Search Results (404)

Rotating machinery plays a critical role in industrial systems, and effective anomaly detection and assessment are indispensable for ensuring operational safety and reliability. However, the performance of existing methods is often constrained by the difficulty in acquiring fault samples—such samples are typically scarce during the initial operational phase of equipment. To address this challenge, this paper proposes a novel anomaly detection and evaluation framework based on Data-Accumulation-Aware Generative Adversarial Networks (DAA-GANs) and similarity estimation. The core innovation of this framework lies in its adaptability across different data accumulation stages. During the early operational phase dominated by normal samples, only normal data is used to train the DAA-GAN to establish a baseline detector. As fault data gradually accumulates, the detection threshold undergoes adaptive adjustment through collaborative optimization of normal and abnormal samples, thereby enhancing the detector’s generalization capability. Upon amassing annotated fault samples of varying severity, the framework assesses anomaly severity by analyzing the similarity between test outputs of unknown samples and known fault samples. The framework is validated through two case studies: a fault simulation model for a torque-splitting transmission system and the publicly available Case Western Reserve University (CWRU) bearing dataset. In the simulation case, the detection accuracy reaches 100% for the gear tooth breakage levels. On the CWRU dataset, the proposed method achieves an overall average detection accuracy of 99.83% across three operating speeds (1730/1750/1772 rpm), and the similarity-based assessment provides consistent severity identification. These results demonstrate that the proposed framework can support reliable anomaly detection and severity assessments under progressive data accumulation. Full article

Metal foreign objects left in fields pose a significant challenge during silage harvester operation, leading to reduced mechanical efficiency, compromised feed quality, and risks to livestock safety. However, due to the complex and demanding working environment of agricultural machinery, such as high levels of vibration, dust, and temperature/humidity fluctuations, and the minimal dimensions of critical metallic foreign objects, which often require detection down to a few millimeters, the application of traditional metal detection technology faces significant technical challenges in this field. As a result, metal detection devices have not yet become standard equipment on silage harvesters in China. By consulting the relevant literature, this paper systematically analyzes the basic principles of metal detection technology, compares the technical characteristics of metal detection devices in the field of agricultural machinery and equipment at home and abroad, and puts forward suggestions for the challenges of reliability, foreign object removal, and system response time of metal detection devices. The application of metal detection technology in the field of agricultural machinery and equipment provides information support. Full article

With the increase in thrust–weight ratio of advanced aeroengines, the rotor and stator often exhibit comparable stiffness characteristics, leading to significant vibration coupling which harms the safety and reliability of operations. However, an effective vibration coupling evaluation method for complex rotor–stator systems is still lacking. This paper proposes the Vibration Coupling Evaluation Factor (VCEF) to quantitatively evaluate the interaction between the rotor and stator within the framework of the linear system. Then a new evaluation procedure is established for the structural optimization during the early design phase and the fault source localization in troubleshooting scenarios in the high-speed rotating machinery. In this paper, two typical rotor–stator systems are studied with the VCEF method: a simplified rotor–stator system is studied numerically to reveal the influence pattern of different parameters, and a complex rotor–stator system is studied numerically and experimentally to examine the validity of the evaluation method. The results show that VCEF can effectively capture rotor–stator vibration coupling. The VCEF curve with rotational speed shows a significant stepped decrease, indicating a significant strengthening of the rotor–stator vibration coupling, which aligns closely with experimental data. This evaluation method quantitatively assesses the degree of rotor–stator vibration coupling by comparing the differences in modal characteristics between the rotor system and the rotor–stator system under the gyroscopic effect. Optimizing rotor–stator stiffness and mass distribution based on VCEF mitigates operational risks in high-speed regimes. This methodology provides engineers with a systematic, quantitative tool to determine when integrated rotor–stator analysis is essential for accurate dynamic prediction and offers broad applicability to aeroengine design and other high-speed rotating machinery. Full article

This study formulates predictive maintenance of complex technical systems as a constrained multi-layer probabilistic optimization problem that unifies four interdependent analytical paradigms. The mathematical framework integrates: (i) Weibull reliability modelling with parametric lifetime estimation; (ii) Bayesian posterior updating for dynamic adaptation under uncertainty; (iii) nonlinear machine-learning inference for data-driven pattern recognition; and (iv) ontology-based semantic reasoning governed by logical axioms and domain-specific constraints. The four layers are synthesized through a formal orchestration operator, defined as a sequential composition, where each sub-operator is governed by explicit mathematical constraints: Weibull cumulative distribution functions, Bayesian likelihood-posterior relationships, gradient-based loss minimization, and description logic entailment. The system operates within a cognitive digital twin architecture, with orchestration convergence formalized through iterative parameter refinement until consistency between numerical predictions and semantic validation is achieved. The framework is validated through a case study on aircraft wheel-hub crack prediction. The mathematical formulation establishes a rigorous analytical foundation for cognitive predictive maintenance systems applicable to safety-critical technical systems including aerospace, energy infrastructure, transportation networks, and industrial machinery. Full article

Bearings are critical components in industrial machinery, and their failures can lead to equipment downtime and significant safety hazards. Traditional fault diagnosis methods rely on manually crafted features and classical classifiers, often suffering from poor robustness, weak generalization under noisy or small-sample conditions, and limited suitability for lightweight deployment. This study proposes a Lightweight Multi-Scale Multi-Dimensional Self-Attention Transformer (LiMS-MFormer)—an end-to-end lightweight fault diagnosis framework integrating multi-scale feature extraction and multi-dimensional attention. The model integrates lightweight multi-scale convolutional feature extraction, hierarchical feature fusion, and a multi-dimensional self-attention mechanism to balance feature expressiveness with computational efficiency. Specifically, the front end employs Ghost convolution and enhanced residual structures for efficient multi-scale feature extraction. The middle layers perform cross-scale concatenation and fusion to enrich contextual representations. The back end introduces a lightweight temporal-channel-spatial attention module for global modeling and focuses on key patterns. Experiments on the Paderborn University (PU) dataset and the University of Ottawa bearing vibration dataset (Ottawa dataset) show that LiMS-MFormer achieves an accuracy of 96.68% on the small-sample PU dataset while maintaining minimal parameters (0.07 M) and low computational cost (13.55 M FLOPs). Moreover, under complex noisy conditions, the proposed model demonstrates strong fault diagnosis capability. On the University of Ottawa dataset, LiMS-MFormer consistently outperforms several state-of-the-art lightweight models, exhibiting superior accuracy, robustness, and generalization in challenging diagnostic tasks. Full article

Gears, as critical components of rotating machinery, are prone to wear and fracture due to their complex structural dynamics and harsh operating conditions, leading to catastrophic failures, economic losses, and safety risks. AE technology enables real-time fault diagnosis by capturing stress wave emissions from material defects with high sensitivity. However, mechanical background noise significantly corrupts AE signals, while optimal selection of gear health indicators remains challenging, critically impacting fault feature extraction accuracy. This study develops an adaptive feature extraction method for fault diagnosis using AE. Through gear fault simulation experiments, VMD analyzes mode number and penalty factor effects on signal decomposition. Correlation coefficient-based reconstruction optimization is implemented. For feature selection challenges, SVM-RFE enables adaptive parameter ranking. Finally, SVM with optimized kernel parameters achieves effective fault classification. Optimized VMD enhances signal decomposition, while SVM-RFE reduces feature dimensionality, addressing manual selection uncertainty and computational redundancy. Experimental results demonstrate superior accuracy in gear fault classification. This study proposes an AE-based adaptive feature extraction method with three innovations: (1) establishing VMD parameter–decomposition quality relationships; (2) developing an SVM-RFE feature selection framework; (3) achieving high-accuracy gear fault classification. The method provides a novel technical approach for rotating machinery diagnostics with significant engineering value. Full article

Bolter miners have been widely used in coal mining or excavation industries. Its efficiency is closely related to the performance of its cutting reducer, which is literally determined by the thermal behavior of the planetary gear set. Thus, this study conducts experimental investigation on the thermal behavior of a cutting reducer (produced by Zhengzhou Machinery Research Institute Transmission Technology Co., Ltd., rated input power 170 kW, transmission ratio 3.06), where the results show the high temperature rise around the intermediate shaft for unloaded condition and significant influence of the torque for loaded conditions. Then, the Finite Element Method (FEM) is used to analyze the temperature field and thermal–structural coupling of the planetary gear set. The thermal stress and deformation increase by 11.5% and 38.4%, respectively, indicating high risk of gear damage. Moreover, the load spectrum imitating the actual industrial condition is added to the KISSsoft to evaluate the reliability and contact of the planetary gear set. The findings including low safety factors of the sun gear tooth surface and planetary gear root, slipping during the sun gear and planetary gear meshing, and uneven contact fluctuations can benefit planetary gear set optimization. Full article

Stereo cameras, also known as depth cameras or RGB-D cameras, are increasingly employed in a large variety of machinery for obstacle detection purposes and navigation planning. This also represents an opportunity in agricultural machinery for safety purposes to detect the presence of workers on foot and avoid collisions. However, their outdoor performance at medium and long range under operational light conditions remains weakly quantified: the authors then fit a field protocol and a model to characterize the pipeline of stereo cameras, taking the Intel RealSense D455 as benchmark, across various distances from 4 m to 16 m in realistic farm settings. Tests have been conducted using a 1 square meter planar target in outdoor environments, under diverse illumination conditions and with the panel being located at 0°, 10°, 20° and 35° from the center of the camera’s field of view (FoV). Built-in presets were also adjusted during tests, to generate a total of 128 samples. The authors then fit disparity surfaces to predict and correct systematic bias as a function of distance and radial FoV position, allowing them to compute mean depth and estimate a model of systematic error that takes depth bias as a function of distance, light conditions and FoV position. The results showed that the model can predict depth errors achieving a good degree of precision in every tested scenario (RMSE: 0.46–0.64 m, MAE: 0.40–0.51 m), enabling the possibility of replication and benchmarking on other sensors and field contexts while supporting safety-critical perception systems in agriculture. Full article

To address the limitations of single evaluation methods, complex risk factors, and subjective weight allocation in university mining lab safety management, this study proposes an improved EW-FCE model integrating entropy weighting and fuzzy comprehensive evaluation. A multi-level evaluation index system was developed, covering personnel status, hazardous objects, operating environment, and lab standardization (4 secondary and 24 tertiary indicators). By combining objective entropy weights with quantitative risk affiliation from fuzzy evaluation, the model overcomes traditional subjectivity. Applied to a key mining lab in Shanxi, it calculated indicator weights and overall risk values using survey data. Key risk factors identified include special equipment operation certification (weight 0.0909), heavy machinery maintenance records (0.0813), and radioactivity detector qualification (0.0761). The model enables scientific risk ranking and aligns closely with actual lab safety conditions, offering a practical tool for safety management and supporting AI-assisted decision-making in engineering universities. Full article

Rolling bearings are critical components in rotating machinery, and their performance degrades over time due to operational wear, which may compromise the safety and efficiency of mechanical systems. Therefore, accurate and timely fault diagnosis of rolling bearings is crucial. In real-world industrial environments, such diagnosis remains challenging owing to complex and varying operating conditions. Conventional single-modality deep learning methods often face limitations and fail to satisfy practical demands. To overcome these challenges, this paper proposes a novel fault diagnosis approach based on a Parallel Heterogeneous Deep Network (PHDN-FD). First, the original vibration signals are segmented according to signal pattern similarity. The continuous wavelet transform (CWT) using the Morse wavelet is applied to convert one-dimensional signal segments into two-dimensional time–frequency representations. Subsequently, each signal segment and its corresponding time–frequency representation are paired to form input data for a dual-branch parallel network. One branch, based on the ConvNeXt architecture, extracts spatial features from the time–frequency images, while the other branch employs a 1D-ResNet to capture temporal features from the raw signal segments. The features from both branches are then fused and fed into a three-layer feedforward neural network for final fault classification. Experimental results on the Case Western Reserve University (CWRU) bearing dataset and Korean Academy of Science and Technology (KAIST) bearing datasets show that the proposed method achieves high diagnostic accuracy even under adverse conditions, such as noise interference, limited training samples, and variable load levels. Moreover, the model exhibits strong cross-load transferability. By effectively integrating multimodal feature representations, the PHDN-FD framework improves both diagnostic accuracy and model robustness in complex operational scenarios, establishing a solid foundation for industrial deployment and demonstrating significant potential for practical applications. Full article

Astrocytes play a key role in maintaining redox balance and supporting neuronal survival within the central nervous system (CNS). Their antioxidant machinery, primarily involving the Nrf2–ARE (nuclear factor erythroid 2-related factor 2–antioxidant response element) pathway, glutathione (GSH) metabolism, and mitochondrial function, enables the removal of reactive oxygen and nitrogen species (ROS and RNS) and supports neuronal resistance to oxidative stress. Effective communication between neurons and astrocytes coordinates metabolic and antioxidative responses via glutamate-, nitric oxide-, and calcium-dependent signalling. Disruption of this crosstalk during traumatic injury, ischemia, or neurodegenerative disease causes redox imbalance, neuroinflammation, and excitotoxicity, which contribute to progressive neurodegeneration. Astrocytic Nrf2 activation reduces oxidative damage and inflammation, while its suppression encourages a neurotoxic glial phenotype. Current evidence emphasizes various therapeutic strategies targeting astrocytic redox mechanisms, including small-molecule Nrf2 activators, GSH precursors, mitochondria-targeted antioxidants (MTAs), and RNA- and gene-based approaches. These interventions boost the antioxidant ability of astrocytes, influence reactive cell phenotypes, and support neuronal recovery in preclinical models. Although there are still challenges in delivery and safety, restoring neuron–glia redox signalling offers a promising strategy for neuroprotective treatments aimed at reducing oxidative stress-related CNS injury and disease progression. Full article

The maritime industry is undergoing a digital transformation, in which predictive maintenance and intelligent diagnostics play a crucial role in enhancing operational safety and efficiency. This paper investigates the application of infrared thermography (IRT) for fault detection and condition monitoring of ship machinery, with particular emphasis on its integration within condition-based and predictive maintenance frameworks. A systematic review was conducted in accordance with the PRISMA 2020 methodology, analyzing 210 publications retrieved from the Web of Science (WoS), Scopus, and Google Scholar databases to identify prevailing technological trends and research gaps. The results indicate that IRT enables early detection of critical faults such as overheating, insulation degradation, and poor electrical connections, thereby reducing unplanned downtime and improving system reliability. When integrated with artificial intelligence (AI), deep learning (DL), and convolutional neural networks (CNNs), diagnostic accuracy can be automated through enhanced data interpretation. Despite its proven effectiveness, standardized protocols and real-world validation of IRT–AI systems remain limited in the maritime sector. IRT is therefore recognized as a key enabler of safer, smarter, and more sustainable ship maintenance within the broader maritime digitalization framework. Full article

Achieving sustainability is a strategic challenge for manufacturing. This study investigates the environmental and economic benefits of remanufacturing as a circular strategy to extend the lifetime of mechanical components while ensuring structural integrity, safety, and compliance with EU regulations. A mechanical synchronizer shaft used in the continuously variable transmission (CVT) of earth-moving machinery is analysed through a comparative life cycle assessment (LCA). Three scenarios are modelled: (i) the production of a new component; (ii) the remanufacturing of a discarded (at the end of its nominal life) component, considering the current remanufacturable rate of the inspected discarded lot (53.6%); and (iii) the remanufacturing of a discarded component assuming an improved remanufacturable rate (85%). Industrial data combined with Ecoinvent datasets are used to model cradle-to-grave impacts through SimaPro^®. Results show that a remanufactured component significantly decreases the global warming potential compared with a new component. However, when accounting for the actual remanufacturable rate achievable in practice, the reduction in the global warming index is more limited, highlighting the need to improve remanufacturability to unlock the full environmental benefits. A parametric LCA model integrating the DfRem approach is developed to evaluate how increasing the initial shaft diameter enables multiple remanufacturing cycles. Over multiple remanufacturing cycles, the improved design demonstrates substantial cumulative emission savings compared with repeated production of new components, also confirming the long-term environmental benefits of remanufacturing strategies. In addition to the environmental analysis, a cost evaluation is carried out to evaluate the economic feasibility of the different scenarios. The results confirm that higher remanufacturable rates not only reduce greenhouse gas emissions but also lower overall production costs, providing a comprehensive perspective on the benefits of remanufacturing-oriented design. Full article

Reliable bearing fault diagnosis plays an important role in maintaining the safety and performance of rotating machinery in industrial systems. Although deep learning models have achieved remarkable success in this field, their dependence on a single feature-extraction approach often restricts the diversity of learned representations and limits diagnostic accuracy. To overcome this limitation, this study proposes an attention-guided dual-path framework that integrates spatial and time–frequency feature learning with transformer-based classification for precise fault identification. In the proposed framework, vibration signals collected from an experimental bearing test rig are simultaneously processed through two complementary pipelines: one converts the signals into two-dimensional matrix images to extract spatial features, while the other transforms them into continuous wavelet transform (CWT) scalograms to capture fine-grained temporal and spectral information. The extracted features are fused through a lightweight transformer encoder with an attention mechanism that dynamically emphasizes the most informative representations. This fusion enables the model to effectively capture cross-domain dependencies and enhance discriminative capability. Experimental validation on an industrial vibration dataset demonstrates that the proposed model achieves 99.87% classification accuracy, outperforming conventional CNN and transformer-based approaches. The results confirm that integrating multi-domain features with attention-driven fusion significantly improves the robustness and generalization of deep learning models for intelligent bearing fault diagnosis. Full article

The Korean aquaculture sector relies heavily on foreign workers, who face elevated risks due to language barriers and limited safety training. This disparity necessitates data-driven safety interventions addressing specific worker vulnerabilities to ensure sustainable industry growth. This study quantitatively investigated accident characteristics and economic losses by nationality in Korean aquaculture by integrating 325 approved cases (2018–2022) from Industrial Accident Compensation Insurance (268 Korean; 57 foreign) and field survey data into the Formal Safety Assessment and Fault Tree Analysis frameworks recommended by the International Maritime Organization (IMO). The study revealed that entanglement during machinery operations accounted for 63.5% of the total cost among foreign workers. For Korean workers, slip and fall accidents were most frequent, while falls from height were the most severe in terms of unit cost and fatality. Based on the importance index and Human Element analysis, four risk control options were proposed: guarding and interlocks retrofit, multilingual training for foreign workers, and fall-protection upgrades and permit-to-work systems with lockout/tagout for Korean workers. Scenario analysis demonstrated consistent cost-saving effects. Both direct and indirect costs were incorporated into total loss estimation, with indirect costs calculated as 0.5–1.0 times the direct costs following the Ministry of Employment and Labor (2021). Full article