Adaptive observers have undergone sustained theoretical evolution and gained widespread industrial adoption due to their inherent capability for simultaneous parameter and state estimation in dynamic systems. While significant advancements have been made in nonlinear system identification and adaptive control, critical challenges persist in closed-loop implementations. These challenges stem primarily from input-noise correlation induced by feedback mechanisms and performance degradation caused by unknown disturbances. To solve these problems, a closed-loop robust adaptive estimation framework is proposed in this article. It employs coprime factorization to construct noise-decoupled auxiliary variables as reconstructed system inputs, thereby effectively decoupling input-noise correlations. The proposed framework integrates a disturbance estimation module into the adaptive observer while implementing optimal step size adaptation for noise suppression. This cooperative approach achieves simultaneous estimation of system dynamics and disturbances with guaranteed stability and convergence. Experimental validation demonstrates superior performance compared to existing algorithms.

Deep learning methods have made significant progress in medical image analysis, particularly in the segmentation of knee cartilage MRI images. However, the cartilage regions are of relatively small size and they are susceptible to background interference. As a result, traditional segmentation methods are prone to practical limitations such as class imbalance and background noise. The boundaries of knee cartilages are often unclear, especially in pathological conditions where the morphology of the cartilage may change, making it difficult to segment the boundaries of the cartilages accurately. To address these issues, this paper proposes an innovative two-stage approach that leverages the functions of object detection and segmentation (D2MSeg). At the first stage, an object detection module is used to precisely localize the knee cartilage region, thereby reducing background interference and the influence of non-target areas, effectively tackling the class imbalance problem. At the second stage, a memory-augmented module is proposed to help the model learn the fine details of the cartilage boundary by guiding the network to focus on fine-grained information. Experimental results on our dataset show that D2MSeg achieves a Dice score of 83.34%, outperforming most existing methods, including U-Net and TransUNet under comparable settings. These results highlight the effectiveness of our approach in capturing fine cartilage structures and its strong potential for clinical application.

This paper presents an adaptive residual generator-based co-estimation algorithm for multi-sinusoidal signals with unknown components. By modeling the multi-sinusoidal signal, a residual generator algorithm integrated with the adaptive estimation mechanism is constructed. The proposed algorithm can simultaneously estimate the amplitude, frequency, and phase of every sinusoidal component online with stability and convergence guarantees. The performance of the proposed co-estimation approach is evaluated with a simulation experiment.

This paper presents a data-driven framework for integrating encryption transmission and attack detection in cyber-physical systems (CPS) with nonlinear physical plants. The main focus of this research is to use deep neural networks to realize the coprime factorization (CF) of nonlinear systems. The definition of the CF guides the network training and designing process, and the model’s topology is designed in the state-space form, which improves the interpretability of the data-driven CF. Based on the CF-aided neural networks, an encrypted transmission module is designed that projects information related to system dynamics into a perpendicular data space, which complements existing encryption methods from a control theory perspective. Subsequently, an anomaly detector are designed using the same CF pairs. This detector not only provides high-accuracy detection of attacks but also distinguishes between attacks and faults, thereby reducing the false positive rate and enhancing the reliability of the attack detection. The proposed method has been validated in a real CPS using a mecanum-wheeled vehicle as the physical plant, demonstrating its effectiveness and applicability.

Ultrasound is an important routine screening modality for breast cancer. Breast ultrasound screening is a dynamic process, and clinical practice involves radiologists recording representative frames during dynamic breast scanning for subsequent diagnosis. However, existing computer-assisted diagnosis methods often concentrate on dull diagnostic results by analyzing these representative frames and ignore the valuable information in the dynamic examination process that facilitates diagnosis. Moreover, breast lesions could exhibit various characteristic differences during scanning, and effective learning of lesion representations is challenging and may affect the clinical interpretability of the methods. To this end, we draw insights from the behavior of radiologists during the dynamic breast examination and leverage the knowledge of breast anatomy to propose a clinical knowledge-aware framework for lesion detection and classification of breast lesions in ultrasound videos. It is equipped with global-local attentive aggregation and a dynamic allocation mechanism that simulates the behavior of radiologists searching for diagnostic clues, thus integrating local localization and global semantic information from the video into the feature representation of the lesion. An anatomically-aware transformer is also designed to refine the lesion feature representation using spatial relationships within and across different anatomical layers of the breast anatomy. Extensive experiments show that the proposed framework can achieve competitive performance in both lesion detection and video classification tasks while exhibiting good clinical availability and interpretability, with an average precision of 40.80% and an AUC of 85.86% on our constructed breast video dataset and an average precision of 39.79% and an AUC of 87.04% on a publicly available dataset.

This article proposes a game-based distributed decision optimization method for heterogeneous multiagent systems with unknown nonlinear dynamics. Due to the information exchange between agents in the network, the unknown nonlinear dynamics lead to the degradation of local and all-agent control performance, which causes the strategies of all agents to deviate from the Nash equilibrium under a given goal. To address this problem, an adaptive distributed algorithm is designed to seek Nash equilibrium by combining two optimization levels. Specifically, the decision layer uses a distributed consensus algorithm to achieve benefit evaluation and a gradient algorithm to generate reference signals. Then, the control layer uses the virtual reference signal from the decision layer and the neural network estimation information to design an adaptive control algorithm. The proposed method performs real-time adaptive optimization of the strategies and control performance of the decision and control layers, ensuring the successful implementation of the distributed Nash equilibrium search. The convergence of the proposed algorithm is proved in the Lyapunov sense. Finally, simulation examples demonstrate the performance and effectiveness of the proposed method.

This article proposes a subspace-aided distributed monitoring and control performance optimization integrated framework and the corresponding distributed monitoring and optimization approaches equivalent to centralized designs. It effectively realizes the online global control performance optimization and solves the predesigned controller parameter adjustment limitation. The main contributions of this article are as follows. First, the proposed distributed monitoring and optimization modules can cooperate to establish a subspace-aided distributed integrated framework. The framework effectively addresses the issue of separate design in monitoring and optimization, achieving modularization that facilitates the expansion and maintenance of interconnected systems. Second, the proposed subspace-aided control performance optimization approach breaks the limitations of existing methods that require predesigned controller parameter adjustments, which can achieve distributed control performance optimization while ensuring closed-loop stability of interconnected systems. Third, the proposed optimization approach can automatically adjust the iterative step size, avoiding the disadvantage of manually setting the step size in the traditional optimization algorithm. It shortens the optimization time and reduces the design difficulty. The new methodologies have been evaluated against the current techniques and validated using an interconnected dc motor system, which holds significant engineering importance.

The idea of stacking layers is adopted to construct a deep multivariate statistical model, hierarchical canonical correlation analysis (HCCA). Its hierarchical structure is motivated form the deep network. The proposed HCCA model has the features of low computational complexity, strong correlative feature extraction, and causal interpretability. Its correlation advantages are theoretically demonstrated, then the evaluation metrics about accuracy and complexity are presented. The HCCA-based fault monitoring method is proposed for industrial processes, and the variable contributions are analyzed based on the residual statistic. The experiment results on Tennessee Eastman and real industry wastewater treatment processes show an average fault detection rate of 87.91$\%$and 99.49$\%$. It also decreases an average false alarm rate to 0.92$\%$and 0.32$\%$, respectively.

Aiming at the current challenges in converting electrical parameters to indicator diagrams, a subspace-aided indicator diagram estimation approach is proposed to establish a data-driven mapping model from electrical to force parameters, which helps avoid the need for analyzing the mechanism model of tower-type pumping systems. Specifically, the lifting technique is adopted based on the subspace method to construct the space of the electrical parameter signals, addressing the correspondence between input and output signals, while preventing the loss of effective information. Then, a recursive indicator diagram estimation approach is proposed, utilizing the updating/downdating of the Cholesky decomposition to enable online updating of the data-driven mapping model. In addition, for tower-type pumping systems operating under multiple conditions, a gap metric indicator is developed as a test statistic to determine the switching of operating conditions. The effectiveness of the proposed methods is verified through experimental measurements from tower-type pumping systems in actual oil wells.

Source-free domain adaptation (SFDA) has emerged as a promising and practical approach to achieve better cross-domain fault diagnosis in privacy-preserving scenarios, yet face challenges in identifying target-private faults within open-set (OS) scenarios. To address this limitation, a theoretical generalization bound error is employed to analyze the root causes, which primarily stem from domain shift and OS scenarios. Guided by this theoretical foundation, a novel SFDA-OS approach is proposed to integrate target adaptation process and OS separation using entropy-based confidence index and corresponding confidence sets. It incorporates a comprehensive loss function for adaptation, combining pseudolabel learning, clustering, and uncertainty-aware updating for high-confidence samples, alongside additional clustering for low-confidence samples. Extensive experimental results validate the effectiveness of the proposed method, demonstrating its capability to provide a potential, practical, and privacy-compliant solution for deployable fault diagnosis in actual engineering systems where unknown faults emerge and source data access is restricted.

This article proposes a projection-aided robust distributed monitoring and control optimization approach for interconnected systems with disturbances. The disturbances and state coupling between subsystems are a challenge in achieving accurate distributed process monitoring using data-driven techniques. To address the problems, a distributed adaptive residual generator uses the average consensus algorithm to perform data fusion on the subsystem residual generator to implement disturbance decoupling process monitoring. The key to implementing this process is to use input and output data disturbance in the perturbed orthogonal complementary space to drive the adaptive residual generator. Then, using the projection technique, the residual signal in the disturbance space drives the distributed learning of plug-and-play (PnP) controller parameters. The average consensus algorithm ensures that the subsystem PnP controller parameter gradient consistency converges to the centralized design. The feasibility and effectiveness of the proposed approach are verified and demonstrated through a simulation.

This article designs a data-driven security defense and monitoring approach that involves encrypted transmission and attack detection to defend cyber-physical systems (CPS) against stealthy attacks. The approach starts by using subspace theory to achieve data-driven coprime factorization of the closed-loop CPS. Based on this, the physical dynamics are encrypted from a control perspective to minimize the risk of information leakage and hinder the creation of stealthy attacks. Meanwhile, the security monitoring approach is designed using the same offline-learned coprime factorization. This approach is effective in detecting and distinguishing between cyber-physical attacks and machine-induced faults, which enables effective maintenance measures to be taken for different anomalies. The proposed encrypted transmission and security monitoring approach provides a comprehensive defense against nonstealthy and stealthy attacks. The effectiveness of our work is illustrated through a numerical example and experimental results on a Mecanum-wheeled vehicle platform.

This article focuses on utilizing process data to detect faults in nonlinear systems. To accomplish this, stable image/kernel representation is learned for nonlinear systems using deep neural networks, which serve as the basis for residual generators and fault detection. First, the closed-loop image representation of nonlinear systems is identified using gate recurrent units and fully connected neural networks. The involved network topology is designed to learn the nonlinear mapping in the form of linear time-varying state space, allowing the extension of existing linear methods to nonlinear systems. Then, with the identified image representation, the data-driven realization of kernel representation is derived. Finally, the residual generator is developed utilizing the system's kernel representation to enable precise fault detection in nonlinear systems. The effectiveness of our study is demonstrated through a numerical benchmark study and an actual experiment on a real Mecanum-wheeled vehicle platform.

This paper presents the parameter identification based on generalized orthonormal basis function (GOBF) without persistent excitation via two learning-based paradigms. The problem is formulated as a two-stage identification of poles and weight coefficients of GOBFs. The GOBF is designed based on the two-parameter Kautz basis function for the compatiblity with complex poles. The two learning-based paradigms are established on the nature-inspired meta-heuristic optimization and deep reinforcement learning, respectively. The ability of identification without strict persistent excitation is discussed as well. The effectiveness of the two paradigms are verified through a simulation study on a 4-order transfer function model.

Currently, deep learning methods in the analysis and processing of Magnetic Resonance Imaging (MRI) images have found widespread use in medical research. Due to the highly uniform features of human organs or tissues in medical images, pathological conditions are often distinguished only by subtle differences. The manifestations of knee-joint edema are complex and varied, possibly caused by various factors including injury, inflammation, and degenerative diseases, among others. The diversity in edema characteristics in images increases the difficulty of classification. Therefore, the task of pathological identification of knee joint edema poses significant challenges. This paper constructs a neural network model for extracting features of the knee joint and establishes a corresponding classification model. We propose a novel Multi-dimensional knee-joint edema classification network based on attention mechanism (MKEA), which includes a one-dimensional feature extraction network, a two-dimensional feature extraction network, and a feature fusion classification network. In the 2D feature extraction network, a channel attention mechanism module is embedded. we integrate these components to develop a network model for classifying knee edema images from the NYU fastMRI Initiative database. By using well-designed attention models, the network can selectively focus on key regions in medical images, eliminating the need for expensive annotations like bounding boxes or partial labeling. Our method was compared with state-of-the-art approaches on the knee-joint edema dataset. Experimental results show that our approach surpasses the current state-of-the-art methods in terms of performance.

Aiming at the problem of colored noise in the signal, this article proposes a subspace frequency estimation approach under colored noise with application to fault diagnosis of motor rolling bearings. First, a nonlinear discrete-time system is described to generate colored noise. An extended I/O model with parameters of a nonlinear discrete-time system is given by the subspace method. Then, the gap metric-aided system order determination approach is developed for extended observability matrix identification. Then, the data-driven diagnostic observer parameter identification approach and the fast approximate power iterative subspace method are adopted to realize online monitoring for frequency change detection. Eventually, a data-driven design scheme of residual generator is proposed for the implementation of fault detection. The effectiveness of the proposed methods is verified for fault diagnosis performance through numerical simulations and the experimental measurements from the dynamic motor rolling bearing experiment rig.

This article proposes a distributed performance recovery method for multiagent systems with actuator faults in noncooperative games. The local agent (player) can only obtain the policy information of neighboring agents through the communication network. The strategies of nonneighbors in the cost function are unknown, and a leader–follower consensus algorithm is introduced to estimate nonneighbors' strategy. When the actuator faults occur in any agents and lead to performance degradation, i.e., the agents' strategy is biased from its optimal strategy. A distributed optimization control method is proposed to recover performance without changing the original control scheme. An observer-based residual feedback plug-and-play optimization method is used to ensure that the strategies of all agents can still converge to the optimal strategy (or close to the optimal strategy). Numerical case studies are applied to demonstrate the performance and effectiveness of the proposed method.

To ensure system reliability and maintain power supply in fault conditions, this article proposes a fault-tolerant sun-pointing controller based on physics-guided neural networks for handling sensor faults. The proposed controller gains the fault tolerance ability by learning from the behavior of the nominal controller, which integrates a physics-based model with a deep learning model to exploit implicit physical insights during the learning process. The proposed controller enhances the intrinsic interpolative nature of the pure deep learning model, thereby improving fault tolerance for unknown faults. Furthermore, a novel loss function that incorporates the physics-based model is proposed. The loss function assigns different loss terms to the fault-free and the fault datasets, facilitating accurate utilization of loss terms. Unlike traditional active fault-tolerant control schemes, the proposed method requires no explicit fault detection and diagnosis module. The effectiveness of the proposed controller is validated through hardware-in-the-loop simulations. The results indicate that the proposed controller outperforms the pure deep learning controller, as evidenced by a shorter sun-pointing convergence time and more precise angular velocity.

The intelligent manufacturing system is a complex, large-scale, interconnected system composed of many intelligent agents, and there may be physical or information space couplings between the agents. A distributed monitoring system and optimization control method are proposed to ensure the system completes its tasks safely and efficiently. The distributed monitoring system based on the average consensus algorithm is equivalent to the centralized design method, in which the submonitoring system only requires local and neighbor subsystem information. The advantage of this design is that it uses local and interactive information to achieve global diagnosis. In addition, sending data from all subsystems to a central computing node is challenging to implement in large-scale manufacturing systems. Based on the centralized plug-and-play (PnP) optimization control method, an average consensus algorithm distributed manufacturing system PnP optimization control method is proposed. Its advantage is that it uses local information and interactive information to achieve global control optimization. On this basis, an integrated architecture for distributed fault detection and optimization control is developed. The simulation results verify the feasibility and effectiveness of proposed method.

This article designs a data-driven unsupervised defense scheme for nonlinear systems by proposing a machine learning approach called gate recurrent unit-based modified denoising and stable image representation-aided autoencoders. The proposed scheme decomposes original data into two subspaces through orthogonal projection. For secure transmission, information related to the system's dynamics, which is in the image space of the controlled system, is hidden through filtering, whereas only the dynamic-independent information is plaintext for transmission, which supplements the cryptographic encryption methods from a control perspective. Moreover, attack detection for nonstealthy and stealthy attacks is achieved simultaneously under the same framework. A case study is conducted for validation on the a hardware-in-the-loop platform with a mecanum-wheeled vehicle. The comparative experiments with well-known unsupervised data-driven methods show the high detection accuracy of the proposed defense scheme for nonstealthy and stealthy attacks and the excellent encryption capability.

Accurate remaining useful life (RUL) prediction of lithium-ion batteries is critical for energy supply systems. In conventional data-driven RUL prediction approaches, the battery's degradation mechanism is difficult into incorporate in the RUL prediction. Furthermore, there are notable limitations in reflecting the significance of different time instances, and the uncertainty in the degradation process. Consequently, a novel data-model interactive RUL prediction approach based on particle filter-temporal attention mechanism-bidirectional gated recurrent unit (PF-BiGRU-TSAM) is proposed. Specifically, BiGRU-TSAM is trained offline through historical data, which assigns corresponding significance to battery capacities at different time instances. Moreover, regarding the interactive data-model for the online prediction phase based on PF-BiGRU-TSAM, the advantages of data-driven and model-based approaches are integrated, which accomplishes the purpose of modifying each other. The proposed PF-BiGRU-TSAM approach is validated with a real-world battery dataset. Experimental results demonstrate the proposed approach is better than some published approaches. Taking the 50th operational cycle of the four batteries B0005, B0006, B0007, and B0018 in the dataset as an instance, the absolute errors of the proposed PF-BiGRU-TSAM are 0, 1, 3, 3, respectively, which represents the proposed approach has an excellent performance.

Over the last decade, transfer learning has attracted a great deal of attention as a new learning paradigm, based on which fault diagnosis (FD) approaches have been intensively developed to improve the safety and reliability of modern automation systems. Because of inevitable factors such as the varying work environment, performance degradation of components, and heterogeneity among similar automation systems, the FD method having long-term applicabilities becomes attractive. Motivated by these facts, transfer learning has been an indispensable tool that endows the FD methods with self-learning and adaptive abilities. On the presentation of basic knowledge in this field, a comprehensive review of transfer learning-motivated FD methods, whose two subclasses are developed based on knowledge calibration and knowledge compromise, is carried out in this survey article. Finally, some open problems, potential research directions, and conclusions are highlighted. Different from the existing reviews of transfer learning, this survey focuses on how to utilize previous knowledge specifically for the FD tasks, based on which three principles and a new classification strategy of transfer learning-motivated FD techniques are also presented. We hope that this work will constitute a timely contribution to transfer learning-motivated techniques regarding the FD topic.

Accurate bearing fault diagnosis is of great significance of the safety and reliability of rotary mechanical system. In practice, the sample proportion between faulty data and healthy data in rotating mechanical system is imbalanced. Furthermore, there are commonalities between the bearing fault detection, classification, and identification tasks. Based on these observations, this article proposes a novel integrated multitasking intelligent bearing fault diagnosis scheme with the aid of representation learning under imbalanced sample condition, which realizes bearing fault detection, classification, and unknown fault identification. Specifically, in the unsupervised condition, a bearing fault detection approach based on modified denoising autoencoder (DAE) with self-attention mechanism for bottleneck layer (MDAE-SAMB) is proposed in the integrated scheme, which only uses the healthy data for training. The self-attention mechanism is introduced into the neurons in the bottleneck layer, which can assign different weights to the neurons in the bottleneck layer. Moreover, the transfer learning based on representation learning is proposed for few-shot fault classification. Only a few fault samples are used for offline training, and high-accuracy online bearing fault classification is achieved. Finally, according to the known fault data, the unknown bearing faults can be effectively identified. A bearing dataset generated by rotor dynamics experiment rig (RDER) and a public bearing dataset demonstrates the applicability of the proposed integrated fault diagnosis scheme.

Due to limitations in large-area communication and computation, it can be challenging to apply centralized diagnosis and optimization control design approaches to cascaded systems. This work proposes a distributed diagnosis and optimization control approach, which is realized using data-driven techniques. Specifically, an adaptive observer-based subdiagnosis system design approach is proposed for cascaded systems using only the local input/output (I/O) data and the state estimations of adjacent subsystems. The state estimations from neighboring subsystems are treated as known inputs in the local subsystem. In the centralized design approach, the residual signals generated by all subsystem observers need to be sent to the central computing node to reconstruct controller parameters. The learning process of the local optimization controller only needs to be driven by the residual signals from local and adjacent subsystems, avoiding centralized calculation and reducing the computational burden of the central node. The learning process of the locally optimal controller only needs to be driven by residual signals from the local and neighboring subsystems. In the end, the simulation results verify the effectiveness of the proposed distributed approach.

Coverage control describes the optimal deployment problem of multi-agent system with communication sensors, aiming to drive the multi-agent system reach the optimal deployment location. To accomplish coverage tasks, agents are required to communicate with each other. Thus, the connectivity of multi-agent system is a fundamental requirement in case of agent disconnection and disappearance. In this paper, we propose a distributed coverage control algorithm with connectivity optimization. According to the designed cost function, the controller is divided into two parts: coverage controller and connectivity optimization controller, and the method of gradient descent is used to minimize the cost function to get the controller. Finally, the simulation serves to show the effectiveness of the algorithm.

With the development of Cyber-Physical Systems (CPSs), many industrial facilities have realized remote control and monitoring. However, the widespread of CPSs has brought new issues and challenges in terms of security. Attackers can exploit vulnerabilities induced by network communication, tamper with transmitted data, and cause serious accidents through carefully designed covert attacks. This paper proposes a residual-driven comprehensive defense scheme based on the coprime factorization technique to address the threat posed by concealed CPS attacks. The novel scheme protects CPS from stealth cyber-physical attacks through secure transmission and attack detection. In particular, a secure transmission method is first introduced to prevent information leakage from the source. The pivotal idea is to convert confidential transmission control and measurement signals into non-essential filtered residual signals. It contributes to the reduction of information leakage and helps reduce the risks of stealth attacks. Then, under the same residual-driven framework, a stealth attack detection approach is put forward. It can eliminate false alarms caused by system faults, and therefore, achieve superior efficacy in detection accuracy under stealth attacks. Finally, simulation research is conducted on the F-404 engine to verify the effectiveness and performance of the proposed scheme and approach.

Knee segmentation and landmark localization from 3D MRI are two significant tasks for diagnosis and treatment of knee diseases. With the development of deep learning, Convolutional Neural Network (CNN) based methods have become the mainstream. However, the existing CNN methods are mostly single-task methods. Due to the complex structure of bone, cartilage and ligament in the knee, it is challenging to complete the segmentation or landmark localization alone. And establishing independent models for all tasks will bring difficulties for surgeon's clinical using. In this paper, a Spatial Dependence Multi-task Transformer (SDMT) network is proposed for 3D knee MRI segmentation and landmark localization. We use a shared encoder for feature extraction, then SDMT utilizes the spatial dependence of segmentation results and landmark position to mutually promote the two tasks. Specifically, SDMT adds spatial encoding to the features, and a task hybrided multi-head attention mechanism is designed, in which the attention heads are divided into the inter-task attention head and the intra-task attention head. The two attention head deal with the spatial dependence between two tasks and correlation within the single task, respectively. Finally, we design a dynamic weight multi-task loss function to balance the training process of two task. The proposed method is validated on our 3D knee MRI multi-task datasets. Dice can reach 83.91% in the segmentation task, and MRE can reach 2.12 mm in the landmark localization task, it is competitive and superior over other state-of-the-art single-task methods.

A new fault-tolerant controller is designed in this paper, which ensures the event-triggered leader-following consensus of multiple robotic manipulators subject to switching topologies. A Markov distributed sequence with a known probability transition matrix is employed to describe the switching communication topologies of multiple robotic manipulators. The investigated actuator fault model contains both constant and time-varying faults. Also, the norm-bounded conditions are utilized to denote the manipulators nonlinearities and additive noises. Furthermore, a set of output-based control gains are explicitly characterized via ensuring mean-square stability on dynamics of consensus errors. Finally, simulation results illustrate the designed consensus protocol can compensate actuator failure effectively.

For manufacturing industry, scheduling problem is a very important problem. Good scheduling scheme can greatly improve the production efficiency of enterprises. The flexible job shop scheduling problem (FJSP) not only needs to arrange the processing sequence for the operations of each workpiece, but also needs to consider how to allocate machines to the operations to improve the processing efficiency. Dynamic flexible job shop scheduling problem (DFJSP) is based on FJSP, which studies how to dynamically reschedule enterprise production according to the actual situation when disturbance events occur, so as to minimize the impact of emergencies on production. For DFJSP under machine fault, this strategy can dynamically schedule in time for different states before and after the machine fault is repaired, maximize the use of workshop resources, and reduce the impact of machine fault on production. A scheduling scheme combining predictive scheduling and real-time scheduling is proposed for DFJSP under machine fault. Then the standard test cases are used to verify the scheduling scheme from multi-objective with NSGA-II. The experimental results show that the scheduling scheme is feasible.

The control of three-phase inverters with output LC filter is of great importance in many applications such as renewable energy, energy storage systems and uninterruptible power supplies, where the generation of sinusoidal output voltages with required amplitude, frequency and lowest harmonic distortion is desired. However, the inevitable parameter uncertainties and disturbances caused by manufacturing tolerance, aging of electrical components and load changes will degrade controller performance, which have always been challenges to traditional model predictive control methods. To deal with these challenges, a data-driven predictive control scheme is proposed in this paper. All unknown parameters and load current can be estimated online with a moving window adaptive observer. The estimation results are used to build a predictive model. Then, predictive control is applied to minimize the error between the output voltage and the reference value. Simulation results verify that the proposed scheme has a better ability to deal with parameter uncertainties and load changes than the traditional model predictive control scheme.

Threats of cyberattacks have penetrated from disclosing critical user information to destroying/manipulating industrial control systems. Study on data security during network transmission has raised increasing attention in the systems and control community, which is found very necessary and timely in the context of Industry 4.0. In most existing approaches, the protection of the transmitted data from eavesdropping attacks and the detection of malicious integrity attacks are usually carried out separately. In this study, an integrated data-driven framework applicable at the control level is proposed to deal with secure transmission and attack detection simultaneously. In the framework, a secure correlation-based encryption/decryption approach and a trustworthiness judgement approach are proposed. Comprehensive discussions are made regarding the analysis of the sensitivity to attacks, the introduced time delay, and the design degree-of-free. Executable algorithms are presented, corresponding to which hardware is modularized and can work standalone independent from the configuration of the monitoring and control systems or any third-party authentication agencies. Evaluation results on a simulated two-area frequency-load control power grid system are provided to show the effectiveness and performance of the proposed approaches.

Three-tank system is an important benchmark in industrial process. However, so far, the research on the three-tank system is mainly limited to simulation studies, and the use of virtual simulators. In this article, a real-time three-tank system setup is used for practical investigations. Differing with the virtual simulator of a three-tank system, the setup can enable the setting of different types of faults (such as cloggings and leaks in the system, sensor faults, and actuator faults) through manual manipulation, users can choose the combinations of different valves and knobs in the setup, which is helpful to evaluate and compare methods for process monitoring and control. The relevant codes or modules can be applied directly that are developed in the MATLAB/Simulink environment. On this setup, two methods are used to verify the effectiveness in this study. One method is to solve the problem of process monitoring and fault detection; due to the fluctuation of the liquid level caused by flow, the input/output (I/O) data are preferred to be decomposed to different subspaces, which aims to identify the data-driven stable kernel representation. Moreover, the original controller of the three-tank system cannot match the system accurately, and therefore, needs to be modified. To solve the problem, a plug-and-play process control method (the other method used in this article) is applied, which adds a stable Youla parameterization matrix on the basis of the original controller. All controllers that internally stabilize the control loop improves the performance of the system without changing the original controller of the three-tank system. The experimental results of the two methods indicate that the proposed approach has strong practicality.

The fourteen papers in this special section focus on data-drive management of complex systems via plant-wide performance supervision. Currently, massive amounts of data are continuously being produced by social and industrial activities. Consequently, data-driven techniques have received considerable attention both in industry and academia in recent years, aiding scientists to manage and interpret the available data. The reasons behind such popularity of data-driven techniques are twofold. On the one hand, advanced data processing and information acquisition technologies have been developed to the extent that large amounts of data in different forms are available for big data analysis from descriptive to prescriptive. On the other hand, with the help of machine learning methodologies, the supervision and management systems can provide effective decisions for plant-wide optimal performance. Compared to the conventional model-based techniques, the data-driven ones can not only save the costly modeling procedures but also extract valuable information from available process data for real-time analysis and management. However, there are many complex and challenging problems in the data-driven supervision and management techniques, such as data-driven supervision on the safety, security, and robustness, as well as the performance-supervised management and their distributed designs. The papers in this section target recent results, trends, and practical developments in the data-driven methodologies of plant-wide performance supervision and management for complex systems, especially those related to process monitoring and machine learning activities with their industrial applications.

Skeletal fluorosis is a form of endemic disease caused by the excessive intake of fluoride. Bone deformation and periosteal calcification are the typical manifestations that can be observed in the images and are usually served as a basis of pathological grading. In the current medical systems, the diagnosis of skeletal fluorosis fully relies on doctors' knowledge and experience, and no research effort has been made in automatic image information diagnostic systems. According to the image information, the shape of the lesion is irregular, the boundary is unclear and the lesion related pixels only occupy a small part of the image. We take the lead in proposing a two-stage scheme that can achieve automated X-ray image diagnosis and severity grading. In the first stage, a Dense U-Net is proposed for reliable lesion determination, and a multitype feature fusion approach passes effective and comprehensive features to the subsequent stage. In the second stage, a novel classifier is designed with the integration of ensemble learning and multiple instance learning, which can ensure classification accuracy in case that the feature for diagnosis only takes up a small proportion of the whole image. Through plenty of experiments on the actual data collected from the hospitals, it is verified that the proposed strategy can achieve satisfactory results on skeletal fluorosis image diagnosis and severity grading.

Lithium-ion batteries are widely used in many fields of modern life, e.g. wearable devices, electric vehicles and electric grids, etc. The safety and reliability of the lithium-ion battery are critical issues during the battery operation, where the battery management system (BMS) plays a key role. An accurate estimation of the state-of-charge (SOC) of the battery is essential for the BMS. However, due to the intrinsic nonlinearity of the lithium-ion battery, the accurate estimation of the SOC is technically challenging and has drawn lots of attention both from academic and industrial fields. In order to tackle this difficulty, many SOC estimation approaches have been proposed, in which an identification method for the parameters of the battery is normally implemented. However, the additional parameter identification approach greatly reduces the efficiency of SOC estimation and the bias from identification may significantly affect the accuracy of the SOC estimation. This paper proposes a novel data-driven SOC estimation approach based on the adaptive residual generator, which realizes integrating the parameter identification and the SOC estimation into a simultaneous procedure, where the convergences for both the parameter identification and SOC estimation are guaranteed. The proposed adaptive residual generator can estimate the SOC of the battery accurately due to real-time parameter identification that proactively minimizes the modeling error. The effectiveness and the performance of the proposed method are demonstrated through the case studies on a battery simulator. Also, owing to accurately identified parameters, the SOC of the battery is estimated accurately with almost 0% SOC estimation error.

Cup anemometers are widely used instruments for wind turbines to measure wind speed in wind farm. Aimed to reduce the adverse impact on wind energy resource estimation, this paper proposes a data-driven fault diagnosis approach for assessing the anemometer health status. Auto-associative netural network (AANN) is developed to reconstruct the anemometer measurement data after data pre-processing, and residual analysis is performed between the anemometer measurement data and the AANN reconstruction data. In addition, the quantitative indicators that can reflect the health status of the anemometer gained from residuals are obtained through the K-Means clustering algorithm, based on which the faulty anemometers in the wind farm can be identified. The approach can provide guidance for the production and operation of the wind farm.

The safety, stability and reliability of the modern complex processes have always been the focus of the industry. An abnormity can lead to failures in the production and manufacturing processes or even dramatic accidents. The fault diagnosis techniques aim to enhance the aforementioned aspects by detecting the system's deviations from the normal operating conditions and providing early warnings. By mining the hidden system features in the historical data, complex physical modeling procedures and the dependence on large amounts of prior knowledge can be avoided. In many practical scenarios, data-driven fault diagnosis algorithms are more suitable for modern industrial diagnosis. In this paper, a novel approach is proposed which integrates both multivariate statistical analysis and deep neural network to deal with the nonlinearities in the complex systems. Based on the theory of traditional data-driven methods, deep learning methods and the newly proposed method, a MATLAB-based fault diagnosis toolbox is developed and published online. Plentiful function libraries are provided to the researchers to analyze those algorithms and satisfy the need of practical industrial applications. By applying the developed toolbox, the characteristics of those algorithms are also compared, especially on the time-consumption feature and the fault discrimination feature.

In this article, two performance-based fault-tolerant control strategies are investigated for multiplicative faults in industrial processes. This is motivated by the fact that the changes in the system parameters caused by malfunctions generally lead to multiplicative faults, which may cause remarkable changes in system dynamics and performance. To be specific, the representation forms of the faulty plants are first given in terms of the so-called stable image and kernel representations, respectively. Then, by measuring the fault-induced system performance degradation, two performance-based fault-tolerant control strategies are formulated. Specifically, a residual-driven dynamic controller, which is also called plug-and-play control, is implemented to achieve control performance recovery in the context of stability margin. Finally, a benchmark study is demonstrated to show the efficiency of the proposed methods.

Due to the recent rapid developments in communication and networking technologies as well as computer science, the complexity of automatic control systems has increased significantly. To ensure the safety and the reliability of such systems under continuous operation, real-time supervision and control systems have now to run in parallel. These developments challenge scientists and engineers to come up with advanced fault diagnosis (FD) and fault-tolerant control (FTC) approaches that can monitor the abnormal changes in automatic control systems promptly. The objective is to maintain safe operating conditions that avoid severe performance degradation. The tasks involved in meeting the objective consist of fault detection, estimation, localization, isolation, feasible control strategies, and maintenance actions.

In the control theory, after the stability of the control system is guaranteed, improving the performance of the system has always been a hot topic. In this paper, based on the Plug-and-Play process monitoring and control architecture (PnP-PMCA), without changing the previously designed controller, new actuators plugged into original system will be presented. In addition, feedforward controller (one of the components of PnP-PMCA) related to tracking performance will also be designed. After the new actuator is inserted into the original system, the feedforward controller is adjusted by iterative method to achieve the desired tracking performance and the original controller is not modified. For the implementation of plug-and-play actuators and the effectiveness of the iterative feedforward controller, the three tank system benchmark experiment will be used to verify the feasibility of the above study.

Aiming at establishing reliable and flexible data-driven designs of process monitoring and control systems, this paper presents the latest study on the identification of the data-driven realization of the stable image representation (SIR) in the plug-and-play process monitoring and control architecture (PnP-PMCA). The core of this study is the identification of the multiplication operators from the reference signal to the control input and the system output measurement. This work is essential to the future research on the data-driven PnP process monitoring and control system designs. The correctness and the effectiveness of the proposed identification approach have been verified and demonstrated through randomly generated system and designed closed-loop.

This paper presents the study on the data-driven process monitoring system design for the dynamic processes with periodic rectangular wave disturbance. The basic idea of the proposed methods are to identify the stable kernel representation (SKR) of the dynamic process by projecting the process data into the row subspace of the periodic rectangular wave disturbance. With the help of the projection, the kernel subspace of the system can be further determined. Based on the identified data-driven SKR, fault detection are developed. The performance and effectiveness of the proposed scheme is verified and demonstrated through the numerical study on randomly generated systems.

Industrial systems are always subjected to the deterministic disturbance due to some inherited factors, which is likely to degrade the control and monitoring performance to some extent. This paper presents an approach to the closed-loop subspace identification of the data-driven stable kernel representation (SKR) with the deterministic disturbance. The essence is that we extend the CSIMPCA algorithm by introducing the deterministic disturbance and subsequently separate the part corresponding to the SKR of the system from the obtained parity space. The inspiration for the idea mainly stems from the necessity for the identification and process monitoring of practical closed-loop systems. The effectiveness of the proposed method is demonstrated and illustrated through randomly generated 4-order MIMO discrete-time LTI systems. Furthermore, the identified SKR is finally applied to the fault detection and related experimental results show a decent detection performance.

This paper proposes a new method to estimate the stability margin of a system by factorizing it into system's data-driven stable kernel representation (SKR) and controller's stable image representation (SIR). To this end, a coprime factorization technology is applied to the closed-loop system firstly. By analyzing the relations between the reference signal and internal signal, a new approach is adopted to calculate SKR of the system by the least square (LS) method. Furthermore, the data-driven realization of stability margin is calculated through system's SKR and controller's SIR. An example is given in the last part to testify the correctness of methodologies proposed in this paper.

This paper presents the latest study on the data-driven process monitoring system design for the dynamic processes with sinusoidal disturbance. In the previous study, it is understood that the row space of the deterministic disturbance is essential to the subspace method aided data-driven design. Based on the previous study, this paper first determines the row space of sinusoidal disturbance. By projecting the process data into the determined subspaces, the fault detection systems can be designed based on the identified kernel subspace of the system. The performance and effectiveness of the proposed scheme are verified and demonstrated through the numerical study on randomly generated systems.

Stimulated by the recent development of fog computing technology, in this paper, a fog-computing-aided process monitoring and control architecture is proposed for large-scale industrial processes, which enables reliable and efficient online performance optimization in each fog computing node without modifying predesigned control subsystems. Moreover, a closed-loop data-driven method is developed for the process monitoring system design and an adaptive configuration approach is proposed to deal with the problems caused by the changes of process parameters and operating points. The feasibility and effectiveness of the proposed design approaches are verified and demonstrated through the case study on the Tennessee Eastman benchmark system.

In this paper, after a brief introduction on the proposed plug-and-play (PnP) process monitoring and control system, two online configuration approaches are proposed for the observer-based residual generator. Firstly, an adaptive residual generator is developed based on the adaptive observer scheme. Aiming at higher feasibility and reliability of industrial application, an iterative learning approach is later developed. The well established three-tank benchmark system is utilized for the demonstration of the effectiveness of the proposed approaches.

Kernel method has been applied to many multivariate statistical analysis techniques. In this paper, we investigated the regression properties of Kernel Partial Least Squares (KPLS) and compared it to the standard technique. Basic mathematical algorithms and application of KPLS were shown. We further established regression model based on KPLS and demonstrated the model by a numerical case.

With the rapid development in science and technology, data acquisition, storage and mining technology are widely applied to various fields. All aspects of people's lives are recorded as data. Through the analyzing and arranging of data, people can get a lot of valuable information. In this paper, support vector machine (SVM), least squares support vector machine (LSSVM) and partial least squares (PLS) are respectively used in the field of economic research. Real-time monitoring and forecasting for stock index is vital to the market. The changing trend and index of stocks are predicted according to the analysis to the history data of the stock. By combining particle swarm algorithm (PSO) algorithm and LSSVM algorithm, the parameters in the LSSVM model can be optimized. These algorithms are compared on the basis of their forecasting results.