摘要：Abstract Aiming at the complex and volatile conditions of the blast furnace, a support vector machine with multi-fault classification is proposed to solve the problem on blast furnace fault diagnosis. The normal or failure data is handled with a normalization and dimensionality reduction of principal component analysis (PCA). As a small amount of failure sample, a C-support vector classification (C-SVC) is applied in this filed. Different optimization methods have been performed for optimizing SVM parameters, including the grid-search method (GSM), the genetic algorithm (GA) and the particle swarm optimization (PSO). It compares these optimization algorithm strengths and limitations for multi-fault classification on classification ability and classification speed.
