Method for extracting dynamic characteristic parameters of intelligent ship system equipment

Abstract

The invention provides a method for extracting dynamic characteristic parameters of intelligent ship system equipment. The method comprises the following steps: processing original data by using a dynamic fractal theory, and constructing an optimal time-delay matrix; performing kernel principal component analysis on the constructed optimal time-delay matrix, calculating a centralized matrix, and screening data by using characteristic values; analyzing and calculating the centralization matrix, obtaining the numerical values of principal component characteristic parameters through calculation according to the fractal theory, and constructing a principal component characteristic parameter matrix. According to the method, the dynamic characteristic parameter information of the equipment can be screened and extracted according to the operation characteristics of the system equipment at different time and in different states, and the overall health state of the system can be evaluated by using the selected principal component characteristic data. According to the method, dimension reduction processing is carried out on multi-parameter data of the system equipment, and the calculation of redundant data is reduced; meanwhile, timeliness and effectiveness of equipment monitoring can be guaranteed through dynamic feature extraction, and the intelligent operation and maintenance efficiency of the system equipment is improved.

Description

Technical field [0001] The present invention relates to the field of intelligent ships, in particular, more particularly to a dynamic feature parameter extraction method of intelligent ship system equipment. Background technique [0002] With the further development of modern intelligent sensing, Internet of Things and large data technology, the amount of ship intelligence and autonomy is gradually improved, and the ship system and equipment will provide a more abundant state information, and the amount of measurement will be sharply expanded, data type Also become more diverse, how to use detection data and related knowledge information to achieve health management of mechanical equipment is a problem that the current ship intelligent operation and maintenance needs. Ship system equipment has a sense of perceived variables, many operating modes, and unique in failure mode, usually lacks dominant feature parameters. At the same time, due to the influence of external factors, such...

AI Technical Summary

Problems solved by technology

These methods still have deficiencies in the feature extraction of dynamic nonlinear data, and it is difficult to meet the analysis requirements of multi-parameter data of ship system equipment.

Images