Wyniki wyszukiwania - Biblioteka Nauki

1

Wybrane problemy diagnostyki procesów przemysłowych

100%

Kościelny J. M. , Syfert M.

|

tom Vol. 53, nr 7

65-79

PL

W referacie omówiono problemy praktyczne, występujące w diagnostyce procesów przemysłowych. Należą do nich: trudności z uzyskaniem odpowiednio wysokiej rozróżnialności uszkodzeń, niepewności występujące we wnioskowaniu diagnostycznym, złożoność struktury obiektu i jej zmienność w trakcie eksploatacji, dynamika powstawania symptomów oraz występowanie uszkodzeń wielokrotnych. Podano sposoby rozwiązania tych problemów. Zostały one zastosowane w opracowanym w Instytucie Automatyki i Robotyki Politechniki Warszawskiej systemie diagnostycznym realizowanym w ramach projektu CHEM.

EN

In the paper the practical issues of diagnostics of industrial processes are described. Here, to the most frequently problems are belonging: difficulties with achievement of sufficiently high fault insolubility, uncertainties of diagnostic reasoning, complexity of the structure of industrial systems and its changeability during exploitation, symptom dynamics as well as occurrence of the multiple faults. The methods of overcoming of those problems are given. Methods presented, were developed in the Institute of Automatic ControI and Robotics of Warsaw University of Technology and have been applied in the diagnostic system developed in the frames of the CHEM project.

2

Fuzzy diagnostic reasoning that takes into account the uncertainty of the relation between faults and symptoms

100%

Kościelny J. M. , Syfert M.

|

tom Vol. 16, no 1

27-35

EN

Knowledge about the relation between faults and the observed symptoms is necessary for fault isolation. Such a relation can be expressed in various forms, including binary diagnostic matrices or information systems. The paper presents the use of fuzzy logic for diagnostic reasoning. This method enables us to take into account various kinds of uncertainties connected with diagnostic reasoning, including the uncertainty of the faults-symptoms relation. The presented methods allow us to determine the fault certainty factor as well as certainty factors of the normal and unknown process states. The unknown process state factor groups all the states with unknown and multiple faults with the states with improper residual values, while the normal state factor indicates similarity between the observed state and the pattern fault-free state.

3

Application properties of methods for fault detection and isolation in the diagnosis of complex large-scale processes

100%

Kościelny J. M. , Syfert M.

|

tom Vol. 62, nr 3

571--582

EN

The survey presents a selection of the methods of the fault detection and isolation suitable to be useful for the diagnostics of the complex, large scale industrial processes. The paper focuses on these methods that have appropriately high level of potential applicability in industrial practice. The novelty of the paper relies on the discussion of the dependency of the level of knowledge about diagnosed process and recommended diagnostic approaches. Appropriate recommendations were given in the convenient form of the table.

4

DiaSter - Intelligent system for diagnostics and automatic control support of industrial processes

80%

Syfert M. , Wnuk P. , Kościelny J. M.

|

tom Vol. 5, No. 4

41-46

EN

The paper presents general description of the DiaSter system implementing advanced methods of modeling, diagnostics and supervisory control for industrial processes. The scope of the tasks realized in the system as well as the system software platform were characterized, in particular: the software structure, central archival and configuration databases, the way of data exchange in the system and the modules of modeling and calculations.

5

System zaawansowanego monitorowania i diagnostyki procesów przemysłowych 'AMandD'

80%

Kościelny J. M. , Syfert M. , Wnuk P.

|

tom nr 3(39)

229-238

PL

W artykule zaprezentowano strukturę oraz właściwości użytkowe systemu zaawansowanego monitorowania i diagnostyki AMandD. System ten przeznaczony jest dla złożonych procesów przemysłowych. Przedstawiono opis wykorzystanych w systemie nowoczesnych algorytmów modelowania oraz detekcji i lokalizacji uszkodzeń jak i wykorzystanych rozwiązań informatycznych. Na zakończenie zarysowano także kierunki dalszych badań i rozwoju systemu.

EN

The paper presents structure and functional properties of the Advanced Monitoring and Diagnostic System 'AMandD' dedicated for large scale industrial processes. Applied in the system up-to-date algorithms of modeling methods and fault detection and isolation were described in the paper. Also a brief description of used IT solutions was presented. As a conclusion, the further directions of development and researches were mentioned.

6

Fuzzy-Logic Fault Diagnosis of Industrial Process Actuators

80%

Kościelny J. M. , Syfert M. , Bartyś M.

|

tom Vol. 9, no 3

653-666

EN

The paper presents an idea of decomposition of diagnostic tasks in complex systems. Such decomposition consists in splitting basic diagnostic functions into lower-level units existing in decentralised structures of automatic control and supervision of the process. An example of a unit that realises this concept and includes a positioner that controls and diagnoses an assembly consisting of a servomotor and a pneumatic control valve is also given. An application of fuzzy logic to the actuator diagnosing algorithm is presented and results of the corresponding fault detection tests in an industrial environment are discussed.

7

Porównanie cząstkowych modeli parametrycznych w zadaniu detekcji uszkodzeń sieci gazowej

80%

Syfert M. , Jankowska A. , Łabęda-Grudziak Z. , Tabor Ł.

Pomiary Automatyka Kontrola

|

2012

|

tom R. 58, nr 1

3-8

PL

Zreferowano badania detekcji uszkodzeń gazociągu z użyciem cząstkowych modeli parametrycznych. Stosując trzy metody modelowania: addytywne modele regresyjne (najnowszą z badanych technik), sztuczne sieci neuronowe oraz układy rozmyte typu TSK opracowano aproksymacje ciśnień w węzłach sieci. Modele testowano w zadaniu detekcji wycieku oraz uszkodzenia czujnika pomiarowego. Wszystkie modele zapewniały dużą dokładność aproksymacji ciśnienia w poprawnych stanach pracy, wykazując także bardzo skuteczną detekcję uszkodzeń czujników pomiarowych ciśnień, natomiast w sytuacji symulowanych wycieków ich przydatność w detekcji była znacznie mniejsza.

EN

The results of faults detection [1, 2, 3, 4, 5] in a gas system network (Fig. 1) with use of parametric partial models [6, 7, 8] are presented in the paper. This is a new approach to the task with use of exploratory data analysis [10, 11, 17] and partial models. Three techniques were used to build models of pressure in network nodes: additive regression (ADD - new method of modelling [10, 11, 12, 13, 14, 15]), artificial neural networks (ANN) [16, 17, 18] and TSK fuzzy logic modelling [8, 16, 17]. The measured pressures in adjacent nodes as well cumulative flows in the main line (from global analytical model [9]) of gasoline were the inputs of the models. For the analysed stations (in parts A and B marked in Fig. 1) a set of test failures in the form of leaks and damage of pressure sensors is given in Tab. 1.Using trial and error method, by evaluating the effectiveness of fault detection, there were obtained structures of models of different complexity for individual modelling techniques: ADD - presented by equations (1) and (2), ANN- (3) and (4), TSK- (5) and (6). The model order is not greater than 2. The exemplary results of leak detection with use of particular models are shown in Figs. 3, 5, 7 and of sensor fault detection in Figs. 4, 6, 8. In the conclusions there is summarised the relative accuracy of models (in Table 2), the relative normalized values of the studied residues of leaks - Tab.3 and the pressure sensor failures - Tab. 4. All models provided highly precise pressure approximation in non-fault states, but TSK and ADD models turned out to be the more accurate. Additionally, all of them were effective in case of pressure sensor fault detection, however, in case of simulated leakages their usefulness was much lower.