An Integrated System of Artificial Intelligence and Signal Processing Techniques for the Sorting and Grading of Nuts

The existence of conversion industries to sort and grade hazelnuts with modern technology plays a vital role in export. Since most of the hazelnuts produced in Iran are exported to domestic and foreign markets without sorting and grading, it is necessary to have a well-functioning smart system to create added value, reduce waste, increase shelf life, and provide a better product delivery. In this study, a method is introduced to sort and grade hazelnuts by integrating audio signal processing and artificial neural network techniques. A system was designed and developed in which the produced sound, due to the collision of the hazelnut with a steel disk, was taken by the microphone placed under the steel disk and transferred to a PC via a sound card. Then, it was stored and processed by a program written in MATLAB software. A piezoelectric sensor and a circuit were used to eliminate additional ambient noise. The time-domain and wavelet domain features of the data were extracted using MATLAB software and were analyzed using Artificial Neural Network Toolbox. Seventy percent of the extracted data signals were used for training, 15% for validation, and the rest of the data was used to test the artificial neural network (Multilayer Perceptron network with Levenberg-Marquardt Learning algorithm). The model optimization and the number of neurons in the hidden layer were conducted based on mean square error (MSE) and prediction accuracy (PA). A total of 2400 hazelnuts were used to evaluate the system. The optimal neural network structure for sorting and grading hazelnuts was 4-21-3 (four neurons in input layers, 21 neurons in the hidden layer, and three outputs which are the desired classification). This neural network (NN) was used to classify hazelnut as big, small, hollow, or damaged. Results showed 96.1%, 89.3%, and 93.1% accuracy for big/small, hollow, or damaged hazelnuts were obtained, respectively.

Research of tribotechnical characteristics of materials used in the development of compositions of lubricants for casting under pressure of aluminum alloys and polymeric products

The article describes the requirements for lubricants (release coatings) used in injection molding of aluminum alloys and polymeric materials. A methodology for conducting research to determine the tribotechnical characteristics of materials used in the development of the composition of a lubricant for injection molding aluminum alloys and polymer products, as well as the results of a study of tribotechnical characteristics (friction coefficient) are presented. It has been established that as materials used in the development of a multifunctional lubricant composition for casting aluminum alloys and polymer products, it is advisable to use a fraction of soap stock and fus after their preliminary sedimentation (at least 3 months). It is shown that the smallest value of the coefficient of friction at the time of indenter breaking on the surface of the steel disk was obtained using a fus. Moreover, the value of the coefficient of friction is 14–33% lower than the same indicator for other studied lubricants (petroleum jelly, PMS-100 and soap stock). It was found that in the mode of reciprocal movement of the indenter on the surface of the steel disk, the coefficient of friction when using a fus is 1,7–3,3 times lower than when using Vaseline, PMS-100 and soap stock as lubricant.

Cavities "Pit Number" and micro-jets impingements

Cavitation pits and erosion were obtained using the rotating disk device, where a steel disk with cavitation inducers and specimens fixed on it rotates inside a water chamber to provide the cavitating flow. These pits were observed with the aid of a scanning electronic microscopy. Micro-jets resulting from cavity collapse cause damages to solid surfaces. Because they are caused by the micro-jets, these pits are approximate circular. The exponent named pit number was calculated using the pit counting, that is the number of pits by area and by time unit. The influence of flow velocity was also analyzed here, and how greater is the flow velocity, how greater is the pit counting calculated. It was also calculated the distance from the collapsing cavity to the wall, considering a conic micro-jet.

QUESTION OF APPLICABILITY OF THE CALCULATION ASSESSMENT METHOD OF RESISTANCE FOR DETAILS AFTER THERMAL DIFFUSION HARDENING

Introduction.The article discusses the question of applicability of the calculation assessment method of resistance for details from gray cast iron after thermal diffusion hardening. The purpose of research is to check applicability of the calculated model for determination of intensity in case of the variable blanket hardness.Materials and methods.The model of intensity dependence on contact of two disks of friction gear is used in the research. Calculated determination of parameters is executed in two options: contact of the steel disk and disk from gray cast iron with the strengthened layer, and contact of the steel disk and disk from the tempered high-strength cast iron. Thus, roughness corresponding to the earned extra surface in contact zone is created. Experimental check of received results is carried out by means of specific work of abrasive wear definition for gray cast iron with the strengthened layer and the high-strength tempered cast iron.Results.As a result, it was established that the resistance of details from gray cast iron with the strengthened layer is comparable to high-strength cast iron after hardening. The results of experimental check prove the obtained calculations since the parameters values of resistance received would be well coordinated. Therefore, the possibility of the calculated resistant technique usage for such case could be considered as proved one and, therefore, it could be used at design calculations of the frictional units containing details from gray cast iron with the strengthened layer.Discussion and conclusions.The considered way of superficial hardening needs to be applied depending on features of operation on frictional unit. In such case, when the allowed values of wear change in wide limits (for example, brakes, coupling, etc.) it would be better not to subject a blanket to machining where the formation of optimum parameters of friction surfaces happened in natural way, or it would be necessary to delete an allowance. This suggests that the calculation method of the determination of layer resistance enables to define concrete values of an allowance which needs to be deleted.

Elastic-plastic analysis for wet multidisc brake during repeated braking

To reveal the mechanism and evolution laws of the braking performance declining from heat load in the repeated braking applied for wet multidisc brake, a finite element analysis was carried out by using the bidirectional thermal-structure coupling method. Based on the fundamental principles of the energy conservation and virtual work principle, the elemental equations between temperature and heat load, and deformation displacement and load with heat transferring boundary conditions and heat–structure interaction were derived. Taking a steel disk in the brake for example, the deformation state of its elements, and the starting time, the location, the severity, and evolution laws of the plastic deformation were analyzed and demonstrated by using dimensionless stress distribution contours. The area in contact along the interface and the ratio of the element numbers to produce plastic deformation to the total element numbers on the steel disk were described by contact ratio and plasticity ratio, respectively. Moreover, the results under the repeated braking case were compared with that under the lasting braking case, which indicates that the influence of the temperature load on the performance declining of the repeated braking case is much lower than one of the lasting braking case, and the temperature is lower than 40 K and the plasticity ratio is smaller than 0.35 after the braking time is longer than 350 s. The conducted finite element analyses provided the theoretical fundamentals for the design and the application of the brake in the heavy type of trucks.

Investigation of Inhibitor Polyphosphate Properties for Rotating Steel Disk Electrode in Potassium Nitrate Solution

<p>Inhibition properties of a number of glass-like polyphosphates on 65J steel were investigated using the gravimetry and methods potassium nitrate solution polarization curves in a 0,1M (pH=6,05). The possibilities<br />of optimum experimental conditions were considered as well. Basing on the experimental data the inhibition coefficient and protective effect were found. The inhibiting action of polyphosphates, apparently, is due to the formation of inhomogeneous protecting film on the steel surface.</p>

Development of a Technique for the Calibration of HPGe Detector to Estimate Radionuclides Present in Steel Samples

The quantitative assay of radionuclides present in steel samples is required for the environmental safety as well as in the process control and quality control of the finished products. The standard sources should also be prepared in the required size and shape as that of the sample, for the efficiency calibration of the HPGe detector system. A method was developed and tested to use 152Eu point source for the determination of efficiency of an extended steel disk source using HPGe detector system. Standard point sources of 152Eu were prepared by transferring known amount of 152Eu activity by weight. Standard steel disk sources of required dimensions were also prepared by distributing uniformly the standard activity of 152Eu on both sides of the inactive steel disk. The extrapolated efficiency of the steel disk sample was determined using the efficiency of the 152Eu point source and it was compared with the efficiency determined using the standard sources of 152Eu prepared on the steel disks. The two efficiency calibration curves matched very well within the experimental limits. Using this efficiency calibration, a few steel samples were analyzed for the radionuclides present in them. The detections limits for most of the nuclides were much less than the specified limits. The method can further be extended for other types of geometries with suitable modifications for the changes in thickness and attenuation corrections.