October 5, 2018

Column: Condition monitoring

Big data Where is it and is it useful?   Abstract A great deal has been made of big data and its potential usefulness in...

---

Big data

Where is it and is it useful?

 

Abstract

A great deal has been made of big data and its potential usefulness in many applications in the electric power industry. It certainly is useful in many domains, such as banking and logistics, giving insights to previously ‘hidden’ data aspects that can and do escape the human eye.

Data for assets in substations is required to facilitate condition assessments of equipment and to develop the subsequent action plans for maintaining a safe and secure electrical infrastructure. Often when one seeks to retrieve this data, it can be difficult to find. If it is found, the question arises: how accurate is the data and is it current?

For those engaged in the development of condition (or health) indices, this can prove to be a major challenge. Data quality and timeliness determines the confidence one can place on the evaluations made.

Keywords: data, big data, data quality, timeliness

 

1. Introduction

In my last column, the discussion centred on the essential requirement for communications of data, information and alarms to a place where it can be acted upon. This carries the implication of the movement of data and access to previous test records, inspection reports, etc. indicating that the realm of big data is with us now.

The application of big data tools and data analytics by electric power utilities should consider the specific features of the world of managing of major assets such as transformers, switchgear and battery systems. Challenges arise regarding not only the quality and timeliness of the data records of the equipment’s past life, but also the amount of data that has gone missing. An IEC White Paper published in 2015 points out the concerns of the age distribution of these assets. From my point of view, this includes many other transformers outside of the utility realm, such as industrial and renewable generation applications, as well as concerns such as safety hazards (explosion and fire), environmental issues (oil spills), loss of revenue, obsolescence, spare parts, and the lack of knowledgeable and qualified manpower.

A recent article on ‘expert systems’ vs. human expert written by Georg Daemisch and published in Transformers Magazine brings to light a concern I have had for many years, regarding the need for better control of data being processed by not only ‘expert systems’ but by humans as well.

The output of HV equipment condition assessment indexing (manually or automated) is widely used as a tool for planning, refurbishment or replacement of these critical assets. A condition index can be a weighted value, or some other statistical combination of a range of factors and parameters influencing their condition, which in turn can be derived from a combination of inspection, off-line testing and on-line continuous monitoring data.

These approaches generally assume that the data presents a reliable picture of current transformer condition, meaning that the test record is complete and up to date. In an operational context, the data may not be as reliable as is often assumed, and yet asset managers must still make decisions about maintenance and replacement based on it.

Subscribe to Transformers Magazine