Search Results (118)

Unexpected machine failures in industrial environments lead to high maintenance costs, unplanned downtime, and safety risks. This study proposes a proactive predictive model using a hybrid of eXtreme Gradient Boosting (XGBoost) and Neural Networks (NN) to forecast machine failures. A synthetic dataset capturing recent breakdown history and time since last failure was used to simulate industrial scenarios. To address class imbalance, SMOTE and class weighting were applied, alongside a focal loss function to emphasize difficult-to-classify failures. The XGBoost model was tuned via GridSearchCV, while the NN model utilized ReLU-activated hidden layers with dropout. Evaluation using stratified 5-fold cross-validation showed that the NN achieved an F1-score of 0.7199 and a recall of 0.9545 for the minority class. XGBoost attained a higher PR AUC of 0.7126 and a more balanced precision–recall trade-off. Sample predictions demonstrated strong recall (100%) for failures, but also a high false positive rate, with most prediction probabilities clustered between 0.50–0.55. Additional benchmarking against Logistic Regression, Random Forest, and SVM further confirmed the superiority of the proposed hybrid model. Model interpretability was enhanced using SHAP and LIME, confirming that recent breakdowns and time since last failure were key predictors. While the model effectively detects failures, further improvements in feature engineering and threshold tuning are recommended to reduce false alarms and boost decision confidence. Full article

This paper presents a digital twin-driven multi-objective optimization approach for enhancing the performance and productivity of a multi-product manufacturing system under complex operational challenges. More specifically, the concept of digital twin is applied to virtually replicate a physical system that leverages real-time data fusion from Internet of Things devices or sensors. JaamSim serves as the platform for modeling the digital twin, simulating the dynamics of the manufacturing system. The implemented digital twin is a manufacturing system that incorporates a three-stage production line to complete and stockpile two gear types. The production line is subject to unpredictable events, including equipment breakdowns, maintenance, and product returns. The stochasticity of these real-world-like events is modeled using a normal distribution. Manufacturing control strategies, such as CONWIP and Kanban, are implemented to evaluate the impact on the performance of the manufacturing system in a simulation environment. The evaluation is performed based on three key indicators: service level, the amount of work-in-progress items, and overall system profitability. Multiple objective functions are formulated to optimize the behavior of the system by reducing the work-in-progress items and improving both cost-effectiveness and service level. To this end, the proposed approach couples the JaamSim-based digital twins with evolutionary and swarm-based algorithms to carry out the multi-objective optimization under varying conditions. In this sense, the present work offers an early demonstration of an industrial digital twin, implementing an offline simulation-based manufacturing environment that utilizes optimization algorithms. Results demonstrate the trade-offs between the employed strategies and offer insights on the implementation of hybrid production control systems in dynamic environments. Full article

In this study, we investigated the electrochemical corrosion behavior and mechanisms of FeCrNi/WC alloys with varying contents of CTC-S (spherical WC) and CTC-A (angular WC) in a 3.5 wt.% NaCl solution, addressing the corrosion resistance requirements for stainless steel composites in marine environments. The electrochemical test results demonstrate that the corrosion resistance of the alloy initially increases with the CTC-A content, followed by a decrease, which is associated with the formation, stability, and rupture of the passivated film. Nyquist and Bode diagrams for electrochemical impedance spectroscopy confirm that the charge transfer resistance of the passivated film is the primary determinant of the composite’s corrosion performance. A modest increase in CTC-A contributes to the formation of a more heterogeneous second phase, providing a physical barrier and enhancing solid solution strengthening, and thus delaying the cracking and corrosion processes of the passivation film. However, excessive CTC-A content leads to significant dissolution of the alloy’s reinforcement phase and promotes decarburization, resulting in the formation of corrosion pits, craters, and cracks that compromise the passivation film and expose fresh alloy surfaces to further corrosion. When the CTC-A content is 10% and the CTC-S content is 30%, this combination results in minimal degradation in the corrosion performance (0.213 μA·cm²) while balancing the hardness and toughness of the alloy. Additionally, electrochemical evaluations reveal that incorporating angular CTC-A particles at 10 vol% effectively delays the breakdown of the passivation film by mitigating the interfacial galvanic coupling through enhancing the mechanical interlocking at the WC/FeCrNi interface. The CTC-A/CTC-S hybrid system exhibits a remarkable 62% reduction in the pitting propagation rate compared to composites reinforced solely with spherical WC, which is attributed to the preferential dissolution of angular WC protrusions that sacrificially suppress crack initiation at the phase boundaries. Full article

The rise of hybrid electric vehicles (HEVs) marks a shift away from traditional engines driven by environmental and economic concerns. With the rapid growth of HEVs worldwide, their reliability becomes of utmost concern; thus, guaranteeing the proper operation of HEVs is a crucial quest. Condition-based monitoring (CBM), which intends to observe different kinds of parameters in the system to detect defects and reduce any unwanted breakdowns and equipment failure, plays an efficient role in enhancing HEVs’ reliability and ensuring their healthy operation. The permanent magnet machine (PMM) is the most used electric machine in the electric propulsion system of HEVs, as well as the most expensive. Hence, the condition monitoring of this machine is of great importance. The magnet crack is one of the most severe faults that may arise in this machine. Artificial intelligence (AI) is showing high capability in the field of CBM, fault detection, and fault identification and prevention. Hence, the aim of this paper is to present two data-based fault detection approaches, which are the support vector machine (SVM) and the Hidden Markov Model (HMM). Their capability to detect primitive faults like tiny cracks in the machine’s magnet will be shown. Applying and evaluating various CBM methods is essential to identifying the most effective approach to maximizing reliability, minimizing downtime, and optimizing maintenance strategies. A strategy to specify the remaining useful life (RUL) of the defected element is proposed. 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

Using the observation data from Fast Antenna Lightning Mapping Array, we have sub-divided 288 hybrid flashes that are obviously different from traditional intracloud (IC) and negative cloud-to-ground (NCG) flashes into three types: IC–NCG lightning (85), NCG–IC lightning (95), and the flashes (108) with negative leaders originating from the upper parts of bi-level structures of IC flashes. Hereinafter, we refer to these hybrid flashes as hybrid A, B, and C, respectively. The statistical comparisons indicate that characteristics from preliminary breakdown (PB) to return stroke (RS) are significantly different. On average, hybrid A and C flashes have higher initiation altitudes, larger PB–RS intervals, and longer propagation lengths than hybrid B flashes (7.9, 7.8 vs. 5.7 km; 430.3, 239.3 vs. 54.4 ms; 6.4, 7.8 vs. 2.3 km). Compared to 1562 IC and 844 CG flashes, hybrid flashes unsurprisingly have much larger horizontal flash sizes (189, 210, and 126.9 km² vs. 86.1 and 80.2 km²). In addition, hybrid B flashes tend to produce more RSs and larger RS1st peak currents. The striking points of hybrid C flashes appear to be close to or out of the cloud edge. Based on these statistical results, we discuss the formation mechanisms of three types of hybrid flashes. Full article

The release of synthetic dyes like Basic Red 46 (BR46) from industrial wastewater has raised growing concerns due to their toxicity, long-term persistence, and resistance to standard biological treatment methods. In this work, we developed and tested a pilot-scale electrocoagulation–ozonation (EC–O) hybrid system aimed at removing BR46 from aqueous solutions. The system integrates electrocoagulation, using iron electrodes, with ozone-based advanced oxidation processes, facilitating a combination of coagulation, adsorption, and oxidative breakdown of dye molecules. The response surface methodology (RSM) with a central composite design (CCD) was applied to optimize the treatment process, focusing on five variables: current density, flow rate, ozone dosage, ozonation time, and initial dye concentration. The quadratic model exhibited strong predictive power, with an adjusted R² of 0.9897 and a predicted R² of 0.9812. The optimal conditions identified included a current density of 70 A/m², flow rate of 1.6 L/min, ozone dose of 2.0 g/h, and an ozonation time of 20 min, achieving a predicted removal efficiency of 91.67% for a solution with BR46 at an initial concentration of 300 mg/L. Experiments conducted under these conditions confirmed the model’s reliability, with observed removal rates exceeding 90% and deviations under 2%. The EC–O system had a treatment capability of 26.19 L/h and an energy consumption of 3.04 kWh/m³. These findings suggest that the EC–O system is an effective and scalable option for treating dye-contaminated wastewater, offering faster and more efficient results than conventional techniques. Full article

The hyperglycemic microenvironment in diabetic wounds predisposes them to bacterial infections, sustains chronic inflammation, and hinders therapeutic efficacy. In this study, antibiotic-loaded fast-crosslinked hybrid nanogel wound dressings (florfenicol nanogels) based on Schiff’s base bond were obtained through N, O-carboxymethyl chitosan (N, O-CMCS) and oxidized hyaluronic acid (OHA). The successfully prepared florfenicol N, O-CMCS/OHA nanogels exhibited obvious pH- and HAase-responsiveness release, which allowed it to quickly release florfenicol at infected wounds to exert on-demand antibacterial activity, as well as accelerate diabetic bacterial-infected wound healing. The nanogel dressings showed excellent antibacterial activity by destroying the bacterial cell membrane and wall. More specifically, the glucose oxidase in the dressings can catalyze the breakdown of high-concentration glucose, generating abundant ROS that directly cause cellular damage. According to the results of wound healing, the dressings showed satisfactory anti-inflammatory and therapeutic effects for the full-thickness mouse skin defect wounds. The nanogel dressings are anticipated to be excellent wound dressings to synergistically overcome the theraputic difficulty of diabetic bacterial wounds. Full article

The air-handling unit (AHU) is an essential component of heating, ventilation, and air-conditioning (HVAC) systems. Hence, detecting the faults in AHUs is essential for maintaining continuous HVAC operation and preventing system breakdowns. The advent of artificial intelligence has transformed the AHU fault diagnosis techniques. Specifically, deep learning has obviated the necessity for manual feature extraction and selection, thereby streamlining the fault diagnosis process. While conventional convolutional neural networks (CNNs) effectively detect defects, incorporating more spatial variables could enhance their performance further. This paper presents a hybrid architecture combining a CNN model with a long short-term memory (LSTM) model to diagnose the faults in AHUs. The advantages of the LSTM model and convolutional layers are combined to identify significant patterns in the input data, which considerably facilitates the detection of AHU defects. The hybrid design enhances the network’s capability to capture both local and global characteristics, thus improving its ability to differentiate between normal and abnormal circumstances. The proposed approach achieves strong diagnostic accuracy, exhibiting high sensitivity to nuanced fault patterns. Furthermore, its efficacy is corroborated through comparisons with state-of-the-art AHU fault identification techniques. Full article

Indolic glucosinolates are a group of plant secondary metabolites found in Brassica vegetables, and their breakdown products could act as important anti-cancer and defense compounds against biotic stresses. Transcriptional regulation plays a key role in modulating the biosynthesis of indolic glucosinolates in the model plant Arabidopsis, but little is known about the transcriptional regulatory landscape of these glucosinolates in Brassica vegetables. In this study, we selected and functionally validated the important biosynthetic gene BolCYP83B1 from the indolic glucosinolate pathway in cabbage. Through a yeast one-hybrid assay, we systemically screened and identified upstream regulators of BolCYP83B1 in cabbage with BolANTs as the top candidates for further functional validation. Two homologs of BolANTs, BolANT1 and BolANT3, were confirmed to bind the promoter of BolCYP83B1 via both a yeast one-hybrid assay and an LUC assay. The overexpression of BolANT3 in cabbage significantly increased the accumulation of indolic glucosinolates, while the virus-induced gene silencing (VIGS) of BolANT3 significantly reduced the accumulation of indolic glucosinolates in cabbage. Our work provides valuable insights into the transcriptional regulatory mechanisms of indolic glucosinolates in Brassica vegetables. Full article

The worldwide adoption of artificial turf in sports facilities and urban landscapes, alongside the systematic transition from natural grass and soil-based grounds, has raised growing concerns about its contribution to the significant source of nano- and microplastics in ecosystems. This review examines current knowledge on the mechanisms of nano- and microplastic generation from artificial turf systems and their environmental impacts. Combined mechanical stress, ultra-violet radiation, and weathering processes contribute to the breakdown of synthetic grass fibers and infill materials, generating particles ranging from nanometer to millimeter scales. These nano- and microplastics are detected in drainage systems and surrounding soils near sports facilities. Laboratory studies demonstrate that artificial turf-derived nano- and microplastics can adversely affect soil microbial communities, aquatic organisms, and potentially human health, through various exposure pathways. While current mitigation approaches include hybrid turf, particle retention systems, and improved maintenance protocols, emerging research focuses on developing novel, environmentally friendly materials as alternatives to conventional synthetic turf components. However, field data on emission rates and environmental fate remain limited, and standardized methods for particle characterization and quantification are lacking. This review identifies critical knowledge gaps, underscoring the need for comprehensive research on long-term ecological impacts and highlights the future goal of mitigating nano- and microplastic emissions from artificial turf systems into the ecosystem. Full article

This paper serves as a comprehensive “starter pack” for electrical diagnostic methods for power transformers. It offers a thorough review of electrical diagnostic techniques, detailing the required instrumentation and highlighting key research directions. The methods discussed include frequency response analysis, partial discharge testing, dielectric dissipation factor (tan delta), direct current (DC) insulation resistance, polarization index, transformer turns ratio test, recovery voltage measurement, polarization–depolarization currents, frequency domain spectroscopy, breakdown voltage testing, and power factor and capacitance testing. Additionally, the paper brings attention to less-explored electrical diagnostic techniques from the past decade. For each method, the underlying principles, applications, necessary instrumentation, advantages, and limitations are carefully examined, alongside emerging trends in the field. A notable shift observed over the past decade is the growing emphasis on hybrid diagnostic approaches and artificial intelligence (AI)-driven data analytics for fault detection. This study serves as a structured reference for researchers—particularly those in the early stages of their careers—as well as industry professionals seeking to explore electrical diagnostic techniques for power transformer condition assessment. It also outlines promising research avenues, contributing to the ongoing evolution of transformer diagnostics. Full article

This narrative review provides an overview of the various diagnostic tools used to assess cartilage health, with a focus on early detection, nutrition intervention, and management of osteoarthritis. Early detection of cartilage damage is crucial for effective patient management. Traditional diagnostic tools like radiography and conventional magnetic resonance imaging (MRI) sequences are more suited to detecting late-stage structural changes. This paper highlights advanced imaging techniques, including sodium MRI, T2 mapping, T1ρ imaging, and delayed gadolinium-enhanced MRI of cartilage, which provide valuable biochemical information about cartilage composition, particularly the glycosaminoglycan content and its potential links to nutrition-related factors influencing cartilage health. Cartilage degradation is often linked with inflammation and measurable via markers like CRP and IL-6 which, although not specific to cartilage breakdown, offer insights into the inflammation affecting cartilage. In addition to imaging techniques, biochemical markers, such as collagen breakdown products and aggrecan fragments, which reflect metabolic changes in cartilage, are discussed. Emerging tools like optical coherence tomography and hybrid positron emission tomography–magnetic resonance imaging (PET-MRI) are also explored, offering high-resolution imaging and combined metabolic and structural insights, respectively. Finally, wearable technology and biosensors for real-time monitoring of osteoarthritis progression, as well as the role of artificial intelligence in enhancing diagnostic accuracy through pattern recognition in imaging data are addressed. While these advanced diagnostic tools hold great potential for early detection and monitoring of osteoarthritis, challenges remain in clinical translation, including validation in larger populations and integration into existing clinical workflows and personalized treatment strategies for cartilage-related diseases. Full article

Fault diagnostics in internal combustion engines (ICEs) is vital for optimal operation and avoiding costly breakdowns. This paper reviews methodologies for ICE fault detection, including model-based and data-driven approaches. The former uses physical models of engine components to diagnose defects, while the latter employs statistical analysis of sensor data to identify patterns indicating faults. Various methods for ICE fault identification, such as vibration analysis, thermography, acoustic analysis, and optical approaches, are reviewed. This paper also explores the latest approaches for detecting ICE faults. It highlights the challenges in the diagnostic process and ways to enhance result accuracy and reliability. This paper concludes with a review of the progress in fault identification in ICE components and prospects, highlighted by an experimental investigation using 16 machine learning algorithms with seven feature selection techniques under three load conditions to detect faults in a four-cylinder ICE. Additionally, this study incorporates advanced deep learning techniques, including a deep neural network (DNN), a one-dimensional convolutional neural network (1D-CNN), Transformer and a hybrid Transformer and DNN model which demonstrate superior performance in fault detection compared to traditional machine learning methods. Full article

The preservation of interfacial integrity in esthetic dental restorations remains a critical challenge, with hybrid layer degradation being a primary factor in restoration failure. This degradation is driven by a combination of host-derived enzymatic activity, including matrix metalloproteinases (MMPs), bacterial proteases, and hydrolytic breakdown of the polymerized adhesive due to moisture exposure. This review examines the multifactorial mechanisms underlying hybrid layer degradation and presents current advancements in restorative materials aimed at counteracting these effects. Principal strategies include collagen preservation through the inhibition of enzymatic activity, the integration of antimicrobial agents to limit biofilm formation, and the use of ester-free, hydrolysis-resistant polymeric systems. Recent research highlights acrylamide-based adhesives, which exhibit enhanced resistance to acidic and enzymatic environments, as well as dual functionality in collagen stabilization. Furthermore, innovations in bioactive resins and self-healing materials present promising future directions for developing adhesives that actively contribute to long-term restoration stability. These findings underscore the importance of continuous advancements in adhesive technology to enhance the durability and clinical performance of dental restorations. Full article