Journal of Mechatronics and Artificial Intelligence in Engineering
Not a member yet
1200 research outputs found
Sort by
Finite element analysis and vibration simulation of electromagnetic imaging sensor housing based on ANSYS
Get PDFMining sensors work in harsh environments and are subject to complex vibrations. Its internal structure is prone to strength failure or fatigue damage. This paper focuses on the structural design of the front discharge and receiver housing inside the electromagnetic imaging sensor for coal-rock demarcation detection. Static analysis, modal analysis, and random vibration simulation were performed using ANSYS Workbench software to verify its reliability and strength in mining. In the static analysis, the thickness of the designed housing is 2 mm. The maximum equivalent elastic strain after applying a pressure of 0.5 MPa to the housing is 0.133 %, much less than the criterion of material fracture strain. This proves that it has excellent strength properties and will not experience strength failure. Modal analysis shows that the first-order intrinsic frequency of the housing is 3298.7 Hz. It is much higher than the vibration frequency in the actual working environment, which can effectively avoid resonance and improve the reliability of the structure. Random vibration simulation results show that the housing's maximum equivalent force and displacement are within the safe range, and the impact on the structural performance is negligible. These results provide a theoretical basis for the optimal design of the sensor housing and its application in complex vibration environments
Stress-strain state of a welded high-strength steel pipeline in the presence of surface defects
Get PDFThe construction of main pipelines is now predominantly carried out using high-strength steels. This makes it possible to increase pipeline capacity while maintaining the existing pipe geometry. However, the issue of ensuring the strength of such pipelines in the presence of surface defects is still relevant. This is especially true for pipeline segments that are located in hard-to-reach places, and therefore, it is difficult to repair and restore. At the same time, the introduction of high-strength steels involves a complex system of material alloying and special thermo-mechanical strengthening technologies. As a result, special structures of increased strength can be produced, but they are sensitive to reheating, in particular when welding technologies are used. This is due to the formation of a special zone of thermal deformation influence in the vicinity of the weld. Material properties of the pipes differ from their original characteristics. The stress-strain state is formed, which also affects the strength of the welded pipeline. The nature of the stress-strain state of welded joints of pipes made of high-strength materials differs from the well-studied stress distributions in pipelines built in the past sixty-eighty years of the past century. In particular, several localized maxima of stresses can be located not only on the weld axis but also in the zone of thermal deformation influence. Therefore, it is important to evaluate the effect of weld stresses in welded joints of high-strength steel pipes on the strength of the pipeline in the presence of surface defects. Since the defect may be located at an arbitrary distance from the weld axis, the predicted strength of the welded pipeline segment can vary significantly
Small targets detection in low-resolution remote sensing images based on super-resolution joint optimization
Get PDFWhile convolutional neural networks have driven remarkable progress in remote sensing object detection, persistent challenges remain in detecting small targets within low-resolution imagery due to their limited pixel representation and feature degradation during hierarchical downsampling. To address this, this study proposed the joint super-resolution and detection network (JSRDN), which synergistically optimizes SR reconstruction through task-specific detection feedback, significantly enhancing small target recognition in LR remote sensing imagery. Firstly, generator in generative adversarial network incorporates improved residual blocks, enabling enhanced perception of complex deep-level features in the SR reconstruction process. Then, a perceptual loss function is introduced into the adversarial training process, which captures perceptual discrepancies in high-level features between reconstructed images and original HR references. After that, an edge-enhancement network is designed to dynamically detect edges in intermediate features restored by the generator, prioritizing edge influence across network layers to generate discriminative features for target recognition. Furthermore, the JSRDN implements detection-driven feedback by backpropagating object recognition loss through the generator, enforcing the super-resolution process to prioritize detection-salient feature recovery. Evaluated on 64×64 low-resolution COWC datasets, JSRDN achieves 0.1819 dB peak signal-to-noise ratio (PSNR) and 7.18 % average precision (AP) improvements over the deep residual dual-attention network (DRDAN), with ablation studies and visualizations confirming its balanced optimization of reconstruction fidelity and detection-oriented feature learning. This technology can provides valuable support for small target measurement and opens new opportunities in the field
Research on bearing equipment fault diagnoses via SAWOA-LSTM
Get PDFTo address the current low fault diagnosis accuracy problem for bearing equipment, and improve the detection methods, in this paper a sine-adapted whale optimization algorithm (SAWOA)-based optimization of a long short-term memory (LSTM) network is proposed as the equipment fault diagnosis method (SAWOA-LSTM). First, an optimization strategy based on sinusoidal population initialization and adaptive optimization is proposed for the whale optimization algorithm, which has the two drawbacks of slow convergence and easily falling into a local optimum. Second, to improve the accuracy and efficiency of fault diagnoses, the SAWOA is used to optimize the number of hidden units and the learning rate parameter of the LSTM. Compared with ACO-, PSO-, and WOA-based LSTM models, the proposed method improves diagnostic accuracy by 14.17 %, 15.03 %, and 4.32 %, respectively. In tests on 50 bearing samples, SAWOA-LSTM further improves accuracy for RBD, IRA, and ORD by 1.08 %, 1.62 %, and 1.10 %, respectively. Our algorithm provides an innovative solution for the health management of complex industrial bearing equipment
Logo recognition of vehicles based on deep convolutional generative adversarial networks
Get PDFVehicle logo recognition plays a critical role in enhancing the efficiency of intelligent transportation systems by enabling accurate vehicle identification and tracking. Despite advancements in image recognition technologies, accurately detecting and classifying vehicle logos in diverse and dynamically changing environments remains a significant challenge. This research introduces an innovative approach utilizing a Deep Convolutional Generative Adversarial Network (DCGAN) framework, tailored specifically for the complex task of vehicle logo recognition. Unlike traditional methods, which heavily rely on manual feature extraction and pre-defined image processing techniques, our method employs a novel DCGAN architecture. This architecture automatically learns the distinctive features of vehicle logos directly from data, enabling more robust and accurate recognition across various conditions. Furthermore, we propose a refined training strategy for both the generator and discriminator components of our DCGAN, optimized through extensive experimentation, to enhance the model’s ability to generate high-fidelity vehicle logo images for improved training efficacy. The technical core of our approach lies in the strategic integration of transfer learning techniques. These techniques significantly boost classification accuracy by leveraging pre-learned features from vast image datasets, thereby addressing the challenge of limited labeled data in the vehicle logo domain. Our experimental results demonstrate a substantial improvement in logo detection and classification accuracy, achieving an Intersection over Union (IoU) ratio of 42.67 % and a classification accuracy of 99.78 %, which markedly surpasses the performance of existing methods. This research not only advances the field of vehicle logo recognition but also contributes to the broader domain of measurement science and technology, offering a technically sound and logically coherent solution to a complex problem
Solving Saint Venant torsion problems for rectangular beams using single finite Fourier sine transform method
Get PDFThis research presents the single Fourier sine transform method (SFSTM) for solving the Saint Venant torsion problem of rectangular prismatic bars. The problem is a common theme in the theory of elasticity of unrestrained torsion which was previously expressed by Prandtl using Prandtl stress functions ϕ(x,y) as a Poisson type nonhomogeneous partial differential equation (PDE) called the stress compatibility equation. In this work the SFSTM was applied to the stress compatibility equation, converting the PDE to an easier to solve ordinary differential equation (ODE) in the transformed domain. The boundary conditions were used to find the integration constant and inversion was used to find the solution in the physical domain. The non vanishing stresses and torsional moments were thus found as a single series of infinite terms with rapid convergence. The maximum stresses and moments were found in standard form in terms of torsional parameters which were tabulated for various ratios of the cross-sectional dimensions. A comparison of the torsional parameters with previous results show that the present results are identical with previous results illustrating the accuracy of the SFSTM used. The sine kernel of the SFSTM satisfies the boundary conditions of the problem and contributed to the exact solution obtained. The SFSTM simplified the PDE to an ODE which is simpler to solve
Checking the manufacturing of Simões Network 10 – SN10 through surface electromyography (sEMG) – case report study
Get PDFUse of functional orthopedic appliances (FOA) in the treatment of malocclusion and Temporomandibular Disorders (TMD) has been proved to be effective but there is still questions to be answered like the muscular action of the referred appliances. The aim of this study is checking through a proven protocol of surface electromyography (sEMG) to study muscular action of FOA to check to check if it is correctly manufactured. The appliance studied is a Simões Network 10 – SN10 to treat Class II malocclusion of retrognathia. The sEMG was collected 1 patients with class II malocclusion with retrognathia who belong to a 164 volunteers with malocclusion, in two times T1 before installation of the FOA in mouth, T2 15 minutes after the FOA installation in the mouth. sEMG data of bilateral masseter, bilateral temporal and bilateral suprahyoid muscles using conditioner signals module from Lynx Electronics Ltda with 8 channels, model EMG1000; software AqDAnalysis 4,18 from Lynx Electronics Ltda.; Software Lynx BioInspector 1,8r; passive surface electrodes (Ag/AgCl) from Noraxon Dual Electrodes (USA); dischargeable reference electrodes Kendall Meditrace (Ag/AgCl) – Canada were used for the sEMG measurements. Frequency calibration was 2000 Hz, with 2048 sample by channel and time 1,024 seconds, and filters regulation was 20 Hz and 1000 Hz. With the FOA in the mouth all measurements improved with a more simetrical sEMG in T2 in rest and isometric contraction measurements. The protocol used to check the manufacturing of functional orthopedic appliances using surface EMG proved to be a valid tool in this case report study. Further investigations are needed to confirm this protocol and check if the same happens with other types of functional orthopedics appliances
The impact of occlusal plane rehabilitation on the face of a patient with traumatic peripheral facial paralysis by Timpanic jugular tumor – case report
Get PDFThe musculature of the face is innervated by cranial nerves, each with a motor, sensory and/or both function. The Facial nerve (FN) is responsible for the motor innervation of the muscles of the face. Some branches of the trigeminal nerve are responsible for the sensory part of the facial muscles and other branches act on the motor part of the chewing muscles. Traumatic Facial Paralysis (TFP) is the one where there was section or traction or compression or ischemia of the FN, in surgery for tumor resection or trauma in general. In this case occurs the nerve’s section in one surgery. Facial Paralysis (FP) can be evaluated subjectively through the House and Brackmann classification scale (HB) [1]. It is considered a chronic FP when it persists for a period longer than 6 months and leaves sequelae, such as synkinesis, contractures and lack of complete innervation of some nerve branches. Some patients who evolve with chronic FP may also evolve with alteration of the occlusal plane. The occlusal plane is the meeting point between the antagonist teeth, plane that is in the final stop of the masticatory cycle. The rehabilitation of this plan is performed according to the needs of each patient, in this case was made through implant prostheses
Finite element analysis of rockfall impact on pipelines with different erosion resistant coatings
Get PDFIn this paper, the finite element analysis method is used to extensively study the response of rockfall impact on pipelines with different erosion resistant coating. Based on the numerical results, the safety of the pipeline is comprehensively evaluated. Firstly, through the establishment of detailed pipeline and rockfall models, the impact of different rockfall materials and speeds on the pipeline is simulated. The results of the finite element analysis indicate that rockfall impact can cause significant stress concentration and deformation in the pipelines and damage to the coating. With the increment of impact speed, the damage to the pipeline also increases significantly, and different rockfall materials exhibit varying damage conditions, and it is found that fibreglass reinforced epoxy is better than the polyethylene coating. By comparing the analysis results under different conditions, the safety threshold of the pipeline under various rockfall impact scenarios is obtained. This provides an important theoretical basis and reference for the protection design and safety maintenance of the pipeline. The research in this paper not only aids in deepening the understanding of the mechanism of rockfall impact on pipelines but also serves as a valuable reference for improving the safety and reliability of pipeline engineering
Self-synchronisation of vibration exciters of a biharmonic vibration drive
Get PDFThe paper considers the practical possibility of self-synchronisation of two biharmonic unbalanced vibration exciters mounted on a solid body with plane oscillations. The problem is solved by the method of direct separation of motions. The equations for slow processes of establishing synchronous modes of rotation of the exciters are obtained; expressions for vibration torque; the vibration coupling coefficient and the condition for the existence of an synphase mode of motion. It is shown that the latter condition is relatively “soft”. An expression for the vibration torque is obtained for the case of “stuck” velocity of a biharmonic exciter in the resonance zone of a vibration machine. Recommendations for selecting the parameters of the vibration drive are given. The analytical conclusions are confirmed by computer modelling