Combustion Optimization of Unit Based on KPCA-FCM Simplified Operating Conditions
Aiming at the problem that the frequent changes of operating conditions under deep peak shaving make it more difficult to adjust the optimization parameters of boiler combustion,this paper proposed a combustion optimization method based on KPCA-FCM to simplify operating conditions.Firstly,after extracting the steady-state working condi-tions from the actual historical operation data of the boiler,dimensionality reduction was performed by Kernel Principal Component Analysis(KPCA).We selected the operating parameters with high contribution rates and used the fuzzy clustering algorithm(FCM)to analyze,classify and achieve working condition simplification.Secondly,the corre-sponding working condition clusters were matched for different combustion conditions,and the combustion parameters were adjusted to the best operating parameters of this type to achieve the purpose of improving thermal efficiency.In or-der to verify the rationality of the method,the least squares support vector machine was used to identify the boiler com-bustion thermal efficiency model.Taking the high and low working condition intervals as an example,the simulation verification was carried out.The results show that the extracted target value of the optimal operating parameters can in-crease the thermal efficiency of the boiler by up to 0.2％.Therefore,the proposed method for streamlining operating conditions can effectively select the optimal operating target value and provide a reasonable data reference for field oper-ators to adjust operating parameters.
working condition simplificationcombustion optimizationKPCAFCMboiler efficiency
万方数据
维普
