Journal of Mechatronics and Artificial Intelligence in Engineering
Not a member yet
1200 research outputs found
Sort by
Multi frequency weak signals detection based on under-sampling bistable stochastic resonance
Get PDFSignal detection has a wide range of practical applications. Compared with traditional weak signal detection, the nonlinear effect of noise in the bistable system is typical and easy to extend, so bistable stochastic resonance detection technique has a wider applicability. In this paper, the multi-frequency weak signals detection based on under-sampling bistable stochastic resonance is studied. Based on the theory of bistable stochastic resonance, a simulation model is established to simultaneously detect multiple low-frequency weak signals. The spectrum of input and output signals is obtained through numerical simulation calculation, and the system characteristics are analyzed. When the large parameter signal does not meet the adiabatic approximation theory, the appropriate sampling coefficient can be selected to directly under-sample the input signal to make it conform to the conditions, and then the scale inverse transformation can be carried out. Finally, combined with the simulation analysis, the correctness of the under-sampling bistable stochastic resonance system to detect the multi-frequency weak signals is verified, the sampling rate is reduced, and the complexity is effectively decreased
DIC measurement method based on binocular stereo vision for image 3D displacement detection
Get PDFThe deformation detection of large machinery is usually achieved using three-dimensional displacement measurement. Binocular stereo vision measurement technology, as a commonly used digital image correlation method, has received widespread attention in the academic community. Binocular stereo vision achieves the goal of three-dimensional displacement measurement by simulating the working mode of the human eyes, but the measurement is easily affected by light refraction. Based on this, the study introduces particle swarm optimization algorithm for target displacement measurement on Canon imaging dataset, and introduces backpropagation neural network for mutation processing of particles in particle swarm algorithm to generate fusion algorithm. It combines the four coordinate systems of world, pixel, physics, and camera to establish connections. Taking into account environmental factors and lens errors, the camera parameters and deformation coefficients were revised by shooting a black and white checkerboard. Finally, the study first conducted error analysis on binocular stereo vision technology in three dimensions, and the relative error remained stable at 1 % within about 60 seconds. At the same time, three algorithms, including the spotted hyena algorithm, were introduced to conduct performance comparison experiments using particle swarm optimization and backpropagation network algorithms. The experiment shows that the three-dimensional error of the fusion algorithm gradually stabilizes within the range of [–0.5 %, 0.5 %] over time, while the two-dimensional error generally hovers around 0 value. Its performance is significantly superior to other algorithms, so the binocular stereo vision of this fusion algorithm can achieve good measurement results
An efficiency calculation model for ball screws by accounting for lead errors
Get PDFTransmission efficiency is a pivotal indicator, providing a comprehensive view of the overall performance of a ball screw. While extensive research has predominantly focused on computing transmission efficiency across various operating conditions, the factors influencing the variability have often been overlooked. This study introduces an innovative method for computing transmission efficiency, which considers lead error, drawing on deformation coordination theory and load distribution. Multiple ball screws of varying precision grades underwent rigorous testing to quantify lead errors. Subsequently, each screw was matched with an identical set of nuts to measure the respective transmission efficiencies. Experimental results reveal a linear correlation between lead error and transmission efficiency when both lead error and uneven ball load distribution in ball screws are considered. The relative error between the calculated transmission efficiency results and experimental values for ball screws of different precision grades falls within the range of 0 % to 7.42 %, confirming the validity of the proposed model in this paper
A third-order shear deformation plate bending formulation for thick plates: first principles derivation and applications
Get PDFA third-order shear deformation plate bending formulation is presented in this study from the first principles. The derivation assumed a displacement field constructed using third-order polynomial function of the transverse (z) coordinate; and made to apriori satisfy the linear three-dimensional (3D) kinematics relations as well as the transverse shear stress free boundary conditions at the top and bottom plate surfaces. The formulation thus has no need for shear stress correction factors of the first-order shear deformation plate theories. The domain equations of equilibrium are obtained as a set of three coupled differential equations in terms of three unknown displacements. The system of coupled equations is solved for simply supported rectangular and square plates subjected to four cases of loading distributions: sinusoidal loading, uniformly distributed loading, linearly distributed loading and point load at the plate center. Navier’s double trigonometric series method is used to construct trial solutions for the three displacement functions such that the boundary conditions are satisfied identically. The integration problem is thus reduced to an algebraic problem and is solved for each considered loading. It is found that the present formulation gives exact results for the normal stresses σxx for sinusoidal and uniformly distributed loads. The study further showed that the results for deflection and stresses agreed with Krishna Murty’s higher order shear deformation plate theory results. The present formulation gave accurate results because of the inclusion of transverse normal strain effects in the formulation. The formulation gives a quadratic variation of the transverse shear stresses across the thickness in consonance with the theory of elasticity method
A review on path planning ai techniques for mobile robots
Get PDFAn Industrial Robot is used in industries for transporting, assembly, manufacturing and many more applications. Industrial robots include manufacturing robots, material handling robots, robotic arm and manipulator, mobile robots, assembly robots, etc. In this paper, Mobile Robots are further being discussed. One of the tools that a Mobile Robot uses to function is all with the help of Artificial Intelligence (AI) for performing several tasks autonomously. AI works as the intelligence of the human body for robots. AI is the technology that made it possible for robots to be capable of being totally autonomous. AI marks its presence in the Manufacturing Industry with the 4th Industrial Revolution. AI has several algorithms that help in collecting and analyzing data in order to help robots to function in specific ways. These techniques include Fuzzy Logic, Genetic Algorithm, Neural Network, etc. In this paper, the role of these algorithms in Mobile Robots is discussed. Based on the review of 74 papers and articles, it is observed that there are no review papers discussing the role of nature-based and conventional algorithms used for navigation in Mobile Robots. The use of different AI techniques for specific applications has been discussed in tabular form in this paper
Transportation of hydrogen by main gas pipelines as a methane-hydrogen mixture
Get PDFDue to the emergence of new technologies that make it possible to obtain hydrogen from associated petroleum gas, it has become necessary to store and transport it. As a solution to this problem, the possibility of hydrogen transportation as a methane-hydrogen mixture was considered, i.e. natural gas with a certain hydrogen content. The article considers the issues of methane-hydrogen mixture (MHM) transportation through existing main gas pipelines at various percentages of hydrogen to natural gas. As an example, the Urengoyskoye field was chosen, where it is possible to produce hydrogen from the associated gas of gas condensate fields, and a section of the Novopskovskiy corridor, through which it is possible to transport MHM. In the work, the influence of the hydrogen content in the methane-hydrogen mixture on the gas-dynamic characteristics of the pipeline, mainly on the pressure and throughput capacity of gas in the pipeline, as well as the influence of its content on the operating mode of the compressor station and the power of the gas turbine, when using MHM for the station's own needs, was studied. The obtained results show an insignificant effect of the hydrogen percentage in the mixture on the pressure and throughput of the gas pipeline, which is a weighty argument in favor of the possibility of transporting hydrogen through existing gas pipelines
Vibrator with two impacting pairs, one of them in the position of equilibrium
Get PDFIn the dynamic processes taking place in manipulators and robots, impact interactions play an important role. Among them two sided impacts are important. In this paper investigation of dynamic regimes of a system with two impacting surfaces, one of which is in the position of equilibrium is performed. Dynamics in steady state regime for typical parameters of the investigated system having one degree of freedom is investigated. Displacements as functions of time as well as velocities as functions of time for various positions of the impacting surface are presented. Non symmetric impacts enable to reduce the dimensions of the vibrator and to achieve increase of effectiveness of useful impacts of a manipulator. Investigations of the conservative system as well as of the system with forced harmonic excitation are performed
Capillary force method to improve the green density of binder jet additive manufacturing
Get PDFThis study investigates the impact of capillary adhesion force on the green part density in metal powder binder jetting 3D printing. Gas atomized Co-Cr-Mo, SS316L, and pure Cu powders were used to print various samples. The printed samples were then treated with water, 1-Hexanol, and n-Amyl alcohol vapor for 24 hours to nucleate capillary bridges between particles and shrink samples uniformly. The volume change was calculated for each sample, and up to –3.1 % volume change was observed. The proposed method can be used to improve green part densities directly on printed parts before sintering
Research on lightweight pedestrian detection based on improved YOLOv5
Get PDFAiming at the problems of low detection accuracy and the large size of the pedestrian detection algorithm, to improve the edge intelligent recognition capability of the terminal, this paper proposes a lightweight pedestrian detection scheme based on the improved YOLOv5. In this paper, the algorithm first takes the original YOLOv5 as the basic framework and uses the Ghost Bottleneck module to replace the C3 module in the original YOLOv5 network to reduce the number of parameters, eliminate redundant features, and obtain a more lightweight model. Then the attention mechanism CBAM module is added to improve the feature extraction capability and detection accuracy of the algorithm. After experimental verification, the improved lightweight YOLOv5 algorithm significantly reduces the model size and computational cost while guaranteeing accuracy, which is suitable for deployment in edge devices
The application of fault diagnosis techniques and monitoring methods in building electrical systems – based on ELM algorithm
Get PDFThe reliability of modern building electrical systems are receiving increasing attention as they become more intelligent and complex. As the majority of building electrical systems use neutral point grounding, earth faults or short circuits can get worse over time and damage both the distribution system and the electrical equipment. To this end, the corresponding three phases and four categories, namely three-phase voltage, three-phase current after fault, three-phase voltage distortion rate, three-phase current distortion rate, a total of 12 dimensional fault feature vectors and 10 fault simulation types, were summarised and extracted in conjunction with the actual operating conditions of the system. Using traditional fault identification ideas and neural network algorithm as reference, a 12-dimensional fault feature vector is used as the model input to construct a building electrical fault diagnosis and detection model based on ELM algorithm. Results showed that the ELM-based model’s classification accuracy for this experimental sample was 97.56 %, its AUC was 0.92, and its RMSE was 0.3521. These figures were higher than the classification accuracy and performance of the BP algorithm and GA-BP algorithm fault diagnosis models, and they also demonstrate better robustness and generalizability. The model also has a 97.27 % correct rate in fault discrimination, while the computation time is only 0.201 s, and its fault identification and diagnosis speed is faster than other algorithmic models. At the same time, this research model has a good fault monitoring accuracy of up to 98.6 % for building electrical systems. The research can provide a more sensitive, accurate and rapid fault monitoring method for the current building electrical system. It also improves the reliability of the building electrical system in a complex environment and achieves better protection of the system. This has a certain significance for the development of the building electrical industry