本文已被：浏览 910次 下载 403次
中文摘要: 基于BP神经网络，对某9F燃气轮机机组历史运行数据进行了建模与分析，提出了一种燃气轮机压 气机叶片积垢导致其性能下降的分析方法，得到了燃气轮机压气机效率、压气机压比、压气机流量、燃气轮机 功率四个性能参数偏差值随燃气轮机实际运行小时的变化曲线。结果表明，可将上述四个性能参数的实际 运行值与理想状态下的运行值（神经网络预测值）偏差3%、3%、4%、5%作为压气机离线水洗的判据。据此, 对9F燃气轮机机组现有的离线水洗周期进行优化,得出当前燃气轮机压气机积垢状态实际运行指导小时数 为3 000 h。该方法为燃气轮机离线水洗周期优化提供了一种思路,具有一定的工程应用价值。
Abstract:Based on BP neural network, the historical operation data of a 9F gas turbine unit was modeled and analyzed. An analytical method for the performance degradation of the gas turbine compressor blade was proposed. The variation curves of gas turbine compressor efficiency, compressor pressure ratio, compressor flow rate and gas turbine power performance with the actual operating hours of the gas turbine were obtained. The results showed that the relative deviation of the above four performance parameters between actual operating values and ideal operating values ( neural network predicting values) by3% , 3% , 4% , and 5% could be regarded as the criteria for offline washing of the compressor. According to this, the existing offline washing cycle of the 9F gas turbine unit was optimized, and the actual operation guidance time of the current gas turbine compressor fouling state was 3 000 h. This method provided an idea for the optimization of gas turbine offline washing cycle and had certain engineering application value.
文章编号： 中图分类号：TM611.31 文献标志码：
基金项目:
| Author Name | Affiliation |
| Chen Jialun | Shanghai Minghua Power Technology Co. , Ltd. |
| Bian Shaoshuai | Shanghai Minghua Power Technology Co. , Ltd. |
| Huang Xin | Shanghai Minghua Power Technology Co. , Ltd. |
引用文本：
作者.题名[J].刊名,出版年份,卷号(期号):起止页码.
[2]KIM K M, PARK J S, DONG H L, et al. Analysis of conjugated heat transfer, stress and failure in a gas turbine blade with circular cooling passages[J]. Engineering Failure Analysis, 2011, 18(4):1212-1222.
作者.题名[J].刊名,出版年份,卷号(期号):起止页码.
[2]KIM K M, PARK J S, DONG H L, et al. Analysis of conjugated heat transfer, stress and failure in a gas turbine blade with circular cooling passages[J]. Engineering Failure Analysis, 2011, 18(4):1212-1222.