Data-Driven State Transition Algorithm for Fuzzy Chance-Constrained Dynamic Optimization

Feifan Lin; Xiaojun Zhou; Chaojie Li; Tingwen Huang; Chunhua Yang

doi:10.1109/TNNLS.2022.3186475

Data-Driven State Transition Algorithm for Fuzzy Chance-Constrained Dynamic Optimization

Feifan Lin, Xiaojun Zhou^*, Chaojie Li, Tingwen Huang, Chunhua Yang

^*Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

12 Citations (Scopus)

Abstract

Many actual industrial production processes are dynamic and uncertain. When uncertain information are described by subjective experience and experts' knowledge based on scanty or vague information, fuzzy uncertainty exists. Fuzzy chance-constrained dynamic programming are applicable to industrial production modeling accompanied by fuzzy uncertainty and dynamics, where constraints need not or cannot be completely satisfied. In this article, a fuzzy chance-constrained dynamic optimization (FCCDO) formulation on the basis of credibility theory is established, in which, the credibility is used to measure the fuzzy uncertainty level of constraints. To solve the FCCDO problem (FCCDOP), an improved fuzzy simulation technique based on Hammersley sequence sampling is raised to transform fuzzy chance constraints to their deterministic equivalents, and then a data-driven state transition algorithm (DDSTA) using deep neural networks (DNNs) is put forward to achieve a stable, global and robust optimization performance. Finally, the successful applications of the FCCDO method to industrial studies demonstrate its advantages.

© 2022 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.

Original language	English
Pages (from-to)	5322-5331
Number of pages	10
Journal	IEEE Transactions on Neural Networks and Learning Systems
Volume	34
Issue number	9
Online published	7 Jul 2022
DOIs	https://doi.org/10.1109/TNNLS.2022.3186475
Publication status	Published - Sept 2023
Externally published	Yes

Funding

This work was supported in part by the National Natural Science Foundation of China under Grant 72088101, Grant 61873285, and Grant 61860206014; in part by the Research Foundation of Science and Technology of Hunan Province, China, under Grant 2019RS1003; and in part by the Hunan Provincial Natural Science Foundation of China under Grant 2021JJ20082.

Research Keywords

Dynamic optimization
fuzzy chance-constrained optimization
fuzzy uncertainty
state transition algorithm (STA)

Access Output

10.1109/TNNLS.2022.3186475

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{82fba42f3c9a4bb589a976be2c9d89ff,

title = "Data-Driven State Transition Algorithm for Fuzzy Chance-Constrained Dynamic Optimization",

abstract = "Many actual industrial production processes are dynamic and uncertain. When uncertain information are described by subjective experience and experts' knowledge based on scanty or vague information, fuzzy uncertainty exists. Fuzzy chance-constrained dynamic programming are applicable to industrial production modeling accompanied by fuzzy uncertainty and dynamics, where constraints need not or cannot be completely satisfied. In this article, a fuzzy chance-constrained dynamic optimization (FCCDO) formulation on the basis of credibility theory is established, in which, the credibility is used to measure the fuzzy uncertainty level of constraints. To solve the FCCDO problem (FCCDOP), an improved fuzzy simulation technique based on Hammersley sequence sampling is raised to transform fuzzy chance constraints to their deterministic equivalents, and then a data-driven state transition algorithm (DDSTA) using deep neural networks (DNNs) is put forward to achieve a stable, global and robust optimization performance. Finally, the successful applications of the FCCDO method to industrial studies demonstrate its advantages. {\textcopyright} 2022 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.",

keywords = "Dynamic optimization, fuzzy chance-constrained optimization, fuzzy uncertainty, state transition algorithm (STA)",

author = "Feifan Lin and Xiaojun Zhou and Chaojie Li and Tingwen Huang and Chunhua Yang",

year = "2023",

month = sep,

doi = "10.1109/TNNLS.2022.3186475",

language = "English",

volume = "34",

pages = "5322--5331",

journal = "IEEE Transactions on Neural Networks and Learning Systems",

issn = "2162-237X",

publisher = "IEEE Computational Intelligence Society",

number = "9",

}

TY - JOUR

T1 - Data-Driven State Transition Algorithm for Fuzzy Chance-Constrained Dynamic Optimization

AU - Lin, Feifan

AU - Zhou, Xiaojun

AU - Li, Chaojie

AU - Huang, Tingwen

AU - Yang, Chunhua

PY - 2023/9

Y1 - 2023/9

N2 - Many actual industrial production processes are dynamic and uncertain. When uncertain information are described by subjective experience and experts' knowledge based on scanty or vague information, fuzzy uncertainty exists. Fuzzy chance-constrained dynamic programming are applicable to industrial production modeling accompanied by fuzzy uncertainty and dynamics, where constraints need not or cannot be completely satisfied. In this article, a fuzzy chance-constrained dynamic optimization (FCCDO) formulation on the basis of credibility theory is established, in which, the credibility is used to measure the fuzzy uncertainty level of constraints. To solve the FCCDO problem (FCCDOP), an improved fuzzy simulation technique based on Hammersley sequence sampling is raised to transform fuzzy chance constraints to their deterministic equivalents, and then a data-driven state transition algorithm (DDSTA) using deep neural networks (DNNs) is put forward to achieve a stable, global and robust optimization performance. Finally, the successful applications of the FCCDO method to industrial studies demonstrate its advantages. © 2022 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.

AB - Many actual industrial production processes are dynamic and uncertain. When uncertain information are described by subjective experience and experts' knowledge based on scanty or vague information, fuzzy uncertainty exists. Fuzzy chance-constrained dynamic programming are applicable to industrial production modeling accompanied by fuzzy uncertainty and dynamics, where constraints need not or cannot be completely satisfied. In this article, a fuzzy chance-constrained dynamic optimization (FCCDO) formulation on the basis of credibility theory is established, in which, the credibility is used to measure the fuzzy uncertainty level of constraints. To solve the FCCDO problem (FCCDOP), an improved fuzzy simulation technique based on Hammersley sequence sampling is raised to transform fuzzy chance constraints to their deterministic equivalents, and then a data-driven state transition algorithm (DDSTA) using deep neural networks (DNNs) is put forward to achieve a stable, global and robust optimization performance. Finally, the successful applications of the FCCDO method to industrial studies demonstrate its advantages. © 2022 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.

KW - Dynamic optimization

KW - fuzzy chance-constrained optimization

KW - fuzzy uncertainty

KW - state transition algorithm (STA)

UR - http://www.scopus.com/inward/record.url?scp=85134258812&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85134258812&origin=recordpage

U2 - 10.1109/TNNLS.2022.3186475

DO - 10.1109/TNNLS.2022.3186475

M3 - RGC 21 - Publication in refereed journal

C2 - 35797315

SN - 2162-237X

VL - 34

SP - 5322

EP - 5331

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

IS - 9

ER -

Data-Driven State Transition Algorithm for Fuzzy Chance-Constrained Dynamic Optimization

Abstract

Funding

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this