Search

In this paper, the potential of adaptive neuro fuzzy inference system (ANFIS) was appraised for investigation of thermal performances of a minichannel heat sink for cooling of electronics using nanofluid coolant instead of pure water. The process, which simulates the thermal performances with ANFIS network, was constructed. The developed ANFIS network was with three neurons in the input layer, and one neuron (thermal performances) in the output layer. Since there are three thermal performances investigated, three ANFIS networks are created. The inputs were flow rate, as well as the Reynolds number. The third input represents the nanofluid concentration. The Al2O3–H2O nanofluid including the volume fraction was used as a coolant. Obtained experimental results showed the higher improvement of the thermal performances using nanofluid instead of pure distilled water. ANFIS results show that an improvement in predictive accuracy and capability of generalization can be achieved by the ANFIS approach for heat sink base temperature prediction. • Thermal performances of a minichannel heat sink investigation. • Cooling of electronics using nanofluid coolant instead of pure water. • Improvement in predictive accuracy and capability by the ANFIS approach. • The effectiveness of the proposed strategies is verified based on the simulation results. [ABSTRACT FROM AUTHOR]

Abstract Information system development is a complex endeavor, one which is fraught with peril if one do not follow a proven method. The Rational Unified Process (RUP) is one such method which could help to organize the development process of any information system. The RUP takes an evolutionary approach to development which has been shown to be far more effective than the traditional approach which is based on simple procedure. Unified Modeling Language (UML) is a RUP graphical language for visualizing, specifying, constructing, and documenting the artifacts of a information system. UML offers a standard way to write a system's blueprints which is crucial for any information system development. The main goal of the study is to develop electronic patent (e-patent) system by RUP approach and UML standard tools. Afterwards artificial neural networks are applied to predict potential economic growth (GDP) based on science factors including patents. Extreme learning machine (ELM) is used for training process of the networks. Extreme learning machine (ELM) is a class of single-hidden layer feedforward neural network (SLFN). In theory, ELM algorithm tends to provide good generalization performance at extremely fast learning speed. Experimental results show that ELM has very high correlation with current economic dispatch. Highlights • Information system development is a complex endeavor. • To develop electronic patent (e-patent) system. • Artificial neural networks are applied to predict potential economic growth (GDP). • Experimental results show very high correlation with current economic dispatch. [ABSTRACT FROM AUTHOR]

Abstract In this paper was investigated the effect of exchange rate pass-through (ERPT) into aggregate import prices. The results shown in the long run pass-through was not observed. The results of our research confirm the results of previous investigations according to which pass-through is somewhat higher in transition countries than in developed ones and the pass-through degree is declining. Afterwards exchange rate effect on gross domestic product (GDP) was investigated by adaptive neuro fuzzy inference system (ANFIS). Dataset was collected from EUROSTAT database for 37 countries. The dataset was divided into two sets, for training and for testing of the ANFIS model. The main goal was to predict GDP in relation to exchange rate. ANFIS model was created by three Bell shaped membership functions since it was the best model according to the obtained results. Linear membership functions was used for output. Results shown that the ANFIS model can be used for GDP prediction based on exchange rate values. Highlights • Effect of exchange rate pass-through (ERPT) into aggregate import prices. • Long run pass-through was not observed. • Exchange rate effect on gross domestic product (GDP) was investigated. • ANFIS model can be used for GDP prediction based on exchange rate values. [ABSTRACT FROM AUTHOR]

Evapotranspiration of important indicator for management and planning of water resources. It is essential to analyze the evapotranspiration in order to improve water resources planning. The main goal of the study was to analyze the evapotranspiration based on several input parameters. It is important to estimate the influence of the input parameters on the evapotranspiration. For such a purpose evolutionary algorithm was applied. The algorithm applied in this article has space solution of genetic programs. Therefore this methodology is known as genetic programming. The input parameters in the model are monthly minimum and maximum air temperatures, sunshine hours, actual vapour pressure, minimum and maximum relative humidity and wind speed. Results presented in this study could be used for practical application of water resources planning and management based on the input parameters influence on the evapotranspiration. [ABSTRACT FROM AUTHOR]

Purpose The main aim of the study was to measure the cutting forces and chip shapes based on different machining parameters.Design/methodology/approach To get the best optimal machining conditions, it is essential to use the best combination of machining parameters. Although some machining parameters are not important for the process, there are machining parameters which are very important for the machining process.Findings It is essential to determine which machining parameters are the most dominant to make the optimal machining conditions.Originality/value Six different chip shapes are obtained according to ISO standardization. It was determined that the different cutting forces occurred for the different chip shapes. [ABSTRACT FROM AUTHOR]

Purpose The main purpose of the study was to analyze the relationship between cutting forces and tool wear during turning of steel 30CrNiMo8.Design/methodology/approach It is very important to find the optimal machining conditions to increase the tool life and to improve product quality. Width of tool wear was measured by universal microscope.Findings During experimental procedure, one chip shape was obtained for the given machining parameters. Results showed negligible tool wear for the given experimental conditions. In other words, the tool wear is negligible for one chip shape.Originality/value To increase tool wear, there are different chip shapes. [ABSTRACT FROM AUTHOR]

Purpose This study aims to detect the temperature distribution in the cutting zone during the machining process. Furthermore, temperature influence in the cutting zone on the forms of chip shapes during the turning of Steel 30CrNiMo8 was evaluated. It is very important to use optimal machining parameters to get the best production results or for high control of the machining process.Design/methodology/approach Temperature distribution in the cutting zone during the machining process could affect the forms of chip shapes. Forms of chip shapes could be considered as the most important indicator for the quality of the machining process.Findings Therefore, in this study, the forms of chip shapes based on the temperature distribution in the cutting zone were examined.Originality/value It was found that the snarled chip type and the loose chip type have the highest temperature variation during the machining process. [ABSTRACT FROM AUTHOR]

Purpose The paper aims to present an investigation of wood bonding strength as a very important indicator for effective using in further manufacturing processes.Design/methodology/approach In this study, the wood bonding strength sensitivity was estimated based on grain orientation, feed speed, heating time and temperature, temperature and type of adhesive. Artificial intelligence methods were applied for this analysis because it is strongly a nonlinear process.Findings It was shown that the artificial intelligence tools could be useful, reliable and effective for the wood bonding strength sensitivity estimation. Afterwards the power consumption in in solid wood machining process is analyzed and estimated by the artificial intelligence tools.Originality/value Results shown that the wood bonding strength is the most sensitive for type of adhesive. Thus, the results of the present research can be successfully applied in the wood industry to reduce the time, energy and high experimental costs. [ABSTRACT FROM AUTHOR]

Purpose Acoustic emission (AE) could be used for prevention and detection of tool errors in Computer Numerical Control (CNC) machining. The purpose of this study is to analyze the AE form of CNC machining operations.Design/methodology/approach Experimental measurements were performed with three sensors on the CNC lathe to collect the data of the CNC machining. Adaptive neuro-fuzzy inference system (ANFIS) was applied for the fusion from the sensors’ signals to determine the strength of the signal periodic component among the sensors.Findings There were three inputs, namely, spindle speed, feed rate and depth of cut. ANFIS was also used to determine the inputs’ influence on the prediction of strength of the signal periodic component. Variable selection process was used to select the most dominant factors which affect the prediction of strength of the signal periodic component.Originality/value Results were shown that the spindle speed has the most dominant effect on the strength of the signal periodic component. [ABSTRACT FROM AUTHOR]

Adaptive grippers should be able to detect and recognize grasping objects. To be able to do it control algorithm need to be established to control gripper tasks. Compliant underactuated mechanisms with passive behavior can be used for modelling of adaptive robotic fingers. Undearactuation is a feature which allows fully adaptability of robotic fingers for different objects. In this study gripper with two fingers was established. Finite element method (FEM) procedure was used to optimize the gripper structural topology. Kinetostatic model of the underactuated finger mechanism was analyzed. This design of the gripper has embedded sensors as part of its structure. The use of embedded sensors in a robot gripper gives the control system the ability to control input displacement of the gripper and to recognize specific shapes of the grasping objects. Since the conventional control strategy is a very challenging task, soft computing based controllers are considered as potential candidates for such an application. The sensors could be used for grasping shape detection. Given that the contact forces of the finger depend on contact position of the finger and object, it is suitable to make a prediction model for the contact forces in function of contact positions of the finger and grasping objects. The prediction of the contact forces was established by using a soft computing (computational intelligence) approach. To perform the contact forces estimation adaptive neuro-fuzzy (ANFIS) methodology was used. FEM simulations were performed in order to acquire experimental data for ANFIS training. The main goal was to apply ANFIS network in order to find correlation between sensors’ stresses and finger contact forces. Afterwards ANFIS results were compared with benchmark models (extreme learning machine (ELM), extreme learning machine with discrete wavelet algorithm (ELM-WAVELET), support vector machines (SVM), support vector machines with discrete wavelet algorithm (SVM-WAVELET), genetic programming (GP) and artificial neural network (ANN)). The reliability of these computational models was analyzed based on simulation results. [ABSTRACT FROM AUTHOR]

In this paper, the accuracy of the Weibull model of wind speed is evaluated using an adaptive neuro-fuzzy inference system (ANFIS) based on wind data. The wind data comprises of wind speed measurements in the city of Nis in Serbia at different heights of 10 m, 30 m and 40 m for duration of one year. The ANFIS results are compared with the experimental results and Weibull model using root-mean-square error (RMSE), coefficient of determination, and Pearson coefficient. The effectiveness of the proposed unified strategy is verified based on the simulation results. [ABSTRACT FROM AUTHOR]

The potential of marine power to produce electricity has been exploited recently. One of the ways of producing electricity is by using tidal current turbines. In this study, the hydrodynamic performance of a novel type of ducted tidal turbine was investigated. Tidal energy has become a large contender of traditional fossil fuel energy, particularly with the successful operation of multi-megawatt sized tidal turbines. Hence, quality of produced energy becomes an important problem in tidal energy conversion plants. Several control techniques have been applied to improve the quality of power generated from tidal turbines. In this study, the adaptive neuro-fuzzy inference system (ANFIS) is designed and adapted to estimate power coefficient value of the ducted tidal turbines. The back propagation learning algorithm is used for training this network. This intelligent controller is implemented using Matlab/Simulink and the performances are investigated. The simulation results presented in this paper show the effectiveness of the developed method. [ABSTRACT FROM AUTHOR]

Purpose This paper aims to explore detection of heating load of building by machine learning. Detection of heating load of building is very important in design of buildings due to efficient energy consumption.Design/methodology/approach In this study, detection of heating load of building based on effects of dry-bulb temperature, dew-point temperature, radiation, diffuse radiation and wind speed was analyzed. Machine learning approach was implemented for such a purpose.Findings The obtained results could be useful for future planning of heating load of buildings. Because the heating load of building is a very nonlinear phenomenon, it is suitable to use machine learning approach to avoid the nonlinearity of the system.Originality/value The obtained results could be used effectively in detection of heating load of buildings. [ABSTRACT FROM AUTHOR]

Purpose The purpose of the paper is to evaluate a lake lavel prediction model. Lake-level prediction is very important task for different crucial issues like planning of water resource, controlled drainage, etc. Therefore, in this study, a soft computing approach was applied to predict the lake levels based on the different prediction horizons.Design/methodology/approach The main focus was to establish a sensorless estimation of the lake level based on different prediction horizons. Support vector regression approach was implemented for the lake-level prediction, as this approach is suitable for highly nonlinear prediction problems.Findings Ludoš Lake in Serbia was used for analysis.Originality/value According the results, the soft computing models can be used confidently for the lake-level prediction based on the prediction accuracy. [ABSTRACT FROM AUTHOR]

Purpose The paper aims to analyze chip formation during machining process since it can be a very important indicator for the quality of the machining process, as some chip forms can be undesirable.Design/methodology/approach It is essential to determine the sensitivity of the chip formation on the basis of different machining parameters. The main goal of the study was to analyze the sensitivity of the chip formation during the machining process by using adaptive neuro-fuzzy inference system (ANFIS).Findings According to the results, the chip formation is the most sensitive to feed rate.Originality/value Different cutting tests were performed to monitor the chip formation on the basis of the cutting forces and the cutting displacement. ANFIS was used to estimate the sensitivity of the chip formation during the cutting process on the basis of different parameters. [ABSTRACT FROM AUTHOR]

Water cycle shows the continuous movement of water above and below surface. The water moves could involves the energy exchange which can lead to temperature changes. It is crucial to elaborate the energy exchange in relation to climate changing. Evapotranspiration is one of the most important part of the water cycle. Evaporation presents the water movement to the air and transpiration presents the water movements within a plant. Since the evapotranspiration is very important parameter for climate change, in this article the main aim was to estimate the evapotranspiration based on different climatic parameters such as air temperature, vapor pressure and humidity. Neuro-fuzzy approach was used for the process modeling since the evapotranspiration is very unpredictable factor with strong fluctuation through year. The results could be used for evapotranspiration estimation based on the climate data in order to improve water resources management for agricultural production and irrigation scheduling. [ABSTRACT FROM AUTHOR]

Today’s world depends largely on information and communication technologies. These technologies are in use in different areas of human life and work. Each day, more examples of possible application of information and communications technology are being discovered. In most cases, computer science is used to solve complex problems which have mathematical background. The most important and challenging job in agriculture is plant protection. This is due to its complexity and the lack of specialized tools that could predict when the conditions for specific infections are fulfilled. In this paper authors use different mathematics-based techniques for data processing and prediction of possible fruit disease infection. Six significant weather variables and one variable representing the month in the year are selected as predictor variables. Implemented techniques are compared with each other in order to select the best. Prediction includes two most important diseases of cherry fruit: monilinia laxa and coccomyces hiemalis . Data sets used in this research include data of eight year time period, collected over the region of Toplica in Serbia. The best achieved prediction accuracy is 95.8%. Additionally, the same implemented methods can be applied on other fruit species and other diseases for which data are known. [ABSTRACT FROM AUTHOR]

Evaluation of the optimal laser cutting parameters is very important for the high cut quality. This is highly nonlinear process with different parameters which is the main challenge in the optimization process. Data mining methodology is one of most versatile method which can be used laser cutting process optimization. Support vector regression (SVR) procedure is implemented since it is a versatile and robust technique for very nonlinear data regression. The goal in this study was to determine the optimal laser cutting parameters to ensure robust condition for minimization of average surface roughness. Three cutting parameters, the cutting speed, the laser power, and the assist gas pressure, were used in the investigation. As a laser type TruLaser 1030 technological system was used. Nitrogen as an assisted gas was used in the laser cutting process. As the data mining method, support vector regression procedure was used. Data mining prediction accuracy was very high according the coefficient (R 2 ) of determination and root mean square error (RMSE): R 2  = 0.9975 and RMSE = 0.0337. Therefore the data mining approach could be used effectively for determination of the optimal conditions of the laser cutting process. [ABSTRACT FROM AUTHOR]

In current practice, the remediation of landslides has shown that the biggest problem is the increase in the number of works, and therefore the price of the works. This is due to several factors, including characteristic of the soil, such as the collapse (collapse) of the surrounding ground around the main slide during landslide remediation. Unless these soil erosion effects are taken into account, recovery costs will overrun, which can jeopardize the planned budget. This paper presents a multi-criteria optimization of landslide remediation using the PROMETHEE method and determines the optional number of walls for the additional soil erosion. In a case study on examples of real landslides in the Republic of Serbia, the application of the method is presented and appropriate conclusions are drawn. [ABSTRACT FROM AUTHOR]

Abstract The paper presents the use of the difference GMM and the system GMM for the purpose of determining the critical determinants of non-performing loans. The aim of the paper is to point out the theoretical advantages of GMM in relation to other (often used) panel data estimators in the study of NPLs, and to demonstrate its advantages in the case of the emerging markets in the countries of Latin America. The paper seeks to identify a relevant econometric model in order to demonstrate the impact of crucial macro and microeconomic variables on the NPLs. No evidence was found in support of the significance of the impact of the inflation rate and the microeconomic variables that were the subject of research in this paper. Highlights • To point out the theoretical advantages of GMM in relation to other (often used) panel data estimators. • To demonstrate its advantages in the case of the emerging markets in the countries of Latin America. • To identify a relevant econometric model. • To demonstrate the impact of crucial macro and microeconomic variables on the NPLs. [ABSTRACT FROM AUTHOR]

Highlights • Effective chemical protection of fruit is a complex task. • It is important to automate and optimize the fruit protection process. • Different data mining techniques can be used to identify pattern diseases. • To prevent the excessive use of chemicals. • Results shown that the prediction accuracy is 89%. Abstract Effective chemical protection of fruit is a complex task which can enable production of healthy food without chemical residues. As food health is a growing global concern, it is important to automate and optimize the fruit protection process. Different data mining techniques can be used to identify pattern diseases so as to prevent the excessive use of chemicals. However, application of data mining systems in this field is very complex task. Besides that, these systems are often designed for just one specific plant species. One solution for prediction a risk of fruit infection based on data that represent weather (meteorological) conditions and data pathogens is presented in this paper. The research is performed on the data collected at the region of Toplica in Republic of Serbia during five year period. In this paper data mining based tool for early prediction of fruit pathogen infection is performed. The application is based on the open source engine WEKA with GUI created in C#, and uses several data mining algorithms which are evaluated in this paper. Results shown that the prediction accuracy is 89%. [ABSTRACT FROM AUTHOR]

• Determining the influence of parasitic induction torques. • Analyzing the quantities and parameters of equivalent schemes of induction machines. • Comparing the real values of resistance parameters of induction machines. • Method presented in the paper is verified by an adapted simulation performed. This paper presents a theoretical method for determining the impact of parasitic induction torques analyzing the quantities and parameters of equivalent schemes of induction machines fed by PWM inverter. Tested are three-pased and one-phase induction machines of different parameter and power types. For the fundamental values of power supply from PWM invertor and for important parameters of tested induction machines, comparation of results has been made, of simulation of electrical (stator and rotor current) and mechanical sizes (number of rotation and parasitic torque) of equivalent schemes of induction machines with squirrel cage and wound (phase) rotor are adopted. Theoretic model contains a correction factor, defined as relation of supply power and electro-engine force of induction machine when the rotor is stable. Comparing the real values of resistance parameters of induction machines and values obtained, taking into account a correction factor, certain discrepancies could be observed between values calculated by equivalent T and Г scheme for both groups of machines which do not exceed a value of 5%. Obtained formulas calculated according to equivalent Г schemes could be used for determination of short circuited currents. They are also used for analysis of properties of electric motors, usually for determination of currents that electric motors in the case of short circuits inject into electric network, as well as for the calculation of operating, mechanical and electrical characteristics of induction machines. Adapted simulation in the software package Matlab-Simulink in the sub-program psbupwm.mdl, replaced missing laboratory equipment, which has been used to perofm comparing of results of matematical method of such a system. [ABSTRACT FROM AUTHOR]