Research Of Data Applications In Fieldbus-based Monitoring Network Of Marine Engine Room

The safe operation of equipment in the engine room relies heavily on the engine room monitoring network. It can offer advice on how to manage and maintain the equipment and systems in the engine room.The engine room monitoring network can transmit the system status information over the network to the remote monitoring and controlling terminal, and alarm the failure of abnormal situation. This thesis provides a engine room monitoring network simulation platform that based on Controller Area Network to collect the data from the engine room monitoring network and introduces the hardware communication module and the server and the remote terminal software of the platform.Data mining is an effective way to process the mass data collected from the engine room monitoring network. Data mining is an integrated application for statistics, database, pattern identification, artificial intelligence, and visualization technique and data analysis. It is a process to find valuable information and knowledge from a lot of incomplete, noisy vague, stochastic date which is hidden or unknown to people.Rough set theory has been proven to be an important algorithm in the field of data mining. The rough set theory is good at handle uncertain information. It has received much attention of the researchers around the world. Rough set theory has been applied to many areas successfully including pattern recognition, machine learning, decision support, knowledge discovery, fault diagnosis, forecast modeling and so on.Knowledge reduction is one of the core technology in rough set theory.It has become one of the hottest research fields in data mining. An efficient and effective algorithm for knowledge reduction is the foundation of rough set theory.It is also the guarantee of rough set community applied on a large scale.This thesis tries to apply data mining method that based on rough set theory to the engine room monitoring network, use attribute reduction and value reduction to effectively detect the relationships between the condition attributes and the decision attributes of the engine room monitoring network. By investigating30groups of sample data of the low temperature fresh water cooling system,12original attributions were reduced to5attributions, critical parameter combinations for fault diagnosis were obtained. Finally find out the decision rules that can be used to offer decision support.