论文标题:电站锅炉吹灰优化系统的研究与开发
Research and Development of Sootblow Optimization System of Utility Boiler
论文作者
论文导师 张光,论文学位 硕士,论文专业 热能工程
论文单位 华北电力大学（北京）,点击次数 134,论文页数 63页File Size1606K
2007-01-01论文网 http://www.lw23.com/lunwen_554359577/
neural network;model;clean factor;monitoring system;sootblow optimization
本文针对电站锅炉各受热面灰污染严重的普遍现象,以沁北1#炉为研究对象,在低温受热面安装了烟温测点,利用电厂DAS系统实时采集数据,结合长期以来的灰污变化情况,运用三层BP神经网络,建立了以清洁因子作为各受热面灰污特征参数的灰污监测模型。 在建立了适用于该炉的监测模型之后,开发了锅炉受热面灰污染状况监测系统,针对电站锅炉运行特点,全面解析锅炉吹灰运行的各种成本和收益。监测结果分析验证了监测系统与监测模型的准确性和可靠性,模型对锅炉负荷有较大的适应性。探讨了主要影响因素对监测结果的影响,并提出了优化吹灰的新诠释。 最后对全文进行了总结,并对未来模型与监测系统的发展进行了探讨。
As to serious ash deposition on the heating surfaces of coal-fired boilers being a common phenomenon, this paper took QinBei 1# boiler as an object. Taking advantage of the data from the DAS of the plant and fixing new gas temperature measure points on lower-temperature convection heating surfaces, we built the fouling monitoring model with three layers of BP neural network under the condition of observing the variation of fouling conditions for a long time, which is described by clean factor. After building the proper model, we developed a suit of monitoring system to monitor the soot deposition level of the boiler heat exchanger surfaces. We analyzed all sorts of costs and incomes of boiler sootblowing relying on boiler running. The result and analysis prove the accuracy and reliability of both the monitoring model and system. At the same time,we discussed the main factors that affect the monitoring result and explained the new idea of sootblow optimization. At last, we conclude the paper, and discuss the further development of the model and monitoring system in the future.
|
