Principal component analysis (PCA) and independent (ICA) have been widely used for process monitoring in industry. Since the operation data of blast furnace (BF) ironmaking contain both non-Gaussian distribution Gaussian data, above single PCA or ICA method hardly describes information BF completely, which makes diagnosis abnormal working-conditions only with a prone to false positives negatives. In this article, novel integrated PCA-ICA is proposed diagnosing conditions by comprehensively...

Optimal operation of an industrial blast furnace (BF) ironmaking process largely depends on a reliable measurement molten iron quality (MIQ) indices, which are not feasible using the conventional sensors. This paper proposes novel data-driven robust modeling method for online estimation and control MIQ indices. First, nonlinear autoregressive exogenous (NARX) model is constructed indices to completely capture dynamics BF process. Then, considering that standard least-squares support vector...

Blast furnace (BF) in ironmaking is a nonlinear dynamic process with complicated physical-chemical reactions, where multiphases and multifields interactions long time delay phenomena take place during its operation. In BF operation, the molten iron temperature as well Si content ([Si]), phosphorus ([P]), sulfur ([S]) most essential quality (MIQ) indices. The measurement, modeling, control of these indices have always been important issues metallurgic engineering automation. This paper...

This article proposes a multiobjective operation optimization method based on reinforcement self-learning and knowledge guidance for quality assurance consumption reduction of wastewater treatment process (WWTP) with nonstationary time-varying dynamics. First, models are developed by online sequential random vector functional-link (OS-RVFL) neural network, which can realize learning model parameters. Then, base is established to store typical cases guiding the subsequent optimizations. Based...

Optimizing the final grinding production indices (GPIs), which include product particle size and rate, to meet overall manufacturing performance requirements is main function of automatic control a circuit (GC). However, complex time-varying nature GC process dictates that these GPIs cannot be optimized solely by lower-level distributed systems (DCS), therefore an operator often incorporated manually determine set-points for DCS using his/her operational experience. With human being...

Optimal operation of a practical blast furnace (BF) iron-making process depends largely on good measurement molten iron quality (MIQ) indices. However, measuring the MIQ online is not feasible using available techniques. In this paper, novel data-driven robust modeling proposed for an estimation improved random vector functional-link networks (RVFLNs). Since output weights traditional RVFLNs are obtained by least squares approach, robustness problem may occur when training dataset...

In this paper, a novel control algorithm is presented to enhance the performance of tracking property for class nonlinear and dynamic stochastic systems subjected non-Gaussian noises. Although existing standard PI controller can be used obtain basic systems, desired difficult achieve due random To improve performance, an enhanced loop constructed using EKF-based state estimates without changing closed with controller. Meanwhile, gain obtained based upon entropy optimization error. addition,...

The automatic control of blast furnace (BF) ironmaking process has always been an important yet arduous task in metallurgic engineering and automation. In this article, a novel Kalman filter-based robust model-free adaptive predictive (MFAPC) method is proposed for the direct data-driven molten iron quality BF ironmaking. First, compact-form dynamic linearization-based extended MFAPC multivariable by generalizing existing single-variable to systems. Based on it, further considering problems...

By dealing with robust modeling and online learning together in a unified random vector functional-link networks (RVFLNs) framework, this paper presents novel sequential RVFLNs for data of dynamic time-varying systems its application blast furnace (BF) ironmaking process. First, to overcome the difficulties caused by nonlinear dynamics process enable learn avoid saturation, an improved version (OS-RVFLNs) is presented forgetting factor. It has been shown that OS-RVFLNs factor not only...

In order to improve the operation efficiency of high-speed trains and save communication resources railway network, this article proposes an on-demand event-triggered strategy for coordinated control multiple (MHSTs) subject delays input constraints. The MHSTs are modeled as a leader-following multiagent system each train exchanges their states with its neighboring through network. Then, scheme is designed determine when transmitted local controller trains. With fused into dynamic model...

Fused magnesium furnace (FMF) is the vital equipment for magnesia refractory production. The melting process of FMF subject to temperature, magnesite quality and composition, much more dynamic factors, which are prone abnormal conditions such as overheating, exhausting, semi-molten, affect stability safety production seriously. Due difficulties effectively monitoring accurately identifying with existing methods, this article proposes a novel method based on deep learning multi-information...

The inverse calculation of burden distribution matrix (BDM) is one the most important challenges in blast furnace iron-making processes. Focusing on this practical challenge, paper proposes a new spatial model charging process, and develops B-spline approximation-based probability density function (PDF) control algorithm to assign expected thickness layer perform required BDM. First, novel method for given using model. Then, according coexistence continuous bounded discrete variables BDM,...

Trajectory forecasting for human mobility plays a critical role in the effective management and sustainable development of urban transportation, which aligns with advocacy Sustainable Development Goals (SDGs). Although several approaches have been developed other trajectory applications, such as autonomous driving intelligent robotics, there remain limitations trajectories mobility. This is because they do not adequately consider prior knowledge movement patterns heterogeneous effects...

Fused silica is extensively used across various industries due to its superior properties, but densification can significantly alter performance. Detecting these changes requires high spatial resolution, which challenges the limits of current testing methods. This study explores use scattering-type scanning near-field optical microscopy (s-SNOM) analyze in fused through a combination experimental techniques-atomic force microscopy-based infrared spectroscopy (AFM-IR) and s-SNOM-and...