Objective.Local field potential (LFP) decoding is critical for the clinical translation of intracortical brain-machine interfaces, yet existing decoding methods are limited by three key bottlenecks: insufficient single-scale feature utilization, inefficient multi-scale feature fusion, and poor robustness across task paradigms and chronic recording conditions.Approach.To address these challenges, we propose Dual-VCT, a novel dual-branch variational mode decomposition-convolutional neural network-Transformer (VMD-CNN-Transformer) model for end-to-end LFP decoding. The core innovation of Dual-VCT is its symmetric time-frequency parallel architecture with independent VMD modules embedded in both branches: a temporal branch decomposes local motor potential (LMP) signals via VMD to capture motion-related instantaneous neural activity, while a frequency-domain branch leverages VMD to isolate task-relevant spectral power components, with a hierarchical fusion pipeline enabling robust cross-scale feature integration.Main results.Validated in non-human primate experiments, Dual-VCT achieved a classification accuracy of 0.930 ± 0.023 in the 3-class spatial grasping task, and a Pearson correlation coefficient (CC) of 0.910 ± 0.023 in the finger point-to-point tracking task. It significantly outperformed all comparative dual-branch methods under identical experimental conditions (p< 0.05), delivered a 4% performance gain over single-feature decoding, and exhibited strong cross-task robustness and cross-day stability. Ablation experiments confirmed the core contribution of the dual-branch VMD design.Significance.This work provides a high-performance structured paradigm for LFP decoding, with a clinically oriented design that supports the long-term stability of chronic iBMI systems.

To address the challenges of low accuracy and poor robustness in industrial crayfish weight estimation caused by variable postures, this paper proposes a lightweight method that integrates pose awareness. First, a multi-task perception model, Crayfish-YOLO, is developed based on the YOLOv8s-Seg framework. By reconstructing the backbone with MobileNetV3 and integrating Coordinate Attention (CA), CARAFE upsampling, and the Wise Intersection over Union (Wise-IoU) loss function, the model is significantly compressed while enhancing its ability to output high-fidelity pixel-level masks and pose categories. Second, a pose-adaptive weight estimation strategy is proposed, which leverages perceived pose information to dynamically invoke the optimal regression model from a pre-constructed heterogeneous model library. Using seven core geometric features extracted from the segmentation masks, the system achieves precise weight estimation. Experimental results on a self-built dataset show that Crayfish-YOLO reduces parameters by 75.2% compared to YOLOv8s-Seg, while core segmentation accuracy (mAP(50 similar to 95) (Seg)) improves by 1.1%. The integrated end-to-end system achieves a Mean Absolute Error (MAE) of 2.1 g and a mean coefficient of determination (R-2) of 0.92, significantly outperforming comparative algorithms. This research provides an efficient visual perception and estimation solution for the automated grading of crayfish and similar non-rigid aquatic products.

Hybrid wire arc additive-milling subtractive manufacturing (HWMM) provides an approach for producing complex, low-volume structural components. However, milling of the dynamically evolving structure during HWMM is prone to chatter, resulting in process instability. To address this problem, a finite element modal analysis model was developed to evaluate the dynamic characteristics of the milling system. Based on the dynamic model of the "rigid tool-flexible workpiece" system, a stability lobe diagram was established to identify the optimal process window. As the deposition height increases, the natural frequency decreases, causing the stability lobe diagram shifts toward the lower-left region and the process window to shrink. Experimental validation using randomly selected parameters within the stable region showed good agreement with predictions. The mean of milling vibration and Ra values of the chatter-affected sample were 10.5 and 4.1 times higher, respectively, than those of the stable milling sample. To alleviate the reduction of the process window, the influence of stiffeners on natural frequency was investigated. T-shaped and J-shaped stiffeners produced the most significant increase in natural frequency, providing an effective way to expand the process window. A milling scheme for HWMM is proposed to enable rapid parameter determination and improve machining accuracy and efficiency.

Rolling bearing vibration signals exhibit nonsmoothness and nonlinearity in complicated noise environments, which results in an erroneous feature frequency in signals and low feature extraction accuracy. Thus, with the rolling bearing vibration signal as the subject, this work uses fuzzy entropy (FE) theory and the variational mode decomposition (VMD) method to examine issues such as low feature information extraction accuracy. Simulation signals are created by examining the bearing failure mechanism and its failure form. The VMD method is selected for analysis, and the minimum FE method is proposed as the basis for determining VMD components and parameters [K, α]. A rolling bearing fault diagnostic experimental platform is built. The self-test signal and the Case Western Reserve University open dataset are subjected to a combination of VMD and sample entropy analysis. Experimental results validate the superiority of the VMD technique with FE optimization.

Particle-based 3D printing shows great potential in high-performance composite fabrication due to high raw material utilization and flexible material compatibility. However, constrained by conventional extrusion system structures, critical issues (non-uniform melt conveying, insufficient mixing efficacy, poor extrusion stability, etc.) remain. To address these, this study proposes a novel separate-type pin screw integrating solid–liquid separation (from split screws) and high-efficiency mixing (from pin screws) to improve CF/PLA composite extrusion efficiency and mixing homogeneity in particle-based 3D printing. Three-dimensional modeling, static strength/stiffness analysis, and POLYFLOW-based numerical simulation of particle melt conveying/mixing in the screw channel were conducted to analyze structural parameter effects on pressure field, shear rate, and mixing. Experiments assessed printer extrusion rate (different screws) and printed specimen mechanical properties. The simulation and experiment confirmed the optimized screw has better pressure distribution and mixing at 20 rpm, with optimal pin parameters: diameter 2 mm, height 1.6 mm, radial angle 60°, and axial spacing 10 mm. This work offers theoretical/structural support for particle-based 3D printing extrusion system optimization.

In industrial robotic grasping tasks, traditional 3D point cloud registration and pose estimation methods often struggle with low efficiency and limited accuracy in stacked and cluttered environments. To address these challenges, this paper proposes a grasp pose estimation algorithm that integrates 2D object detection based on YOLOv8-URE with 3D point cloud registration. In the detection stage, the method enhances object feature perception and localization by optimizing the receptive field structure and introducing attention mechanisms. It also employs an efficient multi-scale feature fusion strategy to improve bounding box regression accuracy. During point cloud processing, target centers predicted by the detector guide rapid segmentation, followed by robust registration techniques to estimate precise object poses. Experimental results demonstrate that YOLOv8-URE improves detection accuracy by 9.21% compared to YOLOv8n, reduces registration time by 60.5%, and significantly increases grasp success rates, proving its reliability and effectiveness in industrial scenarios.

To address the issue of point cloud incompleteness in industrial scenarios caused by insufficient lighting and occlusions, as well as the limitations of existing grasp pose generation methods that inadequately account for the geometric characteristics of parts-resulting in unreasonable grasp poses-this paper proposes a two-stage industrial part grasping method that integrates point cloud completion and skeleton guidance. In the point cloud completion stage, we introduce a symmetry-geometry collaborative variant of GRNet, trained with a progressive strategy to enable point features to gradually perceive and fuse global symmetry information, thereby achieving high-quality reconstruction of industrial parts under occluded conditions. In the skeleton guidance stage, we extract the skeleton of the completed point cloud using a Euclidean Distance Transform combined with a Minimum Spanning Tree method. Candidate grasp poses are then generated based on the local geometric features of the skeleton, and an evaluation function considering multiple dimensions is employed to select the optimal grasp strategy consistent with the overall structure of the part. Experimental results demonstrate that the improved GRNet reduces Chamfer Distance by 22.4% and improves F-Score@1% by 5.36% on public datasets. Moreover, the skeleton-based grasp pose generation method increases the effective sampling rate by 27.5%, and the generated grasp poses better conform to the geometric characteristics of industrial parts. In real-world grasping experiments, the proposed method achieves a 78% success rate in cluttered stacking scenarios, while maintaining overall processing time within an acceptable range, thereby demonstrating strong industrial applicability and robustness.

The subject of ship structural dynamics has faced new technological obstacles due to scientific and technological advancements, and one of the main concerns in related sectors is how to effectively reduce the vibration levels of different ships. This article focuses on the application scenarios of ship floating raft isolation systems, establishing a wave propagation model for acoustic black hole (ABH) structures based on the idea of the ABH effect. Then, a transfer matrix model for serially connected ABH structures is derived, which serves as a basis for subsequent structural designs. Second, the finite element method is used to study the energy distribution and vibration characteristics of a symmetrically distributed periodic non-uniform multi-level ABH structure. Meanwhile, it examines its bandgap distribution under a one-dimensional periodic arrangement and then investigates the vibration properties of non-uniform multi-level ABH thin-plate constructions with different periods from the perspective of engineering applications. Moreover, parameter optimization studies of non-uniform multi-level ABH structures with finite periods are carried out with an emphasis on engineering applications. The first step is to use the design space to determine the range of values for the parameters that need to be optimized. The hyper Latin cubic sampling method is then employed to select samples, and the EI criterion and PSO optimization algorithm are applied to add new samples to improve the Kriging surrogate model’s accuracy. When the optimal structural parameters have been determined, they are applied to the raft rib plate to verify the isolation effect of the non-uniform multi-level ABH structure by analyzing the vibration level difference at specific raft positions before and after embedding it.

This article presents a metal matrix composite material consisting of NiTi wires embedded in nitrile butadiene rubber (NBR) that preserves NBR’s inherent acoustic characteristics while enabling acoustic modification through the NiTi phase transition induced by stress and temperature. The macroscopic mechanical parameters of transversely isotropic NiTi-NBR composite materials are derived by means of a secondary bridging model that takes into account interfacial phases. On this basis, the acoustic impedance properties and absorption coefficient of composite materials were examined as a function of NiTi volume fraction using the transfer matrix method. The accuracy and effectiveness of the theoretical method were verified by comparing the calculated results with finite element simulation. The research results indicated that regulating the volume fraction of NiTi can lead to the anticipated value of the input impedance of composite materials, improving impedance matching with media like water and rubber, which offers novel insights and a theoretical foundation for the development of underwater sound-absorbing materials.

The two-degrees-of-freedom (DOF) planar seven-bar mechanism is a complicated mechanism because of its two closed kinematic chains and two input joints that lead to its motion's complexity. The majority of previous research in this area primarily focuses on the mechanism with only revolute pairs. Since the revolute pair only produces rotational motion, the need for translational movement is unaddressed. Translational motion created by a prismatic pair where the prismatic pair moves in the same direction at the same speed is needed in numerous mechanical structures. Therefore, kinematic analysis of the two-DOF planar seven-bar mechanisms with a prismatic pair and with two prismatic pairs is necessary. Paired with three-dimensional (3D) simulation, the method for the analysis is algebraic. Firstly, singularity curves, dead center positions, branches, and branch points of the two proposed mechanisms were identified via mathematical analysis; so was the rotational or translational displacement of each joint in each proposed mechanism. Secondly, the singularity configurations of the mechanisms at branch points were simulated and verified via the mechanisms' 3D models. Lastly, the sub-branches of each mechanism were identified mathematically and described by demonstrating different configurations of the mechanisms in different sub-branches via their 3D models.

In conventional gasoline automobiles, the engine powers the air conditioning system and engine noise can somewhat mask the noise and vibration of the air conditioning system. In pure electric vehicles, however, the absence of an engine makes the air conditioning system’s noise more noticeable, concentrated in a limited frequency range at constant speeds. As a result, aerodynamic noise from the air conditioning system is a primary noise source in electric vehicles. Pipeline silencers are the main method for reducing this noise. The current silencer design uses plane wave acoustic theory but when cavity modal resonance occurs, the transmission loss error is relatively high. This article addresses the issue of non-planar wave cavity resonance, studying the cavity modal of a muffler using the finite element method to reveal the transmission loss under cavity mode resonance. A dual cavity expansion structure of an impedance composite muffler is proposed, with sound-absorbing materials placed in the cavity to enhance acoustic performance. The analysis of the transmission loss characteristics of the impedance composite muffler provides a theoretical basis for noise control in pure electric vehicle air conditioning systems.

Shock absorbers are essential in enhancing vehicle ride comfort by mitigating vibrations. However, traditional rubber shock absorbers are constrained by their fixed stiffness and damping properties, limiting their adaptability to varying loads and thus affecting the ride comfort, especially under extreme road conditions. Shape Memory Alloys (SMAs), known for their intelligent material properties, offer a unique solution by adjusting stiffness and damping in response to temperature changes or strain rates, making them ideal for advanced vibration control applications. This study builds upon the Auricchio constitutive model to propose an enhanced SMA hyper-elastic constitutive model that accounts for different loading rates. This new model elucidates the impact of loading rates on the stiffness and damping characteristics of SMAs. Additionally, we introduce an innovative circular rubber-based SMA composite vibration reduction structure. Through a parameterized model and finite element simulation, we comprehensively analyze the stiffness and damping properties of the composite damper under various loading rates and harmonic excitations. Our findings suggest a novel approach to improving the vehicle ride comfort, offering significant potential for engineering applications and practical value.

Fillet welds of highly reflective materials are common in industrial production. It is a great challenge to accurately locate the fillet welds of highly reflective materials. Therefore, this paper proposes a fillet weld identification and location method that can overcome the negative effects of high reflectivity. The proposed method is based on improving the semantic segmentation performance of the DeeplabV3+ network for structural light and reflective noise, and, with MobilnetV2, replaces the main trunk network to improve the detection efficiency of the model. To solve the problem of the irregular and discontinuous shapes of the structural light skeleton extracted by traditional methods, an improved closing operation using dilation in a combined Zhang-suen algorithm was proposed for structural light skeleton extraction. Then, a three-dimensional reconstruction as a mathematical model of the system was established to obtain the coordinates of the weld feature points and the welding-torch angle. Finally, many experiments on highly reflective stainless steel fillet welds were carried out. The experimental results show that the average detection errors of the system in the Y-axis and Z-axis are 0.3347 mm and 0.3135 mm, respectively, and the average detection error of the welding torch angle is 0.1836° in the test of a stainless steel irregular fillet weld. The method is robust, universal, and accurate for highly reflective irregular fillet welds.

Two algorithms that are distinct from the closed algorithm are proposed to create the inverse kinematics model of the UR10 robot: the Sequential Quadratic Programming (SQP) algorithm and the Back Propagation-Sequential Quadratic Programming (BP-SQP) algorithm. The SQP algorithm is an iterative algorithm in which the fundamental tenet is that the joint's total rotation radian should be at a minimum when the industrial robot reaches the target attitude. With this tenet, the SQP algorithm establishes the inverse kinematics model of the robot. Since the SQP algorithm is overly reliant on the initial values, deviations occur easily and the solution speed, and the accuracy of the algorithm is undermined. To assuage this disadvantage of the SQP algorithm, a BP-SQP algorithm incorporating a neural network is introduced to optimize the initial values. The results show that the SQP algorithm is an iterative algorithm that relies excessively on the initial values and has a narrow range of applications. The BP-SQP algorithm eliminates the limitations of the SQP algorithm, and the time complexity of the BP-SQP algorithm is greatly reduced. Subsequently, the effectiveness of the SQP algorithm and the BP-SQP algorithm is verified. The results show that the SQP and BP-SQP algorithms can significantly reduce the operation time compared with the closed algorithm, and the BP-SQP algorithm is faster but requires a certain number of samples as a prerequisite.

Support structures are widely used in laser powder bed fusion (LPBF) for overhanging features. However, the majority of works carried out on support modeling were to obtain the best trade-off between production time, cost, and accuracy. A notable absence in the existing literature pertains to investigate support structure modeling for optimizing heat dissipation and residual stresses for improving the support structure, thus, enhancing the final part quality. In this study, the effects of the support structure on residual stress were investigated systematically. The influences of the support on residual stress in LPBF sample were categorized into the effect of the constraints and heat conduction area. The rigidity and area of the support structure are used to describe the effect of the support structure on the residual stress. The results showed that the constrain of LPBF samples mainly depends on their inherent characteristics, with limited impact from external constraints. The residual stress in the samples increased as the support area increased. Therefore, when designing the support, priority should be given to reduce its thermal conductivity area. In addition, the hardness of the support added sample were lower than that of the sample without the support, but the hardness distribution is uniform along the deposition height regardless of whether the support is added or not. Therefore, the introduction of support does not result in performance irregularities along the sample height direction.

Orthogonal antisymmetric composite laminates embedded with shape memory alloys (SMAs) wires have the potential to improve the sound quality of vibro-acoustics by taking advantage of the special superelasticity, temperature phase transition, and pre-strain characteristics of SMAs. In this research, space discretion and mode decoupling were employed to establish a vibro-acoustic sound quality model of SMA composite laminates. The association between the structural material parameters of SMA composite laminates and the sound quality index is then approached through methodologies. Numerical analysis was implemented to discuss the effects of SMA tensile pre-strain, SMA volume fraction, and the ratio of resin-to-graphite in the matrix on the vibro-acoustic sound quality of SMA composite laminates within a temperature environment. Subsequently, the sound quality test for SMA composite laminates is thus completed. The theoretically predicted value appears to agree well with the experimental outcomes, which validates the accuracy and applicability of the dynamic modeling theory and method for the sound quality of SMA composite laminates. The results indicate that attempting to alter the SMA tensile pre-strain, SMA volume fraction, and matrix material ratio can be used to modify loudness, sharpness, and roughness, which provides new ideas and a theoretical foundation for the design of composite laminates with decent sound quality.

Active control of structural modal vibration is an effective strategy to enhance the sound quality of cabs in commercial vehicles. However, accurate determination of the positioning and quantity of modal active control sensors and actuators is crucial for cabs with intricate structures, owing to the presence of multiorder modes and their coupling. The study presented herein focuses on the cab of a commercial vehicle and contemplates the features of the irregular large-space structure of the cab. By capitalizing on the modal frequency and mode shape of the cab, utilizing the piezoelectric control principle and modal vibration energy as the assessment index, an advanced multimode composite control criterion is postulated to ascertain the configuration of primary sensors and actuators. The particle swarm optimization (PSO) objective function is constructed to accomplish the optimal position matching of the actuator/sensor, using the multimodal surface velocity vector of the vibration sensor as the core parameter. Furthermore, an improved linear adaptive particle swarm optimization (LA-PSO) technique is advanced to satisfy the requirements of optimal convergence performance and accuracy of the complex cab structure. The optimization culminates in a 9 × 9 multichannel active control scheme for determining the optimal position of the actuators/sensors. This investigation provides a technical foundation for the active control of sound quality in automotive cabs and presents an innovative method for implementing effective noise control systems in large-scale machinery and equipment.

A suitable environment is essential for successful long-term cell culturing in vitro. Too high or too low temperature will affect the growth of cells, so we need to maintain the constant temperature of the cell culture environment. Usually, cells are cultured in a cell incubator, and the constant temperature is provided by the cell incubator. Recently, we have developed a multi-channel axon stretch growth bioreactor for rapid acquisition of autologous nerve tissue. Since the motor and controller are placed in the incubator for a long time, the service life of the equipment will be shortened or even damaged due to high humidity and weak acid environment. In order to enable the axon stretch growth bioreactor to culture cells independently, we designed a constant temperature control system for the device. Firstly, the simulation results show that the fuzzy PID control reduces the overshoot and improves the traditional PID control with large overshoot and low control precision. Then, the two control algorithms were applied to the multi-channel axon stretch growth bioreactor by STM32F4 microcontroller. The experimental data show that the fuzzy PID control algorithm has good control effect and can meet the requirement of constant temperature of cell growth. Finally, nerve cells derived from human pluripotent stem cells were successfully cultured in a cell culture amplification chamber under a constant temperature environment provided by a fuzzy PID controller, and well-developed axons could be seen. In the future, we may transplant stretch growth axons into living organisms to repair nerve damage.

Multi-loop spherical mechanisms are extremely beneficial for creating versatile mechanical devices, including robotic joints and surgical tools, since multi-loop spherical mechanisms possess unique capabilities to operate in spatial situations with relatively simple movement. Nevertheless, the research on multi-loop spherical mechanisms with spherical sliders containing spherical prismatic pairs is lacking. Therefore, the main innovation of this paper is to propose the Stephenson-III two-loop spherical mechanism that possesses a spherical slider containing a spherical prismatic pair and to analyze the proposed spherical mechanism’s motion characteristics. An algebraic approach was employed to obtain the branch graphs of the proposed spherical mechanism with a spherical slider. The branch graphs were categorized into two types, according to whether branch points existed. With the algebraic approach, loop equations of the two spherical kinematic chains inside the proposed spherical mechanism were established to identify the input–output curves and singularity curves, with which the branch graphs were obtained. With the branch graphs, the joint rotation spaces (JRSs) of the proposed mechanism were recognized and so were the dead center positions, branches, sub-branches, and branch points. The results from the mathematical analysis were simulated and verified by three-dimensional (3D) models of the proposed spherical mechanism. The analytical results demonstrate that the spherical prismatic pair diversifies the motion of the proposed spherical mechanism by producing rotational sliding movement, which can cover the entire circumference of a specific greater circle on the proposed mechanism’s sphere.

For analyzing the influence of the system parameters on the density of the powder layers in laser powder bed fusion (LPBF) technology, an experimental method is proposed to improve the structure of the recoater in the powder laying system and optimize the parameters of the powder laying system. With this experimental method, the appropriate density of the powder layers can be attained. In the proposed experimental method, the recoater in the powder laying system was taken as the research object and the forces affecting the powder and recoater when the powder was in contact with the recoater were analyzed. The discrete element model of the powder laying system was established to simulate and analyze the influences of the recoater’s radius, translational velocity and angular velocity on the density of powder layers. In addition, orthogonal experiments were designed to discuss the magnitude of the influence of each of the powder laying system’s parameters on the density of powder layers. Finally, the optimized parameter combination plan was put forward. The results show that increasing the recoater’s radius can enhance the density of powder layers within a certain range; but, as the recoater’s radius is increased continuously, its impact on the recoater’s radius on f powder layers’ density decreases. When the translational velocity of the recoater rises, powder layers’ density increases first and then decreases. The coater’s angular velocity has little effect on powder layers’ density. Eventually, the optimized processing parameters were determined, which are 25 mm for the recoater’s radius, 30 mm/s for the recoater’s translational velocity, and 12 s−1 for the recoater’s angular velocity. The results provide some significance and guidance in improving the recoater’s structure and optimizing the powder laying system’s parameters.