The invention discloses a subway vehicle bearing fault online detection method, and belongs to the field of subway safety monitoring. The key point of the technical scheme comprises the following steps: (1) establishing a model: the establishment of a bearing fault model is the basis for fault identification; (2) fault diagnosis: collecting and diagnosing vehicle bearing information of the vehicle; and (3) form a report and uploading the report: form the reporting of comparative judgment results, and uploading the report. By adopting the subway vehicle bearing fault online detection method disclosed by the invention, the problem that a bearing fault cannot be found in time is solved, and effects of founding the bearing fault in advance and replacing or maintaining the faulty bearing in time are realized.