Milos Hammer

Fuzzy systems for simulation and prediction of the residual life of insulating materials for electrical machines windings

Nowadays, the perspective diagnostic methods not only evaluate the current insulation condition, but also forecast the certain prognoses of the life of insulating material under the specified operational conditions. This contribution undertakes both simulation and prediction of the residual life of the Relanex insulating material for electrical rotating machine windings. In case of simulation, the current condition of insulating material based on the input data is determined. In case of prediction, the insulation condition in the future time k+1 is predicted based on the input quantities in the times k, k-1, k-2, etc. Prediction means forecasting an output quantity in future based on the N values of this quantity and/or the other quantities measured in the past. By means of the diagnostic quantities Ba (the quantity is proportional to the effective activation energy of polarization effects), Bv (the quantity is proportional to the effective activation energy of conductive effects) and Uk (the quantity is proportional to critical voltage) and by using a fuzzy method in the form of fuzzy models and predictors, we can determine breakdown voltage. This approach determines either the current condition of insulating material, taking into account electric strength, or the life prognosis of this material. To simulate and predict a magnitude of breakdown voltage, the Sugeno type fuzzy system was applied, especially for easy setting input parameters. According to the input quantity matrix (i.e., Ba, Bv, and Uk) measured at the Relanex insulating material samples, and according to a consecutive training phase, it is possible to simulate and predict the values of breakdown voltage Ups. The values can be compared to the real measured values of breakdown voltage Up. The evaluation of the fuzzy system quality is performed on the basis of relative and absolute errors.

The use of neural networks for the life prediction of insulating material of electric rotating machines

The life of the insulating systems of electric rotating machines is strongly dependent upon electrical and thermal features of the insulating material used. The subject of the diagnostic prediction is to specify the condition of insulation used. At present days, the most popular prediction tools are the methods of artificial intelligence, and one method is the neural networks. This paper is concentrated on the use of neural networks in the life prediction of Relanex insulating material that is applied as insulation of electrical machine windings. In this case the condition of insulating in a time step k+1 is predicated from input quantity in time steps k, k-1, k-2, etc. Anyway the prediction means forecasting of quantity in future from N previous measurement this or other quantities in the past. The first part of the paper describes the use of artificial neural networks which forecast the life of insulating material for windings in electric rotating, the description of train and test data and setting of neural network for prediction. The second part shows the simulation of insulating material behavior with neural networks. Tables evaluate the application of this tool for the solution of the problems investigated. We have used the above-mentioned neural networks for the prediction of insulating materials that were programmed in Matlab 6 environment.

USE OF MULTIPARAMETRIC DIAGNOSTICS IN PREDICTIVE MAINTENANCE

The present article describes how to use multiparametric diagnostics in maintenance. First, the maintenance is defined and its history is briefly analysed. Subsequently, the maintenance is divided according to current considerations. It is stated that the proactive maintenance represents the state-ofthe-art approach to maintenance management. The use of multiparametric diagnostics, such as vibration analysis, electrodiagnostics, tribodiagnostics, etc., is mentioned. A special attention in the present article is paid to the examples of the use of diagnostics in dynamic and static measurements. The so-called route diagnostics focusing on vibrations, as well as diagnostics of current and voltage values, power input monitoring, spectral analysis of current, and temperature, flow and pressure measurements are mentioned. The measurements of insulation resistance and other parameters of the device drive are also given. The text is supplemented with several pictures showing the results of specific diagnostic measurements from industrial practice.

Expert Systems in Transformer Diagnostics

The contribution is focused on the diagnostics of transformers in power engineering practice. First, attention is paid to the brief description of the general expert systems. Furthermore, the classification of expert systems and the analysis of the diagnostic expert system without vagueness are presented. In this contribution, emphasis is laid on the description of the rule expert system which is applied in the diagnostics of transformers. The composition of this expert system and the specific example of the results obtained are analysed in detail.

Artificial Intelligence in Diagnostics of Electric Machines

The article is focused on the applied artificial intelligence in the diagnostics of electric machines. Attention is paid to some developmental trends of artificial intelligence, for example, neural networks, fuzzy systems, genetic algorithms and expert systems. Having in mind the intended future usage in electric machine diagnostics the accent is placed on the analysis of topology and behaviour of an artificial intelligence method – fuzzy systems. The obtained results are evaluated in detail.

IDENTIFICATION OF SAFETY CULTURE LEVEL USING QUESTIONNAIRE SURVEYS

e-mail: Irina.Fedorycheva@vutbr.cz The aim of the present article is to provide information on the results of the safety culture assessment carried out in three engineering companies in the Czech Republic in 2017. Determining the level of safety culture helps to reveal the weaknesses in the work process from the point of view of safety in a particular company and, of course, it also allows to propose the necessary measures for improvement. The article builds on the previous publications of the authors; therefore, it no longer announces the theoretical essence of the safety culture, but addresses the practical aspects of the subject based on factual examples. The article has two main parts. First, the issue of investigating the safety culture is described, including one of the selected approaches. The principles and techniques of questionnaire processing are analysed. The next part of the article introduces the results of the assessment. The issues of safety culture are quite extensive; it is not possible to tackle all of them in a single article. In some areas, the safety culture is not systematically addressed in its complexity. This also applies to engineering. In our workplace, we intensively focus on the issues of safety culture; some partial approaches and results are the content of the present article. Experience with the described assessment method can be useful or serve as a guide to analyse the level of safety culture in other industrial companies.

DIAGNOSTICS AND MAINTENANCE OF MACHINE TOOL SPINDLES - NEW VIEWS

This paper discusses changes in the field of maintenance brought by the Fourth Industrial Revolution Industry 4.0. Main pillars of the Industry 4.0 are as follows: digitization, interconnection, linking and visualization of all corporate parts, starting from production, through maintenance, and ending by logistics. Maintenance is one of the areas affected most by these changes. It is not enough to monitor only certain machine parameters and assess their status –the offline diagnostics. Monitoring of all machines and measurable parameters is requested and, in addition to it, it is advisable to ensure visualizationfor the users –the online diagnostics. Technical diagnostics belongs to important aspects for ensuring maintenance, mainlythe preventive, predictive and proactive maintenance. Vibrodiagnostics is one of the most widespread diagnostics in the field of mechanical engineering, where the signal from the source of vibrations carries the information concerning the cause of vibrations, and its analysis can establish, even well in advance, the emerging or developing defect or damage. This article describes the differences between the online and the offline vibrodiagnostics and analyzes the results of specific measurements. Online diagnostics visualization with the possibility of its use in the maintenance sector is demonstrated here as well. KEYWORDS

PROGNOSIS OF BEHAVIOUR OF MACHINE TOOL SPINDLES, THEIR DIAGNOSTICS AND MAINTENANCE

The present article focuses on the use of neural networks to predict the behaviour of certain diagnostic parameters of spindles of machine tools. An online vibro-diagnostics is used, and from many specific measured parameters, the effective value of some variables in the time series. The results are used in the maintenance based on the technical condition, in particular, in preventive and proactive maintenance. This procedure is completely original and allows for better setting of maintenance policy, which is also beneficial for planning maintenance costs. The article also mentions the necessity to implement the steps described, also in the context of the Industry 4.0 initiative, and further, it briefly discussesprognostics, technical diagnostics, maintenance and maintenance systems. The used neural networks and the calculation procedure are also analysed. The conclusions obtained are evaluated.

SELECTED CHARACTERISTICS AND DIAGNOSTICS OF MOTOR POWERED BY FREQUENCY CONVERTER

All of the technical devices that are powered by the frequency converter, apart from their great advantages, also bring considerable pitfalls and risks. When designing a machinery, it is necessary to consider the negative effects of characteristics of the frequency converter on the rotating parts, especially on the bearings of motors, gearboxes, gears, seals, etc. These devices and their parts are usually exposed to the effects of capacitive and shaft currents that have a considerable impact on the reliability of machines and equipment. This article focuses on the reasons for the use of insulated bearing (or insulated coupling) for asynchronous motors and on the influence of the measures taken to eliminate the adverse effects on the rotating parts. The following is an example of the use of technical diagnostics to determine the condition of some parts of the machinery, the example is evaluated, conclusions are drawn and analysed.

Operational limits in vibration diagnostics

The paper discusses some practical problems occurring at ISO 10816-1 application in technical practice. Technical diagnosticians find out frequently that the zone boundaries proposed by the standard are not sensitive adequately to the changes in vibrations during operation resulting from a change of technical condition of the machine. The principle of statistical determination of individual operational limits from the measured overall level of RMS vibration velocity (overall level) with utilization of statistical regulation of individual values is also described in the paper. The alarm limit for the overall level (boundary between the B and C zones) in the range 10–1000 Hz is specified in the paper on the basis of measuring of vibrations on the electric motor of Bosch Rexroth hydraulic unit.