Search Results (360)

With the development of the Industrial Internet of Things (IIoT) technology, fault diagnosis has emerged as a critical component of its operational reliability, and machine learning algorithms play a crucial role in fault diagnosis. To achieve better fault diagnosis results, it is necessary to have a sufficient number of fault samples participating in the training of the model. In actual industrial scenarios, it is often difficult to obtain fault samples, and there may even be situations where no fault samples exist. For scenarios without fault samples, accurately identifying the unknown faults of equipment is an issue that requires focused attention. This paper presents a method for the normal-sample-based mechanical equipment unknown fault detection. By leveraging the characteristics of the autoencoder network (AE) in deep learning for feature extraction and sample reconstruction, normal samples are used to train the AE network. Whether the input sample is abnormal is determined via the reconstruction error and a threshold value, achieving the goal of anomaly detection without relying on fault samples. In terms of input data, the frequency domain features of normal samples are used to train the AE network, which improves the training stability of the AE network model, reduces the network parameters, and saves the occupied memory space at the same time. Moreover, this paper further improves the network based on the traditional AE network by incorporating a convolutional neural network (CNN) and a long short-term memory network (LSTM). This enhances the ability of the AE network to extract the spatial and temporal features of the input data, further improving the network’s ability to extract and recognize abnormal features. In the simulation part, through public datasets collected in factories, the advantages and practicality of this method compared with other algorithms in the detection of unknown faults are fully verified. Full article

Background/Objectives: Conductive hearing loss (CHL) recurrence or persistence after stapes surgery is often due to prosthesis displacement or malfunction, with malleus fixation being a less common cause. While persistent CHL linked to malleus fixation can be managed with appropriate diagnosis and surgical intervention, recurrent CHL cases remain poorly documented. This report describes a rare case of recurrent CHL due to malleus neck fixation, likely secondary to surgical trauma. Case Presentation: A 49-year-old woman underwent bilateral stapedectomy. CHL worsened after two years. CT showed right incus erosion and a left bony bridge. Revision surgery corrected the right side. Left tympanotomy revealed malleus fixation from a prior atticotomy. Removing the bony bridge restored ossicular mobility and hearing, stable at 6 and 12 months. Discussion: Malleus fixation after stapedectomy is rare and often related to congenital anomalies, chronic otitis media, tympanosclerosis, or surgical trauma. Bone dust or fragments from surgery may promote new bone formation, causing delayed fixation. Ossicular fixation can develop postoperatively and may be missed during primary surgery. High-resolution CT aids in diagnosis, especially in revision cases, while intraoperative palpation is key to detecting subtle abnormalities. Treatment options include ossicular mobilization, prosthesis revision, or chain reconstruction, tailored to the fixation’s location and severity. Conclusions: Surgical trauma should be considered a potential cause of recurrent CHL post-stapedectomy. Thorough removal of bone debris through aspiration and irrigation during surgery is essential to minimize this risk and optimize long-term hearing outcomes. Full article

Insulation degradation in photovoltaic (PV) cables can cause electrical faults and fire hazards, thereby compromising system reliability and safety. Early detection of precursor signals is crucial for preventive maintenance. However, conventional diagnostic techniques are limited to static assessments and fail to capture early-stage electrical anomalies in real-time. This study investigates the time-series behavior of voltage, current, and temperature in PV cables under thermal stress conditions. Experiments were conducted using TFR-CV cables installed in a vertically stacked and tight-contact configuration. A gas torch was applied for localized heating to induce insulation degradation. A grid-connected testbed with six series-connected PV modules was constructed. Each module was instrumented with PV-M sensors, temperature sensors, and an infrared camera. Data were acquired at 1 Hz intervals. Results showed that cable surface temperature exceeded 280 °C during degradation. The output voltage exhibited transient surges of up to +13.3% and drops of −68%, while the output current decreased by over 20%, particularly in the PV-M3 module. These anomalies, such as thermal imbalance, voltage spikes/dips, and current drops, were closely associated with critical degradation points and are interpreted as precursor signals. This work confirms the feasibility of identifying fire-related precursors through real-time monitoring of PV cable electrical characteristics. The observed correlation between electrical responses and thermal expansion behaviors suggests a strong link to the stages of insulation degradation. Future work will focus on quantifying the relationship between degradation and electrical behavior under controlled environmental conditions. Full article

The On-Load Tap Changer (OLTC), as a critical component of transformers, undergoes frequent switching operations that can lead to faults such as contact wear and arc discharge, which are often difficult to detect at an early stage using traditional monitoring methods. In particular, dissolved gas analysis (DGA) in OLTC oil is challenged by the unique oil gas decomposition mechanisms and the presence of background noise, making conventional DGA criteria less effective. Moreover, OLTC oil monitoring data are typically obtained through intermittent sampling, resulting in sparse time series with low resolution that complicate fault prediction. To address these challenges, this paper proposes an integrated framework combining LGOD-based anomaly detection, Locally Weighted Regression (LWR) for data repair, and the ETSformer temporal prediction model. This approach effectively identifies and corrects anomalies, restores the dynamic variation trends of gas concentrations, and enhances prediction accuracy through deep temporal modeling, thereby providing more reliable data support for OLTC state assessment and fault diagnosis. Experimental results demonstrate that the proposed method significantly improves prediction accuracy, enhances sensitivity to gas concentration evolution, and exhibits robust adaptability under both normal and fault scenarios. Furthermore, ablation experiments confirm that the observed performance gains are attributable to the complementary contributions of LGOD, LWR, and ETSformer, rather than any single component alone, highlighting the effectiveness of the integrated approach. Full article

Objectives: This study aimed to assess the diagnostic contribution of fetal MRI across different anatomical systems and evaluate its added value beyond prenatal ultrasonography. Methods: This retrospective cohort included 556 fetuses who underwent both prenatal ultrasound and fetal MRI in a single tertiary center. Cases were classified by anatomical system. The concordance between ultrasound and MRI findings, as well as additional or ruled-out findings identified by MRI, was analyzed. Statistical significance and clinical relevance were also evaluated. Results: Among the 556 cases, complete concordance between ultrasound and MRI findings was observed in 48.9%. MRI ruled out the initial diagnosis in 20.1% and revealed additional findings in 32% of cases. A total of 192 additional findings were identified, while 115 previously suspected anomalies were ruled out. The highest diagnostic contribution was observed in central nervous system (CNS) and gastrointestinal system (GIS) anomalies. Posterior fossa abnormalities and cystic or mass lesions were frequently detected as additional findings on MRI. In contrast, ultrasound alone was generally sufficient for evaluating genitourinary (GUS), thoracic, and vertebral anomalies. The overall diagnostic yield of MRI was higher in anatomically complex or sonographically ambiguous cases. Conclusions: Fetal MRI provides significant additional diagnostic value, particularly in CNS and GIS anomalies, by detecting additional findings, clarifying uncertain diagnoses, or excluding suspected anomalies. Its selective use may enhance both prenatal counseling and postnatal management. Full article

The object of the research is the process of intelligent monitoring and diagnosis of animal health using IoT technology in the context of a digital farm. The problem lies in the absence of an integrated approach that can provide near-real-time assessment of an animal’s physiological and behavioral state, predict potential health risks, and adapt decision-making algorithms to specific species and environmental conditions. Traditional monitoring methods rely heavily on periodic manual inspection and limited sensor data, which reduces the timeliness and accuracy of diagnostics, especially for large-scale farms. To address this issue, a comprehensive model is proposed that integrates an IoT-based tag device for livestock, a data collection and transmission system, and an intelligent analysis module. The system utilizes statistical profiling to create baseline health parameters for each animal, applies anomaly detection methods to identify deviations, and leverages machine learning algorithms to predict health deterioration. The novelty of the approach lies in the combination of individualized baseline modeling, continuous sensor-based monitoring, and adaptive decision-making for early intervention. The approach scales across farm sizes and multi-sensor setups, making it practical for precision livestock farming. From a sustainability perspective, the approach enables earlier and more targeted interventions that can reduce unnecessary treatments, avoid preventable productivity losses, and support animal welfare. The design uses energy-aware IoT practices (on-device 60 s aggregation with one-minute uplinks) and lightweight analytics to limit device power use and network load, aligning the system with resource-efficient livestock operations. Full article

This study presents an integrated condition-monitoring approach for industrial processes. The proposed approach conveniently combines a computational intelligence-based mechanism to guarantee the resilience of the proposed scheme against unknown anomalies and a machine learning model with optimized parameters capable of unified detection and pinpointing of faults and cyberattacks in industrial plants. During the offline phase, process data are labeled, normalized, and used to train the machine learning model with hyperparameter tuned by using an optimization tool. In the online phase, the system performs real-time monitoring enhanced with a novelty mechanism to detect anomalous conditions not present in the training data, which are flagged for expert analysis and incorporated into the system through incremental learning. The implementation of the proposed strategy uses computational intelligence tools consisting of a multilayer perceptron neural network, local outlier factor, and differential evolution. The proposed framework was validated using the two-tank process benchmark, demonstrating superior detection accuracy of 99% and robustness compared to other machine learning algorithms. These results highlight the potential of combining fault diagnosis and cybersecurity in a unified architecture, thereby contributing to resilient and intelligent systems in the context of Industry 4.0/5.0. Full article

Background and clinical significance: Paget’s disease of bone involves anomalies of the bone metabolism; however, the presence of tumor-derivate abnormal parathyroid hormone (PTH) levels does not represent one of these disturbances. To our best knowledge, the association with normocalcemic variant of primary hyperparathyroidism has been limitedly reported, and here we introduce such an unusual overlap in a male suffering from osteoporosis. Case presentation: A 71-year-old, non-smoker man was hospitalized for mild, nonspecific dysphagia, asthenia, decreased appetite, and mild weight loss during the latest 2 months. His medical history included cardiovascular conditions and an abnormal PTH level with normal serum calcium under daily cholecalciferol supplements (tested twice during latest 12 months). The lab findings pointed out a normocalcemic primary hyperparathyroidism (PTH of maximum 163 pg/mL, and total calcium of 9.3 mg/dL) caused by a right parathyroid tumor of 1.2 cm, as confirmed by computed tomography (CT). Additionally, CT showed a left humerus lesion suggestive of Paget’s disease of bone, a confirmation that also came from the whole-body bone scintigraphy. The subject presented increased P1NP and osteocalcin, CrossLaps as bone formation, and resorption markers, with normal total alkaline phosphatase. CT scan also detected multiple vertebral fractures and small kidney stones. Zoledronate i.v. (3 mg, adjusted for creatinine clearance) was administered, taking into consideration all three bone ailments (Paget’s disease, high PTH/calcium, and osteoporosis) with further follow-up. Conclusions: This case highlights the following technical notes based on a real-life setting: 1. Despite the mentioned bone diseases, no bone pain was present. Loss of appetite, dysphagia, and asthenia may be a consequence of mineral metabolism disturbances. 2. The panel of blood bone turnover markers levels might be related to both hyperparathyroidism and Paget’s disease; notably, rare cases of Paget’s disease with normal alkaline phosphatase were prior reported. 3. A meticulous differentiation between secondary and primary hyperparathyroidism is required. In this instance, lack of hypocalcaemia and vitamin D deficiency was suggestive of the diagnosis of a primary variant. 4. Kidney stones, osteoporosis, and osteoporotic fractures may be correlated with both conditions, as well, while a dual perspective of the therapy, since the patient was not a parathyroid surgery candidate, included a first dose of zoledronate with consecutive long-term follow-up. To our best knowledge, the co-presence of normocalcemic variant of primary hyperparathyroidism represents an exceptional finding in a patient synchronously diagnosed with Pagetic lesions and osteoporosis complicated with vertebral fractures. Full article

Background/Objectives: The primary aim of this study was to describe all cases of fetal hemivertebrae diagnosed prenatally at the Hospital Clínico Universitario de Salamanca over the last 15 years. Additionally, the presence of associated malformations was assessed, pregnancy outcomes were evaluated, and child development results were analyzed in affected cases. Methods: We undertook a prospective observational analysis of all cases (N = 10) of prenatally diagnosed hemivertebrae at our hospital between 2007 and 2022. Postnatal follow-up was performed through telephone interviews and reviewing medical records. Results: Most cases were diagnosed during the second-trimester ultrasound, with the lumbar region being the most frequently affected site (60%). Multiple hemivertebrae were detected in 4 of 10 cases. One case of Marfan syndrome and two cases of VACTERL association (vertebral defects, anal atresia, tracheoesophageal fistula, renal dysplasia, and limb abnormalities) were documented. Six cases presented with additional malformations. Cases involving multiple hemivertebrae (40%) were more likely to be associated with other anomalies and poorer prognoses, while isolated single hemivertebra showed favorable outcomes, with normal development during childhood. Vaginal delivery occurred in six cases, while cesarean sections were performed for standard obstetric indications unrelated to the hemivertebra diagnosis. Conclusions: Prenatal diagnosis of hemivertebra is achievable and holds critical neonatal and postnatal relevance. Hemivertebrae are often linked to additional disorders, including genetic syndromes, and carry significant prognostic implications depending on the associated anomalies and the extent of vertebral involvement. Full article

To address the challenge of anomaly detection in vibration signals from high-speed electric multiple unit (EMU) motor bearings, characterized by strong non-stationarity and multi-component coupling, this study proposes a synergistic approach integrating variational mode decomposition (VMD) and deep learning. Unlike datasets focused on fault diagnosis (identifying known fault types), anomaly detection identifies deviations into unknown states. The method utilizes real-world, non-real-time vibration data from ground monitoring systems to detect anomalies from early signs to significant deviations. Firstly, adaptive VMD parameter selection, guided by power spectral density (PSD), optimizes the number of modes and penalty factors to overcome mode mixing and bandwidth constraints. Secondly, a hybrid deep learning model integrates convolutional neural networks (CNNs), bidirectional long- and short-term memory (BiLSTM), and residual network (ResNet), enabling precise modal component prediction and signal reconstruction through multi-scale feature extraction and temporal modeling. Finally, the root mean square (RMS) features of prediction errors from normal operational data train a one-class support vector machine (OC-SVM), establishing a normal-state decision boundary for anomaly identification. Validation using CR400AF EMU motor bearing data demonstrates exceptional performance: under normal conditions, root mean square error $(RMSE=0.005)$, Mean Absolute Error $(MAE=0.002)$, and Coefficient of Determination $(R^2=0.999)$; for anomaly detection, accuracy = 95.2% and F1-score = 0.909, significantly outperforming traditional methods like Isolation Forest (F1-score = 0.389). This provides a reliable technical solution for intelligent operation and maintenance of EMU motor bearings in complex conditions. Full article

Laser Powder Bed Fusion (LPBF) has emerged as a leading additive manufacturing (AM) process for producing complex metal components. Despite its advantages, the inherent LPBF process complexity leads to challenges in achieving consistent quality and repeatability. To address these concerns, recent research efforts have focused on sensor fusion techniques for process monitoring, and on developing more elaborate control strategies. Sensor fusion combines information from multiple in situ sensors to provide more comprehensive insights into process characteristics such as melt pool behavior, spatter formation, and layer integrity. By leveraging multimodal data sources, sensor fusion enhances the detection and diagnosis of process anomalies in real-time. Closed-loop control systems may utilize this fused information to adjust key process parameters–such as laser power, focal depth, and scanning speed–to mitigate defect formation during the build process. This review focuses on the current state-of-the-art in sensor fusion monitoring and control strategies for LPBF. In terms of sensor fusion, recent advances extend beyond CNN-based approaches to include graph-based, attention, and transformer architectures. Among these, feature-level integration has shown the best balance between accuracy and computational cost. However, the limited volume of available experimental data, class-imbalance issues and lack of standardization still hinder further progress. In terms of control, a trend away from purely physics-based towards Machine Learning (ML)-assisted and hybrid strategies can be observed. These strategies show promise for more adaptive and effective quality enhancement. The biggest challenge is the broader validation on more complex part geometries and under realistic conditions using commercial LPBF systems. Full article

Power transformers are critical components in electrical power systems, where failures can cause significant outages and economic losses. Traditional maintenance strategies, typically based on offline inspections, are increasingly insufficient to meet the reliability requirements of modern digital substations. This work presents an integrated multi-sensor monitoring framework that combines online frequency response analysis (OnFRA^® 4.0), capacitive tap-based monitoring (FRACTIVE^® 4.0), dissolved gas analysis, and temperature measurements. All data streams are synchronized and managed within a SCADA system that supports real-time visualization and historical traceability. To enable automated fault diagnosis, a Random Forest classifier was trained using simulated datasets derived from laboratory experiments that emulate typical transformer and bushing degradation scenarios. Principal Component Analysis was employed for dimensionality reduction, improving model interpretability and computational efficiency. The proposed model achieved perfect classification metrics on the simulated data, demonstrating the feasibility of combining high-fidelity monitoring hardware with machine learning techniques for anomaly detection. Although no in-service failures have been recorded to date, the monitoring infrastructure is already tested and validated through laboratory conditions, enabling continuous data acquisition. Full article

Acute pulmonary embolism (APE) represents a significant cause of morbidity and mortality worldwide, requiring rapid and precise diagnosis and effective therapy strategies. Computed Tomography Pulmonary Angiography (CTPA) is currently the gold standard technique for diagnosing PE; however, it presents some disadvantages, including limited sensitivity in detecting sub-segmental emboli and contrast-related risks. Recent advancements in imaging technologies, including Dual-Energy Computed Tomography (DECT) and Photon Counting (PC), offer improved sensitivity and specificity for APE and perfusion abnormalities detection. Digital Dynamic Radiography (DDR) perfusion imaging represents a novel imaging that allows pulmonary perfusion assessment without contrast medium administration, able to detect anomalies at the patient’s bedside, representing a promising advancement, particularly for critically ill or contrast-allergic patients. In parallel, interventional radiology has become integral to APE management, particularly for high-risk and intermediate–high-risk patients, with evolving intravascular treatment techniques such as catheter-directed thrombolysis, mechanical thrombectomy, and thrombus aspiration. This narrative review provides an overview of the latest developments in APE diagnostic imaging and interventional radiology, contextualizing them within current guideline recommendations for endovascular treatment. Full article

Pediatric obstructive sleep apnea (OSA) is a highly prevalent, multifactorial, and often underdiagnosed condition with significant consequences for cognitive and behavioral development. Early detection and timely multidisciplinary interventions are essential, particularly in children with craniofacial anomalies or syndromes associated with increased OSA risks, to prevent long-term complications. This narrative review explores the orthodontists’ role in the interdisciplinary management of pediatric OSA, focusing on early screening for craniofacial risk factors and implementing interceptive orthodontic interventions that support favorable airway development and growth modulation. Through early and frequent interaction with pediatric patients, orthodontists are well-positioned to identify clinical signs of airway-related abnormalities and craniofacial risk factors such as mandibular and maxillary retrognathism, maxillary constriction, and high-arched palatal vaults. Orthodontic interventions such as rapid maxillary expansion (RME), mandibular advancement, and myofunctional therapy may improve airway patency in selected cases. These approaches should be coordinated and integrated within the multidisciplinary team, including orthodontists, pediatricians, sleep specialists, ENT specialists, and speech-language pathologists. Furthermore, caregivers’ involvement and patients’ compliance are keys to success. Despite encouraging clinical observations, current evidence is limited by heterogeneity and a lack of long-term outcome data. Future research should prioritize well-designed prospective trials, explore the effectiveness of combined therapeutic strategies, and support the development of standard diagnostic protocols. Equally important is a stronger focus on early diagnosis and preventive measures to enhance patient outcomes and long-term treatment strategies. Integrating orthodontists into early OSA care is essential for optimizing outcomes and reducing long-term morbidity. Full article

Ultrasound imaging is widely used in early pregnancy to screen for fetal brain anomalies. However, the accuracy of diagnosis can be influenced by various factors, including the sonographer’s experience and environmental conditions. To address these limitations, advanced methods are needed to enhance the efficiency and reliability of fetal anomaly screening. In this study, we propose a novel approach based on a Fetal Brain Structures Detection Network (FBStrNet) for identifying key anatomical structures in fetal brain ultrasound images. Specifically, FBStrNet builds on the YOLOv5 baseline model, incorporating a lightweight backbone to reduce model parameters, replacing the loss function, and utilizing a decoupled detection header to improve accuracy. Additionally, our method integrates prior clinical knowledge to minimize false detection rates. Experimental results demonstrate that FBStrNet outperforms state-of-the-art methods, achieving real-time detection of fetal brain anatomical structures with an inference time of just 11.5 ms. This capability enables sonographers to efficiently visualize critical anatomical features, thereby improving diagnostic precision and streamlining clinical workflows. Full article