A novel forecast model based on CF-PSO-SVM approach for predicting the roll gap in acceleration and deceleration process

Abstract

Purpose In the cold rolling process, friction coefficient, oil film thickness and other factors vary dramatically with the change in the rolling speed, which seriously affects the strip thickness deviation. This paper aims to study the law among the parameters in the rolling process to improve the strip control precision. Design/methodology/approach In this paper, a novel forecasting model of the roll gap based on support vector machine (SVM) optimized by particle swarm optimization with compression factor (CF-PSO) is proposed. Based on lots of online data, the roll gap models regressed by PSO-SVM, genetic algorithm (GA)-SVM and CF-PSO-SVM are obtained and verified through evaluating the performances with the decision coefficient (R2), mean absolute error and root mean square error. In addition, with the good forecasting performances of CF-PSO-SVM, a roll gap compensation model is studied. Findings The results indicate that the proposed CF-PSO-SVM has excellent learning regression ability compared with other optimization algorithms. And the obtained roll gap compensation model based on the rolling speed and plastic coefficient have been applied in product, which is validated and gets a good product effect. Originality/value In this paper, the SVM algorithm is combined with traditional rolling technology to solve the problems in actual production, which has great supporting significance for the improvement of production efficiency.

Development of Cold‐Rolling Edge‐Drop Control Technology for Electrical Steel: A Review

“…Additionally, strip rolling generates vast amounts of industrial data, which makes it suitable for machine-learning techniques. Several scholars have attempted to utilize machinelearning methods for modeling the rolling process, primarily focusing on a single industrial index or process parameter such as thickness, [94] crown, [95,96] bending force, [97] and rolling force. [98] Some studies have focused on multidimensional indexes, particularly the distribution of strip flatness.…”

Crude oil price forecasting: An ensemble‐driven long short‐term memory model based on CEEMDAN decomposition and ALS‐PSO optimization

“…The setting of inertia weight and acceleration factor is a commonly used configuration in the classic PSO algorithm and is widely used in many PSO algorithms. 53,54 The hyperparameters 55,56 in LSTM were optimized by ALS-PSO. The hyperparameters chosen for this study included batch size, number of hidden layers, learning rate, and optimization range, as shown in Table 3.…”

Prediction of Standard Time of the Sewing Process using a Support Vector Machine with Particle Swarm Optimization

“…To prevent the particle disengaging from the search space in the search process, , where max V is the maximum flying speed. To speed up the convergence of the algorithm, w is linearly reduced as the iteration progresses: (5) where iter and max iter are the current and maximum iteration times, respectively; and max w and min w are the maximum and minimum inertial weights, respectively [19].…”

“…SVM was proposed by Vapnik et al in 1995, and it is based on structural risk minimization (SRM) and Vapnik-Chevronenks dimension principle. Research shows that SVM with many attributes of excellence, such as fast learning, global optimization, and excellent generalization ability for the smallsample data set, is generally superior to the ANN model [19]. It has been studied increasingly in recent years and applied to several standard time formulating problems.…”