Application of Machine Learning to Performance Assessment for a Class of PID-Based Control Systems

被引：12

作者：

Grelewicz, Patryk ^{[1
]}

Khuat, Thanh Tung ^{[2
]}

Czeczot, Jacek ^{[1
]}

Nowak, Pawel ^{[1
]}

Klopot, Tomasz ^{[1
]}

Gabrys, Bogdan ^{[2
]}

机构：

[1] Silesian Tech Univ, Fac Automatic Control Elect & Comp Sci, Dept Automatic Control & Robot, PL-44100 Gliwice, Poland

[2] Univ Technol Sydney, Data Sci Inst, Fac Engn & Informat Technol, Complex Adapt Syst Lab, Sydney, NSW 2007, Australia

来源：

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS | 2023年 / 53卷 / 07期

关键词：

Process control; Control systems; Training; Tuning; Closed loop systems; Machine learning; Steady-state; Control performance assessment (CPA); diagnostic analysis; machine learning (ML); pattern classification; PID control; practical validation;

D O I：

10.1109/TSMC.2023.3244714

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this article, a novel machine learning (ML)-derived control performance assessment (CPA) classification system is proposed. It is dedicated for a wide class of PID-based control industrial loops with processes exhibiting dynamical properties close to second order plus delay time (SOPDT). The proposed concept is very general and easy to configure to distinguish between acceptable and poor closed-loop performance. This approach allows for determining the best (but also robust and practically achievable) closed-loop performance based on very popular and intuitive closed-loop quality factors. Training set can be automatically derived off-line using a number of different, diverse control performance indices (CPIs) used as discriminative features of the assessed control system. The proposed extended set of CPIs is discussed with comprehensive performance assessment of different ML-based classification methods and practical application of the suggested solution. As a result, a general-purpose CPA system is derived that can be immediately applied in practice without any preliminary or additional learning stage during normal closed-loop operation. It is verified by practical application to assess the control system for a laboratory heat exchange and distribution setup.

引用

页码：4226 / 4238

页数：13

共 50 条

[1] AN INTRODUCTION TO KERNEL AND NEAREST-NEIGHBOR NONPARAMETRIC REGRESSION [J].

ALTMAN, NS .

AMERICAN STATISTICIAN, 1992, 46 (03) :175-185

[2]

Aström KJ, 2000, IFAC WORK S, P165

[3] Random forests [J].

Breiman, L .

MACHINE LEARNING, 2001, 45 (01) :5-32

[4]

Breiman L, 1984, Classification and Regression Trees, DOI DOI 10.1201/9781315139470

[5] Operating performance assessment based on multi-source heterogeneous information with deep learning for smelting process of electro-fused magnesium furnace [J].

Bu, Kaiqing ;

Liu, Yan ;

Wang, Fuli .

ISA TRANSACTIONS, 2022, 128 :357-371

[6]

Caesarendra W, 2019, PROCEEDINGS OF 2019 12TH INTERNATIONAL CONFERENCE ON INFORMATION & COMMUNICATION TECHNOLOGY AND SYSTEM (ICTS), P120, DOI [10.1109/icts.2019.8850990, 10.1109/ICTS.2019.8850990]

[7] AN EFFICIENT METHOD FOR ONLINE IDENTIFICATION OF STEADY-STATE [J].

CAO, SL ;

RHINEHART, RR .

JOURNAL OF PROCESS CONTROL, 1995, 5 (06) :363-374

[8] XGBoost: A Scalable Tree Boosting System [J].

Chen, Tianqi ;

Guestrin, Carlos .

KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, :785-794

[9]

Desborough L., 2002, INCREASING CUSTOMER, V98, P1

[10]

Fratczak M, 2015, 2015 20TH INTERNATIONAL CONFERENCE ON METHODS AND MODELS IN AUTOMATION AND ROBOTICS (MMAR), P1032, DOI 10.1109/MMAR.2015.7284021

← 1 2 3 4 5 →