05 Fakultät Informatik, Elektrotechnik und Informationstechnik
Permanent URI for this collectionhttps://elib.uni-stuttgart.de/handle/11682/6
Browse
7 results
Search Results
Item Open Access Classification of superimposed partial discharge patterns(2021) Adam, Benjamin; Tenbohlen, StefanPhase resolved partial discharge patterns (PRPD) are routinely used to assess the condition of power transformers. In the past, classification systems have been developed in order to automate the fault identification task. Most of those systems work with the assumption that only one source is active. In reality, however, multiple PD sources can be active at the same time. Hence, PRPD patterns can overlap and cannot be separated easily, e.g., by visual inspection. Multiple PD sources in a single PRPD represent a multi-label classification problem. We present a system based on long short-term memory (LSTM) neural networks to resolve this task. The system is generally able to classify multiple overlapping PRPD by while only being trained by single class PD sources. The system achieves a single class accuracy of 99% and a mean multi-label accuracy of 43% for an imbalanced dataset. This method can be used with overlapping PRPD patterns to identify the main PD source and, depending on the data, also classify the second source. The method works with conventional electrical measuring devices. Within a detailed discussion of the presented approach, both its benefits but also its problems regarding different repetition rates of different PD sources are being evaluated.Item Open Access Compatibility study of silicone rubber and mineral oil(2021) Karambar, Smitha; Tenbohlen, StefanIn this study, three types of silicone rubbers, namely, insulative silicone rubber, conductive silicone rubber and silicone rubber with conductive as well as insulative layers are investigated for their compatibility with mineral oil. Mineral oil with different silicone rubber samples is thermally aged at 130 °C for 360 h, 720 h and 1080 h and at 23 °C, 98 °C and 130 °C for 360 h. At the end of each ageing interval, mineral oil and oil-impregnated silicone rubbers are investigated for their dielectric properties. Aged mineral oil samples are investigated for their moisture content, breakdown voltage, colour number, dissolved gases and total acid number, whereas solid insulation samples are investigated for their moisture content. Additionally, pressboard samples in mineral oil and mineral oil without any solid insulation materials are also aged under the same conditions and are investigated for their dielectric properties. From the obtained results, it can be assessed that the presence of carbon particles in conductive silicone rubber negatively impacts the dielectric properties of mineral oil. Among the investigated silicone rubbers, the insulative silicone rubber exhibits good compatibility with mineral oil and a strong potential for being used in mineral oil.Item Open Access Frequency range of UHF PD measurements in power transformers(2023) Tenbohlen, Stefan; Beura, Chandra Prakash; Sikorski, Wojciech; Albarracín Sánchez, Ricardo; Albuquerque de Castro, Bruno; Beltle, Michael; Fehlmann, Pascal; Judd, Martin; Werner, Falk; Siegel, MartinAlthough partial discharge (PD) measurement is a well-accepted technology to assess the quality of the insulation system of power transformers, there are still uncertainties about which frequency range PDs radiate and which frequency range should be evaluated in a measurement. This paper discusses both a UHF PD frequency range obtained from studies investigating laboratory experiments and a frequency range from numerous practical use cases with online and on-site measurements. The literature review reveals a frequency spectrum of ultrahigh-frequency (UHF) PD measurements in the range of 200 MHz to 1 GHz for most publications. Newer publications extend this range from 3 to 6 GHz. The use cases present UHF PD measurements at transformers with power ratings up to 1000 MVA to determine frequency ranges which are considered effective for practical applications. The “common” frequency range, where measurements from all use cases provide signal power, is from approximately 400 MHz to 900 MHz, but it is noted that the individual frequency range, as well as the peak UHF signal power, strongly varies from case to case. We conclude from the discussed laboratory experiments and practical observations that UHF PD measurements in power transformers using either valve or window antennas, according to Cigré, are feasible methods to detect PD.Item Open Access Transformer winding condition assessment using feedforward artificial neural network and frequency response measurements(2021) Tahir, Mehran; Tenbohlen, StefanFrequency response analysis (FRA) is a well-known method to assess the mechanical integrity of the active parts of the power transformer. The measurement procedures of FRA are standardized as described in the IEEE and IEC standards. However, the interpretation of FRA results is far from reaching an accepted and definitive methodology as there is no reliable code available in the standard. As a contribution to this necessity, this paper presents an intelligent fault detection and classification algorithm using FRA results. The algorithm is based on a multilayer, feedforward, backpropagation artificial neural network (ANN). First, the adaptive frequency division algorithm is developed and various numerical indicators are used to quantify the differences between FRA traces and obtain feature sets for ANN. Finally, the classification model of ANN is developed to detect and classify different transformer conditions, i.e., healthy windings, healthy windings with saturated core, mechanical deformations, electrical faults, and reproducibility issues due to different test conditions. The database used in this study consists of FRA measurements from 80 power transformers of different designs, ratings, and different manufacturers. The results obtained give evidence of the effectiveness of the proposed classification model for power transformer fault diagnosis using FRA.Item Open Access Experimental analysis of ultra-high-frequency signal propagation paths in power transformers(2022) Beura, Chandra Prakash; Beltle, Michael; Wenger, Philipp; Tenbohlen, StefanUltra-high-frequency (UHF) partial discharge (PD) monitoring is gaining popularity because of its advantages over electrical methods for onsite/online applications. One such advantage is the possibility of three-dimensional PD source localization. However, it is necessary to understand the signal propagation and attenuation characteristics in transformers to improve localization. Since transformers are available in a wide range of ratings and geometric sizes, it is necessary to ascertain the similarities and differences in UHF signal characteristics across the different designs. Therefore, in this contribution, the signal attenuation and propagation characteristics of two 300 MVA transformers are analyzed and compared based on experiments. The two transformers have the same rating but different internal structures. It should be noted that the oil is drained out of the transformers for these tests. Additionally, a simulation model of one of the transformers is built and validated based on the experimental results. Subsequently, a simulation model is used to analyze the electromagnetic wave propagation inside the tank. Analysis of the experimental data shows that the distance-dependent signal attenuation characteristics are similar in the case of both transformers and can be well represented by hyperbolic equations, thus indicating that transformers with the same rating have similar attenuation characteristics even if they have different internal structures.Item Open Access Transformer winding fault classification and condition assessment based on random forest using FRA(2023) Tahir, Mehran; Tenbohlen, StefanAt present, the condition assessment of transformer winding based on frequency response analysis (FRA) measurements demands skilled personnel. Despite many research efforts in the last decade, there is still no definitive methodology for the interpretation and condition assessment of transformer winding based on FRA results, and this is a major challenge for the industrial application of the FRA method. To overcome this challenge, this paper proposes a transformer condition assessment (TCA) algorithm, which is based on numerical indices, and a supervised machine learning technique to develop a method for the automatic interpretation of FRA results. For this purpose, random forest (RF) classifiers were developed for the first time to identify the condition of transformer winding and classify different faults in the transformer windings. Mainly, six common states of the transformer were classified in this research, i.e., healthy transformer, healthy transformer with saturated core, mechanically damaged winding, short-circuited winding, open-circuited winding, and repeatability issues. In this research, the data from 139 FRA measurements performed in more than 80 power transformers were used. The database belongs to the transformers having different ratings, sizes, designs, and manufacturers. The results reveal that the proposed TCA algorithm can effectively assess the transformer winding condition with up to 93% accuracy without much human intervention.Item Open Access Untersuchung der thermischen Überlastbarkeit von Leistungstransformatoren(2022) Khandan, Saeed; Gerber, Malte; Tenbohlen, StefanDurch die voranschreitende Energiewende und den stetig steigenden Ausbau der Erneuerbaren Energien besteht vermehrt die Notwendigkeit des Ausbaus von Umspannwerken mit neuen Transformatoren. Dieser Ausbau erfolgt meist auf Basis der maximalen Einspeisung im Jahr. Um hierbei dem Netzbetreiber einen besseren Überblick in Bezug auf die Überlastbarkeit des Transformators zu geben, wird im Rahmen eines Projektes die thermische Überlastbarkeit von Transformatoren untersucht. Für eine genauere Betrachtung des thermischen Verhaltens von Leistungstransformatoren wird eine numerische Berechnung mittels computergestützter Strömungsmechanik (CFD) verwendet. Diese erfolgt anhand im Labor gemessener Messdaten an einem Wicklungsmodell. Dieses numerische 3D-Modell ermöglicht es, die Heißpunkttemperatur eines natürlich ON-gekühlten Transformators zu bestimmen und die Veränderung des Heißpunktfaktors in Abhängigkeit von unterschiedlichen Anfangstemperaturen im Labor zu berechnen. Durch die Berechnung des Heißpunktfaktors kann das transiente thermische Verhalten untersucht und im zeitlichen Verlauf verglichen werden. Des Weiteren werden im Rahmen des beschriebenen Projektes über den Zeitraum von einem Jahr Temperatur‑, Leistungs- und Umgebungsmessdaten eines Windparktransformators gezeigt, anhand derer das thermische Verhalten des Transformators untersucht wird. Mit einem Trainingssatz der Messdaten werden unterschiedliche thermische Modelle zur Berechnung der oberen Öltemperatur in Abhängigkeit der Auslastung und der Umgebungstemperatur erstellt und zur Validierung mit einem weiteren Datensatz verglichen. Mithilfe des Heißpunktfaktors aus dem numerischen 3D-Modell kann die Heißpunkttemperatur des natürlich gekühlten Transformators abgeschätzt und mit den Temperaturen aus der Simulation verglichen werden. Basierend auf der nach DIN IEC 60076‑7 empfohlenen maximalen Heißpunkttemperatur und dem erstellten thermischen Modell wird eine Überlastungskurve in Abhängigkeit der Außentemperatur erzeugt. Mit dieser kann die Überlastbarkeit des Leistungstransformators bei unterschiedlichen Umgebungstemperaturen errechnet und somit der Transformator ohne erhöhtes Risiko nach Bedarf mit höherer Last entsprechend der Überlastungskurve betrieben werden.