Search

The step response for hydraulic automatic gauge control (HAGC) determines the steel rolling speed and the steel sheet thickness in the process of rolling production. In this paper, the step response test process of HAGC was analysed, and a test approach was proposed for it. Based on that, the transfer function model of the step response test was established and simulated by using Matlab. In order to reduce the settling time and the overshoot, an adaptive proportional-integral-derivative (APID) link was presented in order to compensate for the input signal by using back propagation neural networks (BPNN). The experimental results show that the improved step response test model reaches the process requirements of HAGC, eliminates the jitter of the HAGC system at the start-up phase, and has better stability as well as faster response for steel sheet rolling. [ABSTRACT FROM AUTHOR]

Over the last thirty years, there has been an extraordinary growth in the financial derivatives market, in the field of shipping. This can be attributed to the fact that financial derivatives are contracts that allow all players participating in the shipping market to reduce their exposure to fluctuations in freight rates, bunker prices, interest rates, foreign exchange rates and vessel values. This paper employs an artificial neural network (ANN) in order to forecast the future price of freight derivatives. More specifically, drawing on historical data for the period between January 2005 and March 2009, an ANN is built and trained, and its estimates lead to two individual results. The resulting model indicates to the investor which position to take in the derivatives market (short for sale of agreements and long for the purchase of agreements). [ABSTRACT FROM AUTHOR]

In this study, the effects of cutting parameters (i.e., cutting speed, feed rate) and deep cryogenic treatment on thrust force (Ff) have been investigated in the drilling of AISI 316 stainless steel. To observe the effects of deep cryogenic treatment on thrust forces, M35 HSS twist drills were cryogenically treated at -196 °C for 24 h and tempered at 200 °C for 2 h after conventional heat treatment. The experimental results showed that the lowest thrust forces were measured with the cryogenically treated and tempered drills. In addition, artificial neural networks (ANNs) and multiple regression analysis were used to model the thrust force. The scaled conjugate gradient (SCG) learning algorithm with the logistic sigmoid transfer function was used to train and test the ANNs. The ANN results showed that the SCG learning algorithm with five neurons in the hidden layer produced the coefficient of determinations (R2) of 0.999907 and 0.999871 for the training and testing data, respectively. In addition, the root mean square error (RMSE) was 0.00769 and 0.009066, and the mean error percentage (MEP) was 0.725947 and 0.930127 for the training and testing data, respectively. [ABSTRACT FROM AUTHOR]

V članku je podan predlog za uporabo umetnih nevronskih mrež (ANN) za točno napovedovanje kritične uklonske napetosti cilindričnih izotropnih vijačnih vzmeti s pritrjenima koncema, krožnega preseka in z velikim kotom vijačnice. Uklon aksialno obremenjenih cilindričnih izotropnih vijačnih vzmeti opisuje nabor dvanajstih linearnih diferencialnih enačb. Ker bi bilo iskanje rešitev po analitični poti preveč težavno, se natančne rešitve enačb računajo numerično po metodi prenosne matrike, dosledni brezdimenzijski numerični podatki pa se uporabijo za proces učenja. Na ta način so pridobljene skoraj popolne vrednosti uteži za napovedovanje brezdimenzijskih uklonskih obremenitev. Rezultati se dobro ujemajo s podatki, ki so dostopni v literaturi. [ABSTRACT FROM AUTHOR]