Rolling mill multi-row bearings are subjected to axial loads, which cause damage of rolling elements and cages, so the axial vibration signal contains rich fault character information. The vertical shock caused by the failure is weakened because multiple rows of bearings are subjected to radial forces together. Considering the special characters of rolling mill bearing vibration signals, a fault diagnosis method combining Adaptive Multivariate Variational Mode Decomposition (AMVMD) and Multi-channel One-dimensional Convolution Neural Network (MC1DCNN) is proposed to improve the diagnosis accuracy. Additionally, Deep Convolutional Generative Adversarial Network (DCGAN) is embedded in models to solve the problem of fault data scarcity. DCGAN is used to generate AMVMD reconstruction data to supplement the unbalanced dataset, and the MC1DCNN model is trained by the dataset to diagnose the real data. The proposed method is compared with a variety of diagnostic models, and the experimental results show that the method can effectively improve the diagnosis accuracy of rolling mill multi-row bearing under unbalanced dataset conditions. It is an important guide to the current problem of insufficient data and low diagnosis accuracy faced in the fault diagnosis of multi-row bearings such as rolling mills.

The roll-bearing-bearing housing (RBBH) system is one of the most common kernel structures used to determine strip mill stability and product surface quality in modern metallurgical machinery. To better understand dynamic characteristics of the RBBH system, this paper provides a nonlinear dynamic model and designs an engineering test platform on the RBBH system in the whole rolling process. First, a nonlinear dynamic model of the RBBH system supported by four-row rolling bearings under high speed and heavy load is established. Then, the method of combining Riccati transfer matrix and Newmark-β numerical integration is employed to solve nonlinear dynamic equations. After that, the engineering test platform is designed and assembled to capture and analyze the vibration signals of weathering steel (SPA-H) with finished thicknesses of 1.6 and 3.2 mm. Finally, the dynamic characteristics of the RBBH system are studied with the method of the dynamic model and vibration data fusion. The results show that the SPA-H with a finished thickness of 1.6 mm is rolled, the RBBH system fluctuates violently in both horizontal and vertical directions, and numerical results are highly consistent with experimental results in acceleration response, velocity response, and displacement response. In addition, the dynamic performance parameters of the four-row rolling bearing will also fluctuate greatly. Finally, there is significant interest to gain the benefits for the RBBH system design and mill stable rolling purposes.