Martin Miškuf

Service oriented architecture for remote machine control in ICS

Innovative approaches in the field of information technology gets easily inside automation and creates better platform for integration and cooperation of information and control systems (ICS) components. This innovations lead to the ability of ICS for automatic agile reconfiguration, according to market requirements. To implement this ability has become SOA (service orientated architecture) a part of ICS. This paper deals about SOA with the meaning of communication and integration facility in SCADA/HMI (Supervisory Control And Data Acquisition / Human-Machine Interface) for remote control through mobile devices. Mobile devices integrate big potential for increasing the agility of ICS and can be involved into SOA. Main contribution is increasing agility of ICS with remote control via mobile devices and SOA.

Comparison between multi-class classifiers and deep learning with focus on industry 4.0

Growing amounts of data will be one of consequences in Industry 4.0. This paper deals about mining frequent patterns and important factors in data. Classification is one of the most common assignments in data analytics. We used letter recognition data from the UCI repository as data set for our experiment. Data set contains more than 20000 instances of 26 classes. In our case, it represents multi-class classification. This idea can be transformed into industrial environment. Deep learning is a new area of machine learning research. We decided to use Deep learning from open source H2O machine learning framework and compare it with four multi-class classification algorithms available as services on Microsoft Azure. We are focusing this idea on Industrial systems, cloud architecture and data analytics, which will be fundamental pillars of Industry 4.0.

Application of business intelligence solutions on manufacturing data

Wide range of software from business intelligence (BI) category are used in almost every big company. They allow users to create various reports and analyses. BI idea was primary used for business data, but now many companies like Wonderware, Rockwell are offering solutions for manufacturing data, so new form of intelligence was formed. It is called Manufacturing intelligence or Enterprise intelligence. This paper deals with idea that normal Business intelligence solutions can be used for basic reporting of manufacturing data that covers wide range of user needs. We used data from the biggest private employer in Slovakia, U.S. Steel in Kosice, and BI solutions named Cognos from IBM and second from Oracle. Results was presented management aimed on new IT solutions.

Application of business intelligence solutions from microsoft and IBM on manufacturing data

This paper describes the design, comparison and evaluation of two software solutions from business intelligence category for the purpose of improving report process in the one of the biggest European steel companies. Industrial companies very often use old information system, which were made many years ago. Management chooses business intelligence solutions and our task was to set up web portals and create reports which will be the most similar to actual reports. In this paper we used business intelligence tools in visual studio from Microsoft and Cognos from IBM. Whole process of creation new dynamic ad-hoc reports and predefined static reports in tested solutions was compared with current situation, where workers use old information system. These conclusions achieved during our work were beneficial for company, since they could see how upgrade to newer technologies can affect their reporting process.

Industrial IoT Gateway with Machine Learning for Smart Manufacturing

Working together is important aspect of future industry. Therefore, technologies like Internet of Things (IoT), cloud computing, SOA give rise to another industrial revolution. We propose here a concept definition, which focuses on data acquisition, integration and predictive control in the industry. The concept consists of industrial IoT gateway, cloud services and machine learning services. We used machine learning to verify our data acquisition solution and we implemented prediction control as a cloud service. Finally, proposed solution will exceed boundaries inside ICS (Information and Control System), improve flexibility, interoperability and test plant prediction control in smart manufacturing.

Data mining in cloud usage data with Matlab's statistics and machine learning toolbox

This paper focuses on use of Matlab for data mining. There is wide range of data mining software where free or cheaper solutions offer similar possibilities. We wanted to try Matlab for these purposes. Our data consists of parameters, which describes cloud usage at IT company that offers cloud services. We used phases from the CRISP-DM methodology in our work. We built clustering and classification models that use functions of the Statistics and Machine Learning Toolbox. In the conclusion we summarize our outcomes, weather Matlab is appropriate to data analysis based on conducted experiments.

Advanced analysis of manufacturing data in Excel and its Add-ins

This article focuses on the business analytics and data analysis by application of the advanced tools, technologies and methods of Business Intelligence (BI). These tools enable companies to gain competitive advantage and improve their processes. We had data from the biggest steel factory in Slovakia. In papers [1], [2] we worked with BI solutions and there was request that all reports have to be in formats supported by Microsoft Excel. In this paper, we decided to use Excel and Add-ins like Power Query, Power Pivot, Power View, Power Map, and Power BI for advanced business analysis. Sequentially with the selected Excel Add-ins and based on the available data a complete management information system has been created, capable respond to various queries.

Conchoidal Fracture of Zr- and Mg-Based Amorphous Glass

In metallic glasses plastic deformation occurs via the creation and the propagation of a softened region in the shear bands. Some of the high strength metallic glasses (as Zr-based metallic alloys) exhibit complex shear band topography and the final failure respects the allocation of the shear bands. We studied the differences in the fracture surfaces of Zr-and Mg-based amorphous alloys. Ductile behaviour of the shear bands in Zr-based amorphous alloy tends to the dimple creation during the failure. On the fracture surfaces the vein pattern morphology manifestations were present. Conchoidal fracture was typical for Mg-based amorphous glass. Two different surface morphologies, plumes and rib marks ornament the fracture surfaces.

Innovation of information control system for batching and packaging production line of pasta

This paper deals about reconstruction of a manufacturing line for batching and packaging pasta. We had to design and realise all infrastructure of information control system built on distributed control system. The focus of our work was to replace and upgrade the control system of this manufacturing line. We improved hardware by replacing scale sensors for tensometric sensors and control unit with new graphical supervisor panel. Then we improved scale sensor with a signal conditioner for tensometric sensors. Afterwards, control program and visualization for control system have been created. To make the production more effective, information system for collecting, storing and processing production information has been applied. System functionality has been verified in real-time conditions.

Generation of Nanoscale Stripes at Failure of Amorphous Metals

We analyzed the failure characteristics of the metallic glass Co43Fe20Ta5.5B31.5 (at.%) deformed in bending. The nanoscale fracture surface morphology respects the micromechanisms of the failure of the amorphous structure. The fracture surfaces consist of nanosized dimples (40 nm) arranged in the lines respecting the periodic corrugation zones oriented perpendicular to the crack propagation direction. The corrugation topology exhibits the point nature of the generation site, the concentric form of the stress waves and their interference.