Prediction and analysis of cold rolling mill vibration based on a data-driven method

An In-Depth Study of Vibration Sensors for Condition Monitoring

Heavy machinery allows for the efficient, precise, and safe management of large-scale operations that are beyond the abilities of humans. Heavy machinery breakdowns or failures lead to unexpected downtime, increasing maintenance costs, project delays, and leading to a negative impact on personnel safety. Predictive maintenance is a maintenance strategy that predicts possible breakdowns of equipment using data analysis, pattern recognition, and machine learning. In this paper, vibration-based condition monitoring studies are reviewed with a focus on the devices and methods used for data collection. For measuring vibrations, different accelerometers and their technologies were investigated and evaluated within data collection contexts. The studies collected information from a wide range of sources in the heavy machinery. Throughout our review, we came across some studies using simulations or existing datasets. We concluded in this review that due to the complexity of the situation, we need to use more advanced accelerometers that can measure vibration.

Using feed-forward perceptron Artificial Neural Network (ANN) model to determine the rolling force, power and slip of the tandem cold rolling

In this paper, an Artificial Neural Network (ANN) is used to investigate the influence of rolling parameters such as thickness reduction, inter-strand tension, rolling speed and friction on the rolling force, rolling power, and slip of tandem cold rolling. For this reason, the rolling power was derived for 195 various experiments through a series of observation tests. The network is trained and tested using real data collected from a practical tandem rolling line. The best topology of the ANN is determined by Broyden-Fletcher-Goldfarb-Shanno (BFGS) training algorithm and error, and nine neurons in the hidden layer had the best performance. The average of the training, testing, and validating correlation coefficients data sets are mentioned 0.947, 0.924, and 0.943, respectively. The obtained results show MSE value 4.2 × 10^-4 for predicting slip. In addition, the effect of friction and angular velocity condition on the cold rolling critical slip phenomena are investigated. The results show that ANNs can accurately predict the cold rolling parameters considered in this study.

Pareto multi-objective optimization of tandem cold rolling settings for reductions and inter stand tensions using NSGA-II

In this paper, multi-objective optimization of tandem cold rolling settings for reductions and inter-stand tensions using NSGA-II and Pareto-optimal front are investigated. In this multi-objective optimization, the total power consumption and uniform power distribution are suggested as objective functions, and reduction thicknesses in each stand and inter stand tensions were selected as problem decision variables. Analytical formulations are introduced to determine the rolling forces and power based on the Stone approach. Then, the main variables of the optimization problem, objective functions, linear and nonlinear constraints, are defined. Moreover, some empirical constraints are introduced regarding the practical limitations of cold rolling equipment and the mechanical properties of the material. At first, considering the conditions of a practical tandem rolling line, single-objective optimization is performed separately, and finally, NSGA-II was used for multi-objective optimization. Compared to the initial setting of the rolling line, the obtained single objective schedules have better performance. Moreover, the multi-objective results based on the Pareto-optimal front are investigated, and an optimized setting for rolling schedule has been suggested. Using this proposed schedule the total power consumption is reduced by more than 11% comparing to the initial setting and more uniform power distribution has been obtained in rolling stands. The normalized reductions calculated from this investigation are compared with numerical and experimental results found in the literature and the similarity was observed in the pattern of thickness reduction distribution.

Vibration prediction and analysis of strip rolling mill based on XGBoost and Bayesian optimization

The stable operation of strip rolling mill is the key factor to ensure the stability of product quality. The design capability of existing domestic imported and self-developed strip rolling mills cannot be fully developed, and the frequent occurrence of mill vibration and operation instability problems seriously restrict the equipment capacity and the production of high-end strip products. The vibration prediction analysis method for hot strip mill based on eXtreme gradient boosting (XGBoost) and Bayesian optimization (BO) is proposed. First, an XGBoost prediction model is developed based on a self-built data set to construct a complex functional relationship between process parameters and rolling mill vibration. Second, the important hyperparameters and parameters of XGBoost are optimized using Bayesian optimization algorithm to improve the prediction accuracy, computational efficiency, and stability of the model. Third, a comprehensive comparison is made between the prediction model in this paper and other well-known machine learning benchmark models. Finally, the prediction results of the model are interpreted using the SHapley Additive exPlanations (SHAP) method. The proposed model outperforms existing models in terms of prediction accuracy, computational speed and stability. At the same time, the degree of influence of each feature on rolling mill vibration is also obtained.