Hasil untuk "Mechanical engineering and machinery"

Bilquees Bozdar, N. Ahmed, Mehtab Rai Meghwar et al.

Seed pelleting is an emerging precision‐agriculture technology that transforms small or irregular seeds into uniform units to enhance mechanical sowing, placement accuracy, and early crop establishment. Pelleting performance depends on the interplay among binder–filler composition, pellet structure, and post‐pelleting moisture conditions, which collectively influence durability, germination, and seedling vigor. Recent developments include biodegradable and bio‐based materials, biochar and micronutrient additives, and biological agents that enhance stress tolerance and early growth. Advances in pelleting machinery and quality‐control tools have improved uniformity and process automation, while nano‐enabled and stimuli‐responsive coatings introduce new opportunities for controlled release and climate‐resilient applications. Integrating mechanistic insights on filler–binder interactions with digital technologies such as artificial intelligence (AI) offers a pathway toward more consistent and scalable formulations. Despite these gains, adoption remains limited in smallholder systems due to cost, access, and material constraints. Seed pelleting represents a converging frontier of material science, engineering, and sustainable agriculture, with significant potential to improve input efficiency and contribute to resilient food systems.

David A. Brattley, Wayne W. Weaver

This paper introduces a reinforced learning-based supervisory control architecture that oversees multiple Recursive Least Squares (RLS) based self-tuning pump controllers and determines when each loop is permitted to adapt its gains. The supervisor learns adaptation policies that minimize interaction between loops while preserving responsiveness to changing hydraulic conditions. A two-loop pump station simulation is used to evaluate performance under product changes and transient flow disturbances. The results show that the supervisory layer reduces the number of simultaneous adaptation events by over 70%, leading to a 32% lower pressure-tracking error and 45% fewer gain-induced oscillations compared to conventional independent adaptive control. The reinforcement learning policy converges within 15 training episodes, resulting in stable adaptation scheduling and seamless transitions. The key novelty of this work lies in introducing decentralized reinforcement-learning-based coordination for adaptive pump control, enabling supervisory decision-making that actively prevents interference between controllers during transients. This approach provides a scalable and lightweight solution for coordinating multi-loop pump stations, enhancing robustness and operational performance in real-world pipeline systems.

Lunpan Wei, Xiuyan Peng, Yunpeng Cao

Tie Chang, Yifan Zheng, Mingrui Jiang et al.

Yanchen Ye, Jinhai Wang, Jianwei Yang et al.

With advancements in industrial automation, the accurate prediction of the remaining useful life (RUL) in bearings is crucial for the proactive maintenance and reliability of industrial machinery. Traditional machine learning approaches often rely heavily on manual feature engineering and struggle to capture complex, nonlinear interdependencies between features that are vital for understanding machinery behavior under varying operational conditions. Addressing these limitations, our research introduces an innovative deep learning framework that integrates multiadaptive graph neural networks (MAGNNs) with temporal convolutional networks (TCNs), thereby harnessing the power of graph-based learning to model complex interdependencies directly from raw sensor data. Our MAGNN framework employs a dynamic adjacency matrix that adapts to reflect the changing operational states of bearings, enabling the model to maintain high predictive accuracy even under fluctuating conditions. This adaptability is enhanced through a multiscale feature extraction strategy that captures temporal patterns across different resolutions, providing a comprehensive feature set that is robust against environmental noise and operational variability. Experimental validation on the PHM2012 and XJTU datasets indicates the advanced performance of our MAGNN framework, significantly outperforming established AI benchmarks such as GNN-TCN, GNN-GRU, and Transformer models. In particular, the MAGNN-TCN configuration achieves a substantial improvement, reducing RMSE by up to 36.04% and reducing MAE by up to 34.19% when compared to the best of these conventional graph-based and sequence models. This performance boost highlights the effectiveness of our approach in leveraging dynamic, adaptive graph structures and multiscale feature extraction, which are crucial for capturing the complex nonlinear interrelationships inherent in sensor data from mechanical systems.

Haibin Sun, Weilong Zhu

ABSTRACT Fault diagnosis of rolling bearings is of paramount significance in the field of engineering, as it directly impacts the reliability and safety of mechanical systems. Although deep learning techniques have demonstrated promising performance in this field, their efficacy often diminishes under varying operational conditions or when labelled data is limited. To overcome these challenges, this paper introduces a more precise cross-domain approach for bearing fault diagnosis. The proposed method exploits the temporal multiscale characteristics of vibration signals and the inherent multiscale nature of bearing faults by constructing a one-dimensional multiscale convolutional neural network. This network extracts features at multiple scales from raw vibration signals, which are then fused to form robust and generalised representations. Additionally, the integration of the Efficient Channel Attention mechanism further refines feature selection, enhancing the overall performance of the model. The label classifier, in conjunction with the Nuclear-norm Wasserstein Discrepancy, serves as a domain discriminator to facilitate adversarial domain adaptation. Concurrently, local maximum mean discrepancy and adversarial domain adaptation techniques align both global and subdomain feature distributions. Furthermore, label smoothing is incorporated to enhance the model’s generalisation capabilities. Experimental validation on the CWRU and PU rotating machinery datasets demonstrates the method’s exceptional robustness and superior transferability.

Chun Zhang, Junjie Liu, Y. Shao et al.

The triboelectric nanogenerator (TENG) is an efficient mechanical energy harvesting device that exhibits excellent performance in the fields of micro-nano energy harvesting and self-powered sensing. In practical application scenarios, it is very important to monitor the speed of rotational machinery in real time. In order to monitor a wider range of rotational speeds, the TENG based on a machine learning algorithm is designed in this paper. The peak power of the TENG reaches a maximum of 6.6 mW and can instantly light up 65 LEDs connected in series. The results show that machine learning can detect speed, greatly improving the speed detection range. The neural network is trained and tested based on the collected electrical signals at different speeds so as to monitor the health of the machine. For the analysis of the collected experimental data, normalization data and a more practical label assignment method of Gaussian soft coding were considered. The study found that after data normalization, the classification prediction accuracy for different speeds is above 0.9, and the prediction results are stable and efficient. Therefore, the machine learning prediction model for speed monitoring proposed by us can be applied to the early warning and monitoring of rotating machinery speed in actual engineering projects.

Peng Liu, Chunyu Song, Jin He et al.

Crop straw chopping and returning technology has gained global implementation to enhance soil structure and fertility, facilitating increased crop yield. Nevertheless, technological adoption faces challenges from inherent limitations in machinery performance, including poor chopping and returning quality and high energy consumption. Consequently, this review first presented a theoretical framework that described the mechanical properties of straw, its fracture dynamics, interactions with airflow, and motion characteristics during the chopping process. Then, based on the straw returning process, the chopping devices were classified into five types: the chopped blade, the chopping machine, the chopping device combined with a no-tillage or reduced-tillage seeder, the chopping and ditch-burying machine, the chopping and mixing machine, and the harvester-powered chopping device. Advancements in spreading devices were also summarized. Finally, six key directions for future research were proposed: developing an intelligent field straw distribution mapping system, engineering adaptive self-regulating mechanisms for chopping and returning equipment, elucidating the mechanics and kinematics of straw in the chopping and returning process, implementing real-time quality assessment systems for straw returning operations, pioneering high forward-speed (>8 km/h) straw returning machines, and establishing context-specific straw residue management frameworks. This review provided a reference and offered support for the global application of straw returning technology.

Paramvir Yadav, Kaushal Kumar, Prawar Chaudhary et al.

Purpose This study aims to investigate the effect of varying load and rotational speed on the pressure distribution characteristics of mild steel-based hydrodynamic journal bearings. Understanding these influences is crucial for optimizing lubrication performance, minimizing friction and enhancing bearing durability. By analyzing pressure variations under different operational conditions, the research provides insights into improving bearing design and predictive maintenance strategies. The findings contribute to the advancement of tribology and mechanical engineering by offering a better understanding of fluid film behavior, ultimately leading to more efficient and reliable bearing systems in industrial applications. Design/methodology/approach This study employs an experimental approach to analyze the performance characteristics of mild steel-based hydrodynamic journal bearings under varying load and speed conditions. A test rig was designed to measure circumferential pressure distribution using SAE 20W40 lubricant at rotational speeds of 250, 500 and 750 RPM and loads of 0, 0.25 and 0.50 kg. Optical Emission Spectroscopy (OES) was used for material characterization. Taguchi optimization with an L18 orthogonal array and analysis of variance (ANOVA) analysis were applied to identify key influencing factors. The findings provide insights into lubrication dynamics and bearing efficiency, contributing to improved predictive maintenance and bearing design. Findings The study reveals that rotational speed significantly influences the pressure distribution in hydrodynamic journal bearings compared to applied load. Maximum pressure is observed at higher speeds, with peak values occurring between 120° and 150° bearing angles. Increased speeds enhance lubricant film stability, reducing metal-to-metal contact and improving bearing efficiency. Load variations shift the pressure peak but have a lesser impact on overall pressure distribution. Taguchi optimization and ANOVA confirm that speed is the dominant factor affecting bearing performance. These findings provide valuable insights for optimizing journal bearing design and improving lubrication strategies in rotating machinery applications. Research limitations/implications This study is limited to experimental investigations under controlled laboratory conditions, focusing on mild steel-based hydrodynamic journal bearings using SAE 20W40 lubricant. Variations in environmental factors, bearing materials and lubricant properties may influence real-world performance. Originality/value This study provides a novel experimental investigation into the pressure distribution characteristics of mild steel-based hydrodynamic journal bearings under varying load and speed conditions. Unlike previous research, it integrates Taguchi optimization and ANOVA to systematically analyze the influence of operational parameters. The findings offer new insights into lubrication dynamics, highlighting the dominant role of rotational speed in enhancing bearing efficiency. The study’s practical implications contribute to optimizing journal bearing design, reducing frictional losses, and improving predictive maintenance strategies. These results are valuable for researchers and engineers working on tribology, mechanical systems and industrial lubrication technologies.

K. Sherov, Medgat Мussayev, Ainur Тurusbekova et al.

This study aims to enhance the technological capabilities of additive manufacturing and to assess their applicability in the repair and maintenance sector of the agro-industrial complex of Kazakhstan. The research investigates the feasibility of fabricating hydraulic machine components, particularly gear pump (GP) parts, using additive methods. The approach integrates concepts of additive manufacturing, materials science, mechanical engineering, design and strength assessment, and computer simulation. An experimental case study was conducted on a GP shaft-gear, produced via the FDM method on a Raise3D Pro Plus 3D printer. Finite element analysis in SolidWorks demonstrated that the printed shaft-gear withstands operational loads, with maximum stress of 18.45 MPa, remaining within acceptable limits for polymer-based 3D printing materials. Stress calculations for PLA specimens further confirmed that both stresses and deformations are below critical thresholds, ensuring operational reliability. The novelty of this work lies in validating the structural integrity of functional pump components produced by additive manufacturing, which has been insufficiently studied in repair applications. The results provide a scientific basis for expanding the use of additive technologies in hydraulic machinery and highlight their potential to improve efficiency and cost-effectiveness in industrial repair processes.

Masae HAYASHI, Hiroshi OKUDA, Kazuhisa INAGAKI et al.

Short fiber reinforced rubber composites (SFRRCs) are crucial, lightweight, and durable materials used across various industries. We've developed a simulator for full rubber belt-pulley friction contact behavior utilizing the large-scale parallel FE structural software FrontISTR. However, accurately integrating SFRRC's complex material behavior into this already large-scale simulation presented a significant challenge: traditional solid element modeling for both rubber and fibers proved impractically expensive. To overcome this, we developed and added an insert element function to FrontISTR. This function represents short fibers as embedded truss elements within the solid rubber matrix and supports distributed-parallel computation based on domain decomposition. The proposed method was verified by comparing the results obtained using the specimen model with actual short fiber orientations to those from commercial software. Our approach significantly reduces the computation time, achieving a speed-up of 400 times compared to conventional analysis with solid elements.

Guoqing Zhang, Junxin Li, Xiaoyu Zhou et al.

The powder-laying arm of a metal 3D printer is heavy, which can easily cause long-term damage to the powder-laying servomotor or belt, so it is necessary to design a lightweight powder-laying arm. To this end, we first use 3D modeling Rhino software to rebuild the powder-laying arm, and then, we carry out topology optimization design on the rebuilt powder-laying arm in Altair Inspire software. Finally, we use the Aurora Elva 3D printer to complete manufacturing and assembly to verify compatibility. The results show that the maximum displacement of the original powder-spreading arm is concentrated in the lower right corner at 4.319 × 10⁻⁵ mm; the maximum stress is concentrated in the middle transition part, decreasing toward the ends; the maximum stress is 3.843 × 10⁻² MPa; the stress concentration and deformation of the powder-spreading arm when spreading powder is small, which provides a large optimization space. The topology-optimized powder-spreading arm, with a 25% quality objective, maintains the integrity of the connection with the fixing hole while having a large mass reduction. The surface of the parts of the completed 3D-printed powder arm is bright, with low roughness, and there is no obvious warping and deformation or other defects; the completed 3D-printed powder-spreading arm and the assembly of the wall are closely coordinated with each other, and the location of the screw holes is appropriate, having no obvious assembly conflicts between the parts, which lays the foundation for the mass production of the powder-spreading arm of high-performance metal 3D printers.

Mingjie Cui, Huixiang Yang, Dawei Jiang et al.

Xuyang Cao, Baokang Yan, Kai Lin et al.

Pengfei Yang, Luhong Yue, Jing Yang

Dhrishya Shetty, K. K, Nirupama G N et al.

Scattering Wavelet Networks (SWNs) have emerged as a very strong and mathematically sound competitor to conventional feature extraction and deep learning techniques. It is designed for signal and image processing; their scope has expanded to other domains in mechanical engineering where accurate and dependable interpretation of intricate data is critical. This review discusses the application of Scattering Wavelet Transforms (SWT) and Wavelet Scattering Networks (WSNs) in mechanical systems, particularly their application in fault detection, non-destructive testing, structural health monitoring, and material classification. Through the utilization of the multiscale, multi-resolution properties of wavelet transforms and the stability of scattering networks, researchers have made significant improvements in the classification accuracy and model interpretability. This provides an overview of important methodologies, performance comparison, and hybridization of SWNs with other machine learning models in various high-impact studies. The results validate the promise of SWNs as a revolutionary tool in the development of mechanical diagnostics reliability and intelligence.

Huibin Wang, Changfeng Yan, Yingjie Zhao et al.

Rolling bearing plays an important role in carrying and transmitting power in rotating machinery, and the bearing fault is easy to lead to mechanical accidents, resulting in huge losses and casualties. Therefore, the condition monitoring and diagnosis of rolling bearings are very important to improve the safety of equipment. Compound fault is a common fault evolved from the initial defect, which is characterized by randomness, coupling, concealment, and secondary. The existence of these characteristics brings great challenges to the accurate diagnosis of compound faults. In the diagnosis of compound faults, the traditional methods that select the single optimal demodulation frequency band for analysis and identification sometimes cannot completely extract multiple fault components, which are prone to miss diagnosis and misdiagnosis. In order to solve this problem, the SEACKgram method is proposed by constructing a Square Envelope Unbiased Autocorrelation Correlation Kurtosis (SEACK) index. The frequency band of the original signal is divided by the Maximal Overlap Discrete Wavelet Packet Transform, and the SEACK index is used to quantitatively describe the fault signals of different frequency bands. According to the different fault periods, the resonant frequency bands of the maximum SEACK value are selected, then the resonance band signal is analyzed by square envelope spectrum, and the fault type is identified according to the fault characteristic frequency. The simulated and experimental vibration signals of rolling bearings with compound faults are used to verify the feasibility of the proposed method. The results show that the proposed SEACKgram can improve the accuracy of compound faults identification and would be applied in engineering practice to a certain extent.

Huibin Wang, Changfeng Yan, Yaofeng Liu et al.

As the main part of industrial rotating machinery, rolling bearings play an important role in improving the efficiency of mechanical equipment. Due to the influence of the complicated working environment, the single fault is easy to develop into the compound fault. The accurate identification of compound faults can effectively assess the severity of bearing damage, and can provide references for the continued use or replacement of bearings by technicians. The compound faults of rolling bearings are characterized by coupling, concealment, and complex resonance. For the diagnosis of compound faults, the “blind” methods that select the single optimal demodulation frequency band for analysis and identification sometimes cannot completely extract multiple fault components, and some “target” methods cannot effectively extract fault features because they do not consider the influence of random slip of bearing. In order to solve this problem, the LFIgram method is proposed by constructing the log envelope autocorrelation slice bispectrum (LEAB) and LEAB feature index (LFI). The frequency band of the original signal is divided by the maximal overlap discrete wavelet packet transform (MODWPT), and the LFI index is used to quantitatively describe the fault signals of different frequency bands. According to the different fault characteristic frequencies (FCFs), the resonant frequency band of the maximum LFI value is selected, the resonance band signal is analyzed by LEAB, and the fault type is identified according to the fault characteristic frequency in the LEAB. The simulated and experimental vibration signals of rolling bearings with compound faults are used to verify the feasibility of the proposed method. The results show that the proposed LFIgram can improve the accuracy of compound faults identification and would be applied in engineering practice to a certain extent.

Manbok Park, Seongjin Yim

This paper presents a method to design a path-tracking controller with an adaptive preview distance scheme for autonomous vehicles. Generally, the performance of a path-tracking controller depends on tire–road friction and is severely deteriorated on low-friction roads. To cope with the problem, it is necessary to design a path-tracking controller that is robust against variations in tire–road friction. In this paper, a preview function is introduced into the state-space model built for better path-tracking performance. With the preview function, an adaptive preview distance scheme is proposed to adaptively adjust the preview distance according to the variations in tire–road friction. Front-wheel steering (FWS) and four-wheel steering (4WS) are adopted as actuators for path tracking. With the state-space model, a linear quadratic regulator (LQR) is adopted as a controller design methodology. In the adaptive preview distance scheme, the best preview distance is obtained from simulation for several tire–road friction conditions. Curve fitting with an exponential function is applied to those preview distances with respect to the tire–road friction. To verify the performance of the adaptive preview distance scheme under variations in tire–road friction, a simulation is conducted on vehicle simulation software. From the simulation results, it was shown that the path-tracking controller with an adaptive preview distance scheme presented in this paper was effective for path tracking against variations in tire–road friction in the peak’s center offset, and the settling delays were reduced by 60% and 23%, respectively.

Ajjanna Roja, Pudhari Srilatha, Umair Khan et al.

This work examines the second law analysis of an electrically conducting reactive third-grade fluid flow embedded with the porous medium in a microchannel with the influence of variable thermal conductivity, activation energy, viscous dissipation, joule heating, and radiative heat flux. A suitable non-dimensional variable is included into the governing equations to transform them into an ensemble of equations that are devoid of dimensions. The acquired equations are then tackled using the Runge Kutta Felhberg 4th and 5th order (RKF-45) approach in conjunction with the shooting methodology. Through comparison with the current results, the numerical results are verified, which provides a good agreement. From the present outcomes, it is established that the entropy generation is supreme for the viscous heating constraint, variable thermal conductivity, Frank Kameneski, heat source ratio parameter and third-grade fluid material constraint. The Bejan number boosts up with larger values of activation energy, and Frank Kameneski constraint and the decreasing nature is noticed for increasing third-grade material parameter, viscous heating parameter. With magnetism, the fluid’s velocity slows down because of a resistive force. A similar impact in the channel on velocity is noticed for larger third-grade fluid, activation energy parameter, and Frank-Kameniski parameters and increasing behavior is noticed for variable thermal conductivity, and permeability parameter. Further, it is cleared that the variable thermal conductivity assumption in the channel plate leads to a significant under prediction of the irreversibility rate.