Search

The aluminum fluoride (AF) addition in aluminum electrolysis process (AEP) can directly influence the current efficiency, energy consumption, and stability of the process. This paper proposes an optimization scheme for AF addition based on pruned sparse fuzzy neural network (PSFNN), aiming at providing an optimal AF addition for aluminum electrolysis cell under normal superheat degree (SD) condition. Firstly, a Gaussian mixture model (GMM) is introduced to identify SD conditions in which the operating modes of AEP are unknown. Then, PSFNN is proposed to establish the AF addition model under normal SD condition identified by GMM. Specifically, a sparse regularization term is designed in loss function of PSFNN to extract the sparse representation from nonlinear process data. A structure optimization strategy based on enhanced optimal brain surgeon (EOBS) algorithm is proposed to prune redundant neurons in the rule layer. Mini-batch gradient descent and AdaBound optimizer are then introduced to optimize the parameters of PSFNN. Finally, the performance is confirmed on the simulated Tennessee Eastman process (TEP) and real-world AEP. Experimental results demonstrate that the proposed scheme provides a satisfactory performance. • A novel pruned sparse fuzzy neural network (PSFNN) is developed to establish the AF addition model under normal SD condition. • A sparse regularization term based on Kullback–Leibler divergence is designed in loss function of PSFNN to obtain the sparse representation. • The parameters of network are learned based on mini-batch gradient descent method with AdaBound optimizer. • An enhanced optimal brain surgeon (EOBS) algorithm is proposed to obtain a compact network structure. • The experimental results demonstrated that our method achieves a satisfactory performance. [ABSTRACT FROM AUTHOR]

Heat balance plays a significant role in reflecting the health state of aluminum electrolysis process (AEP). However, current methods hardly take into consideration the quantitative Heat Balance Indicator (HBI) construction by using the unlabeled data. In addition, it is limited to construct HBI by learning the complex relationship between degraded features and large-scale HBI labels in a supervised manner, because the labeled data are scarce and annotations are expensive in practice. To quantitatively construct HBI by using the unlabeled data, this paper proposes an unsupervised HBI construction method based on variational autoencoder (VAE). Firstly, we propose fuzzy evaluation strategy to estimate the tendency of cell temperature to highlight the trend of heat balance. Rather than simply using the latent features, we extract the feature representation of the heat balance state considering not only the latent features but also the reconstruction error. Finally, HBI is constructed by calculating the distance between the features representation of normal heat balance and degraded state. The applications of heat balance monitoring in a real-world aluminum electrolysis plant are performed to verify its effectiveness. The experimental results demonstrate that our proposed HBI construction method can better represent heat balance state of AEP, the average fault detection rate can achieve 80% for the monitoring electrolytic cells, increasing by more than 3% compared with these traditional monitoring statistics. [ABSTRACT FROM AUTHOR]

Abundant late Neoarchean granitoids occur in southwestern Liaoning Province, part of the Eastern Ancient Terrane of the North China Craton. These rocks include intermediate gneiss, TTG gneisses and potassic granitoids, and we report on the geochemistry and zircon SHRIMP ages as well as Hf-in-zircon isotopes of these granitoids in order to determine their petrogenesis. Field relationships suggest that most of these granitoids experienced widespread metamorphism and deformation, associated with anatexis at some localities. The intermediate gneisses, TTG gneisses and potassic granitoids were all emplaced at the end of the Neoarchean (2.50–2.53 Ga), and CL images document widespread recrystallization in the zircons. The intermediate and TTG gneisses yielded similar Hf isotopic systematics (ε Hf(t) = −3.73 to +6.42) as the associated potassic granitoids (ε Hf(t) = −2.44 to +7.80), and both rock types yielded mean Hf crustal model ages of 2.8–2.9 Ga. Combined with the geochemistry, we propose that the formation of the intermediate and TTG gneisses was related to partial melting of mafic rocks at different depth, whereas the potassic granitoids have variable petrogenesis. The nearly coeval TTG gneisses and potassic granitoids and their widespread metamorphism, deformation and zircon recrystallization suggest that a large-scale heat source must have been present at or near the base of the crust in southwestern Liaoning Province at the end of the Neoarchean. We propose that collision and post-collisional extension is the most likely tectonic environment for generation of the above granitoids, and the formation of widespread potassic granitoids played an important role in the maturation of continental crust in the North China Craton. Unlabelled Image • TTG gneisses and potassic granitoids show indistinguishable formation ages and Hf isotopes. • Widespread zircon recrystallization occurred immediately after formation of these granitoids. • A long-lived heat source is necessary for the formation and metamorphism of these granitoids. • Post-collision extension is the most likely environment for these granitoids. [ABSTRACT FROM AUTHOR]

In aluminum electrolysis process, cell temperature is an important index to reflect the current efficiency of electrolytic cell. Maintaining cell temperature in an appropriate range can improve current efficiency and economic benefits. Because aluminum electrolysis process is in a complex environment with high temperature, strong corrosivity, multivariable coupling and nonlinearity, cell temperature measuring instrument and equipment have the shortcomings of short service life and high cost. Therefore, this paper develops a cell temperature prediction model based on the integration of dual attention long short-term memory (DA-LSTM) and autoregressive moving average (ARMA). Firstly, the cell temperature series is decomposed into non-stationary sub-sequence and stationary sub-sequences by wavelet transform. The DA-LSTM is proposed to approximate non-stationary sub-sequence, which introduces a two-stage attention mechanism including feature attention mechanism and temporal attention mechanism. ARMA is employed to predict the stationary sub-sequences. Then, the integration model for the cell temperature prediction is reconstructed through multiple linear regression of DA-LSTM and ARMA. The integration model can overcome the problems that the prediction accuracy of a single model is low and the hysteresis phenomenon due to the mixed multi-information of aluminum electrolysis time series data. Experiments in a real-world aluminum electrolysis production process are conducted to demonstrate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

The analytical structure of fuzzy controller is important for better understanding and effective design of the fuzzy control system, especially for explaining why fuzzy control system work well. In this paper, we develop a three-dimensional fuzzy controller with arbitrary triangular input fuzzy sets. Then, the analytical structure of this fuzzy controller is derived rigorously, and some properties of this controller are given. To determine the parameters of the fuzzy controller, a novel proximal policy optimization algorithm with recall pool (RP-PPO) is proposed. A recall pool is designed in proximal policy optimization algorithm to store the best ten sets of parameters to enhance the optimization results. Finally, simulation studies are carried out on two time-delay systems and a nonlinear chemical process with time-varying time delay to validate the applicability and effectiveness of the proposed fuzzy controller. • A three-dimensional fuzzy controller with arbitrary triangular input fuzzy sets is designed. • We derive the analytical structure of fuzzy controller and analysis its properties. • A proximal policy optimization algorithm with a recall pool is proposed to optimize the parameters of fuzzy controller. • Simulations on time-delay models demonstrate the excellent performance of our proposed fuzzy controller. [ABSTRACT FROM AUTHOR]

The goethite process is a complicated process with multiple interactive chemical reactions in zinc hydrometallurgy. The use of a dynamic model plays an important role in predicting the key indicator on-line and in process control and optimization. However, because of the coupling influences among the chemical reactions, the conventional continuous stirred tank reactor (CCSTR) model is not adequate to describe this process. In this paper, we develop a weighted-coupling CSTR (WCCSTR) model for the goethite process by introducing weighted parameters. A parameter identification method is proposed to determine the unknown parameters. Then, a model predicted control (MPC) scheme is designed to achieve the process performance goals and minimize the process cost. To overcome the impact of frequent fluctuations in production conditions on the control performance, a novel parameter adaptive correction approach is proposed. The convergence of the adaptive correction approach is proved based on Lyapunov stability theory. Simulation results verify that the WCCSTR model has a higher prediction accuracy than the CCSTR model. The experimental results demonstrate that the MPC scheme performs better in controlling the process and reducing the process costs. [ABSTRACT FROM AUTHOR]

Generally, the iron removal process is modelled as a lumped parameter system that does not provide information about the distribution of reactants in the steady state. In this paper, we investigate the distributed parameter model and control for the iron removal process. By analyzing the process properties, we study the mass balance over a differential volume element, and the spatiotemporal distributions of the Fe 2+ , Fe 3+ and H + concentrations are derived by partial differential equations. An optimization problem is constructed to estimate the unknown parameters. Then, an optimal control problem for the oxidation rate of the ferrous ions in the steady state is proposed to achieve process requirements that have the lowest cost of oxygen and zinc oxide and obtain high goethite quality. To eliminate the impact from inevitable disturbances, an expert-based correction mechanism is constructed to compensate for the optimal control when the outlet ferrous ion concentrations are out of the desired range. Finally, the simulation results demonstrate the good performance of distributed parameter model. Industrial experiments demonstrate the satisfactory control performance of the optimal control strategy. Regarding manual operation and PI control, the control strategy increased the qualified ratio of the #4 reactor outlet Fe 2+ concentrations by 8.4% and 3.4%, respectively. Additionally, on average 17760 m 3 of oxygen and 109.68 t of zinc oxide per month were saved compared to manual operation. The mass percent of iron in the goethite increased from 34.31% (manual operation) and 35.12% (PI control) to 35.83%. [ABSTRACT FROM AUTHOR]

The North China Craton is an ideal place for studying the transition of the Earth's thermal structure and tectonics at the Archean–Proterozoic boundary due to its good preservation of the ~ 2.5 Ga tectono-thermal events. We report the discovery of a high-pressure mafic granulite from the Jiaodong Terrain in the North China Craton. The mafic granulite occurs as garnet–clinopyroxene–orthopyroxene–hornblende gneiss enclaves within a late-Archean trondhjemite–tonalite–granodiorite (TTG) gneiss. Typical high-pressure mineral assemblage of garnet–clinopyroxene–plagioclase–quartz ± rutile has been identified. Plagioclase + clinopyroxene ± orthopyroxene ± hornblende symplectite surrounding garnet (“white eye”) is also observed. Using the conventional geothermobarometry and the pseudosection modeling, a clockwise metamorphic P–T path with the peak conditions at ~ 17 kbar and ~ 880 °C was determined. Zircon U–Pb analyses (SHRIMP) on the overgrowth rim of zircon grains of two samples from the same outcrop yielded a metamorphic age of 2473 ± 6 Ma (MSWD = 0.8). The analyses on magmatic core gave a probable magmatic age of 2527 ± 12 Ma (MSWD = 1.9). The high-pressure granulite facies metamorphism corresponds to a collisional event between the ~ 2.5 Ga crust and ~ 2.9 Ga crust at the dawn of Paleoproterozoic in the North China Craton. It also represents a new but rare case of a subduction–collision tectonics at the Archean–Proterozoic transition and provides insight into the change of the Earth's thermal structure. [ABSTRACT FROM AUTHOR]

Iron precipitation by goethite plays an important role in zinc hydrometallurgy. The ferrous ion concentration, which is a key index for assessing the iron removal rate and process control results, cannot be measured on-line. In this study, an integrated predictive model of the ferrous ion concentration is established by integrating the mechanism model and error compensation model, which is based on data identification. The mechanism model is proposed based on an analysis of the process reaction and considering the reaction unit as a continuous stirred tank reactor model. For unknown parameters in the mechanism model, a double-particle swarm optimization algorithm based on information exchange and dynamic adjustment of the feasible region is developed for optimal selection. To improve the adaptive capability of the integrated model, we propose a model-updating strategy and parameter calibration method based on a sensitivity analysis to accomplish on-line adaptive updating of the predictive model. The simulation results demonstrate that the proposed model can effectively track the variation tendency of the ferrous ion concentration and successfully improve the adaptability of the integrated model. [ABSTRACT FROM AUTHOR]

• We propose an image enhancement method based on region decomposition and guided filtering. • In regions with insufficient illumination, we employ guided filtering to get information from brighter points in their neighborhood. • In regions with sufficient illumination, we regulate the magnitude of pixel variations to prevent overexposure. • A detail enhancement method is proposed based on a multi-scale Gaussian pyramid and texture fusion to improve clarity and naturalness. • The experiments show that the proposed method surpasses several state-of-the-art algorithms. Extraction of information from froth images is important for automatic control of froth flotation. However, images captured by cameras often suffer from severe uneven lighting, which significantly reduces the quality of froth images. Low-quality images hinder the accurate extraction of froth information, thereby affecting the control of the froth flotation system. Hence, we propose an image enhancement method based on region decomposition and guided filtering to improve the quality of images. Initially, we separate the image into regions with sufficient and insufficient illumination based on reflectance. In regions with insufficient illumination, the guided filter is applied to direct pixels to acquire information from brighter points in their neighborhood. Conversely, in other regions, we regulate the magnitude of pixel variations to prevent overexposure. Finally, a detail enhancement method is proposed based on a multi-scale Gaussian pyramid and texture fusion to improve clarity and naturalness. The experiments show that the method we proposed surpasses several state-of-the-art algorithms on public datasets. In the field of flotation, our method effectively enhances the image quality. Compared to other enhancement methods under the same segmentation strategy, our method significantly improves segmentation accuracy, demonstrating its strong practical value. In addition, our method also shows advantages in terms of computational speed. [ABSTRACT FROM AUTHOR]

Operational optimization of the Hall-Héroult cell is essential for achieving high efficiency and cost-effectiveness in the aluminum electrolysis process. Due to the complicated mechanism and variable working conditions, manual operational decision-making is extensively used in practice. They challenge the reliable and optimal operation of aluminum electrolysis process. In this paper, we develop a data-knowledge-driven decision-making support system (DMSS) to achieve operational optimization for the aluminum electrolysis process. DMSS consists of a prediction model, a multi-objective optimizer, and a knowledge-guided decision-making module. Specifically, we propose a working-conditions-based attention with the exogeneous inputs auto-regressive neural network (WCA-NARX) to construct a data-driven heat balance indicator (HBI) prediction model, where the working condition-related variables serve as covariates to enhance predictability. In addition, the designed structure of introducing working condition information through an attention mechanism can decouple covariates from operational variables and autoregressive variables, facilitating subsequent operational optimization. Then, a novel knowledge-assigned reference vector evolutionary algorithm (KRVEA) is designed to solve the multi-objective optimization problem of the aluminum electrolysis process, in which Pareto front solutions can be solved in the preferred region. Finally, we utilize the knowledge base that stores historical optimization cases to make decisions regarding the selection of a practical-requirement-based control scheme from the Pareto set. Real-world industrial experiments demonstrate that DMSS can effectively enhance control performance and achieve superior results compared to other competitive methods. The source code is available at https://github.com/wjiecsu/WCA-NARX. [ABSTRACT FROM AUTHOR]

In modern industrial processes, each subsystem interacts frequently and involves a large number of process variables with complex relations, which challenge process monitoring. In this paper, a distributed process monitoring method based on joint mutual information (JMI) and projective dictionary pair learning (DPL) is proposed for effective process monitoring in industrial systems with multimode, complex, and high-dimensional data. Firstly, considering the interactive information, redundancy and irrelevance among process variables, an automatic block division method based on JMI is proposed to divide process variables into several low dimensional blocks. Secondly, DPL-based monitoring model is established in each block of each mode. According to the multimode characteristic of industrial processes, a joint probability based on reconstruction error is proposed for mode recognition. Then, Bayesian inference method that fuses block statistics into global statistics is introduced for anomaly detection. The anomaly source is further determined by defining the block contribution coefficient and variable contribution coefficient. Finally, the effectiveness of the proposed method is demonstrated by a numerical simulation, Tennessee Eastman benchmark test, and experiments in an aluminum electrolysis industrial process. • A distributed process monitoring method via JMI-DPL is proposed. • An automatic block division method based on JMI is developed. • This method gives better performances in mode identification and anomaly detection. • An application in a real-world aluminum electrolysis process is provided. [ABSTRACT FROM AUTHOR]

The development of information and communication technology and its wide application in industrial control systems (ICSs) has brought a growing number of security risks to ICSs. Quantifying and dynamically assessing the security risks of ICSs is of great significance to protect ICSs from cyber attacks. Current risk assessment methods, however, do not take into account social engineering (SE) attacks and the potential cyber-to-physical risks associated with cyber attacks. To address these issues, we propose a novel method for the dynamic security risk assessment of ICSs, called SEAG. Specifically, the scheme first extends and modifies three metrics in the common vulnerability scoring system to four metrics for objectively calculating the exploit probability of SE. Then, we construct the attack graph by relying on the knowledge graph that integrates three kinds of knowledge including SE knowledge, common vulnerability knowledge, and control system knowledge. In addition, we combine real time attack data that causes system performance loss with the industrial protocol function code attack detected by the intrusion detection system to accurately quantify the potential cyber-to-physical risks associated with cyber attacks. This method allows us to dynamically assess the security risks of ICSs in real time. Finally, the method is verified by one simulation testbed, which shows the effectiveness and accuracy of the proposed method for dynamic quantitative evaluating security risks of ICSs. • Propose a novel method for the dynamic security risk assessment of ICSs, called SEAG. • Extend the CVSS metrics for calculating the exploit probability of social engineering. • Relying on the knowledge graph that integrates multi-knowledge, construct attack graph. • Combine attack data to quantify the cyber-to-physical risks. [ABSTRACT FROM AUTHOR]

Outlet ferrous ion concentration is an essential indicator to manipulate the goethite process in the zinc hydrometallurgy plant. However, it cannot be measured on-line, which leads to the delay of this feedback information. In this study, a self-adjusting structure radial basis function neural network (SAS-RBFNN) is developed to predict the outlet ferrous ion concentration on-line. First, a supervised cluster algorithm is proposed to initialize the RBFNN. Then, the network structure is adjusted by the developed self-adjusting structure mechanism. This mechanism can merge or divide the hidden neurons according to the distance of the clusters to achieve the adaptability of the RBFNN. Finally, the connection weights are determined by the gradient-based algorithm. The convergence of the SAS-RBFNN is analyzed by the Lyapunov criterion. A simulation for a benchmark problem shows the effectiveness of the proposed network. The SAS-RBFNN is then applied to predict the outlet ferrous ion concentration in the goethite process. The results demonstrate that this network can provide a more accurate prediction than the mathematical model, even under the fluctuating production condition. • A self-adjusting structure RBF neural network (SAS-RBFNN) is developed. • The network is initialized by the proposed supervised cluster algorithm. • The network structure is adjusted by the proposed self-adjusting structure mechanism. • The convergence of the SAS-RBFNN is analyzed by Lyapunov criterion. [ABSTRACT FROM AUTHOR]

Distributed anode current (DAC) is a high-dimensional spatial-distributed signal that can be measured online in the industrial aluminum electrolysis process. The difference of physicochemical properties in different spatial regions in an aluminum electrolysis cell can be obtained by spatial clustering analysis of DAC data. In this study, a dynamic spatial distributed information clustering method (DSDIC) for aluminum electrolysis cell is proposed. This method can effectively capture the complex dynamic spatio-temporal correlations in DAC. Firstly, the dynamic graph is identified to capture the complex dynamicity of the DAC. Then, the anode-spatial structure information (ASSI) extends the one-dimensional current signal generated by each carbon anode into a feature matrix to achieve the fusion of data and spatial structure knowledge. Finally, the adjacency matrix of dynamic graph performs low-pass filtering on the feature matrix to obtain low-frequency information that is beneficial to downstream learning tasks. Meanwhile, a fixed graph structure based on process mechanism knowledge is designed to capture the spatial correlation caused by external periodic operations in industrial process. The experimental results on the actual industrial aluminum electrolysis datasets show that our method improves the clustering accuracy by 3.96% compared with existing clustering methods. • A dynamic spatial distributed information clustering method is proposed. • A novel fixed graph structure based on process mechanism knowledge is proposed. • A method using adaptive dynamic graph to capture the dynamic spatial correlation is proposed. • A learning mode combining dynamic graph and static graph is proposed. [ABSTRACT FROM AUTHOR]