At present, some elementary problems need to be solved when apply information fusion technique to gearbox fault diagnosis system. Firstly, it is exceedingly necessary to present the precise definition, model and architecture for gearbox, even for mechanical equipment fault diagnosis application, since current definitions, models and architectures about information fusion all refer to target identification, image processing and automatic command system. Secondly, it is also important that investigate the information pre-processing for gearbox fault diagnosis, viz. how to associate data in fault diagnosis application, which is very different with military application. Based on it, the fusion demands can be brought forward in terms of different information, e.g. through fusion to get feature parameter or enhance the information quantity---to get respective fusion method ultimately. Finally, investigate how to assess properly the performance of gearbox fault diagnosis system based on information fusion, including assessment of performance of the chosen feature parameters. In this paper we investigate and discuss preliminarily these three problems.
Mine ventilator fault diagnosis based on information fusion technique
