in this paper, the fuzzy system has been used for fault detection and diagnosis of a yeast fermentation bioreactor based on measurements corrupted by noise. in one case, parameters of membership functions are selected in a conventional manner. in another case, using certainty factors between normal and faulty conditions the optimal values of these parameters have been obtained through the genet...

we present an approach to design of fault tolerant computing systems. in this paper, a technique is employed that enable the combination of several codes, in order to obtain flexibility in the design of error correcting codes. code combining techniques are very effective, which one of these codes are turbo codes. the algorithm-based fault tolerance techniques that to detect errors rely on the c...

The condition of mechatronic production equipment slowly deteriorates over time, increasing the risk failure and associated unscheduled downtime. A key indicator for an increased failures is shifting resonances. aim this paper to track resonances online during normal operation. This contributes real-time parametric fault diagnosis by applying comparing parameter estimators in new context, highl...

This paper describes the ongoing research on Rough Sets based classifier applied to Induction Motors fault diagnosis through Motor Current Signature Analysis (MCSA). The results of mechanical failures detection and how a Rough Sets based classifier is used as a monitoring system using current signature analysis in predictive maintenance are also described in this paper. Key-Words: Predictive Ma...

Acoustic Emissions (AE), generated by the formation and growth of micro-cracks in metal components, provide us with a promising mechanical fault detection technique in monitoring complex-shaped components in helicopters and aircraft. A major challenge for an AE-based fault detection algorithm is to distinguish crack related AE signals from other interfering transient signals, such as fretting r...

By combining the disciplines of control design, condition monitoring and fault detection identification and accommodation, it should be possible to provide actuators that possess: consistent and tuneable closed-loop performance, a tolerance to sensor faults and the ability to detect actuator deterioration early. This will lead to improved reliability and availability of the actuator. This paper...

This paper presents a new Fast Kurtogram Method in the time-frequency domain using novel types of statistical features instead of the kurtosis. For this study, the problem of four classes for Bearing Fault Detection is investigated using various statistical features. This research is conducted in four stages. At first, the stability of each feature for each fault mode is investigated. Then, res...

In this paper, a fault detection and isolation model based method for backlash phenomenon is presented. The aim of this contribution is to be able to detect then distinguish the undesirable backlash from the useful one inside an electromechanical test bench. The dynamic model of the real system is derived, using the bond graph approach, motivated by the multi-energy domain of such mechatronic s...

The gearbox is a complicated rotating machinery equipment, in order to realize the gearbox fault early detection and prevention, it is the key to carry out the online diagnosis. This paper used the adaptive variable step-length natural gradient blind source separation algorithm to realize the helicopter gearbox meshing vibration signal and fault vibration signal effective separation. Through th...

Symmetrical nature of mean of electrical signals during normal operating conditions is used in the fault detection task for dependable, robust, and simple fault detector implementation is presented in this work. Every fourth cycle of the instantaneous current signal, the mean is computed and carried into the next cycle to discover nonlinearities in the signal. A fault detection task is complete...