Journal of Mechatronics and Artificial Intelligence in Engineering
Not a member yet
1200 research outputs found
Sort by
An improved semi-supervised prototype network for few-shot fault diagnosis
Get PDFThe collection of labeled data for transient mechanical faults is limited in practical engineering scenarios. However, the completeness of sample determines quality for feature information, which is extracted by deep learning network. Therefore, to obtain more effective information with limited data, this paper proposes an improved semi-supervised prototype network (ISSPN) that can be used for fault diagnosis. Firstly, a meta-learning strategy is used to divide the sample data. Then, a standard Euclidean distance metric is used to improve the SSPN, which maps the samples to the feature space and generates prototypes. Furthermore, the original prototypes are refined with the help of unlabeled data to produce better prototypes. Finally, the classifier clusters the various faults. The effectiveness of the proposed method is verified through experiments. The experimental results show that the proposed method can do a better job of classifying different faults
Reliability analysis of cable crimping terminals with different applicator tools
Get PDFThis study provides a comprehensive evaluation of the stability of crimping of the same terminal on FLRY A cables using three different applicators. The research involved conducting pull tests on 50 samples for each applicator type, analyzing the results using Minitab software to assess the consistency and strength of the crimp connections. The findings indicate that while the Demirel applicator produces the highest average pull test values, the Tyco applicator demonstrates superior consistency, making it more suitable for applications where process stability is critical
Identification and characteristic statistics of surface microstructure of titanium metal based on cavitation water jet
Get PDFThe application of cavitation water jet technology to modify medical implant surfaces facilitates the formation of distinctive microporous structures, thereby enhancing the contact area between the implant and alveolar bone, and improving osseointegration. Therefore, the microstructure characteristics of the modified implant are one of the important evaluation indicators of the modification effect. This paper proposes a processing method for the identification and statistical analysis of surface micro-morphology images. The method incorporates techniques such as image enhancement, image segmentation, morphological image processing methods, and pixel matrix operations, enabling automated quantification of pit counts, the relative positions of the pits, and other topographic characteristics of the material surface. Simultaneously, the microstructure of each pit is spatially fitted and reconstructed to standardize measurement benchmarks for pit diameter and depth characteristics. This facilitates in-depth multi-dimensional analysis of material surface characteristic information and provides foundational support for further exploration of cavitation jet modification technology. In the study, the modification effect of processing time on the surface morphology of titanium metal was used as an application case. A surface morphology feature information database was established under different processing times, and statistical analysis was conducted on proportion, structural distribution, and other characteristics in the focus areas. The results show that the diameter and proportion distribution of the pits produced by cavitation jet modification tend to be stable when the jet pressure and standoff distance remain constant, while the depth of the pit increases with the increasing processing time
Effect of pier bearing construction on nearby high-speed rail line bridges
Get PDFIn order to analyze the impact of the new pier bearing platform construction on the bridge section adjacent to the high-speed railway line, a new pier bearing platform project adjacent to the high-speed railway line in the soft soil area of the Yangtze River Delta is taken as the background of the project, and the finite element software Plaxis 3D is used to study the impact of the pier bearing platform construction on the bridge section adjacent to the high-speed railway line, and to analyze the effect of distance on the horizontal displacement and settlement of the bridge foundation soil body. The neighboring high-speed rail line bridge is displaced horizontally toward the foundation, with the maximum horizontal displacement of 1.5 mm and the maximum settlement of 5.5 mm; the existing pier bearing platforms are also displaced in the same direction, with the maximum horizontal displacement of 2.7 mm and the maximum settlement of 5.4 mm, and the pier bearing platforms in the middle are affected the most
Modeling of unsteady-state creep of asphalt concrete
Get PDFThe article experimentally investigated unsteady-state creep of a hot fine-grained dense asphalt concrete under uniaxial tension at temperatures of 22-24 °C. 61 samples of the asphalt concrete in the form of a rectangular beam with dimensions of 50×50×150 mm were tested to complete failure at seven different stresses (from 0.084 MPa to 0.3053 MPa) in a special installation with a heat chamber. Based on the test results, unsteady-state creep curves were constructed, which were normalized and approximated with high accuracy by a power function. Reliable dependences of the limiting time of hardening, the limiting strain of hardening, and the hardening rate on stress have been established
Binary rat swarm optimizer algorithm for computing independent domination metric dimension problem
Get PDFIn this article, we look at the NP-hard problem of determining the minimum independent domination metric dimension of graphs. A vertex set B of a connected graph G(V,E) resolves G if every vertex of G is uniquely recognized by its vector of distances to the vertices in B. If there are no neighboring vertices in a resolving set B of G, then B is independent. Every vertex of G that does not belong to B must be a neighbor of at least one vertex in B for a resolving set to be dominant. The metric dimension of G, independent metric dimension of G, and independent dominant metric dimension of G are, respectively, the cardinality of the smallest resolving set of G, the minimal independent resolving set, and the minimal independent domination resolving set. We propose the first attempt to use a binary version of the Rat Swarm Optimizer Algorithm (BRSOA) to heuristically calculate the smallest independent dominant resolving set of graphs. The search agent of BRSOA are binary-encoded and used to identify which one of the vertices of the graph belongs to the independent domination resolving set. The feasibility is enforced by repairing search agent such that an additional vertex created from vertices of G is added to B, and this repairing process is repeated until B becomes the independent domination resolving set. Using theoretically computed graph findings and comparisons to competing methods, the proposed BRSOA is put to the test. BRSOA surpasses the binary Grey Wolf Optimizer (BGWO), the binary Particle Swarm Optimizer (BPSO), the binary Whale Optimizer (BWOA), the binary Gravitational Search Algorithm (BGSA), and the binary Moth-Flame Optimization (BMFO), according to computational results and their analysis
On the decisional problem based on matrix power function defined over non-commutative group
Get PDFIn this paper, we perform statistical analysis for the decisional problem which is fundamental for the security of the key exchange protocol based on matrix power function. We have proven previously that the considered decisional problem is NP-complete and hence our proposal could potentially be quantum-safe. However, we did not explore the dependence of the complexity of the considered problem on the security parameters. Here we show that for small matrices certain information could be gained from the distribution of the entries of the public key matrices. On the other hand, we show that as the size of the matrices grows, the public key matrices are indistinguishable from truly random matrices
Lubrication optimization of high-speed train drive gearbox
Get PDFThe gears in the high-speed heavy-duty gearbox of the high-speed train are typical high-speed heavy-duty gears. Combined with the transmission principle and structural characteristics of the high-speed train drive gearbox, to ensure adequate lubrication of meshing gears and bearings, an optimization of the lubricating oil flow inside the gearbox was conducted. The oil and gas two-phase flow model inside the gearbox adopts the VOF model, and the turbulence model adopts the standard κ-ε model. Fluent is used for simulation calculation. The results show that the exhaust port position of the gearbox has little effect on the flow of lubricating oil inside the gearbox; the overall pressure distribution inside the gearbox is relatively uniform, with higher pressure only at the meshing gears; the distribution of lubricating oil inside the gearbox is related to the rotation of the gears, and the flow velocity of lubricating oil is mainly affected by the rotation of the gears, with the maximum flow velocity appearing around the gears; the flow of lubricating oil inside the gearbox meets the lubrication requirements of the gearbox. These results provide support for the lubrication design, flow channel structure improvement, and effectiveness evaluation of high-speed train transmission gearboxes
Optimal path for automated pedestrian detection: image deblurring algorithm based on generative adversarial network
Get PDFThe pedestrian detection technology of automated driving is also facing some challenges. Aiming at the problem of specific target deblurring in the image, this research built a pedestrian detection deblurring model in view of Generative adversarial network and multi-scale convolution. First, it designs an image deblurring algorithm in view of Generative adversarial network. Then, on the basis of image deblurring, a pedestrian deblurring algorithm in view of multi-scale convolution is designed to focus on deblurring the pedestrians in the image. The outcomes showcase that the peak signal to noise ratio and structural similarity index of the image deblurring algorithm in view of the Generative adversarial network are the highest, which are 29.7 dB and 0.943 dB respectively, and the operation time is the shortest, which is 0.50 s. The pedestrian deblurring algorithm in view of multi-scale convolution has the highest peak signal-to-noise ratio (PSNR) and structural similarity indicators in the HIDE test set and GoPro dataset, with 29.4 dB and 0.925 dB, 40.45 dB and 0.992 dB, respectively. The resulting restored image is the clearest and possesses the best visual effect. The enlarged part of the face can reveal more detailed information, and it is the closest to a real clear image. The deblurring effect is not limited to the size of the pedestrians in the image. In summary, the model constructed in this study has good application effects in image deblurring and pedestrian detection, and has a certain promoting effect on the development of autonomous driving technology
Analysis and optimization of abnormal noise in lubricating oil circuit of diesel engine
Get PDFEngine abnormal noise is one of the common engine faults, which will affect the comfort, power and safety of the automobile at the same time. In order to study the abnormal noise existing in the test process of diesel engine lubricating oil circuit system, 1D numerical simulation analysis of its flow field is carried out by using simulation software GT-power to verify the boundary conditions of the model and analyze the fluctuation of pressure at different speeds and temperatures. Through numerical analysis, it is found that there is almost no pressure fluctuation in the lubrication system before the pressure limiting valve is opened, but after the pressure limiting valve is opened, pressure fluctuation occurs in the pipeline, and the pressure fluctuation is different at different positions. Finally, the lubrication pipeline is simulated and analyzed by Pumplinx software, and the pressure fluctuation in the lubrication pipeline of diesel engine is reduced by optimizing the diameter of the oil pipeline and increasing the cavity structure