When the tunnel boring machine (TBM) is engaged in rock-breaking operations, the cutters are subject to wear due to the harsh underground environment. This study aims to investigate the effects of cutter wear on rock-breaking force and overall rock fragmentation efficiency. Firstly, a three-dimensional simulation model of the cutter breaking rock is generated through PFC3D. Then, the rock-breaking force, specific energy consumption and the internal crack breaking mode of the rock are studied under different partial wear degrees of the cutter. Finally, the simulation results were verified and analyzed through indoor scale-down experiments. The research results show that: 1) When the partial wear of the cutter is 8%, the normal force and tangential force increase by 29.1 kN and 12.2 kN, respectively, compared to those without wear. 2) The unit specific energy consumption increases continuously with cutter partial wear. At the 8% wear threshold, the inter-cutter synergistic effect is completely lost, and 91% rock ridge are formed. 3) When the partial wear occurs on the cutter, it will cause a change in the rock fragmentation form, from intergranular cracking to transgranular cracking.

The main bearing of the TBM (tunnel boring machine) provides support for the cutter head, which significantly defines the penetration efficiency. In this paper, a dynamic model considering the impure lubrication condition is established on the basis of the elastohydrodynamic lubrication (EHL) theory. The results of the oil film thickness and pressure reveal that impurities significantly affect the oil film distribution. On the basis of the Reynolds equation and the roller slicing method, the dynamic characteristics of the main thrust roller considering impure lubrication are determined. When the fraction of impurities increases to 15

Objective.Electroencephalogram (EEG) signal variability caused by external factors and subject differences limits the adaptation of motor imagery (MI) classification models in brain-computer interfaces (BCIs). Existing domain alignment methods often inadequately utilize critical source and target domains information, leading to negative transfer problems. This paper proposes a Feature Alignment and Enhancement Framework for cross-domain MI-EEG classification to address these limitations.Approach.First, by aligning the covariance matrices of the source and target domains, the spatial distributions of the two domains are preliminarily aligned, establishing a consistent foundation for feature mapping. Second, a conditional domain adversarial network optimizes cross-domain representations, reducing distribution discrepancies while enhancing discriminability. Finally, this paper introduces an EEG feature-based guided tuning method. This method extracts high-confidence features from both the source and target domains and generates centroid features to construct cross-domain feature banks. The input feature representations are dynamically optimized by attending to the relationships between centroid features, thus enhancing the model's adapt-ability to target domain tasks.Main results.Experimental data show that in the four-class MI task of the BCI Competition IV-2a dataset, the cross-session and cross-subject model classification accuracies were 76.89% and 57.91%, respectively. The model achieved accuracy rates of 84.61% and 82.78% on the BCI Competition IV-2b datasets and the High Gamma Datasets, respectively, as well as 84.09% and 70.81%.Significance.The proposed framework effectively mitigates cross-domain variations, providing a reliable solution for cross-session and cross-subject MI-EEG classification.

Self-filling thin-walled cellular cushions fabricated by additive manufacturing offer a practical route to tailor crashworthiness for protective packaging. Here, 3D-printed self-filling square cellular structures were designed by inserting internal thin-walled square units into a parent square cell (n = 0-2). Specimens were printed using copolyamide (CoPA) and thermoplastic polyurethane (TPU; Shore 70 A and 85 A). Quasi-static compression tests, supported by validated finite-element simulations, were performed to characterize collapse modes, plateau stress, and energy absorption as functions of unit side length (L = 30 and 50 mm), specimen height (H = 25 and 30 mm), and self-filling stage. All structures showed an elastic regime followed by a progressive buckling plateau and densification; increasing n promoted denser stacking and more stable progressive collapse. For H = 25 mm, the plateau stress ranged from 51.61 to 125.97 MPa (CoPA), 0.27-6.26 MPa (TPU 70 A), and 0.64-15.41 MPa (TPU 85 A), indicating that material stiffness primarily governs the load level while geometry controls the collapse pattern. Drop-impact tests further reveal a non-monotonic role of the filling level on cushioning performance, with an optimal intermediate configuration (n = 1) that minimizes peak acceleration while maintaining stable progressive collapse. These findings establish quantitative structure-property relationships and provide practical design guidelines for additively manufactured self-filling cellular cushions.

Due to load variations in composite ground that can trigger shield pitch instability and tunneling axis deviation, the proposed deterministic policy continuous control network (DPCN) extends the deep deterministic policy gradient actor-critic framework by introducing trajectory embedding and similarity-based replay for shield pitch regulation. Multiscale Gaussian kernels are employed to embed state sequences into trajectories and represent them as latent continuous variables (LCVs). Based on these LCVs, a similarity-driven bucketed and weighted experience replay mechanism is constructed to enhance experience reuse efficiency and control stability. Multiscenario disturbance simulations show that, compared with five baseline deep reinforcement learning control algorithms, DPCN reduces the average pitch angle error across all test scenarios by approximately 46% and decreases the standard deviation of the residual pitch moment by about 25%. The DPCN is deployed on a partitioned thrust experimental platform, and the closed-loop experiments verify both the practical implement ability of the proposed method and its robustness to load disturbances across different scenarios.

Real-time diagnosis of motor bearing faults is essential for fault detection and timely maintenance, minimizing operational risks. However, most existing approaches often depend on cloud platforms or high-performance local servers, which introduce latency and potential security vulnerabilities due to raw data transmission. To overcome these limitations, this article presents an adaptive pruning triple-lightweight network (APTL-net), which achieves model lightweighting for edge deployment across three stages: model construction, feature extraction, and structural pruning. First, a lightweight fault diagnosis framework optimized for edge environments is proposed, enabling parallel training and recursive inference to eliminate the traditional tradeoff between training efficiency and inference performance. Second, a frequency-domain decomposition (FDD)-based, weight-sharing multiscale convolution module is designed to efficiently extract multiscale features from periodic signals while harmonizing scale variations. Moreover, a fully automated adaptive pruning strategy is proposed to dynamically group and remove redundant structures during training without manual intervention. Finally, APTL-net is deployed on the edge device and validated on the physical platform equipped with real hardware. Experimental results indicate that APTL-net achieves a diagnostic accuracy of 99.54 % while reducing parameters by 47.82 %, FLOPs by 49.98 %, and edge inference latency by 20.59 %, thereby delivering superior performance over existing lightweight fault diagnosis networks.

Fault-diagnosis methods based on deep learning technology have been widely applied in gear fault diagnosis. Gearboxes often operate under complex and harsh conditions, which can lead to faults. Therefore, monitoring the condition of gearboxes and diagnosing faults are crucial for ensuring the reliability and safety of the system. In response, this paper proposes a gear fault diagnosis model based on the adaptive prototype hashing (APH) optimisation algorithm for diagnosing faults in rotating machinery. This method combines the advantages of adaptive prototype hashing with transformers to improve the accuracy of fault diagnosis. The model utilises an adaptive prototype selection mechanism to dynamically select the most representative samples as prototypes and employs the transformer model to extract feature representations of the input data. In classification tasks using two datasets, the model achieved an accuracy of 98.11% under normal conditions. In experiments with added white noise and a smaller sample size, the accuracies reached 96.81% and 86.41%, respectively. Additionally, we conducted ablation experiments with advanced transformer models, where the APHformer model incorporating the APH layer achieved fault diagnosis accuracies exceeding 97%, significantly outperforming other combinations. Furthermore, T-SNE visualisation results indicate that the method performs well in feature representation. This study provides important insights into the field of gear fault diagnosis based on deep learning and has potential practical application values.

Due to the limited sample size caused by preventive maintenance and the variable data distribution caused by environmental factors, the performance of well-trained laboratory models has decreased significantly when confronted with actual industrial bearing fault diagnosis. The existing domain adaptation methods using cross-domain labeled samples for classification make it difficult to resist the influence of outliers on the overall matching, which leads to a negative transfer problem. Given the above issues, a dynamic weight-optimized prototypical contrastive network is proposed. Primarily, domain adaptation is assisted by the discriminative information the classifiers convey during the prediction process. The model is prompted to find the source data that matches the distribution, removing the effect of distribution variability. Furthermore, the sample-aware weighting term evaluates the difficulty of the sample classification and suppresses the performance degeneration of domain adaptation. Subsequently, the in-domain prototypical contrastive learning evaluates dynamically the intensity of feature distribution around each prototype. The features from the same category are inspired to move closer to the prototype to enhance the consistency and discrimination of intra-class features. Meanwhile, cross-domain instance-prototype learning reduces the distribution inconsistency of the corresponding category data in the source and target domains to enable fine-grained inter-domain alignment and mitigate the negative transfer problem. Through numerous comparative experiments, this method shows superior effectiveness and engineering diagnostic feasibility under cross conditions with limited data resources.

Tunnel boring machine disc cutters use heavy load, low speed tapered roller bearings as the support. The surface defects of tapered roller bearing impact the dynamic characteristics and rock-breaking capabilities directly. As the roller passes through the defect zone, the contact force, displacement, and vibrational responses are needed to simplification and observation for research. This study builds a surface defect-aware time-varying dynamic model for the tapered roller bearing of disc cutter system. By the way, takes the defect displacement into consideration, and the dynamic equations are solved via the numerical method. The vibration responses under varied rotational speeds and radial pressures are analyzed. For the axial defect’s maximum width is 85°–89°, the analysis shows that the vibration responses are mostly affected by the radial load. As the roller passes through the defect area, the vibration acceleration and displacement rise to 4.86 mm/s 2 and 1.37 mm, respectively. The results of experiment which obtained by the cutter system experimental platform illustrates the great accordance with the simulation results, with an error less 7.5%. This research gives a guidance function for the defect vibration recognition.

In the process of rock breaking, the surrounding rock pressures exert a remarkable influence on the rock-breaking efficiency of disc cutters. This study focuses on the rock-breaking efficiency of tunnel breaking machine (TBM) disc cutters under varying surrounding rock pressures and temperatures. Firstly, based on the servo principle and linear parallel bonding theory, the discrete element software PFC2D is used to establish a two-dimensional simulation rock-breaking model. Meanwhile, considering the rock temperature, the extent of cutter penetration and specific energy are studied under different conditions. Subsequently, a rock-breaking experiment platform utilizing cutters is also established to conduct validation. Finally, the findings indicate that the rock fragmentation effectiveness of high temperature rock is 12.56% higher than that of low temperature rock. The cutter exhibits superior efficiency in breaking rocks under low or medium surrounding rock pressure, particularly at a surrounding rock pressure of 8 MPa, with the average specific energy being 8.72% lower than at 4 MPa and 21.03% lower than at 12 MPa, respectively. The maximum error of the simulation model and experiment is 9.51%. A theoretical foundation for the practical implementation of TBM is offered.

As the main bearing component of the tunnel boring machine (TBM), the three-row roller slewing bearing is required to withstand a heavy load and overturning moment in the tunnelling process. Therefore, a dynamic model of a slewing bearing considering the external load and internal structural parameters is established. First, the influence of the complex load on the internal structural parameters (clearance, radial displacement, roller tilt and skew) of the slewing bearing is analysed. Then, by using the four-stage Runge–Kutta method, the dynamic model is solved, and the influence of different parameters on the dynamic performance and stability is obtained. Finally, the proposed model is verified via experimental research, and the accuracy error of the model is less than 7%. The state of the inner ring’s motion progressively changes from stable to unstable as the rotational speed increases. The dynamic characteristics of a slewing bearing can be improved by reducing the radial clearance and the number of rollers while it is subjected to excessive eccentric loading. The results of this study provide important guidance for the design of slewing bearing structures.

Slewing bearings are important components in heavy-duty machinery, with their failure mechanisms critically impacting operational reliability. Firstly, considering the coupling effect of roller defects and tilting of inner ring, a three-dimensional dynamics model is developed. And the nonlinear vibration equation with time-varying contact stiffness is constructed based on Hertz contact theory. Then the defect-roller dynamic collision process is characterized by the introduction of the defect roller motion trajectory function. Moreover, the fourth-order Runge-Kutta method is used to solve the vibration response of the system, emphasizing on analyzing the dynamic coupling mechanism of roller defect size, eccentric load angle, and contact force. Finally, a slewing bearing experiment platform is built to verify the simulation results. The changes in stiffness and intrinsic frequency of the slewing bearing are measured by the eccentric load under different defect sizes. Time-domain analysis reveals defect size-dependent amplitude characteristics, with a peak increase of 42.6% observed. Spectral analysis revealed distinct mf(o) +/- nf(r) modulation patterns (fundamental frequency error <= 7.86%). The multiparameter coupling model proposed in this study reveals the mapping law of defect size-vibration response under eccentric load condition. It provides a theoretical basis for the fault diagnosis of slewing bearings.

The earth pressure balance shield machine (EPB) is an important piece of engineering equipment used in tunnel excavation and plays an important role in large underground tunnel projects. This article takes the sand and gravel formation as the research object, while discrete element simulation is utilized to study the correlation between cutterhead torque and thrust and other parameters. The EPB tunneling experiment was carried out by setting up formations with different sand and gravel contents. The reliability of the simulation model was verified by the experimental data, which provided the data samples for the training of the excavation formation identification network. Finally, a GTNet (gated Transformer network) based on the formation identification method was proposed. The reliability of the network model was verified by contrasting the model used with other network models and by analyzing the results of experiment and visualization. The effects of different parameters were weighted using the ablation study for tunneling parameters. The proposed method has a high accuracy of 0.99, and the cutterhead torque and thrust have a great recognition feature, the weight of which is over 0.95. This paper can provide significant guidance for the torque and thrust analysis of cutterheads in tunnel construction.

In order to improve the cushioning performance of cushioning materials and reduce the use of materials, the structural parameter is designed and the static cushioning performance of Paper-based Spherical Porous Materials is analyzed in this paper. The cushioning coefficient and the stress-strain curve are investigated under the different structural parameters. The results show that the different structural parameters of the materials affect the static cushioning performance of such materials. The compression process can be divided into three stages: linear elasticity, yielding, and densification. As the pore size decreases, the yield value increases progressively, indicating an enhancement in the rigidity of the paper-based spherical porous materials and a reduction in cushioning effectiveness. Smaller pore sizes result in improved cushioning performance for paper-based spherical porous materials. Increasing the thickness enhances the cushioning performance of paper-based spherical porous materials.

In order to improve the impact resistance of glass containers, this study utilized the finite element method to investigate the mechanical properties of liquid-containing glass beer with different drop mode. The results show that stress within the beer bottle is primarily concentrated at the bottle-ground contact point throughout the drop, creating a fracture once the stress surpasses the critical threshold. As the fracture forms, the stress continues to increase until it reaches its maximum, after which it progressively disperses throughout the entire bottle body. From research data, it was found that when θ is 30°, its maximum stress is 283.703 MPa, while θ are 0° and 90°, the stresses are 184.987 MPa and 116.583 MPa, respectively. Therefore, inclined drops generate greater stress impact onto the bottle, making it more vulnerable to damage compared to fully vertical / horizontal drops. Regardless of the drop mode, the point of maximum stress is always situated at the bottle-ground contact point, whereas the magnitude of maximum stress at the moment of fracture is not directly proportional to the different drop modes.

During the bearing operation, surface waviness can cause severe nonlinear vibrations and reduce the life and reliability of bearing-rotor systems. A temperature increase can deform the surface waviness, which can exacerbate this unstable vibration. To address this problem, a dynamic waviness model considering thermal deformation is proposed, and the dynamic support stiffness is calculated and introduced into the dynamic model of a 12-DOF full-ceramic bearing-rotor system. The Newton–Raphson and Newmark-β nested iterative solution method combines the quasi-static and dynamical models. The bifurcation, maximum Lyapunov exponent, and Poincaré mapping analysis methods serve to analyse how thermal deformation, waviness amplitude and other parameters affect the system nonlinear vibration. Experimental measurements are conducted to verify the model accuracy and reveal that a larger waviness amplitude causes a delayed motion state and expands the influence of the thermal deformation. The wavenumber is close to an integer multiple of the ball, and the time-varying displacement excitation curve shows a monotonic variation trend, which makes the system violently vibrate. The model effectively reveals the characteristics of the failure frequency and provides important theoretical support for the fault detection of full-ceramic bearings.

Rolling bearing fault diagnosis is significant to the stable operation of rotating machinery systems. However, the fault data collected in practical engineering are seriously imbalanced, which degrades the diagnosis performance. A DRNet intelligent fault diagnosis model was proposed in this article based on the probabilistic diffusion model to enhance fault diagnosis performance under imbalanced data. This article utilized a probabilistic diffusion model to learn a deep semantic representation of fault data, which in turn generates high-quality fault features to balance the number of fault samples. Moreover, we utilized the deep features of fault signals to build a feature metric module that optimized the features of the generated samples. This enhances the accuracy and diversity of the generated data. Finally, the fault categories of the samples were identified using the residual network after data enhancement. The experimental results indicate that compared to other common methods, our method can more effectively fit the feature distribution of real samples resulting in generated samples with higher similarity and exhibiting good stability and accuracy when processing bearing unbalanced fault data.

In tunnel boring projects, wear and tear in the tooling system can have significant consequences, such as decreased boring efficiency, heightened maintenance costs, and potential safety hazards. In this paper, a fault diagnosis method for TBM tooling systems based on SAV−SVDD failure location (SSFL) is proposed. The aim of this method is to detect faults caused by disk cutter wear during the boring process, which diminishes the boring efficiency and is challenging to detect during construction. This paper uses SolidWorks to create a complete three−dimensional model of the TBM hydraulic thrust system and tool system. Then, dynamic simulations are performed with Adams. This helps us understand how the load on the propulsion hydraulic cylinder changes as the TBM tunneling tool wears to different degrees during construction. The hydraulic propulsion system was modeled and simulated using AMESIM software. Utilizing the load on the hydraulic propulsion cylinder as an input signal, pressure signals from the two chambers of the hydraulic cylinder and the system’s flow signal were acquired. This enabled an in−depth exploration of the correlation between these acquired signals and the extent of the tooling system failure. Following this analysis, a collection of normal sample data and sample data representing different degrees of disk cutter abrasions was amassed for further study. Next, an SSFL network model for locating the failure area of the cutter was established. Fault sample data were used as the input, and the accuracy of the fault diagnosis model was tested. The test results show that the performance of the SSFL network model is better than that of the SAE−SVM and SVDD network models. The SSFL model achieves 90% accuracy in determining the failure area of the cutter head. The model effectively identifies the failure regions, enabling timely tool replacement to avoid decreased boring efficiency under wear conditions. The experimental findings validate the feasibility of this approach.