Browsing by Author "Kouadri, Abdelmalek (Supervisor)"

Now showing 1 - 5 of 5

Identification of A distributed parameter system using the least squares technique
(2016) Dahlouk, Abdelkader; Azzoug, El-Mehdi; Kouadri, Abdelmalek (Supervisor)
The identification of such systems represents one of the important directions of theoretical and practical research, due to large class of applications; fluid flow systems, heat diffusion systems, etc. In this context, we consider the linear parametric identification of distributed parameters systems using the Least Square. Two numerical examples of heat transfer systems are presented where linear and nonlinear models are obtained from heat difference equation. The third application is about the identification of a heat conduction in a cement rotary kiln using experimental data. We anticipate that this work be intuitive for practical applications in the areas of controls and signal processing.
On fault detection in a grid-connected photovoltaic system under two different operating modes
(2018) Harkane, Mohamed Amine; Kouadri, Abdelmalek (Supervisor); Bakdi, Azzeddine (Supervisor)
This project proposes an efficient fault detection method based on process history method using Principal Component Analysis (PCA) technique in dimension reduction and feature extraction for Grid Connected PhotoVoltaic System (GCPV) labeled data. The Fault Indicator (FI) developed in this work is an elliptic threshold based on the gaussian distribution of Normal Operation Condition (NOC) of the two different operating modes, Maximum Power Point Tracking (MPPT) and Power Rating (PR), of the system. The proposed fault detection method has been validated experimentally by the evaluation of the False Alarms Rate (FAR), Fault Detection Rate (FDR) and the Detection Delay (DD).The results
Optimal control of distributed parameter systems via orthogonal polynomials
(2016) Akkouche, Said; Meddeb, Khaled; Kouadri, Abdelmalek (Supervisor)
In this thesis, orthogonal polynomials are employed successfully to solve optimal control problem of distributed parameter systems. Three types of orthogonal polynomials are described and used to give approximate solutions, mainly, Legendre polynomials, Chebyshev polynomials and Bernstein polynomials. By the use of the particular properties of these orthogonal polynomials, the optimal control problem is simplified into the optimal control of a linear time invariant lumped-parameter system. Next, a directly computational formulation for evaluating the optimal control and trajectory of a linear distributed- parameter system is developed, unlike the variational iteration method, which allows iteratively to approximate the solution where the problems are initially approximated with possible unknowns. By means of orthogonal polynomials the solutions of optimal control problems are obtained, comparison with the variational method is made. Examples are applied to verify the convergence results and to illustrate the efficiency and the reliability of each method.
PCA-Based approach for fault detection in cement rotary kiln
(2016) Aribi, Yacine; Guermi, Hamza; Kouadri, Abdelmalek (Supervisor)
Principal component analysis (PCA) is a well-known data dimensionality technique that is widely used in industrial processes detection fault. Dynamic PCA is acknowledged for its capability to cope with autocorrelation in time-series. False indications impose one of the greatest problems in the monitoring of many processes. A study is carried in the first part of this work in order to compare the performances of Static and Dynamic PCA approaches in cement rotary kiln. The issue of false indications in fault detection systems is investigated in the second part. A monitoring approach based on constant false alarms rate (CFAR) is proposed to reduce false detections. A piecewise constant threshold is developed for ..2 and .. statistics to limit the rate of false alarms to a given percentile at each time instant. A control chart constructed using the rate of false alarms per window is used to monitor the process. Finally, the proposed monitoring technique is tested on SPCA to confirm the ability of the proposed approach to result in zero false detections without imposing high delays or misdetections.
Reduced kernel PCA based approach for fault detection in complex systems
(2019) Bennai, Sabrina; Kouadri, Abdelmalek (Supervisor)
Multivariate statistical methods have been widely applied to complex systems for fault detection. While methods based on principal component analysis (PCA) are popular, more recently kernel PCA (KPCA) has been utilized to better model nonlinear process data. This report proposes a new method for fault detection using a reduced kernel principal component analysis (RKPCA) to cope with the computational problem introduced by KPCA. The proposed RKPCA method consists on reducing the number of observations in a data matrix using the dissimilarities between the pairs of its observations. PCA, KPCA and the suggested approach RKPCA are carried out using the cement rotary kiln system. The Hotelling’s T², Q in addition to the new proposed index called the combined statistic φ are used as fault indicators. The two methods PCA and KPCA are compared to the proposed approach in terms of False Alarms Rate (FAR), Missed Alarms Rate (MDR), Detection Time Delay (DTD), the cost function (J) and the Execution Time (ET). The obtained results demonstrate the effectiveness of the proposed technique in reducing the computational time from 1h37min when KPCA is used to 9min30s.Moreover, it has effectively detected the different types of faults when using the φ index.