Mahdi Aliyari Shoorehdeli

Faults and operational disturbances in heat recovery steam generators (HRSGs), such as valve leakage, present significant challenges, disrupting steam temperature regulation and potentially causing efficiency losses, safety risks, and unit shutdowns. Traditional PI controllers often struggle due to inherent system delays, nonlinear dynamics, and static gain limitations. This paper introduces a fault‐tolerant temperature control framework by integrating a PI plus feedforward control strategy with physics‐informed neural networks (PINNs). The feedforward component anticipates disturbances, preemptively adjusting control actions, while the PINN adaptively tunes control gains in real‐time, embedding thermodynamic constraints to manage varying operating conditions and valve leakage faults. A Lyapunov‐based stability analysis confirms the asymptotic convergence of temperature tracking errors under bounded leakage conditions. Simulation results using operational data from the Pareh‐Sar Combined Cycle Power Plant demonstrate significantly improved response times, reduced temperature deviations, enhanced fault resilience, and smooth gain adjustments. The proposed adaptive, data‐driven methodology shows strong potential for industrial deployment, ensuring reliable operation, autonomous fault recovery, and enhanced performance in HRSG systems.

State estimation, as the core of the Energy Management System (EMS), plays a vital role in ensuring the secure and efficient operation of modern power systems. However, false data injection attacks (FDIAs) remain a major threat by evading conventional detection schemes and undermining grid resilience. To address this challenge, this study introduces an unsupervised detection framework based on dynamic State Space Models (SSMs) for AC state estimation. The method leverages a Variational Recurrent Neural Network (VRNN) trained only on normal data, eliminating the need for labeled attacks. By modeling sequential latent states with time-evolving priors, it captures long-range temporal dependencies and improves sensitivity to stealthy FDIAs. Moreover, its probabilistic generative nature enables robust anomaly scoring under noise and uncertainty, while aligning the latent space with system states enforces physical interpretability. Extensive case studies on the IEEE 118-bus system validate the effectiveness of the proposed framework, demonstrating superior detection performance with high accuracy and low false alarm rates, making it suitable for practical deployment in real-world power systems.

The object segmentation mask’s observation sequence shows the trend of changes in the object’s observable geometric form, and predicting them may assist in solving various difficulties in multi-object tracking and segmentation (MOTS). With this aim, we propose the entangled appearance and motion structures network (EAMSN), which can predict the object segmentation mask at the pixel level by integrating VAE and LSTM. Regardless of the surroundings, each EAMSN keeps complete knowledge about the sequence of probable changes in the seen map of the object and its related dynamics. It suggests that EAMSN understands the item meaningfully and is not reliant on instructive examples. As a result, we propose a novel MOTS algorithm. By employing different EAMSNs for each kind of item and training them offline, ambiguities in the segmentation mask discovered for that object may be recovered, and precise estimation of the real boundaries of the object at each step. We analyze our tracker using the KITTI MOTS and MOTS challenges datasets, which comprise car and pedestrian objects, to illustrate the usefulness of the suggested technique. As a result, we developed distinct EAMSNs for cars and pedestrians, trained using the MODELNET40 and Human3.6 M datasets, respectively. The discrepancy between training and testing data demonstrates that EAMSN is not dependent on training data. Finally, we compared our strategy to a variety of other ways. Compared to the published findings, our technique gets the best overall performance.

False and nuisance alarms in industrial fault detection systems are often triggered by uncertainty, causing normal process variable fluctuations to be erroneously identified as faults. This paper introduces a novel encoder-based residual design that effectively decouples the stochastic and deterministic components of process variables without imposing detection delay. The proposed model employs two distinct encoders to factorize the latent space into two orthogonal spaces: one for the deterministic part and the other for the stochastic part. To ensure the identifiability of the desired spaces, constraints are applied during training. The deterministic space is constrained to be smooth to guarantee determinism, while the stochastic space is required to resemble standard Gaussian noise. Additionally, a decorrelation term enforces the independence of the learned representations. The efficacy of this approach is demonstrated through numerical examples and its application to the Tennessee Eastman process, highlighting its potential for robust fault detection. By focusing decision logic solely on deterministic factors, the proposed model significantly enhances prediction quality while achieving nearly zero false alarms and missed detections, paving the way for improved operational safety and integrity in industrial environments.

In industrial and real‐world systems, recognising errors and adopting the best approaches are gaining relevance. The authors’ goal is to identify artificial intelligence apps that provide the most reliable and valuable data‐based fault detection techniques. A system for fault identification is presented based on reinforcement learning and proximal policy optimisation (PPO). Due to the lack of fault data, one of the key issues with the standard policy is its inability to recognise fault classes; this issue was resolved by modifying the cost equation. Using improved PPO, the authors can improve performance, address data imbalances, and forecast possible failures more accurately. The approach utilises policy‐based optimisation, which offers several advantages. Firstly, it directly optimises the advantage quantity, and secondly, it ensures the stability of function approximation. The authors have studied two different turbines in Iran and collected data from them separately when a fault occurred. To demonstrate the efficiency of our algorithm, the authors have included the third and fourth datasets as cyber attack benchmarks. When the authors’ proposed policy is adopted, all evaluation metrics will improve by 3%–4% as compared to the previous policy in the first benchmark, between 20% and 55% in the second benchmark, between 6% and 14% in the third benchmark, and between 4% and 5% in the fourth benchmark, with improved results and prediction times compared to existing studies.

To gain access to networks, various intrusion attack types have been developed and enhanced. The increasing importance of computer networks in daily life is a result of our growing dependence on them. Given this, it is glaringly obvious that algorithmic tools with strong detection performance and dependability are required for a variety of attack types. The objective is to develop a system for intrusion detection based on deep reinforcement learning. On the basis of the Markov decision procedure, the developed system can construct patterns appropriate for classification purposes based on extensive amounts of informative records. Deep Q‐Learning (DQL), Soft DQL, Double DQL, and Soft double DQL are examined from two perspectives. An evaluation of the authors’ methods using UNSW‐NB15 data demonstrates their superiority regarding accuracy, precision, recall, and F1 score. The validity of the model trained on the UNSW‐NB15 dataset was also checked using the BoT‐IoT and ToN‐IoT datasets, yielding competitive results.

This letter studies the design of state and output feedback control for a class of bilinear systems aimed at achieving global exponential tracking of (admissible, differentiable) time-varying trajectories. We demonstrate that a persistency of excitation (PE) assumption on the desired trajectories is sufficient to achieve the control objective via a simple state feedback proportional (P) controller. The controller, in conjunction with a globally stable Kalman-like observer, is further developed into a certainty-equivalent output feedback version, maintaining stability under a detectability condition that depends on the behavior of the desired control effort. The proposed algorithm is applied to control a lossless single-phase grid-connected PV inverter with an unmeasurable output current.