A case-based knowledge system for safety evaluation decision making of thermal power plants

Abstract

Safety assessment of thermal power plants (TPP) is an important means to ensure the safety of production in thermal power production enterprises. Modern information technology can play an important role in TPP safety assessment. The evaluation of power plant systems relies, to a large extent, on the knowledge and experience of the experts undertaking the task. Case-based reasoning (CBR) is introduced for the safety assessment of TPP since it models expertise through experience management. This paper provides a case-based approach for the Management System safety assessment decision making of TPP (MSSATPP). We introduce a case matching method named CBR-Grey, which integrates the Delphi approach and grey system theory. Based on this method, we implement a prototype of case-based knowledge system (CBRSYS-TPP) for the evaluation decision making of the panel of experts. Our experimental results based on a real-world TPP safety assessment data set show that CBRSYS-TPP has high accuracy and systematically good performance.

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.