用于机组状态分析的数据处理和筛选方法研究  

Data Processing and Screening Method for Unit State Analysis

作　　者：余洁 范世望 YU Jie;FAN Shiwang(Shanghai Turbine Works Co.,Ltd.,Shanghai 200240,China)

机构地区：[1]上海汽轮机厂有限公司,上海200240

出　　处：《热力透平》2022年第2期92-97,共6页Thermal Turbine

基　　金：智慧汽轮机健康运维关键技术研究(19QB1404400)。

摘　　要：以热力专业理论、规范为背景,基于统计学科方法,参考人工智能算法思想,梳理了适用于火电机组状态分析的数据准备流程和方法。描述了数据的集成、测量误差检测、稳态筛选3部分数据工作的必要要求,阐释了基于统计检验延伸的系列处理方法的原理依据、推导过程和应用方法,提供了实际电厂机组运行数据处理的基本算例。研究成果可以在智能运维新领域的在线机组状态分析中形成方法简明、计算量小、适用性高、参照行业规范的数据准备。Based on thermodynamic theory and specifications,the data preparation process and methods suitable for state analysis of thermal power unit are sorted out based on the statistical methods and the idea of artificial intelligence algorithms.The necessary requirements for data integration,measurement error detection and steady-state screening are described.The principle,derivation and application of a series of processing methods based on statistical tests are explained.The basic calculation example of operation data processing of actual power plant is provided.Referring to the industry standards,the research result can provide data preparation which has features of concise method,low computation and high applicability in the unit state online analysis of the new field of intelligent operations.

关 键 词：热工测量 异常检测 稳态筛选 统计检验 

分 类 号：TK267[动力工程及工程热物理—动力机械及工程]