The dynamic evolution of Internet of Things (IoT) threats necessitates reliable network intrusion detection (NID) systems. Such systems should not only respond to known security risks but also adapt effectively to emerging threats. However, practical deployments in novel IoT environments often suffer from significant data scarcity. In these cases, only a few labeled samples are available for training, which typically leads to poor performance. To address this challenge, we introduce a Semi-supervised Meta-negatIve-LEarning approach, termed SMILE, for few-shot network intrusion detection using network traffic data. Our approach begins by pretraining a baseline NID model with historical attack data, followed by an improved negative learning strategy with uncertainty-aware pseudo-negative labels. Bagging sampling is further incorporated to dynamically balance pseudo-labeled data distributions and enhance tolerance to labeling errors. SMILE enables effective knowledge transfer from historical attacks to few-shot traffic streams. Experimental results on the CICIDS-2017 dataset demonstrate that SMILE significantly improves detection accuracy by 7.30%–16.65% across diverse classifier architectures in both 5-shot and 10-shot scenarios, achieving a peak accuracy of 81.91%. Additional validation on the Edge-IIoT and IoT-23 datasets shows consistent improvements of 9.38% and 4.78%, reaching respective accuracies of 96.25% and 84.08% under 10-shot detection.

Root cause analysis is critical for identifying fault propagation paths and root cause variables in industrial processes. However, existing methods often overlook deep causal information, require per-variable modeling of temporal dependencies, and offer limited interpretability. To address these challenges, we propose a novel lag-wise temporal squeeze-and-excitation network. This method decomposes the causal inference task along the time lag dimension, employing subnetworks to extract deep-layer causal features. A unified temporal squeeze-and-excitation module then models temporal dependencies across all lags. The proposed scheme integrates lagged inputs, a temporal causal matrix, and interpretable predictions to enable exploration of causality variations and preservation of local causal patterns. Finally, a reachability matrix derived from the causal adjacency matrix quantifies root cause scores. Experimental validation on a real-world industrial mineral process demonstrates the effectiveness and superiority of the proposed method.

Multi-stage processes, such as batch and transition processes, often have unequal operation duration due to differing conditions, posing significant challenges to process monitoring. Although dynamic time warping (DTW) has been applied for offline synchronization, it cannot adequately align an evolving, incomplete online batch with completed historical batches due to inherent inconsistencies in their progression. Moreover, traditional methods generally overlook time-scale faults in the operational progress of the process, which undermines overall monitoring performance. To address these issues, a novel projective weighted DTW (PwDTW)-based method is proposed to monitor multi-stage processes with unequal durations. First, the asymmetric weighted DTW is adopted to offline align the original training dataset with different lengths, incorporating the Itakura parallelogram constraint to restrict the region of the warping path. Then, the PwDTW with an open-ended strategy is proposed to handle the online asynchronization problem by assessing the progress and similarity of the ongoing trajectory against each training trajectory. Further, the k-nearest neighbor (KNN) is used to identify the most similar subsequences of the training dataset with the online trajectory. Leveraging these subsequences, two monitoring indices are designed to monitor the process in not only amplitude scale but also time scale. The two indices reflect both the strength and speed of the process. Finally, a benchmark Tennessee Eastman process and a practical semiconductor manufacturing case are introduced to prove the effectiveness of the proposed method. Note to Practitioners—This paper aims to solve the practical problem of on-line monitoring multi-stage processes with unequal durations from both amplitude and time perspectives. Traditional methods typically focus on offline alignment of processes with different durations and lack online applicability. Additionally, their focus on monitoring only the signal amplitude also limits the potential to monitor whether the process is progressing too fast or too slowly. This paper proposes a novel PwDTW-based monitoring method to address these issues. The approach begins by using asymmetric weighted DTW (wDTW) for offline alignment of historical data, synchronizing datasets with varying durations. When new samples arrive, this paper develops a PwDTW method with an open-ended strategy that evaluates process progress and identifies similar patterns for the online sample. Further, by assessing both the strength and the speed of the process, this paper provides dual-perspective monitoring that is more comprehensive than traditional methods. The effectiveness of this approach has been demonstrated through its application to the TE process and a real-world semiconductor manufacturing process. The proposed method is universal and can be adapted to other industries, such as energy production or pharmaceuticals, where varying durations are ubiquitous in the systems.

Industrial Internet of Things (IIoT) enables smart factories, production, and logistics. However, any vulnerability in the network can lead to severe consequences for both industries and individuals. Being essential cybersecurity tools for IIoT, intrusion detection systems (IDS) play an important role in detecting network attacks. However, IDS can suffer from inaccuracy due to the rare nature of cyberattacks, a.k.a. sample imbalance. In this article, we introduce a transformer-based model termed aTtack-awaRe divide-And-ConquEr tRansformer (Tracer) for both anomaly detection and attack classification, which only needs network traffic data instead of content data. In particular,Tracerincorporates attack-aware learnable queries to enhance category-specific information. A hierarchical divide-and-conquer decoder is also designed tailored to these queries, which is effective in enhancing the accuracy of minority classes.Traceraims to detect complex, imbalanced traffic attacks without the need for data balancing samplers or separate classifiers.Tracerachieves remarkable 98.8% accuracy in anomaly detection on the UNSW-NB15 dataset, with 0.3% false alarm rate. It also reports multiclass attack accuracy of 86.02%, 96.17%, and 99.48% on the UNSW-NB15, Edge-IIoT, and CICIDS-2017 dataset, respectively, increasing the detection accuracy by about 1%–10%. The results suggest ourTracermodel shows potential to be an effective and easy-to-use solution for generic intrusion detection in IIoT.

In this article, we advance a compensation matrix based model predictive control (CMB-MPC) framework for the register control of roll-to-roll (R2R) printing systems to overcome the deficiencies of traditional model predictive control (MPC) in register precision and computational complexity. Within the structure of CMB-MPC, a compensation matrix is introduced, serving to simplify the internal predictive model tailored for the MPC controller of R2R printing systems through the preprocessing of control variables. According to the processed model, we propose a novel predictive control algorithm for register control, incorporating a coupling-based selection algorithm to strategize the control weight matrix of the controller against the adverse effects of system coupling. The effectiveness and superior performance of CMB-MPC are demonstrated by experiments and comparisons, and the results indicate that CMB-MPC imparts three distinct advantages. First, it significantly reduces the computational complexity of traditional MPC controllers for the register control of R2R printing systems. Second, it achieves a remarkable enhancement in register accuracy within R2R printing systems, surpassing the capabilities of conventional MPC and fully decoupled proportional-differential control methods. Third, the waste material controlled by CMB-MPC exhibits exceptional less, rendering it highly suitable for industrial applications.

Fault diagnosis of dynamic multivariate systems is a challenging problem. In this article, a novel fault diagnosis scheme based on variable-wise stacked temporal autoencoder (VW-STAE) is proposed. First, a variable-wise strategy is proposed on the raw industrial data, which sorts the variables for a specific fault by its deviation factor and introduces fault label information during pretraining procedure. Then, temporal autoencoder (TAE) is designed to capture the temporal and spatial feature synchronously and model the complex dependencies of dynamic samples. The stacked TAE is built to enhance the ability of feature extraction by combining multiple TAEs. By inputting the sorted variables sequentially, the VW-STAE is trained as a binary classifier for a specific fault; thereby its input variables and the corresponding network parameters are ultimately selected according to the VW-STAE with the optimal diagnosis performance. Finally, a bank of VW-STAEs is adopted for all faults, which is followed by a fully connected layer to achieve comprehensive fault diagnosis result. The effectiveness of the proposed method is demonstrated in the sensorless drive diagnosis example. The results indicate that the proposed method outperforms other existing deep learning methods.

Real-time nonlinear multimode process monitoring of actual industrial systems has attracted increasing attention recently. In this article, the time-weighed kernel sparse representation (TWKSR) method is proposed to partition the mode of the training dataset by introducing the time-series-dependent characteristics into the kernel sparse representation algorithm. The alternating direction method of multipliers is utilized to solve the optimization problem of the proposed TWKSR method. Then, the representative samples from each identified mode are selected to update the dictionary matrix. Based on the updated dictionary matrix, the sparse coefficient is used for online mode identification, and the reconstruction error is utilized for fault detection. Finally, a numerical simulation case and the wastewater treatment process example verify the effectiveness of the proposed method.

The roll-to-roll (R2R) web printing system is a complex coupling system, in which tension fluctuation is caused by upstream register control, thus results in downstream register errors. Therefore, it is indispensable to compensate for the couplings in order to improve the register precision in R2R printing systems. However, existing control methods do not realize complete decoupling due to their indirect calculation of compensations for the register errors. In this article, a mechanical model is set up to represent the direct relationship between the downstream register errors and all their upstream register controls. According to the model, compensation is calculated on the basis of the Lyapunov stability theorem to converge the register errors to zero. Then, a direct-decoupling closed-loop control method with first-order compensation terms, i.e., the direct-decoupling proportional derivative control (DDPD), is proposed to completely compensate for the couplings between all upstream register controls and downstream register errors. In addition, the first-order expression of the compensation makes it easy to implement in industrial applications. An industrial example indicates that the proposed control method eliminates the couplings and maintains the range of register errors within ±0.06 mm.Note to Practitioners—This article proposes a control strategy for the roll-to-roll (R2R) printing system, particularly for printing systems with electronic line shafts. Few existing studies have been done in detailedly analyzing the upstream register controls and the downstream register errors. This article establishes a mechanical model of printing registration and gives a systematic analysis of the complete relationship between upstream register controls and downstream register errors and then proposes a control strategy based on the Lyapunov stability analysis. The proposed method can be extended to other similar R2R systems. Simulation and industrial examples show that the control method is more feasible and effective compared with the existing methods. In future work, we will study a control method combined with the mechanical model and data model in different R2R systems.

In this paper, the torus-event-based fault detection and isolation (FDI) problem is investigated for a class of time-varying multirate systems. An ellipsoidal constraint is first adopted to describe the fault in a more practical pattern, and a novel torus-event-triggering scheme is proposed to improve the unilateral triggering mechanism. The aim is to design the torus-event-based fault detection filter and fault isolation estimators such that both the prescribed variance constraint on the estimation error and the desired H∞performance on the disturbance are guaranteed over the finite horizon. Especially, the residual evaluation function is employed to detect the fault, and the residual matching function is developed to isolate the fault. Furthermore, three optimization problems are provided to seek separately the minimal parameters on the H∞performance level, the upper bound of the estimation error variance, and the triggering torus. Finally, two simulation examples are utilized to show the effectiveness of the FDI scheme proposed in this paper.

High precision register controls are indispensable in roll-to-roll (R2R) printing systems for mass manufacturing. In R2R printing systems, each gravure cylinder is driven by an individual motor and guiding rolls distributed between two adjacent gravure cylinders are driven by the tension of their wrapped web. In the speed-up phase, tension fluctuations caused by torque balance of guiding rolls generate register errors in each printing unit. Therefore, it is a challenging issue to design a control method to reduce the register errors. In this paper, a mechanical model of R2R printing systems in the speed-up phase is developed based on the principle of mass conservation and torque balance. A model-based feed-forward proportion-derivative controller is designed to reduce the register errors caused by the tension fluctuations. The validity of the proposed method is demonstrated by simulation and experiments carried out on an industrial rotogravure printing press. A comparison with other control methods especially a well-tuned proportion differential control which is widely adopted by printing presses shows that the absolute maximum register error is drastically reduced and the average register error is greatly decreased by the proposed method. The results verify the effectiveness and feasibility of the proposed control method. Note to Practitioners-This paper presents control strategy for the speed-up phase in R2R printing system, particularly for printing systems with electronic line shafts. Few existing systematic research is relevant with the speed-up phase in the R2R printing system. This paper analyses the relationship of the register error and the web tension fluctuations between two adjacent gravure cylinders which are driven by the guiding rolls, then proposes the control strategy based on the identification of the acceleration of guiding rolls. The proposed method can be extended to other similar R2R systems. Simulation and industrial experiments suggest that the control method is feasible and has superior performance compared with the existing methods. In the future research, we will study the adaptive model representing the acceleration of guiding rolls in different R2R web systems.

In many batch-based industrial manufacturing processes, feedback run-to-run control is used to improve production quality. However, measurements may be expensive and cannot always be performed online. Thus, the measurement delay always exists. The metrology delay will affect the stability and performance of the process. Moreover, since quality measurements are performed offline, delay is not fixed but is stochastic in nature. In this paper, a modeling approach Takagi-Sugeno (T-S) model is presented to handle stochastic metrology delay in both single-product and mixed-product processes. Based on the Markov characteristics of the delay, the membership of the T-S model is derived. Performance indices such as the mean and the variance of the closed-loop output of the exponentially weighted moving average (EWMA) control algorithm can be derived. A steady-state error of the process output always exists, which leads the output deviating from the target. To remove the steady-state error, an algorithm called compensatory EWMA run-to-run (COM-EWMA-RtR) algorithm is proposed. The validity of the T-S model analysis and the efficiency of the proposed COM-EWMA-RtR algorithm are confirmed by simulation.

Run-to-run controllers based on the exponential weighted moving average (EWMA) statistic are probably the most frequently used for the quality control of certain semiconductor manufacturing process steps. The threaded-EWMA run-to-run control is an important stable control scheme. However, the process outputs will deviate largely in the first few runs of each cycle if the disturbance follows an IMA(1,1) series with deterministic linear drift and the thread has a long break length. In this paper, the output of the threaded-EWMA run-to-run control is derived, stability conditions are given, and the causes of large deviations in the first few runs of each cycle are found. Based on the analysis of system performance, a cycled resetting (CR) algorithm for discount factor is proposed to reduce the large deviations, as well as to achieve the minimum asymptotic variance control. Furthermore, how to deal with step fault is also discussed in this paper. By analyzing the influence of the fault, a discount factor resetting fault-tolerant (RFT) approach is proposed. Simulation study shows both the mean square error (MSE) and variance of the output by the proposed algorithm is about 30% to 50% lower than that of the algorithm with fixed discount factor in the process with and without oscillation. This verifies the effectiveness of the proposed approach.