Technical diagnostic system in the maintenance of turbomachinery for ammonia synthesis in the process industries

Natalia Nikolova, Kaoru Hirota, K. Kolev, Kiril Tenekedjiev

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Technical maintenance of machines and equipment in processing industry requires elaborate technical diagnostics systems to recognize the current state and forecast their future state. Creating such a system is a complex task due to multiple factors, with aging in aggressive exploitation environment being an important one. Statistical pattern recognition systems are very suitable to solve problems of technical diagnostics as they produce quantitative estimates of the states. We present the use of a hybrid Bayesian pattern recognition classifier that utilizes statistical and fuzzy paradigms and expresses the measurement information with four types of features (discrete, pseudo-discrete, multi-normal and independent continuous). It uses frequentist and subjective information (from training samples and expert opinion respectively) to identify the unknown parameters of the conditional likelihood density functions of each technical state. We discuss possible sources to collect learning information, and different methods to represent it. The classifier uses three different methods for parameter estimation of the conditional likelihood densities using data fusion. The classification is realised as a discriminant non-linear machine, which incorporates fuzzy approaches at different levels. We develop a novel algorithm for fault prediction without dynamic learning with four possible types of answers. A detailed example of technical diagnostics system for classification and prediction of states of turbomachinery for ammonia synthesis is presented. For the journal bearing diagnostics, we introduce modification of the hybrid Bayesian classifier using pseudo-priors to incorporate rule-based knowledge and improve the classification.

Original languageEnglish
Pages (from-to)102-115
Number of pages14
JournalJournal of Loss Prevention in the Process Industries
Volume58
DOIs
Publication statusPublished - Mar 1 2019

Fingerprint

Turbomachinery
Ammonia
Industry
Classifiers
ammonia
Maintenance
industry
synthesis
Automated Pattern Recognition
learning
Learning
Pattern recognition systems
processing equipment
Likelihood Functions
prediction
Journal bearings
expert opinion
Expert Testimony
Data fusion
Parameter estimation

Keywords

  • Aging
  • Ammonia synthesis
  • Backward discriminant functions
  • Fuzzy parameter estimation
  • Hybrid Bayesian classifier
  • Pseudo-discrete features
  • Pseudo-priors

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Food Science
  • Chemical Engineering(all)
  • Safety, Risk, Reliability and Quality
  • Energy Engineering and Power Technology
  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering

Cite this

Technical diagnostic system in the maintenance of turbomachinery for ammonia synthesis in the process industries. / Nikolova, Natalia; Hirota, Kaoru; Kolev, K.; Tenekedjiev, Kiril.

In: Journal of Loss Prevention in the Process Industries, Vol. 58, 01.03.2019, p. 102-115.

Research output: Contribution to journalArticle

@article{327612305679480189d190ead93b200b,
title = "Technical diagnostic system in the maintenance of turbomachinery for ammonia synthesis in the process industries",
abstract = "Technical maintenance of machines and equipment in processing industry requires elaborate technical diagnostics systems to recognize the current state and forecast their future state. Creating such a system is a complex task due to multiple factors, with aging in aggressive exploitation environment being an important one. Statistical pattern recognition systems are very suitable to solve problems of technical diagnostics as they produce quantitative estimates of the states. We present the use of a hybrid Bayesian pattern recognition classifier that utilizes statistical and fuzzy paradigms and expresses the measurement information with four types of features (discrete, pseudo-discrete, multi-normal and independent continuous). It uses frequentist and subjective information (from training samples and expert opinion respectively) to identify the unknown parameters of the conditional likelihood density functions of each technical state. We discuss possible sources to collect learning information, and different methods to represent it. The classifier uses three different methods for parameter estimation of the conditional likelihood densities using data fusion. The classification is realised as a discriminant non-linear machine, which incorporates fuzzy approaches at different levels. We develop a novel algorithm for fault prediction without dynamic learning with four possible types of answers. A detailed example of technical diagnostics system for classification and prediction of states of turbomachinery for ammonia synthesis is presented. For the journal bearing diagnostics, we introduce modification of the hybrid Bayesian classifier using pseudo-priors to incorporate rule-based knowledge and improve the classification.",
keywords = "Aging, Ammonia synthesis, Backward discriminant functions, Fuzzy parameter estimation, Hybrid Bayesian classifier, Pseudo-discrete features, Pseudo-priors",
author = "Natalia Nikolova and Kaoru Hirota and K. Kolev and Kiril Tenekedjiev",
year = "2019",
month = "3",
day = "1",
doi = "10.1016/j.jlp.2019.02.002",
language = "English",
volume = "58",
pages = "102--115",
journal = "Journal of Loss Prevention in the Process Industries",
issn = "0950-4230",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Technical diagnostic system in the maintenance of turbomachinery for ammonia synthesis in the process industries

AU - Nikolova, Natalia

AU - Hirota, Kaoru

AU - Kolev, K.

AU - Tenekedjiev, Kiril

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Technical maintenance of machines and equipment in processing industry requires elaborate technical diagnostics systems to recognize the current state and forecast their future state. Creating such a system is a complex task due to multiple factors, with aging in aggressive exploitation environment being an important one. Statistical pattern recognition systems are very suitable to solve problems of technical diagnostics as they produce quantitative estimates of the states. We present the use of a hybrid Bayesian pattern recognition classifier that utilizes statistical and fuzzy paradigms and expresses the measurement information with four types of features (discrete, pseudo-discrete, multi-normal and independent continuous). It uses frequentist and subjective information (from training samples and expert opinion respectively) to identify the unknown parameters of the conditional likelihood density functions of each technical state. We discuss possible sources to collect learning information, and different methods to represent it. The classifier uses three different methods for parameter estimation of the conditional likelihood densities using data fusion. The classification is realised as a discriminant non-linear machine, which incorporates fuzzy approaches at different levels. We develop a novel algorithm for fault prediction without dynamic learning with four possible types of answers. A detailed example of technical diagnostics system for classification and prediction of states of turbomachinery for ammonia synthesis is presented. For the journal bearing diagnostics, we introduce modification of the hybrid Bayesian classifier using pseudo-priors to incorporate rule-based knowledge and improve the classification.

AB - Technical maintenance of machines and equipment in processing industry requires elaborate technical diagnostics systems to recognize the current state and forecast their future state. Creating such a system is a complex task due to multiple factors, with aging in aggressive exploitation environment being an important one. Statistical pattern recognition systems are very suitable to solve problems of technical diagnostics as they produce quantitative estimates of the states. We present the use of a hybrid Bayesian pattern recognition classifier that utilizes statistical and fuzzy paradigms and expresses the measurement information with four types of features (discrete, pseudo-discrete, multi-normal and independent continuous). It uses frequentist and subjective information (from training samples and expert opinion respectively) to identify the unknown parameters of the conditional likelihood density functions of each technical state. We discuss possible sources to collect learning information, and different methods to represent it. The classifier uses three different methods for parameter estimation of the conditional likelihood densities using data fusion. The classification is realised as a discriminant non-linear machine, which incorporates fuzzy approaches at different levels. We develop a novel algorithm for fault prediction without dynamic learning with four possible types of answers. A detailed example of technical diagnostics system for classification and prediction of states of turbomachinery for ammonia synthesis is presented. For the journal bearing diagnostics, we introduce modification of the hybrid Bayesian classifier using pseudo-priors to incorporate rule-based knowledge and improve the classification.

KW - Aging

KW - Ammonia synthesis

KW - Backward discriminant functions

KW - Fuzzy parameter estimation

KW - Hybrid Bayesian classifier

KW - Pseudo-discrete features

KW - Pseudo-priors

UR - http://www.scopus.com/inward/record.url?scp=85062017283&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062017283&partnerID=8YFLogxK

U2 - 10.1016/j.jlp.2019.02.002

DO - 10.1016/j.jlp.2019.02.002

M3 - Article

AN - SCOPUS:85062017283

VL - 58

SP - 102

EP - 115

JO - Journal of Loss Prevention in the Process Industries

JF - Journal of Loss Prevention in the Process Industries

SN - 0950-4230

ER -