Jianxin Zhou

Nitrogen oxide emission modeling for boiler combustion using accurate online support vector regression

Using the data of boiler combustion, an accurate online support vector regression (AOSVR) model of the Nitrogen Oxide (NOx) emission property is built. After the training and the testing, the result shows that AOSVR is a good tool for modeling with small sample data, compared with the method of SVR and artificial neural network (ANN). The model can estimate the NOx emission accurately under different conditions when the load or other parameters changes. The accuracy of this model can also meets the demand of the combustion optimization. The result shows that this new model has a good learning efficiency and prediction accuracy because the algorithm can update the parameters of the model by itself as time and other parameters change.

An Investigation on System Anomaly Source Diagnosis Using KPCA-FPSDG

The process monitoring using kernel PCA is lack of inference and can not find the root cause of abnormal data. An abnormal root cause diagnosis method combining KPCA and FPSDG was proposed. First the FPSDG and KPCA models should be built. All the variables are monitored using KPCA, when anomaly occurs, the abnormal variable is isolated and fuzzed. Based on the states of variables, inference diagnosis on FPSDG is used to find real anomaly source. The KPCA-FPSDG has the multivariate monitoring characteristics of KPCA and fault explanation capability of SDG, and also the shortcoming of single variable statistics in discriminating node conditions and threshold values in traditional SDG avoided. This method can effectively save diagnosing time as well as raise the degree of diagnosing process automation. Case studies show that the KPCA-FPSDG method can effectively monitor the thermal system process and find the anomaly source promptly.

Monitoring method of slurry quality in wet flue gas desulfurization system based on fuzzy C-means clustering

In this paper, a method of slurry quality monitoring and diagnosis in Wet Flue Gas Desulfurization(WFGD) system was proposed based on feature extraction of slurry quality and Fuzzy C-means(FCM) clustering. Focusing on the WFGD system of a 600 MW unit in a certain power plant, a new index for slurry quality monitoring was put forward. And clustering centers could be obtained to be the standard modes for slurry quality identification by adopting FCM to perform clustering analysis, in which the desulfurization efficiency and pH were regarded as feature information. Slurry quality diagnosis could be realized eventually by calculating the membership between the unknown samples and the standard modes of slurry quality. Furthermore, a fuzzy quantitative monitoring index was presented to quantitatively monitor the slurry quality state during its actual operation according to the theory of fuzzy membership. On the basis of diagnostic analysis of the field operating data, it demonstrates that the method raided in this dissertation can monitor the slurry quality state efficiently, providing foundation for operation adjustment.

Fault diagnosis of slurry pH data base on autoregressive integrated moving average and least squares support vector machines

A hybrid model that exploits the unique strength of the autoregressive integrated moving average (ARIMA) model and the least squares support vector machine (LSSVM) model was proposed for slurry pH value fault diagonosis in wet flue gas desulfurization (WFGD) system. The hybrid model was validated and evaluated by operating data and compared with individual ARIMA and LSSVM models. The results show that the hybrid prediction model can capture both linear and nonlinear patterns and has a better prediction performance than any single model. On this base, a sensor fault diagnosis system for pH value was designed by using the hybrid model. Firstly, the sensor fault location is determined on the reconstruction residuals, and then data reconstruction is implemented by the hybrid model instead of fault data. The simulation results from a 600 MW unit case study show that the model has high modeling precision and strong generalization. The fault diagnosis based on the hybrid model can diagnose the sensors fault and obtain credible reconstruction data.

A modified mutative scale chaotic optimization algorithm for economic load dispatch

A modified mutative scale chaotic optimization (MMSCO) algorithm for economic load dispatch among power generation units is proposed in this paper. The MSCO does not require derivative information and uses stochastic random search instead of a gradient search. In MSCO, mutative scale chaotic sequences are changed into generation load variables through load maps for calculation of the cost function. But these load variables do not always correspond with load constraints, searching becomes random and sightless. In MMSCO, a novel load map is built after the chaotic search to ensure the load variables fit the feasible region. MMSCO is validated for a test system consisting of 13 thermal units whose incremental fuel cost function takes into account the valve-point loading effects. MMSCO is simple in concept, few in parameters, and easy in implementation. The proposed modified method outperforms other chaotic search algorithms in solving load dispatch problems with the valve-point effect.