空调机组故障诊断中多未知模态检测方法的研究-控制科学与工程专业毕业论文.docxVIP

ABSTRACT Fault detection and diagnosis for HVAC system in intelligent building is the guarantee of building safety, comfort and energy-saving. Optimization of fault detection and diagnosis method is able to improve the air conditioning efficiency, improve air quality, and reduce maintenance costs. A new idea of clustering based on gaussian mixture model in fault detection and diagnosis is put forward on the basis of study of mature detection technology about domestic and foreign air conditioning system, and combination with the feature that same unit that has similar characteristics. A new idea that using Gaussian mixture model(GMM) to identify unknown modes on the basis of comparision about different clustering methods and analysis about characteristics of air conditioning is proposed. And the advantage of clustering by using the gaussian mixture model is introduced. Upon this method, the structure and process of the temperature and humidity units are discussed. According to the law of conservation of energy and material, models are built.Then parameters to represent attributes are selected, and estimated through kalman filter algorithm.These characteristic parameters are as the basis of gaussian mixture model. EM algorithm is the core of Gaussian mixture model, which is composed of two steps, namely Step.E and Step.M. Algorithm is realized by the iterations of Step.E and Step.M, until the convergence of mixture model parameters. Then the optimal estimated result is obtained. After the gaussian mixture model is built, distribution of data points and identification of modes is according to the maximum a posteriori probability criterion. Using simulated air conditioning system platform, the gaussian mixture model of clustering method is verificated. By the MATLAB program, the corresponding algorithm is designed. Testing effect based on gaussian mixture model for air conditioning unit can be gotten from simulation experiments. Keywords: Operation Modes，Clustering，Gau