Journal of Mechatronics and Artificial Intelligence in Engineering
Not a member yet
1200 research outputs found
Sort by
Enhancing loess deformation resistance using waste tire rubber particles
Get PDFLoess, characterized by its large pore structure and vertical joints, is prone to collapsible deformation upon moisture infiltration and significant settlement under load, threatening the stability of buildings and infrastructure. This study systematically investigates the effects of rubber particle size (10, 20, 40, and 100 mesh), content (0 %, 5 %, 10 %, 15 %, and 20 % by volume), moisture content, and freeze-thaw cycles on the deformation properties of loess. This systematic investigation distinguishes itself by using waste tire rubber particles as the sole amendment to elucidate both the individual and coupled effects of these factors. Results demonstrate that incorporating rubber particles significantly reduces the compression coefficient of loess, with optimal compressibility achieved at a 5 % rubber particle content and 40 mesh particle size. The collapsibility coefficient is minimized at a 20 mesh particle size with the same 5 % content. Moisture content significantly influences deformation behavior, with both high and low levels increasing the compression and collapsibility coefficients. The study also reveals that rubber particle-loess mixtures exhibit superior freeze-thaw resistance, with smaller increases in deformation coefficients after multiple freeze-thaw cycles compared to remolded loess. The particle size and content of rubber particles are identified as the most important factors influencing the compressibility and collapsibility of loess. This research provides specific guidelines for optimizing rubber particle size and content, controlling moisture levels, and evaluating freeze-thaw impacts to enhance the engineering performance of loess. The findings offer a scientific basis for sustainable waste tire management and advance the application of rubber particles in geotechnical engineering
A vision-based deep learning approach for non-contact vibration measurement using (2+1)D CNN and optical flow
Get PDFThis paper introduces a proof-of-concept vision-based deep learning approach for vibration measurement, proposing a factorized (2+1)D Convolutional Neural Network (CNN) model to predict four vibration metrics: acceleration, velocity, displacement, and frequency, with a focus on rigid body motion. Unlike conventional neural network models that primarily focus on frequency prediction alone, this approach uniquely enables the simultaneous estimation of four critical vibration metrics, offering a comprehensive and cost-effective alternative to traditional contact-based sensors such as accelerometers. The framework relies on the visibility of a training fiducial marker, eliminates the need for calibration in controlled settings, enhancing scalability across specific environments. A curated dataset was generated using a controlled experimental setup comprising a single object in a lab-scale environment, augmented synthetically to enhance frequency diversity. An optical flow-based preprocessing algorithm synchronized motion features in recorded video inputs with measured vibration labels, improving measurement accuracy. The proposed model achieved an average Mean Absolute Percentage Error (MAPE) of 7.51 %, with acceleration predictions exhibiting the lowest error at 4.84 % and displacement the highest at 8.80 % across varying brightness levels and object-camera distances. Techniques such as Region of Interest (ROI) cropping and multi-section frame extraction were implemented to reduce computational complexity while further enhancing accuracy. These results highlight the framework’s potential for non-invasive vibration analysis, though its generalizability is limited by the single-object dataset. Future work will expand the dataset, integrate multi-sensor inputs, explore marker-less tracking methods, and enable real-time deployment for predictive maintenance and structural health monitoring
Reinforcement of the embankment with reinforced concrete piles in the transition zone from the railway embankment to the bridge
Get PDFThe article presents the design of the transition section to be used in different conditions in the region of junction of roadbed and the bridge, establishment and reasons of vertical shifts under the action of vibro-dynamic forces which appear when trains are driven along transition section. Likewise, in the sections of the foundation of the roadbed and the bridge, the types and types of a variety of defects caused by this fact, such as when the pressure of the weight of constant and temporary forces dropped on the rolling stock passes the active pressure of the ground (Ea), which acts on the support of the bridge shore at the point of the passage, are provided. In order to minimize the active effort at the junction formed by soil, reinforce and make the junction location defect-free, reinforced concrete piles are driven into the embankment to act as bases of junction location between the roadbed of the railway and the bridge location and a formula of computing the spacing of the piles has been contributed taking into consideration outer influences
Evaluation and modeling of airborne dust pollution in the Kamchik railway tunnel during train movements
Get PDFThis paper presents the results of a study on airborne dust pollution in the Kamchik Railway Tunnel caused by train movements. Field measurements were carried out to determine the concentrations of suspended particulate matter (PM10, PM2.5, PM1), as well as air temperature, pressure, and humidity in different sections of the tunnel – near the portals and in its central part. It was established that during train passages, the level of dust concentration increases by 6-10 times compared to background values, exceeding sanitary and hygienic standards. The main sources of dust generation were identified as frictional interactions between wheels and rails, braking processes, and the transportation of bulk materials. To reduce dust concentrations, engineering solutions are proposed, including the implementation of automatic water-based dust suppression systems, enhanced tunnel ventilation, and the use of hydrophobic surface coatings. The obtained results can be used to optimize ventilation modes and improve the operational safety of the Kamchik Railway Tunnel
Die casting mold design of CH367B1 aluminum alloy throttle valve body
Get PDFAs a core component of the automotive engine intake system, the throttle valve body is subjected to long-term engine vibrations. Defects such as gas pores and shrinkage pores in the die-cast part will cause uneven stiffness of the throttle valve body, and thus lead to fatigue failure due to local stress concentration under vibration loads. In this paper, the aluminium alloy was used as the die-casting alloy to design an efficient and simple die-casting mould for CH367B1 aluminium alloy throttle valve body. After measuring the target dimensions and conducting a preliminary analysis of the UG 3D drawing of the part, the size and structure of the valve body were analysed according to the 3D model of the part to select the appropriate parting surface. In the design process, the clamping force, chamber capacity, projected area and other parameters were calculated in order to select a suitable die-casting machine. Part-related dimensions and features were analyzed. Push-out mechanisms, molded parts, guide mechanisms, etc. were designed. The whole set of molds was obtained. Suitable casting systems were designed by calculating and checking references. Mold flow analysis was carried out using ProCAST2021 software. The optimal solution was selected by observing the liquid metal filling process and the distribution of defects, and then calibrated
Establishing the natural frequency of oscillations of a continuous system with a concentrated mass in aviation and manufacturing engineering
Get PDFThe uneven transportation of products in the working bodies (trays) of one-mass vibrating conveyors with inertial exciters prompted the conduct of a study aimed at establishing the natural frequency of oscillations of a continuous system, namely, a long-dimensional body with distributed parameters in the form of a beam with a rigidly fixed concentrated mass. Using the Krylov-Duncan functions, the differential equation of movement of the beam was solved, taking into account the concentrated mass and the boundary conditions at its ends. The system of equations made it possible to analytically establish the natural frequency of such a continuous system. This approach was tested to establish the natural oscillation frequency of a glider, demonstrating its versatility for use in various industries. An analysis of the obtained results was carried out, and conclusions were drawn
Design and verification of a new type of hydraulic vibration isolator for high-speed train floors
Get PDFWith the development of high-speed trains, the requirements for noise, vibration, and comfort are becoming increasingly stringent. The train body floor, as one of the main pathways for vibration transmission, is crucial to be treated for vibration reduction and noise attenuation. This paper, in response to this demand, has developed a new type of floor vibration isolator specifically for high-speed trains. Through finite element simulation analysis and experimental verification, it has been proven that this vibration isolator can effectively reduce the vibration of the train body floor and significantly enhance the NVH (Noise, Vibration, and Harshness) performance of the train
An integrative review of control strategies in robotics
Get PDFThis paper presents an integrative review of control strategies in robotics, covering classical control methods (linear quadratic regulator, proportional-integral-derivative), modern methods (adaptive, sliding mode, model predictive, and H-infinity), intelligent control methods (neural network, fuzzy logic, and machine learning), and hybrid control methods (integration of classical, modern, and intelligent control methods) to identify the advantages, limitations and gaps for future. A brief comparison of control methods between the types of control strategies is conducted with respect to robustness, stability, and complexity of implementation on 3 different levels of evaluation criteria: high, average, and low; advantages; limitations; and robotic applications, including examples. This paper discusses the theoretical and practical advancements and the classification of control strategies according to controller types (linear, nonlinear, and learning-based), approaches (model-based and model-free), and classifications (centralized, decentralized, and modal control). The review highlights the strengths, limitations, and potential research directions in bridging classical, modern, intelligent, and hybrid control paradigms to achieve safe, efficient, and adaptive robotic behavior in complex, uncertain environments. We discuss the future direction: autonomy, human-robot collaboration, and enhanced learning and challenges: cost, reliability, safety of control strategies, concluding with recommendations for future research
The effect of Cranial Postural Balance (CPB) appliance on re-establishing mandible and body posture in an adult patient. Case report
Get PDFThis case report intends to present a functional appliance designed by the first author, that follow the principles expected for all functional appliances. It is not anchored on teeth. It does not produce mechanical forces and uses tongue and mandible posture change as natural forces. The appliance was used for 24 months, only to sleep. The patient came complaining discomfort with improper occlusion of the teeth and temporomandibular pain. Body balance was evaluated by DIERS and was also altered. It was possible to find out the presence of a unilateral crossbite and alteration on condyle position inside the cavity evaluated by CBCT. After the treatment with CPB (Cranial Posture Balance) appliance associated with osteopathic procedures, the occlusion and the temporomandibular complains were improved
Dual-aggregation feature compilation network for urban traffic object detection and pedestrian pose estimation
Get PDFWith the increasing complexity of urban transportation systems, object detection and pedestrian pose estimation play a crucial role in intelligent traffic management and autonomous driving technologies. However, existing feature compilation networks are often designed for single tasks and perform poorly in small object detection and high occlusion pedestrian pose estimation tasks. To address the above issues, this paper proposes an efficient feature compilation network with Dual-aggregation, compatible with both object detection and pedestrian pose estimation. This network adopts a transfer learning-like training strategy in the feature extraction network, using a micro-complex convolution structure during training to bring the training results as close as possible to global optimization. During inference, a single simple convolution is used to inherit the training results, improving the model performance while ensuring model lightweight. The feature fusion employs a global-local dual aggregation structure, simultaneously considering multi-scale global and local features. Additionally, we use multiple public datasets to create a hybrid dataset under various scenarios to validate the robustness of the network. The experiments show that the proposed method outperforms existing mainstream methods in detection accuracy for urban object detection and pedestrian pose estimation tasks, especially demonstrating better robustness in complex urban traffic scenarios