Michal Kebisek

Concept of predictive maintenance of production systems in accordance with industry 4.0

In the proposed paper, we described the approach to build Hadoop based knowledge discovery platform. The proposal focuses on predictive maintenance of production systems, including manufacturing machines and tools, to increase the production process quality. The proposal utilises production data storage, built on Hadoop framework and NoSQL systems, integrated into traditional data warehouse discovery platform, preserving the well proven and robust data warehouse decision support and analytic tools. The initial proof of concept case study is included in the proposed paper.

Data Mining Model Building as a Support for Decision Making in Production Management

The paper gives the next stages of the project that is oriented on the use of data mining techniques and knowledge discoveries from production systems through them. They have been used in the management of these systems. Production data was obtained in previous stages of project. This production data are stored in data warehouse that was proposed and developed by authors. Data mining model has been created by using specific methods and selected techniques for defined problems of production system management. The main focus of our article is the proposal of data mining model.

Active Control of Oscillation Patterns in the Presence of Multiarmed Pitchfork Structure of the Critical Manifold of Singularly Perturbed System

We analyze the possibility of control of oscillation patterns for nonlinear dynamical systems without the excitation of oscillatory inputs. We propose a general method for the partition of the space of initial states to the areas allowing active control of the stable steady-state oscillations. Furthermore, we show that the frequency of oscillations can be controlled by an appropriately positioned parameter in the mathematical model. This paper extends the knowledge of the nature of the oscillations with emphasis on its consequences for active control. The results of the analysis are numerically verified and provide the feedback for further design of oscillator circuits.

Application of open source software on arm platform for data collection and processing

Nowadays embedded solutions based on platform ARM are finding their place on the market. The ARM platform is very popular in the area of mobile devices such as the smart phones, personal players of audio and video, GPS systems etc. This paper describes usage of the IGEPv2 DM3730 device with software for the collecting and processing of physical data. The operating system chosen was the Ubuntu distribution of GNU/Linux operating system, which was adapted for use with the ARM platform. Data source for the proposed measurement system is represented by a sensor network connected to the device through the I2C interface. The data is stored in local databases on the memory card of the device. This paper includes the comparison of the database systems for the proposed application. Connectivity of the device is ensured through wired or wireless connection to a computer network. Application logic of the whole measuring system is installed directly on the development board. For users, the application is accessible through a web browser. Solution shows the use of open source software in the area, which in recent times has been the dominant of proprietary business solutions.

The Utilization of Metrics Usability to Evaluate the Software Quality

This article discusses about metrics that could be used in the field of software testing. The standard ISO/IEC 9126 was analysed. There is need for change of the design of academic information system at the Faculty of Materials and Science in Trnava as the current one is obsolete. Knowledge about usability metrics has been used for purpose of the proposed new design. By preparing the new application design and testing before being put into service have been saved considerable financial resources that can be invested in further development of the system.

Prediction of Selected Production Goals by Classification Methods

The goal of this work was to use the process of knowledge discovery in planning and control of production processes. This work is focused on the prediction of the system behavior from the data of production process. The classification was used as a task of data mining. Some predictive models were created and the predictions of the production process behavior were realized by varying the input parameters using selected methods and techniques of data mining. It can be confirmed that the selected input parameters will lead to the fulfillment of the declared objectives of the process. The process of knowledge discovery has been implemented in the program STATISTICA Data Miner.

Mathematical Approach to Security Risk Assessment

The goal of this paper is to provide a mathematical threat modeling methodology and a threat risk assessment tool that may assist security consultants at assessing the security risks in their protected systems/plants, nuclear power plants and stores of hazardous substances: explosive atmospheres and flammable and combustible gases and liquids, and so forth, and at building an appropriate risk mitigation policy. The probability of a penetration into the protected objects is estimated by combining the probability of the penetration by overcoming the security barriers with a vulnerability model. On the basis of the topographical placement of the protected objects, their security features, and the probability of the penetration, we propose a model of risk mitigation and effective decision making.

Identification of Surface Topography Scanned by Laser Scanning Confocal Microscope

Topography and surface roughness is defined as a set of surface textures formed due to used machining or other production technology. It is a key factor mainly for dynamically stressed components. Greater surface roughness negatively affects the fatigue strength of component or its wear resistance.The paper deals with the visualization and processing of data obtained from a laser confocal microscope Zeiss LSM 700. Data acquired by LSM software ZEN2009 are exported in the text form of 3D coordinates of the image data points and are arranged as a set of 2D profiles with resolution 1.10-7 m. The aim is to describe an alternative method of evaluating raw data extracted from z-stack of acquired TIFF images in order to achieve higher precision and identify the topography of the scanned sample surface. Different methods of data processing have been tested to eliminate deficiencies located mainly in the parts of the scanned surface with low intensity.

Decision Trees Accuracy Improvement for Production Errors Classification

The paper is focused on improvement of classification accuracy of decision trees used in the data mining process. Real production data from the paint shop process serve as its basis. The proposal utilizes various approaches for selection of target attribute intervals and classes and key attributes for classification. The decision tree parameters are optimized to obtain the best possible combination. The results are evaluated across multiple decision tree algorithms.

Integration of Production Line with the Wonderware Platform.

The aim of this paper is to create communication between Wonderware and model of the production line using DAServer. The paper consists of three parts. The first part deals with the introduction of Wonderware and the options it provides. The second part provides a brief overview of the Wonderware modules that we have used. And the third part shows the results we have achieved in creating communication.