Deep Learning Applied to SFRA Results: A Preliminary Study

Giovanni Bucci 1
Fabrizio Ciancetta 1
Edoardo Fiorucci 1
Simone Mari 1
Andrea Fioravanti 1
Publication typeProceedings Article
Publication date2021-04-23
Abstract
The SFRA (Sweep Frequency Response Analysis) is a measurement technique that allows to evaluate the integrity of power transformers. The goal of SFRA is to determine the transfer function (TF) of each winding of the transformer in a certain frequency range. The technique has recently been successfully used for the characterization of rotating machines, such as induction motors, widely found in industry. Promising results have also recently been demonstrated in the use of the technique for the identification and characterization of household appliances. This article illustrates the possibility of using TFs, obtained by applying the SFRA technique, as an input to Deep Learning algorithms, in order to create systems capable of making decisions based on these results. Furthermore, the work reports the results obtained by a Deep Learning system applied to the recognition of household appliances through the use of this analysis.
Fioravanti A., Prudenzi A., Bucci G., Fiorucci E., Ciancetta F., Mari S.
2020-06-01 citations by CoLab: 10 Abstract
The paper describes some initial evaluations concerning the possible use of SFRA based method of analysis to the pattern of energy use in the domestic residential sector. The paper illustrates the SFRA techniques of investigation that are well-consolidated tools in various research sectors as for the identification of faults in transformers and induction motors. The SFRA techniques are then applied to the very current interesting problem of domestic appliance signature identification in non-intrusive approaches of load research. Some first results of the applications of the techniques as obtained from laboratory tests conducted on a domestic electric installation simulator.
Bucci G., Ciancetta F., Fiorucci E., Mari S.
2020-05-01 citations by CoLab: 13 Abstract
In this paper we mainly focus on monitoring the energy consumption of individual electrical appliances connected to a home. The adopted system measures the total electric current and extracts the absorption of each individual device, using a NILM algorithm (Non Intrusive Load Monitoring). The characteristics of a new NILM algorithm have been identified by comparing the different load disaggregation techniques. It was initially verified with aggregate data available online. Successively, measurements were performed using a suitable system that reproduces a typical domestic electrical wiring with connected household appliances was implemented. The paper describes the measurement system, including the NILM algorithm. Additionally, some performance evaluation results are also reported in the paper.
Bucci G., Ciancetta F., Fioravanti A., Fiorucci E., Prudenzi A.
2020-05-01 citations by CoLab: 9 Abstract
• A low-cost SFRA device to checking transformers in hospital environments is proposed. • Faults of IT-M transformers have effects on health care facilities and diagnostic rooms. • Some IT-M defects are frequent and well known, others are rarer and less obvious. • SFRA on IT-M transformers improves the resilience of critical electrical systems. • The adoption of SFRA is useful both from an economic and safety point of view. Medical environments must guarantee the electrical safety of medical personnel and, especially, of patients in contact with electro-medical devices. These environments are equipped with IT-M distribution systems, where an isolation transformer transfers the electricity while the devices are isolated from the power source. This safety system works reliably only if the isolation transformer is functioning properly. A failure of this transformer also involves high risks when the supplied equipment is in direct contact with the patient. A system for the online diagnosis of these transformers could play a crucial role in terms of safety, allowing their state to be analyzed and their reliability assessed over time. The SFRA technique represents a possible solution to monitor the status and prevent breakdowns. SFRA is a non-invasive technique that allows the evaluation of the integrity of the transformer without applying high voltages. In critical installation it could be automatically carried out on a daily basis, through a low-cost measuring device, connected in parallel to the transformer. In this paper we proposed a low-cost SFRA test system. We also investigated the most common types of faults affecting IT-M transformers and carried out experimental tests on a set of single-phase isolation transformers for medical use, in order to correlate the TF diagrams with the most common deteriorations and defects.
Ruano A., Hernandez A., Ureña J., Ruano M., Garcia J.
Energies Q1 Q3 Open Access
2019-06-10 citations by CoLab: 186 PDF Abstract
The ongoing deployment of smart meters and different commercial devices has made electricity disaggregation feasible in buildings and households, based on a single measure of the current and, sometimes, of the voltage. Energy disaggregation is intended to separate the total power consumption into specific appliance loads, which can be achieved by applying Non-Intrusive Load Monitoring (NILM) techniques with a minimum invasion of privacy. NILM techniques are becoming more and more widespread in recent years, as a consequence of the interest companies and consumers have in efficient energy consumption and management. This work presents a detailed review of NILM methods, focusing particularly on recent proposals and their applications, particularly in the areas of Home Energy Management Systems (HEMS) and Ambient Assisted Living (AAL), where the ability to determine the on/off status of certain devices can provide key information for making further decisions. As well as complementing previous reviews on the NILM field and providing a discussion of the applications of NILM in HEMS and AAL, this paper provides guidelines for future research in these topics.
Khalili Senobari R., Sadeh J., Borsi H.
2018-02-01 citations by CoLab: 115 Abstract
Power transformers are one of the most important components of the electrical power networks. A wide range of mechanical and electrical stresses in addition to the aging could cause failures in these apparatuses. As a result, evaluating the condition of the transformers during their lifetime is crucial to the power network reliability and service continuity. A large number of different fault diagnosis techniques are introduced for this purpose. Frequency Response Analysis (FRA) is sensitive to the great number of electrical or mechanical changes in the transformers that could occur during the manufacturing, transportation, installation, maintenance or operation of the device. Therefore, FRA is considered among the powerful methods of transformers’ condition assessment. This paper explains the frequency response analysis of transformers method, its application and test procedure as well as providing a comprehensive review of the researches and attempts that are done on different aspects of this field for enhancing quality and repeatability of the test and the interpretation of the results.
Albawi S., Mohammed T.A., Al-Zawi S.
2017-08-01 citations by CoLab: 2612 Abstract
The term Deep Learning or Deep Neural Network refers to Artificial Neural Networks (ANN) with multi layers. Over the last few decades, it has been considered to be one of the most powerful tools, and has become very popular in the literature as it is able to handle a huge amount of data. The interest in having deeper hidden layers has recently begun to surpass classical methods performance in different fields; especially in pattern recognition. One of the most popular deep neural networks is the Convolutional Neural Network (CNN). It take this name from mathematical linear operation between matrixes called convolution. CNN have multiple layers; including convolutional layer, non-linearity layer, pooling layer and fully-connected layer. The convolutional and fully-connected layers have parameters but pooling and non-linearity layers don't have parameters. The CNN has an excellent performance in machine learning problems. Specially the applications that deal with image data, such as largest image classification data set (Image Net), computer vision, and in natural language processing (NLP) and the results achieved were very amazing. In this paper we will explain and define all the elements and important issues related to CNN, and how these elements work. In addition, we will also state the parameters that effect CNN efficiency. This paper assumes that the readers have adequate knowledge about both machine learning and artificial neural network.
Makonin S., Popowich F.
2014-10-31 citations by CoLab: 150 Abstract
Nonintrusive load monitoring (NILM), sometimes referred to as load disaggregation, is the process of determining what loads or appliances are running in a house from analysis of the power signal of the whole-house power meter. As the popularity of NILM grows, we find that there is no consistent way the researchers are measuring and reporting accuracies. In this short communication, we present a unified approach that would allow for consistent accuracy testing.
Sharma U., Chatterjee S., Bhuyan K.
2012-12-01 citations by CoLab: 8 Abstract
Any deformation or displacement in the transformer winding can cause change in the circuit parameters and frequency response. The changes can be detected using Sweep Frequency Response Analysis (SFRA). For the detection of the changes, SFRA needs a reference which is generated during commissioning of the transformer. The reference generated can be used by the same SFRA kit. But SFRA kit keeps on updating. If the transformer needs to have SFRA tests after 20 years of its commissioning, the SFRA kit might be updated and hence the old reference is unable to be used. SFRA response at design stage would remove this bottleneck which can be used for any SFRA kit. In this paper a high frequency simulated model of a 10 MVA transformer is developed based on lumped parameter representation for SFRA interpretation. SFRA plot of the model (simulated data) can be compared with the experimental SFRA plot (measured data) of the transformer and it has been found that the same can be used as a reference.
Di Pasquale A., Fiorucci E., Ometto A., Rotondale N.
2012-06-01 citations by CoLab: 5 Abstract
The performance and the reliability of the power transformers are critical parameters for the electric power production, transmission and utilization. In the last years diagnostic techniques have been widely utilized to improve the safety and to reduce the maintenance costs of power transformers. The Bticino group had recently acquired the plant in Castellalto, Italy, from the Zucchini EMM, that is devoted to the design and the production of cast-resin MV/LV power transformers; a research project concerning the application of the SFRA (Sweep Frequency Response Analysis) to Bticino transformers has been started as a cooperation with the Department of Electrical and Information Engineering of the University of L'Aquila, with the main aim of creating a database for the fault analysis. This paper presents the developed measurement system and the first experimental results that have been obtained by applying the SFRA to transformers of different rated power.
Mari S., Bucci G., Ciancetta F., Fiorucci E., Fioravanti A.
Sensors Q1 Q2 Open Access
2023-05-31 citations by CoLab: 5 PDF Abstract
In traditional nonintrusive load monitoring (NILM) systems, the measurement device is installed upstream of an electrical system to acquire the total aggregate absorbed power and derive the powers absorbed by the individual electrical loads. Knowing the energy consumption related to each load makes the user aware and capable of identifying malfunctioning or less-efficient loads in order to reduce consumption through appropriate corrective actions. To meet the feedback needs of modern home, energy, and assisted environment management systems, the nonintrusive monitoring of the power status (ON or OFF) of a load is often required, regardless of the information associated with its consumption. This parameter is not easy to obtain from common NILM systems. This article proposes an inexpensive and easy-to-install monitoring system capable of providing information on the status of the various loads powered by an electrical system. The proposed technique involves the processing of the traces obtained by a measurement system based on Sweep Frequency Response Analysis (SFRA) through a Support Vector Machine (SVM) algorithm. The overall accuracy of the system in its final configuration is between 94% and 99%, depending on the amount of data used for training. Numerous tests have been conducted on many loads with different characteristics. The positive results obtained are illustrated and commented on.
Bucci G., Ciancetta F., Fioravanti A., Fiorucci E., Mari S., Silvestri A.
Sensors Q1 Q2 Open Access
2023-02-26 citations by CoLab: 7 PDF Abstract
Asynchronous motors represent a large percentage of motors used in the electrical industry. Suitable predictive maintenance techniques are strongly required when these motors are critical in their operations. Continuous non-invasive monitoring techniques can be investigated to avoid the disconnection of the motors under test and service interruption. This paper proposes an innovative predictive monitoring system based on the online sweep frequency response analysis (SFRA) technique. The testing system applies variable frequency sinusoidal signals to the motors and then acquires and processes the applied and response signals in the frequency domain. In the literature, SFRA has been applied to power transformers and electric motors switched off and disconnected from the main grid. The approach described in this work is innovative. Coupling circuits allow for the injection and acquisition of the signals, while grids feed the motors. A comparison between the transfer functions (TFs) of healthy motors and those with slight damage was performed with a batch of 1.5 kW, four-pole induction motors to investigate the technique’s performance. The results show that the online SFRA could be of interest for monitoring induction motors’ health conditions, especially for mission-critical and safety-critical applications. The overall cost of the whole testing system, including the coupling filters and cables, is less than EUR 400.
Mari S., Bucci G., Ciancetta F., Fiorucci E., Fioravanti A.
Energies Q1 Q3 Open Access
2022-11-28 citations by CoLab: 9 PDF Abstract
Load monitoring systems make it possible to obtain information on the status of the various loads powered by an electrical system. The term “electrical load” indicates any device or circuit that absorbs energy from the system to which it is connected, and which therefore influences electrical quantities such as power, voltage, and current. These monitoring systems, designed for applications related to energy efficiency, can also be used in other applications. This article analyzes in detail how the information derived from Non-Intrusive Load Monitoring (NILM) systems can be used in order to create Energy Management Systems (EMS), Demand Response (DR), anomaly detection, maintenance, and Ambient Assisted Living (AAL).
Bucci G., Ciancetta F., Fiorucci E., Mari S., Fioravanti A.
2021-12-01 citations by CoLab: 21 Abstract
Nowadays, non-intrusive load monitoring (NILM) systems represent an effective alternative to monitoring individual appliances' consumption, avoiding the costs and spatial constraints imposed by the installation of additional sensors. Modern artificial intelligence algorithms, such as machine learning algorithms, make it possible to split the aggregate power absorption profile of a user into the individual power absorption profiles of the main household appliances. However, there is still no full awareness of how these systems can be used effectively and in what situations they can provide consistent support. This paper illustrates the most promising management, diagnostics, and automation activities that can be carried out with the help of an efficient NILM system, referring to the most significant works in literature. A discussion of challenges and future research directions is also provided.

Top-30

Journals

1
2
1
2

Publishers

1
2
3
1
2
3
  • We do not take into account publications without a DOI.
  • Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
  • Statistics recalculated weekly.

Are you a researcher?

Create a profile to get free access to personal recommendations for colleagues and new articles.
Found error?