Transformers are prolific and one of the critical components of the distribution power system. For each HV/MV primary substation, there are tens of secondary substations. As a result, there are around one thousand distribution transformers in a medium-sized city with 40 HV/MV primary substations
The article appeared in ESI Africa Issue 1-2021.
Read the full digimag or subscribe to receive a free print copy.
Accelerated degradation and failure of distribution transformers can occur due to several conditions such as oil leakage, overloading, unbalanced loading and harmonics. However, most failures are caused by a combination of these electrical, mechanical and thermal stresses acting on the power transformer components over time.
Although the manufacturer generally establishes design and operational limits, the impact on service life is non-binary and multi-dimensional. For example, exceeding a thermal limit to a moderate extent for a short amount of time will not cause immediate failure. Still, more severe overloading for an extended period will likely cause irreversible damage.
To properly assess the transformer’s health, the monitoring system must perform physical measurements and analyse the results in the context of given environmental conditions. This will provide information about the transformer’s state of health and detect incipient faults. Health Indices (HI) methods are practical tools to aggregate the results of multiple operating observations, field inspections, and site and laboratory testing into a single objective index that quantifies overall health. Here follow a few health assessment techniques.
Health Index Calculation
The HI Calculation is a helpful technique in that it is the most basic method used to create maintenance strategies for transformers. This health index method uses the representative indexes of the transformer’s operation and statement to convert them into a quantitative index and evaluate the general condition of the transformer.
Fuzzy logic has been proposed as a suitable approach to overcome the limitations of the HI calculation method. It is supposed to represent vague concepts and uncertain information, especially in cases in which conventional logic techniques couldn’t be applied effectively. The structure of a complete fuzzy control system includes three steps: fuzzification, inference, and defuzzification.
At the first step, fuzzification calculates fuzzy values from exact values at the input. The fuzzy inference applies all applicable fuzzy rules to calculate the fuzzy value for the output. The defuzzification determines the exact output value from the fuzzy result obtained in the fuzzy inference step.
Machine learning algorithms
Normally, the transformer HI can be computed from a parameter by creating a relationship rule and equation. To improve accuracy and reliability, the HI is determined from many parameters that might not be related and are hard to calculate. Several papers have presented the method for predicting transformer health using artificial intelligence (AI) tools, such as machine learning (ML).
ML is the algorithm that improves automatically through experience. ML can teach itself and adapt non-linear mappings between input and output. Advanced ML techniques are used to build surrogate models that can be put in an application as low computational-cost approximations of more expensive calculations. All the ML-based HI methods need the database to learn the wanted correlations and make predictions or decisions without being explicitly programmed to implement the task. Transformer condition assessment programmes using AI algorithms may have the potential to apply to inexpensive sensor systems, which helps to keep the overall system cost and complexity low.
Hybrid artificial intelligence approaches
In recent years, the searching algorithms have been adopted in by researchers to find the best subset of features in the feature selection problems. The hybrid AI approaches that use optimisation algorithms to support learning algorithms can overcome the weakness of single learning algorithms because the selection parameters of learning algorithms significantly impact their usefulness and classification performance. Therefore, it is necessary to find the optimal value of these parameters to improve the prediction accuracy. The optimisation algorithm can support the HI computation methods and fuzzy logic to optimise weighted parameters so the results for transformer health assessment will be more accurate.
It is necessary to consider the dependency of the methods on the load condition, temperature, and transformer ageing effect over time. The root causes of failures on distribution transformers are mainly due to overloading and unbalanced loading. The transformer loading directly affects the current in the winding and hence raise the temperature in the winding and the transformer’s oil, which results in accelerating ageing and reducing the asset’s service life. This represents the tight relationship between a distribution transformer’s loading parameters, its temperature, its ageing and its health.
The transformer ageing index is also an important parameter, but this parameter can only be calculated through other parameters. The estimation of transformer ageing parameters is complex and non-deterministic because the heat transfer process is distributed over different surfaces in the winding and insulation structures. There may be measurement errors. It requires a high-quality sensor to provide high accuracy data. Transformer ageing is normally included in the evaluation models that use HI calculation or fuzzy logic methodologies. AI approaches are often applied based on actual measurement parameters to enhance accuracy. The research will need to be investigated to evaluate the importance of the indicators on the distribution transformer, thereby improving the accuracy and reliability of the assessment models.
Significant deviations or rapid changes in this index or its factors could be used to predict the need for maintenance, reconfiguration, upgrade, or replacement. Ultimately, this will improve reliability and reduce the cost of electric service. It is essential with the advent of higher penetrations of distributed PV, electric vehicles, and other energy resources that are rapidly changing the grid’s operation and can introduce added stress to service transformers. ESI
A Review of Health Assessment Techniques for Distribution Transformers in Smart Distribution Grids. 2020. By Quynh T. Tran, Kevin Davies, Leon Roose, Puthawat Wiriyakitikun, Jaktupong Janjampop, Eleonora Riva Sanseverino, and Gaetano Zizzo. The article above is based on the research paper published under Creative Commons. View the full paper online: https://www.mdpi.com/2076- 3417/10/22/8115/htm