Stimulated by growing requirements for security and reliability in Cyber-Physical Systems (CPS), this paper proposes a federated intrusion detection framework integrating improved prototype learning and adjusted-logits Cross-Entropy loss to address the challenges of hybrid feature-label shifts. A dual-path federated learning approach (DP-FL) with prototype alignment and dynamic logits is proposed, featuring a two-branch architecture: At first, a dynamically log-weighted prototype aggregation mechanism employing dual adaptive factors is introduced, achieving a more balanced and informative global prototype. Building upon this, a dynamic logits adjustment mechanism is further designed to calibrate the decision boundaries of local client models by jointly considering both label frequency and prototype divergence, thereby strengthening the discriminative capability and generalization efficacy of the model. Finally, the validation of the proposed DP-FL framework’s effectiveness is conducted on the NSL-KDD and CICIDS2017 datasets. Experimental results show that the proposed DP-FL framework outperforms existing methods under scenarios involving hybrid feature-label distribution shifts.

Given the pervasive presence of feedback mechanisms and inertial loops inherent in industrial processes, increasing research efforts have focused on integrating latent feature dynamics into deep learning architectures to address the issue of strong dynamic autocorrelation in industrial processes. However, the complex temporal dependencies present in latent features and the limitations imposed by traditional alternating training methods have already constrained the performance of such models. In this paper, we propose a latent probabilistic dynamics embedding supervised deep networks for soft sensing. In detail, a probabilistic dynamic model with graph-guiding based on the past and current latent features is constructed in the latent space of the supervised deep networks to capture the complex dependencies between the latent sequences. The article introduces a new approach involving a probability-distribution-based predictive regularization term for latent features. By jointly training the model, the network parameters are optimized to ensure the overall convergence of the network. An improved variational graph recurrent neural network with the inclusion of randomness into the high-level latent space was proposed to model the latent dynamics for supervised deep networks and additional graph structure information to help analyze temporal dependencies. Finally, the proposed methods are implemented on two real industrial cases to demonstrate their effectiveness and superiority. Comparative experiments and ablation experiments are designed to illustrate the higher prediction accuracy and effectiveness of the proposed method.

The complex industrial environment and poor data quality inherent in electrolytic copper foil production often lead to inaccurate energy consumption predictors, and consequently unreliable energy optimization. Given the difficulty in further improving the accuracy of energy consumption predictors, this article proposes a high-reliability stochastic prediction-based ensemble optimization (SPEO) method for energy saving of copper foil electrodeposition. The approach begins by introducing stochastic prediction to establish a standard stochastic prediction optimization framework, wherein filtering operations are applied to mitigate the adverse effects of prediction errors on the optimization process. Subsequently, reliability analysis methods are employed to derive reliability metrics based on optimization results generated by energy consumption predictors of varying accuracy. Finally, these metrics are comprehensively incorporated to integrate multiple optimizers, along with their respective optimal result feedback, thereby enhancing the generalizability and stability of the method. Experimental evaluations using real-world data from an industrial electrodeposition process demonstrate the superiority of the proposed SPEO method.

Since the low labeled rate, especially the extremely low labeling rate with only one label data for each class, will greatly limit the performance of traditional fault diagnosis algorithms, this paper proposes a pseudo-label guided rotating machinery fault diagnosis method. Firstly, the vibration signal is converted into power spectral density (PSD) data and the structural similarity (SSIM) index is used to measure the relationship between PSD, which reasonably characterizes the structural relationship between the data. On this basis, more reliable pseudo labels are selected according to the adaptive threshold and assigned to the unlabeled data, which increases the number of available labeled samples and eliminates the influence of noisy labels. Then, in the pre-training stage, the weights based on pseudo-labels are improved by contrastive learning and embedded into the stacked autoencoder (ICSAE), enabling the model to learn deep features that are easier to classify. During the fine-tuning stage, labeled data and pseudo-label data with different weights are used to help improve the accuracy of model fault diagnosis. Finally, the laboratory bearing dataset verify the excellent performance of ICSAE in extremely low labeled rate scenarios.

A single-fiber forward transmission distributed vibration sensor (SF-FTDVS) is proposed in this article based on bi-directional structure, which breaks the dependence of traditional FTDVS on the interference loop structure or the multifiber optical path. The proposed SF-FTDVS inherits the advantages of fiber sensors with forward transmission. It can realize the relay-free distributed vibration sensing greater than 210 km since the continuous forward transmission of light waves provides good signal-to-noise ratio (SNR) performance. Besides, the bidirectional transmission structure enhances the consistency of vibration event perception, so that it can achieve a more precise location. Experiments demonstrated the feasibility of vibration event location with a wide-frequency range from 400 Hz to 10 kHz, allowing for an un-repeated sensing link up to 212 km. To the best of our knowledge, this represents the longest perception distance achieved by a relay-free sensor. The average location standard deviation (STD) and the location fluctuation range are estimated to be 15.7 m and ±37 m, respectively, demonstrating an improvement of 14% and 12% compared to the traditional distributed vibration sensors (DVS) scheme. The proposed SF-FTDVS not only offers the advantages of simple deployment, high-positioning accuracy, and wide vibration response bandwidth, but also exhibits good compatibility with other components, demonstrating great potential for applications in Internet of Things (IoT) systems.

Since the poor quality of signals and redundant features may reduce the accuracy of fault diagnosis of rotating machinery components, an ensemble targeted stacked denoising autoencoders (ETSDAE) method is proposed for machinery running under harsh environment. At first, a targeted denoising strategy is designed for ensemble models to remove noise from time-domain and frequency-domain data in the encode stage. The multidomian data makes up for the limitations of single-domain data while the denoising strategy improves the anti-noise ability of ETSDAE. On the other hand, two indexes based on mutual information are designed into cost function as a soft constraint to learn min-redundant deep features that have max-relevance to the class targets, thus it can get rid of the dependence on additional feature selection procedure. On this basis, integrated deep features are directly input to single-hidden layer feedforward neural network to realize fault diagnosis. Finally, the effectiveness of the proposed method are verified by rolling bearing test rig and industrial reciprocating pump. The results show that ETSDAE has excellent performance in fault diagnosis, especially in terms of anti-noise and feature learning.

In deep-learning-based process monitoring, obtaining an effective feature representation is a critical step in constructing a reliable deep-learning monitoring model. Conventional deep-learning methods like stacked auto-encoders (SAEs) capture feature representation by minimizing the data reconstruction errors, which lack the expression of essential information and ultimately lead to degradation of the monitoring performance. To solve this problem, variational discriminative SAE (VDSAE) is proposed in this article. First, a variational generative discriminative structure is designed to obtain a reliable prelearned discriminator. Based on this new variational discriminator, the authenticity of the reconstructed data is evaluated as an important criterion for feature learning. Then, an SAE incorporating the prelearned discriminator is trained by both minimizing the reconstruction error and maximizing the data authenticity. In this way, the prelearned discriminator makes the network effectively capture the essential expression of the reconstructed data. The proposed approach enables SAE to learn a better feature representation owing to the excellent reconstruction performance. Finally, the feature representation and fault detection performance of VDSAE are verified in two cases. The results show that the average fault detection rates (FDRs) of the multiphase flow facility and the waste-water treatment process (WWTP) can be improved to 72% and 97%, respectively, compared with the other fault detection methods.

A LADRC-based control strategy with performance guarantee for on-board supercapacitor (SC) energy storage systems (ESS) of urban rail traction is proposed in this paper. An outer loop control structure utilizing linear active disturbance rejection control (LADRC) is employed to improve bus voltage tracking performance and alleviate the impact of system disturbances and minor faults that may cause performance degradation. A fuzzy logic-based state of charge (SOC) restriction unit is implemented to prevent overcharging and over-discharging of the SC. Moreover, a hysteresis-comparison-based selecting signal generator is used for switching between charge and discharge modes. Simulation results show that the proposed strategy outperforms the traditional double closed-loop PI control in terms of control performance and provides better guaranteed performance.

Due to the complex static, dynamic, and large-scale characteristics for modern industrial processes, in this article, we propose a double-layer distributed monitoring approach based on multiblock slow feature analysis and multiblock independent component analysis. To this end, the processed dataset is divided into the static and dynamic blocks on the basis of the sequential information of each variable in the first layer. Considering the correlations between the variables in the large-scale processes, the sequential correlation matrices in two blocks are calculated, which serves as the second-layer block division rule. Then, the static and dynamic blocks are further divided into several static and dynamic subblocks in which the variables in each subblock are strongly correlated and in the same state. The slow feature analysis and independent component analysis monitoring models are, respectively, generated for the dynamic and static subblocks. Finally, the monitoring results in each subblock are integrated by Bayesian inference to get the final statistics. The average fault detection rate of the proposed method for the Tennessee Eastman process is 0.842, while those of the other traditional methods are lower than 0.75, which shows the advantages of the proposed method.