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

In recent years there have been issues of unusual dissolved gas analysis (DGA) results from routine testing of wind-turbine transformers. These are differences when compared to results from tests of standard oil-filled distribution transformers. This paper reports on a comparison of DGA test results for such transformers in Australian wind farms.The results were analysed for their predictive potential fault effects using data from a number of locations around Australia. They were analysed using the Duval Triangle representation which allows multiple DGA results to be easily compared. Results from wind and grid transformers were compared from Australian laboratories. The results show significant differences which indicate different apparent sources of dissolved gases for the two transformer groups. Wind turbine transformer results were predominantly of electrical discharge origin while grid transformer results were primarily thermal in origin. While the data used for the comparison was limited the differences are quite distinct and support similar differences found in North America. This paper looks at possible sources of discharge activity and their connection to characteristics of wind turbines.

Dissolved Gas Analysis Results in Wind Turbine Transformers

Medium and high voltage power cables are the arteries of the transmission and distribution network. They have been widely used in the power industry for many years. In insulation condition monitoring of MV and HV cables, partial discharge (PD) measurement is one of the most effective techniques. PD has been recognized as a major cause of insulation failure as almost all insulation breakdown starts from PD phenomenon. To make an accurate insulation assessment, the PD information obtained has to be carefully interpreted with other factors taken into consideration such as load, noise level, fault type, location, etc. This paper investigates the load effect on PD measurement. The PD signal is detected by the inductive sensor and processed with both narrow band and wide band coupling methods. Experimental results are compared with simulation results.

Load and Other Effects on Measuring Partial Discharge in Power Cables

This paper provides a brief overview of the main areas of research in high voltage (HV) insulation and insulation diagnostics in Australia, particularly at the University of New South Wales, Queensland University of Technology, and the University of Queensland.The main disciplines of activity are those directly associated with condition monitoring of HV equipment and with those dielectric material properties directly applicable to high voltage equipment operation.

https://ieeexplore.ieee.org/iel5/10008/32125/01496076.pdf

A review of Australian research activity in HV insulation and insulation diagnostics

Partial discharge and dissolved gas analysis of common fault types in bio-degradable oil transformers

This paper presents the statistical analysis of partial discharge distributions in oil-impregnated pressboard and paper configurations. The experiment reported here was aimed at an investigation of the characteristics of partial discharges in a cavity for both new and aged oil-impregnated pressboard-paper samples. Two different measurement systems, which provide four different measurement bandwidths were used to observe whether they would produce similar characteristics of discharges. The results indicated that, while there was some general similarity in the shape of PD patterns, a detailed statistical analysis of the PD data showed some significant differences in the results. These differences were significant in terms of the frequency response of the PD sensor systems. As a conclusion, the analysis of such PD data must be performed carefully with particular attention being given to the frequency response.

Trevor Blackburn

Papers

Dissolved Gas Analysis Results in Wind Turbine Transformers

Load and Other Effects on Measuring Partial Discharge in Power Cables

A review of Australian research activity in HV insulation and insulation diagnostics

Partial discharge and dissolved gas analysis of common fault types in bio-degradable oil transformers

Comparison of measured PDs in oil-impregnated insulation using different sensor bandwidths