|
Process mining and deep learning in the natural sciences and process development
|
Help
Print
|
Here you can view and search the projects funded by NKFI since 2004
Back »
|
|
Details of project |
|
|
Identifier |
116674 |
Type |
K |
Principal investigator |
Abonyi, János |
Title in Hungarian |
Természettudományos kutatás és technológiafejlesztés folyamatbányászati és deep learning algoritmusokkal |
Title in English |
Process mining and deep learning in the natural sciences and process development |
Keywords in Hungarian |
folyamatmérnökség, folyamatbányászat, kémiai és bioinformatika, gépi tanulás |
Keywords in English |
process engineering, process mining, chemical and bioinformatics, machnine learning |
Discipline |
Information Technology (Council of Physical Sciences) | 50 % | Ortelius classification: Applied informatics | Chemical Engineering (Council of Physical Sciences) | 50 % | Ortelius classification: Environmental chemistry |
|
Panel |
Informatics and Electrical Engineering |
Department or equivalent |
Department of Chemical and Process Engineering (University of Pannonia) |
Participants |
Chován, Tibor Nagy, Lajos Németh, Sándor Ulbert, Zsolt
|
Starting date |
2016-02-01 |
Closing date |
2020-01-31 |
Funding (in million HUF) |
18.472 |
FTE (full time equivalent) |
5.60 |
state |
closed project |
Summary in Hungarian A kutatás összefoglalója, célkitűzései szakemberek számára Itt írja le a kutatás fő célkitűzéseit a témában jártas szakember számára. A természettudományos kutatás és a termelő (pl. vegyipari) rendszerek üzemeltetése során keletkező adatokból adatbányászati technikákkal potenciálisan tudományos, mérnöki és gazdasági szempontból hasznos információk állíthatók elő. A probléma szempontjából releváns változók kiválasztása, a györkérokok elemzése az összetettebb adatelemzési feladatok közé tartozik. Sok változó együttes előfordulása, kapcsolatrendszere komplex struktúrák feltárását, tanulását igényli. A kép- és szövegfeldolgozás (pl. Google új algoritmusai) és a mesterséges intelligencia (pl. IBM Watson kognitív rendszere) területén az elmúlt öt évben robbanásszerű sikereket értek el a deep learning megoldások, melyek adatokból komplex struktúrák feltárását tették lehetővé. A kutatás célja ezen eszközök célirányos továbbfejlesztése annak érdekében, hogy a természettudományos kutatás és a technológiák (pl. vegyipari rendszerek) üzemeltetése során keletkező adatokból strukturális modellek, szekvenciák, üzemeltetési körülmények hatékonyan kinyerhetők legyenek. A kutatás során a neurális hálózatok értelmezhetőségével, a többváltozós adatelemzéssel és mérleghiba-kiegyenlítéssel, a gyakori elemhalmazok és szekvenciák feltárásával és a folyamatbányászattal kapcsolatos eddigi eredményeink teljesen újszerű továbbgondolását tervezzük.
Mi a kutatás alapkérdése? Ebben a részben írja le röviden, hogy mi a kutatás segítségével megválaszolni kívánt probléma, mi a kutatás kiinduló hipotézise, milyen kérdéseket válaszolnak meg a kísérletek. A kutatás alapkérdése, hogy a szöveg- és képfeldolgozásban és a mesterséges intelligenciában a nagy multinacionális informatikai vállalatok (IBM, Google) által sikeresen alkalmazott deep learining technikák miként alkalmazhatók a kémiai kutatásban, a bioinformatikában, illetve a technológiai (vegyipari) rendszerek fejlesztésében. A kiinduló hipotézisünk, hogy a folyamatbányászat és a deep learing célirányos, problémaorientált fejlesztése olyan új eszközöket és módszereket hozhat létre melyek a kísérleti adatok feldolgozását, a modellalkotást, a hibadiagnosztikát és a technológafejlesztést és üzemeltetést hatékonyan támogathatják.
Mi a kutatás jelentősége? Röviden írja le, milyen új perspektívát nyitnak az alapkutatásban az elért eredmények, milyen társadalmi hasznosíthatóságnak teremtik meg a tudományos alapját. Mutassa be, hogy a megpályázott kutatási területen lévő hazai és a nemzetközi versenytársaihoz képest melyek az egyediségei és erősségei a pályázatának! Gépi tanulás segítségével adatokból regressziós és osztályozási feladatokra alkalmas modellek állíthatók elő. A csaknem két évtizedes múlttal rendelkező adatbányászat nagyméretű adatokból nyer ki e modellekkel hasznos információkat. A manapság elterjedő „big data” megoldások akkor sikeresek, amikor ezen adatok nem férnek el a számítógép memóriájában. Az adatból-információ területén az új forradalmat a „deep learing” jelenti, mely összetett, rejtett struktúrák, azaz komplex modellek feltárására alkalmas. A kutatás jelentősége abban áll, hogy e megközelítésmódot egy teljesen új területen kívánjuk alkalmazni, illetve a leginkább neurális hálózat alapú algoritmusok mellett a folyamatbányászat, a szekvencia- és a hálózat- és a többváltozós adatelemzés eszköztárára támaszkodva problémaorientált megoldások fejlesztésével kívánjuk kiegészíteni. Kutatásunk eredményeként tehát a kísérleti és technológiai adatok elemzésére a korábbinál hatékonyabb algoritmusok jönnek létre, illetve a deep learning eszköztára is fejlődik.
A kutatás összefoglalója, célkitűzései laikusok számára Ebben a fejezetben írja le a kutatás fő célkitűzéseit alapműveltséggel rendelkező laikusok számára. Ez az összefoglaló a döntéshozók, a média, illetve az érdeklődők tájékoztatása szempontjából különösen fontos az NKFI Hivatal számára. a döntéshozók, a média illetve az adófizetők tájékoztatása szempontjából különösen fontos az OTKA számára A természettudományos kutatás egyik fontos mozzanata a megfigyelt jelenségek, mért értékek alapján új, korábban nem ismert összefüggések feltárása. A feladat kicsit hasonló ahhoz, ahogy mi emberek egy kép alapján képesek vagyunk azonosítani egy arcot. A megfelelő jellegzetességek (pl. orr, fül, szem alakjának, színének) azonosítása hasonló feladat ahhoz, ahogy a kísérleti adatokból modelleket, a változók közötti hatásláncokat, folyamatokat tárunk fel. A kutatás célja ezen analógiát felhasználva új, a természettudományos kutatást és a műszaki (különösen a vegyipari) rendszerek fejlesztését támogató algoritmusok feltárása.
| Summary Summary of the research and its aims for experts Describe the major aims of the research for experts. By the help of data mining techniques we can extract useful information from data generated during the operation of production systems (e.g. chemical) or during the research of natural sciences. The selection of relevant features or the analyses of root causes are complex data analysis tasks. The exploration of correlations of a huge number of variables requires the learning and revealing of complex structures. In the last five years, researchers achieved extremely important successes with the use of deep learning techniques in the field of image and text processing (like the new algorithms of Google) and artificial intelligence (like the cognitive system of IBM Watson). These techniques have allowed the uncovering of complex structures from data. The main goal of the research is the improvement of these tools to effectively retrieve structural models, sequences and operating conditions from the data emerged during research of natural sciences and technologies (e.g. chemical systems). During the research we plan to investigate the interpretability of neural networks, to deal with data analysis and reconciliation, to find frequent itemsets and sequences, and to improve our previous process mining results in a completely novel way.
What is the major research question? Describe here briefly the problem to be solved by the research, the starting hypothesis, and the questions addressed by the experiments. The main question of this research is how deep learning techniques - which are successfully applied by the huge multinational companies (like IBM, Google) in the field of text and image processing and artificial intelligence - can be used in the field of chemical sciences, bioinformatics and in the development of technological (chemical) systems. Our initial hypothesis is that the targeted and problem oriented improvement of process mining and deep learning can give rise to new tools and methods, which can effectively support the processing of experimental data, modeling, fault diagnosis, technological development and operation.
What is the significance of the research? Describe the new perspectives opened by the results achieved, including the scientific basics of potential societal applications. Please describe the unique strengths of your proposal in comparison to your domestic and international competitors in the given field. By the help of machine learning we can construct models, which are suitable for regression and classification problems. For almost two decades, data mining uses these models to obtain useful information from large amounts of data. The so-called “big data” solutions are especially effective when data cannot fit in the memory of the computer. Nowadays, the so-called “deep learning” can be considered as a revolutionary approach of data analysis, since by its help the complex, hidden structures can be discovered, i.e. complex models can be revealed. The main importance of the research consists in the application of this approach in a completely new field, furthermore, beside the neural network based algorithms, we would like to develop problem-oriented solutions depending on the tools of process mining, sequence-, network- and multivariate data analysis. Consequently, as a result of our research, more effective, improved algorithms will be created for analyzing experimental and technological data, furthermore, the tools of deep learning will be evolved.
Summary and aims of the research for the public Describe here the major aims of the research for an audience with average background information. This summary is especially important for NRDI Office in order to inform decision-makers, media, and others. The key issue in the research of natural sciences is the exploration of previously unknown connections based on the observed phenomena and measures values. The problem is similar how humans should identify a given face. The identification of the corresponding characteristics (like the shape and color of nose, ear, eyes) is a similar task to exploration of models, interactions between variables, and processes from experimental data. Using this analogy, the main goal of the research is to explore new algorithms which are capable to support the research of natural sciences, and the development of technical (especially chemical) systems.
|
|
|
|
|
|
|
|
|
List of publications |
|
|
Csaba Pigler, Ágnes Fogarassy-Vathy, János Abonyi: Scalable co-Clustering using a Crossing Minimization ‒ Application to Production Flow Analysis, Acta Polytechnica Hungarica Vol. 13, No. 2, 209-222, 2016 | GYULA DÖRGŐ, JÁNOS ABONYI: GROUP CONTRIBUTION METHOD-BASED MULTI-OBJECTIVE EVOLUTIONARY MOLECULAR DESIGN, HUNGARIAN JOURNAL OF INDUSTRY AND CHEMISTRY, Vol. 44(1) pp. 39–49, 2016 | Daniel Leitold, Agnes Vathy-Fogarassy, and Janos Abonyi: Controllability and observability in complex networks – the effect of connection types, Scientific Reports, elfogadva, 2017 | Richard B. Karoly, Janos Abonyi: Multi-temporal sequential pattern mining based improvement of alarm management systems, IEEE Systems Man and Cybernetics Conference, Budapest, 2153, 1-8, 2016 | Dániel Leitold, Ágnes Vathy-Fogarassy, Zoltán Süle*, Robert Manchin, János Abonyi: MEASURING SUSTAINABILITY – NETWORK SCIENCE BASED ANALYSIS OF WATER RESOURCES MODELS, 7th EDSI Conference - THE WATER FOOTPRINT IN DECISION SCIENCES - Helsinki, Finland May 24 – 27, 2016, 189-203, 2016 | ZOLTÁN SÜLE, JÁNOS BAUMGARTNER, JÁNOS ABONYI: SURVIVAL ANALYSIS BASED DECISION SUPPORT SYSTEM – APPLICATION TO PROCESS IMPROVEMENT, 7th EDSI Conference - THE WATER FOOTPRINT IN DECISION SCIENCES - Helsinki, Finland, May 24 – 27, 119-128, 2016 | Tamás Ruppert, János Abonyi: Production order scheduling with stochastic operation times, 7th VOCAL Optimization Conference: Advanced Algorithms, St. Adalbert Conference Center in Esztergom, Hungary, December 12-15, 2016 | Gyula Dörgő, János Abonyi: The formalization of a multiobjective optimization problem for molecular design, 7th VOCAL Optimization Conference: Advanced Algorithms, St. Adalbert Conference Center in Esztergom, Hungary, December 12-15, 2016 | Dániel Leitold, Ágnes Vathy-Fogarassy, János Abonyi: Process mining based analysis of changeover times - an integrated approach to support line balancing, th VOCAL Optimization Conference: Advanced Algorithms, St. Adalbert Conference Center in Esztergom, Hungary, December 12-15, 2016 | János Baumgartner, Zoltán Süle, Péter Mezőségi, János Abonyi: Test sequence optimization using survival analysis, 7th VOCAL Optimization Conference: Advanced Algorithms, St. Adalbert Conference Center in Esztergom, Hungary, December 12-15, 2016 | Daniel Leitold, Agnes Vathy-Fogarassy, and Janos Abonyi: Controllability and observability in complex networks – the effect of connection types, Scientific Reports, 2017 | G. Dorgo, J. Abonyi: Sequence Mining based Alarm Suppression, IEEE Access, 2018 | Dorgo, P. Pigler, J. Abonyi: Understanding the importance of process alarms based on the analysis of deep recurrent neural networks trained for fault isolation, Journal of Chemometrics, 2018 | Laszlo Gadar, Janos Abonyi: Graph configuration model based evaluation of the education-occupation match, PLOS ONE, open acess megjelenés várható a napokban, 2018 | G. Dörgő, P. Pigler , M. Haragovics: Learning operation strategies from alarm management systems by temporal pattern mining and deep learning, 28th European Symposium on Computer-Aided Process Engineering (ESCAPE), in Computer Aided Chemical Engineering book series, elfogadva, 2018 | Gyula Dorgo, Gergely Honti, Janos Abonyi: Key Factors and Mechanisms of Sustainability - Network Analysis Comparision of Texts and Causal-loop Diagrams, The 6th International Conference on Complex Networks and Their Applications. 412 p. , Konferencia helye, ideje: Lyon, Franciaország, 2017.11.29-2017.12.01. Lyon:2017. pp., 2017 | G. Dörgő, G. Honti, J. Abonyi: Automated analysis of the interactions between sustainable development goals extracted from models and texts of sustainability science, in Chemical Engineering Transactions, PRES 2018 (03/2018), elfogadva, 2018 | K. Varga, G. Dorgo, J. Abonyi: Hierarchical process mining algorithm based on structural analysis of chemical processes, Winter Symposium on Chemometrics, 2018 | G. Dorgo, J. Abonyi: Multi-temporal pattern based fault classification, Conferentia Chemometrica, Gyöngyös-Farkasmály, 03-06. September 2017, Prize for best young scientist presentation., 2017 | Gy Dorgo, J. Abonyi: Improving process safety of water treatment systems by process mining techniques, Víz- és szennyvízkezelés az iparban ’17, 19. October 2017, Prize for best speaker, 2017 | János Baumgartner,Zoltán Süle,Botond Bertók,János Abonyi: Test-sequence optimisation by survival analysis, CENTRAL EUROPEAN JOURNAL OF OPERATIONS RESEARCH, 2018 | Leitold Daniel,Vathy-Fogarassy Agnes,Abonyi Janos: Evaluation of the Complexity, Controllability and Observability of Heat Exchanger Networks Based on Structural Analysis of Network Representations, ENERGIES 12: (3) pp. 1-24., 2019 | Abonyi J.: Feature selection and transformation based analysis and reduction of many-objective optimisation problems, , 2018 | D Leitold,A Vathy-Fogarassy,K Varga,J Abonyi: RFID-based task time analysis for shop floor optimization, IEEE, 2018 | Daniel Leitold,Agnes Vathy-Fogarassy,Janos Abonyi: Empirical working time distribution-based line balancing with integrated simulated annealing and dynamic programming, CENTRAL EUROPEAN JOURNAL OF OPERATIONS RESEARCH 26: pp. 1-19., 2018 | Dörgo G.,Sebestyén V.,Abonyi J.: Evaluating the interconnectedness of the sustainable development goals based on the causality analysis of sustainability indicators, SUSTAINABILITY 10: (10), 2018 | Dörgő Gy,Varga K,Abonyi J: Hierarchical frequent sequence mining algorithm for the analysis of alarm cascades in chemical processes, IEEE ACCESS 2018: pp. 1-20., 2018 | Dörgő Gy.,Ruppert T.,Abonyi J.: Multiobjective optimal sensor placement for data reconciliation, , 2018 | Dörgő Gyula,Abonyi János: Hierarchical Representation Based Constrained Multi-objective Evolutionary Optimisation of Molecular Structures, PERIODICA POLYTECHNICA-CHEMICAL ENGINEERING 1: (1) pp. 1-16., 2018 | Dörgő Gyula,Honti Gergely,Abonyi János: Automated Analysis of the Interactions Between Sustainable Development Goals Extracted from Models and Texts of Sustainability Science, CHEMICAL ENGINEERING TRANSACTIONS 70: pp. 781-786., 2018 | Dörgő Gyula,Pigler Péter,Haragovics Máté,Abonyi János: Learning operation strategies from alarm management systems by temporal pattern mining and deep learning, Elsevier, 2018 | Dörgő Gyula,Varga Kristóf,Haragovics Máté,Szabó Tibor,Abonyi János: Towards Operator 4.0, Increasing Production Efficiency and Reducing Operator Workload by Process Mining of Alarm Data, CHEMICAL ENGINEERING TRANSACTIONS 70: pp. 829-834., 2018 | Gadar Laszlo,Kosztyan Zsolt T.,Abonyi Janos: The Settlement Structure Is Reflected in Personal Investments: Distance-Dependent Network Modularity-Based Measurement of Regional Attractiveness, COMPLEXITY 2018:, 2018 | Gadár László,Kosztyán Zsolt Tibor,Abonyi János: Measurement of regional attractiveness based on company-ownership networks, , 2018 | Gyula Dorgo,Janos Abonyi: Sequence Mining based Alarm Suppression, IEEE ACCESS 6: pp. 15365-15379., 2018 | Gyula Dorgo,Peter Pigler,Janos Abonyi: Understanding the importance of process alarms based on the analysis of deep recurrent neural networks trained for fault isolation, JOURNAL OF CHEMOMETRICS 32: (4), 2018 | Gyula Dörgő,Péter Pigler,János Abonyi: Multivariate statistical models and Bayes chain rule-based analysis of sequence to sequence deep learning models, , 2018 | Laszlo Gadar,Janos Abonyi: Graph configuration model based evaluation of the education-occupation match, PLOS ONE 13: (3), 2018 | Leitold D,Vathy-Fogarassy A,Abonyi J: Network Distance-Based Simulated Annealing and Fuzzy Clustering for Sensor Placement Ensuring Observability and Minimal Relative Degree, SENSORS 18: (9), 2018 | Leitold Dániel,Vathy-Fogarassy Ágnes,Abonyi János: Design-Oriented Structural Controllability and Observability Analysis of Heat Exchanger Networks, CHEMICAL ENGINEERING TRANSACTIONS 70: pp. 595-600., 2018 | Ruppert T,Jaskó Sz,Holczinger T,Abonyi J: Enabling Technologies for Operator 4.0: A Survey, APPLIED SCIENCES-BASEL 8: (9) pp. 1-19., 2018 | Ruppert Tamás,Abonyi János: Worker movement diagram based stochastic model of open paced conveyors, HUNGARIAN JOURNAL OF INDUSTRY AND CHEMISTRY 46: (2) pp. 55-62., 2018 | Süle Zoltán,Baumgartner János,Abonyi János: Reliability - Redundancy Allocation in Process Graphs, CHEMICAL ENGINEERING TRANSACTIONS 70: pp. 991-996., 2018 | Tamás Ruppert,Gergely Honti,János Abonyi: Multilayer Network-Based Production Flow Analysis, COMPLEXITY 2018:, 2018 | Tamas Ruppert,Janos Abonyi: Industrial Internet of Things based cycle time control of assembly lines, IEEE, 2018 | Tamas Ruppert,Janos Abonyi: Software Sensor for Activity-Time Monitoring and Fault Detection in Production Lines, SENSORS 18: (7), 2018 | Dörgő Gyula,Abonyi János: Hierarchical Representation Based Constrained Multi-objective Evolutionary Optimisation of Molecular Structures, PERIODICA POLYTECHNICA-CHEMICAL ENGINEERING 1: (1) pp. 1-16., 2018 | Tamás Ruppert,Gergely Honti,János Abonyi: Multilayer Network-Based Production Flow Analysis, COMPLEXITY 2018:, 2018 | Daniel Leitold,Agnes Vathy-Fogarassy,Janos Abonyi: Empirical working time distribution-based line balancing with integrated simulated annealing and dynamic programming, CENTRAL EUROPEAN JOURNAL OF OPERATIONS RESEARCH 26: pp. 1-19., 2018 | János Baumgartner,Zoltán Süle,Botond Bertók,János Abonyi: Test-sequence optimisation by survival analysis, CENTRAL EUROPEAN JOURNAL OF OPERATIONS RESEARCH, 2018 | Leitold Dániel, Vathy-Fogarassy Ágnes, Abonyi János: Network-Based Analysis of Dynamical Systems, Springer International Publishing, 2020 | Dörgő Gyula, Abonyi János: Group Contribution Method-Based Multi-Objective Evolutionary Molecular Design, HUNGARIAN JOURNAL OF INDUSTRY AND CHEMISTRY 44: (1) pp. 39-49., 2016 | Süle Z, Baumgartner J, Bertók B, Abonyi J: Energy Minimization of Test Processes under Uncertainties by the P-graph Methodology, In: Jiří, J Klemeš (szerk.) Sustainable Process Integration Laboratory Scientific Conference, (2017) p. 16., 2017 | Laszlo Gadar, Janos Abonyi: Graph configuration model based evaluation of the education-occupation match, PLOS ONE 13: (3) e0192427, 2018 | Gyula Dorgo, Janos Abonyi: Sequence Mining based Alarm Suppression, IEEE ACCESS 6: pp. 15365-15379., 2018 | Gyula Dorgo, Peter Pigler, Janos Abonyi: Understanding the importance of process alarms based on the analysis of deep recurrent neural networks trained for fault isolation, JOURNAL OF CHEMOMETRICS 32: (4) e3006, 2018 | D Leitold, A Vathy-Fogarassy, K Varga, J Abonyi: RFID-based task time analysis for shop floor optimization, In: IEEE (szerk.) 2018 IEEE International Conference on Future IoT Technologies, Future IoT 2018, IEEE (2018) pp. 1-6., 2018 | Tamas Ruppert, Janos Abonyi: Industrial Internet of Things based cycle time control of assembly lines, In: IEEE (szerk.) 2018 IEEE International Conference on Future IoT Technologies, Future IoT 2018, IEEE (2018) pp. 1-4., 2018 | Gyula Dörgő, Péter Pigler, János Abonyi: Multivariate statistical models and Bayes chain rule-based analysis of sequence to sequence deep learning models, In: 11th Winter Symposium on Chemometrics, (2018) pp. 29-30., 2018 | Richard Karoly, Janos Abonyi: Multi-temporal sequential pattern mining based improvement of alarm management systems, In: Szakál, A (szerk.) 2016 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings, IEEE (2016) pp. 3870-3875., 2016 | Dörgő Gyula, Abonyi János: Hierarchical Representation Based Constrained Multi-objective Evolutionary Optimisation of Molecular Structures, PERIODICA POLYTECHNICA-CHEMICAL ENGINEERING 63: (1) pp. 210-225., 2019 | Dörgő Gyula, Pigler Péter, Haragovics Máté, Abonyi János: Learning operation strategies from alarm management systems by temporal pattern mining and deep learning, In: Friedl, Anton; J Klemeš, Jiří; Radl, Stefan; S Varbanov, Petar; Wallek, Thomas (szerk.) 28th European Symposium on Computer Aided Process Engineering, Elsevier (2018) pp. 1003-1008., 2018 | Tamás Ruppert, Honti Gergely, János Abonyi: Multilayer Network-Based Production Flow Analysis, COMPLEXITY 2018: 6203754, 2018 | Daniel Leitold, Agnes Vathy-Fogarassy, Janos Abonyi: Empirical working time distribution-based line balancing with integrated simulated annealing and dynamic programming, CENTRAL EUROPEAN JOURNAL OF OPERATIONS RESEARCH 27: (2) pp. 455-473., 2019 | Tamas Ruppert, Janos Abonyi: Software Sensor for Activity-Time Monitoring and Fault Detection in Production Lines, SENSORS 18: (7) 2346, 2018 | Leitold Dániel, Vathy-Fogarassy Ágnes, Abonyi János: Design-Oriented Structural Controllability and Observability Analysis of Heat Exchanger Networks, CHEMICAL ENGINEERING TRANSACTIONS 70: pp. 595-600., 2018 | Dörgő Gyula, Honti Gergely, Abonyi János: Automated Analysis of the Interactions Between Sustainable Development Goals Extracted from Models and Texts of Sustainability Science, CHEMICAL ENGINEERING TRANSACTIONS 70: pp. 781-786., 2018 | Dörgő Gyula, Varga Kristóf, Haragovics Máté, Szabó Tibor, Abonyi János: Towards Operator 4.0, Increasing Production Efficiency and Reducing Operator Workload by Process Mining of Alarm Data, CHEMICAL ENGINEERING TRANSACTIONS 70: pp. 829-834., 2018 | Süle Zoltán, Baumgartner János, Abonyi János: Reliability - Redundancy Allocation in Process Graphs, CHEMICAL ENGINEERING TRANSACTIONS 70: pp. 991-996., 2018 | Dörgő Gy, Varga K, Abonyi J: Hierarchical frequent sequence mining algorithm for the analysis of alarm cascades in chemical processes, IEEE ACCESS 6: pp. 50197-50216., 2018 | Ruppert T, Jaskó Sz, Holczinger T, Abonyi J: Enabling Technologies for Operator 4.0: A Survey, APPLIED SCIENCES-BASEL 8: (9) 1650, 2018 | Leitold D, Vathy-Fogarassy A, Abonyi J: Network Distance-Based Simulated Annealing and Fuzzy Clustering for Sensor Placement Ensuring Observability and Minimal Relative Degree, SENSORS 18: (9) 3096, 2018 | Dörgo G., Sebestyén V., Abonyi J.: Evaluating the interconnectedness of the sustainable development goals based on the causality analysis of sustainability indicators, SUSTAINABILITY 10: (10) pp. 3766-3792., 2018 | Gadar Laszlo, Kosztyan Zsolt T., Abonyi Janos: The Settlement Structure Is Reflected in Personal Investments: Distance-Dependent Network Modularity-Based Measurement of Regional Attractiveness, COMPLEXITY 2018: 1306704, 2018 | Ruppert Tamás, Abonyi János: Worker movement diagram based stochastic model of open paced conveyors, HUNGARIAN JOURNAL OF INDUSTRY AND CHEMISTRY 46: (2) pp. 55-62., 2018 | Leitold Daniel, Vathy-Fogarassy Agnes, Abonyi Janos: Evaluation of the Complexity, Controllability and Observability of Heat Exchanger Networks Based on Structural Analysis of Network Representations, ENERGIES 12: (3) pp. 1-24., 2019 | Sebestyén Viktor, Bulla Miklós, Rédey Ákos, Abonyi János: Network model-based analysis of the goals, targets and indicators of sustainable development for strategic environmental assessment, JOURNAL OF ENVIRONMENTAL MANAGEMENT 238: pp. 126-135., 2019 | Leitold Dániel, Vathy-Fogarassy Ágnes, Abonyi János: Network-based Observability and Controllability Analysis of Dynamical Systems: the NOCAD toolbox, F1000RESEARCH 8: 646, 2019 | Süle Zoltán, Baumgartner János, Dörgő Gyula, Abonyi János: P-graph-based multi-objective risk analysis and redundancy allocation in safety-critical energy systems, ENERGY 179: pp. 989-1003., 2019 | Honti Gergely Marcell, Abonyi Janos: A Review of Semantic Sensor Technologies in Internet of Things Architectures, COMPLEXITY 2019: pp. 1-21., 2019 | Dorgo Gyula, Abonyi Janos: Learning and predicting operation strategies by sequence mining and deep learning, COMPUTERS & CHEMICAL ENGINEERING 128: pp. 174-187., 2019 | Kummer A., Varga T., Abonyi J.: Genetic programming-based development of thermal runaway criteria, COMPUTERS & CHEMICAL ENGINEERING 131: 106582, 2019 | Honti Gergely, Dörgő Gyula, Abonyi János: Review and structural analysis of system dynamics models in sustainability science, JOURNAL OF CLEANER PRODUCTION 240: pp. 1-25., 2019 | Honti Gergely, Dorgo Gyula, Abonyi Janos: Network analysis dataset of System Dynamics models, DATA IN BRIEF 104723, 2019 | Abonyi János: Constrained Recursive Input Estimation of Blending and Mixing Systems, CHEMICAL ENGINEERING TRANSACTIONS 76: pp. 727-732., 2019 |
|
|
|
|
|
|
Back »
|
|
|