Most recent issue published online for the International Journal of Adaptive and Innovative Systems.

ESA_Petri net: dynamic reliability analysis tool

R. Guillerm — 2010-08-23T23:20:50-05:00

ESA_Petri net: dynamic reliability analysis tool
R. Guillerm, H. Demmou, N. Sadou
International Journal of Adaptive and Innovative Systems, Vol. 1, No. 3/4 (2010) pp. 201 - 215
This paper presents a new version of critical (feared) scenarios derivation tool ESA PetriNet (extraction scenarios algorithm from Petri net) available from: http://www.laas.fr/ESA. ESA PetriNet allows to derive scenarios leading to critical (feared) situation. In the past version of the tool hybrid aspect (both discrete and continuous dynamic) of system is tacked into account by temporal abstraction. In the version presented in this paper, the system model is given by a hybrid Petri net (differential predicate-transition Petri net) and the hybrid model is directly considered (without temporal abstraction). The algorithm implemented deals with both continuous and discrete dynamics. Furthermore, generated scenarios are minimal (only necessary events). Only necessary information is provided to designer.

Use of HMM for evaluation of maintenance activities

Pascal Vrignat — 2010-08-23T23:20:50-05:00

Use of HMM for evaluation of maintenance activities
Pascal Vrignat, Manuel Avila, Florent Duculty, Frederic Kratz
International Journal of Adaptive and Innovative Systems, Vol. 1, No. 3/4 (2010) pp. 216 - 232
This paper deals with a tool which may help maintenance managers to schedule maintenance activities. To help them, we show that by using events which can be observed on a process, like maintenance events, we can predict failures before they occur. Principles are based on hypothesis that failure is preceded by a typical sequence of events. We also show that hidden Markov models can be used according to the right choice of parameters.

Performance assessment of systems including conflict in the context of dynamic reliability

Gabriel Antonio Perez Castaneda — 2010-08-23T23:20:50-05:00

Performance assessment of systems including conflict in the context of dynamic reliability
Gabriel Antonio Perez Castaneda, Jean-Francois Aubry, Nicolae Brinzei
International Journal of Adaptive and Innovative Systems, Vol. 1, No. 3/4 (2010) pp. 233 - 247
This article presents the assessment performed through a Monte Carlo simulation of the dependability parameters in a context of dynamic reliability. For that, the system is modelled by a stochastic hybrid automaton which has been defined formally. This stochastic hybrid automaton allows taking into account an important problem of the dynamic reliability: the different behaviours under the occurrence of events. The conflict that appears at any given time during the simulation representing the choice of one of these possible behaviours is determined by a probabilistic choice; a probability distribution is associated to each conflict. This approach is illustrated on a case-study represented by the temperature control system of an oven.

Non-linear multiscale principal component analysis for fault detection: application to pollution parameters

O. Bara — 2010-08-23T23:20:50-05:00

Non-linear multiscale principal component analysis for fault detection: application to pollution parameters
O. Bara, M.T. Khadir, M. Djeghaba
International Journal of Adaptive and Innovative Systems, Vol. 1, No. 3/4 (2010) pp. 248 - 266
In the general frame of process surveillance, principal component analysis (PCA) has been often selected due to its simplicity and ability to capture the linear relations between the stationary process variables. However, the method showed limitations when dealing with industrial data that generally presents non-linear and multiscale features. The approach proposed in this study rests on the modelling using non-linear PCA coupled with artificial neural networks (ANNs) to extract the non-linear inter-correlation between variables and on the wavelet analysis to decompose each sensor signal into a set of coefficients at different scales. The contribution of each variable for each scale is then collected in separated matrices and a non-linear PCA model is constructed for each matrix. The proposed approach is applied to fault detection of pollution parameters affecting the region of Annaba in Algeria. The performance of the approach is then illustrated and compared with those of classic PCA and multiscale PCA (MSPCA).

Multiple sensor fault detection and isolation of an air quality monitoring network using RBF-NLPCA model

Mohamed-Faouzi Harkat — 2010-08-23T23:20:50-05:00

Multiple sensor fault detection and isolation of an air quality monitoring network using RBF-NLPCA model
Mohamed-Faouzi Harkat, Yvon Tharrault, Gilles Mourot, Jose Ragot
International Journal of Adaptive and Innovative Systems, Vol. 1, No. 3/4 (2010) pp. 267 - 284
This paper presents a data-driven method based on non-linear principal component analysis to detect and isolate multiple sensor faults. The RBF-NLPCA model is obtained by combining a principal curve algorithm and two three-layer radial basis function (RBF) networks. The reconstruction approach for multiple sensors is proposed in the non-linear case and successfully applied for multiple sensor fault detection and isolation of an air quality monitoring network. The proposed approach reduces considerably the number of reconstruction combinations and allows to determine replacement values for the faulty sensors.

Embedded diagnosis based on vibration data

Ouadie Bennouna — 2010-08-23T23:20:50-05:00

Embedded diagnosis based on vibration data
Ouadie Bennouna, Houcine Chafouk, Olivier Robin, Jean-Philippe Roux
International Journal of Adaptive and Innovative Systems, Vol. 1, No. 3/4 (2010) pp. 285 - 296
This article deals with a method based on vibration data measured on electronic systems to detect, identify and localise defects generated in these systems, in order to improve their reliability. The diagnosis procedure is based on the combination of wavelet transforms and neural networks; this procedure is applied to a simplified printed circuit board.

Performance evaluation and risk management for industrial systems by using fuzzy controller

Abdennaceur Zizouni — 2010-08-23T23:20:50-05:00

Performance evaluation and risk management for industrial systems by using fuzzy controller
Abdennaceur Zizouni, Abdeldjebar Hazzab, Ismail Khalil Bousserhane, Pierre Sicard
International Journal of Adaptive and Innovative Systems, Vol. 1, No. 3/4 (2010) pp. 297 - 317
In this work, we present a synthesis methodology of a multivariable fuzzy controller for the control of a multi-motor system (MMS) that can be intended for winding and unwinding controlled transport processes. The simulation results show that the integration of the fuzzy multivariable controller brought good performances compared to the multivariable PI-structure controller, and a clear improvement at the level of control and synchronism performances between velocities of the MMS motors compared to the fuzzy mono-variable controller. This shows that the integration of the proposed controller can increase the line production.

Free and forced modes responses of fractional operators based on non-identical RLC cells

Roy Abi Zeid Daou — 2010-08-23T23:20:50-05:00

Free and forced modes responses of fractional operators based on non-identical RLC cells
Roy Abi Zeid Daou, Clovis Francis, Xavier Moreau
International Journal of Adaptive and Innovative Systems, Vol. 1, No. 3/4 (2010) pp. 318 - 333
In this article, we study the behaviour of the RLC cells for the four configurations that we presented earlier in Abi Zeid Daou et al. (2009a). An electric circuit is used in order to study the fractional behaviour and the robustness of these RLC operators and compare their responses to the behaviour of the fractance which is an ideal fractional operator (Moreau et al., 2003). This analysis is conducted for both natural and forced responses. In more details, the initial conditions of the capacitors and inductances are neglected in the first case and they are taken into consideration in the second one. The number of initial conditions is related to the number of RLC cells used. The robustness of all arrangements is analysed by varying the unsteady parameter value which is represented by an inductance in the electrical circuit. This inductance represents a different variable parameter in each field of application. For example, in the hydropneumatic domain, this inductance refers to the mass of the vehicle as the mass has the main influence on the dynamics and the robustness when designing the active suspension (Moreau et al., 2001). A conclusion will sum up the results for all four arrangements and a confirmation that the phase constancy and the robustness are present in both modes.

A neuro-fuzzy-based fault detection and fault tolerance methods for industrial robotic manipulators

M. Dev Anand — 2010-08-23T23:20:50-05:00

A neuro-fuzzy-based fault detection and fault tolerance methods for industrial robotic manipulators
M. Dev Anand, T. Selvaraj, S. Kumanan, T. Ajitha
International Journal of Adaptive and Innovative Systems, Vol. 1, No. 3/4 (2010) pp. 334 - 371
Fault tolerance is increasingly important in industrial robots. The ability to detect and tolerate failures allows robots to effectively cope with internal failures and continue performing designated tasks without the need for immediate human intervention. To tolerate hardware failures, a set of fault tolerance algorithms are written for each component. These processes are responsible for detecting faults in their respective component and minimising the impact of the failure on the robot's performance. This work presents new intelligent neuro-fuzzy fault detection algorithms, which detect failures in robot components using analytical redundancy relations. An intelligent fault tolerance framework is proposed in which a fault component database or rule base and the detection algorithms work together to detect and tolerate sensor or motor failures in a robot system. Motor faults as well as sensor faults are considered. The Scorbot ER 5u plus model was simulated in robotics toolbox for MATLAB using the neuro-fuzzy algorithms.