Search Results (237)

To address the challenges of linguistic fuzziness, cognitive variability across fault modes, and the risk of model distortion during optimization, this paper proposes an interpretable belief rule-based fault diagnosis method for complex equipment considering linguistic fuzzy information. First, to address the difficulty experts face in providing precise probability values, an interval grey number table is constructed. By converting linguistic fuzzy information into interval grey representations, the approach quantifies the uncertainty inherent in expert judgments while fully preserving the boundary information of the underlying knowledge. Second, recognizing that expert familiarity varies across different fault modes, a certainty degree fusion method is introduced. This method utilizes fusion weights to mitigate the interference of low-confidence evidence during rule generation. Finally, an interpretable parameter optimization method featuring dynamic knowledge anchoring is designed to constrain model parameters within the reasonable bounds defined by expert knowledge. Validation on an electromechanical actuator demonstrates that the proposed method not only achieves superior diagnostic performance but also ensures model usability and interpretability in practical engineering applications. Full article

Cobalt ferrite (CoFe₂O₄) magnetostrictive ultrasonic elliptical vibration cutting (UEVC) tools have recently emerged as a low-cost, low-eddy-loss alternative to piezoelectric and rare-earth-driven cutting heads. The structural design and resonance characterisation of such a dual-bending CoFe₂O₄ UEVC tool was reported in our previous work. The present paper builds directly on that platform and addresses a different objective: to determine how the four primary process variables—feed rate, cutting speed, cutting depth, and inter-channel phase difference—should be set to obtain the best surface quality on a representative ductile metal. Using H62 brass as the workpiece and a single-crystal diamond tool with a 0.2 mm nose radius and 60° included angle, single-factor experiments are run on a custom 5-axis precision lathe, and surface roughness is mapped in both the cutting and the feed direction with a Keyence VK-X1000 confocal microscope (Keyence, Osaka, Japan). The speed ratio K = Vc/(2πfA) is computed for every test point so that each result can be classified as belonging to the continuous-contact or to the intermittent-contact UEVC regime. The results show: (i) feed rate has a non-monotonic effect, with an optimum at 1 μm where ductile-mode separation is achieved without secondary tool-trajectory overlap, reducing the cutting direction roughness by up to 45% with respect to conventional cutting (CC); (ii) the UEVC advantage shrinks at high cutting speeds because the speed ratio approaches unity and the intermittent regime collapses, but is still 12.6%–38% over the 50–375 mm/s range tested; (iii) the relative improvement is largest at low depth and decreases as the depth grows, retaining 11.5%–49% gain over CC across 0.5–10 μm; (iv) the inter-channel phase difference, which controls the geometry of the tool-tip ellipse, is the strongest single lever—at 60°, the trajectory becomes an oblique ellipse whose major axis is tilted with respect to the cutting direction, bringing the cutting direction roughness down to 1.21 μm against 2.82 μm for CC, a 57% reduction. A simple kinematic argument links this optimum to a maximum effective separation duration per cycle and offers a design rule for analogous UEVC tools. Full article

A novel method for recognizing acoustic signals of partial discharge optical fiber sensors using the time-frequency phase composition property is proposed in this paper. The method involves obtaining the Wigner–Ville time-frequency distribution for acoustic signals from partial discharge optical fiber sensors through the Cohen bilinear time-frequency transformation, which provides a high time-frequency resolution. The Wigner–Ville distribution could reflect the insulation defect-related properties in detail, owing to the fact that the intensity distribution in the time domain and energy distribution in the frequency domain is seriously influenced by medium dispersion and acoustic propagation. The time-frequency phase composition property is implemented by combining the Wigner–Ville distributions at different phases in the power cycle, which comprehensively represent the characteristics of the acoustic signals from partial discharge optical fiber sensors. A Vision Transformer with an attention block is introduced to identify the acoustic signals of partial discharge sensors. The attention block ensures that the neural network assigns more weight to the energy concentration areas in the extracted acoustic features. To validate the proposed approach, experiments are conducted to identify the acoustic signals of partial discharge optical fiber sensors. The proposed method achieves an impressive accuracy of 99.56% on three group testing sets. This indicates that the proposed approach is a promising method for identifying acoustic signals of partial discharge sensors to detect various insulation defects using acoustic emission feature analysis. Full article

Due to the scarcity of high-quality, specialized datasets for coal mining equipment operation and maintenance (O&M) and the poor adaptability of large language models to domain-specific scenarios, the reliability of actual mining O&M cannot be guaranteed. To address this, this paper investigates the construction of vertical-domain large language models for coal mining equipment O&M scenarios under limited fine-tuning data. First, to tackle the lack of O&M scenario data, a safety-guided evolutionary self-instruction method (SafeEvol-Instruct), is developed by integrating Self-Instruction, Evol-Instruct, and Rule-Based Filtering. This approach achieves the unified fusion of scalable generation, deep evolution, and safety filtering on limited O&M data, resulting in the construction of scenario-specific datasets for system status assessment, equipment fault diagnosis, maintenance plan formulation, and preventive maintenance. Second, to account for the distinct characteristics of different O&M tasks, a hybrid fine-tuning strategy (SynergyLoRA) is proposed based on the Qwen2.5-7B-Instruct foundation model. This strategy incorporates middle-layer LoRA, top-layer LoRA, middle-layer IA³, Prompt Tuning, and Prefix Tuning to enable specialized training of vertical-domain models for each O&M scenario. Finally, the constructed Coal Mining Equipment O&M Large Language Model (CMEOM-LLM) is evaluated through ablation studies across various scenarios, validating the effectiveness of the proposed methods. Experimental results demonstrate that, in the system status assessment scenario, CMEOM-LLM achieves improvements of 4.9%, 1.5%, and 1.4% over the Qwen model in accuracy, recall, and F1-score, respectively. In the equipment fault diagnosis scenario, CMEOM-LLM outperforms Qwen by 7.4% in accuracy, with BLEU-4 and ROUGE-L scores increasing by 6.6% and 6.5%, respectively. In the maintenance plan formulation scenario, CMEOM-LLM surpasses ChatGLM with improvements of 6.6%, 6.5%, and 8.5% in ROUGE-L, BLEU-4, and human evaluation, respectively. In the preventive maintenance scenario, CMEOM-LLM achieves improvements of 7.1% and 8.9% over Qwen in ROUGE-L and BLEU-4, along with a 0.69-point increase in human evaluation scores. This paper provides an effective approach for knowledge management in coal mining equipment O&M. Full article

To address the low loading rate of shearer drums in thin coal seams under restricted coal-flow space, this study proposes a rotation direction-driven multi-parameter optimization framework based on discrete element method (DEM) simulation. A DEM coal wall model is established to characterize the interaction and transport behavior of coal particles during the cutting process, and a systematic parametric analysis considering drum rotation direction, helix angle, cutting depth, rotational speed, and traction speed is conducted through coupled simulations. The results indicate that rotation direction, helix angle, and traction speed significantly affect coal loading performance, whereas cutting depth and rotational speed have a relatively minor influence. Based on these findings, an optimal parameter combination is identified, where inward rotation with a 20° helix angle and a traction speed of 7 m/min achieves a loading rate of 73.6%. Field application results demonstrate that the proposed method improves coal throwing performance, reduces coal accumulation beneath the ranging arm, and enhances coal flow stability, providing a practical optimization approach for shearer drum performance in thin coal seams and supporting efficient and intelligent coal mining. Full article

To address the polarization fading noise in coherent detection phase-sensitive optical time-domain reflectometry (Φ-OTDR) for distributed low-frequency vibration sensing, a Φ-OTDR sensing scheme integrating polarization diversity reception and the variational mode decomposition (VMD) algorithm is proposed. The mechanism of polarization fading induced by fiber birefringence and external perturbations is systematically analyzed. A signal–noise mathematical model for polarization diversity reception is established, and the adaptive decomposition capability of the VMD algorithm for non-stationary phase signals is elaborated. This scheme can accurately separate the additional noise introduced by polarization diversity reception from the target low-frequency vibration signals. Experimental results demonstrate that, compared with the single-path detection scheme, the proposed method eliminates the amplitude attenuation of beat frequency signals caused by polarization mismatch at the optical path level. Meanwhile, it effectively suppresses both the additional noise introduced by polarization diversity and the low-frequency phase drift resulting from unstable laser frequency. It achieves precise phase restoration of vibration signals excited at 50 Hz under three typical sensing distances of 5 km, 10 km, and 30 km. Additionally, it successfully restores low-frequency vibration signals as low as 0.6 Hz at the sensing distance of 30 km. Full article

Traditional domain adaptation methods often assume balanced data distributions. However, this assumption is frequently violated in real-world industrial scenarios, where normal samples predominate while fault samples are inherently scarce. Under severe class imbalance, conventional decision boundaries tend to shift toward minority fault regions. This shift leads to persistently high misclassification rates for rare fault samples. To overcome this limitation, we propose the Dynamic Maximum Triple-View Classifier Discrepancy (DMTVCD) network, which integrates a Triple-View Classifier (TVC) Architecture and a Primary–Auxiliary Fused Cooperative Loss (PAFL). Specifically, the TVC employs auxiliary binary classifiers to aggregate fine-grained fault sub-classes into a unified “Fault Super-class.” This constructs a robust “normal-fault” binary boundary that effectively counteracts class imbalance. Driven by the PAFL, this boundary acts as a hierarchical geometric constraint to suppress the primary classifier’s tendency to misclassify faults as normal samples, thereby enhancing feature discriminability. Furthermore, a dynamic weighting strategy is introduced to assign large initial weights. This forces the model to bypass simple decision logic dominated by the majority class, ensuring a smooth transition from global exploration to fine-grained alignment. Extensive evaluations on the CWRU and JNU datasets demonstrate that DMTVCD consistently outperforms state-of-the-art approaches under high imbalance ratios (e.g., 20:1). Full article

Rotating machinery serves as a critical component in various engineering systems, making accurate prediction of its Remaining Useful Life (RUL) essential for ensuring operational stability. To address the technical limitations of mainstream RUL prediction models comprehensively capturing spatial correlations among multiple sensors, this paper proposes a multi-graph-structured spatiotemporal feature fusion model for RUL prediction of rotating machinery. Breaking through the constraints of constructing a single correlation graph, the model first builds two distinct graphs—a prior correlation graph based on the structural mechanism of the rotating machinery and a similarity correlation graph derived from monitoring data distribution characteristics. These dual-perspective graphs collectively characterize the potential spatial dependencies among multiple sensors. Subsequently, a Graph Attention Network (GAT) is introduced to aggregate spatial features from both graphs, and a feature concatenation fusion strategy is adopted to achieve a comprehensive representation of the inter-sensor spatial dependencies. Finally, a Long Short-Term Memory (LSTM) network is employed to extract temporal evolution features from the operational data. The effective fusion of these spatial and temporal features enhances the model’s RUL prediction performance. Simulation experiments conducted on the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset validated the robustness of the proposed method. Full article

The tension control of carbon fiber diagonal weaving looms is severely affected by the coupling between structured friction and unstructured disturbances, leading to strong nonlinearities and time-varying uncertainties. To overcome the chattering and model-dependency issues inherent in traditional sliding mode control, a nonlinear dynamic model incorporating the Stribeck friction term was established. An Improved Adaptive Radial Basis Function-based Nonsingular Fast Terminal Sliding Mode Control (I-ARBF-NFTSMC) framework was then proposed. The framework adopts a divide-and-conquer composite compensation mechanism, in which a smooth Hyperbolic Tanh Fixed-Time Disturbance Observer (Tanh-FTDO) estimates external disturbances and suppresses chattering, and an Improved Adaptive Radial Basis Function (I-ARBF) neural network approximates and compensates internal nonlinear friction. Simulation results show that, compared with the conventional Fixed-Time Extended State Observer-based method (FESO-NFTSMC), the proposed controller achieves higher disturbance-estimation accuracy and tracking performance under sinusoidal, triangular, and composite disturbances. In composite-disturbance conditions, the steady-state mean-squared error is reduced by about 60%, the maximum tracking error decreases from 0.08787 N to 0.01965 N, and the settling time shortens by approximately 25.2%, while effectively mitigating high-frequency chattering. The proposed strategy achieves fast finite-time convergence with enhanced smoothness and robustness, providing a real-time executable solution for high-precision tension control in complex nonlinear weaving processes. Full article

The primary focus of enhancing the efficiency of operations in the Industry 4.0 setting is Predictive and Preventive Maintenance (PPM). The paper introduces a predictive-maintenance system based on the Unified Namespace (UNS), which involves real-time sensor measurements, photogrammetry, and modelling of a digital twin to improve fault prediction and responsiveness to maintenance. This experiment was conducted over six months in a medium-sized discrete electromechanical production plant equipped with motors, Variable Speed Drives (VSDs), robot/cobots, precision grip systems, pipework systems, Magnemotion/linear motor drives, and a CNC machine. The continuous data, such as high-frequency vibration, temperature, current, and pressure, were monitored and analysed with machine-learning models, including support-vector machines, Gradient Boosting, long-short-term memory, and Random Forest, through which temporal degradation can be predicted. UNS architecture integrated all sensor and imaging data into a vendor-neutral data model through OPC UA to help ensure that all experiments could be integrated consistently and be updated in real time to real digital twins. The suggested system correctly identified mechanical and electrical failures and predicted failures before they really took place. Consequently, machine downtime was reduced by 42.25%, and Mean Time to Repair (MTTR) by 36%, compared to the prior six-month baseline period. These improvements were associated with earlier anomaly detection and digital-twin-supported pre-inspection. Overall, the findings indicate that the integration of UNS with multi-modal sensing and digital-twin technologies may enhance predictive maintenance performance in comparable industrial settings. The framework provides a data-driven, scalable solution to organisations that aim to modernise their maintenance processes, attain greater reliability and better equipment utilisation, as well as enhanced Industry 4.0 preparedness. Full article

This paper addresses the issue of coordination failures in fully mechanized mining equipment under complex operating conditions, which can lead to operational abnormalities and safety hazards. We systematically analyze the dynamic coordination relationships within the equipment system across three dimensions: temporal, spatial, and geometric. Centered on the coal flow, we establish a comprehensive “mining–transportation” coordination mathematical model covering the entire production process from the coal flow cut off by the shearer to the coal flow transported out by the conveyor. Building upon this foundation, a deep learning prediction method integrating long short-term memory (LSTM) and transformer architectures is proposed to construct an intelligent prediction model for the shearer traction speed. This model effectively captures temporal features and long-term dependencies within equipment operation data, enabling the prediction of critical operational parameters for fully mechanized mining systems. It significantly enhances the early identification and warning capabilities for equipment coordination failure states. The experimental results based on the operational data of fully mechanized mining systems show that the LSTM–Transformer model performs excellently in the prediction of traction speed. The mean square error (MSE) of prediction reached 0.041, the mean absolute error (MAE) was 0.122, and the coefficient of determination (R²) was 0.996, fully demonstrating the advantages of the model in terms of prediction accuracy and stability. This article provides a theoretical basis and technical support for the judgment of the operating status of coal mine working faces and the early warning of accident risks, which is of great significance for promoting the intelligent construction of coal mines. Full article

The unloading port of a scraper conveyor is a critical component in fully mechanized mining operations and is prone to blockages caused by large coal fragments. These blockages primarily result from the limited accuracy and insufficient real-time performance of existing visual perception methods used by crushing robots to identify large coal pieces in complex mining environments. To address this issue, this paper proposes a visual inspection method for coal mine crushing robots based on transfer learning and an adaptive weighted attention mechanism, termed LCDet. First, a lightweight backbone network incorporating grouped convolution is designed to enhance feature representation while significantly reducing model complexity, thereby meeting deployment requirements. Second, an adaptive weighted attention mechanism is introduced to suppress background interference and emphasize regions containing large coal fragments, particularly enhancing blurred edge textures. In addition, a transfer learning-based training strategy is adopted to improve generalization performance and reduce dependence on large-scale training data. The experimental results on the public DsLMF+ dataset demonstrate that LCDet achieves accuracy, recall, mAP50, and mAP50–95 values of 79.3%, 75.1%, 84.5%, and 56.2%, respectively, achieving a favorable balance between detection accuracy and model complexity. On a self-constructed large coal dataset, LCDet attains accuracy, recall, mAP50, and mAP50–95 of 90.4%, 91.3%, 96.5%, and 69.3%, respectively, outperforming the baseline YOLOv8n model. Compared with other detection methods, LCDet exhibits superior performance while maintaining a relatively low parameter count. These results indicate that LCDet enables lightweight and accurate detection of large coal fragments, supporting real-time deployment on crushing robots in fully mechanized mining environments. Full article

To achieve “carbon peak and carbon neutrality” in manufacturing, this paper tackles high energy consumption in flexible job shop production by developing a low-carbon scheduling optimization model with time-of-use electricity pricing, incorporating a photovoltaic microgrid. The model minimizes makespan, carbon emissions, and costs, considering photovoltaic power uncertainty, energy storage dynamics, and time-of-use pricing. To address coupled scheduling and energy management challenges, a three-stage bilevel collaborative optimization framework is proposed, enhancing the Multi-Objective Particle Swarm Optimization (MOPSO) algorithm to develop a Collaborative MOPSO (CMOPSO). The improved algorithm features a four-layer encoding mechanism with energy factors, chaotic mapping for better global search, and adaptive mutation for population diversity. Validation using the Brandimarte benchmark demonstrates the algorithm’s robustness. Specifically, comparative experiments reveal that the proposed strategy significantly outperforms the traditional scheduling mode. While maintaining a similar makespan, the proposed method reduces production costs by 44.3% and carbon emissions by 29%. Simulations confirm that the method effectively shifts tasks to low-price periods and leverages photovoltaic energy during peak hours, supporting the manufacturing industry’s green transition. Full article

To address the challenges of strong electromechanical coupling, nonlinear friction, and poor disturbance rejection in semi-direct-drive scraper conveyor systems under complex coal mining conditions, this paper aims to propose a high-performance drive control strategy that balances dynamic response speed with steady-state operational smoothness. First, an integrated electromechanical coupling dynamic model incorporating Permanent Magnet Synchronous Motor (PMSM) vector control and the time-varying meshing stiffness of a two-stage planetary gear train is established. Subsequently, a Sliding Mode Control (SMC) strategy optimized with a saturation boundary layer is designed and compared with traditional Proportional-Integral (PI) control under multiple operating conditions. Time-frequency domain analysis indicates that SMC significantly enhances the dynamic stiffness of the drive system. Under sudden load change conditions, the speed recovery time is shortened by approximately 76%, and the steady-state error is reduced by 37% compared to PI control. Microscopic characteristic evaluation based on FFT and Total Variation (TV) metrics reveals that SMC achieves active disturbance rejection through spectral broadening of the electromagnetic torque. Crucially, the steady-state cumulative control effort of SMC is equivalent to that of PI, implying no additional mechanical stress burden, while the equivalent dynamic transmission force fluctuation in the mechanical chain is reduced by about 3%. The study confirms that the proposed strategy successfully achieves a synergistic optimization of “macroscopic rapid response” and “microscopic smooth operation,” providing a theoretical basis for the high-precision control of heavy-duty underground transmission equipment. Full article

Unsteady atmospheric disturbances significantly compromise the stability of ornithopters, necessitating advanced turbulence-mitigation strategies. In contrast, natural flyers display remarkable aerodynamic adaptability through dynamic flow-control mechanisms such as covert feathers, enabling stability across unsteady flow regimes. Drawing inspiration from this biological phenomenon, this study presents the modeling and hybrid control of a kestrel-based ornithopter equipped with a Nature-Inspired Flow Control Device (NFCD) that replicates the adaptive feather deployment mechanism observed in kestrels. A reduced-order multibody bond-graph model (BGM) of the full ornithopter is developed, incorporating the main body, propulsion system, rigid wings, and the NFCD subsystem. The model captures key fluid-structure-interaction (FSI) effects between morphing feathers and surrounding airflow. A Linear Quadratic Regulator (LQR) ensures optimal performance under nominal gust conditions (≤3 m/s), while an H₂ controller activates during high-intensity gusts (≥4 m/s) to enhance disturbance rejection through electromechanical feather actuation. A gain-scheduled transition is employed in the intermediate gust range (3–4 m/s) to ensure a smooth transition between controllers. Simulations indicate up to 70% reduction in gust-induced oscillations and 32% gust-mitigation efficiency, achieved through feather actuation in the NFCD combined with hybrid control, stabilizing the ornithopter in less than 1.4 s under higher gust conditions. The close correspondence between simulated responses and previously reported findings validates the proposed approach. Overall, by merging biomimetic aerodynamics, nature-inspired flow control, and advanced control design, the LQR-H₂ governed NFCD provides a promising pathway toward gust-tolerant ornithopters capable of resilient and stable flight in unsteady atmospheric environments. Full article