Maxim Bobyr

Southwest state university Russian Federation
{{numberWithCommas(41)}} Publications

A nonlinear method of learning neuro-fuzzy models for dynamic control systems


The paper describes a new learning algorithm of adaptive neuro-fuzzy inference systems that is based on the method of areas’ ratio (MAR-ANFIS). Using linear and nonlinear functions we obtain a generalized model for fuzzy inference. Considering various implication methods, different t- or s- norms and equations for fuzzy inference composition we can change the properties of the resulting output variable. As an example, we illustrate the proposed learning algorithm and show its distinctive characteristics. Firstly, MAR-ANFIS learning algorithm is additive. Secondly, soft operators provide symmetry for the output variable. Also, the proposed algorithm that allows improving accuracy when learning fuzzy system and speed of its learning. Using detailed numerically calculated RMSE and MAPE we evaluate the proposed algorithm. High accuracy of the proposed MAR-ANFIS is confirmed through the calculation of the learning time of neuro-fuzzy network RMSE and MAPE.

Mekhatronika, Avtomatizatsiya, Upravlenie

Fuzziy Digital Filter for Robotic Manipulator Operation

In this article it is described the operation principle of a robotic manipulator ARMino device and the connection diagram of its electrical components. The device includes: An Arduino Mega control board, four servos, four potentiometers, a prototyping board, a computer. Turning the shafts on the potentiometer adjusts the position of the servo spindles. When the voltage on the potentiometer’s pin changes, the voltage at the analog inputs of the microcontroller changes. Then, in the microcontroller, the voltage is scaled to the value of the servo rotation angle. After that, the joints of the robotic manipulator are rotated. During the operation of the ARMino robotiсarm, a contact bounce problem appeared, significantly reducing the accuracy of positioning and the smooth movement of the ARMino joints. To solve this problem, a digital filter was developed. This article describes the digital filter working algorithm, which consists of four steps. One of the steps consists on finding the digital filter coefficients, which regulate the signal voltage level transmitted to the servo motors, and its transition process time which forms the signal edge. The main problem developing a digital filter is that the standard procedure of finding the digital filter coefficients, the coefficients are given by a recommended range of values, which complicates choosing from this range, a single value and transmitting it to the servos. To solve this problem, a fuzzy digital filter was developed, the algorithm of which consists of six steps. The first step determines the input variables degree of truth. The second step is to calculate the degrees of truth of the fuzzy rules preconditions. The third step is to calculate the degrees of truth of the fuzzy rules conclusions by using the process of finding the maximum values. The fourth step is the defuzzification stage in which a precise value of the fuzzy digital filter coefficient is calculated. The fifth step is the output voltage transmitted to the servos. In the sixth step, the output voltage in the microcontroller is converted to the angle value and the servo is given the command to rotate. This article presents numerical simulation of the fuzzy digital filter algorithm, using as an example the servo responsible of the ARMino base rotation. Experimental studies on the functioning of the fuzzy digital filter have been carried out, confirming the expediency of its use. The graphics of the transition process of the robotic manipulator base movement without and with the use of a digital filter are given.

Fuzzy devices for cooling the cutting tool of the CNC machine implemented on Fpga


Heating of a cutting tool during the processing detail on CNC machine cause thermal deformations which reduce the quality of the machined surfaces. The authors propose to use Peltier thermoelement to control thermal deformations. The article presents two devices to control thermoelement based on a current generator and a field effect transistor. Both devices change the current signal transmitted to the thermoelement by using two fuzzy-logical models. We used FPGA Spartan 3E for increasing speed of fuzzy models and the both devices. Therefore, the main goal of the article is to increase the speed of information processing in fuzzy devices. We increased the speed of processing information by using singleton membership functions on the output of fuzzy models, optimizing and parallelizing the program code for calculating fuzzy operations and replacing the division operations by shifts. Time tests conducted at frequency of 200 MHz showed that the current was calculated to 380 ns, the voltage conversion was carried out to190 ns.

Bulletin of Bryansk state technical university


{{numberWithCommas(vm.followersTotal)}} Followers
{{numberWithCommas(vm.followingTotal)}} Following