Traditional　fault　diagnosis　systems　of　rolling　mills　mostly　use　single　machine　monitoring　net,　which　leads　the　real-time　data　running　only　in　the　enterprise　locally　and　can　not　monitor　and　manage　the　high-speed　wire　rolling　mills　between　units,　workshops　and　factories　concentratedly.　A　new-type　structure　of　remote　diagnosis　system　for　high-speed　wire　rolling　mills　is　presented　in　this　paper.　The　signal　processing,　computer　network　and　remote　diagnosis　etc　techniques　are　used　to　predictive　maintenance　manage　the　rolling　mills　units　in　this　system.　The　new　structure　reinforced　the　remote　feedback　function,　made　up　the　existing　fault　diagnosis　systems＇　insufficiency　in　the　extension　and　the　function,　promoted　resource　sharing　and　avoided　the　repeat　development.　The　remote　diagnosis　example　shows　that　the　system　can　monitor　and　diagnose　the　fault　information　of　remote　machine　timely　and　effectively.