Search

Edge preserving filter is the basis of many computational photography and image processing. This can be achieved by global optimization method or local filtering method. Generally, the filtering results of global optimization methods are better than that of local filtering methods, and local filtering methods usually run much faster than global optimization methods. In this paper, a globally optimized method called iterative self-guided image filter (isGIF) is extended based on the assumptions of the guided image filter (GIF), which can produce high-quality edge-preserving filtering results by using the input image itself as the guidance image. Some comparisons with other edge-aware filters are presented to show the advantages of our method. Extensive experiments demonstrate that our filter generates images with better visual quality, while reducing/avoiding halo artifacts in the final image, and the running time is competitive.

Improving the robustness of the soft sensor model of industrial processes is an important yet challenging problem for a large amount of noise interference and missing data in practical industrial data. In this article, an adversarial training-based deep supervised variational autoencoder (Adv-DSVAE) is proposed to enhance the performance of industrial soft sensor models. Specifically, a supervised variational autoencoder (SVAE) is first designed to extract the quality-relevant feature representation. Then, a deep SVAE (DSVAE) model is constructed by stacking the hidden features extracted by SVAE, such that a high-level output-related feature representation can be captured. In this way, the missing data situation can be handled by the probabilistic latent feature representation extracted in DSVAE. To improve the robustness of a DSVAE-based soft sensor model, an adversarial training method is designed, in which adversarial examples are generated by adding perturbations to the last hidden feature of DSVAE, such that the model can perform well on both clean and perturbed feature representations. We further provide theoretical convergence analysis for the proposed Adv-DSVAE to guarantee its successful practical application. The ablation studies confirm that industrial quality prediction using the adversarial training strategy can ensure better robustness. Case studies on both the debutanizer column process and the real-world aluminum electrolysis process validate the superiority of Adv-DSVAE.

Industrial predictive modeling plays an important role in process control and optimization. Industrial process data arisen in the real-world applications often involves nonlinear and temporal characters, which are two main challenges for accurate industrial predictive modeling. While the previous transformer-based industrial predictive models only considered the temporal information of the industrial time-series data, however, the different importance of the process variables is generally ignored. In this article, we propose a novel dual cross-attention-based transformer (DCAFormer) to capture both the cross-time dependencies and the cross-variable dependencies in parallel for better predictability. Specifically, the proposed DCAFormer is composed of a cross-time self-attention layer and a cross-variable self-attention layer. The cross-variable self-attention is developed to capture multivariate correlations by inverting the input time series into variate tokens. The destationary cross-time self-attention is employed to extract the intrinsic nonstationary information into the temporal dependencies from the time-series data. The comparative as well as the ablation experiments are conducted on the real-world aluminum electrolysis process. The experimental results show that DCAFormer achieves better prediction performance than other competitive transformer models.

Accurate identification of multimodal Superheat Degree (SD) plays a critical decision-making role in Aluminum Electrolysis Process (AEP). Because the labeled SD data are scarce and annotation is expensive in real-world AEP, it is a challenge to develop a well-behaved SD identification model. In this paper, a Contrastive Anchors-based Label Propagation (CALP) algorithm is proposed to construct a Deep Semi-Supervised Learning (DSSL) model, called CALP-DSSL, for better identifying SD by utilizing large-scale unlabeled data and limited labeled data. Specifically, to improve the reliability of affinity graph and its affinity matrix, positive anchors and negative anchors are generated by estimating the uncertainty of label predictions, which can guide the correct direction of inferring pseudo-labels. For tackling the unsupervised domain adaptation problems existing in AEP, we propose a Variational Information Domain Adaptation (VIDA) module using the pseudo-labels generated by CALP to fine-tune the deep Variational Information Bottleneck (VIB) network. Finally, the overall CALP-DSSL model is trained by the Mini-Batch Incremental Learning (MBIL) technique in local level. It matches the nearest neighbors based on batch embedded features, which provides more distinct information flow during subsequent label propagation to construct the affinity graph. Benchmark datasets verify the superiority of CALP algorithm. Case study on a real-world AEP shows that CALPDSSL model improves the accuracy of SD identification over other state-of-art DSSL methods. Our source code is available at https://github.com/wjiecsu/CALP-DSSL. Note to Practitioners—The focus of this paper is to develop a well-behaved SD identification model based on the improved deep semi-Supervised learning (CALP-DSSL) model. In this model, a Contrastive Anchors based-Label Propagation (CALP) algorithm is used to predict pseudo-labels to construct DSSL model for improving the reliability of the generated pseudolabels. In this way, a Variational Information Domain Adaption (VIDA) module is constructed to solve the domain shift problems existed in the unstable working conditions. Moreover, the overall model is trained by Mini-Batch Incremental Learning (MBIL) strategy to build better underlying representation for supporting effective label propagation.

Concentrate grade and recovery are key production indexes (KPIs) for industrial flotation process. To establish the soft sensor model of the concentrate grade and recovery, a lot of froth image features are extracted as the input variables. However, these image features contain some redundant and irrelevant features. To improve the efficiency without degrading the performance of the soft sensor model, a sensitive feature selection (FS) method is proposed in this article. Sensitivity coefficient is defined to weigh the attribute significance of features to label, which is calculated by gray correlation analysis. Then, the criterion of sensitive FS based on minimal-redundancy-maximal-relevance (mRMR) is proposed. To solve the FS problem, a multiswarm particle swarm optimization (PSO) with collaborative search PSO (CS-PSO) is developed. Information exchange mechanism among three particle swarms in CS is proposed to improve the search effect and search accuracy. Self-adjusting structure RBFNN (SA-RBFNN) is employed to establish the soft sensor model to predict the concentrate grade based on the selected froth image features. The effectiveness of the proposed method is validated by the industrial flotation process data by comparing with other methods.

Numerous studies on learning algorithms have been done in the neural networks community, however concerning to training strategy is limited. In this article, to enhance the performance of fuzzy neural network (FNN) in industrial process identification, an FNN based on two-stage training (TSTFNN) is proposed. First, to initialize TSTFNN, we propose a supervised clustering method. It determines the initial centers and number of neurons for TSTFNN through clustering part of samples based on their labels. Then, the gradient-based algorithm is employed to further learning the parameters of TSTFNN. To improve its generalization performance, we developed a two-stage training scheme. In the first stage, a standard 10-fold cross-validation is executed to learn parameters. The samples whose prediction errors exceed a preset threshold are utilized to train the network in the second stage. According to Lyapunov criterion, we show the convergence of TSTFNN if the learning rate is selected in an appropriate range. The effectiveness of TSTFNN is validated by simulations on two benchmark problems. The proposed TSTFNN performs better and outperforms the state-of-the-art. Compared with supervised long short-term memory, root mean square error is decreased by 17%. Then, we apply it to the industrial rougher flotation process for soft sensor modeling. The experimental results show that TSTFNN achieves a satisfactory prediction performance.

Deep learning models are increasingly being used as effective techniques for industrial process modeling. However, decisions generated from deep learning models can hardly to interpret and cannot provide convinced results to users. To break the traditional tradeoff between accuracy and interpretability of deep neural network for industrial process modeling, we propose a deep probabilistic network-based knowledge-guided framework, which injects external knowledge into the deep neural network to guide its training process. In this framework, a deep probabilistic regression model (DPRM) is first developed to learn Gaussian latent feature representation yet establish regression relationship. Then, the external knowledge represented by fuzzy rules, which can evaluate the fitness of current network output and characterize constraints of the process, is encoded into a same structured Gaussian latent feature representation. We propose to inject the feature representation of external knowledge into DPRM using Kullback–Leibler divergence between two Gaussian distributions. The proposed knowledge-guided framework is evaluated on the Tennessee Eastman Process and the real-world aluminum electrolysis process. Experimental results highlight that our proposed approach achieves better prediction performance than the compared methods, also interprets the results.

The purpose of texture smoothing is to preserve the prominent structure in the image while smoothing the salient texture. However, the existing methods are difficult to achieve a satisfactory balance between filtering out salient textures and preserving weak edge structures and small structures. To this end, we propose a structure-preserving texture smoothing method via scale-aware bilateral total variation. First, the joint bilateral filter is introduced to construct the window bilateral variation, and combined with the window total variation, a regularizer called the bilateral total variation is formed, which accurately quantifies the characteristics of texture and structure, to finely smooth salient textures while preserving weak edge structures and small structures. Subsequently, we proposed a scale-aware scheme to make the proposed regularizer more powerful in preserving small structures and adopted an optimization scheme to convert the original non-convex optimization problem into a least squares regression problem. The effectiveness of the proposed regularizer is verified in the dataset. The experimental results demonstrate the superiority of the proposed method in texture smoothing and other applications compared to other state-of-the-art approaches.

Soft sensors have been widely applied to predict key variables that are difficult to measure for industrial process modeling. In this paper, a novel randomized interval type-2 fuzzy neural network with parallel learning, called IT2F-PSCN, is presented for soft sensor modeling of industrial processes. It trains the upper and lower bounds of the interval type-2 fuzzy logic system separately to facilitate type reduction, thereby integrating the fuzzy logic system with stochastic configuration networks. To achieve the appropriate structure and parameters of the model, we develop a two-phase training scheme. In the first phase, a sparse rule interpolation method with stochastic configuration is applied to generate new fuzzy rules. In the second phase, the hidden layer is constructed through parallel stochastic configuration to enhance the nonlinear representational capacity. The validity of IT2F-PSCN is confirmed by a series of experiments, including four benchmark data modelings, simulation on the Tennessee Eastman process, and soft sensor modeling for the slurry grade of the first rougher in a zinc flotation process. The experimental results indicate that the proposed IT2F-PSCN performs favorably compared with other methods. [ABSTRACT FROM AUTHOR]

As a population-based stochastic optimization algorithm, Gravitational Search Algorithm (GSA) has attracted numerous interests and has been applied in various applications. However, GSA has drawbacks such as uneven search and premature convergence in practical applications. This paper specifically explains the inherent characteristic of GSA in prioritizing the center position. Correspondingly, an improvement strategy of fitness normalization with mass shift is proposed, creating a situation where gravity and repulsion are mixed. Then, the global best mechanism with weights is incorporated into the particle's velocity update formula, which compensates for the difficulties in the later exploitation stage. Finally, an empirical formula for the initial gravitational constant related to the size of the solution space is proposed, which enhances the global search ability together with the former strategy. 12 shifted benchmark functions are used to construct 20 optimization problems ranging from 2 to 120 dimensions. The average performance of the proposed algorithm, other GSA and well-known algorithms are compared under the same budget. The results demonstrate that the proposed GSA not only effectively addresses the drawbacks of GSA and maintains good performance, but also exhibits strong competitiveness compared to various similar algorithms. [ABSTRACT FROM AUTHOR]

Due to the unknown system structure of the froth flotation process and frequent fluctuations in production conditions, design of control strategy is a challenging problem. As a result, manual operation is still widely applied in practice by observing froth image features. However, since the manual observation is subjective and the production conditions are time-varying, the manual operation cannot make decisions quickly and accurately. In this paper, a data-driven-based adaptive fuzzy neural network control strategy is developed to implement the automatic control of the antimony flotation process. The strategy is composed of fuzzy neural network (FNN) controllers, a data-driven model, and an on-line adaptive algorithm. The FNN is constructed to derive the control laws of the reagent dosages. The parameters of the FNN controllers are tuned by gradient descent algorithm. To obtain the real-time error feedback information, the data-driven model is established, which integrates the long short term memory (LSTM) network and radial basis function neural network (RBFNN). The LSTM network is utilized as a primary model, and the RBFNN is used as an error compensation model. To handle the challenges of the frequent fluctuations in the production conditions, the on-line adaptive algorithm is proposed to tune the parameters of the FNN controllers. Simulations and experiments are carried out in a real-world antimony flotation plant in China. The results demonstrate that the proposed adaptive fuzzy neural network control strategy produces better control performance than the other two existing methods. [ABSTRACT FROM AUTHOR]