Machine learning algorithms for the prediction of non-metallic inclusions in steel wires for tire reinforcement

Towards big industrial data mining through explainable automated machine learning

“…The machine learning is widely used in many industrial applications across different levels, including processes, machines, shop floors, and supply chain levels. For instance, machine learning models can be used to control product quality [14], to monitor the condition of tools by tracking the evolution of their state [15], or to monitor the health of machines by predicting the time of occurrences of machine failures and also to estimate the criticality of these failures [16]. However, de-spite its countless benefits and advances, building a machine learning pipeline is still a challenging task, partly because of the difficulty in manually selecting an effective combination of an algorithm and hyper-parameters values for a given task or problem.…”

Application of Time Series Data Anomaly Detection Based on Deep Learning in Continuous Casting Process

“…Machine learning algorithms such as logistic regression, support vector machines, and random forests have been used to predict inclusions in cord steel. 14) However, traditional methods based on statistical values of time series variables are no longer applicable with the increasing demand for uniformity and stability of product quality. 1) The modeling strategies based on time series have received widespread attention.…”

Convolutional Neural Network‐Based Method for Predicting Oxygen Content at the End Point of Converter

“…[13] As an important branch of machine learning in recent years, deep learning has been introduced into the field of steelmaking. [14][15][16][17] It is a nonlinear modeling algorithm that uses artificial neural networks as the basic architecture to extract features from data and realize knowledge learning. [18] Since the artificial neural network can approach any continuous nonlinear mapping, with strong self-learning ability, the artificial neural network technology is applied to converter steelmaking end point prediction, as long as there are enough training samples, a good fitting effect can be achieved.…”