Source-free domain adaptation (SFDA) enables knowledge transfer without source data, addressing privacy constraints of the transfer learning. However, existing methods often depend on fixed confidence thresholds for pseudolabeling, which are poorly adaptable and lead to unstable performance. Moreover, class distribution mismatch is frequently ignored, further hindering adaptation. To tackle these challenges, incremental contrastive learning with dual distilling for SFDA is proposed and applied in industrial process fault diagnosis in this article. A threshold-free pseudolabeling strategy is first introduced to dynamically assess label reliability. Then, a stage-wise incremental contrastive learning framework progressively expands from per-class Top-K samples to the full target set, effectively mitigating class imbalance. In addition, a dual distilling mechanism at both feature and label levels is employed to alleviate model drift caused by forgetting source knowledge. Finally, extensive experiments on three-phase flow and wastewater treatment datasets demonstrate the effectiveness of the proposed method.

With the increase of wastewater treatment volume and the insufficiency of preventive maintenance measures, the potential safety hazards of wastewater treatment process (WWTP) are gradually emerging. The unplanned sensor failures may result in false information feedback and reduce the reliability of the control system. This paper attempts to formulate a working mode substitution-based performance self-recovery control (WMS-based PSRC) strategy for the WWTP against sensor failures. Therein, a substitution indication-based switching function scheme is developed to automatically activate different sensor working modes. The transient and steady-state process regulation performance after one working mode substitution are guaranteed by establishing the prescribed-time performance function and error transformation dynamics. Then, an adaptive performance self-recovery control is developed to ensure the desired regulation level of the WWTP. Extensive studies on a recognized WWTP platform illustrate that the proposed control scheme can guarantee the working mode substitution and desired regulation performance while mitigating the failure detriment.Note to Practitioners—The vulnerability of industrial control systems in terms of policy, architecture and platform, as well as the hysteresis and subjectivity of manual operations on sensor maintenance, will result in unstable process performance, loss of critical control data, unnecessary workload and economic losses. In this paper, a WMS-based PSRC is presented for the WWTP with sensor failures. Three main aspects are contained: mode substitution, performance guarantee and WMS-based PSRC structure. The total sensor working modes are divided, meanwhile the switching function index is updated or maintained based on the mode substitution indication. After reconstructing performance function, the guaranteed performance technology is developed and applied to improve response rate and regulation accuracy. Then, a WMS-based PSRC structure is designed to comprehensively analyse the monitoring and control process. Finally, the industrial application results of WWTP demonstrate that the WMS-based PSRC can optimize process operation. This strategy is, therefore, useful for practitioners to achieve the fast performance self-recovery after the abnormal conditions.

Considering the complexity of centralized plant-wide optimization and the presence of communication delay in production units, a distributed asynchronous optimization framework is developed for energy consumption optimization problem during ethylene production. First, the energy consumption optimization problem of ethylene process is formulated into a distributed asynchronous optimization problem. Then, considering multiple production units and the material transfer time involved, each unit is treated as a node, and each node is decomposed into calculation nodes, constraint nodes, and delay nodes. Specifically, each production unit can be optimized asynchronously without the necessity for synchronization. To overcome the impact of communication delay on asynchronous process, state vectors are incorporated into the distributed parameter projection algorithm. Additionally, to ensure that the inseparable coupled constraints between nodes during asynchronous operations are met, the parameter projection algorithm is employed. Numerical experiments and industrial simulations demonstrate the proposed algorithm exhibits faster convergence speeds compared to distributed synchronous algorithms, and the energy consumption is lower than the results obtained by the centralized algorithm. Note to Practitioners—As the scale of ethylene production expands, traditional centralized optimization methods struggle to meet the demands of plant-wide optimization due to their high model complexity and slow convergence rates. In this study, we develop a distributed optimization framework, in which the large-scale complex model is decomposed into small parts, and the global optimization task is accomplished cooperatively through local information exchange. Furthermore, considering the time delay due to material residence time in processing units, a distributed asynchronous parameter projection algorithm is proposed to solve the energy consumption issue in ethylene plant. Experimental results demonstrate that the proposed method is capable of converging to the feasible solution in the presence of time delay. Compared with the existing centralized methods, the proposed asynchronous distributed algorithm exhibits better performance, i.e. lower energy consumption. Besides, the proposed asynchronous distributed optimization framework holds potential for application in other process industries, such as the metallurgical industry and steel production process.

Energy trading in industrial parks has great potential for reducing carbon emissions and lowering energy bills. This article proposes a safe multiagent deep reinforcement learning algorithm for optimizing the energy trading strategy in industrial parks to achieve less reliance on the main grid and save energy costs. Specifically, an industrial park that contains multiple industrial users with both thermal and electrical load requirements is considered, in which the different users can trade energy with each other and with the main grid based on their own strategies. Unlike the existing studies, the time-phased energy trading problem is transformed into a constrained partially observable Markov game, which models the industrial users and objectives of the buyers and sellers. Finally, a novel multiagent primal-dual proximal policy optimization algorithm that guarantees safety is developed to achieve the optimal trading strategies between the main grid and multiple users. Numerical simulations with real-world data demonstrate that the proposed algorithm allows higher total revenue for sellers and lower total costs for buyers in the park, limits each user's bid or offer to a relatively safe range, and increases the amount of electricity traded locally, while reducing trading with the grid.

Near-infrared analysis has demonstrated superiority in constructing calibration models for evaluating gasoline properties during blending. However, the intricacies of sampling and the time-intensive analysis process frequently pose challenges in obtaining sufficient labeled samples, thereby hindering the establishment of calibration model with the satisfactory performance. Generative adversarial networks (GANs) bridge this gap by generating virtual samples. Nevertheless, existing methods neglect the global distribution of samples and lack explicit mechanisms for generating properties. To expand labeled sample sets sufficiently for constructing precise and reliable calibration models, a regression Wasserstein deep convolutional generative adversarial network with divergence (RWDCGAN-div) is proposed. Wasserstein divergence is designed in the RWDCGAN-div framework to broaden the global spatial distribution of labeled samples and consistent convolutional neural networks are utilized to simplify model construction. Regression models are integrated to facilitate the discriminator learn the relationship between spectra and properties, thereby guiding the generator in producing spectra and corresponding properties with explicit mechanisms. The effectiveness of the proposed method is verified through prediction experiments based on gasoline blending process.

This study focuses on building an intelligent decision-making attention mechanism in which the channel relationship and conduct feature maps among specific deep Dense ConvNet blocks are connected to each other. Thus, develop a novel freezing network with a pyramid spatial channel attention mechanism (FPSC-Net) in deep modeling. This model studies how specific design choices in the large-scale data-driven optimization and creation process affect the balance between the accuracy and effectiveness of the designed deep intelligent model. To this end, this study presents a novel architecture unit, which is termed as the "Activate-and-Freeze" block on popular and highly competitive datasets. In order to extract informative features by fusing spatial and channel-wise information together within local receptive fields and boost the representation power, this study constructs a Dense-attention module (pyramid spatial channel (PSC) attention) to perform feature recalibration, and through the PSC attention to model the interdependence among convolution feature channels. We join the PSC attention module in the activating and back-freezing strategy to search for one of the most important parts of the network for extraction and optimization. Experiments on various large-scale datasets demonstrate that the proposed method can achieve substantially better performance for improving the ConvNets representation power than the other state-of-the-art deep models.

This article is concerned with the optimal fault detection issues for discrete-time nonlinear systems with the aid of Takagi–Sugeno fuzzy dynamic modeling technique. To this end, in the first part of this article, the nonlinear system is formulated in the time-varying fuzzy manner, and based on it, a unified fault detection approach is developed by solving a multiobjective optimization problem. In this sense, the optimal tradeoff between fault detectability and robustness against unknown inputs is ensured by solving the Riccati equation. Meanwhile, a fuzzy fault detection approach is studied in the second part of this article based on piecewise-fuzzy Lyapunov functions, which is realized by solving linear matrix inequalities. Two examples are given at the end of this article to demonstrate the proposed approaches.

The increasing utilization of wastewater necessitates dedicated attentions to the potential security threats, and formulate strategies for defense, response, and future protection. The nonideal actuator subject to the faults and constraints may underload the driving force and reduce the sewage purification efficiency. This article proposes an adaptive performance self-recovery control strategy for the wastewater treatment process (WWTP) with nonideal actuator. Therein, a Gaussian error function is reconstructed to imitate the asymmetrical actuator constraints. A fault effect identifier is designed to indirectly acquire fault information. Two boundary estimators are co-designed to estimate the infimum of virtual controller gain and the supremum of lumped uncertainty, respectively. The proposed control strategy can largely enhance the faulty performance self-recovery capability of the WWTP, while ensuring robust output regulation and fast convergence. Extensive experiments on dissolved oxygen control are executed on a WWTP platform to show the efficacy of the suggested control scheme.

This article focuses on fault detection for nonlinear industrial processes with multiple operating conditions, in which transfer learning is used to deal with the limited training data issue for unusual operating conditions. To this end, the Tucker decomposition is first implemented to deliver the Gaussian kernel of the nonlinear processes with multiple operation conditions. Then, transfer learning is carried out based on correlation analysis to achieve fault detection for the target process. It is noted that the traditional statistic will lead to false alarms due to the switching of the operating conditions. To deal with this issue, a stationary statistic is investigated based on co-integration analysis. Finally, by transferring the fault detection systems from multiple operating conditions to unusual operating conditions based on extended manifold regularization, fault detection for unusual operating condition can be achieved with both the traditional statistics and the stationary statistic. The experimental result demonstrates the efficiency of the proposed fault detection method for the wastewater treatment process.

As environmental pollution becomes increasingly serious and industrial energy consumption continuously rises, an intelligent and efficient industrial energy management policy is urgently needed to reduce costs and maximize the benefits of industrial energy systems. However, modern industrial energy systems are characterized by hybrid industrial equipment actions, diverse objectives, and highly intermittent and stochastically distributed renewable energy sources. Therefore, efficient operation and control are difficult. This article presents a novel, model-free energy management policy using a hybrid action deep reinforcement learning algorithm for energy scheduling of industrial equipments operating in various modes. Specifically, the interaction process between the industrial energy management center and each equipment is modeled as a Markov decision process that minimizes the daily operating cost of the energy system and maximizes the revenue of the production equipment. Then, a double parameterized deep Q-networks that does not require an explicit environmental model is developed to learn the hybrid action signals using actor and critic networks, in which the double Q value mechanism avoids value overestimation and improves the algorithm efficiency. In addition, the policy gradient of the proposed algorithm is derived and its convergence proof is discussed. Finally, numerical studies are conducted using real-world data to evaluate algorithm performance and verify its effectiveness.

Meter pointers exhibit stable and anti-interference capabilities, rendering them extensively utilized in industrial environments. However, automated reading poses a significant challenge due to the fact that current segmentation methods struggle to isolate the fine-grained pointers and scales for accurate reading calculations. This challenge can be alleviated by enhancing the feature extraction capability of the segmentation network. As is well-known that Attention plays an essential role in human vision by selectively focusing on convex parts, and attention-based methods have been applied to various computer vision tasks. Therefore, we propose a new image segmentation network called multipath attention network (MPANet) for pointer meter recognition in the complex industrial environments. The designed network employs an attention gate mechanism to proficiently capture local features stemming from various pathways during skip-connection and upsample processes. In addition, our network incorporates deep supervision by merging the outputs of the final three layers to extract abundant low-dimensional information. To further improve the performance of encoders and decoders, a residual U-block is employed, thereby forming an enhanced U-shaped network structure. In the experiments, we employ HD95, Dice, and Recall as evaluation metrics. MPANet demonstrates superior performance compared to state-of-the-art networks on three our self-collected datasets, showing improvements of over 1% across all metrics. In addition, we validate the efficacy of MPA as a plug-and-play module and the benefits of applying deep supervision to multidecoder network.

Data-driven methods for predicting quality variables in wastewater treatment processes (WWTPs) have mostly ignored the slow time-varying nature of WWTP, and they are data-consuming that need a large amount of independent and homogeneously distributed data, which makes it difficult to collect. To address this issue with few-shot and inconsistent distribution, a transfer learning method called transferable deep slow feature network (TDSFN) for time-series prediction is proposed by leveraging the knowledge of relevant datasets. TDSFN extracts nonlinear slow features of WWTP with inertia from the time series through a deep slow feature network and constructs the domain invariant features based on them. Target feature attention is designed in TDSFN to enhance the predictor adaptability to the target domain by assigning weights to the source features based on their similarity to target features. Furthermore, a variational Bayesian inference framework is introduced to learn the parameters of TDSFN. The effectiveness of TDSFN is verified through prediction experiments based on WWTP.

Forecasting NOx concentration in fluid catalytic cracking (FCC) regeneration flue gas can guide the real-time adjustment of treatment devices, and then furtherly prevent the excessive emission of pollutants. The process monitoring variables, which are usually high-dimensional time series, can provide valuable information for prediction. Although process features and cross-series correlations can be captured through feature extraction techniques, they are commonly linear transformation, and conducted or trained separately from forecasting model. This process is inefficient and might not be an optimal solution for the following forecasting modeling. Therefore, we propose a time series encoding temporal convolutional network (TSE-TCN). By parameterizing the hidden representation of the encoding–decoding structure with the temporal convolutional network (TCN), and combining the reconstruction error and the prediction error in the objective function, the encoding–decoding procedure and the temporal predicting procedure can be trained by a single optimizer. The effectiveness of the proposed method is verified through an industrial reaction and regeneration process of an FCC unit. Results demonstrate that TSE-TCN outperforms some state-of-art methods with lower root mean square error (RMSE) by 2.74% and higher${R}^{2}$score by 3.77%.

Cluster assignment of large and complex datasets is a crucial but challenging task in pattern recognition and computer vision. In this study, we explore the possibility of employing fuzzy clustering in a deep neural network framework. Thus, we present a novel evolutionary unsupervised learning representation model with iterative optimization. It implements the deep adaptive fuzzy clustering (DAFC) strategy that learns a convolutional neural network classifier from given only unlabeled data samples. DAFC consists of a deep feature quality-verifying model and a fuzzy clustering model, where deep feature representation learning loss function and embedded fuzzy clustering with the weighted adaptive entropy is implemented. We joint fuzzy clustering to the deep reconstruction model, in which fuzzy membership is utilized to represent a clear structure of deep cluster assignments and jointly optimize for the deep representation learning and clustering. Also, the joint model evaluates current clustering performance by inspecting whether the resampled data from estimated bottleneck space have consistent clustering properties to improve the deep clustering model progressively. Experiments on various datasets show that the proposed method obtains a substantially better performance for both reconstruction and clustering quality compared to the other state-of-the-art deep clustering methods, as demonstrated with the in-depth analysis in the extensive experiments.

This article proposes a variable-gain state observer-based sliding mode self-healing control (VSO-based SMSHC) method for a wastewater treatment process (WWTP) with changeable external disturbances and sensor failures. To reconstruct the disturbances and unmeasured system states, a novel VSO is developed, in which the VSO gains are adjusted by following an automatic variable-gain mechanism for adapting to the variation of external disturbances. An adaptive compensation coefficient of failure factor is designed to counteract the failure effects on observation and tracking performance. By utilizing the cubic absolute-value Lyapunov stability criterion, it is shown that system stability and tracking performance of WWTP are guaranteed. Experimental studies are carried out on a standardized platform of WWTP, and the results on dissolved oxygen and nitrate nitrogen regulation indicate that the proposed control strategy can ensure excellent control performance and reduce both failure and disturbance impacts.

Under closed-set scenarios (CSS), distributed modeling performs well in fault diagnosis of plant-wide industrial processes due to its flexibility and robustness. However, a more realistic scenario is often open, where unseen situations may arise unexpectedly, rendering existing methods infeasible. The advent of open-set recognition algorithms that can effectively distinguish known samples and reject unknown ones bridges this gap. Nevertheless, the poor scalability of these algorithms prevents them from being elegantly embedded in popular distributed modeling schemes, which hinders the implementation of plant-wide industrial process fault diagnosis toward open-set scenarios (OSS). In this work, we formulate a novel distributed fault diagnosis scheme toward OSS to solve this problem. First, a mutual information-based local module decomposition and expansion strategy is proposed to minimize the loss of intermodule relevant information. Second, a novel generalized basic probability assignments generation technique based on extreme value theory is developed for modeling unknown information. It enables any classifier capable of probabilistic prediction to be applied to OSS and easily embedded in distributed modeling schemes. Finally, a conflict management scheme combining supervised and unsupervised is devised to address the vulnerability of the modified generalized combination rule to counter-intuitive results from fusing conflicting evidence. Experimental results on two plant-wide industrial process datasets demonstrate the proposed approach's feasibility and superiority.

Plant-wide optimization plays a vital role in improving the overall performance of large-scale industrial processes. Considering the modeling complexity and convergence difficulty of centralized plant-wide optimization, in this article, we propose a distributed framework by decomposing the global optimization problem into a set of subproblems, where multiple local units interact with each other between nodes. According to the proposed framework, plant-wide optimization problem can be effectively solved by distributed optimization. To eliminate the limitations of existing distributed algorithms, we introduce constraint node to describe the inseparable coupled constraints between nodes. By combining Lagrange duality and parameter projection, the proposed algorithm can solve optimization problems with multiple constraints. Taking ethylene production process as an example, the global energy consumption optimization is guaranteed without the whole-process mechanism model. Numerical simulation and industrial experimental results demonstrate that the proposed algorithm can reduce the energy consumption of the entire ethylene process with fewer computation time.

In this article, optimal observer-based fault detection (FD) and estimation schemes for Takagi–Sugeno fuzzy systems with process faults are investigated. In particular, an optimal FD scheme for fuzzy systems is proposed first aiming at enhancing the sensitivity to the faults and simultaneously increasing robustness against unknown inputs, which gives the extension of the socalled unified solution to fuzzy systems. To further provide the fault information, a least squares fault estimation scheme is developed. It is noteworthy that, the observers for the proposed FD and estimation schemes are updated online recursively. A case study on the laboratory three-tank system is then given to demonstrate the proposed FD and estimation approaches.

Gaussian process regression (GPR) has shown superiority in terms of state estimation for its nonparametric characteristic and uncertainty prediction ability. Due to its heavy computational complexity, GPR is generally used for small datasets. To efficiently deal with the big data, the sparse spectrum approximation method has been successfully applied to GPR to decrease the computational complexity. However, the stationarity of this method is a strict assumption for data and usually mismatches the industrial processes. In this article, we proposed a sparse nonstationary GPR, which can deal with the nonstationary relationship among samples and make the model more flexible, to settle the aforementioned problems. Furthermore, the performance of the proposed method is evaluated using three public datasets and a sampled diesel engine dataset, and the results show the superiority of our proposed method in terms of accuracy.

In soft sensing, relationship variation of process variables and quality indicators may cause the model trained from the training datasets unsuitable for the prediction on the testing datasets. As the model-agnostic meta-learning can utilize the supporting datasets to strengthen the prediction performance of the query samples, it can maintain reliable prediction performance in relationship variation. However, the traditional model-agnostic meta-learning contains inconsistencies between the parameters evaluated in the training stage and those adapted in the predicting stage. The phenomenon is inferred as the dilemma of getting valuable evaluated parameters related to the initial parameters and accurate parameters representing the parameters adapted in the predicting stage. In this article, we propose the stage-related adaption block to use the model-agnostic meta-learning modularly. Finally, the model-agnostic meta-learning method based on the optimal alternative scaling value is proposed and verified in a numerical example and an industrial application.

This study focuses on the classification and pathological status monitoring of hyper/hypo-calcemia in the calcium regulatory system. By utilizing the Independent Component Analysis (ICA) mixture model, samples from healthy patients are collected, diagnosed, and subsequently classified according to their underlying behaviors, characteristics, and mechanisms. Then, a Just-in-Time Learning (JITL) has been employed in order to estimate the diseased status dynamically. In terms of JITL, for the purpose of the construction of an appropriate similarity index to identify relevant datasets, a novel similarity index based on the ICA mixture model is proposed in this paper to improve online model quality. The validity and effectiveness of the proposed approach have been demonstrated by applying it to the calcium regulatory system under various hypocalcemic and hypercalcemic diseased conditions.

An online monitoring method, which aims to deal with the high order non-Gaussian characteristics in chemical process, is proposed in this paper. In the framework of the proposed method, kernel based independent component analysis is utilized to identify the operation status of the chemical process and statistics pattern analysis is employed to combine with independent component analysis to extract high order information from the process so as to improve the monitoring performance. The modified statistics pattern analysis introduces the Mahalanobis distance into statistics pattern to analyze the inner structure relationship between the samples. Then, the validity and effectiveness of our proposed method is illustrated by applying to a representative non-Gaussian process, Continuous Stirred Tank Reactor (CSTR). The results show that the proposed method has its advantages when compared to other conventional Eigen-decomposition monitoring algorithms.

This paper examines the tracking property of nonlinear delayed multi-agent systems with impulsive effects. The strengths and locations of the stabilizing impulses, as well as the number of the controlled nodes are all assumed to be time-varying. Some sufficient criteria are established such that the considered system can exponentially track the dynamical reference state based on the given impulsive control algorithm. Finally, the dynamic system of robotic arms modeled by nodes is presented to verify that the established results are of not only theoretical validity but also practical effectiveness.

H∞consensus is investigated for multi-agent systems with linear dynamics and impulsive effects in this paper. First of all, by considering the effects of distributed impulses, the model of linear multi-agent systems with impulsive effects and external disturbances has been obtained. Then, in view of the average impulsive interval and the Lyapunov stability theory, an algorithm has been given to solve the H∞impulsive consensus for the linear multi-agent system under consideration. The theoretical results are verified by an example in the final.