It can be observed that k--means algorithm classifies, for all cases, of healthy condition during startup transient and steady state, almost all the cases (37 of 38) for
faulty condition during both regimes at 50 Hz, which represent a good classification effectiveness.
Sources stated that most of the accidents were happened owing to the
faulty condition of railway tracks.
Islamabad -- The Federal Capital inhabitants are facing acute water shortage for past many weeks owing to the
faulty condition of water filtration plants.
The resulting signal in
faulty condition is shown in Fig.
This metric is generally used to determine how good a method is in discriminating between a normal and a
faulty condition. Given a "discriminator" or a "scalar operator" that is acting on a set of data, the Bhattacharyya Distance is a measure of the statistical separability of two sets, "Normal" (N) and "Fault" (F).
In the first
faulty condition (three turns), [V.sub.CN] is connected to [C.sub.1] terminal.
Department in a
faulty condition. Neither it has equipment nor
In the presented graphs, red and dashed navy blue lines are representative of experimental data and simulation results, respectively, under the
faulty condition. In the same way, purple and green lines are representative of experimental data and simulation results under fault-free condition.
Voltage of phase A and phase B falls to zero, while voltage swell which exists in phase C can be seen during the
faulty condition. In the same way, the current of phase A and phase B shoots up to its maximum value, while the current of phase C remains zero, Figure 13.
Fault detection can be considered as a special classification problem involved in model-based method [22] and data-based method, with the purpose to timely recognise
faulty condition. With the help of cross-validation algorithm to optimise parameters, the performance of classification is greatly enhanced [23-25].
Firstly, the method adopted with pattern recognition collects history data under normal condition and
faulty condition. Then, the supervised decision making algorithm is trained with the feature samples that have been extracted from history data and belong to explicit set of each pattern [4].