As a key component of the rolling mill, the four-row cylindrical roller bearing (FCRB) operates under complex working conditions of high speed, high temperature, and heavy load. Due to the lack of an effective temperature test scheme for rolling mill bearings, a too high temperature can easily lead to bearing failure or damage under unsteady conditions. To reveal the internal temperature distribution law of four-row roller bearings of rolling mills and solve the common problem of difficult temperature monitoring of rolling mill bearings, in this paper, a four-row cylindrical roller bearing of 1140 mm cold rolling six-high mill is taken as the research object, and the temperature field calculation model for four-row cylindrical roller bearings is established. Firstly, the mechanical analysis model of FCRB is established on the basis of single row bearing by slice method. Secondly, the mechanical calculation model of FCRB is established by the Newton–Raphson method (NRM) and the finite element method (FEM). Thirdly, based on the mechanical calculation model, the finite element method is used to establish the temperature field model of FCRB under uniform load distribution and non-uniform load distribution. Finally, the temperature test experiment is carried out with the FCRB in the rolling mill fault diagnosis test bench. The results show that the error between the FCRB temperature calculation model and the experimental results is less than 10%. It can be seen that the uneven temperature distribution of FCRB is mainly caused by the uneven load distribution. The temperature distribution along the axial direction of the bearing is related to the load distribution of each column, while the circumferential temperature distribution is related to the azimuth angle.

To achieve early perception and accurate prediction of flatness quality, a partial least squares–particle swarm optimization–multi-output support vector regression (PLS-PSO-MSVR) is proposed. Firstly, we parameterized the flatness and used it as an evaluation indicator for flatness. Then, the prediction model was constructed using multi-output support vector regression (MSVR). In the modeling process, particle swarm optimization is used to optimize the parameters. To overcome the problem of information redundancy, reduce data dimensions to reduce computational time, and improve the prediction performance of the algorithm, this paper combines partial least squares and PSO-MSVR to achieve accurate prediction of the flatness features. Finally, the actual industrial process data from the hot rolling 1580 production line was used for validation, and the predicted performance was evaluated using mean absolute error (MAE), mean square error (MSE), root mean square error (RMSE), and coefficient of determination (R²). MAE decreased to 0.15, MSE decreased to 0.038, and RMSE decreased to 0.195. The R² approaches 1, indicating excellent model fit. This study achieves accurate prediction of the flatness characteristic coefficient, which not only enhances the diagnostic efficiency of steel flatness quality but also helps avoid unnecessary economic losses. Moreover, the prediction model provides a reliable basis for flatness control, offering operators a user-friendly reference tool. This approach compensates for the time lag inherent in the original system and contributes to improved accuracy in flatness control.