Browsing by Author "Karlik, B"

Now showing 1 - 7 of 7
  • No Thumbnail Available
    Item
    Artificial neural network-based prediction technique for wear loss quantities in Mo coatings
    Çetinel, H; Öztürk, H; Çelik, E; Karlik, B
    Mo coated materials are used in automotive, aerospace, pulp and paper industries in order to protect machine parts against wear and corrosion. In this study, the wear amounts of Mo coatings deposited on ductile iron substrates using an atmospheric plasma-spray system were investigated for different loads and environment conditions. The Mo coatings were subjected to sliding wear against AISI 303 counter bodies under dry and acid environments. In a theoretical study, cross-sectional microhardness from the surface of the coatings, loads, environment and friction test durations were chosen as variable parameters in order to determine the amount of wear loss. The numerical results obtained via a neural network model were compared with the experimental results. Agreement between the experimental and numerical results is reasonably good. (c) 2006 Elsevier B.V. All rights reserved.
  • No Thumbnail Available
    Item
    Determination of hardness of AA 2024 aluminium alloy under ageing conditions by means of artificial neural networks method
    Atik, E; Meric, C; Karlik, B
    As known, 2XXX and 7XXX Aluminium wrought alloys can have high strength values by means of precipitation hardening heat treatment. Determination of the precipitation hardening conditions, which can give the most suitable strength values of an alloy, requires numerous tests. But the results of this process which require long time and high cost can be obtained in a shorter time and at a lower cost with less data by means of Artificial Neural Networks method. Since this method is used, less number of experiments and therefore less data are needed. Then other values are found by means of Artificial Neural Networks (ANN) method. This paper, presents the feed forward ANN to determine hardness of alloy for different temperatures. For this purpose, a classic Back-Propagation Algorithm was used that is structure as 1:2:4.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Vibrations of a beam-mass systems using artificial neural networks
    Karlik, B; Ozkaya, E; Aydin, S; Pakdemirli, M
    The nonlinear vibrations of an Euler-Bernoulli beam with a concentrated mass attached to it are investigated. Five different sets of boundary conditions are considered. The transcendental equations yielding the exact values of natural frequencies are presented. Using the Newton-Raphson method, natural frequencies are calculated for different boundary conditions, mass ratios and mass locations. The corresponding nonlinear correction coefficients are also calculated for the fundamental mode. The calculated natural frequencies and nonlinear corrections are used in training a multi-layer, feed-forward, backpropagation artificial neural network (ANN) algorithm. The algorithm produces results within 0.5 and 1.5% error limits for linear and nonlinear cases, respectively. By employing the ANN algorithm, computational time is drastically reduced compared with the conventional numerical techniques. (C) 1998 Published by Elsevier Science Ltd. All rights reserved.
  • No Thumbnail Available
    Item
    An artificial neural network case study: The control of work-in-process inventory in a manufacturing line
    Col, M; Karlik, B
    In manufacturing systems, the cost of stock, which constitutes a significant portion of the total cost, is one of the important costs that has to be dealt with by the managers, The problem of inventory is encountered in cases where accumulation of physical materials is needed for the purpose of meeting the demand of raw materials, work in process and finished goods in a specific period. Work-in-process, between the stages of manufacturing process comes up because of the high rate of flow of raw materials or finished products and insufficient number of labor-machines at work stations, However, work-in-process can be reduced in a manner that does not hinder the process by determining the optimum number of labor-machine according to the process time. Thus, costs of work-in-process become minimum. In this study work in process at a middle-scale shoe factory is investigated, At the manufacturing center, there are five work departments composed of Cutting, Sewing, Hand-leather Working, Assembling and Quality Control-Packing. these In departments there are work in process because of different processing times and insufficient number of labor-machines. Artificial Neural Network (ANN) with backpropagation is used for solving this work-in-process problem, In the study, optimum number of labor-machines at work stations were obtained for work-in-process without hindering the production by considering processing times and flow at these work stations.
  • No Thumbnail Available
    Item
    An improved approach to the solution of inverse kinematics problems for robot manipulators
    Karlik, B; Aydin, S
    A structured artificial neural-network (ANN) approach has been proposed here to control the motion of a robot manipulator. Many neural-network models use threshold units with sigmoid transfer functions and gradient descent-type learning rules. The learning equations used are those of the backpropagation algorithm. In this work, the solution of the kinematics of a six-degrees-of-freedom robot manipulator is implemented by using ANN. Work has been undertaken to find the best ANN configurations for this problem. Both the placement and orientation angles of a robot manipulator are used to fin the inverse kinematics solutions. (C) 2000 Elsevier Science Ltd. All rights reserved.
  • No Thumbnail Available
    Item
    Differentiating types of muscle movements using a wavelet based fuzzy clustering neural network
    Karlik, B; Kocyigit, Y; Korürek, M
    The electromyographic signals observed at the surface of the skin are the sum of many small action potentials generated in the muscle fibres. After the signals are processed, they can be used as a control source of multifunction prostheses. The myoelectric signals are represented by wavelet transform model parameters. For this purpose, four different arm movements (elbow extension, elbow flexion, wrist supination and wrist pronation) are considered in studying muscle contraction. Wavelet parameters of myoelectric signals received from the muscles for these different movements were used as features to classify the electromyographic signals in a fuzzy clustering neural network classifier model. After 1000 iterations, the average recognition percentage of the test was found to be 97.67% with clustering into 10 features. The fuzzy clustering neural network programming language was developed using Pascal under Delphi.