With　the　rapid　development　of　high-speed　railway　technology,　ensuring　its　operational　safety　has　become　an　important　issue.　In　particular,　real-time　monitoring　of　the　high-speed　railway　pantograph　network　system　is　of　great　significance　for　preventing　failures　and　reducing　accidents.　This　research　aims　to　improve　the　intelligent　detection　performance　of　high-speed　railway　pantograph　network　status　through　the　improved　YOLO　algorithm.　Research　methods　include　the　use　of　deep　learning　technology　and　image　processing　technology,　focusing　on　improving　the　YOLO　algorithm　to　enhance　its　detection　accuracy　in　complex　environments,　especially　its　ability　to　identify　small　targets　and　its　adaptability　to　dynamic　environments.　It　is　expected　that　through　these　improvements,　more　accurate　and　efficient　status　monitoring　of　high-speed　railway　pantographs　will　be　achieved,　thereby　improving　the　safe　operation　level　of　high-speed　railways.　©　2024　IEEE.