1,721,006 research outputs found
Identification and fault diagnosis of a simulated model of an industrial gas turbine
No full textIn this study a model-based procedure exploiting
analytical redundancy for the detection and isolation of faults
of a gas turbine system is presented. The diagnosis scheme is
based on the generation of so-called ”residuals” that are errors
between estimated and measured variables of the process. The
work is completed under both noise-free and noisy conditions.
Residual analysis and statistical tests are used for fault detection
and isolation, respectively. The final section shows how the actual
size of each fault can be estimated using a multi-layer perceptron
neural network used as a non-linear function approximator. The
proposed fault detection and isolation tool has been tested on a
single-shaft industrial gas turbine model
Neural networks for fault diagnosis of industrial plants at different working points
No full textIndustrial plants often work at different operating points. However,
in literature applications of neural networks for fault diagnosis
usually consider only a single working condition or small changes of
operating points. A standard scheme for the design of neural
networks for fault diagnosis at all operating points may be
impractical due to the unavailability of suitable training data for
all working conditions. This paper addresses the design of a single
neural network for the diagnosis of faults in the sensors of an
industrial gas turbine working at different conditions. The
presented results illustrate the performance of the trained neural
network for sensor fault diagnosis
Fault diagnosis of non-linear dynamic processes using identified hybrid models
No full textThis work addresses an approach for fault diagnosis of industrial processes using identified hybrid models. This paper concerns the identification of the hybrid model parameters through the input-output data acquired from the non-linear process. In order to show the effectiveness of the developed technique, the results obtained in the fault diagnosis of an industrial plant are finally reported
Model--Based Data-Driven Approaches to Robust Fault Diagnosis in Chemical Processes
No full textThis paper presents a robust model--based technique for the
diagnosis of faults in a chemical process. The diagnosis system is
based on the robust estimation of process outputs. A dynamic
non--linear model of the process under investigation is
obtained by a procedure exploiting Takagi--Sugeno (T-S)
multiple--model fuzzy identification. The combined identification
and residual generation schemes have robustness properties with
respect to modelling uncertainty, disturbance and measurement noise,
providing good sensitivity properties for fault detection and fault
isolation. The identified system consists of a fuzzy combination of
T-S models to detect changing plant operating conditions. Residual
analysis and geometrical tests are then sufficient for Fault
Detection and Isolation (FDI), respectively. The procedure here
presented is applied to the problem of detecting and isolating
faults in a benchmark simulation of a tank reactor chemical process
Fault diagnosis of a simulated model of an industrial gas turbine prototype using identification techniques
No full textIn this study a model-based procedure exploiting
analytical redundancy for the detection and isolation of faults
of a gas turbine system is presented. The diagnosis scheme is
based on the generation of so-called ”residuals” that are errors
between estimated and measured variables of the process. The
work is completed under both noise-free and noisy conditions.
Residual analysis and statistical tests are used for fault detection
and isolation, respectively. The final section shows how the actual
size of each fault can be estimated using a multi-layer perceptron
neural network used as a non-linear function approximator. The
proposed fault detection and isolation tool has been tested on a
single-shaft industrial gas turbine model
Special Issue on “Fault Diagnosis and Fault Tolerant Control of Wind Turbine Systems” in International Journal of Adaptive Control and Signal Processing
No full textThis special issue comes from a real need to have an overview about the challenges of modelling and control for Wind Turbine (WT) systems, which require reliability, availability, maintainability, and safety over power conversion effi-ciency. These topics have begun to stimulate research and development in the wide control community particularly for these installations that need a high degree of tolerance with respect to possible fault. Note that this topic repre-sents a key point mainly for offshore wind turbines with very large rotors, since they are characterized by challenging modeling and control problems, as well as expensive and safety critical maintenance works. In this case, a clear con-flict exists between ensuring a high degree of availability and reducing maintenance times, which affect the final ener-gy cost. On the other hand, wind turbines have highly nonlinear dynamics, with a stochastic and uncontrollable driv-ing force as input in the form of wind speed and self induced loads, thus representing an interesting challenge also from the modelling point of view. Fault tolerant control methods can provide a sustainable optimization of the energy conversion efficiency over wider than normally expected working conditions.
This special issue is devoted to any kind of fault detection and isolation (FDI) and fault tolerant control methods ap-plied to WT systems. The goal of this issue is to provide a state of art picture of model-based as well as data-driven methods that take into account realistic conditions such as in the presence of unknown uncontrollable inputs, struc-tured and unstructured model uncertainties
Model-based fault diagnosis in dynamic systems using identification techniques
No full textSafety in industrial process and production plants is a concern of rising importance but because the control devices which are now exploited to improve the performance of industrial processes include both sophisticated digital system design techniques and complex hardware, there is a higher probability of failure. Control systems must include automatic supervision of closed-loop operation to detect and isolate malfunctions quickly. A promising method for solving this problem is "analytical redundancy", in which residual signals are obtained and an accurate model of the system mimics real process behaviour. If a fault occurs, the residual signal is used to diagnose and isolate the malfunction. This book focuses on model identification oriented to the analytical approach of fault diagnosis and identification covering: choice of model structure; parameter identification; residual generation; and fault diagnosis and isolation. Sample case studies are used to demonstrate the application of these techniques
Fault diagnosis of an industrial gas turbine prototype using a system identification approach
No full textIn this work, a model-based procedure exploiting analytical redundancy for the detection and isolation of faults on a gas turbine simulated process is presented. The main point of the paper consists of exploiting an identification scheme in connection with dynamic observer or filter design procedures for diagnostic purposes. Thus, black-box modelling and output estimation approaches to fault diagnosis are in particular advantageous in terms of solution complexity and performance achieved. Moreover, the suggested scheme is especially useful when robust solutions are considered for minimising the effects of modelling errors and noise, while maximising fault sensitivity. In order to experimentally verify the robustness of the solution obtained, the proposed FDI strategy has been applied to the simulation data of a single-shaft industrial gas turbine plant in the presence of measurement and modelling errors. Hence, extensive simulations of the test-bed process and Monte Carlo analysis are the tools for assessing experimentally the capabilities of the developed FDI scheme, when compared also with different data-driven diagnosis methods. © 2007 Elsevier Ltd. All rights reserved
A System Identification Approach for the FDI of an Industrial Gas Turbine Model
No full textIn this work, a model--based procedure exploiting the analytical
redundancy principle for the detection and isolation of the
input--output sensor faults on a gas turbine simulated process is
presented. The contribution of the paper consists of exploiting an
identification scheme in connection with Kalman filter design
procedure for diagnostic purposes. Thus, black--box modelling and
output estimation approach to fault diagnosis are in particular
advantageous in terms of solution complexity and performance
achieved. In order to verify the effectiveness of the proposed FDI
strategy, it has been applied to the simulation data of a
single--shaft industrial gas turbine model in the presence of
measurement and modelling errors. Hence, extensive simulations of
the gas turbine simulator are the tools for assessing the
capabilities of the developed FDI scheme, when compared also with
different model--based and data--driven fault diagnosis methods
Fault Diagnosis of a Simulated Model of an Industrial Gas Turbine Prototype Using Identification Techniques
No full textIn this paper a model-based procedure exploiting analytical
redundancy for the detection and isolation of faults of a gas
turbine system is presented. The diagnosis scheme is based on the
generation of so--called ``residuals'' that are errors between
estimated and measured variables of the process. The work is
completed under both noise-free (deterministic) and noisy
(stochastic) conditions. Residual analysis and statistical tests
are used for fault detection and isolation, respectively. The final
section shows how the actual size of each fault can be estimated
using a multi-layer perceptron neural network used as a non-linear
function approximator. The proposed fault detection and isolation
tool has been tested on a single-shaft industrial gas turbine model
- …
