Font Size: a A A

Monitoring Ash Fouling On The Boiler Convective Surfaces Based On The BP Neural Network And Genetic Algorithm

Posted on:2007-01-26Degree:MasterType:Thesis
Country:ChinaCandidate:J S WanFull Text:PDF
GTID:2132360212465347Subject:Power Machinery and Engineering
Abstract/Summary:PDF Full Text Request
Firing coal in utility boilers makes soot-sections foul with ash deposits that have negative effects on heat transfer and boiler efficiency. Because of electricity market competition, inferior coal is oftern used .It make ash deposits images worsened. So fouling monitoring and sootblowing optimization becomes a recent domestic and international studies lance hot. The common solution is sootblowing, which is an effective method to clean fouling and enhance boiler heating surfaces performance. Knowing where and when to blowsoot is of paramount importance if the blowing necessary.To realize the optimization of sootblowing, some research is done on the theories and methods about the on-line monitoring of fouling and slagging on utility boiler heat surfaces. After analyzing the fouling and slgging characteristics of boiler heating surfaces, the possibility of the artificial neural network to monitor ash fouling on the boiler convective surfaces is studied. The parameters such as boiler load, steam temperature and flue gas temperature before and after the heating surface etc., are used as the inputs, deposit factor as the output. With the analysis of the effects of operation conditions and coal property on the state of fouling, the ash deposit monitoring model is presented by adapting a three-layer network.The weitghts of the designed neural networks is optimized through the genetic algorithm. By using the operation such as selection and crossover and mutation etc, it can modify the capacity of the network and enhances the efficiency. Training data are from on-line DCS after pre-selected and normalized.After on-line debugging and soot-blowing experimentation, the presented ash deposit monitoring model is used to monitor ash deposit of No.2 300MW-boiler in Qingdao Power Station. The result shows that the model can identify the sootblowing process and can be used to monitor the status of ash deposit and optimize sootblowing intervals.
Keywords/Search Tags:firing coal utility boilers, fouling and slagging, soot-blowing optimization, smudginess coefficient, neural network, genetic algorithm
PDF Full Text Request
Related items