Goran Šimunović

An adaptive network-based fuzzy inference system (ANFIS) for the forecasting: The case of close price indices

The close price prediction model of the Zagreb Stock Exchange Crobex(R) index is presented in this paper. For the input/output data plan modeling the Crobex(R) index close price historical data are retrieved from the Zagreb Stock Exchange official internet pages. The prediction model is created in the way that for each of 5days in advance it predicts the Crobex(R) close price. The prediction model is generated based on the input/output data plan by means of the adaptive neuro-fuzzy inference system method, representing the fuzzy inference system. It is of the essence to point out that for each day a separate fuzzy inference system is created by means of the adaptive neuro-fuzzy inference system method based on the same set of input/output data, the only difference being that for every separate fuzzy inference system different subsets for training and checking are used so that input variables are differently created. The input/output data set represents the historical data of the Crobex(R) index close price from 4 November 2010 to 24 January 2012 and the Crobex(R) index close price is predicted for the subsequent 5days, the first day of prediction being 25 January 2012. After that the above mentioned input/output data set is shifted 5days in advance and the Crobex(R) index close price is predicted in advance for the next 5days starting with the last day of the input/output data set. In that way the Crobex(R) index close prices are predicted until 19 October 2012 based on the Crobex(R) index close price historical data. At the end of the paper qualitative and quantitative estimates are presented for the given approach of predicting the Crobex(R) index close price showing that the approach is useful for predicting within its limits.

Modelling and simulation of surface roughness in face milling

The paper presents a research on machined surface roughness in face milling of aluminium alloy on a low power cutting machine. Based on the results of the central-composite plan of experiment with varying machining parameters (number of revolutions - spindle speed n, feed rate f and depth of cut a) and the roughness observed as output variable, two models have been developed: a regression model and a model based on the application of neural networks (NN model). The regression model (coefficient of determination of 0.965 or 0.952 adjusted) with insignificant lack of fit, provides a very good fit and can be used to predict roughness throughout the region of experimentation. Likewise, the model based on the application of neural networks approximates well the experimental results with the level of RMS (Root Mean Square) error in the phase of validation of 4.01%.

Use of Neural Networks in Prediction and Simulation of Steel Surface Roughness

Researches on machined surface roughness prediction in the face milling process of steel are presented in the paper. The data for modelling by the application of neural networks have been collected by the central composite design of experiment. Input variables are the parameters of machining (number of revolutions – cutting speed, feed and depth of cut) and the way of cooling, while the machined surface roughness is output variable. In the modelling process the algorithms Back-Propagation Neural Network, Modular Neural Network and Radial Basis Function Neural Network have been used. Various architectures of neural networks have been investigated on a data sample and they have generated the prediction results which are at the RMS (Root Mean Square) error level of 5.24 % in the learning phase (8.53 % in the validation phase) for the Radial Basis Function Neural Network, 6.02 % in the learning phase (8.87 % in the validation phase) for the Modular Neural Network and for the Back-Propagation Neural Network 6.46 % in the learning phase (7.75 % in the validation phase).

Different Approaches to the Investigation and Testing of the Ni-Based Self-Fluxing Alloy Coatings—A Review. Part 1: General Facts, Wear and Corrosion Investigations

The main aim of this two-part article is to present and arrange the collected important information on widely applicable Ni-based self-fluxing alloy coatings and to point to the variety of investigations considering the period from 2000 to 2013. A survey of the investigations of these coatings obtained by the following deposition technologies will be given: flame spraying, high-velocity oxy-air fuel spraying, detonation gun spraying, electric arc spraying, plasma spraying, plasma-transferred arc welding, and laser cladding. The treated subject is very extensive and is divided into two parts (in the first part wear and corrosion investigations are presented; in the second part the focus is on investigating the impact of external mechanical loading, residual stresses, and the microstructure of coatings). In the first part, following the general facts (terms, deposition technologies, types of investigations, and application), a description and systematization is given of numerous investigations of wear and corrosion as well as cases of the coexistence of wear and corrosion processes.

Different Approaches to the Investigation and Testing of the Ni-Based Self-Fluxing Alloy Coatings—A Review. Part 2: Microstructure, Adhesive Strength, Cracking Behavior, and Residual Stresses Investigations

After presenting general facts about Ni-based self-fluxing alloy coatings and describing the wear and corrosion studies in Part 1, Part 2 of the article deals with the review and systematization of the investigations on behavior of these coatings exposed to external mechanical loading (cracking behavior, adhesive strength, fatigue), residual stresses, and microstructure (particle state, phases, porosity, dilution, dissolution) considering the period from 2000 to 2013. The following deposition technologies are included: flame spraying, high-velocity oxy/air fuel spraying, detonation gun spraying, electric arc spraying, plasma spraying, plasma-transferred arc welding, and laser cladding. In addition to the review of investigations on microstructure and effects of external loading and residual stresses, reference is also given to papers describing the application of the Ni-based self-fluxing coatings, as well as to those in which these coatings were used as a reference material or an addition to obtain a composite coating.

Predicting the Surface Quality of Face Milled Aluminium Alloy Using a Multiple Regression Model and Numerical Optimization

Abstract The surface roughness is a very significant indicator of surface quality. It represents an essential exploitation requirement and influences technological time and costs, i.e. productivity. For that reason, the main objective of this paper is to analyse the influence of face milling cutting parameters (number of revolution, feed rate and depth of cut) on the surface roughness of aluminium alloy. Hence, a statistical (regression) model has been developed to predict the surface roughness by using the methodology of experimental design. Central composite design is chosen for fitting response surface. Also, numerical optimization considering two goals simultaneously (minimum propagation of error and minimum roughness) was performed throughout the experimental region. In this way, the settings of cutting parameters causing the minimum variability in response were determined for the estimated variations of the significant regression factors.

MACHINED SURFACE ROUGHNESS PREDICTION USING ADAPTIVE NEUROFUZZY INFERENCE SYSTEM

This work considers the effect of the depth of cut, feed, and number of revolutions on the roughness of the machined surface. The results obtained by experimentally investigating the workpiece “diving manifold” were used to model the input/output data plan for the adaptive neurofuzzy inference system (ANFIS). Those data were used to generate a fuzzy inference system that made it possible to predict the output (surface roughness) based on the given inputs (feed, number of revolutions, and depth of cut). The surface roughness results obtained by the fuzzy inference system (FIS) were compared with the surface roughness results obtained by neural networks, moving linear least square method and moving linear least absolute deviation method on the same set of experimental data. These methods and systems for prediction of surface roughness are helpful when solving practical technological problems in a manufacturing process, first by determining the cutting parameter values that will add to the demanded quality of a product, and later when optimizing the technological process.

Estimation of Machining Time for CNC Manufacturing using Neural Computing

An approach to solving the problem of machining time estimation in production of complex products within CNC machining systems is presented in the paper. Heuristic analysis of the process is used to define the attributes of influence to machining time. For the problem of estimating machining time the following „Neural Computing techniques“ are used: Back-Propagation Neural Network, Modular Neural Network, Radial Basis Function Neural Network, General Regression Neural Network and Self-Organizing Map Neural Network. Real data from the technological process obtained by measuring are used to design the model used in investigation. The established model is used to carry out the investigation aimed at learning and testing different algorithms of neural networks and the results are given by the RMS error. The best results in the validation phase were achieved by Modular Neural Network (RMSE: 1.89 %) and Back-Propagation Neural Network (RMSE: 2.03 %) while the worst results were achieved by Self-Organizing Map Neural Network (RMSE: 10.05 %). (Received in January 2016, accepted in June 2016. This paper was with the authors 3 months for 1 revision.)

Applying artificial intelligence to the scheduling problem in the ERP system

The basic enterprise tasks are how to satisfy customer demands, how to fulfil due dates, low prices and undoubted quality. Today most of Croatian enterprises are not able to fulfil those obligations. Usually, enterprises have inappropriate planning, scheduling and launching models. The paper shows structure of Croatian Enterprise Resource Planning System (ERP) that is developed for single and batches production and place of artificial intelligence technologies in development of new generation of EPR system. Through the application of 3-tournament steady-state selection genetic algorithm scheduling process can be improved and plan variants can be achieved according to cost, time or both. At the beginning were only some planning techniques such as line charts, line of balance, organisational appliances. The computer era began the first computer programs so called informational islands. These programs solved only particular problems like problems connected with accounting, bookkeeping or employees.

Increasing Stiffness of Constructions through Application of Enhancing Elements

Presented in this work is a study on construction stiffness, based on examination of their neutral lines for various cross-section geometries and different force magnitudes. Investigations were conducted both through numerical simulations and experimentally. The results of numerical simulations indicate that stiffness enhancement reduces deflection in the range of 41-52 %, while the experimental tests showed the reduction of 42-54 %. Also reviewed is comparative analysis between the stiffness results obtained by numerical analyses and experiments, which showed high degree of their compliance. The deviations between the results offered by the two methods are 1-3 %, on average, while in the worst case, which occurs in just a couple of points, the deviation equals 10 %. This study revealed significant increase of element stiffness, which was obtained by employment of additional stiffness enhancing elements.