ISA transactions最新文献

In recent years, deep learning techniques have been increasingly adopted in soft sensor modeling, with the transformer architecture demonstrating notable advantages not only in natural language processing and image analysis but also in time-series modeling. Autoencoders, known for their ability to learn compact representations of process data, have also been widely applied for feature extraction in soft sensors. However, when dealing with multivariate process data, conventional autoencoder-based models often suffer from underfitting due to persistent reconstruction errors or overfitting when the reconstruction loss converges prematurely. These issues hinder effective feature learning and limit the model's generalization capability in real-world applications. To address these challenges, this paper proposes Resformer, a novel transformer-based architecture that incorporates residual feature compensation. Resformer employs a two-stage autoencoding structure to extract both primary and secondary features and fuses them via a cross-attention mechanism to enhance representation completeness. Time tokens are used as the basic modeling units to capture spatiotemporal dependencies among process variables, which are then mapped to the target quality variable through a dedicated decoding structure. Experimental results on the Tennessee Eastman (TE) process and an industrial alkylation process dataset demonstrate that Resformer, with residual compensation and spatiotemporal feature learning, significantly outperforms recent transformer-based variants while maintaining comparable architectural complexity suitable for practical deployment.

Satellites are vital for communication and navigation, yet delayed or incomplete telemetry data hinder the evaluation of degradation processes and system reliability. As the core of satellite power systems, lithium batteries ensure operational stability. This study focuses on lithium batteries in low Earth orbit satellites and addresses telemetry delay-induced data loss. A data recovery method, termed the FAST Model, based on feature acquisition and short-sequence prediction, is proposed. The method effectively captures degradation trends and capacity fluctuations, including regeneration effects, with minimal data. In the satellite battery dataset with approximately 70 % missing data, the proposed model reduces recovery errors by more than 50 % compared with existing methods. Furthermore, the data recovered by the FAST Model enables more accurate estimation of the remaining useful life of batteries. Under the same prediction framework, the use of FAST-recovered data leads to a reduction of prediction errors by about 5 %-30 %, as evaluated by metrics such as MAE and RMSE, compared with other recovery approaches.

Climate change mitigation necessitates significant reductions in carbon emissions from traditional refining industries. However, accurately attributing renewable bio-feedstock contributions to CO₂ emissions in refinery co-processing remains challenging due to dynamic feedstock variability and complex nonlinear process interactions. Existing static and linear methodologies inadequately address these real-time adaptive demands and intricate nonlinearities. To overcome these shortcomings, we propose a hybrid adaptive modeling framework integrating constrained Recursive Least Squares (RLS) with sparse Generalized Additive Models (GAM), complemented by conformal prediction for uncertainty quantification. Our method adaptively tracks feedstock contributions, ensures physical interpretability through non-negativity constraints. Validated on an industrial dataset of over 86,000 samples, the proposed framework achieves superior predictive accuracy (RMSE: 345.4, R²: 0.950), outperforming 15 baseline methods. More importantly, it delivers interpretable and uncertainty-aware estimates of renewable CO₂ emissions in real time, establishing a practical pathway for transparent and data-driven refinery decarbonization.

The air quality monitoring system (AQMS) has attracted considerable attention due to its environmental significance and impact on human health. AQMS are critical for facilitating early-warning mechanisms to implement policies and protect urban communities. However, existing frameworks rely on physical sensors compromised by degradation, leading to unreliable decision-making. To overcome this limitation, this study introduces a region-wide soft sensor validation using a memory-integrated graph convolutional autoencoder (LSTM-GCN-AE). Results indicate that the relevance-embedded LSTM-GCN-AE outperforms the traditional GCN, achieving a 43.4 % improvement in reconstruction accuracy under precision faults and a 50.2 % enhancement in imputation performance for PM_2.5 sensor, identified through interpretability analysis of relevant nodes in the GCN. Moreover, the proposed framework successfully maintained consistency between predicted and actual environmental conditions, thereby enhancing the reliability of real-time AQMS data, health risk assessment, and early-warning mechanisms for urban air quality management.

In industrial process monitoring, factors such as production schedule changes, equipment aging, and environmental disturbances often lead to shifts in the underlying data distribution. These distributional changes tend to increase false alarm rates and undermine the reliability and adaptability of traditional fault detection methods, thereby compromising the safe and stable operation of industrial facilities. To address these critical challenges, a lifelong fault detection strategy that integrates a Kolmogorov-Arnold Network (KAN) with a novel test-time training (TTT) mechanism is proposed in this paper. Unlike conventional hybrid models, the proposed method introduces a new adaptation framework, in which reconstruction errors dynamically guide selective parameter updates. This allows the model to continuously adapt to distributional shifts without requiring retraining or labeled target data. During online test operation, the model automatically refines its hidden representations using trusted normal samples through a lightweight online update mechanism, thereby improving generalization and robustness under nonstationary conditions. Comprehensive experiments on a widely recognised benchmark dataset from the chemical industry demonstrate that the proposed method significantly outperforms existing state-of-the-art approaches, achieving 92.7 % correct monitoring rate with 0 % false alarm rate under nonstationary conditions.

This paper addresses the co-design problem of event-triggered control, feedback control law, and switching rules for discrete-time switched affine systems under unknown disturbances, from both model-based and data-driven perspectives. The main contribution is a unified framework that yields single LMI formulations applied to both model-based and data-driven settings and guarantees a tunable convergence region under the proposed switching strategies. For the model-based case, sufficient conditions are established for the co-designed control to ensure the practical exponential stabilization of the system. The convergence region can be tuned via parameters to actively compensate for disturbance effects. For the model-free scenario, a data-driven counterpart is developed, featuring a novel switching rule that eliminates the need for an explicit system model and improves computational efficiency. Within this setup, the event-triggered mechanism, switching rule, and control law are jointly synthesized by solving a single LMI, greatly simplifying the implementation. Simulations conducted on a DC-DC boost converter confirm the effectiveness of the proposed method in enhancing resource efficiency while maintaining system performance.

This work addresses the adaptive nonlinear control of a single-stage grid-connected photovoltaic (PV) system, focusing on harmonic current mitigation in highly distorted electrical grids. The proposed interfacing system employs a multilevel inverter topology, which improves power quality compared to its conventional two-level counterpart, particularly in single-stage PV applications. The control scheme employs a dual-loop structure to achieve the following three key objectives: (i) maximum power extraction from the PV arrays, (ii) reduced voltage stress on the switching devices, and (iii) power factor correction (PFC). To enhance performance under realistic grid conditions, the controller incorporates an adaptive observer for real-time estimation of grid voltage and impedance, which are often assumed to be known or directly measurable. The controller's design and analysis are carried out using Lyapunov stability theory. The theoretically predicted performances of the controller are confirmed by numerical simulations performed in Matlab/SimPowerSystems environment and in a Processor-In-the-Loop (PIL) implementation.

This study proposes a novel methodology to develop and manage data-driven models for ship machinery Prognostics and Health Management (PHM). A four-stroke marine engine is investigated considering exhaust valve wear degradation. Simulated datasets are generated using a physics-based digital twin integrated with stochastic degradation models. Health indicators (HI) construction and forecast sub-models are developed, based on Multi-Layer Perceptron and Bayesian Neural Networks, respectively. Data-driven model management employs error and uncertainty metrics for deciding re-training of HI forecast sub-models, resulting in R² increases from 0.24 to 0.89 and from 0.26 to 0.94 in Cases 1 and 2, respectively. This is the first study that integrates thermodynamic models with stochastic degradation models to develop marine engine digital twins, while also introducing data-driven model management, thus contributing to the PHM system adoption by the maritime industry.

As equipment ages, the distortion of relevant parameters leads to increasingly severe degradation in control performance. This paper proposes a novel aging-free estimationless sliding mode control strategy for interior permanent magnet synchronous motor (IPMSM) in low-carbon transportation systems. Firstly, a time-varying disturbance (TVD)-based aging model is proposed. The TVD integrates multi-stage dynamic disturbance transition models for various aging parameters of the IPMSM. Then, a multi-condition correction (MCC)-based sliding mode current control method is proposed. The MCC associates the sliding surface parameters with the temporal factor and integrates the correction functions in the reaching law. Finally, the stability conditions are derived based on the Lyapunov function. The proposed strategy is validated by the hardware-in-the-loop (HIL)-based platform. The test results show that the proposed strategy can reduce the current control error of the aging motor, thereby reducing system power losses and significantly enhancing the operational efficiency of the aging IPMSM for the low-carbon transportation system.

In industrial data stream environments, the acquisition of real quality variables is challenging and subject to delay, posing significant obstacles to effective updates of adaptive soft sensors. To this end, this paper proposes a novel framework, Adaptive Soft Sensor for Label Delay (ASSLD). An adaptive multilevel regression model, weighting and integrating outcomes from layers at different depths, is designed to enhance online adaptability. To efficiently reuse historical labeled data, a diverse database is maintained online, from which similar samples are selected and weighted. Moreover, unlabeled samples within the delay time are utilized to help accommodate recent data. The experimental results on the sulfur recovery unit dataset and polyester dataset show the effectiveness of ASSLD in handling label delay, with accuracy improvements of more than 12 % over baselines.