This article describes in more detail the issue of using predictive models of NAR neural networks to predict the course of certain quantities, which may indicate a problem with the industrial machines or their major failures. It is very important to find sufficient size of the structure and values of parameters that directly affect the output accuracy of the model. This article presents the way in which it is possible to automatically find the settings of these NAR models so that the required final accuracy metric is achieved. This presented algorithm was tested on simulation data samples collected by using the M5StickC microcontroller device. This collected dataset presented in this article contains accelerometer and gyroscopic data only, but there is a possibility to expand and add some other sensors to this microcontroller, to collect some other relevant data. This M5-StickC microcontroller device can be used for gathering data in the first phase of the machine state analysis without interfering with the mechanical construction and electrical connections of the machine. Testing of proposed algorithm was carried out in MATLAB environment. The article also describes the way in which these predictive NAR neural network models can be implemented directly in control systems, specifically PLCs from the manufacturer SIEMENS without the use of 3rd party analytical platforms. This application can be helpful in the area of predictive maintenance tasks, especially in avoiding critical failures of industrial machines and devices, or some of their specific parts.

At present, there is a tendency to make greater use of hot water heat sources for the combustion of solid fuels, such as lump wood, coal, coke, instead of heat sources for the combustion of natural gas. This tendency is due to the high price of natural gas as well as the availability of cheaper solid fuel. In many cases, as part of saving on heating costs, respectively. as part of waste disposal, municipal waste of various compositions is also co-incinerated with solid fuel. This co-incineration entails increased emissions, such as CO (carbon monoxide), NOx (nitrogen oxides), TZL (particulate matter), PM10, HCl (hydrogen chloride), PCDD/Fs (polychlorinated dibenzodioxins and dibenzofurans), PCBs (polychlorinated biphenyls) and others which, with a relatively large number of heat sources for the combustion of solid fuel in municipalities, have a significant impact on the quality of the environment in the locality. Between the population and representatives of the state administration as in Žilina, Thus, the Moravian-Silesian Region also lacks awareness of how the environment is degraded due to the co-incineration of solid fuel and municipal waste. At present, there is no qualitative comparison of the effect of combustion of solid fuel and municipal fuel waste to the emission burden on the environment. There are no real measured emission factors for determining the production of the above emissions from the co-incineration of solid fuels and a certain amount of municipal waste. The combustion of fossil fuels and the consequent occurrence of harmful emissions on the environment are therefore becoming a central theme of current heating technology.

Nowadays, artificial intelligence is used everywhere in the world and is becoming a key factor for innovation and progress in many areas of human life. From medicine to industry to consumer electronics, its influence is ever-expanding and permeates all aspects of our modern society. This article presents the use of artificial intelligence (prediction) for the control of three motors used for effector control in a spherical parallel kinematic structure of a designed device. The kinematic model used was the “Agile eye” which can achieve high dynamics and has three degrees of freedom. A prototype of this device was designed and built, on which experiments were carried out in the framework of motor control. As the prototype was created through the means of the available equipment (3D printing and lathe), the clearances of the kinematic mechanism were made and then calibrated through prediction. The paper also presents a method for motor control calibration. On the one hand, using AI is an efficient way to achieve higher precision in positioning the optical axis of the effector. On the other hand, such calibration would be rendered unnecessary if the clearances and inaccuracies in the mechanism could be eliminated mechanically. The device was designed with imperfections such as clearances in mind so the effectiveness of the calibration could be tested and evaluated. The resulting control of the achieved movements of the axis of the device (effector) took place when obtaining the exact location of the tracked point. There are several methods for controlling the motors of mechatronic devices (e.g., Matlab-Simscape). This paper presents an experiment performed to verify the possibility of controlling the kinematic mechanism through neural networks and eliminating inaccuracies caused by imprecisely produced mechanical parts.

No abstract

In this paper we are finding input-output dependencies of feed-forward neural network which usually behaves as black box. It is very important and difficult to find or evaluate those dependencies especially for multi-input/output data approximation. We will use small neural network which will be trained on a given data in MATLAB Mathworks. Network will be simulated in standalone .NET application.