• Nuclear Engineering and Technology
• /
• v.50 no.8
• /
• pp.1306-1313
• /
• 2018

The randomness and incipient nature of certain faults in reactor systems warrant a robust and dynamic detection mechanism. Existing models and methods for fault diagnosis using different mathematical/statistical inferences lack incipient and novel faults detection capability. To this end, we propose a fault diagnosis method that utilizes the flexibility of data-driven Support Vector Machine (SVM) for component-level fault diagnosis. The technique integrates separately-built, separately-trained, specialized SVM modules capable of component-level fault diagnosis into a coherent intelligent system, with each SVM module monitoring sub-units of the reactor coolant system. To evaluate the model, marginal faults selected from the failure mode and effect analysis (FMEA) are simulated in the steam generator and pressure boundary of the Chinese CNP300 PWR (Qinshan I NPP) reactor coolant system, using a best-estimate thermal-hydraulic code, RELAP5/SCDAP Mod4.0. Multiclass SVM model is trained with component level parameters that represent the steady state and selected faults in the components. For optimization purposes, we considered and compared the performances of different multiclass models in MATLAB, using different coding matrices, as well as different kernel functions on the representative data derived from the simulation of Qinshan I NPP. An optimum predictive model - the Error Correcting Output Code (ECOC) with TenaryComplete coding matrix - was obtained from experiments, and utilized to diagnose the incipient faults. Some of the important diagnostic results and heuristic model evaluation methods are presented in this paper.

• Geophysics and Geophysical Exploration
• /
• v.13 no.1
• /
• pp.31-39
• /
• 2010

The goal of automatic velocity analysis is to extract accurate velocity from voluminous seismic data with efficiency. In this study, we developed an efficient automatic velocity analysis algorithm by using bootstrapped differential semblance (BDS) and Monte Carlo inversion. To estimate more accurate results from automatic velocity analysis, the algorithm we have developed uses BDS, which provides a higher velocity resolution than conventional semblance, as a coherency estimator. In addition, our proposed automatic velocity analysis module is performed with a conditional initial velocity determination step that leads to enhanced efficiency in running time of the module. A new optional root mean square (RMS) velocity constraint, which prevents picking false peaks, is used. The developed automatic velocity analysis module was tested on a synthetic dataset and a marine field dataset from the East Sea, Korea. The stacked sections made using velocity results from our algorithm showed coherent events and improved the quality of the normal moveout-correction result. Moreover, since our algorithm finds interval velocity ($\nu_{int}$) first with interval velocity constraints and then calculates a RMS velocity function from the interval velocity, we can estimate geologically reasonable interval velocities. Boundaries of interval velocities also match well with reflection events in the common midpoint stacked sections.