Zsolt János Viharos

• Doctor of Philosophy
• Senior Researcher at Institute for Computer Science and Control

In this paper we demonstrate a practical post-hoc approach for explainable reinforcement learning (RL) in vehicle powertrain control. The goal is to exploit the advantages of RL yet obtain a solution that is feasible to implement in safety-critical control engineering problems. This means finding a solution that balances optimal product design with...

Background: Early and accurate diagnosis is crucial for effective prevention and treatment of severe mental illnesses, such as schizophrenia and bipolar disorder. However, identifying these conditions in their early stages remains a significant challenge. Our goal was to develop a method capable of detecting latent disease liability in healthy volu...

Machine learning is a powerful tool for extracting valuable information and making various predictions from diverse datasets. Traditional machine learning algorithms rely on well-defined input and output variables; however, there are scenarios where the separation between the input and output variables and the underlying, associated input and outpu...

Motor activity alterations are key symptoms of psychiatric disorders like schizophrenia. Actigraphy, a non-invasive monitoring method, shows promise in early identification. This study characterizes Positive Schizotypy Factor (PSF) and Chronic Schizophrenia (CS) groups using actigraphic data from two databases. At Hauke Land University Hospital, da...

Introduction Alterations in motor activity are an extremely important characteristic and one of the leading symptoms of major functional psychiatric disorders. These pattern disturbances can be observed in schizophrenia. Actigraphy is a non-invasive method that can be used to monitor these changes, and recent studies emphasize its significance in t...

Enhancing the safety of passengers by venturing beyond the limits of a human driver is one of the main ideas behind autonomous vehicles. While drifting is mostly witnessed in motorsports as an advanced driving technique, it could provide many possibilities for improving traffic safety by avoiding accidents in extreme traffic situations. The purpose...

10 éve, 2014-ben született meg a döntés a kecskeméti közgazdászképzés létrehozásáról. A Neumann János Egyetem az egyik legdinamikusabban fejlődő felsőoktatási intézmény Magyarországon. A Gazdaságtudományi Kar pedig az egyetemi fejlődés egyik meghatározó szereplője. A Gazdaságtudományi Kar oktatói és kutatói valódi interdiszciplináris térben mozogna...

A vállalatirányítási rendszerek (ERP) elterjedésének köszönhetően számtalan új lehetőség vált elérhetővé a vállalatok számára, ezek közül emelnénk ki egy kevéssé ismert funkciót, az értesítésmenedzsmentet. A napjainkban használt vállalatirányítási rendszerek rendelkeznek automatikus értesítések küldésére alkalmas lehetőségekkel, az ilyen ún. „monit...

A cikk a vállalati működés során előforduló adatáramlási és anyagmozgási hibákra és lehetséges megoldásaikra, illetve ezek felismerhetőségét biztosító jelek gyűjtésére, strukturálására és elemzésére fókuszál. A kutatás célja egy gyakorlatban és elméleti szinten is használható eljáráscsomag létrehozása, mellyel az ezeken a területeken felmerülő hibá...

The paper discusses training methodologies associated with the introduction of a corporate management IT (Information Technology) system and it analyses corporate training efficiency through a multinational company use-case. The application of flowcharts in the novel IT system-related company trainings, and in the tutorial materials are evaluated....

Felgyorsult világunk egyre jobban megköveteli a vállalatok részéről is, hogy tevékenységüket fenntarthatóan, környezetileg és társadalmilag felelősségteljesen végezzék [1]. Ezen pontokra való odafigyelés abból adódik, hogy az emberek igényt tartanak a felelősségteljes viselkedésre és törvények is egyre jobban szabályozzák a vállalatokat ilyen téren...

(1) Background and Goal: Several studies have investigated the association of sleep, diurnal patterns, and circadian rhythms with the presence and with the risk states of mental illnesses such as schizophrenia and bipolar disorder. The goal of our study was to examine actigraphic measures to identify features that can be extracted from them so that...

The paper analyses and serves with a positioning of various error measures applied in neural network training and identifies that there is no best of measure, although there is a set of measures with changing superiorities in different learning situations. An outstanding, remarkable measure called $E_{Exp}$ published by Silva and his research partn...

For maintenance conform processing of brittle materials (ceramics, glass), the resulting chips are not continuous, as in the case of soft and tough materials, it is called a brittle chip removal range. In this machining zone, the quality of the produced surface may decline (appears the cracks and pitting of the material) and the tool life also decr...

During machining along a complex tool path, it is difficult to connect the change in the amplitude and in the frequency of the recorded vibration signals to the actual state of tool wear. In this article, a method is presented in which the tool wear processes that occur during the machining of a complex geometry (cooling pocket formed on the cerami...

For maintenance conform processing of brittle materials (ceramics, glass), the resulting chips are not continuous, as in the case of soft and tough materials, it is called a brittle chip removal range. In this machining zone, the quality of the produced surface may decline (appears the cracks and pitting of the material) and the tool life also decr...

The effect of the magnetic assisted ball burnishing on a general, C45 steel was investigated considering tribological aspects. In engineering practice, the tribological properties of machined surfaces are characterized by amplitude roughness parameters from roughness profiles, as Rpk, Rk, Rvk, Rsk and Rku. Information about the sliding properties c...

A publikáció a mágnesezhető és nem mágnesezhető anyagok permanens mágneses síkfelület hengerlő szerszámmal végzett során kapott eredményeket foglalja össze. Mind ismeretes, a hidegképlékeny felületjavító eljárások közé tartozik e megmunkálási módszer, amellyel nem csak a felületi érdesség javítható, hanem a felületi réteg szilárdítása és szövetszer...

The main aim of the paper is to monitor the micro- milling tool wearing process offline, by a microscopic tool measurement on one hand, and using high-frequency vibration measurement online, during the cutting process, on the other. Relations between the rake face wear stages and the measured online and offline parameters were determined applying a...

The main aim of the paper is to monitor the micro-milling tool wearing process offline, by a microscopic tool measurement on one hand, and using high-frequency vibration measurement online, during the cutting process, on the other. Relations between the rake face wear stages and the measured online and offline parameters were determined applying an...

Ceramics are non-conductive materials, consequently, they cannot be machined directly by any electrical means. If these ceramics contain some small fractions of conductive components, e.g., as pollutant or as glue materials, they perform a certain, really low level, local and accidental flash of some conductivity. The reported research was performe...

Ceramics are non-conductive materials, consequently, they cannot be machined directly by any electrical means. If these ceramics contain some small fractions of conductive components, e.g., as pollutant or as glue materials, they perform a certain, really low level, local and accidental flash of some conductivity. The reported research was performe...

When using a unique tool with different controlled path strategies in the absence of a punch and die, the local plastic deformation of a sheet is called Single Point Incremental Forming (SPIF). The lack of available knowledge regarding SPIF parameters and their effects on components has made the industry reluctant to embrace this technology. To mak...

In our days, simulation based development is a core element of vehicle engineering, especially considering highly automated or fully autonomous vehicles. Accordingly, the paper presents a benchmark of three different automotive simulators: PreScan, IPG CarMaker, and VTD Vires. The three software tools were applied for the same goal, namely, modelli...

The 21st century manufacturing technology is unimagined without the various CAM (Computer Aided Manufacturing) toolpath generation programs. The aims of developing the toolpath strategies which are offered by the cutting control software is to ensure the longest possible tool lifetime and high efficiency of the cutting method. In this paper, the go...

Autonomous production control (APC) is able to deal with challenges, inter alia, high delivery accuracy, shorter planning horizons, increasing product and process complexity, and frequent changes. However, several state-of-the-art approaches do not consider maintenance factors contributing to operational and tactical decisions in production plannin...

The main concept of the authors is to place Reinforcement Learning (RL) into various fields of manufacturing. As one of the first implementations, RL for Statistical Process Control (SPC) in production is introduced in the paper; it is a promising approach owing to its adaptability and the continuous ability to perform. The widely used Q-Table meth...

The development of modern science requires developing more economical, more environmentally friendly and more efficient procedures in the area of machine parts production as well. Corrosion, as a natural process, shortens the lifetime of our structures and machines. Although there are corrosion-resistant materials and various ways of protections ag...

This paper deals with the problem of integrating the most suitable feature selection methods for a given problem in order to achieve the best feature order. A new, adaptive and hybrid feature selection approach is proposed, which combines and utilizes multiple individual methods in order to achieve a more generalized solution. Various state-of-the-...

Witnessing the unprecedented scale and speed of industry transformation due to digitization in general and the emergence of smart solutions in all aspects of manufacturing in particular, it is well justified to deal with the question of what production of the future will look like. How intelligent will it be when the hard challenges and disruptive...

Autonomous production control (APC) is able to deal with challenges, inter alia, high delivery accuracy, shorter planning horizons, increasing product and process complexity, and frequent changes. However, several state-of-the-art approaches do not consider maintenance factors contributing to operational and tactical decisions in production plannin...

Based on their favourable mechanical features, applications of ceramics are continuously spreading in industrial applications. Hardness and the resistance against heat shock make them usable, so, currently they are widely used, e.g. as coating material for gas turbines. The main aim of the paper is to follow the wearing process of the micro-milling...

Single Point Incremental Forming (SPIF) is a flexible process to manufacture sheet metal parts that is well adapted and profitable for prototypes or small batch production. Compared to traditional sheet forming technologies this relatively slow process can be used in different applications in automotive and aircraft industries, in architecture engi...

Distinguished Readers, the here presented issue of Acta IMEKO makes public in open access form the selected highlights of the 16th IMEKO TC10 Conference on “Testing, Diagnostics & Inspection as a comprehensive value chain for Quality & Safety” held in Berlin, Germany, on September 3-4, 2019. Publication authors from 14 countries contributed to the...

The burnishing process is applied to improve the surface roughness and hardness. The goal of the reported research was to evaluate the machining conditions on magnetisable and non-magnetisable materials by the novel permanent magnetic assisted ball burnishing (MABB) tool. The MABB tool was designed to reduce the surface roughness but this process h...

The aim of this paper is to investigate the effect of different burnishing strategy on a C45 steel machining. Burnishing is a well-known, cold working surface improving technology, it is usually applied for cylindrical workpiece. In the reported research a novel developed magnetic assisted ball burnishing (MABB) tool was applied which was designed...

Based on their favourable mechanical features, applications of ceramics are continuously spreading in industrial environment. Such a good feature is their resistance against heat shock, so, currently they are applied e.g. as coating material for gas turbines. The paper proposes an indirect method for supervision of the cutting tool wear in the opti...

This paper presents the results of various experimental analysis regarding a permanent Magnetic Assisted Ball Burnishing (MABB) tool. This type is a special tool using the magnetic field to produce the necessary force for burnishing, it is applicable especially to rolling flat and 3D harmonic surfaces. For the correct operation of this special kind...

The prevention of electrostatic discharge (ESD) is of crucial importance in the electronics industry, and surfaces of workstations have to be of specific resistance for effective ESD protection. The paper presents results of an R&D project which investigated the—so far rarely researched—dependence of worksurface resistance on ambient conditions and...

Pellet production and consumption are steadily increasing as a renewable energy source. The production and combustion properties of pellets are defined by molecular structure and elemental composition of raw materials. Quality control tools are different in terms of areas they cover the pellet-production cycle, but considering the raw materials, th...

In the automotive and aerospace industries the engineers are encouraged to develop new materials, having special features mainly for the purposes of mass reduction, favourable (specifi) mechanical properties, appropriate strength, heat resistance, and environmental impacts, becoming even more critical technically. The matrix of the metal matrix com...

A full methodology of short-term traffic prediction is proposed for urban road traffic network via Artificial Neural Network (ANN). The goal of the forecasting is to provide speed estimation forward by 5, 15 and 30 min. Unlike similar research results in this field, the investigated method aims to predict traffic speed for signalized urban road lin...

As a well-known conventional finishing process, the grinding is commonly used to manufacture seal mating surfaces and bearing surfaces. It would lead to generate another finishing machining, which more cost-and energy-efficient, so the grinding process could be replaced by machining with roller burnishing or special type of polishing. The machined...

The vehicle industry is facing two megatrends nowadays: alternative drives and autonomous vehicles. Extreme loads have crucial importance inside these trends, too. Unforeseen events happening in real life can be considered as special forms of extreme loads, this is the key novelty of the paper together with the presentation that the classical 6 sig...

Layout planning is an important practical problem for manufacturing companies. In today's market conditions —characterized with continuously changing product portfolio and shortening product lifecycles— frequent reconfiguration is requested if the primary goal for the company is to remain competitive. The key to win customers is to widen the produc...

p>The paper introduces a methodology to define production trend classes and also the results to serve with trend prognosis in a given manufacturing situation. The prognosis is valid for one, selected production measure (e.g. a quality dimension of one product, like diameters, angles, surface roughness, pressure, basis position, etc.) but the applie...

Cutting of metal matrix composites (MMCs) has been considerably difficult due to the extremely abrasive nature of the reinforcements causing rapid tool wear and high machining cost. In this experimental study, three aluminium-based metal matrix composites (MMCs) were produced using a high pressure infiltration. Machining tests were carried out by f...

Both fuzzy logic, as the basis of many inference systems, and Neural Networks, as a powerful computational model for classification and estimation, have been used in many application fields since their birth. These two techniques are somewhat supplementary to each other in a way that what one is lacking of the other can provide. This led to the cre...

The paper introduces an algorithm for increasing the speed for building up the general system model on Artificial Neural Network (ANN) basis. It finds that input/output configuration of the field analysed which realizes the most accurate estimation and explores the maximal number of dependencies among the related system parameters. The availability...

"Big Data" (BD) problems require handling extremely large or complex datasets that would be difficult and expensive using traditional relational databases. Software solutions with distributed processing, weakened consistency requirements and well-designed data models help overcoming scalability issues. Wind energy systems produce extremely large da...

Due to their open and dynamic character, business processes in lack of adequate feedback mechanisms tend to become unstable in case of unanticipated disturbances or target adjustments. In order to face this challenge and to ensure entrepreneurial quality the implementation of quality control loops is proposed, whose design is derived from cyberneti...

A typical wind turbine monitors tens of parameters such as temperatures at different locations, rotation speed of the components, power produced, availability, etc. In many cases sensor data are not collected and stored continuously, because of different reasons like sensor or communication failure, storage size restrictions, condition and situatio...

As the share of wind energy increases on the global energy market, the efficient operation of wind farms gains an ever growing significance. Among operational decisions, the planning and scheduling of maintenance operations are crucial for the availability of turbines, as well as for the operational costs. The paper introduces a system that perform...

The paper introduces an algorithm for building up the optimal system model applying the Support Vector Machine (SVM) modeling approach. It finds that input/output configuration of the system model that realizes the most accurate estimation and explores the maximum of dependencies among the related system parameters. Its performance is tested and ev...

The role of the plastic injection technology has increasing role in automotive industry. The mould maker companies face a considerable challenge not only in terms of productivity of design and manufacturing, but also in trying to meet the increased demand in quotation. The article presents the application of an artificial neural network for cost es...

With the extensive and worldwide increase of the market share of wind energy, the optimal operation of wind farms gains an ever growing significance. The planning and scheduling of maintenance operations is both decisive for turbine availability and a key component of the operational costs. This paper introduces a formal model of wind farm maintena...

The environmental effects of wind power are relatively minor, compared to those of more traditional energy sources. Among the renewable energy arts wind energy plays a significant role and, as forecasted its ratio within the total energy production will rapidly increase. Wind turbines are relatively complex electro-mechanical systems, their smooth...

One of the most important prerequisites of smooth, controlled manufacturing is the application of appropriate monitoring systems. Information about the production processes is dispatched to these systems in a form of measured parameters ahich can be used for accomplishing state analysis and feedback. The usually high number of processed data can be...

Today's complex manufacturing systems operate in a changing environment rife with uncertainty. The performance of manufacturing companies ultimately hinges on their ability to rapidly adapt their production to current internal and external circumstances. On the base of a running national research and development project (NRDP) on digital enterprise...

The key advantage of camera-based moni-toring in automated production lines is its extended functionality combined with reduced costs, owing to the possibility of replacing several classical sen-sors with one vision-based system. While appropri-ate image processing parameters are, usually, easy to find, the same cannot be said about timing pa-ramet...

On the base of a running national research project on digital enterprises and production networks, the paper illustrates how the concepts of intelligent manufacturing systems in view of digital enterprises can contribute to the realization of a digital factory. It describes the main targets, steps and results of the third cluster of the above intro...

This paper recapitulates the results of a long research on a family of artificial intelligence (AI) methods—relying on, e.g., artificial neural networks and search techniques—for handling systems with high complexity, high number of parameters whose input or output nature is partly unknown, high number of dependencies, as well as uncertainty and in...

A mesterséges intelligencia technikák (sokszor más diszciplínák eredményeivel integrálva) nyújtják talán a legígéretesebb eszközöket (pl. mesterséges neurális hálózatok, fuzzy megközelítések, szakértő rendszerek) az intelligens gyártórendszerek által új kihívások megválaszolására. A szub-szimbolikus technikák (pl. a mesterséges neurális hálók) legi...

This paper presents two main groups of results in the field of process modeling; first, highlighting complexity-related properties shared by several, if not all, levels of production; second, a family of methods set up to handle problems resulting from the aforementioned properties. The presented algorithms lead up to a submodel decomposition metho...

In addition of the four main R&D directions, i.e., adaptive manufacturing, digital manufacturing, knowledge-based manufacturing, and networked manufacturing, emphasised by the European initiative Manufuture, two additional requirements, i.e., the real-timeness and cooperativeness of production structures are also outlined in the paper, which are of...

The paper introduces an algorithm for building up the general system model applying the Support Vector Machine (SVM) modeling approach. It finds that input/output configuration of the system model that realizes the most accurate estimation and explores the maximum of dependencies among the related system parameters. Its performance is tested and ev...

Today's complex manufacturing systems operate in a changing environment rife with uncertainty. The performance of manufacturing companies ultimately hinges on their ability to rapidly adapt their production to current internal and external circumstances. On the base of a running national research and development project (NRDP) on digital enterprise...

The application of pattern recognition techniques, expert systems, artificial neural networks, fuzzy systems and nowadays hybrid artificial intelligence techniques in manu- facturing can be regarded as consecutive elements of a proc- ess started two decades ago. The paper outlines the most important steps of this process. Agent-based systems are hi...

The paper summarizes the main ideas and results for realizing agile manufacturing systems having active disturbance handling approach for real-time manufacturing control. The intelligent integration of information received from production-, quality and process monitoring systems is addressed as the enabler of the approach.

In addition of the four main R&D directions, i.e., adaptive manufacturing, digital manufacturing, knowledge-based manufacturing, and networked manufacturing, emphasised by the European initiative Manufuture, two additional requirements, i.e., the real-timeness and cooperativeness of production structures are also outlined in the paper, which are of...

The paper presents two applications of the novel, artificial neural network (ANN) and feature selection based combined, dynamic technique to automatically dissolve a large, complex system into a net of connected submodels. The first application is a solution for the lower level of customised mass-production systems, for increasing their productivit...

This paper highlights similarities between higher and lower levels of production, focusing on assign-ments and solution techniques. Various production levels are examined with respect to several aspects (complexity of relations, large number of parameters) and typical generic tasks ("classical" modelling, problem solving, optimization and submodel...

In addition of the four main R&D directions, i.e., adaptive manufacturing, digital manufacturing, knowledge- based manufacturing, and networked manufacturing, emphasised by the European initiative Manufuture, two additional requirements, i.e., the real-timeness and cooperativeness of production structures are also outlined in the paper, which are o...

Reliable process models are extremely important in different fields of computer integrated manufacturing. They are required e.g. for selecting optimal parameters during process planning, for designing and implementing adaptive control systems or model based monitoring algorithms. Because of their model free estimation, uncertainty handling and lear...

Today's complex manufacturing systems operate in a changing environment rife with uncertainty. The performance of manufacturing companies ultimately hinges on their ability to rapidly adapt production to current internal and external circumstances. Partly based on a running national research project on digital enterprises and production networks, t...

Today's complex manufacturing systems operate in a changing environment rife with uncertainty. The performance of manufacturing companies ultimately hinges on their ability to rapidly adapt their production to current internal and external circumstances. On the base of a running national research and development project (NRDP) on digital enterprise...

Today's complex manufacturing systems operate in a changing environment rife with uncertainty. The performance of manufacturing companies ultimately hinges on their ability to rapidly adapt their production to current internal and external circumstances. On the base of a running national research project on digital enterprises and production networ...

In addition to developing novel ways of part formation (e.g. for the purpose of rapid prototyping), cutting remained one the most important manufacturing technologies [2],[11]. Though being the traditional way of manufacturing, the exact description of cutting processes is unknown, i.e. there are no comprehensive analytical models available for the...

The paper describes a novel approach for learning and applying artificial neural network (ANN) models based on incomplete data. A basic novelty in this approach is not to replace the missing part of incomplete data but to train and apply ANN-based models in a way that they should be able to handle such situations. The root of the idea is inherited...

A block-oriented framework for modelling and optimisation of process chains is introduced and its applicability is shown by the results of the optimisation of cutting processes. The paper illustrates how the framework can support the simulation-based optimisation of whole production plants. The benefits of substituting the time-consuming simulation...

The paper describes a novel approach for generating multipurpose models of machining operations, combining machine learning and search techniques. A block-oriented framework for modelling and optimisation of process chains is introduced and its applicability is shown by the results of the optimisation of cutting processes. The paper illustrates how...