This paper presents a method of forecasting stable operation of gas compressor unit (GCU) centrifugal supercharger (CFS) installed on a piping of compressor shops servicing gas pipelines. The stability of supercharger...This paper presents a method of forecasting stable operation of gas compressor unit (GCU) centrifugal supercharger (CFS) installed on a piping of compressor shops servicing gas pipelines. The stability of superchargers operation is assessed in relation to the phenomenon of surge. Solution of this problem amounts to the development and numerical analysis of a set of ordinary differential equations. The set describes transmission of gas through a compressor shop as a fluid dynamics model with lumped parameters. The proposed method is oriented to wide application by specialists working in the gas industry. The practical application of this method can use all-purpose programming and mathematical software available to specialists of gas companies.展开更多
The article describes an approach to building a self-learning diagnostic algorithm. The self-learning algorithm creates models of the object under consideration. The models are formed periodically through a certain ti...The article describes an approach to building a self-learning diagnostic algorithm. The self-learning algorithm creates models of the object under consideration. The models are formed periodically through a certain time period. The model includes a set of functions that can describe whole object, or a part of the object, or a specified functionality of the object. Thus, information about fault location can be obtained. During operation of the object the algorithm collects data received from sensors. Then the algorithm creates samples related to steady state operation. Clustering of those samples is used for the functions definition. Values of the functions in the centers of clusters are stored in the computer’s memory. To illustrate the considered approach, its application to the diagnosis of turbomachines is described.展开更多
文摘This paper presents a method of forecasting stable operation of gas compressor unit (GCU) centrifugal supercharger (CFS) installed on a piping of compressor shops servicing gas pipelines. The stability of superchargers operation is assessed in relation to the phenomenon of surge. Solution of this problem amounts to the development and numerical analysis of a set of ordinary differential equations. The set describes transmission of gas through a compressor shop as a fluid dynamics model with lumped parameters. The proposed method is oriented to wide application by specialists working in the gas industry. The practical application of this method can use all-purpose programming and mathematical software available to specialists of gas companies.
文摘The article describes an approach to building a self-learning diagnostic algorithm. The self-learning algorithm creates models of the object under consideration. The models are formed periodically through a certain time period. The model includes a set of functions that can describe whole object, or a part of the object, or a specified functionality of the object. Thus, information about fault location can be obtained. During operation of the object the algorithm collects data received from sensors. Then the algorithm creates samples related to steady state operation. Clustering of those samples is used for the functions definition. Values of the functions in the centers of clusters are stored in the computer’s memory. To illustrate the considered approach, its application to the diagnosis of turbomachines is described.
