1 |
The design and implementation of a statistical pattern recognition system for induction machine condition monitoringHatzipantelis, Eleftherios January 1995 (has links)
Automated fault diagnosis in induction machines is a difficult task and normally requires background information of electrical machines. Here a different methodology to the condition monitoring problem is devised. The approach is based entirely on Digital Signal Processing (DSP) and Statistical Pattern Recognition (PR). Description of machine conditions is extracted from empirical data. The main tasks that must be carried out by a PR-based condition monitoring system are: condition identification, knowledge reinforcement and knowledge creation for previously unseen conditions. The DSP operations are employed to quickly isolate sensor faults and to remove noise using data acquired from a single channel. DSP transformations may seem promising in making the monitoring system portable. Most importantly, they can compensate for operational changes in the machine. These changes affect the supply line currents and the primary signal quantities to be measured, i.e. the current and the axial leakage flux. The data which is input to the statistical monitoring system may be transformed, in the form of features, or remain unaltered. The system exploits the statistical properties of the feature vectors. The particular features, namely the LAR coefficients, convey short-term, high-resolution spectral information. For a long record, the feature vector sequence may provide information about changes in the record spectral characteristics, with time. Many induction machine processes are stationary and they can be properly be dealt with by a simple statistical classifier, e.g. a Gaussian model. For nonstationary processes, the system may employ a more comprehensive tool, namely the Hidden Markov Model. which may track the changing behaviour of the process in question. Initially a limited number of machine conditions are available to the process engineer. By identifying their boundaries, new faulty conditions could be signalled for and adopted into the database.
|
2 |
Isolamento automático de falhas em sistemas. / Automatic isolation of system failures.PORTO, Wagner de Souza. 28 August 2018 (has links)
Submitted by Johnny Rodrigues (johnnyrodrigues@ufcg.edu.br) on 2018-08-28T16:50:59Z
No. of bitstreams: 1
WAGNER DE SOUZA PORTO - DISSERTAÇÃO PPGCC 2009..pdf: 3676431 bytes, checksum: 91bede14a64447aa4598ba5c6b3365a4 (MD5) / Made available in DSpace on 2018-08-28T16:50:59Z (GMT). No. of bitstreams: 1
WAGNER DE SOUZA PORTO - DISSERTAÇÃO PPGCC 2009..pdf: 3676431 bytes, checksum: 91bede14a64447aa4598ba5c6b3365a4 (MD5)
Previous issue date: 2009-09-16 / Este trabalho apresenta o Auto-FDI (Automatic Fault Detection and Isolation), uma
ferramenta de detecção e isolamento de falhas em sistemas. A ferramenta usa o conceito
de redundância analítica, onde sinais obtidos do sistema (possivelmente com falha) são
comparados com sinais esperados, obtidos de um modelo. O isolamento de falhas
emprega uma técnica desenvolvida neste trabalho, chamada isolamento automático. A
técnica usa uma abordagem baseada em grafos que considera a propagação de falhas e a
falta de informação sobre determinados componentes do sistema. Falhas são localizadas
de forma mais precisa possível, dado o nível de detalhe do modelo. No escopo deste
trabalho foi abordado todo o processo de especificação, projeto, implementação e
validação da ferramenta, utilizada como prova de conceito para a técnica desenvolvida.
A validação da ferramenta foi feita através da realização de um estudo de caso por
potenciais usuários, o que permitiu demonstrar a aplicabilidade da ferramenta e a da
técnica desenvolvida. / This work presents Auto-FDI (Automatic Fault Detection and Isolation), a software
tool for detection and diagnosis of faults in systems. The tool uses the analytical
redundancy concept, where signals from the (possibly faulty) system are compared with
expected signals from a model. The fault isolation employs a technique developed on
this work, called automatic isolation. This technique uses a graph-based approach
which considers the fault propagation and the lack of information about certain
components of the system. Faults are pinpointed as accurately as possible given the
level of detail in the model. In the scope of this work was addressed the whole process
of specification, design, implementation and validation of the tool - used as proof of
concept for the developed technique. The validation of the tool was made by conducting
a case study for potential users, that has demonstrated the applicability of the tool and
the technique developed.
|
Page generated in 0.1073 seconds