Chang Tai-hua

The balanced model and optimization of NOx emission and boiler efficiency at a coal-fired utility boiler

In order to meet the requirement of high efficiency and low emission in boiler operations, a hybrid model is established based on experimental data and combined with BP neural network. This model uses the adjustable operation parameters of boiler as inputs and chooses NOx emission and boiler efficiency as outputs to achieve the prediction of NOx emission and thermal efficiency. And it optimizes the combustion process by using genetic algorithm. The results show that it is an applicable and effective numerical optimization method.

Research in data stream clustering based on Gaussian Mixture Model Genetic Algorithm

Clustering data streams is one of the important branches in mining data streams. Because of dynamic and massive characteristics of data streams, traditional data mining algorithms could not satisfy the requirement of online analysis and the appropriate value of number of clusters. The focus on data stream technologies is to design one-pass scan data set, and maintain an effective data structure in memory incrementally which is far smaller than the size of whole data set. In the paper proposes a new feature mining method named Gaussian Mixture Model with Genetic Algorithm (GMMGA), based on an extending method of Gaussian mixture model. This method is use a probability density based data stream clustering which requires only the newly arrived data, not the entire historical data. The GMMGA algorithm can determine the number of Gaussian clusters and the parameters of each Gaussian component through random split and merge operation of Genetic Algorithm. In the GMMGA, a function was made to threshold value to clusters to reduce the bad clusters effect on the clustering result. In this algorithm, it can improve the robustness and accuracy of the clustering numbers, also can save memory and run time. Experimental results show that the method is effective and has higher clustering precision compared with conventional STREAM algorithm and CluStream algorithm.

Data driven state detection algorithm for ash deposition detection

A data driven state detection algorithm was proposed to improve the security and reliability of equipment. The algorithm is used for one class of objects whose state parameters change slowly and cumulatively in the long term. The concepts of multi-scale system, multi-scale entropy and multi-scale exergy were used to describe these processes. With the help of the algorithm, an ash deposition index for the radiant heating surface of a 600 MW unit was constructed to monitor the states of the instruments. Noise was analyzed. The results of simulation experiments demonstrate the effectiveness of the algorithm, which can provide a technical basis for condition maintenance.

A data mining rule extraction method for thermal power unit operation optimization

Abstract A rule extraction method for thermal power unit operation optimization which based on data mining technology is proposed in this paper. Data mining technology is employed to analyze history data stored in real-time/history database of the unit. Stability index, economic index, environmental index and synthetic index are constructed to evaluate the performance of current operating condition. Through comparison analysis on similar operating condition, the best operating parameters and operating mode can be found out at the current condition. Accompanying with data accumulation proceeding in database, nonlinear static model between the unit operation performance index and controllable parameters is drawn over all operating conditions. Effectiveness of this method is illustrated by a practical operation optimization project, in which the realization scheme of operation guidance is also given out.