Wyniki wyszukiwania - BazTech

1

A graph theory-based approach to the description of the process and the diagnostic system

Kościelny Jan Maciej, Bartyś Michał, Syfert Michał, Sztyber Anna

International Journal of Applied Mathematics and Computer Science

|

2022

|

Vol. 32, no. 2

213--227

EN

The paper proposes an original, comprehensive, and methodically consistent graph theory-based approach to the description of the diagnosed process and the diagnosing system. The main baseline of the presented approach is in the dichotomous approach to diagnosing. It involves a separate description of both the process and the diagnostic system. This approach reflects the practice of designing implementable diagnostic systems. Thus, it can be seen as a proposal of a new, alternative, and, at the same time, flexible design procedure with great potential for applications. The primary motivation behind it was an attempt to circumvent the numerous limitations of well-known and well-established diagnosis approaches proposed by the communities working on fault detection and isolation (FDI) and artificial intelligence theories for diagnosis (DX). Accordingly, the paper identifies and provides an extensive discussion and a critical analysis of the existing limitations. Numerous examples and references to practical applications of the approach are indicated.

2

A data driven fault isolation method based on reference faulty situations with application to a nonlinear chemical process

Ragot José, Mourot Gilles, Kallas Maya

International Journal of Applied Mathematics and Computer Science

|

2022

|

Vol. 32, no. 4

635--655

EN

The diagnosis of systems is one of the major steps in their control and its purpose is to determine the possible presence of dysfunctions, which affect the sensors and actuators associated with a system but also the internal components of the system itself. On the one hand, the diagnosis must therefore focus on the detection of a dysfunction and, on the other hand, on the physical localization of the dysfunction by specifying the component in a faulty situation, and then on its temporal localization. In this contribution, the emphasis is on the use of software redundancy applied to the detection of anomalies within the measurements collected in the system. The systems considered here are characterized by non-linear behaviours whose model is not known a priori. The proposed strategy therefore focuses on processing the data acquired on the system for which it is assumed that a healthy operating regime is known. Diagnostic procedures usually use this data corresponding to good operating regimes by comparing them with new situations that may contain faults. Our approach is fundamentally different in that the good functioning data allow us, by means of a non-linear prediction technique, to generate a lot of data that reflect all the faults under different excitation situations of the system. The database thus created characterizes the dysfunctions and then serves as a reference to be compared with real situations. This comparison, which then makes it possible to recognize the faulty situation, is based on a technique for evaluating the main angle between subspaces of system dysfunction situations. An important point of the discussion concerns the robustness and sensitivity of fault indicators. In particular, it is shown how, by non-linear combinations, it is possible to increase the size of these indicators in such a way as to facilitate the location of faults.

3

Performance optimization of model-free fault diagnosis schemes

Kalisch M., Przystałka P., Katunin A., Timofiejczuk A.

Diagnostyka

|

2016

|

Vol. 17, No. 1

51--58

EN

This paper describes the method of model-free fault detection and isolation. The main purpose of the research is to present one possibility of the development of diagnostic schemes for which the component structure and behavioural parameters are tuned automatically in order to obtain the maximal efficiency of the fault detection and isolation system. The proposed approach can be viewed as the intersection of elementary methods (classic and soft computing) such as discrete wavelet analysis, machine learning (using decision trees or artificial neural networks), and evolutionary algorithms. The fundamental verification of the method was conducted for data made available within the benchmark problem involving a wind turbine. The achieved results confirm the effectiveness of the proposed approach while also showing its limitations.

PL

Artykuł opisuje metodę detekcji i izolacji uszkodzeń bez użycia modelu. Głównym celem badań jest pokazanie możliwości opracowania schematów diagnostycznych, których struktura oraz parametry są dostrajane automatycznie w celu osiągnięcia najwyższej możliwej sprawności detekcji i izolacji uszkodzeń. Zaproponowane podejście może być postrzegane jako połączenie elementarnych metod (klasyczne metody oraz obliczenia miękkie) jak np. analiza falkowa, metody uczenia maszynowego (drzewa decyzyjne i sztuczne sieci neuronowe) oraz algorytmy ewolucyjne. Weryfikacja metody została przeprowadzona na danych symulacyjnych wygenerowanych za pomocą modelu turbiny wiatrowej. Uzyskane wyniki potwierdziły wysoką skuteczność metody oraz pokazały jej ograniczenia.

4

Modelowanie testów diagnostycznych za pomocą metod uczenia maszynowego

Kalisch M.

Modelowanie Inżynierskie

|

2014

|

T. 22, nr 53

70--77

PL

W pracy zaprezentowano metodykę tworzenia testów diagnostycznych służących do detekcji i izolacji uszkodzeń za pomocą algorytmów uczenia maszynowego z wykorzystaniem darmowego oprogramowania RapidMiner. Porównano różne metody łączenia klasyfikatorów na przykładzie danych symulacyjnych wygenerowanych za pomocą modelu numerycznego zaworu elektro-pneumatycznego opracowanego w ramach projektu DAMADICS. Przedstawione wyniki badań potwierdzają poprawność proponowanego podejścia.

EN

The papers deals with the methodology of designing diagnostics tests that can be used for fault detection and isolation using machine learning algorithms implemented in open source RapidMiner application. In the paper there were compared different methods of combining classifiers using the benchmark data generated by means of the simulator of electro-pneumatic valve that has been developed within the DAMADICS project. The results of the research study confirm the effectiveness of the proposed approach.

5

Fault diagnosis of dynamical systems using evolutionary algorithms

Witczak M., Korbicz J.

Prace Naukowe Politechniki Warszawskiej. Elektronika

|

2006

|

z. 156

413-420

EN

Challenging and complex design problems arise regularly in modern fault diagnosis systems. Unfortunately, the classical analytical techniques cannot often provide acceptable solutions to such difficult tasks. This explains why soft computing techniques such as evolutionary algorithms are becoming more and more popular in industrial applications of fault diagnosis. The main objective of this paper is to present recent developments regarding the application of evolutionary algorithms in fault diagnosis. The main attention is on the techniques that integrate the classical and evolutionary approaches. A selected example, dealing with the DAMADICS benchmark, is carefully described in the paper.

6

Test Signal Design for Failure Detection: a Linear Programming Approach

Scola H. R., Nikoukhah R., Delebecque F.

International Journal of Applied Mathematics and Computer Science

|

2003

|

Vol. 13, no 4

515-526

EN

A new methodology for the design of filters that permits failure detection and isolation of dynamic systems is presented. Assuming that the normal and the faulty behavior of a process can be modeled by two linear systems subject to inequality bounded perturbations, a method for the on-line implementation of a test signal, guaranteeing failure detection, is proposed. To improve the fault detectability of the dynamic process, appropriate test signals are injected into the system. All the computations required by the proposed method are implemented as the solution of large sparse linear optimization problems. A simple numerical example is given to illustrate the proposed procedure.