A case-based knowledge system for safety evaluation decision making of thermal power plants
Introduction
Industrial production, especially in the area of power generation, oil and gas, aviation, mining, and nuclear plants, often has significant safety implications on the safety of people’s life and property, thus is attracting increasing attention from industry practitioners as well as researchers [1]. As an essential industrial component, thermal power plants (TPP) equip many industrial departments and their production process is very complicated. When operating TPP, the safety of people’s lives and work conditions is a major concern. There are numerous TPP all over the world. Taking China as an example, there are over 1200 coal-fired thermal plants. In 2006, the total power generated in China by TPP reached 2834.4 terawatt per hour (TWh) and the total installed capacity reached 622 gigawatts (GW) [2]. As one of the nations with most electric power generation, China produces its electric power mainly from coal [3]. Another country that relies heavily on TPP for power generation is Turkey, where 80% of the total electricity is generated from TPP [4]. Safety assessment of TPP mainly concerns three aspects: Production Equipment Systems (PES), Working Circumstance Systems (WCS), and Production Management Systems. The third is also referred to as the Management System (MS) in current research. Through analyzing and evaluating these three subsystems, TPP can establish necessary corrective, remedial, and preventive measures, and realize the goal of controlling the accidents in advance.
As one of modern management ladders, safety assessment is a powerful tool for automatically diagnosing safety issues. However, numerous existing evaluations for production safety are irregular, unscientific, and capricious.
Because of the lack of powerful information and knowledge support for panel of experts during their decision making process of evaluation, the current used approach of direct expert evaluation is too subjective. Accordingly, there is a sizable margin of error. Hence, it is necessary to reduce its subjectivity. Along with the perfection of safety assessment rules and the development of information technologies, new techniques are being applied to almost all aspects of power systems to improve efficiency [5]. It is of both scientific and social significance for TPP to improve their safety assessment process toward better quantification, scientization, and automatization. MS safety represents an important aspect of the safety issue in the production of TPP. Numerous facts show that a large part of safety accidents in TPP occurred due to the managerial inadequateness and not for the equipment malfunctions.
From the perspective of Management Systems Safety Assessment of TPPs (MSSATPP), this paper investigates the whole range of safety assessment in TPPs’ production, and applies the case-based reasoning (CBR) technique to the evaluation decision making process of MSSATPP. It presents a case-based decision support method named improved grey CBR (IGCBR) for MSSATPP and a framework of knowledge system for intelligent decision making (IDSS-MSSATPP).
This paper is organized in six sections. Section 2 is literature review regarding the evaluation on the power system and case retrieval methods in knowledge-based decision making, as well as the motivation of this study. Section 3 describes TPP safety evaluation process, introduces the evaluation indexes and defines four statistics for performance evaluation in the later experiments. Section 4 deals with problem’s domain knowledge acquisition methodology mainly focusing on the weight determination method based on Delphi method and the retrieval algorithm based grey system theory. Also, the data set for experiments is introduced in this section. Section 5 introduces the system implementation and relevant experiments. And the main results are presented and brief discussion is also given. Section 6 concludes the paper and briefly introduced the trial application in a large-scale thermal power plant.
Section snippets
The evaluation on the power system
Common evaluation issues concerning the power industry have been reported in the literature. In view of the special importance of production safety for TPP, it is important to study scientific approaches that fit the characteristic features of the production and management of TPP for safety assessment. However, few research studies focus on the safety assessment of TPP in production – the inside safety itself. Most of the literature focuses on the operational performance [6], energetic and
TPP safety evaluation: process, indexes and statistics
Power plant safety evaluations are performed by panels of experts through investigation, discussion, and negotiation. This process is explained in this section. Also, we introduce the evaluation indexes and the motivations of our research.
Research methodology
Uncertainty of information generally includes four inter-related categories. The first one is random uncertainty which is due to inadequate conditions or the interference from causal factors. The second one is fuzzy uncertainty which is caused by fuzzy extension of unknown information. The third one is grey uncertainty which means part information is known but other is unclear, missing or unavailable. The last one is unascertained uncertainty referring to that decision-makers cannot fully grasp
System implementation and experiments
We implemented the CBRSYS-TPP, a prototype of and IDSS-TPP mentioned earlier, and completed the later experiments regarding the performance of information acquisition. In this section, we completed two distinct randomized controlled experiments. The first one is to test the accuracy, sensitivity and specificity as well as calculate the Fmacro-Value of our proposed case matching methods which combines Delphi method and grey system theory. And the second one is to test several common
Conclusion
In this paper, we propose a method that integrates grey system theory and the Delphi method into CBR methodologies, with which the intelligent knowledge-based system can provide intelligent decision support for MSSATPP, and the evaluation cycles of experts can be reduced with improved efficiency. This paper provides a novel and effective way for the safety assessment of thermal power plants as well as a new perspective on the use of prototypes through case aggregation, which is one of the
Acknowledgements
This research is partially supported by the National Natural Science Foundation of China under Grant No. 70771037, No. 70871034, No. 90924021 and No. 70871032, China National “863” Plan Program (2006AA04A126), China Ministry of Education Humanity and Social Science Research Found for Young Scholars (09YJC630055), the Project of Key Research Institute of Humanities and Social Science in University of Anhui Province, Anhui Provincial Natural Science Foundation (No. 090416249) and Science Research
References (70)
- et al.
Industrial safety perception among post-graduate engineering students
Knowledge-Based Systems
(2010) - et al.
Power generation from pulverized coal in China
Energy
(2010) Toward zero emissions from coal in China
Energy for Sustainable Development
(2001)Investigation of coal-fired power plants in Turkey and a case study: Can plant
Applied Thermal Engineering
(2009)- et al.
Evaluation of thermal power plant operational performance in Taiwan by data envelopment analysis
Energy Policy
(2010) - et al.
Comparative energetic and exergetic performance analyses for coal-fired thermal power plants in Turkey
International Journal of Thermal Sciences
(2009) - et al.
Coding, evaluation and selection of thermal power plants – A MADM approach
International Journal of Electrical Power & Energy Systems
(2007) - et al.
Radon activity and exhalation rates measurements in fly ash from a thermal power plant
Radiation Measurements
(2005) - et al.
Decision tree approach to power systems safety assessment
International Journal of Electrical Power & Energy Systems
(1993) - et al.
Dynamic safety assessment of power systems using structure-preserving energy functions
International Journal of Electrical Power & Energy Systems
(1989)
Power system safety assessment using pattern recognition and fuzzy estimation
International Journal of Electrical Power & Energy Systems
Automatic induction of fuzzy decision trees and its application to power system safety assessment
Fuzzy Sets and Systems
Power system probabilistic safety assessment using Bayes classifier
Electric Power Systems Research
Voltage safety evaluation based on perturbation method
International Journal of Electrical Power & Energy Systems
Scenario analysis using Bayesian networks: A case study in energy sector
Knowledge-Based Systems
A hybrid artificial neural network (ANN) and Ward equivalent approach for on-line power system voltage safety assessment
Electric Power Systems Research
Knowledge based decision support system to assist work-related risk analysis in musculoskeletal disorder
Knowledge-Based Systems
Rule-based and case-based reasoning approach for internal audit of bank
Knowledge-Based Systems
Development of a case-based system for grouping diagnoses in general practice
International Journal of Medical Informatics
Case-based adaptation for automotive engine electronic control unit calibration
Expert Systems with Applications
General uncertainty in portfolio selection: A case-based decision approach
Journal of Economic Behavior & Organization
A study of mutual information based feature selection for case based reasoning in software cost estimation
Expert Systems with Applications
Incorporating domain-specific knowledge into a genetic algorithm to implement case-based reasoning adaptation
Knowledge-Based Systems
Developing a diagnostic system through integration of fuzzy case-based reasoning and fuzzy ant colony system
Expert Systems with Applications
A case-based reasoning with the feature weights derived by analytic hierarchy process for bankruptcy prediction
Expert Systems with Applications
Fuzzy logic weighted multi-criteria of dynamic route lifetime for reliable multicast routing in ad hoc networks
Expert Systems with Applications
Recommendation based on rational inferences in collaborative filtering
Knowledge-Based Systems
Entropy of interval-valued fuzzy sets based on distance and its relationship with similarity measure
Knowledge-Based Systems
A new model of evaluating concept similarity
Knowledge-Based Systems
Developing fuzzy classifiers to predict the chance of occurrence of adult psychoses
Knowledge-Based Systems
Grey system theory-based models in time series prediction
Expert Systems with Applications
Sensitivity and specificity based multiobjective approach for feature selection: Application to cancer diagnosis
Information Processing Letters
Real formal concept analysis based on grey-rough set theory
Knowledge-Based Systems
Manufacturing process optimization for wear property of fiber–reinforced polybutylene terephthalate composites with grey relational analysis
Wear
Dynamic voltage safety assessment by a neural network based method
Electric Power Systems Research
Cited by (47)
Review-driven configuration scheme evaluation methodology with configuration interaction effects
2023, Advanced Engineering InformaticsA mathematical model of an existing gas-steam combined heat and power plant for thermal diagnostic systems
2018, EnergyCitation Excerpt :Presented in the literature review the mathematical models of gas turbine units, heat recovery steam generators and steam-water cycles, use commercial or proprietary software written in different program languages. For the existing systems, the simulation model should also consider the current technical condition of the modelled machines [22], [23]. This requires the calibration of equations which describe physical phenomenon within the process [24], [25].
State of The Art-Intense Review on Artificial Intelligence Systems Application in Process Planning and Manufacturing
2017, Engineering Applications of Artificial IntelligenceTowards next-generation energy planning decision-making: An expert-based framework for intelligent decision support
2017, Renewable and Sustainable Energy ReviewsCitation Excerpt :Several taxonomies and concepts of uncertainty have been proposed in recent years (e.g., linguistic uncertainty, knowledge/epistemic uncertainty, variability/aleatoric uncertainty, decision uncertainty, procedural uncertainty, etc.). Gu et al. [166] identified four interrelated categories of uncertain information: UT1.
Comparison of four direct classification methods for intelligent fault diagnosis of rotating machinery
2016, Applied Soft Computing Journal
- 1
Tel.: +86 551 2904962; fax: +86 551 290492.