The fan is one of the key components of the power transformer cooling system. The operating condition of fans determines transformers' internal temperature rise and long-term reliability. However, at present, the fans' condition monitoring only includes switch status (online) and regular maintenance (offline), online direct monitoring of the fans' operating condition is lacking due to economic costs. In view of the above-mentioned problem, this paper proposes a transformer fan early fault detection method based on the oil exponent, which is monitored by the existing transformer top-oil temperature data, thereby detecting the abnormality of the fans. In this method, the oil exponent was chosen as the characteristic criterion. First, to obtain the range of oil exponent in different cooling modes, a set of physical models describing global oil flow and its interaction with air was established based on fluid dynamics and heat transfer principle. Then, regarding the constantly changing top-oil temperature, ambient temperature and load current, an oil exponent tracking algorithm using particle swarm optimization (PSO) was proposed within an improved IEC dynamic thermal model. The operation data from an oil-immersed transformer with a rated capacity of 120-MVA and rated voltage of 220-kV was selected to verify the above methods under two different scenarios.