Effective IoT-based deep learning platform for online fault diagnosis of power transformers against cyberattacks and data uncertainties

Condition assessment of insulating oil is crucial for the reliable long-term operation of power equipment, especially power transformers. Under thermal aging, critical degradation in oil properties, including chemical, physical, and dielectric properties, occurs due to the generation of aging byproducts. Ultraviolet-visible (UV-Vis) spectroscopy was recently proposed for the condition assessment of mineral oil. However, this absorption technique may involve all electronic states of the investigated material which typically yield a broad spectrum, and thus cannot precisely reflect the electronic structure of aged oil samples. It also cannot be implemented as an online sensor of oil degradation. In this paper, photoluminescence (PL) spectroscopy is introduced, for the first time, for effective condition assessment of insulating oil. The PL technique involves emission processes that only occur between a narrow band of electronic states that are occupied by thermalized electrons and consequently yields a spectrum that is much narrower than that of the absorption spectrum. Aged oil samples with different aging extents were prepared in the laboratory using accelerated aging tests at 120 °C, under which 1 day of laboratory aging is equivalent to approximately 1 year of aging in the field. These aged samples were then tested using PL spectroscopy with a wavelength ranging from 150 nm to 1500 nm. Two main parameters were evaluated for quantitative analysis of PL spectra: The full width at half-maximum and the enclosed area under the PL spectra. These parameters were correlated to the aging extent. In conjunction with PL spectroscopy, the aged oil samples were tested for the dielectric dissipation factor as an indication of the number of aging byproducts. Interestingly, we find a correlation between the PL spectra and the dielectric dissipation factor. The results of PL spectroscopy were compared to those of UV-Vis spectroscopy for the same samples and the parameters extracted from PL spectra were compared to the aging b-products extracted from UV-Vis spectra. Finally, the corresponding physical mechanisms were discussed considering the obtained results and the spectral shift for each spectrum. It was proved that PL spectroscopy is a promising technique for the condition assessment of insulating oil when compared to conventional transformer oil assessment measuring techniques and even to other optical absorption techniques.

https://www.mdpi.com/2227-9717/9/5/732/pdf

Photoluminescence Spectroscopy Measurements for Effective Condition Assessment of Transformer Insulating Oil

Recently, the penetration of energy storage systems and photovoltaics has been significantly expanded worldwide. In this regard, this paper presents the enhanced operation and control of DC microgrid systems, which are based on photovoltaic modules, battery storage systems, and DC load. DC–DC and DC–AC converters are coordinated and controlled to achieve DC voltage stability in the microgrid. To achieve such an ambitious target, the system is widely operated in two different modes: stand-alone and grid-connected modes. The novel control strategy enables maximum power generation from the photovoltaic system across different techniques for operating the microgrid. Six different cases are simulated and analyzed using the MATLAB/Simulink platform while varying irradiance levels and consequently varying photovoltaic generation. The proposed system achieves voltage and power stability at different load demands. It is illustrated that the grid-tied mode of operation regulated by voltage source converter control offers more stability than the islanded mode. In general, the proposed battery converter control introduces a stable operation and regulated DC voltage but with few voltage spikes. The merit of the integrated DC microgrid with batteries is to attain further flexibility and reliability through balancing power demand and generation. The simulation results also show the system can operate properly in normal or abnormal cases, thanks to the proposed control strategy, which can regulate the voltage stability of the DC bus in the microgrid with energy storage systems and photovoltaics.

https://www.mdpi.com/2079-9292/10/11/1261/pdf

Novel Control Strategy for Enhancing Microgrid Operation Connected to Photovoltaic Generation and Energy Storage Systems

Fault type diagnosis is a very important tool to maintain the continuity of power transformer operation. Dissolved gas analysis (DGA) is one of the most effective and widely used techniques for predicting the power transformer fault types. In this paper, a convolutional neural network (CNN) model is proposed based on the DGA approach to accurately predict transformer fault types under different noise levels in measurements. The proposed model is applied with three categories of input ratios: conventional ratios (Rogers’4 ratios, IEC 60599 ratios, Duval triangle ratios), new ratios (five gas percentage ratios and new form six ratios), and hybrid ratios (conventional and new ratios together). The proposed model is trained and tested based on 589 dataset samples collected from electrical utilities and literature with varying noise levels up to ±20%. The results indicate that the CNN model with hybrid input ratios has superior prediction accuracy. The high accuracy of the proposed model is validated in comparison with conventional and recently published AI approaches. The proposed model is implemented based on MATLAB/toolbox 2020b.

/pdf/power-transformer-fault-diagnosis-based-on-dga-using-a-1g21rvs1cw.pdf

Power Transformer Fault Diagnosis Based on DGA Using a Convolutional Neural Network With Noise in Measurements

Power transformer is one of the main equipment in power transmission and distribution network. Thus, it is important to ensure optimal operation of power transformer for an efficient supply of energy to utilities. One of the main components of a power transformer is the transformer insulation system, namely, transformer insulation oil and transformer insulation paper. This review provides an in-depth discussion on the reactions that occur in the insulation system of the power transformer. These include, oxidation, hydrolysis, pyrolysis, partial discharge, and arcing. The reaction mechanisms, conditions and the relationship between these reactions are thoroughly analysed in this review. Apart from that, this review also provides an inclusive discussion on the state-of-the-art methods used to monitor the byproducts formed from the mentioned reactions. These methods were developed to overcome the limitation of conventional methods that are complex and costly. Moreover, it presents an impartial evaluation of the challenges and prospects in making the power transformer monitoring system more efficient in terms of cost and time. Information corroborated in this review is expected to provide an important roadmap for future research in monitoring the condition of power transformer. 

Power transformer insulation system: A review on the reactions, fault detection, challenges and future prospects

Power transformers are considered important and expensive items in electrical power networks. In this regard, the early discovery of potential faults in transformers considering datasets collected from diverse sensors can guarantee the continuous operation of electrical systems. Indeed, the discontinuity of these transformers is expensive and can lead to excessive economic losses for the power utilities. Dissolved gas analysis (DGA), as well as partial discharge (PD) tests considering different intelligent sensors for the measurement process, are used as diagnostic techniques for detecting the oil insulation level. This paper includes two parts; the first part is about the integration among the diagnosis results of recognized dissolved gas analysis techniques, in this part, the proposed techniques are classified into four techniques. The integration between the different DGA techniques not only improves the oil fault condition monitoring but also overcomes the individual weakness, and this positive feature is proved by using 532 samples from the Egyptian Electricity Transmission Company (EETC). The second part overview the experimental setup for (66/11.86 kV-40 MVA) power transformer which exists in the Egyptian Electricity Transmission Company (EETC), the first section in this part analyzes the dissolved gases concentricity for many samples, and the second section illustrates the measurement of PD particularly in this case study. The results demonstrate that precise interpretation of oil transformers can be provided to system operators, thanks to the combination of the most appropriate techniques.

https://www.mdpi.com/1424-8220/21/6/2223/pdf

Towards Precise Interpretation of Oil Transformers via Novel Combined Techniques Based on DGA and Partial Discharge Sensors

Transformer oil insulation level may be deteriorated due to electrical and thermal faults, which may lead to transformer failure and system outage. In this regard, the first part of this paper presents comprehensive maintenance for power transformers aiming to diagnose transformer faults more accurately. Specifically, it aims to identify incipient faults in power transformers using what is known as dissolved gas analysis (DGA) with a new proposed integrated method. This proposed method for DGA is implemented based on the integration among the results of five different DGA techniques; 1) conditional probability, 2) clustering, 3) Duval triangle, 4) Roger’s four ratios refined, and 5) artificial neural network. Accordingly, this proposed integrated DGA method could improve the overall accuracy by 93.6 % compared to the existing DGA techniques. In addition, the second part used for predictive maintenance is based on determining the health index for a new and an aged power transformer (66/11 kV, 40 MVA) filled with NYTRO 10XN oil by evaluating the breakdown voltage, DGA, moisture content, and acidity for the oil itself. In the breakdown voltage test, two practical types of transformer oil; transformer oil type (NYTRO 10 XN) and another type HyVolt III alongside their mixtures are evaluated and compared, where this mixture has not been reported in the literature. In addition, aged oil samples extracted from a real case study in-service transformer during operation with different aged durations; 9, 10, 11, 12, and 13 years, are tested for breakdown voltage and then compared with fresh oil samples. In the DGA task, the temperature rise test is carried out firstly on the case study, and hot dc resistance of winding is measured under different cooling systems. Considering five transformers of the same rating and oil type, the DGA was performed on oil samples extracted before and after the temperature rise test. The DGA results predicted that there was a possibility exists of local overheating. While the complementation of oil breakdown voltage technique for dielectric severity indication and temperature rise technique for thermal severity indication in addition to moisture and acidity measurements can lead to an effective maintenance plan for power transformers into the field. Hence, by using the proposed multi-criteria analysis approach (i.e., breakdown, acidity, moisture, and DGA results), the various factors are combined into a condition-based Health Index, yielding reliable estimation results compared to individual approaches.

https://ieeexplore.ieee.org/ielx7/6287639/9668973/09726145.pdf

Reliable Estimation for Health Index of Transformer Oil Based on Novel Combined Predictive Maintenance Techniques

Novel accurate modeling of dust loaded wire-duct precipitators using FDM-FMG method on one fine computational domains

Electrical transformers are considered one of the very important elements on the operation of power systems. The operation of electrical transformers is dependent on the performance of transformer oils. Hence, it is very necessary for continuous and on line checking the transformer oil insulation level. Transformer oil wet process generates oil discharge space charge in the long run and bubbles are formed. When the electric field reaches a certain limit, partial discharge appears and lead to deterioration of oil insulation level. Multi-wall carbon nanotube (MWNT) has many advantages for detecting PD of oils (e.g., high surface to volume ratio). So, we reported the performance of (MWNTs) films sensor for continuous and on line monitoring the oil insulation level. MWNTs sensors were synthesized using chemical treatment. Treatments of MWNTs sensors were made by using different acids. Specifications of nanotubes were made using microscope (operate in two and tree directions) and fourier microscope. Experimental results show the performance of nanotube sensors is very good.

Partial Discharge Detection Inside Transformer Oils Using On-Line Monitoring Nanotechnology Techniques

/pdf/identification-of-transformer-oil-incipient-faults-based-on-3gd99ms2.pdf

Mohamed Badawi

Papers

Towards Precise Interpretation of Oil Transformers via Novel Combined Techniques Based on DGA and Partial Discharge Sensors

Reliable Estimation for Health Index of Transformer Oil Based on Novel Combined Predictive Maintenance Techniques

Novel accurate modeling of dust loaded wire-duct precipitators using FDM-FMG method on one fine computational domains

Partial Discharge Detection Inside Transformer Oils Using On-Line Monitoring Nanotechnology Techniques

Identification of Transformer Oil incipient Faults Based on the Integration between Different DGA Techniques