Composite materials are the most important materials in materials science and engineering, which contain two or more materials. In materials engineering, the scanning electron microscopy (SEM) technique is an approach to measure the material''s Particle size. A new procedure was used instead of SEM is called Artificial Intelligence (AI). Artificial Intelligence (AI) is an interdisciplinary science and branch of computer science that involves solving problems that require human intelligence and capabilities. The computer vision is a subfield of AI, which uses some algorithms to detect the details of images by using computer called image processing. Detecting the Particles and measuring the size of materials scanned by SEM is an essential task that helps to describe their feature, traditionally, the size is calculated manually by adding mesh to an SEM image or by drawing a diagonal line in an arbitrary Particle. In this paper, a new model based on Artificial Intelligence (AI) is proposed using computer vision to analyze the size of all Particles. This model is used to detect the Particle size of additives in composite materials like graphene flakes and measure the size of them depending on the reference size fixed on the scanning electron microscope (SEM). The model was used based on the Open-source Computer Vision (OpenCV) library, utilizing multi-layers of canny edge detection, Sobel filter, Brightness and contrast algorithms, using Python 3. The results have achieved very satisfied indication with a very low process time = 0.2 mili-seconds.

Particle characterization is a principal factor in the research and development of the product, production, and material quality control. Particle size plays a critical role in the borderline sciences, such as biotechnology and nanotechnology. In this study, light scattering devices ( dynamic and Static) and their theory is discussed. Also, suggest theory to calculate form factor of scattering such as Rayleigh and Mi e was explained.

The hydrocyclone has a very important roll in industrial separation. The consideration of its behavior is very important for design. In this investigation, behavior of water flow and Particles trajectory inside a hydrocyclone has been considered by means of numerical and experimental methods, and results have been compared together. To have a numerical simulation, a CFD software was used, and for modeling flow the RNG k-e model applied. Finally, the effect of Particle size on hydrocyclone performance has been studied. It was found that the grade efficiency and number of Particle that exit from underflow of the hydrocyclone is increased when bigger Particles is used.A series of experiments has been carried out in a laboratory with a hydrocyclone. Comparison shows that, there is a good agreement between the CFD models and experimental result.

Most properties of nanoParticles are size-dependent. In fact, the novel properties of nanoaprticles do not prevail until the size has been reduced to the nanometer scale. The Particle size and size distribution of alumina nanoParticle, as a critical properties, have been determined by transmission electron microscopy (TEM), photon correlation spectroscopy (PCS), surface area analysis (BET) and x-ray diffraction peak broadening analysis. The Particle size was found to be in the range of 5-95 nm. Cumulative percentage frequency plot of the data extracted form TEM images indicates that Particle size distribution obeys the log-normal function. The TEM images also reveal that Particles are spherical in shape and loosely agglomerated. Comparing of the XRD and TEM results shows that the Particles are single-crystal. The HRTEM images also verify that the Particles have a single-crystal nature. In comparison, there is a good correlation between the BET, XRD and TEM measurements other than PCS that is sensitive to the presence of the agglomerates.

Vibration signals were measured in a lab-scale fluidized bed to investigate the changes in Particle sizes. Experiments were carried out in the bed with a different mass fraction of coarser Particles at different superficial gas velocities, and probe heights. The S-statistic test evaluates the dimensionless squared distance between two attractors reconstructed from time series of vibration signals. Values of parameters needed for the attractor reconstruction were derived from time series. These parameters consist of time delay, embedding dimension, bandwidth, and segment length with the values of 1, 35, (0. 4-0. 8), and (300-400), respectively. To reduce the sensitivity of the S-statistic to small changes in superficial gas velocities, the vibration signals were normalized in order to apply the attractor comparison test. The results showed that the attractor comparison can be a reliable technique for detecting Particles size changes in fluidized beds even with small changes in the amount of coarser Particles. The sensitivity of the method to Particle size changes was decreased with an increase in superficial gas velocity. The results also show that the S-statistic test was almost independent of the measurement position of the vibration signals.

In this paper, flow past a single Dissipative Particle Dynamics (DPD) Particle with low Reynolds number is investigated and it is inquired that whether a single DPD Particle immersed in a fluid, has an intrinsic size. Then a minimum length scale is determined such that the hydrodynamic behavior based on standard DPD formulation is modeled correctly. Almost all of the previous studies assume the DPD Particles as point centers of repulsion with no intrinsic size. Hence to prescribe the size of a simulating sphere, a structure of frozen DPD Particles is created. In this paper two effective radii, Stokes-Einstein radius and a radius based on the Stokes law, for DPD Particles are introduced. For small Reynolds numbers; it is proved that the two radii approach each other. Finally in spite of the typical simulations which assume DPD Particles as point centers of repulsion, it is concluded that each of the individual DPD Particles interact with other Particles as a sphere with non-zero radius. It results the reduction of the required number of Particles and eventuates more economical simulations. Moreover contemplating the radius of the Particles is necessary for the new Low-Dimensional model which is derived based on the DPD method.

Considering safety and environmental issues are very important in all domains of agriculture, industry and services in different countries. In the agricultural domain despite of numerous efforts to find alternative methods, millions of liters of toxic chemicals are used by chemical methods to control plant pests every year. Certainly, the most important issue in spraying is the size of drops which is influenced by several factors including pressure, nozzle hole diameter, viscosity of the chemical solution and wind speed in the area. In this study, MLP network Feed Forward modeling was used. Input consisted of two layers including nozzle diameter (three sizes) and spraying pressure (three pressure levels). Output of the artificial neural network determined by volume median diameter. In order to choose the best procedure, five methods including gradient descending, descending gradient with momentum, Levenberg-Marquart, conjugate gradient and Delta Bar Delta were used. Considering both minimum mean square error and coefficient of determination, the descending gradient with momentum was chosen. After training and validation of the network, MSE and coefficient of determination were 0.0176 and 0.90, respectively. In order to verify the results from neural network several tests were carried out and observed Particle diameters were compared with values obtained from neural networks by chi-square test. The difference was not significant. These results indicate that neural networks can estimate properly the size of the droplets.