In this dissertation, some problems of support vector machine algorithms are analyzed. To solve the problem of uneven size of classes and other problems, two new support vector machine algorithms and two new classification methods are showed.The main research in this paper can be classed as follows:(1) An overview on a variety of classification algorithms for support vector machine (SVM) is given. Some algorithms such as v-SVM, One-class SVM, RSVM, weighted SVM and LS-SVM are concentrated.(2) Based on the theory of support vector machine, a novel approach that contains support vectors describing the hypershpere to separates the samples is showed.(3) When training sets with uneven class sizes are used, the classification result based on support vector machine is undesirably biased towards the class with more samples in the training set. That is to say, the larger the sample size, the smaller the classification error, whereas the smaller the sample size, the larger the classification error. This paper proposes weighted support vector machine algorithms based on the analysis of the cause of such problem, and this algorithm overcomes the drawback which standard support vector machine algorithm can't deal with each sample flexibly and compensates for the unfavorable impact caused by this bias. Such weighted support vector machines improve classification accuracy for class with small size at the cost of accuracy reduction for large size class, and can be applied to the case of regarding small sort of classification accuracy, such as fault diagnosis.(4) A new classification method named Rough Support Vector Machine is presented in this paper, based on support vector machine and rough set theory. This method has high predictive classification accuracy with much less attributes, which means less sensors and less cost. And it keeps certain redundant attributes to have high predictive accuracy in the case of missing information caused by such as sensors fault. By good performances of support vector machine, this method increases classification accuracy with good generalization performance.(5) A new classification method based on support vector machine theory and principal component analysis (PCA) techniques is presented. Noise is eliminated by PCA, which can increases the predicted classification accuracy. The compensating way for training sets with uneven class sizes is shown inthis method.(6) The proposed support vector machine algorithms and classification methods are used in classifying operation state of wastewater treatment processes. The numerical experiments show that these algorithms and methods are effective.