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

The development of high Tc superconductors (HTS) has now reached the stage where their application in power system equipment is in the process of being implemented As a consequence there is a need to investigate the properties and applicability of high voltage insulation at cryogenic temperatures This paper will examine the insulating materials being used at such temperatures and the dielectric properties of such materials A major factor in the deterioration of electrical insulation at normal operating conditions is the insulation temperature and there is a well developed understanding of the aging characteristics under such temperature conditions However, at cryogenic temperatures the properties of insulation under high electric stress may be quite different than the case for conventional operating temperatures and the aging process may be substantially altered There is thus a need to investigate the insulation properties at cryogenic temperatures This paper reviews the test methods for condition monitoring of insulation under such conditions and reports the first part of experimental results at ambient condition The results obtained and further study at cryogenic temperature will provide necessary information for design of new HTS equipment

High voltage insulation test for high T c superconducting types

Silicone Rubber Surge Arrester housings that were removed from site were tested under conditions of high humidity and artificial pollution. Surface partial discharge behaviour that occurred was detected and recorded by utilizing the CDA3 Computer based partial discharge analysis system. Statistical properties, in particular skewness and kurtosis, provide some indicator of surface damage on the insulator.

Surface Discharge Characteristics of Silicone Rubber Surge Arrester Housings with High Humidity and Pollution

In order to detect partial discharges (PDs) in cable accessories, it is necessary to investigate and understand the generation processes of PDs along insulation surfaces and the signal characteristics of such PDs. Electric field analysis is used in this paper to find the effect of a void produced by a poor termination of cable. Such discharge signals were detected using a measurement system with a high frequency response in the GHz region and analysed both in the time and frequency domains. Based on the features of such signals a detection technique was developed and applied to an experimental model and an actual cable. The results obtained are encouraging. They indicate that practical PD detection in the field using this technique is feasible.

http://ieeexplore.ieee.org/iel5/7678/20977/00973721.pdf

Partial discharge characteristics in polymeric cable accessories

In this paper arc discharge characteristics during standard lightning impulse test are analyzed by proposed soft-threshold shrinkage de-noising technique based on wavelet transform (WT) frame. Experimental data is provided to show that the partial features of original digitally recorded and noise contaminated signals can be preserved by using proposed noise suppression method. In addition to characterization of single arc discharge in the time-frequency domain, WT has been applied to obtained de-noised waveforms. It is shown that not only the frequency content of arc discharge but also the time of its occurrence can be determined using WT.

Soft-Threshold Wavelet De-Noising Technique Application for a Single Arc Discharge Across a Static Gap

This paper presents the measurements results of simulated partial discharge propagation on a compact three phase XLPE cable, and shows how the high frequency signal on one phase of the cable is induced on the other two phases. A frequency dependent three phase cable model is employed to simulate this phenomena.

http://ieeexplore.ieee.org/iel5/4807911/4812967/04813127.pdf

Trevor Blackburn

Papers

High voltage insulation test for high T c superconducting types

Surface Discharge Characteristics of Silicone Rubber Surge Arrester Housings with High Humidity and Pollution

Partial discharge characteristics in polymeric cable accessories

Soft-Threshold Wavelet De-Noising Technique Application for a Single Arc Discharge Across a Static Gap

Investigation of partial discharge propagation on compact three phase XLPE cables