Search results

Condition‐based maintenance (CBM) has increasingly drawn attention in industry because of its many benefits. The CBM problem is a kind of state‐dependent scheduling problem, and is very hard to solve within the conventional Markov decision process framework. The purpose of this paper is to present an intelligent CBM scheduling model for which incremental decision tree learning as an evolutionary system identification model and dynamic programming as a control model are developed.

To fully exploit the merits of CBM, this paper models CBM scheduling as a state‐dependent, sequential decision‐making problem. The objective function is formulated as the minimization of the total maintenance cost. Instead of interpreting the problem within the widely used Markovian framework, this paper proposes an intelligent maintenance scheduling approach that integrates an incremental decision tree learning method and deterministic dynamic programming techniques.

Although the intelligent maintenance scheduling approach proposed in this paper does not guarantee an optimal scheduling policy from a mathematical viewpoint, it is verified through a simulation‐based experiment that the intelligent maintenance scheduler is capable of providing a good scheduling policy that can be used in practice.

This paper presents an intelligent maintenance scheduler. As a system identification model, we devise a new incremental decision tree learning method by which interaction patterns among attributes and machine condition are disclosed in an evolutionary manner. A deterministic dynamic programming technique is then applied to select the best safe state in terms of the total maintenance cost.

Many incidents of rotor failures are reported due to the development and propagation of the crack. Condition monitoring is adopted for the identification of symptoms of the crack at very early stage in the rotating machinery. Identification requires a reliable and accurate vibration analysis technique for achieving the objective of the study. The purpose of this paper is to detect the crack in the rotating machinery by measuring vibration parameters at different measurement locations.

Two different types of cracks were simulated in these experiments. Experiments were conducted using healthy shaft, crack simulated shaft and glued shaft with and without added unbalance to observe the changes in vibration pattern, magnitude and phase. Deviation in vibration response allows the identification of crack and its location. Initial data were acquired in the form of time waveform. Run-up and coast-down measurements were taken to find the critical speed. The wavelet packet energy analysis technique was used to get better localization in time and frequency zone.

The presence of crack changes the dynamic behavior of the rotor. 1× and 2× harmonic components for steady-state test and critical speed for transient test are important parameters in condition monitoring to detect the crack. To separate the 1× and 2× harmonic component in the different wavelet packets, original signal is decomposed in nine levels. Wavelet packet energy analysis is carried out to find the intensity of the signal due to simulated crack.

Original signals obtained from the experiment test set up may contain noise component and dominant frequency components other than the crack. Wavelet packets contain the crack-related information that are identified and separated in this study. This technique develops the condition monitoring procedure more specific about the type of the fault and accurate due to the separation of specific fault features in different wavelet packets. From the experiment end results, it is found that there is significant rise in a 2× energy component due to crack in the shaft. The intensity of a 1× energy component depends upon the shaft crack and unbalance orientation angle.