The application discloses an abnormal
vibration detection method, device, equipment and medium, comprising: obtaining historical running data of a target
rolling mill, the historical running data comprising
vibration measurement data, rolling piece plate shape data, rolling piece production data and rolling process data corresponding in
time sequence; constructing a training sample set and a
test sample set according to the historical running data; training a preset prediction model according to the training sample set and the
test sample set to obtain a target prediction model; obtaining real-time running data of a
rolling mill to be detected, and inputting the real-time running data into the target prediction model to determine whether the
rolling mill to be detected has abnormal vibration. The application can find the best
speed reduction window before the abnormal vibration causes great damage to the rolling mill or the rolling piece, and thus the rolling mill can be controlled to reduce the speed in time, the
occurrence probability of abnormal vibration is reduced, the rolling quality of the rolling piece is improved, and the service life of the rolling mill is prolonged to a certain extent.