Professional Documents
Culture Documents
Altai e 2015
Altai e 2015
Altai e 2015
Abstract— The goal of this research is to focus and adopt a Also, these methods were applied on three phase single and
fast, accurate and reliable fault detection technique and double circuit TL [6]. Thus, the proposed researches are
classification method for the high voltage transmission line. The focusing on the voltage and current signals together [1, 2, 4, 6]
proposed method reduces the outage time and hence this or the current signals only [7]. All these researches have
eliminates any possible damage to the other parts of the
advantages and disadvantages. In the other hand, one
system. First, detection of the fault is carried out using a new
proposed technique that combines three type of relays. disadvantages may cause a big problem. Furthermore, one of
Second, the technique isolates the faulty part in a very fast time the major problem on the protection system is the time from
frame. Finally, classifying the fault is carried out by data the detecting till the clearing fault on TL. While many
recorded using Digital Signal Processing (DSP) and Artificial proposals did not mention it on their research. Also, many of
Neural Network (ANN) based on different ways. The input these researches did not applied on system with a
training data of the recording devices was sampled using Digital compensating. For the ANN it is very popular algorithm for the
Signal Processing (DSP). In this research the data collected from fault classification on the high voltage TL, and the reason due
the recorders will be used to classify the fault only because the to the capability of this algorithm to learn and recognize the
time is not an important factor as in fault detecting and clearing.
pattern and the behavior of the system under any circumstances
Also, all types of faults are investigated for the fault
classification. Three methods are used (Phase Current sampling, with high efficiency [2, 8]. Therefore, it has earned much
Phase Shift of the Phase Voltage sampling and Phase Voltage interest by the researcher [10, 13]. While, using of the classical
sampling) to evaluate the efficiency, accuracy and the analysis methods with new technique will give new analytic for the
the mean square error. situations, but no longer included all of the transient time
analysis in a very short time [5]. Also, the conventional
Index Terms— ANN, Differential Over Current Protection, approach detects and classifies the fault depending on the
Distance Protection, Fault Detection, Fault Classification. fundamental component of each signal might not achieve the
I. INTRODUCTION desire analysis. Hence, many researches did not addressed the
series faults or not proposed a general ANN system, but
Electrical Power System (EPS) is divided into several parts divided the system into few parts each one for similar fault
and each part classified as a system. Transmission line type different phase.
considered one of the main parts of the EPS network. Therefore, in this research the combinational technique has
However, Overhead Transmission line is more prone to the been adopted and tested to detect the fault on TL with a very
fault than the other parts, because it is long and out of the short time and no one use it earlier. On the other hand, using of
room. Hence, the faults can be divided into two types normal the feed forward Neural Network was built to classify the fault
and abnormal faults, the normal one come from the external on TL. This system was strongly classify all types of fault
influences while, the abnormal faults come from the internal whether it is series like (one line open and two line open) or
influences due to the flow design. Therefore, this research will even shunt fault like (Single Line to ground SLG, Double line
introduce two major tasks as fault detection and classification. DL, double line to ground DLG, Three phase 3PH and Three
Designing of the fast, accurate and reliable algorithm to Phase to Ground 3PH-G). Furthermore, this system will
detect and classify the fault is the first goal of all researches, identify which line was particularly. This method is based on
articles and proposals for the faults in the high voltage the theory that the input value of any variable should be
transmission line (TL) [1-13]. In the last decade many equaled or closed to the output value of the same variable like
researches were presented for the fault detection and the output current has to be same value of the input current,
classification and many of them adopted the classical which delivered to the load under the normal operation. It has
protection method with new technique [1, 2, 4]. Therefore, to be in the same zone to be protected, but when the fault or
there are few general methods to detect the fault. Hence the any abnormal behavior happen in specific zone some of this
new technique mostly used the Artificial Neural Network current will pass through the fault point. So, the current out of
(ANN) [2-4, 6-7, 10-13], Wavelet [8, 12], Support Vector the zone will be less than the current into the zone. Thus, the
Machine [5], Adaptive Nero Fuzzy Inference system [1], etc.
five types of sampling, two types of validation and testing, As a result, the best design of this method founded by (50)
three types of variables and one algorithm were applied to get samples, (15% of validation and testing), the voltage variable
satisfying system that can be applied in different systems. and ANN algorithm were giving the best result, as shown in
the charts above from (13-15).
Furthermore, the last three charts from (16-18) show the
comparison between the same variable with different layers,
validation and testing. Thus, it is clearly that the Phase Voltage
variable gives better results than the Phase Current or even the
Phase Shift of the Phase Voltages variables.
Fig. 16. One layer 10% of (Validation and Training) on the top Ten
Layers 15% of (Validation and Training) in the bottom phase Voltage test
Fig. 11. Five Layers 10% of (Validation and Training)
Fig. 17. One layer 10% of (Validation and Training) on the top Ten
Layers 15% of (Validation and Training) in the bottom phase Current test
Fig. 12. Ten Layers 10% of (Validation and Training)
From the previous charts, despite the fact that the results
were good, but it still needs to improve. Therefore, the next
step is trying to get the best result through changing the
classifier performance and features as follow.
Fig. 18. One layer 10% of (Validation and Training) on the top Ten Layers
15% of (Validation and Training) in the bottom Angle of Phase Voltage test
CONCLUSION
Fig. 13. One Layer 15% of (Validation and Training) This proposed research has investigated the use of
combination method for fault detection and clearing. It uses
RMS values of phase current as input. The combination
method achieved a desired performance that met the
expectations of the requirement of a protective system. While,
it applied on both types of fault, and it was highly satisfactory,
due to the fast fault detecting and clearing time with fault
analysis. Also, it was demonstrated that the Feed-Forward
ANN performs well in fault classification on TL. It uses RMS
Fig. 14. Five Layers 15% of (Validation and Training)
values of phase voltage, phase current and phase voltage angle
as an inputs and compared among them. All faults were
discussed; series faults and shunt faults (with respect to all
types of them). Based on the flexibility of the Neural Networks
algorithm that accept any real values as an input, resistant to
errors in the training data and fast evaluation. The results
obtained proved that the performance of the (FF) Neural
Network architecture is robust.
Fig. 15. Ten Layers 15% of (Validation and Training)
356
Fig. 19. Complete Three Phase Series Compensated Network with Proposed Protection Scheme