To provide a suitable rotation rate for different machining processes, a single machine tool spindle should work over a wide range of speeds. This study considered the effects of speed on dynamic behaviour of ball bearings and combined the fatigue life model and ball bearing internal load distribution model to determine the appropriate preload. First, the influence of speed on internal load distribution and ball bearing contact angles was analysed. The preload was calculated using a ball bearing internal load distribution model. Next, assuming constant bearing fatigue life, the theoretical preload curves were determined using the fatigue life model by changing the reliability factor. Finally, at low speeds, the maximum designed preload (design value) was set as the initial preload. With the increase in speed, the optimum preload was hierarchically obtained within the internal region between the theoretical preload curves. An experimental test rig for the optimum preload of ball bearings, which can automatically adjust the preload, was developed. The proposed method for determining the optimum preload was verified using the measured performance indicators, including the temperature, motor currents, and vibration of ball bearings. The results showed that the optimum preload suggestion made the test ball bearings exhibit excellent behaviour.