Data-Driven Robust M-LS-SVR-Based NARX Modeling for Estimation and Control of Molten Iron Quality Indices in Blast Furnace Ironmaking

A Survey of Data-Driven Soft Sensing in Ironmaking System: Research Status and Opportunities

Data-driven soft sensing modeling is becoming a powerful tool in the ironmaking process due to the rapid development of machine learning and data mining. Although various soft sensing techniques have been successfully used in both the sintering process and blast furnace, they have not been comprehensively reviewed. In this work, we provide an overview of recent advances on soft sensing in the ironmaking process, with a special focus on data-driven techniques. First, we present a general soft sensing development framework of the ironmaking process based on the mechanism analysis and process characteristics. Second, we provide a detailed taxonomy of current soft sensing methods categorized by their predictive tasks (i.e., quality indicators prediction, state parameters prediction, etc.). Finally, we outline several insightful and promising directions, such as self-supervised learning and digital twins in the ironmaking process, for future research.

Fault Detection of Urban Wastewater Treatment Process Based on Combination of Deep Information and Transformer Network

As one of the hot issues of concerns during modern social development, the wastewater treatment process is acknowledged to be a process with complex biochemical reactions and susceptible to an external environment, featuring strong nonlinear and time correlation characteristics, which are difficult for traditional mechanism-based models to tackle. For many classical data-driven fault detection methods, a complete retraining process is necessary to monitor every new fault, and most of the current neural network-based strategies rarely achieve satisfactory monitoring accuracy or robustness either. Giving full consideration to the aforementioned problems, this article takes advantage of position encoding, residual connection, and multihead attention mechanism embedded in the Transformer structure to establish an effective and efficient wastewater treatment process fault detection model, where offline modeling and online monitoring are performed successively to achieve accurate detection of the faults. In the experimental part, the advantages of the proposed method are strongly verified through the simulation monitoring of 27 faults on the benchmark simulation model 1 (BSM1), where the false alarm rate (FAR) and miss alarm rate (MAR) of the established method are proved to be significantly lower than those of the compared state-of-the-art methods.

Transfer Dynamic Latent Variable Modeling for Quality Prediction of Multimode Processes

Quality prediction is beneficial to intelligent inspection, advanced process control, operation optimization, and product quality improvements of complex industrial processes. Most of the existing work obeys the assumption that training samples and testing samples follow similar data distributions. The assumption is, however, not true for practical multimode processes with dynamics. In practice, traditional approaches mostly establish a prediction model using the samples from the principal operating mode (POM) with abundant samples. The model is inapplicable to other modes with a few samples. In view of this, this article will propose a novel dynamic latent variable (DLV)-based transfer learning approach, called transfer DLV regression (TDLVR), for quality prediction of multimode processes with dynamics. The proposed TDLVR can not only derive the dynamics between process variables and quality variables in the POM but also extract the co-dynamic variations among process variables between the POM and the new mode. This can effectively overcome data marginal distribution discrepancy and enrich the information of the new mode. To make full use of the available labeled samples from the new mode, an error compensation mechanism is incorporated into the established TDLVR, termed compensated TDLVR (CTDLVR), to adapt to the conditional distribution discrepancy. Empirical studies show the efficacy of the proposed TDLVR and CTDLVR methods in several case studies, including numerical simulation examples and two real-industrial process examples.

Multigranularity Surrogate Modeling for Evolutionary Multiobjective Optimization With Expensive Constraints

Multiobjective optimization problems (MOPs) with expensive constraints pose stiff challenges to existing surrogate-assisted evolutionary algorithms (SAEAs) in a very limited computational cost, due to the fact that the number of expensive constraints for an MOP is often large. For existing SAEAs, they always approximate constraint functions in a single granularity, namely, approximating the constraint violation (CV, coarse-grained) or each constraint (fine-grained). However, the landscape of CV is often too complex to be accurately approximated by a surrogate model. Although the modeling of each constraint function may be simpler than that of CV, approximating all the constraint functions independently may result in tremendous cumulative errors and high computational costs. To address this issue, in this article, we develop a multigranularity surrogate modeling framework for evolutionary algorithms (EAs), where the approximation granularity of constraint surrogates is adaptively determined by the position of the population in the fitness landscape. Moreover, a dedicated model management strategy is also developed to reduce the impact resulting from the errors introduced by constraint surrogates and prevent the population from trapping into local optima. To evaluate the performance of the proposed framework, an implementation called K-MGSAEA is proposed, and the experimental results on a large number of test problems show that the proposed framework is superior to seven state-of-the-art competitors.

A Deep Probabilistic Transfer Learning Framework for Soft Sensor Modeling With Missing Data

Soft sensors have been extensively developed and applied in the process industry. One of the main challenges of the data-driven soft sensors is the lack of labeled data and the need to absorb the knowledge from a related source operating condition to enhance the soft sensing performance on the target application. This article introduces deep transfer learning to soft sensor modeling and proposes a deep probabilistic transfer regression (DPTR) framework. In DPTR, a deep generative regression model is first developed to learn Gaussian latent feature representations and model the regression relationship under the stochastic gradient variational Bayes framework. Then, a probabilistic latent space transfer strategy is designed to reduce the discrepancy between the source and target latent features such that the knowledge from the source data can be explored and transferred to enhance the target soft sensor performance. Besides, considering the missing values in the process data in the target operating condition, the DPTR is further extended to handle the missing data problem utilizing the strong generation and reconstruction capability of the deep generative model. The effectiveness of the proposed method is validated through an industrial multiphase flow process.

Variational Progressive-Transfer Network for Soft Sensing of Multirate Industrial Processes

Deep-learning-based soft sensors have been extensively developed for predicting key quality or performance variables in industrial processes. However, most approaches assume that data are uniformly sampled while the multiple variables are often acquired at different rates in practical processes. This article designed a progressive transfer strategy, based on which a variational progressive-transfer network (VPTN) method is proposed for the soft sensor development of industrial multirate processes. In VPTN, the multirate data are first separated into multiple data chunks where the variables within each chunk are acquired at a uniform rate. Then, a variational multichunk data modeling framework is developed to model the multiple chunks in a unified fashion through deep variational structures. The base models, including the unsupervised ones with only partial process variables and the supervised soft sensor model share a similar network structure, such that the subsequent transfer strategy can be readily implemented. Finally, a progressive transfer learning strategy is designed to transfer the model parameters from the fastest sampled data chunk to the slowest one in a progressive manner. Thus, the knowledge from various data chunks can be sequentially explored and transferred to enhance the performance of the terminal soft sensor model. Case studies on both a debutanizer column dataset and a real coal mill dataset in a thermal power plant validate the performance of the proposed method.

Dual ensemble online modeling for dynamic estimation of hot metal silicon content in blast furnace system

Hot metal silicon content (HMSC) is usually utilized to measure the quality of hot metal and reflect the thermal status of blast furnace (BF) system. However, most state-of-the-arts ignore the time-varying behavior of BF ironmaking process, which are impractical. Accordingly, a novel dual ensemble online sequential extreme learning machine (DE-OS-ELM) is proposed to establish the online estimation model of HMSC, which can update the data-driven model with the latest operation data. Specifically, an online learning method with recursive modification is first proposed based on OS-ELM (referred to as RM-OS-ELM) to address the modeling with uncertainty. To heel, a dynamic forgetting factor is presented for the dynamic tracking capability enhancement and convergence acceleration. Furthermore, a final updating rule for sequential implementation is constructed by combining the output weights of OS-ELM and RM-OS-ELM based on their corresponding contributions on modeling. Considering the modeling accuracy and curve trend consistency, multiobjective parameter optimization model is also implemented to achieve the satisfactory performance. By taking the proposed DE-OS-ELM, the estimation model of HMSC is established using industrial data. Comprehensive experiments demonstrate that DE-OS-ELM-based HMSC estimation model is more feasible and practical.

A Multiobjective Evolutionary Nonlinear Ensemble Learning With Evolutionary Feature Selection for Silicon Prediction in Blast Furnace

In the blast furnace ironmaking process, accurate prediction of silicon content in molten iron is of great significance for maintaining stable furnace conditions, improving hot metal quality, and reducing energy consumption. However, most of the current research works employ linear correlation coefficient methods to select input features in modeling, which may not fully take the nonlinear and coupling relationships between features into account. Therefore, this article considers the input feature selection issue of silicon content prediction model from a new perspective and proposes a multiobjective evolutionary nonlinear ensemble learning model with evolutionary feature selection mechanism (MOENE-EFS), in which extreme learning machine is adopted as the base learner. MOENE-EFS takes the input feature scheme of each base learner as well as their network structure and parameters as decision variables and proposes a modified nondominated sorting differential evolution algorithm to optimize two conflicting objectives, i.e., accuracy and diversity of base learners, simultaneously. Through the optimization, a set of Pareto optimal base learners with high accuracy and strong diversity can be obtained. Moreover, different from the linear ensemble methods commonly used in classical evolutionary ensemble learning, this article proposes a nonlinear ensemble method to combine the obtained base learners based on differential evolution. Experimental results indicate that the two proposed strategies, i.e., evolutionary feature selection and nonlinear ensemble, are very effective in improving the accuracy and stability of the prediction model. MOENE-EFS also outperforms the other prediction models in both benchmark data and practical industrial data. Furthermore, analysis on the input features of all Pareto optimal base learners shows that the evolutionary feature selection is capable of selecting essential features and is consistent with human experience, which indicates it is a promising method to deal with the input feature selection issue in silicon content prediction.

Dynamically Generated Hierarchical Neural Networks Designed With the Aid of Multiple Support Vector Regressors and PNN Architecture With Probabilistic Selection

The two issues on dynamically generated hierarchical neural networks such as the sort of basic neurons and how to compose a layer are considered in this article. On the first issue, a variant version of the least-square support vector regression (SVR) is chosen as a basic neuron. Support vector machine (SVM) is a representative classifier which usually shows good classification performance. Along with the SVMs, SVR was introduced to deal with the regression problem. Especially, least-square SVR has the advantages of high learning speed due to the substitution of the inequality constraints by the equality constraint in the formulation of the optimization problem. Based on the least-square SVR, the multiple least-square (MLS) SVR, which is a type of a linear combination of least-square SVRs with fuzzy clustering, is proposed to improve the modeling performance. In addition, a hierarchical neural network, where the MLS SVR is utilized as the generic node instead of the conventional polynomial, is developed. The key issues of hierarchical neural networks, which are generated dynamically layer by layer, are discussed on how to retain the diversity of the nodes located at the same layer according to the increase of the layer. In order to maintain the diversity of the nodes, various selection methods such as truncation selection and roulette wheel selection (RWS) to choose the nodes among candidate nodes are proposed. In addition, in order to reduce the computational overhead to determine all candidates which exhibit all compositions of the input variables, a new implementation method is proposed. From the viewpoint of the diversity of the selected nodes and the computational aspects, it is shown that the proposed method is preferred over the conventional design methodology.

Dual Attention-Based Encoder-Decoder: A Customized Sequence-to-Sequence Learning for Soft Sensor Development

Soft sensor techniques have been applied to predict the hard-to-measure quality variables based on the easy-to-measure process variables in industry scenarios. Since the products are usually produced with prearranged processing orders, the sequential dependence among different variables can be important for the process modeling. To use this property, a dual attention-based encoder-decoder is developed in this article, which presents a customized sequence-to-sequence learning for soft sensor. We reveal that different quality variables in the same process are sequentially dependent on each other and the process variables are natural time sequences. Hence, the encoder-decoder is constructed to explicitly exploit the sequential information of both the input, that is, the process variables, and the output, that is, the quality variables. The encoder and decoder modules are specified as the long short-term memory network. In addition, since different process variables and time points impose different effects on the quality variables, a dual attention mechanism is embedded into the encoder-decoder to concurrently search the quality-related process variables and time points for a fine-grained quality prediction. Comprehensive experiments are performed based on a real cigarette production process and a benchmark multiphase flow process, which illustrate the effectiveness of the proposed encoder-decoder and its sequence to sequence learning for soft sensor.

Temperature Prediction of Heating Furnace Based on Deep Transfer Learning

Heating temperature is very important in the process of billet production, and it directly affects the quality of billet. However, there is no direct method to measure billet temperature, so we need to accurately predict the temperature of each heating zone in the furnace in order to approximate the billet temperature. Due to the complexity of the heating process, it is difficult to accurately predict the temperature of each heating zone and each heating zone sensor datum to establish a model, which will increase the cost of calculation. To solve these two problems, a two-layer transfer learning framework based on a temporal convolution network (TL-TCN) is proposed for the first time, which transfers the knowledge learned from the source heating zone to the target heating zone. In the first layer, the TCN model is built for the source domain data, and the self-transfer learning method is used to optimize the TCN model to obtain the basic model, which improves the prediction accuracy of the source domain. In the second layer, we propose two frameworks: one is to generate the target model directly by using fine-tuning, and the other is to generate the target model by using generative adversarial networks (GAN) for domain adaption. Case studies demonstrated that the proposed TL-TCN framework achieves state-of-the-art prediction results on each dataset, and the prediction errors are significantly reduced. Consistent results applied to each dataset indicate that this framework is the most advanced method to solve the above problem under the condition of limited samples.

A Novel Equivalent Model of Active Distribution Networks Based on LSTM

Dynamic behaviors of distribution networks are of great importance for the power system analysis. Nowadays, due to the integration of the renewable energy generation, energy storage, plug-in electric vehicles, and distribution networks turn from passive systems to active ones. Hence, the dynamic behaviors of active distribution networks (ADNs) are much more complex than the traditional ones. The research interests how to establish an accurate model of ADNs in modern power systems are drawing a great deal of attention. In this paper, motivated by the similarities between power system differential algebraic equations and the forward calculation flows of recurrent neural networks (RNNs), a long short-term memory (LSTM) RNN-based equivalent model is proposed to accurately represent the ADNs. First, the adoption reasons of the proposed LSTM RNN-based equivalent model are explained, and its advantages are analyzed from the mathematical point of view. Then, the accuracy and generalization performance of the proposed model is evaluated using the IEEE 39-Bus New England system integrated with ADNs in the study cases. It reveals that the proposed LSTM RNN-based equivalent model has a generalization capability to capture the dynamic behaviors of ADNs with high accuracy.

A fast and accurate piezoelectric actuator modeling method based on truncated least squares support vector regression

In order to improve the applicability of piezoelectric actuators (PEAs) in precision positioning, least squares support vector regression (LS-SVR) is applied to model hysteresis in PEAs due to its high modeling accuracy and fast convergence speed. However, low robustness of LS-SVR makes modeling accuracy susceptible to noises, which makes LS-SVR hysteresis models difficult to be applied in engineering environment. In this article, a robust truncated least squares support vector regression (T-LSSVR) is proposed. With the truncation strategy, redundancy in the training set is reduced and robustness is improved. Parameters required for T-LSSVR are optimized by particle swarm optimization and cross optimization algorithms. To test the proposed approach, it is applied to predict the hysteresis of PEAs. Results show that the proposed method is more accurate and robust than other versions of LS-SVR when the training set is polluted by noises, and meanwhile reduces the sample size and increases computational efficiency.

Temperature Measurement Method for Blast Furnace Molten Iron Based on Infrared Thermography and Temperature Reduction Model

The temperature measurement of blast furnace (BF) molten iron is a mandatory requirement in the ironmaking process, and the molten iron temperature is significant in estimating the molten iron quality and control blast furnace condition. However, it is not easy to realize real-time measurement of molten iron temperature because of the harsh environment in the blast furnace casthouse and the high-temperature characteristics of molten iron. To achieve continuous detection of the molten iron temperature of the blast furnace, this paper proposes a temperature measurement method based on infrared thermography and a temperature reduction model. Firstly, an infrared thermal imager is applied to capture the infrared thermal image of the molten iron flow after the skimmer. Then, based on the temperature distribution of the molten iron flow region, a temperature mapping model is established to measure the molten iron temperature after the skimmer. Finally, a temperature reduction model is developed to describe the relationship between the molten iron temperature at the taphole and skimmer, and the molten iron temperature at the taphole is calculated according to the temperature reduction model and the molten iron temperature after the skimmer. Industrial experiment results illustrate that the proposed method can achieve simultaneous measurement of molten iron temperature at the skimmer and taphole and provide reliable temperature data for regulating the blast furnace.