Search Results (83)

In practical applications, intelligent diagnostic methods for actuator-integrated gearboxes in industrial driving systems encounter challenges such as the scarcity of fault samples and variable operating conditions, which undermine diagnostic accuracy. This paper introduces a multi-layer feature fusion meta-learning (MLFFML) approach to address fault diagnosis problems in cross-condition scenarios with class imbalance. First, meta-training is performed to develop a mature fault diagnosis model on the source domain, obtaining cross-domain meta-knowledge; subsequently, meta-testing is conducted on the target domain, extracting meta-features from limited fault samples and abundant healthy samples to rapidly adjust model parameters. For data augmentation, this paper proposes a frequency-domain weighted mixing (FWM) method that preserves the physical plausibility of signals while enhancing sample diversity. Regarding the feature extractor, this paper integrates shallow and deep features by replacing the first layer of the feature extraction module with a dual-stream wavelet convolution block (DWCB), which transforms actuator vibration or acoustic signals into the time-frequency space to flexibly capture fault characteristics and fuses information from both amplitude and phase aspects; following the convolutional network, an encoder layer of the Transformer network is incorporated, containing multi-head self-attention mechanisms and feedforward neural networks to comprehensively consider dependencies among different channel features, thereby achieving a larger receptive field compared to other methods for actuation system monitoring. Furthermore, this paper experimentally investigates cross-modal scenarios where vibration signals exist in the source domain while only acoustic signals are available in the target domain, specifically validating the approach on industrial actuator assemblies. Full article

Given that grinding robots are easily affected by internal and external disturbances when machining complex surfaces with high precision, in this study, an adaptive robust impedance control method combining a radial basis function neural network (RBFNN) and sliding mode control (SMC) is proposed. In a Cartesian coordinate system, we first use the universal approximation ability of the RBFNN to accurately identify and actively compensate for complex unknown disturbances in robot dynamics online. Then, an improved sliding mode impedance controller, which uses robust sliding mode control to effectively suppress the influence of RBFNN identification error and residual disturbance on trajectory tracking and ensure the accuracy of impedance control, is implemented. This approach improves the control performance and overcomes the inherent chattering phenomenon of the traditional sliding mode. Full article

Volumetric error decoupling is a critical prerequisite for effective error compensation. In this paper, the forward volumetric error model is established using the screw theory. Additionally, the Jacobian matrix based on the product of exponential is derived to construct the linear relationship between the volumetric error and the axis motion and decouple the volumetric error model. To address the limitation of compensation motion, a step-by-step decoupling method is proposed, where attitude and position errors are compensated sequentially. After detecting the actual geometric errors of the grinding machine, the volumetric error can be determined, and the compensation motion commands for each axis are calculated to correct the volumetric error. The simulation result shows that the mean value of the comprehensive error ranges can be reduced from 19.7 μm to 1.8 μm, demonstrating the effectiveness of the proposed method. Full article

Ensuring cybersecurity and health management is a fundamental requirement in modern chemical industry plants operating under the Industry 4.0 framework. Traditionally, these two concerns have been addressed independently, despite sharing multiple underlying elements which suggest the viability of a unified detection and localization solution. This study introduces a computational intelligence framework based on fuzzy techniques, which allows for the early identification and precise localization of both faults and cyberattacks, along with the capability to recognize previously unseen events during runtime. Once new events are identified and classified, the training database is updated, creating a mechanism for continuous learning. This integrated approach simplifies the computational complexity of supervisory systems and enhances collaboration between the Operational Technology and Information Technology teams within chemical plants. The proposed methodology demonstrates strong robustness and reliability, even in complex conditions characterized by noisy measurements and disturbances, achieving outstanding performance due to its excellent discrimination capabilities. Full article

This paper proposes an improved analytical model for a line-start explosion-proof magnet synchronous motor that considers the effect of magnetic bridge saturation. Under the condition of maintaining the air-gap magnetic field unchanged, and taking into account the topological structures of embedded magnets, squirrel cages, and rotor slot openings, a subdomain model partitioning method is systematically investigated. Considering the saturation effect of the magnetic bridge of the rotor, the equivalent magnetic circuit method was utilized to calculate the permeance of the saturated region. It not only facilitates the establishment of subdomain equations and corresponding subdomain boundary conditions, but also ensures the maximum accuracy of the equivalence by maintaining the topology of the rotor. The motor was partitioned into subdomains, and in conjunction with the boundary conditions, the Poisson equation and Laplace equation are solved to obtain the electromagnetic performance of the motor. The accuracy of the analytical model is verified through finite element analysis. The accuracy of the analytical model is verified through finite element analysis (FEA). Compared to the FEA, the improved model maintains high precision while reducing computational time and exhibiting better generality, making it suitable for the initial design and optimization of industrial motors. Full article

Helical idler gear transmission systems can adapt to high-speed, heavy-load working environments and are thus widely used in aerospace, shipbuilding, and other heavy industry sectors. Root crack is one of the common fault types. Prior studies generally only considered cracks at a single working flank, lacking comparative analysis between the crack at the working flank and the non-working flank. This paper examines the dynamic response of helical idler gears with root cracks at different working flanks, comparing dynamic response differences between working and non-working flank cracks. First, a comprehensive dynamics model of the helical idler gear system is established. Second, the influence of root crack location (the working flank or the non-working flank) on time-varying meshing stiffness is considered based on potential energy method, and a flexible model is established by finite element method for the faulty gear. Finally, solution results of the rigid-flexible coupling dynamics model are analyzed. The dynamic response signal characteristics of root cracks at the working flank and the non-working flank are analyzed in time domain, frequency domain and time frequency domain, respectively. Corresponding experiments are designed based on the FZG experimental platform, and the experimental results are in good agreement with the simulation results, which verified the accuracy of the model. Full article

The thin and straight horn of the ultrasonic transducer is located in the center of the thick transducer, so that the tool tip of the ultrasonic vibration turning tool holder cannot be located on the outermost side of the entire tool holder, which leads to the structural interference between the tool holder and the part during turning. In order to solve this problem, this paper proposes a longitudinal-bending elliptical vibration ultrasonic transducer with a bending horn for ultrasonic vibration-assisted cutting (UVAC). The designed transducer can be used for the partial separation continuous high-speed elliptic ultrasonic vibration cutting (HEUVC) of external surface and internal cavity. The ultrasonic vibration amplitude of the transducer can meet the needs of HEUVC. When using an ultrasonic transducer with a bending horn for HEUVC, compared with conventional cutting (CC), HEUVC can improve the tool life by about 50%. Full article

Bearings are essential rotational components that enable mechanical equipment to operate effectively. In real-world industrial environments, bearings are subjected to high temperatures and loads, making failure prediction and health management critical for ensuring stable equipment operations and safeguarding both personnel and property. To address long-tail defect identification, we propose a coupled time–frequency attention model that accounts for the long-tail distribution and pervasive noise present in production environments. The model efficiently learns amplitude and phase information by first converting the time-domain signal into the frequency domain with the Fast Fourier Transform (FFT) and then processing the data using a real–imaginary attention mechanism. To capture dependencies in long sequences, a multi-head self-attention mechanism is then implemented in the time domain. Furthermore, the model’s ability to fully learn features is enhanced through the linear coupling of time–frequency domain attention, which effectively mitigates noise interference and corrects imbalances in data distribution. The performance of the proposed model is compared with that of advanced models under the conditions of imbalanced label distribution, cross-load, and noise interference, proving its superiority. The model is evaluated using the Case Western Reserve University (CWRU) and laboratory bearing datasets. Full article

Effective fault diagnosis in rotating machinery means extracting fault features from complex samples. However, traditional data-driven methods often overly rely on labeled samples and struggle with extracting high-order complex features. To address these issues, a novel Multi-Metric Fusion Hypergraph Neural Network (MMF-HGNN) is proposed for fault diagnosis in rotating machinery. The approach involves constructing hypergraphs for sample vertices using three metrics: instance distance, distribution distance, and spatiotemporal distance. An innovative hypergraph fusion strategy is then applied to integrate these normalized hypergraphs, and a dual-layer hypergraph neural network is utilized for fault diagnosis. Experimental results on three different fault datasets demonstrate that the MMF-HGNN method excels in feature extraction, reduces reliance on labeled samples, achieving a classification accuracy of 0.9965 ± 0.0025 even with only 5% of labeled samples, and shows strong robustness to noise across varying signal-to-noise ratios. Full article

In aerospace manufacturing, the reliability of machining equipment, particularly spindle bearings, is critical to maintaining productivity, as bearing health significantly constrains operational efficiency. Accurate prediction of the remaining useful life (RUL) of bearings can preempt failures, reduce downtime, and boost productivity. While conventional BiGRU-based models for bearing RUL prediction have shown promise, they often overlook handcrafted extracted time-series features that could enhance accuracy. This study introduces a novel model, BiGRU-ASSA-iTransformer, that integrates deep learning and handcrafted feature extraction to improve RUL prediction. The approach employs two parallel processes with a fusion step: First, a bi-directional gated recurrent unit (BiGRU) captures dynamic degradation features from raw vibration signals, with an adaptive sparse self-attention (ASSA) mechanism emphasizing short-term degradation cues. Second, 13 time-domain, frequency-domain, and statistical features, derived from traditional expertise, are processed using iTransformer to encode temporal correlations. These outputs are then fused via an attention mechanism. Experiments on the PHM 2012 and XJTU-SY datasets demonstrate that this model achieves the lowest prediction error and highest accuracy compared to existing methods, highlighting the value of combining handcrafted and deep learning approaches for robust RUL prediction in aerospace applications. Full article

Wave-based control (WBC) offers a relatively novel approach to the challenge of controlling flexible mechanisms by treating the interaction between actuator and system as the launch and absorption of mechanical waves. WBC is a robust approach but has been unexplored in active suspension systems to date. This study adapts WBC to a quarter-car suspension model. Having embedded an actuator as the active element of a car suspension, a novel but simple ‘force impedance’ adaptation of WBC is introduced and implemented for effective vibration control. Testing with various input signals (pulse, sinusoidal, and random profile) highlights the active system’s significant ride comfort and rapid vibration suppression with zero steady-state error. Compared to two other models—one employing an ideal skyhook strategy and the other a passive suspension—the active system utilizing WBC outperforms across many criteria. The active controller achieves over 38% superior ride comfort compared to the skyhook model for a pulse road input. This is accomplished while adhering to WBC principles: relying solely on actuator-interface measurements, simplicity, cost-effectiveness, with no need for detailed system models, extensive sensors, or deep system knowledge. Full article

The detrimental effects of low-frequency vibrations on the measurement accuracy of commercial high-precision instrumentation demand urgent resolution, particularly for instruments requiring <1 μm positioning stability. Conventional base-mounted active damping systems exhibit limitations in suppressing the structural resonance induced by passive isolators—especially when the environmental vibration intensity surpasses the standard thresholds. Therefore, in this study, we developed an innovative multi-mode control architecture to substantially enhance the vibration-damping capabilities of the DCSMS. The proposed methodology synergistically integrates foundation vibration isolators with embedded passive modules through a dual-stage spring-mass system optimization framework. Experimental validation combining ADAMS–MATLAB multi-physics co-simulation, complemented by a decoupling analytical control model based on the vibrational transmission characteristics of the source propagation path, substantiated the efficacy of the proposed control methodology. Full article

A high-gear-ratio anti-backlash 3K planetary gearbox with a preloaded flexure-based carrier is a suitable reducer for robot joints owning to its compact design and high transmission accuracy. However, to design such a 3K planetary gearbox with high bidirectional efficiencies for backdrivable robot joints, it is critical to develop an accurate transmission efficiency model to predict the effects of the preloaded flexure-based carrier on the efficiency of the 3K planetary gearbox. To determine the meshing forces of gear pairs in the 3K planetary gearbox, a quasi-static model is formulated according to tangential displacements of planet gears resulting from the preloaded flexure-based carrier. Considering the reverse meshing forces in the anti-backlash 3K planetary gearbox, a modified efficiency model is developed and the bidirectional transmission efficiencies are analyzed. Simulation results show that both forward and backward transmission efficiencies of the anti-backlash 3K planetary gearbox decrease as the preload increases, while they all increase with the increasing load torque. It is also revealed that the preload primarily affects the meshing efficiency of the sun–planet gear pair. Four different carrier prototypes are fabricated for experiments. The average errors between the predicted and measured results for forward and backward transmission efficiencies are 2.30% and 4.01%, respectively. Full article

McKibben’s muscle (MKM) is the most adopted among the different types of pneumatic artificial muscles (PAMs) due to its mechanical performance and versatility. Several geometric parameters, including the diameter, thickness, and length of the inner elastic element, as well as functional conditions, such as shortening ratio and feeding pressure, influence the behaviour of this actuator. Over the years, analytical and numerical models have been defined to predict its deformation and developed forces. However, these models are often identified under simplifications and have limitations when integrating new parameters that were not initially considered. This work proposes a hybrid approach between finite element analyses (FEAs) and machine learning (ML) algorithms to overcome these issues. An MKM was numerically simulated as the chosen parameters changed, realizing the MKM dataset. The latter was used to train 27 artificial neural networks (ANNs) to identify the best algorithm for predicting the developed forces. The best ANN was tested on three numerical models and a prototype with a combination of parameters not included in the dataset, comparing predicted and numerical responses. The results demonstrate the effectiveness of ML techniques in predicting the behavior of MKMs while offering flexibility for integrating additional parameters. Therefore, this paper highlights the potential of ML approaches in the mechanical design of MKM according to the field of use and application. Full article

As the field of robotics advances swiftly, industrial automation has become prevalent in the realms of manufacturing and precision measurement. In robot measurement applications, the original path often originates from the discrete output of CAD models or point cloud data of vision systems, and its measurement path is a linear path composed of discrete feature points. Vibrations are generated by robots when passing through corners between adjacent linear segments. In order to reduce vibration, an algorithm for smoothing the robot’s measurement path based on multiple curves is proposed. Based on the proposed robot scanning measurement path generation algorithm, a robot scanning measurement path is generated. The position and attitude of the scanning path are represented as multiple curves using a position and attitude representation method based on multiple curves. The corners of the position curve and attitude curve are smoothed using a 5th-order B-spline curve. Based on the established robot position tolerance and attitude tolerance constraints and geometric continuity, the control points of the B-spline curve are solved, and corresponding position corner smooth B-spline curves and attitude corner smooth B-spline curves are constructed. Based on the geometric continuity, we use B-spline curves to replace the transition parts of adjacent position corner points and adjacent attitude corner points in the scanning path and then achieve the synchronization of robot position and attitude by the common curve parameter method. Finally, the effectiveness of our proposed path smoothing algorithm was verified through robot joint tracking experiments and scanning measurement experiments. Full article