Research On The Method Of The Coal-fired Boilers Combustion Stability Based On Rough Sets And The Image Signal

Keeping stable coal combustion is the most fundamental requirement for the electric power station safe operation.The combustion flame is the most direct reflection of the state of combustion stability.In order to achieve combustion stability diagnosis,the paper obtained the combustion parameters which could reflect the characterization of the combustion state based on digital image processing and proposed a method based on rough set to analysis and process the imprecise,inconsistent and incomplete combustion information,and analyze combustion characteristics.When coal was burning,the flame image affected by various noise sources,the flame has a strong pulsation and the extracted combustion parameters also will fluctuate,the combustion parameters were described as the interval number because of the pulsating flame.Based on the multi-attribute decision making algorithm,a combustion interval sample decision table is formed.The combustion parameters were described as interval number can't solve the redundancy data,the relationship between the properties of the complex and continuous uncertainty because of the pulsating flame.The paper given an interval discretization algorithm based on rough set theory to solve the problem.The interval combustion parameters are described as the distances and similarity relations among objects by extending the rough set define.Then similarity relations among the objects are determined by defining similarity threshold and introducing the concept of rough entropy obtained optimum number interval similarity threshold.By calculating upper and lower approximate rough entropy and determine similarity matrix of these objects,the final discretization result could be obtained.Finally,the paper gives a combustion judgment method.Rough set is an effective tool to analyze and process the imprecise,inconsistent and incomplete information.Attribute reduction is the core content of rough set theory.Because of the objective of rough set data processing,it is sensitive to the noise data.Especially for large data sets processing,the decision rules obtained based on traditional rough set algorithms exhibit incompatibility and the decision information became variation.The paper proposed an improved heuristic attribute reduction algorithm and discussed the structure of heuristic information method.Using the properties of information entropy as the measure,the attribute significance is determined.By extending the concept of maximum distribution attribute reduction,the paper given the maximum distribution attribute reduction algorithm based on attribute significance.Finally,the paper proposed the combustion stability diagnostics model based on rough set classification decision.According to the experiments demonstrate that the improved rough set attribute values and attributes reduction methods have a better generalization and mapping capabilities,and it could be effective in achieving the nonlinear combustion systems stability judgment.