Applications. Springer, Cham, Switzerland, pp. 240-254, Bioinspired Optimization Methods and their Applications 2020, Bruxelles, Belgium, 19/11/20. https://doi.org/10.1007/978-3-030-63710-1_19

A hybrid Neural Network-Genetic Programming Intelligent Control approach. / Marchetti, Francesco ; Minisci, Edmondo.

Bioinspired Optimization Methods and Their Applications. ed. / Bogdan Filipič; Edmondo Minisci; Massimiliano Vasile. Cham, Switzerland : Springer, 2020. p. 240-254.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

TY - GEN

T1 - A hybrid Neural Network-Genetic Programming Intelligent Control approach

AU - Marchetti, Francesco

AU - Minisci, Edmondo

PY - 2020/11/16

Y1 - 2020/11/16

N2 - The proposed work aims to introduce a novel approach to Intelligent Control (IC), based on the combined use of Genetic Programming (GP) and feedforward Neural Network (NN). Both techniques have been successfully used in the literature for regression and control applications, but, while a NN creates a black box model, GP allows for a greater interpretability of the created model, which is a key feature in control applications. The main idea behind the hybrid approach proposed in this paper is to combine the speed and flexibility of a NN with the interpretability of GP. Moreover, to improve the robustness of the GP control law against unforeseen environmental changes, a new selection and crossover mechanisms, called Inclusive Tournament and Inclusive Crossover, are also introduced. The proposed IC approach is tested on the guidance control of a space transportation system and results, showing the potentialities for real applications, are shown and discussed.

AB - The proposed work aims to introduce a novel approach to Intelligent Control (IC), based on the combined use of Genetic Programming (GP) and feedforward Neural Network (NN). Both techniques have been successfully used in the literature for regression and control applications, but, while a NN creates a black box model, GP allows for a greater interpretability of the created model, which is a key feature in control applications. The main idea behind the hybrid approach proposed in this paper is to combine the speed and flexibility of a NN with the interpretability of GP. Moreover, to improve the robustness of the GP control law against unforeseen environmental changes, a new selection and crossover mechanisms, called Inclusive Tournament and Inclusive Crossover, are also introduced. The proposed IC approach is tested on the guidance control of a space transportation system and results, showing the potentialities for real applications, are shown and discussed.

KW - Genetic Programming

KW - Intelligent Control

KW - Neural Networks

KW - optimal control

KW - space transportation system

U2 - 10.1007/978-3-030-63710-1_19

DO - 10.1007/978-3-030-63710-1_19

M3 - Conference contribution book

SN - 9783030637101

SP - 240

EP - 254

BT - Bioinspired Optimization Methods and Their Applications

A2 - Filipič, Bogdan

A2 - Minisci, Edmondo

A2 - Vasile, Massimiliano

PB - Springer

CY - Cham, Switzerland

T2 - Bioinspired Optimization Methods and their Applications 2020

Y2 - 19 November 2020 through 20 November 2020

ER -