Anomaly detection of liquid levels in molds is an important task in continuous casting. Data that consists of a series of liquid levels in mold during a continuous casting process can be viewed as a time series, on which Time Series Anomaly Detection (TSAD) methods can be applied. However, the abnormal and normal data in the liquid data in the mold sequence share similar features. And due to manual control limitations, the anomaly sequence in liquid level in mold data lasts longer. Therefore, using existing TSAD methods based on AutoEncoders (AEs) often results in high false positive rates. In this paper, a novel framework is proposed for anomaly detection of liquid level in mold by using unsupervised deep-learning-based TSAD. The framework decomposes a time series into normal and error sequences. A forecasting network reconstructs the normal sequence to solve the first issue, which allows the proposed method to consider the context. An error extraction network generates errors from the original sequence to solve the second issue. It removes anomalies from the original sequence during training to prevent anomaly pollution and allows the forecasting network’s training to be free from anomaly pollution. A new dynamic threshold method is proposed to identify anomalies. The proposed method is evaluated on the actual casting dataset by comparing it with baseline methods. The experiment results indicate that the proposed framework outperforms some of the best anomaly detection methods in terms of accuracy, precision, and F1 score.

Continuous casting production is an important stage in smelting high-quality steel, and automatic casting control based on artificial intelligence is a key technology to improve the continuous casting process and the product quality. By controlling the opening degree of the stopper rod reasonably, the mold can be filled with liquid steel stably in the specified time window, and automatic casting can be realized. In this paper, an automatic casting control method of continuous casting based on an improved Soft Actor–Critic (SAC) algorithm is proposed. Firstly, a relational model of the stopper rod opening degree and the liquid steel outflow velocity is established according to historical casting data. Then the Markov Decision Process (MDP) model of the automatic casting problem and the reinforcement learning framework based on the SAC algorithm are established. Finally, a Heterogeneous Experience Pool (HEP) is introduced to improve the SAC algorithm. According to the simulation results, the proposed algorithm can predict the stopper rod opening degree sequence under the constraint of the target liquid level curve. Under different billet specifications and interference conditions, an accuracy of 80% of liquid level in the mold and a stopper rod opening degree stability rate of 75% can be achieved, which is 4.29% and 3.17% higher than those for the baseline algorithms, respectively.

To achieve uniform cooling and effective homogenization control in ultra-large beam-blank molds necessitates the optimization of submerged-entry-nozzle (SEN) structures. This study employed computational fluid dynamic (CFD) modeling to investigate the impact of two-port and three-port SEN configurations on fluid flow characteristics, free-surface velocities, temperature fields, and solidification behaviors. Subsequently, integrating numerical simulations with the non-dominated sorting genetic algorithm II (NSGA-II) and metallurgical quality-control expertise facilitated the multi-objective optimization of a three-port SEN structure suitable for beam-blank molds. The optimized parameters enabled the three-port SEN to deliver molten steel to the meniscus at an appropriate velocity while mitigating harmful effects such as SEN port backflow, excessive surface temperature differences, and shell thickness reduction due to fluid flow. The results indicated that the three-port SEN enhanced the molten-steel flow pattern and mitigated localized shell thinning compared with the two-port SEN. Additionally, the optimized design (op2) of the three-port SEN exhibited reduced boundary layer separation and superior fluid dynamics performance over the initial three-port SEN configuration.

The intelligent development of continuous casting quality engineering is an essential step for the efficient production of high-quality billets. However, there are many quality defects that require strong expertise for handling. In order to reduce reliance on expert experience and improve the intelligent management level of billet quality knowledge, we focus on constructing a Domain-Specific Knowledge Graph (DSKG) for the quality engineering of continuous casting. To achieve joint extraction of billet quality defects entity and relation, we propose a Self-Attention Partition and Recombination Model (SAPRM). SAPRM divides domain-specific sentences into three parts: entity-related, relation-related, and shared features, which are specifically for Named Entity Recognition (NER) and Relation Extraction (RE) tasks. Furthermore, for issues of entity ambiguity and repetition in triples, we propose a semi-supervised incremental learning method for knowledge alignment, where we leverage adversarial training to enhance the performance of knowledge alignment. In the experiment, in the knowledge extraction part, the NER and RE precision of our model achieved 86.7% and 79.48%, respectively. RE precision improved by 20.83% compared to the baseline with sequence labeling method. Additionally, in the knowledge alignment part, the precision of our model reached 99.29%, representing a 1.42% improvement over baseline methods. Consequently, the proposed model with the partition mechanism can effectively extract domain knowledge, cand the semi-supervised method can take advantage of unlabeled triples. Our method can adapt the domain features and construct a high-quality knowledge graph for the quality engineering of continuous casting, providing an efficient solution for billet defect issues.

The complex cross-sectional shape of oversized beam blanks and the size effect of ultra-large-section beam blanks create severe issues related to the surface and internal quality of the castings. To ensure quality and control in the production of ultra-large-section beam blanks, a numerical and physical model of molten steel flow in the three-port submerged entrance nozzle (SEN) mould, with section dimensions of 1300 × 510 × 140 mm, was established. This model was created using numerical simulations and NSGA-II genetic algorithm optimisation, and the impact of the casting speed and SEN immersion depth on the mould’s flow behaviour was investigated. The results showed that a deeper SEN immersion depth resulted in, a greater impact depth of the molten steel, and the surface flow velocity decreased. Both the impact depth and the surface flow velocity of the molten steel increased with increasing casting speed. The physical simulation and numerical simulation of the molten steel flow form and flow velocity distribution in the mould were in good agreement with each other, thus verifying the accuracy of the numerical simulation. The process parameters derived from this study were all within an appropriate range, which can help to improve the quality of continuously cast beam blanks. This also provides guidance for selecting optimal parameters for actual continuous casting production processes.

A variety of cast product defects may occur in the continuous casting process. By establishing a Continuous Casting Quality Knowledge Graph (C2Q-KG) focusing on the causes of cast product defects, enterprises can systematically sort out and express the relations between various production factors and cast product defects, which makes the reasoning process for the causes of cast product defects more objective and comprehensive. However, reasoning schemes for general KGs often use the same processing method to deal with different types of relations, without considering the difference in the number distribution of the head and tail entities in the relation, leading to a decrease in reasoning accuracy. In order to improve the reasoning accuracy of C2Q-KGs, this paper proposes a model based on a two-branch reasoning network. Our model classifies the continuous casting triples according to the number distribution of the head and tail entities in the relation and connects a two-branch reasoning network consisting of one connection layer and one capsule layer behind the convolutional layer. The connection layer is used to deal with the sparsely distributed entity-side reasoning task in the triple, while the capsule layer is used to deal with the densely distributed entity-side reasoning task in the triple. In addition, the Graph Attention Network (GAT) is introduced to enable our model to better capture the complex information hidden in the neighborhood of each entity and improve the overall reasoning accuracy. The experimental results show that compared with other cutting-edge methods on the continuous casting data set, our model significantly improves performance and infers more accurate root causes of cast product defects, which provides powerful guidance for enterprise production.