The steelmaking process in the iron and steel industry involves complicated physicochemical reactions. The main aim of steelmaking is to adjust the quality of molten steel. During the steel-tapping process, the temperature and carbon content are the most essential quality indices for end-point prediction. This article presents a novel machine learning framework for the end-point prediction problems in the smelting process. Considering the importance of data representation in modeling, the original data are inputted to a stacked autoencoder (SAE) to extract the essential features in an unsupervised manner. The top layer is then designed as a sparse Bayesian regression (SBR) layer to obtain the predicted mean values and error bars that measure the uncertainty in the prediction. To improve the generalization ability of the prediction model, an intelligent optimization algorithm based on improved differential evolution (DE) is used to optimize the hyperparameters of the model. The main advantage of this model is that the underlying characteristics of the samples can be learned automatically layer by layer, instead of designing them manually. Finally, the effectiveness of the proposed method is verified using real data collected from two steel plants. The experimental results show that the proposed model gives a more precise prediction than other existing models and can provide error bars for the end-point prediction. Note to Practitioners— The end-point prediction is critical to the quality of products produced in the iron and steel production process. Because of the complexity of the physiochemical reactions during smelting, it is difficult to build mechanism models for the complex environment. Generally, expert knowledge and experience are needed for real production. The motivation behind this article was to establish a data-driven model through machine learning methods to solve end-point prediction problems. First, a stacked autoencoder (SAE) was used to extract the essential information from the original data. Second, sparse Bayesian regression (SBR) was applied to the top layer. Thus, the predicted mean values and error bars could be obtained to improve the robustness of the prediction model. Furthermore, an improved differential evolution (DE) algorithm was designed to adaptively optimize the hyperparameters of the model. In the experiments, the proposed method was applied to two real steelmaking production processes. The results verify the effectiveness of the proposed model. This article can be extended to other processes such as continuous casting and reheating furnace. The model can also be generalized for other practical industries to improve the product quality and enable safer production.

中文翻译：

---

带稀疏贝叶斯回归的堆叠式自动编码器，用于炼钢过程中的终点预测问题

钢铁行业的炼钢过程涉及复杂的物理化学反应。炼钢的主要目的是调节钢水的质量。在钢攻丝过程中，温度和碳含量是终点预测最重要的质量指标。本文为冶炼过程中的终点预测问题提供了一种新颖的机器学习框架。考虑到数据表示在建模中的重要性，将原始数据输入到堆叠式自动编码器（SAE），以无人监督的方式提取基本特征。然后将顶层设计为稀疏贝叶斯回归（SBR）层，以获得预测的平均值和误差线，以测量预测中的不确定性。为了提高预测模型的泛化能力，基于改进差分进化（DE）的智能优化算法用于优化模型的超参数。该模型的主要优点是可以自动逐层学习样本的基本特征，而无需手动设计。最后，使用从两个钢铁厂收集的真实数据验证了该方法的有效性。实验结果表明，所提出的模型比其他现有模型提供了更精确的预测，并且可以为终点预测提供误差棒。而不是手动设计它们。最后，使用从两个钢铁厂收集的真实数据验证了该方法的有效性。实验结果表明，所提出的模型比其他现有模型提供了更精确的预测，并且可以为终点预测提供误差棒。而不是手动设计它们。最后，使用从两个钢铁厂收集的真实数据验证了该方法的有效性。实验结果表明，所提出的模型比其他现有模型提供了更精确的预测，并且可以为终点预测提供误差棒。执业者注意事项— 终点预测对于钢铁生产过程中生产的产品质量至关重要。由于冶炼过程中理化反应的复杂性，很难为复杂的环境建立机理模型。通常，真正的生产需要专家的知识和经验。本文的动机是通过机器学习方法来建立数据驱动的模型来解决端点预测问题。首先，使用堆叠式自动编码器（SAE）从原始数据中提取基本信息。其次，将稀疏贝叶斯回归（SBR）应用于顶层。因此，可以获得预测平均值和误差线以改善预测模型的鲁棒性。此外，设计了一种改进的差分进化（DE）算法，以自适应地优化模型的超参数。在实验中，所提出的方法被应用于两个真实的炼钢生产过程。结果验证了所提模型的有效性。本文可以扩展到其他过程，例如连续铸造和再加热炉。该模型还可以推广到其他实际行业，以提高产品质量并实现更安全的生产。