Search Results (170)

Prognostic and Health Management (PHM) strategies are gaining increasingly more traction in almost every field of engineering, offering stakeholders advanced capabilities in system monitoring, anomaly detection, and predictive maintenance. Primary flight control actuators are safety-critical elements within aircraft flight control systems (FCSs), and currently, they are mainly based on Electro-Hydraulic Actuators (EHAs) or Electro-Hydrostatic Actuators (EHSAs). Despite the widespread diffusion of PHM methodologies, the application of these technologies for EHAs is still somewhat limited, and the available information is often restricted to the industrial sector. To fill this gap, this paper provides an in-depth analysis of state-of-the-art EHA PHM strategies for aerospace applications, as well as their limitations and further developments through a Systematic Literature Review (SLR). An objective and clear methodology, combined with the use of attractive and informative graphics, guides the reader towards a thorough investigation of the state of the art, as well as the challenges in the field that limit a wider implementation. It is deemed that the information presented in this review will be useful for new researchers and industry engineers as it provides indications for conducting research in this specific and still not very investigated sector. Full article

Testicular germ cell tumors (TGCTs) are the most common malignancies affecting young men between the ages of 14 and 44, accounting for about 95% of all testicular cancers. Despite being relatively rare compared to other cancers (~3.0 cases per 100,000 population, with high worldwide variability), TGCTs’ incidence is increasing, particularly in industrialized countries. The initial phase of TGCT diagnosis is performed by detecting in the blood the presence of three proteins, i.e., alpha-fetoprotein (AFP), lactate dehydrogenase (LDH), and human chorionic gonadotropin (hCG). Despite these proteins being defined as markers of TGCTs, they present limitations in specificity. Indeed, AFP is not elevated in pure seminomas; LDH serum levels can be elevated in other conditions, such as liver disease or tissue damage, and hCG can be elevated in both seminomas and non-seminomas, reducing its ability to differentiate between tumor types. However, the existence of hCG variants, characterized by distinct glycosylation profiles that are differentially expressed in TGCT types and subtypes, may increase the diagnostic and prognostic potential of this hormone. Furthermore, emerging molecular biomarkers, including miRNAs and tumor cells-related epigenetic status, may offer new promising alternatives to improve diagnostic accuracy. Nonetheless, standardized diagnostic protocols still need to be implemented. Finally, understanding the biological roles of hCG isoforms and their “canonical” (e.g., LHCGR) and “non-canonical” (e.g., TGF-βR) receptor interactions may help in understanding tumor biology and therapeutic targeting. Full article

Rotating machinery is essential in various industrial fields, and growing demands for high performance under harsh operating conditions have heightened interest in fault diagnosis and prognostic technologies. However, a major challenge in fault diagnosis research lies in the scarcity of data, primarily due to the inability to deliberately introduce faults into machines during actual operation. In this study, a physical model is proposed to realistically simulate the system behavior of a ship’s turbo-rotating machinery by coupling the torsional and lateral vibrations of the rotor. While previous studies employed simplified single-shaft models, the proposed model adopted gear mesh interactions to reflect the coupling behavior between shafts. Furthermore, the time-domain response of the system is analyzed through state-space transformation. The proposed model was applied to simulate imbalance and gear teeth damage conditions that may occur in marine turbo-rotating systems and the results were compared with those under normal operating conditions. The analysis confirmed that the model effectively reproduces fault-induced dynamic characteristics. By enabling rapid implementation of various fault conditions and efficient data acquisition data, the proposed model is expected to contribute to enhancing the reliability of fault diagnosis and prognostic research. Full article

As industries become increasingly dependent on cyber-physical systems (CPSs), failures within these systems can cause significant operational disruptions, underscoring the critical need for effective Prognostics and Health Management (PHM). The large volume of data generated by CPSs has made deep learning (DL) methods an attractive solution; however, imbalanced datasets and the limited availability of fault-labeled data continue to hinder their effective deployment in real-world applications. To address these challenges, this paper proposes a transfer learning approach using a pre-trained transformer architecture to enhance fault detection performance in CPSs. A streamlined transformer model is first pre-trained on a large-scale source dataset and then fine-tuned end-to-end on a smaller dataset with a differing data distribution. This approach enables the transfer of diagnostic knowledge from controlled laboratory environments to real-world operational settings, effectively addressing the domain shift challenge commonly encountered in industrial CPSs. To evaluate the effectiveness of the proposed method, extensive experiments are conducted on publicly available datasets generated from a laboratory-scale replica of a modern industrial water purification facility. The results show that the model achieves an average F1-score of 93.38% under K-fold cross-validation, outperforming baseline models such as CNN and LSTM architectures, and demonstrating the practicality of applying transformer-based transfer learning in industrial settings with limited fault data. To enhance transparency and better understand the model’s decision process, SHAP is applied for explainable AI (XAI). Full article

With the advancement of industrial manufacturing and the shift toward high automation, machines have increasingly taken over many production tasks, greatly improving efficiency and reducing human labor. However, this also introduces new challenges, particularly the inability of machines to autonomously detect and diagnose faults. Such undetected issues may cause unexpected breakdowns, interrupting critical operations, leading to economic losses and potential safety hazards. To address this, the present study proposes a novel hybrid deep learning framework that integrates Convolutional Neural Networks (CNN) for feature extraction with Transformer architecture for temporal modeling. The model is validated using NASA’s CMAPSS dataset, a widely used benchmark that includes multi-sensor data and Remaining Useful Life (RUL) labels from aeroengines. By learning from time-series sensor data, the framework achieves accurate RUL predictions and early fault detection. Experimental results show that the model attains over 97% accuracy under both single and multiple operating conditions, highlighting its robustness and adaptability. These findings suggest the framework’s potential in developing intelligent maintenance systems and contribute to the field of Prognostics and Health Management (PHM), enabling more reliable, efficient, and self-monitoring industrial systems. Full article

Insulated Gate Bipolar Transistors (IGBTs) are widely deployed in power electronic systems due to their superior performance. However, at the same time, they are one of the most critical and fragile components in electronic systems. The failure prediction of IGBTs can precisely forecast the potential risk to guarantee system reliability. In this paper, Bayesian-optimized CEEMDAN is adopted to extract fault features efficiently, and a prognostic model named Performer-KAN is proposed for IGBT failure prediction. The proposed model combines the efficient FAVOR+ mechanism from the Performer with the flexible spline-based activation of the Kolmogorov–Arnold Network (KAN), enabling improved nonlinear approximation and predictive precision. Comprehensive experiments were conducted using the IMFS, which were decomposed by BO-CEEMDAN. The model’s performance was evaluated using key metrics such as MAE, RMSE, and R². The Performer-KAN demonstrates superior prediction accuracy while maintaining low computational overhead, compared to six representative deep learning models. The results demonstrate that the proposed method offers a practical and effective solution for real-time IGBT health monitoring and fault prediction in industrial applications. Full article

Remaining useful life (RUL) prediction plays a core role in industrial prognostics and health management (PHM), requiring data-driven models with higher predictive capability for accurate long time series prediction. Developing reliable deep learning-based models based on multi-sensor monitoring data is fundamental for accurately predicting vibration trends during bearing operation and is crucial for bearing fault diagnosis and RUL prediction. In this work, a method for constructing a health index based on vibration signal is developed to describe the performance features of rolling bearings, which mainly includes feature extraction, sensitive feature index selection, dimensionality reduction, and normalization methods. In addition, a new RUL prediction method, TCN–Transformer, is developed which can efficiently learn and integrate local and global features of vibration signals, addressing the long time series prediction problem in RUL prediction. The TCN extracts local features, while the Transformer learns global features, both of which are seamlessly integrated through a specially designed feature fusion attention module. Both the health indicator (HI) constructed from extracted time domain and frequency domain feature parameters and the RUL prediction method were rigorously validated using the IEEE PHM 2012 Data Challenge dataset for rolling bearing prognostics. By employing the proposed HI construction method, the average comprehensive bearing performance index, used to evaluate RUL prediction accuracy, is improved by 8.69% across the entire dataset compared to the original feature-based composite index. The proposed RUL prediction model can more accurately predict the RUL of rolling bearings under different conditions, reducing the RMSE and MAE by 14.62% and 9.26%, respectively, and improving the SCORE by 13.04%. These results underscore the efficacy and superiority of our approach in RUL prediction of rotating machinery across varying conditions. Full article

This study, set within the vast and varied research field of industrial Internet of Things (IoT) systems, proposes a methodology to address uncertainty quantification (UQ) issues in predictive maintenance (PdM) practices. At its core, this paper leverages the commercial modular aero-propulsion system simulation (CMAPSS) dataset to evaluate different artificial intelligence (AI) prognostic algorithms for remaining useful life (RUL) forecasting while supporting the estimation of a robust confidence interval (CI). The methodology primarily involves the comparison of statistical learning (SL), machine learning (ML), and deep learning (DL) techniques for each different scenario of the CMAPSS, evaluating the performances through a tailored metric, the S-score metric, and then benchmarking diverse conformal-based uncertainty estimation techniques, remarkably naive, weighted, and bootstrapping, offering a more suitable and reliable alternative to classical RUL prediction. The results obtained highlight the peculiarities and benefits of the conformal approach, despite probabilistic models favoring the adoption of complex models in cases where the operating conditions of the machine are multiple, and suggest the use of weighted conformal practices in non-exchangeability conditions while recommending bootstrapping alternatives for contexts with a more substantial presence of noise in the data. Full article

Remaining Useful Life (RUL) plays a critical role in prognostics and health management systems. It helps increase reliability and safety for the equipment used in the modern industry. The new idea proposed is the Mamba deep learning model, which aims to find a good balance between predictive performance and computation cost. This paper presents a multimodal RUL prediction model, Cau–BiMamba–LSTM, using causal discovery, a bidirectional Mamba (BiMamba), attention mechanism, and Long Short-Term Memory (LSTM). The framework utilizes maximum information transfer entropy and simple exponential smoothing in building a causal graph model that extracts groups of feature variable groupsLSTM performs long-range dependencies; the attention mechanism dynamically focuses attention according to the temporal context; finally, the bidirectional state space model captures all contextual information over time for a richer insight into underlying data patterns. Tests conducted on the C-MAPSS dataset confirm that this model achieves superior predictive accuracy and robustness. Moreover, the model achieves high predictive performance in very complex, long time–series and provides fast responses. Full article

This paper introduces a novel framework for generating synthetic time-series data from turbine engine sensor readings using a text-conditioned diffusion model. The approach begins with dataset preprocessing, including correlation analysis, feature selection, and normalization. Principal Component Analysis (PCA) transforms the normalized signals into three components, mapped to the RGB channels of an image. These components, combined with engine identifiers and cycle information, form compact 19 × 19 × 3 pixel images, later scaled to 512 × 512 × 3 pixels. A variational autoencoder (VAE)-based diffusion model, fine-tuned on these images, leverages text prompts describing engine characteristics to generate high-quality synthetic samples. A reverse transformation pipeline reconstructs synthetic images back into time-series signals, preserving the original engine-specific attributes while removing padding artifacts. The quality of the synthetic data is assessed by training Remaining Useful Life (RUL) estimation models and comparing performance across original, synthetic, and combined datasets. Results demonstrate that synthetic data can be beneficial for model training, particularly in the early epochs when working with limited datasets. Compared to existing approaches, which rely on generative adversarial networks (GANs) or deterministic transformations, the proposed framework offers enhanced data fidelity and adaptability. This study highlights the potential of text-conditioned diffusion models for augmenting time-series datasets in industrial Prognostics and Health Management (PHM) applications. Full article

Early fault detection in rotating machinery is crucial for optimizing maintenance and minimizing downtime costs, especially in medium-to-large-scale industrial applications. This study presents a multibody model developed in the Simulink^® Simscape environment to simulate the dynamic behavior of medium-sized spherical bearings. The model includes descriptions of the six degrees of freedoms of each subcomponent, and was validated by comparison with experimental measurements acquired on a test rig capable of applying heavy radial loads. The results show a good fit between experimental and simulated signals in terms of identifying characteristic fault frequencies, which highlights the model’s ability to reproduce vibrations induced by localized defects on the inner and outer races. Amplitude differences can be attributed to simplifications such as neglected housing compliancies and lubrication effects, and do not alter the model’s effectiveness in detecting fault signatures. In conclusion, the developed model represents a promising tool for generating useful datasets for training diagnostic and prognostic algorithms, thereby contributing to the improvement of predictive maintenance strategies in industrial settings. Despite some amplitude discrepancies, the model proves useful for generating fault data and supporting condition monitoring strategies for industrial machinery. Full article

Upper aerodigestive tract (UADT) carcinomas have a high and rapidly increasing incidence, particularly in industrialized countries. The identification of diagnostic and prognostic biomarkers remains a key objective in oncological research. However, conflicting data have been reported regarding Lipocalin-2 (LCN-2 or NGAL), Matrix Metalloproteinase-9 (MMP-9), and the MMP-9/NGAL complex in UADT carcinomas. For this reason, the primary aim of this study was to investigate the involvement and modulation of the LCN-2 system in UADT cancer by selecting patients at first diagnosis and excluding any pharmacological or interventional treatments that could act as confounding factors. In this clinical retrospective pilot study, we investigated LCN-2 and MMP-9 tissue gene expression, as well as circulating levels of LCN-2, MMP-9, and the MMP-9/NGAL complex. Our findings revealed a downregulation of LCN-2 and an upregulation of MMP-9 gene expression in tumor tissues compared to healthy counterparts. A similar trend was observed in circulating levels, with decreased LCN-2 and increased MMP-9 in cancer patients compared to healthy controls. Additionally, serum levels of the MMP-9/NGAL complex were significantly elevated in UADT cancer patients relative to controls. Our study suggests a potentially distinct role for the free form of LCN-2 and its conjugated form (MMP-9/NGAL complex) in UADT tumors. These findings not only provide new insights into the molecular mechanisms underlying tumor progression but also highlight the potential clinical relevance of these biomarkers. The differential expression patterns observed suggest that the LCN-2 and MMP-9/NGAL complex could serve as valuable tools for improving early diagnosis, monitoring disease progression, and potentially guiding therapeutic strategies. Further research is needed to validate their utility in clinical settings and to explore their prognostic and predictive value in personalized treatment approaches. Full article

Digital twin (DT) technology has become a key enabler for prognostics and health management (PHM) in complex industrial systems, yet scaling predictive models for multi-component degradation (MCD) scenarios remains challenging, particularly when transferring insights from predictive models of smaller systems developed with limited data to larger systems. To address this, a physics-informed neural network (PINN) framework that integrates a standardized scaling methodology, enabling scalable DT analytics for MCD prognostics, was developed in this paper. Our approach employs a systematic DevOps workflow that features containerized PINN DT analytics deployed on a Kubernetes cluster for dynamic resource optimization, a real-time DT platform (PTC ThingWorx™), and a custom API for bidirectional data exchange that connects the cluster to the DT platform. A key contribution of this paper is the scalable DT model, which facilitates transfer learning of degradation patterns across heterogeneous hydraulic systems. Three (3) hydraulic system configurations were modeled, analyzing multi-component filter degradation under pump speeds of 700–900 RPM. Trained on limited data from a reference system, the scaled PINN model achieved 88.98% accuracy for initial degradation detection at 900 RPM—outperforming an unscaled baseline of 64.13%—with consistent improvements across various speeds and thresholds. This work advances PHM analytics by reducing costs and development time, providing a scalable framework for cross-system DT deployment. Full article

The constant monitoring of the population’s diet and assessment of occupational exposure and environmental impacts are the key to determining health risks and understanding the factors contributing to potential abnormalities in developing lifestyle diseases. Extensive long-term lifestyle monitoring studies can provide data on population health risks, including the most common cardiovascular diseases like hypertension. This paper presents research recommendations for future researchers and doctors to improve the diagnosis of hypertension and targeted, personalised treatment. The research proposal includes a lifestyle study, a diagnostic panel with new biomarkers, and an environmental exposure assessment of men working in the metallurgical industry. New developments and improved interventions are constantly being sought, including new biomarkers with high diagnostic utility for cardiovascular diseases like hypertension. This should enable early diagnosis, and consequently allow for appropriate and, most importantly, personalised therapy, and prevent an increase in CVD deaths. Only the effective diagnosis, treatment, and monitoring of hypertension can reduce the risk of developing diseases associated with hypertension. I propose that several new parameters (NO, cfDNA, MPO, PCSK9, MyBPC3, microRNA, TAS, Pb, and Cd) with prognostic and/or predictive potential should be included in screening to confirm the need for the extensive testing of middle-aged men by healthcare professionals due to the risk of hypertension. Full article

This research provides a thorough examination of the industrial sector’s forecasting of renewable energy consumption, utilizing sophisticated machine learning techniques to enhance the accuracy and reliability of the predictions. LASSO regression, random forest (RF), Support Vector Regression (SVR), eXtreme Gradient Boosting (XGBoost 2.1.3), LightGBM, and multilayer perceptron (MLP) were all selected due to their ability to effectively handle large datasets. Our primary goal was to demonstrate the utility of the Energy Uncertainty Index (EUI) within commonly accepted models to ensure replicability and relevance to a broad audience. The integration of the EUI as an independent variable is a critical innovation of this research, as it addresses the challenges presented by fluctuations in energy markets. A more nuanced comprehension of consumption trends in the presence of uncertainty is achieved through this inclusion. We evaluate the performance of these models in the context of renewable energy consumption forecasting, identifying their strengths and limitations. The results indicate that the prognostic potential of the models is considerably improved by the inclusion of the EUI, providing valuable insights for energy policymakers, investors, and industry stakeholders. These advancements emphasize the role of machine learning in achieving efficient resource allocation, guiding infrastructure development, minimizing risks, and supporting the global transition toward renewable energy and sustainability. Full article