Andrzej Czajkowski

Actuators and sensors fault diagnosis with dynamic, state-space neural networks

In this paper, the actuators and sensors fault detection and localization using a system model is considered. To obtain the system model, the neural network modeling is used. The artificial feedforward neural network with dynamic neurons in the state-space representation is proposed. To estimate the neural network parameters, the Adaptive Random Search algorithm with projection is used. To identify, which of actuators or sensors is faulty, the system input estimator is proposed. The input and output residuals being the difference between the system input and output and its estimates are used to detect and isolate the faults. The final part of the paper presents an application study, which clearly confirms the effectiveness of the proposed approach.

Application of the state space neural network to the fault tolerant control system of the PLC-controlled laboratory stand

This paper deals with the design of a fault tolerant control system for a laboratory stand. With the application of a state space neural network it is possible to design both the nonlinear model and the observer of the considered plant. Analysing outputs of those models, it is possible to carry out fault detection. In order to cope with uncertainties of the model, a robust fault detection scheme is used which is based on the model error modelling technique. When a fault is detected, the fault tolerant control starts to compensate the fault effect. This is achieved through a proper recalculation of a control law. The new control law is obtained by adding an auxiliary signal to the standard control. This auxiliary control constitutes the additional control loop which can affect the stability of the entire control system. Therefore, stability of the proposed control scheme based on the Lyapunov direct method is also investigated. Finally, the approach is tested on the fluid flow and pressure control laboratory stand.

Model Predictive Control of the Two Rotor Aero-Dynamical System Using State Space Neural Networks with Delays

This paper deals with the application of state space neural network model with delays to design a model predictive control for a laboratory stand of the Two Rotor Aero-dynamical system. The work describes approach based on the so-called instantaneous linearisation of the already trained nonlinear state space model of the system. With obtained linear model it is possible to derive a vector of future controls based on the minimisation of the cost function within one optimisation window. Repeating procedure in each step of simulation and applying the obtained control signal allows for efficiently control of the nonlinear systems. All data used in experiments is obtain from the real-time laboratory stand which is working in Matlab/Simulink RTW environment.

Designing nonlinear model of the Two Rotor Aero-dynamical system using state space neural networks with delays

This paper deals with the application of state space neural network model with delays to design a nonlinear model for a laboratory stand of the Two Rotor Aero-dynamical system as an example of the MIMO (multi input multi output) system. The work presented is the first part of the researches on the design of the nonlinear model predictive control and focuses on obtaining of the best system model. The work describes the methodology of system analysis to obtain the most informative data which can be successfully used in training of the neural network. The system analysis is based on spectral analysis with Fouriers transform. All data used in experiments is obtain from the realtime laboratory stand which is working in Matlab/Simulink RTW environment.

Stability analysis of the neural network based fault tolerant control for the boiler unit

This paper deals with the stability analysis of the fault accommodation control system. When a fault is detected, the fault tolerant control tries to compensate the fault effect by adding to the standard control the auxiliary signal. This auxiliary control constitutes the additional control loop which can influence the stability of the entire control system. This paper focuses on the stability analysis of proposed control scheme based on the Lyapunov direct method.

Robust Fault Detection by Means of Echo State Neural Network

This paper deals with the application of Echo State Network (ESN) model to robust fault diagnosis of the Twin Rotor Aero-Dynamical System (TRAS) through modeling the uncertainty of the neural model with the so-called Model Error Modeling method (MEM). The work describes the modeling process of the plant and scenarios in which the system is under influence of the unknown fault. In such fault scenarios the ESN model together with MEM are used to form the uncertainty bands. If the system output exceeds the uncertain region the fault occurrence is signalized. All data used in experiments are collected from the TRAS through the Matlab/Simulink environment.

Robust multi-model fault detection and isolation with a state-space neural network

This paper presents an design of a Robust Fault Detection and Isolation (FDI) diagnostic system by the means of state-space neural network. First, an solution utilizing multimodel technique is described, in which a Single-Input MultiOutput (SIMO) system is decomposed into a number of Multi-Input Single-Output (MISO) and Single-Input Single-Output (SISO) models. Application of such models makes possible to calculate a set of residual signals required in evaluation process with a Model Error Modelling (MEM) to obtain diagnostic signals. In turn, to isolate faults the diagnostic signals together with defined binary diagnostic table are applied. For experimental verification of the proposed approach, the laboratory stand of Modular Servo is chosen. All necessary data were gathered with the Matlab/Simulink software.

Design of predictive fault tolerant control by the means of State Space Neural Networks

This paper deals with the design of Predictive Fault Tolerant Control (PFTC) system by the means of State Space Neural Networks. In this paper the PFTC idea is very simple. The aim is to link the predictive controller with robust fault detection and isolation algorithm to properly switch fault compensation. Also very important property is to achieve very efficient and no computationally burdening approach. Therefore it was decided to apply an instantaneous linearisation of neural network model at each discreet time sample to use simple linear techniques. In this manner the linear model used in controller and fault compensation is not constant and changes together with operating conditions of the plant, which improves overall control quality.

Design of sensor and actuator multi model fault detection and isolation system using state space neural networks

This paper deals with the application of state space neural network model to design a Fault Detection and Isolation diagnostic system. The work describes approach based on multimodel solution where the SIMO process is decomposed into simple models (SISO and MISO). With such models it is possible to generate different residual signals which later can be evaluated with simple thresholding method into diagnostic signals. Further, such diagnostic signals with the application of Binary Diagnostic Table (BDT) can be used to fault isolation. All data used in experiments is obtain from the simulator of the real-time laboratory stand of Modular Servo under Matlab/Simulink environment.

Fault accommodation of the two rotor aero-dynamical system using the state space neural networks based model predictive control.

This paper deals with the application of state space neural network model to design a model predictive control for a laboratory stand of the Two Rotor Aero-dynamical system. The work describes approach based on the so-called instantaneous linearisation of the already trained nonlinear state space model of the system. With obtained linear model it is possible to derive a vector of future controls based on the minimisation of the cost function within one optimisation window. Repeating procedure in each step of simulation and applying the obtained change of the control signal allows for efficiently control of the nonlinear systems in case of faults. All data used in experiments is obtain from the real-time laboratory stand which is working in Matlab/Simulink RTW environment.