Oil Chromatogram Research Articles

Transformer fault diagnosis based on adversarial generative networks and deep stacked autoencoder

Establishing a deep learning model for transformer fault diagnosis using transformer oil chromatogram data requires a large number of fault samples. The lack and imbalance of oil chromatogram data can lead to overfitting, lack of representativeness of the model, and unsatisfactory prediction results on test set data, making it difficult to accurately diagnose transformer faults. A conditional Wasserstein generative adversarial network with gradient penalty optimization (CWGAN-GP) is adopted in this paper, which based on gradient penalty optimization and expand the oil chromatography fault samples of 500 sets of transformer oil chromatography data with 5 types of faults. The proposed method is used to classify transformer faults using a deep autoencoder, and the sample quality of the neural network model proposed in this paper is compared with several other variants of generative adversarial neural network models. The research results show that after using the method proposed in this paper for sample expansion, the overall accuracy of fault diagnosis can reach 93.2 %, which is 4.98 % higher than the original imbalanced samples. Compared with other sample expansion methods, the accuracy of fault diagnosis of the algorithm in this paper is improved by 1.70 %–3.05 %.

Research on transformer fault intelligent diagnosis technology based on improved random forest algorithm

Transformer oil can dissolve a certain amount of gas, which can provide an important basis for transformer fault diagnosis. The relationship between the characteristic amount of dissolved gas in transformers and the type of transformer fault was analyzed, and the main influencing factors were extracted. We studied a transformer fault diagnosis method based on the improved random forest algorithm and combined it with the identification requirements of abnormal data in multiple parts of transformers. We improved the random forest from four aspects: dataset construction, bootstrap sampling, decision tree generation, and multi-node voting. We established an improved random forest diagnosis model with oil chromatogram feature gas ratio as the characteristic parameter and analyzed different input parameter combinations. The effectiveness of improving the random forest diagnosis model under different training times was compared with various machine learning methods. The experimental results show that the diagnostic accuracy of the improved random forest diagnostic model is significantly improved compared to other machine learning methods.

Analysis and Treatment of Abnormal Defects in Transformer Oil Chromatography

This article analyzes the cause of an abnormal defect in the oil chromatogram of a transformer, and puts forward control measures and suggestions. It is analyzed that the cause of the abnormal oil chromatogram of phase A and B of the main transformer is the poor contact o f the dynamic and static contacts of the unloaded tap changer, high temperature and overheatin g, and the development of contact ablation, resulting in abnormal oil chromatogram. The cause of the ablation of the dynamic and static contacts of the no-load tap-changer may be due to the installation and transportation (or electrodynamic shock or U-switch design and other factors), the contacts are not in close contact, the larger contact resistan ce causes the contacts to overheat, and high temperature conditions Sulfur corrosion occurs on the surface of the lower contact, and the corrosion product gradually deposits on the surface of the contact, which further aggravates the poor contact. Although passivation agent is added in t he later period, the protection effect of the passivation agent at high temperature is limited, and it can no longer protect the contact. Under the action of current, the dynamic and static contacts that cause poor contact are gradually ablated.

Research on on-line monitoring data cleaning of transformer oil chromatogram based on machine learning and neural networks

Transformer oil chromatogram on-line monitoring device is a widely used sensing device to monitor the operation state of transformer. Due to the lack of hardware verification means, the on-line chromatographic data generally has the problem of drift. In actual operation, it is mostly used as the basis for trend judgment, but can not reflect the effective value of chromatographic measurement. In this paper, the LSTM neural networks is used to correct the on-line monitoring data of transformer oil chromatogram. The off-line test data combined with neural networks data cleaning technology are used to repeatedly feed back and calibrate the online data, so that the corrected chromatographic on-line number is steadily close to the off-line detection data, which greatly improves the availability and accuracy of on-line chromatographic data. The research results of this paper have important reference significance for the data cleaning of on-line monitoring and measurement of electrical equipment.

Analysis of an Abnormal Faults of UHV DC Low-end YD-A Phase Converter Oil Chromatography

The article introduces an abnormal malfunction of YD-A converter oil chromatogram at the low end of UHVDC converter station, through oil chromatography data, ultrasonic positioning, on-site feeding, returning to plant disassembly and simulation calculation, which confirmed that the breakage of the isopotential of the converter electrostatic plate is the cause of the abnormal oil chromatogram and put forward corresponding suggestions and measures.

Diagnosis Technology of Substation Abnormal State Based on Cloud Edge Collaboration

Abstract The substation monitoring system based on cloud edge collaborative computing is an important application field of power Internet of things (IoT) technology, which can effectively improve the data processing capacity of the system. First of all, the problems of computing range, computing power, delay performance, task priority, information transmission and cross are analysed when cloud and edge computing are applied in the abnormal state monitoring of substation. The application functions of the two computing modes in the monitoring system are studied. Secondly, the system of abnormal state detection and the diagnosis process of substation based on cloud edge collaborative computing are designed. Then, the design of abnormal state diagnosis system for a substation in Laver Park of Lianyungang is proposed. Finally, it is verified that the design has the ability to reduce the data transmission and raise the level of fault processing through the abnormal state diagnosis of transformer oil chromatogram in substation.

Analysis of Total Hydrocarbon Exceeding Standard in Oil Chromatogram of a 500kV Main Transformer

Oil chromatographic analysis is widely used in transformer fault diagnosis However, the problem of excessive total hydrocarbons in the oil chromatogram caused by the failure of the transformer submersible pump is different from the failure of the transformer body. Technicians need to be able to accurately identify these two types of failure. For this problem, this article proposes a method of judging by manually starting and stopping the submersible pump and monitoring the change law of the transformer chromatographic data. This article first finds out suspicious submersible pumps through current data. Subsequently, the operator starts and stops the submersible pump and monitors the change law of the transformer chromatographic data. From this, the correlation between the start or stop of the submersible pump and the chromatographic data was found. Finally, the effectiveness of this method is verified by the submersible pump disassembly inspection and simulated live test.

Online Monitoring Data Processing Method of Transformer Oil Chromatogram Based on Association Rules

AbstractThe oil chromatography online monitoring system can monitor the insulation status of power transformers continuously and real‐time. The accuracy of its detection data directly affects the stable operation of the transformers. Aiming at the problem of abnormal data in the current transformer online monitoring data set, this paper proposes an online oil chromatographic data processing method based on association rules and support vector regression (SVR) analysis. First, using piecewise linearization to convert numerical variables into Boolean variables, and then exploring gas indicators with strong correlations in oil chromatogram. Then, using the improved box plot method to detect the abnormal value points in it, and distinguish the data of different abnormal patterns based on the association rules. Finally, the advanced particle swarm optimization support vector regression (APSO‐SVR) algorithm is used to repair the data to improve the credibility of the data set. Using actual transformer oil chromatographic monitoring data for testing, the results show that the proposed data processing method can effectively improve the accuracy of oil chromatographic online monitoring data. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

Health Assessment and Fault Diagnosis of Substation Equipment Based on Digital Twin

The equipment safety of substation is related to the normal operation of substation and even distribution network. In this paper, the condition monitoring and fault diagnosis of key equipment in substation are realized through the introduction of artificial intelligence algorithm and random matrix theory. A large number of PRPD spectrums are obtained by point tracing simulation of the measured PRPD spectra of switchgear. The characteristics of the spectra are designed and extracted to train the PRPD pattern recognition modelling and the accuracy of the test set of the model is 97%. Based on the random matrix theory, whether the oil chromatogram data generated by transformer operation is abnormal is monitored on-line. Through big data analysis, the equipment status is accurately evaluated and the type, position and severity of defects are accurately evaluated. The health assessment and fault diagnosis of substation equipment based on digital twin improves the intelligence and efficiency of substation equipment monitoring.

Study on Chromatographic Condition Assessment of Transformer Oil Based on Random Forest Model

In order to solve the problem that the accuracy of transformer condition assessment based on oil chromatographic data is not high, this paper adopts random forest to evaluate transformer state. In order to prevent the attribute values carried by the decision tree of the basic unit in the evaluation model from being too few and thus affecting the evaluation accuracy. The ratio of H2, CH4, C2H6, C2H4, C2H2, total hydrocarbon and various characteristic gases is used as the characteristic quantity, a stochastic forest optimization model for oil chromatography state assessment was constructedimmediately following the heading. It is compared with BP neural network and SVM, the test results of field oil chromatogram data show that the accuracy of random forest state assessment is 88.5%, which is better than BP and SVM, and the random forest assessment model has faster assessment speed, This paper provides technical support for the fast and accurate condition assessment of transformer.

Transformer Operating State Monitoring System Based on Wireless Sensor Networks

Transformer operating state prediction is an important module of the transformer operating state maintenance system. Since the analysis of dissolved gas in oil is the prerequisite for realizing the analysis of transformer operating status, the key to predicting the transformer operating status is to predict the content of dissolved gas in oil. Before optimizing the parameters <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula> of the improved grey prediction model GM(1,1,B), this article determines that the average relative error of the model fitting is the objective function. It is stipulated that the search space for the optimal solutions of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula> are both [0~1], and the hybrid algorithm of genetic algorithm and particle swarm optimization is used to optimize the model parameters <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\alpha $ </tex-math></inline-formula> and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula> . By analyzing the characteristics of different types of abnormal values in transformer online monitoring data such as oil chromatogram and oil temperature, a fast analysis and detection method of online monitoring data stream based on multivariate time series and correlation analysis is proposed. For multi-dimensional monitoring data, from the perspective of data association and time series analysis, a sliding time window is used to record the occurrence time and type of abnormal points, establish a judgment model for candidate abnormal data sets, and use clustering algorithms to analyze candidate abnormalities. The data collection performs comprehensive abnormality judgment of multi-dimensional data. Experiments show that this method can detect abnormal operating states in online monitoring data streams in real time, and has high application value.

Chemical Composition, Antioxidant and Antibacterial Activities of Essential Oil From Cymbopogon densiflorus (Steud.) Stapf Flowers

This study reports, for the first time, the chemical composition and biological activity of essential oil from Brazilian Cymbopogon densiflorus flowers. Thirty chemical compounds were identified by gas chromatography coupled with mass spectrometry (GC/MS), corresponding to 95 % of total compounds from an essential oil chromatogram obtained by gas chromatography-flame ionization detection (GC-FID ). The essential oil was mainly composed of cis-p-mentha-1(7),8-dien-2-ol (26 %), trans-p-mentha-1(7),8-dien-2-ol (18 %), trans-p-mentha-2,8-dien-1-ol (13 %) limonene (9 %), cis-p-mentha-2,8-dien-1-ol (7 %), cis-carveol (7 %) and carvone (5 %). The identity confirmation of the major compounds was performed by 1H/13C heteronuclear single-quantum coherence nuclear magnetic resonance (HSQC NMR). The essential oil exhibited a weak antioxidant activity by the DPPH method and a wide spectrum of antimicrobial activity against the pathogenic bacterial strains tested, showing some efficacy against 7 of the 10 strains with the greatest inhibition observed with the Gram-negative bacterium Shigella sonnei.

Theoretical study of engine oil chromatogram formation using the drop sample method

Theoretical study of engine oil chromatogram formation using the drop sample method

Theoretical study of motor oil chromatogram in express diagnostics using the drop test

The quality and compliance with the requirements of motor oils used in operation is one of the key factors determining durability and reliability of the internal combustion engine (ICE). The operating conditions of motor oils in ICE have changed significantly with an improvement in the design of the engine, the increase in power, the increase in pressure in cylinders and the change in the torque of the crankshaft. The requirements to motor oils during operation are constantly increasing, the specified terms of oil drain interval are increased. The composition of motor oils has also changed, and the technologists are adjusting their finished oil compositions to increasing requirements. Thus, it is necessary to constantly monitor the state of oil during ICE operation, the use of traditional express methods of oil quality verification is not always possible for new brands. The study considers the theoretical justification for the application of the drop test for the brands of strongly alkaline oils – Vanellus C6 Global “BP” (U) 15W-40 and Neste Tyrbo LXE.

Determination of triacylglycerols and fatty acid composition ofChilopsis linearisseed oil by reverse-phase high-performance liquid chromatography

In the present work, the compositions of the 27 triacylglycerols (TAGs) as well as fatty acid composition of Chilopsis linearis seed oil were determined by reverse-phase high-performance liquid chromatography (RP-HPLC) with diode array and mass spectrometric detections. It was shown that the main conjugated acid in the seed oil is a catalpic acid, (9E,11E,13Z)-octadeca-9,11,13-trienoic acid, while two unusual fatty acids have the parameters satisfying the literature data for (10E,12E)-octadeca-10,12-dienoic and (9E,12E)-octadeca-9,12-dienoic acids. For the two conjugated acid substituents the isosbestic point (at 234 nm) was found and was used to calculate the ratios of TAGs with different chromophores in the oil, taking into account the peak areas on the oil chromatogram.

Production mechanism of single excessive hydrogen in current transformers: A reactive molecular dynamics simulation study

The present work aims at investigating the single excessive hydrogen (SEH) mechanism in the current transformers (CTs) by reactive force field molecular dynamics (ReaxFF MD) simulations. The chemical components in the CTs, i.e. mineral insulating oil, insulating paper, nickel crystal and moisture were established. Temporal evolutions of dissolved-gas-analysis (DGA) characteristic gases were captured reasonably in the mono-component, dual-component and multi-component simulation systems under electrical stress. And the sources of H2 molecules were traced as well as their dehydrogenation reactions. In addition, the oil chromatogram and dismantle experiments were performed to verify the dynamics simulations. The relative contents of the gas productions in the all-component composite simulation system were well agreed to that from oil chromatogram measurement. The results identified that the nickel-catalyse dehydrogenation from insulating oil played the dominant role in SEH phenomenon. The Nickel promoted the generation of H2 by seizing H atoms from oil molecules under the imposed electric field. In the process of dehydrogenation, the insulating oil molecules reacted to produce macromolecule wax-like solid unsaturated hydrocarbons, which were found in the insulating paper of a dismantled CT.

Case‐based power transformer diagnose model using nonlinear mapping of oil chromatography

In this study, a case-based diagnostic model of a power transformer for oil chromatography is proposed. A nonlinear normalised mapping method is proposed for achieving ideal distribution characteristics of oil chromatogram gas in the case base. A similarity degree algorithm is proposed to calculate the similarity degree in the target spatial domain between the case to be diagnosed and the cases in the case base. A threshold method is proposed to determine the number of similar cases. Also, a method for calculating the weight of the diagnosis result according to the case distribution in the case base is proposed. The diagnostic method proposed is used to deploy the diagnostic system on the Internet. Defeat diagnosis conclusions of two transformers by the method and system in this paper are consistent with the disintegration results. It can be concluded that the proposed method has important practical application value in engineering.

Effects of experimental operations on the Fischer-Tropsch product distribution

The present study provides insight into the effect of experimental operations on the Fischer-Tropsch synthesis (FTS) product distribution by combining experimental and theoretical analyses of the process. Experimental errors originated from GC data processing and product collecting conditions are addressed here based on the experimental data obtained using commercial iron-based catalyst in a tubular fixed-bed reactor. A corrected area normalization method, which is a combination of the area normalization and simulated distillation, is proved to be an accurate and convenient method for FTS heavy oil chromatogram quantification. The flash loss from the hot trap and the cold trap is found to be negligible under the normal operating conditions. However, water may be condensed remarkably in the hot trap at low temperature and wrapped by wax. In addition, the selectivity of the high-carbon-number alcohols will be seriously underestimated at low temperature of the hot trap. The FTS product distributions under a wide range of reaction conditions are exhibited.

Transformer Oil Chromatographic Analysis of Data Anomalies Caused by Harmonics

According to the 66kV transformer blackout phenomenon, the oil chromatogram data analysis, found that the transformer existed temperature (676 °C) and low energy discharge defect. Through measuring the harmonic content to and analyzing the load condition, test results show that the grid was injected harmonic currents by the substation non-linear loads, its 5 times,7 times, 11 times, 13 times harmonic were higher than the state standards, this shows that the harmonic is the cause of the chromatographic data of transformer oil abnormal

Screening of Biosurfactant-Producing Thick Oil-Degrading Bacteria and its Degradation Effect

Four bacterias were separation and purification from oil well produced water of Daqing 9 factory, optimizing two degrading bacterias 17# and 7#. Through fermentation cultivation, observing their growth and metabolism laws and the viscosity of crude oil before and after the action. Results showed that the strains 7# and 17# of thick oil degradation rate were 84.9%, 73.9% respectively. Through the experiment contrasts, give the crude oil composition changes and chromatogram of the strains 7# before and after the action. Finally, choose strains 7# as thick oil-degrading bacteria for industrial fermentation.