Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Sensor Data-Driven Fault Diagnosis Techniques

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Fault Diagnosis & Sensors".

Deadline for manuscript submissions: closed (20 November 2025) | Viewed by 8149

Share This Special Issue

Special Issue Editor

Prof. Dr. Jang Woo Kwon

E-Mail Website
Guest Editor

Department of Computer Engineering, Inha University, Inchon, Republic of Korea
Interests: computer & information technology; fault diagnosis

Special Issue Information

Dear Colleagues,

Recent advancements in sensor technology and data analytics have significantly improved the accuracy, reliability, and responsiveness of fault diagnosis systems across various domains, including manufacturing, transportation, healthcare, energy, and smart infrastructure. As sensors become increasingly ubiquitous and capable of generating high-resolution, real-time data, sensor-driven approaches are emerging as a core enabler of intelligent fault detection, identification, and prediction.

This Special Issue is highly relevant to the scope of Sensors, as it focuses on the pivotal role of sensor data in developing advanced fault diagnosis techniques. We invite high-quality submissions that present innovative methodologies, algorithms, and applications leveraging sensor data for fault diagnosis. Contributions may address theoretical foundations, algorithmic developments, data-driven modeling, and practical implementations in real-world systems.

This Special Issue welcomes innovative research on sensor data utilization, from advanced sensing hardware design to interpretable AI-driven analytics. Potential topics include but are not limited to:

Multimodal sensor data fusion for cross-domain diagnosis
Predictive maintenance with distributed sensor networks
Sensor data transmission for fault diagnosis
Self-supervised learning from unlabeled sensor data
Edge-cloud collaborative diagnosis frameworks

Prof. Dr. Jang Woo Kwon
Guest Editor

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-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors 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 2600 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 diagnosis
intelligent monitoring
predictive maintenance
sensor data analytics
machine learning for fault detection

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 (6 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

20 pages, 7967 KB

Open AccessArticle

HIPER-CHAD: Hybrid Integrated Prediction-Error Reconstruction-Based Anomaly Detection for Multivariate Indoor Environmental Time-Series Data

by Vandha Pradwiyasma Widartha and Chang Soo Kim

Sensors 2026, 26(1), 171; https://doi.org/10.3390/s26010171 - 26 Dec 2025

Viewed by 399

Abstract

This study introduces the Hybrid Integrated Prediction-Error Reconstruction-based Anomaly Detection (HIPER-CHAD) model, which addresses the challenge of reliably detecting subtle anomalies in noisy multivariate indoor environmental time-series data. The main objective is to separate temporal modeling of normal behavior from probabilistic modeling of prediction uncertainty, ensuring that the anomaly score becomes robust to stochastic fluctuations while remaining sensitive to truly abnormal events. The HIPER-CHAD architecture first employs a Long Short-Term Memory (LSTM) network to forecast the next time step’s sensor readings, subsequently forming a residual error vector that captures deviations from the expected temporal pattern. A Variational Autoencoder (VAE) is then trained on these residual vectors rather than on the raw sensor data to learn the distribution of normal prediction errors and quantify their probabilistic unicity. The final anomaly score integrates the VAE’s reconstruction error with its Kullback–Leibler (KL) divergence, yielding a statistically grounded measure that jointly reflects the magnitude and distributional abnormality of the residual. The proposed model is evaluated on a real-world multivariate indoor environmental dataset and compared against eight traditional machine learning and deep learning baselines using a synthetic ground truth generated by a 99th percentile-based criterion. HIPER-CHAD achieves an F1-score of 0.8571, outperforming the next best model, the LSTM Autoencoder (F1 = 0.8095), while maintaining perfect recall. Furthermore, a time-step sensitivity analysis demonstrates that a 20-step window yields an optimal F1-score of 0.884, indicating that the proposed residual-based hybrid design provides a reliable and accurate framework for anomaly detection in complex multivariate time-series data. Full article

(This article belongs to the Special Issue Sensor Data-Driven Fault Diagnosis Techniques)

► Show Figures

Figure 1

29 pages, 3596 KB

Open AccessArticle

MOSOF with NDCI: A Cross-Subsystem Evaluation of an Aircraft for an Airline Case Scenario

by Burak Suslu, Fakhre Ali and Ian K. Jennions

Sensors 2026, 26(1), 160; https://doi.org/10.3390/s26010160 - 25 Dec 2025

Viewed by 464

Abstract

Designing cost-effective, reliable diagnostic sensor suites for complex assets remains challenging due to conflicting objectives across stakeholders. A holistic framework that integrates the Normalised Diagnostic Contribution Index (NDCI)—which scores sensors by separation power, severity sensitivity, and uniqueness—with a Multi-Objective Sensor Optimisation Framework (MOSOF) is presented. Using a high-fidelity virtual aircraft model coupling engine, fuel, electrical power system (EPS), and environmental control system (ECS), NDCI against minimum Redundancy-maximum Relevance (mRMR) is benchmarked under a rigorous nested cross-validation protocol. Across subsystems, NDCI yields more compact suites and higher diagnostic accuracy, notably for engine (88.6% vs. 69.0%) and ECS (67.7% vs. 52.0%). Then, a multi-objective optimisation reflecting an airline use-case (diagnostic performance, cost, reliability, and benefit-to-cost) is executed, identifying a practical Pareto-optimal ‘knee’ solution comprising 12–14 sensors. The recommended suite delivers a normalised performance of ≈0.69 at ≈USD36k with ≈145 kh MTBF, balancing the cross-subsystem information value with implementation constraints. The NDCI-MOSOF workflow provides a transparent, reproducible pathway from raw multi-sensor data to stakeholder-aware design decisions, and constitutes transferable evidence for model-based safety and certification processes in Integrated Vehicle Health Management (IVHM). The limitations (simulation bias, cost/MTBF estimates), validation on rigs or in-service fleets, and extensions to prognostics objectives are discussed. Full article

(This article belongs to the Special Issue Sensor Data-Driven Fault Diagnosis Techniques)

► Show Figures

Figure 1

25 pages, 49210 KB

Open AccessArticle

Eccentricity Fault Diagnosis System in Three-Phase Permanent Magnet Synchronous Motor (PMSM) Based on the Deep Learning Approach

by Kenny Sau Kang Chu, Kuew Wai Chew, Yoong Choon Chang, Stella Morris, Yap Hoon and Chen Chen

Sensors 2025, 25(24), 7416; https://doi.org/10.3390/s25247416 - 5 Dec 2025

Viewed by 561

Abstract

Motor eccentricity faults, stemming from the misalignment of the rotor’s center and pivot point, lead to significant vibrations and noise, compromising motor reliability. This study emphasizes the need for an efficient diagnostic system to enable early detection and correction of these faults. Our research proposes a novel Eccentricity Fault Diagnosis Network (E-FDNet), designed for integration into a Motor Eccentricity Fault Diagnosis System (MEFDS), utilizing neural networks for detection. Evaluation tests reveal that a hybrid Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) architecture is ideal as the internal neural network within the E-FDNet. Key contributions of this research include (1) E-FDNet that stabilizes transition predictions among SEF/DEF/MEF; (2) a steady-state characteristic normalization (SSCN) improving feature consistency under dynamic responses; (3) an integrated physics–FEM–experiment pipeline for controlled analysis and validation; (4) approximately 98.86% accuracy/F1 outperforming classical and deep baselines; and (5) a non-invasive, current-only sensing design suited for deployment. Full article

(This article belongs to the Special Issue Sensor Data-Driven Fault Diagnosis Techniques)

► Show Figures

Figure 1

17 pages, 4091 KB

Open AccessArticle

Novel Physics-Informed Indicators for Leak Detection in Water Supply Pipelines

by Yi Zhang and Suzhen Li

Sensors 2025, 25(16), 5069; https://doi.org/10.3390/s25165069 - 15 Aug 2025

Viewed by 1224

Abstract

Accurate monitoring of leakage in urban water supply pipelines is crucial for ensuring the safety of residential water usage. This study proposes a robust physical indicator for identifying leaks in urban water pipelines, grounded in the physical background of leakage noise sources. An integral form of the leakage source noise power spectral density is established, and a rigorous theoretical analysis leads to the development of an effective physical indicator. This indicator addresses the limitation of existing leakage detection methods that overly rely on data-driven features. Experiments were conducted to validate the effectiveness and robustness of the proposed indicator. The results show that the leakage detection models trained with physical features achieved recognition accuracies of 99.89% for Support Vector Machine (SVM) and 99.97% for eXtreme Gradient Boosting (XGBoost) in the experiments. In the field test conducted on an in-service water supply pipeline with a total length of 701 m, the recognition accuracies for SVM and XGBoost were 97.92% and 99.31%, respectively. Full article

(This article belongs to the Special Issue Sensor Data-Driven Fault Diagnosis Techniques)

► Show Figures

Figure 1

25 pages, 3827 KB

Open AccessArticle

Source-Free Domain Adaptation Framework for Rotary Machine Fault Diagnosis

by Hoejun Jeong, Seungha Kim, Donghyun Seo and Jangwoo Kwon

Sensors 2025, 25(14), 4383; https://doi.org/10.3390/s25144383 - 13 Jul 2025

Cited by 4 | Viewed by 3109

Abstract

Intelligent fault diagnosis for rotary machinery often suffers performance degradation under domain shifts between training and deployment environments. To address this, we propose a robust fault diagnosis framework incorporating three key components: (1) an order-frequency-based preprocessing method to normalize rotational variations, (2) a U-Net variational autoencoder (U-NetVAE) to enhance adaptation through reconstruction learning, and (3) a test-time training (TTT) strategy enabling unsupervised target domain adaptation without access to source data. Since existing works rarely evaluate under true domain shift conditions, we first construct a unified cross-domain benchmark by integrating four public datasets with consistent class and sensor settings. The experimental results show that our method outperforms conventional machine learning and deep learning models in both F1-score and recall across domains. Notably, our approach maintains an F1-score of 0.47 and recall of 0.51 in the target domain, outperforming others under identical conditions. Ablation studies further confirm the contribution of each component to adaptation performance. This study highlights the effectiveness of combining mechanical priors, self-supervised learning, and lightweight adaptation strategies for robust fault diagnosis in the practical domain. Full article

(This article belongs to the Special Issue Sensor Data-Driven Fault Diagnosis Techniques)

► Show Figures

Figure 1

23 pages, 6050 KB

Open AccessArticle

A Digital Signal Processing-Based Multi-Channel Acoustic Emission Acquisition System with a Simplified Analog Front-End

by Gan Tang

Sensors 2025, 25(10), 3206; https://doi.org/10.3390/s25103206 - 20 May 2025

Viewed by 1847

Abstract

Advanced multi-channel acoustic emission (AE) monitoring systems often rely on complex and costly architectures, especially those requiring custom FPGA-based hardware. In this work, we present a digital signal processing (DSP)-based approach to high-performance AE acquisition, implemented using a simplified analog front-end (AFE) and a commercially available synchronous data acquisition (DAQ) card (NI USB-6356). This design eliminates the need for specialized FPGA development, improving accessibility and reducing system complexity. A key feature of the system is the replacement of traditional analog filters with a software-defined digital band-pass filtering module implemented in LabVIEW. This allows for real-time or post-processing filtering with adjustable parameters, enhancing flexibility in data analysis. The system supports 8-channel synchronous sampling at 1.25 MS/s, and performance evaluations demonstrate a dynamic range of 79.22 dB and a signal-to-noise ratio (SNR) of 85.39 dB. These results confirm the system’s ability to maintain high fidelity in AE signal acquisition without the need for dedicated hardware filtering or custom DAQ hardware. The proposed method offers a practical and validated alternative for multi-channel AE monitoring, with potential applications in structural health monitoring, materials testing, and other engineering domains. Full article

(This article belongs to the Special Issue Sensor Data-Driven Fault Diagnosis Techniques)

► Show Figures

Journal Menu

Journal Browser

Sensor Data-Driven Fault Diagnosis Techniques

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (6 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI