Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

As transformers age, their internal condition degrades, which increases the risk of failure. To prevent these failures and to maintain transformers in good operating condition is a very important issue for utilities. Traditionally, routine preventative maintenance programs combined with regular testing were used. The change to condition-based maintenance has resulted in the reduction, or even elimination, of routine time-based maintenance. Instead of doing maintenance at a regular interval, maintenance is only carried out if the condition of the equipment requires it. Hence, there is an increasing need for better nonintrusive diagnostic and monitoring tools to assess the internal condition of the transformers. If there is a problem, the transformer can then be repaired or replaced before it fails. An extensive review is given of diagnostic and monitoring tests, and equipment available that assess the condition of power transformers and provide an early warning of potential failure.

Review of condition assessment of power transformers in service

Pattern recognition

Dissolved gas analysis (DGA) is used to assess the condition of power transformers. It uses the concentrations of various gases dissolved in the transformer oil due to decomposition of the oil and paper insulation. DGA has gained worldwide acceptance as a method for the detection of incipient faults in transformers.

A review of dissolved gas analysis measurement and interpretation techniques

A concise review is given of the progress made in the field of partial discharges (PD) at DC voltage. Although ample reference will be made to work of other authors in this field, the paper will concentrate on the progress that was made at Delft University of Technology over a period of 14 years in three PhD projects. In the first project, a start was made with the analysis of the physics of partial discharges at DC voltage and different types of PD were characterized based on parameters like time interval between PD and PD magnitude. In a second project, PD analysis was applied to HVDC apparatus and different means of classification of PD at DC voltage were proposed. In the third project, PD analysis was applied to HVDC mass-impregnated cables and test specifications were proposed. In this paper the work performed in the above three Ph.D. projects is summarized with ample reference to papers of other workers in this field. Attention is given to the mechanism of PD at DC voltage as compared to AC voltage and techniques for measurement and analysis of DC PD patterns. Examples of practical application of DC PD testing are given. Finally, some thoughts on future work are presented.

/pdf/partial-discharges-at-dc-voltage-their-mechanism-detection-2ka0gekh8r.pdf

Partial discharges at DC voltage: their mechanism, detection and analysis

Dielectric diagnosis with polarization and depolarization currents (PDC) which employs the dielectric response of system in time domain is applied to investigate differences between PDC patterns produced by two types of transformer insulating fluids, mineral and bio-degradable oil The mineral oil used is Shell Diala BX, and the biodegradable one is Envirotemp FR3 The latter is ester-based, and a relatively new transformer insulating fluid introduced as an environmentally-friendly alternative to conventional mineral oil The DC conductivity of the two oil types is obtained under the effects of various temperature and moisture levels The experiment is conducted for two levels of moisture when temperature factor is changed from ambient to 90 °C The oil water content measurement is conducted using Karl-FischerTitration Also, an attempt was made to investigate the effects that different testing voltages and time durations have on the polarization and depolarization spectrum A range of DC voltages up to 1000V, and time durations from 1000 to 10000 seconds have been applied Finally, all the PDC patterns obtained under the effect of mentioned factors are evaluated

Dielectric response of transformer insulation oils

The PDC method is a simple and reliable analysis tool to monitor transformer insulation systems. Based on PDC measurements of the biodegradable oil in a healthy oil condition at different moisture levels and after faults (Partial discharge, Overheating and Arcing) fault identification can be achieved by comparing the PDC pattern of an oil sample against the PDC fingerprints. Furthermore, the relationship curves between the oil moisture level toward its conductivity level and measured capacitance value have been established. These curves can be used to predict the oil moisture condition and the fault type.

http://ieeexplore.ieee.org/iel5/5706732/5710678/05710815.pdf

PDC patterns of biodegradable transformers insulation oil after experienced faults and at different moisture levels

This paper addresses results of PD tests at elevated temperature. Particular interests were given to new and aged oil-impregnated pressboards. The aim of this investigation was to study the impact of the particular conditions, such as those encountered in practical situations, on the ageing rate of the insulation material. The investigation was also aimed at an exploration of whether it is possible to quantify the ageing stage of the material by means of parameter analysis of the measured PD distributions. PD data obtained from the experimental work is presented in phase-resolved analysis (PRA) and voltage difference analysis (VDA).

Investigation of Partial Discharge Properties in Oil-Impregnated Insulation

Lifetime of power cable is influenced by the several factors. One of the most important factors is the occurrence of partial discharge (PD) at the dielectric. The ability to detect and locate a PD source is limited by attenuation of the high frequency PD pulses as they propagating through the cable. Attenuation is the result a range of phenomena, including: dielectric loss of the insulation and the propagation of radial current through the semi-conducting layers. This paper presents results of measurement and simulation on the semi-conducting layers of XLPE cable. The results show that the importance of computing the high frequency loss in the semi-conducting layers. In addition to the study on dielectric shows that thicker insulation will lead to lower loss and lower capacitance per unit length. The influence of tan delta of dielectric is discussed.

The effect of insulation loss and semi-conducting layers on pulse propagation behavior of power cables

Power transformer monitoring as a reliable tool for maintaining purposes of this valuable asset of power systems has always comprised partial discharge offline measurements and online monitoring. The reason lies in non-destructive feature of PD monitoring. Partial discharge monitoring helps to detect incipient insulation faults and prevent insulation failure of power transformers. This paper introduces a software package developed based on structural data of power transformer and discusses the results of the simulation on Abetti winding, which might be considered as a basic layer winding. A hybrid model is used to model the transformer winding, which has been developed by first author. Firstly, winding is modeled by ladder network method to determine model parameters and then multi-conductor transmission line model is utilized to work out voltage and current vectors and study partial discharge propagation as well as its localization. Utilized method of modeling makes it possible to simulate a transformer winding over a frequency range from a few hundred kHz to a few tens of MHz. The results take advantage of accurate modeling method and provide a reasonable interpretation as to PD propagation and location studies

Trevor Blackburn

Papers

Dielectric response of transformer insulation oils

PDC patterns of biodegradable transformers insulation oil after experienced faults and at different moisture levels

Investigation of Partial Discharge Properties in Oil-Impregnated Insulation

The effect of insulation loss and semi-conducting layers on pulse propagation behavior of power cables

Simulation of partial discharge propagation and location in Abetti winding based on structural data