In Persian, the grammatical particle ezafe connects two words. Ezafe is one of the salient factors in Persian phonology and morphology to understand the meaning of a sentence completely and truly, whereas it is not usually written in sentences, resulting in mistakes in reading complex sentences and errors in natural language processing tasks. Therefore, recognizing words that need Ezafe at the end of themselves, is a major factor to improve the performance of a variety of NLP-based systems such as a Text TTSsystem. Because in Persian TTS systems without an Ezafe recognition module cannot make Ezafe constructions to read the text correctly and does not recognize the relations between the words. As Transformer-based methods shows state-of-the-art results in lots of NLP tasks, in this paper, we experiment ParsBERT in the task of ezafe recognition. The latter earning 2. 68% better F1-score than the prior state-of-the-art, we obtain the most advantageous outcomes.

THE POWER Transformer IS ONE OF THE MAIN COMPONENTS IN A POWER TRANSMISSION NETWORK. MAJOR FAULTS IN THESE TransformerS CAN CAUSE EXTENSIVE DAMAGE, WHICH DO NOT ONLY INTERRUPT ELECTRICITY SUPPLY BUT ALSO RESULT IN LARGE REVENUE LOSSES. DUE TO THE LARGE NUMBER OF TransformerS OF DIFFERENT MAKES AND CAPACITIES, ROUTINE MAINTENANCE AND DIAGNOSIS OF SUCH TransformerS, EVEN USING FOREIGN CONSULTANTS, ARE RATHER DIFFICULT AS DIFFERENT TransformerS EXHIBIT DIFFERENT CHARACTERISTICS AND PROBLEMS.MOREOVER, DIFFERENT CLIMATIC AND OPERATING CONDITIONS MAY NOT BE ABLE TO DRAW THE CORRECT CONCLUSION TO SOME PROBLEMS. TO HELP IN OVERCOMING SUCH PROBLEMS, A SOFTWARE IS CURRENTLY BEING DEVELOPED CALLED “TOGA 5.5” FOR THE INTERPRETATION OF THE DISSOLVED GAS ANALYSIS (DGA) PERFORMED ON THE TransformerS USING THE TECHNIQUE OF FUZZY LOGIC. THE FIRST PHASE OF THE PROJECT WHICH ALSO CONSISTS OF A FUZZY LOGIC INTERPRETATION MODULE CAN BE USED FOR INTERPRETING MOST OF THE DGA TEST RESULTS HAS ALREADY BEEN COMPLETED AND IS DISCUSSED IN THIS PAPER. THE NEXT PHASE OF THE PROJECT WOULD INVOLVE UTILIZING OTHER ARTIFICIAL INTELLIGENT TECHNIQUES SUCH AS NEURAL NETWORKS AND OTHER ALGORITHMS TO AUTOMATICALLY GENERATE RULES FROM TRENDS FOUND IN THE DATABASE.

SINCE LARGE POWER Transformer BELONG TO THE MOST EXPENSIVE AND STRATEGICALLY IMPORTANT COMPONENTS OF ANY POWER GENERATION AND TRANSMISSION SYSTEM, THEIR RELIABITY IS OF CRUCIAL IMPORTANT FOR THE ENERGY SYSTEM OPERATION. MOST SERIOUS FAILURE OF A LARGE POWER Transformer IS DUE TO THE INSULATION BREAKDOWN. PARTIAL DISCHARGE (PD) THAT DAMAGE INSULATION BY GRADUAL EROSION IS A MAJOR SOURCE OF INSULATION FAILURE. TECHNIQUES FOR LOCATING A PD SOURCE ARE OF MAJOR IMPORTANCE IN BOTH THE MAINTENANCE AND REPAIR OF A Transformer. THE LOCATING METHOD OF PD CAN BE MAINLY CATEGORIZED INTO TECHNIQUES BASED ON ACOUSTIC SIGNALS OR ELECTRICAL SIGNALS. THE ADVANTAGE OF ACOUSTIC LOCATING METHOD IS ITS SIMPLE ALGORITHM AND NOISE-PROOF FEATURE, BUT ITS SENSITIVITY IS BAD AND THE CONSTRUCTION OF Transformer IS TOO COMPLEX TO FIND THE SPEED OF ULTRASONIC WAVE CAUSED BY PD. THE ELECTRICAL METHOD HAS A BETTER SENSITIVITY BECAUSE IT DEPENDS ON PULSE CURRENT SIGNALS MEASURED AT Transformer TERMINAL.AT THE MOST COMMON STATUS IN THE FIELD, THE DISCHARGE BETWEEN THE WINDING OF THE Transformer AND THE GROUND WAS ANALYZED. ANALYSIS OF PD IN THE COIL TO COIL CAPACITANCE IS DIFFICULT SO THIS OBJECT WAS NOT CONSIDERED COMPLETELY. IN THIS PAPER PARTIAL DISCHARGE IN THE INSULATION BETWEEN COIL TO COIL IS CONSIDERED WITH EMTP SIMULATION TOOLS. THEN THE CURRENT OF NEUTRAL POINT OF WINDING IS MEASURED WHEN PD MODEL IS LOCATED AT DIFFERENT POSITIONS IN THE WINDING. THIS CURRENT WILL BE ANALYZED WITH THE DB2 WAVELET. WITH COMPARE DETAIL LEVEL (1) PD CAN BE LOCALIZED.