Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.7
3.4
Journals
Processes
Special Issues
Fault Detection and Identification in Process Systems
share announcement

Fault Detection and Identification in Process Systems

A Special Issue of Processes (ISSN 2227-9717) belonging to the section "Automation Control Systems".

Deadline for manuscript submissions: 15 February 2027 | Viewed by 3035

Editors

Dr. Siwei Lou

E-Mail Website
Guest Editor
College of Control Science and Engineering, Zhejiang University, Hangzhou 310000, China
Interests: AI-enabled industrial data analytics; signal processing; automation control; smart manufacturing; process monitoring; blast furnace ironmaking process
Special Issues, Collections and Topics in MDPI journals
Dr. Hu Qiao

E-Mail Website
Guest Editor
School of Mechatronic Engineering, Xi’an Technological University, Xi’an 710021, China
Interests: digital design; digital manufacturing; intelligent decision-making and optimization

Special Issue Information

Dear Colleagues,

Process systems, encompassing sectors such as metallurgy and petrochemicals, constitute a foundational pillar of the world economy by virtue of their continuous, large-scale production of primary materials. The ongoing centralization and scaling of modern industrial operations have rendered automated systems and devices indispensable for ensuring safety, stability, and efficiency in production environments. In recent years, the accelerated advancement of artificial intelligence and allied technologies including machine learning, large-language models, the Industrial Internet, digital twins, and embodied intelligence has catalyzed a profound transformation toward intelligent operation and maintenance within these industries. At the information systems level, architectural paradigms are evolving from conventional knowledge-driven frameworks toward trusted data-driven methodologies, thereby enabling precise modeling, real-time monitoring, and diagnostic analysis of energy and material flows. Concurrently, execution units in physical systems are increasingly oriented toward safety-assured operation and maintenance, progressively coalescing into an integrated cyber–physical ecosystem in which information systems serve as the intelligent decision-making core and physical systems act as reliable execution agents. This convergence establishes a robust technological foundation for achieving enhanced operational safety across process industries.

This Special Issue on “Fault Detection and Identification in Process Systems” seeks high-quality works focusing on both academia and industry that advance scholarly understanding and engineering practice. Interdisciplinary research and collaborations spanning industry, academia, and research institutions are especially encouraged. The Special Issue aims to address the full technological spectrum, from control-theoretic foundations and intelligent algorithms to the implementation and engineering demonstration of automated and intelligent systems, with the objective of illustrating the scalability and practical applicability of proposed solutions within the framework of safety-critical process systems. Topics include, but are not limited to, the following:

  • Theory of Trusted Data-Driven Dynamic Modeling and Fault Characterization for Process Systems;
  • Safety-Domain Modeling and Anomaly Propagation Mechanisms in Cyber-Physical Process Systems;
  • Early Detection and Identification of Incipient and Intermittent Faults in Process Systems;
  • Intelligent Fault Detection and Diagnosis for Non-Gaussian and Non-Stationary Process Data;
  • Real-Time Health Assessment of Process Equipment via Digital Twins and the Industrial Internet;
  • Application of Large-Scale Pretrained Models in Process Monitoring and Fault Knowledge Discovery;
  • Safety-Constrained Fault-Tolerant Control and Autonomous Decision-Making System Design;
  • Embodied Intelligence for Process Inspection and Fault Localization in Hazardous Environments;
  • Interpretability, Robustness, and Safety Verification of Intelligent Operation and Maintenance Systems;
  • Plant-Wide Cooperative Fault Prognostics and Intelligent Maintenance Scheduling Optimization;
  • Comprehensive Application of Large and Small Models in Process Optimization;
  • Application of Multi-Sensors in Fault Detection and Identification;
  • Digital Twins and Machine Learning Technology for Fault Detection, Decision-making, and Control;
  • System Fault Identification and Rapid Response;
  • Data-Driven Prediction, Identification, and Impact Assessment of System Faults.

Dr. Siwei Lou
Dr. Hu Qiao
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Processes is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • fault detection and diagnosis
  • process industries
  • trusted data-driven methods
  • intelligent operation and maintenance
  • digital twins
  • industrial artificial intelligence
  • predictive maintenance
  • explainable AI

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

28 pages, 1502 KB  
Article
Run-Level Fault Detection and SHAP-Based Diagnosis of Persistent Classification Difficulty in the Tennessee Eastman Process
by Nuri Furkan Koçak, Ali Saygın, Fuat Türk and Ahmet Mehmet Karadeniz
Processes 2026, 14(16), 2569; https://doi.org/10.3390/pr14162569 - 11 Aug 2026
Viewed by 547
Abstract
Reliable fault detection in nonlinear process systems requires both accurate classification and interpretable analysis of faults with weak or near-normal signatures. This study develops an explainable, data-driven, and temporally informed multiclass framework for the Tennessee Eastman Process (TEP), retaining all 21 operating conditions [...] Read more.
Reliable fault detection in nonlinear process systems requires both accurate classification and interpretable analysis of faults with weak or near-normal signatures. This study develops an explainable, data-driven, and temporally informed multiclass framework for the Tennessee Eastman Process (TEP), retaining all 21 operating conditions (20 fault types and the normal operating condition). Six sliding-window statistics were extracted from 52 process variables and classified using Extreme Gradient Boosting (XGBoost). Performance was evaluated at both sample and run levels through fault-specific window analysis, an a priori validation-driven hierarchical decomposition, SHapley Additive exPlanations (SHAP), a Relative Sensitivity Index (RSI) based on detection-delay sensitivity, and computational benchmarking. Aggregating sample-level predictions (macro F1 = 0.8823) into run-level decisions via majority voting improved performance substantially (macro F1 = 0.9515). Across five seeded repetitions, the mean run-level macro F1-score was 0.9522±0.0035 (95% CI: ±0.0044). Under the primary evaluation, 18 of 21 classes achieved F1 ≥0.97. Fault 3 benefited strongly from extended temporal context, whereas Normal operation, Fault 9, and Fault 15 retained a structured but asymmetric confusion pattern dominated by Normal–Fault 9 errors. SHAP identified model-specific attribution patterns associated mainly with cooling-water-related variability features, while RSI indicated greater prediction-stream sensitivity for the historically difficult faults. Feature extraction and inference required approximately 6.2 ms on CPU and 35.3 ms on GPU, negligible relative to the 180 s sampling interval. These findings indicate that temporal context, run-level aggregation, and explainability can jointly support accurate data-driven fault diagnosis while revealing persistent fault-specific ambiguity. Full article
(This article belongs to the Special Issue Fault Detection and Identification in Process Systems)
►▼ Show Figures

Figure 1

18 pages, 25874 KB  
Article
Axial Flow Check Valve Flow-Field Simulation and Failure Analysis at the Compressor Outlet of a Gas Compressor Station
by Ming Zhang, Wei Zhong, Guotao Nie and Xu Zhang
Processes 2026, 14(15), 2407; https://doi.org/10.3390/pr14152407 - 26 Jul 2026
Viewed by 664
Abstract
In long-distance natural gas transmission, installing an axial flow check valve at the compressor outlet of a compressor station helps prevent backflow. Failure of this valve can cause compressor reverse rotation, which disrupts gas delivery. This study models and simulates the steady-state flow [...] Read more.
In long-distance natural gas transmission, installing an axial flow check valve at the compressor outlet of a compressor station helps prevent backflow. Failure of this valve can cause compressor reverse rotation, which disrupts gas delivery. This study models and simulates the steady-state flow field at 100% valve opening and the transient flow features during valve opening and closing. In addition, a failed axial-flow check valve from a natural gas compressor station was disassembled, and initial observations of wear and deformation were used to verify the model. The results show that the maximum fluid velocity reaches 18.9 m/s at 100% valve opening, with a distinct vortex region forming in the throttling passage between the valve seat and disk. During valve opening, the inlet–outlet pressure difference decreases from 0.35 MPa at 0.001 s to 0.20 MPa at 0.080 s. At 60% relative opening, the maximum amplitude of the transient hydrodynamic force fluctuation reaches 662 N. During closure under a pressure difference of 300 kPa, the maximum disk velocity reaches 12.9 m/s. These transient flow and force characteristics, considered together with the wear observed on the guide sleeve and disk, provide insight into the delayed reseating of the valve. Full article
(This article belongs to the Special Issue Fault Detection and Identification in Process Systems)
►▼ Show Figures

Figure 1

24 pages, 9694 KB  
Article
Traceable Suppression of Vehicle-Induced Dust in Industrial Sheds Through Dynamic–Static Feature Enhancement
by Kun Chen, Xujie Zhang, Yan Shao, Hang Xiao, Di Zheng, Zijie Jiang and Siwei Lou
Processes 2026, 14(6), 952; https://doi.org/10.3390/pr14060952 - 17 Mar 2026
Viewed by 567
Abstract
Existing intelligent monitoring methods are limited by insufficient training samples and target-feature degradation in complex environments. To address these issues, an industrial visual inspection scheme with dual verification is proposed for material sheds. The scheme integrates sample enhancement preprocessing based on a Dynamic [...] Read more.
Existing intelligent monitoring methods are limited by insufficient training samples and target-feature degradation in complex environments. To address these issues, an industrial visual inspection scheme with dual verification is proposed for material sheds. The scheme integrates sample enhancement preprocessing based on a Dynamic Enhanced Generative Adversarial Network (DEGAN) with an Attention-Enhanced YOLO-SLOWFAST (AE-YOLO-SLOWFAST) model for target and behavior detection, enabling feature enhancement, real-time dust monitoring, and timely dust suppression. A dynamic enhancement module is first introduced into a GAN, creating DEGAN to generate high-quality samples and augment the training dataset. An AE-YOLO model is then developed to improve static feature extraction under low illumination and enhance small-target detection. The objective function is refined to improve recognition of hard-to-distinguish samples during training. AE-YOLO is combined with SLOWFAST to recognize vehicle behaviors. Dual verification is performed using dust and vehicle detection results together with action recognition outputs, enabling precise control of dust suppression equipment for targeted water mist spraying. The improved AE-YOLO model achieves an mAP@50 of 94.4%. The proposed method delivers a vehicle–dust association matching accuracy of up to 97.2%, which enables all-weather, intelligent, traceable dust suppression in material sheds, reduces false recognition interference, and ensures timely suppression in areas where vehicles are operating. Full article
(This article belongs to the Special Issue Fault Detection and Identification in Process Systems)
►▼ Show Figures

Figure 1

22 pages, 29429 KB  
Article
FCN for Metallography: An Alternative to U-Net on the MetalDAM Dataset
by Alberto José Alvares
Processes 2026, 14(4), 633; https://doi.org/10.3390/pr14040633 - 12 Feb 2026
Viewed by 784
Abstract
Semantic segmentation of metallographic micrographs is a key task for quantitative microstructural analysis in additive manufacturing, yet it remains challenging due to phase heterogeneity, complex morphologies, and the scarcity of annotated data. The MetalDAM dataset, composed of 42 labeled scanning electron microscopy images [...] Read more.
Semantic segmentation of metallographic micrographs is a key task for quantitative microstructural analysis in additive manufacturing, yet it remains challenging due to phase heterogeneity, complex morphologies, and the scarcity of annotated data. The MetalDAM dataset, composed of 42 labeled scanning electron microscopy images of steel microstructures, has been widely adopted as a benchmark, with U-Net commonly reported as the strongest supervised baseline. Nevertheless, the encoder–decoder structure of U-Net imposes architectural constraints that hinder the precise delineation of heterogeneous and irregular phase boundaries under severe data limitations. To address this limitation, this paper investigates a Fully Convolutional Network (FCN)-based architecture as an alternative approach for semantic segmentation on the MetalDAM dataset. The FCN is trained and evaluated under the same experimental protocol as the U-Net baseline, enabling a direct and fair comparison. Performance is assessed using multiple evaluation metrics, including Intersection over Union (IoU), precision, recall, and mean Average Precision at an IoU threshold of 0.5. The results show that the FCN achieves comparable overall IoU values (0.75) while delivering substantial improvements at the class level, particularly for minority and morphologically complex phases, with gains of up to 25–30% in class-specific IoU. Additional metrics confirm enhanced robustness, with consistently higher precision, recall, and mAP@0.5 values. These findings demonstrate that FCN-based architectures constitute a competitive and robust alternative to U-Net for metallographic segmentation in additive manufacturing scenarios characterized by limited annotated data. Full article
(This article belongs to the Special Issue Fault Detection and Identification in Process Systems)
►▼ Show Figures

Graphical abstract

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop