نشریه مهندسی مکانیک ایران
سال بیست و چهارم شماره 4 (پیاپی 69، زمستان 1401)

In this paper, an intelligent neural network controller is designed that can balance a quadrotor. After comparing the two types of independent reverse controllers and PID in the simulation environment, their differences are stored as data in the software. By specifying the input data of the controller and the target data and using the feedforward neural network architecture and a Narx architecture, intelligent controllers are designed and the obtained results are shown in several stability detection diagrams. The obtained results show that the equilibrium and vertical flight control are quite acceptable. Finally, the results are tested in a practical model on a real vertical plane. In the practical model, due to the limited amount of training data, the performance of Narx network is much more appropriate than the performance of the feed network. In fact, the complexity of the Narx recursion algorithm helps to interpret the complex dynamic behavior of the system well despite the low data. The disadvantage of this type of network is its very complex hardware implementation, which requires a much more powerful processor and memory to run on the controllers.

The behavior of self-driving cars is categorized into different strategic, tactical and operational levels in a hierarchical structure. In this research, a study at the local planning level aims to design an automatic turning system and Focus on path and maneuver planning (single and multi-point). The turn around maneuver as a common scenario in the required conditions, includes one or more forward and backward movements, in which the vehicle must be in the proper position in the opposite lane of the road and with a heading angle of 180 degrees. Moreover, the condition of collision avoidance is considered during the maneuver. For this purpose, the four-wheeled model of the vehicle with the relevant geometry is described; Next, on the basis of the deduced minimum permissible road width, a decision is made according to the objective of the minimum number of commands. Then the path design is presented using the proposed geometrical method with circle arcs for each initial position and orientation and generalized to the backward turning. The proposed method has advantages such as low computational cost and can be used for different situations of the initial states of the vehicle. The result of the turning simulation with sample vehicle data and continuous evaluation of the most feasible maneuver confirms the efficiency of the chosen planning approach. In a case study for the Samand car, while proper planning was done, a distance reduction of about 11% for the road with a width of 12 meters is observed compared to the path planned by one of the references.

In this paper, artificial intelligence is applied for real-time object detection in Tello quadcopters. For this purpose, the YOLOv3 detection algorithm is employed. The results indicate that the YOLOv3 network can detect the target with above 95 percent accuracy at a speed of 15 frames-per-second for different ambient lighting and background conditions. After detecting the target, the errors are calculated and given to the control system to track the target in real-time. The designed controllers efficiently follow the target and prevent flying robots from losing sight of the target.

In this study, the temperature fields in the thermal barrier coating systems (TBC) under various types of thermal loading, including steady and transient thermal loadings, is investigated. Due to the widely use of TBCs on gas turbine blades and the urgent need to increase the temperature of the combustion chamber, thermal barrier coatings are exposed to a variety of harsh thermal loadings, including thermal shock and periodic thermal loads. Therefore, the need to achieve the temperature distribution in different positions in the TBCs, especially in the protective coating is crucial. At first, due to the application of non-uniform temperature distribution on the boundary of the TBC layer, the steady-state temperature distribution inside the coating-substrate is obtained. Using the solution of steady-state temperature distribution as the initial condition, the transient temperature field inside the coating-substrate system is obtained. To investigate the thermal transient response of the TBC system, dual-phase lag (DPL) heat conduction equation is utilized. Fourier and Laplace integral transformations have been used to solve the temperature field equations. The effect of various types of thermal shocks and periodic thermal loading on the TBC is investigated. The results show that the steady-state and transient temperature fields strongly depend on the type of thermal shock, the thickness of the coating and the frequency of thermal loading.

Electromagnetic flowmeters are high-precision devices that can be used to measure fluid flow in engineering systems, including municipal water supply networks. In this research, electromagnetic flowmeter modeling has been used which is a hybrid model based on numerical simulation results of turbulent flow and data estimation method for a pipe with a diameter of 100mm and a length of 800mm. The numerical model is built using three-dimensional simulation framework by creating a magnetic field in the center of the geometry and measuring the volume flow rate using Faraday law and Maxwell equations. In fact, the physics of the problem is such that to measure the flow rate of a fluid, a magnetic field was created in the center of the geometry where the electromagnetic inductors are located. By moving the fluid that has electrical conductivity, the intensity of electromagnetic induction was obtained at that point and the amount of velocity and flow rate was calculated using these data. For this purpose, current simulation under the effect of electromagnetic intensity was performed for the values of 0.01, 0.03 and 0.05 (Tesla) to obtain the most appropriate intensity. The results show that up to an intensity of 0.03, the magnetic field has little effect on the structure of the flow field. In order to develop an alternative model of electromagnetic flowmeter, the method of estimating the inlet average velocity based on information from numerical simulation data has been used. First, for a certain number of pressures (pressure differences), the magnetic field intensity in the position of the sensors was obtained then using these values, the inlet average velocity using direct numerical simulation was calculated. A new magnetic intensity different from the values ​​used was obtained by data mining method. In order to ensure the accuracy of the results, the obtained data were compared with the calculated values ​​of the software.

Today, energy plays an important role in the economic growth of human societies. Among the types of energy consumed by humans, solar energy can be considered the most abundant. Therefore, over the years, various types of solar water heating systems have been developed and used. Considering the remarkable capabilities of nanofluids in improving heat transfer processes and increasing the thermal efficiency of heating systems, the use of nanoparticles as a substitute for conventional fluids in various heating systems, especially solar energy systems, as well as the effect of widely used nanofluids So much attention has been paid to increasing the thermal efficiency of the solar vacuum tube collector. In this research, the most important component, namely the efficiency of solar water heaters and also the heat transfer process using three types of nanofluid (with mass percentage 1%), has been investigated. All tests were performed in accordance with the relevant standards (ISO-9806), on sunny days. The highest increase in heat transfer of nanofluids and also the thermal efficiency of the system is related to noon (religious noon), among which, the highest efficiency is related to aluminum oxide nanofluid (AL2O3 nanofluid), with a 3.46% increase compared to the base fluid (Oil fluid) is. The thermal efficiency of the system with titanium oxide nanofluid (TiO2 nanofluid) and carbon oxide nanofluid (C nanofluid) as well as the base fluid (oil fluid) show 2.54%, 2.12% and 1.6%, respectively. Due to the increase in heat capacity of the nanofluids used, the heat capacity can be considered an important factor in increasing the efficiency of vacuum tube solar water heaters.