Marine diesel engine fault tracing method based on sensitivity analysis

Abstract

The invention discloses a marine diesel engine fault tracing method based on sensitivity analysis. The method comprises the following steps: firstly, establishing a marine diesel engine industrial bigdata analysis model; secondly, constructing a performance early warning characteristic evidence body, a trust interval and a diesel engine fault mode database by utilizing the established model, andjudging whether output parameters in the characteristic evidence body are in the trust interval or not; establishing an evidence body sensitivity mechanism, and determining evidence body sensitivity parameters; and finally, tracing the fault of the diesel engine according to the evidence body sensitive mechanism and the diesel engine fault mode database. According to the invention, a big data technology is applied to marine diesel engine fault tracing, abnormal data can be effectively determined, and an alarm signal is given; meanwhile, based on the abnormal alarm signal, the marine diesel engine performance model and the local sensitivity analysis method, the purpose of rapid tracing of marine diesel engine faults is achieved.

Description

technical field [0001] The invention belongs to the field of big data and diesel engines, and in particular relates to a method for tracing the source of marine diesel engine faults based on sensitivity analysis. Background technique [0002] As the core power equipment of the ship, the marine diesel engine's operating status plays a vital role in the normal operation of the ship. How to actively realize the early warning and traceability of marine diesel engine faults according to the operating status of marine diesel engines is an urgent problem to be solved. [0003] At present, the development and application of science and technology such as sensors, the Internet of Things, and artificial intelligence have promoted the in-depth integration of big data technology in the industrial field, and it has shown strong advantages in solving fault diagnosis by mining valuable data. Liu Jiwei from North China Electric Power University proposed a multi-scale condition monitoring m...

AI Technical Summary

Problems solved by technology

Most of the existing research focuses on abnormal monitoring or fault diagnosis of equipment with the help of big data technology, ignoring the internal relationship between input and output data in fault tracing; and not considering the normal input parameters of marine diesel engines. Changes in performance over time, resulting in changes in output parameters, resulting in a precursor to failure

For fault early warning and source tracing in this case, traditional fault diagnosis and abnormal monitoring methods have little effect

Images