Oil Monitoring Research Articles

Classification and prediction of wear state based on unsupervised learning of online monitoring data of lubricating oil

With the development of the times, the demand for high efficiency and reliability of machine performance in China’s industry has become higher than ever before, and the traditional equipment condition evaluation method has also encountered a huge challenge. As an important branch of machine learning, cluster analysis is widely used in fault diagnosis and other fields because of its advantages of no prior knowledge and massive data processing. This paper introduces the concept of principal component analysis and K-means method based on time series in the field of oil data analysis. Through the test data on the oil monitoring data of the steam turbine unit in the power plant, the condition evaluation and classification of the equipment are carried out, among which the classification effect of 6μm particles, dielectric constant and 4μm particles is very obvious, and the water content is relatively obvious, which can basically distinguish each state. At the same time, on the basis of feature extraction, use the special cyclic neural network (RNN) in deep learning-long and short-term memory network (LSTM) to build a model of data for data prediction, under the powerful ability of LSTM to process temporal data, they have unearthed more irregular and non-linear trends in a large amount of historical data, and achieved better prediction results than traditional methods (ARIMA). Through clustering and prediction of lubrication parameter data, it can realize early warning and abnormal diagnosis of lubrication status and reduce damage to machinery and equipment.

A Novel Impedance Micro-Sensor for Metal Debris Monitoring of Hydraulic Oil

Hydraulic oil is the key medium for the normal operation of hydraulic machinery, which carries various wear debris. The information reflected by the wear debris can be used to predict the early failure of equipment and achieve predictive maintenance. In order to realize the real-time condition monitoring of hydraulic oil, an impedance debris sensor that can detect inductance and resistance parameters is designed and studied in this paper. The material and size of wear debris can be discriminated based on inductance-resistance detection method. Silicon steel strips and two rectangular channels are designed in the sensor. The silicon steel strips are used to enhance the magnetic field strength, and the double rectangular detection channels can make full use of the magnetic field distribution region, thereby improving the detection sensitivity and throughput of the sensor. The comparison experiment shows that the coils in series are more suitable for the monitoring of wear debris. By comparing and analyzing the direction and the presence or absence of the signal pulses, the debris sensor can detect and distinguish 46 µm iron particles and 110 µm copper particles. This impedance detection method provides a new technical support for the high-precision distinguishing measurement of metal debris. The sensor can not only be used for oil detection in the laboratory, but also can be made into portable oil detection device for machinery health monitoring.

Gas and water content’s monitoring of crude oil in pipeline during production in Arctic shelf

The gradual depletion of onshore oil and gas fields and the aggravation of the global energy crisis lead to intensive development of oil and gas resources on the continental shelf, in particular, the Arctic shelf. When monitoring of oil production from wells in the conditions of Arctic shelf, it is necessary to measure free gas concentration and water content in oil-gas-water mixture in a pipeline. The paper discloses a method for non-contact monitoring of gas concentration and the water cut of products of oil wells in a pipeline, as well as presents the results of industrial studies of the interaction between gamma radiation and a flow of oil-gas-water mixture. Conclusions are formulated about the advantages of using and the feasibility of using this method for measuring the concentration of free gas and the water content in the oil-gas-water mixture during oil production.

Application of 4D full waveform inversion in the CO2 storage monitoring: a synthetic example

The time-lapse seismic method is a technique that uses repeated seismic surveys to monitor the dynamic change of reservoir parameters. Nowadays, it has been widely used in the dynamic monitoring of marine oil and gas reservoirs. It could also be used for monitoring the CO2 injection at CO2 geological storage sites. It can give us a clear image of the injected CO2 in the reservoir. Seismic waveform inversion is a relatively new method for time-lapse monitoring. In this paper, we test the double difference full waveform inversion method on a synthetic 4D seismic data set. The preliminary results show that it is possible to use 4D full waveform inversion method to monitor the velocity changes caused by CO2 injection.

Classification of Friction and Wear State of Wind Turbine Gearboxes Using Decision Tree and Random Forest Algorithms

Abstract Based on oil monitoring technology to collect friction and wear parameters, the failure modes of key friction pairs in wind turbine gearboxes can be evaluated and classified. However, the collected data of failures caused by friction and wear are generally small, which limits the application of machine learning in the monitoring or evaluation of the critical friction pairs of wind turbine gearboxes. To verify the feasibility of machine learning in this application, algorithms including decision tree (DT), random forest (RF), k-nearest neighbors (k-NN), and support vector machine (SVM) are implemented, in the context of a small dataset of 424 samples of normal, adhesive, fatigue, and cutting wear for outcome classification. Compared with k-NN and SVM, DT and RF perform better on both training and test samples. The two models identified the key factors and their quantified values associated with failure state, including ferromagnetic particles, viscosity, iron content, and external hard particle silicon. The classifiers developed in this work classified failure state with an average accuracy of 96%, thus offering an accurate decision support tool for classification and evaluation of the friction pair wear state of wind turbine gearboxes.

A Novel Application of the Cross-Capacitive Sensor in Real-Time Condition Monitoring of Transformer Oil

This article presents the novel application of a cross-capacitive sensor for monitoring insulation degradation of transformer oil. The condition of insulating oil is determined by measuring the variation of the moisture content and furfural (2-FAL) concentration in the range of 0–60 ppm. The moisture and 2-FAL are two important by-products formed due to the degradation of cellulose paper used for insulating transformer winding. In addition, a small concentration of moisture is always trapped in oil as well as in paper. An accurate and precise capacitive sensor is developed that uses the cross-capacitive structure proposed by Thomson and Lampard. The sensor is developed using bulk brass material and it consists of four identical brass electrodes that are separated by very small gaps. The sensor has been tested at different concentrations of moisture, and 2-FAL in four insulating oil samples that are commonly used in power transformers, and results are compared by a reference meter. The maximum accuracy of the sensor with respect to the commercial meter is 0.77% and the air cross-capacitance value differs calculated absolute capacitance value by 3%. The calibrated response shows a maximum error of 2%. The output of the sensor is highly precise (±0.0026% for moisture, ±0.0028% for 2-FAL), fast, drift-free, and the maximum nonlinearity of the response is close to 2%. The maximum standard deviations (SDs) for the measurement of the mineral oil moisture and 2-FAL concentrations are 0.025 and 0.023, respectively. The sensor response is independent of temperature variation.

QUANTUM BIOECONOMICS AND ECOMONITORING OF OIL AND GAS FIELDS ON THE EXAMPLE OF SIMULATION OF PROCESSES ON THE SUPERCOMPUTER STEGANOGRAPHIC SOFTWARE AND TECHNOLOGICAL COMPLEXES WITH THE SYSTEM OF DISTRIBUTED REGISTERS

The developments in the field of quantum bioeconomics and environmental monitoring of oil and gas fields are presented. As an example, the modeling of processes on the supercomputer steganographic software and technological complex with the system of distributed registers is considered.

An Ultrasensitive Debris Microsensor for Oil Health Monitoring Based on Resistance–Inductance Parameter

An ultrasensitive debris sensor based on microfluidic technology is introduced in this article. The microsensor not only achieves the traditional inductance detection, but also proposes a resistance detection method based on coil. The magnetic field distribution in the detection region was obtained by simulation, and the magnetization and eddy current effects of metal particles in harmonic magnetic field were simulated. The frequency characteristics and signal characteristics of inductance and resistance detection were studied through experiments. High-frequency excitation can enhance the eddy current effect inside the metal particles, thereby helping to improve the resistance detection sensitivity, enhance the inductance detection effect of nonferromagnetic metal particles, and reduce the inductance detection effect of ferromagnetic metal particles. The research results showed that inductance parameter has stronger detection ability for ferromagnetic metals, and resistance parameter has stronger detection ability for nonferromagnetic metals. According to the characteristics of inductance and resistance signals, the accurate distinction of metal debris property and size can be realized. And the size measurement error caused by the debris shape can be reduced by the judgment method based on two parameters. This impedance detection based on inductance and resistance parameters provides a new method for high-sensitivity monitoring of metal debris. The debris microsensor can be used as a sensing element of portable oil monitoring devices, and provide technical support for health assessment, state warning, and fault diagnosis of mechanical equipment.

Abnormal identification of lubricating oil parameters and evaluation of physical and chemical properties based on machine learning

This paper firstly proposes an abnormality identification model for online oil monitoring parameters. The SVR model was established to predict the output power, and the information entropy of the deviation between the predicted value of the regression model and the actual monitoring value was used to identify the abnormal parameters of the oil. The physical and chemical properties of the oil was evaluated and predicted comprehensively. Principal component analysis (PCA) was used to eliminate the correlation between parameters, and then the deviation degree of each principal component is calculated after feature transformation. After adding the deviation degrees of each principal component according to their weights, the performance evaluation index of the oil is obtained. At the same time, a prediction model of oil performance trend based on Gated Recurrent Unit is proposed. The feasibility and applicability of this model are verified by comparing with the results of LSTM neural network and ARIMA model. The evaluation of the physical and chemical properties of the oil can detect the deterioration of the oil condition at the early stage, avoiding or reducing accidents, so as to ensure the safe and reliable operation of the unit.

Monitoring of total oil and grease in discarded water using data science

Monitoring of total oil and grease in discarded water using data science

Benthic monitoring of oil and gas offshore platforms in the North Sea using environmental DNA metabarcoding.

Since 2010, considerable efforts have been undertaken to monitor the environmental status of European marine waters and ensuring the development of methodological standards for the evaluation of this status. However, the current routine biomonitoring implicates time-consuming and costly manual sorting and morphological identification of benthic macrofauna. Environmental DNA (eDNA) metabarcoding represents an alternative to the traditional monitoring method with very promising results. Here, we tested it further by performing eDNA metabarcoding of benthic eukaryotic communities in the vicinity of two offshore oil and gas platforms in the North Sea. Three different genetic markers (18S V1V2, 18S V9 and COI) were used to assess the environmental pressures induced by the platforms. All markers showed patterns of alpha and beta diversity consistent with morphology-based macrofauna analyses. In particular, the communities' structure inferred from metabarcoding and morphological data significantly changed along distance gradients from the platforms. The impact of the operational discharges was also detected by the variation of biotic index values, AMBI index showing the best correlation between morphological and eDNA data sets. Finally, the sediment physicochemical parameters were used to build a local de novo pressure index that served as benchmark to test the potential of a taxonomy-free approach. Our study demonstrates that metabarcoding approach outperforms morphology-based approach and can be used as a cost and time-saving alternative solution to the traditional morphology-based monitoring in order to monitor more efficiently the impact of industrial activities on marine biodiversity.

Underwater sensor networks: ‘Comparative analysis on applications, deployment and routing techniques’

In today's scenario, underwater wireless sensor network (UWSN) has raised as a most famous research areas for the researchers due to its advancement in the real world. In UWSNs, the sensor nodes sense the environment, and then this sensed information is conveyed to one of the sink node and finally to the base station for processing. It is a known fact that nearly about 70% of the total earth surface is filled with the water. It is difficult for the humans to get the valuable information from the seabed. Major applications of UWSN are marine surveillance, sea monitoring, deep sea archaeology, oil monitoring etc. Major goal of this work is to provide the broad survey of underwater sensor networks with its application, deployment techniques and routing algorithms. This study also provides a comparative analysis of the deployment techniques and routing algorithms that will aid the researchers to find the research gaps in the deployment and routing techniques. Moreover, some of the UWSN applications also reviewed, which provides varied and valuable information about the UWSN approach. This study presents an overview about the conventional technologies of UWSN and its major focus is to present the significant research approaches towards the UWSNs’ applications, deployment techniques, and routing process.

Design and analysis of photonic crystal fiber plasmonic refractive Index sensor for condition monitoring of transformer oil

This paper presents an octagonal photonic crystal fiber based plasmonic refractive index (RI) sensor using graphene to measure the moisture content in transformer oil. For better insulation, moisture content in transformer oil needs to be measured, as the moisture content degrades the insulation property of the oil. Basically, the proposed sensor is able to detect the change in RI of the oil as the moisture content changes the RI. This work is numerically simulated by a finite element method-based simulation tool and the simulation results are processed using a MATLAB environment to understand the performance. Using the proposed sensor, the maximum possible amplitude sensitivity can be obtained as 31,240 RIU-1 and 30,830 RIU-1 for the x- and y-polarized modes, respectively. Besides, the proposed sensor has also found the figure of merit (FOM) to be 5,000. Both the results are found to be highest to date (to the best of my knowledge). The novelty of this work is the idea of measuring the moisture content of transformer oil using graphene plasmonic RI sensor, the high FOM, and the highest amplitude sensitivity.

Reliability Test of Dual-Clutch Automatic Transmission based on Oil Monitoring

In this paper, the reliability test of dual clutch automatic transmission is studied by using oil analysis technology. The performance of dual-clutch automatic transmission oil (DCTF) is evaluated by monitoring the kinematic viscosity, acid value, base number, water content and contamination degree of DCTF, combining with the changing trend of its index. The type and composition of abrasives are determined, and the wear form, cause and degree of friction pairs of transmission are revealed by using oil ferrography analysis technology and Ferrography microscopy, which provides a theoretical basis for the friction design of transmission system.

A Real Time Engine Oil Monitoring System for Diagnosis of Lubricant using IoT Network

In the modern days, Internet of Things (IoT) is smart communicating approach and creates an energetic impression in future of automobile industry. The advancement of IoT innovation in each field can be joined with the rising occasions setting off a requirement for a superior human way of life and its applications are vast and innumerable. One such application can be implied for the automobile industry to real time monitor the engine lubricant because in India, automobile mechanics still use conventional techniques of engine lubricant supervision. So in this paper, we present, an IoT technology based a real time Engine Oil Monitoring (EOM) System for diagnosis of engine lubricant. The main objective of this research paper is to reduce the human effort and to provide a smart sensing approach in automobile industry for maintaining real time engine oil conditions. EOM system is designed with the help of Arduino Nano with sensor devices named as Light Dependent Resistor (LDR) sensor for oil quality, LM35-Temperature sensor for temperature and Ultrasonic Sensor for oil level measurement in engine. Real time testing results shown in the connected display unit and experimental results of proposed EOM system using IoT network provides an efficient diagnosis results. EOM system is working properly that is observed in the experimental analysis section for two different scenario such as 10W-50 4T Scooter Engine Oil-Honda Activa 125 (1L) and 10W-30 Synthetic Engine Oil for Petrol Cars (3.5 L).

Determination of the Place Depressurization of Underground Pipelines in the Monitoring of Oil and Gas Enterprises

Analytical correlations of mathematical model that characterizes the processes of development of corrosive cavity on the surface of underground metallic pipeline are analysed. A pipeline in the environment of moist soil with solution of electrolyte is placed.In the top of cavity a crack appears and translates the system “underground pipeline (UP) – pumping station (PS)” in the state of depressurization.A new approach is proposed for diagnosing places of underground pipeline depressurization on the basis of two types of devices: pressure sensors and non-destructive testing devices, with the help of which we measure potentials and corrosion currents in surface defects.The presence of only pressure sensors makes it possible to set the coordinates of depressurization with a large error – 20…25%. Diagnosis of the pipeline only by devices BVS-K, VPP-M (at the first stage) allows to reveal surface defects. But this information is not enough for a qualitative experiment, as shown by the qualimetric quality criterion. Taking into account the pressure data in the second stage allows to determine which of the defects is the leakage point.A test example for the distance L1 = 6 km from the pumping station of the pipeline is considered. The results of the experiment are used for the example and the growth time of the corrosion crack t = 0.62 year is established.On the basis of computational experiment the errors of estimating of crack growth time t and coordinates of the leakage points was established. They present 5…7 %. Based on the method of neural networks, the main informative parameters for determining the places of depressurization on the surface of the underground pipe are estimated. A method for estimating the gas pressure change in the vicinity of the crack after depressurization of the pipeline was proposed. The principles of determining the limit values of the parameters of the system “pipeline – pumping station” taking into account the criteria of quality and strength of the metal are formulated.

QPCR-based assessment of microfaunal indicators of oil for monitoring benthos around oil and gas platforms

Today's benthic offshore biological monitoring of oil & gas (O&G) activities relies on macrofauna taxa enumeration. For the future, analysis of DNA isolated directly from sediments holds great potential for multi-trophic biodiversity surveys and the monitoring of a larger spectrum of benthic taxa, including micro-fauna. Here, we evaluate more specifically the potential of microfauna-specific gene quantification in relation to both petroleum-related discharge compounds and other seafloor environmental properties. We carried out this evaluation using sediment samples collected at drilling Region III on the Norwegian continental shelf where DNA metabarcoding of eukaryotic diversity was already performed. Generally, the quantification of microfauna indicator taxa related well to the gradient of contamination on the seafloor. Contrary to eukaryotic Euplotida, metabarcoding data and qPCR numbers for indicative prokaryotic taxa showed the same relationship to offshore contaminants (both showed positive relationship). We found absolute numbers of SSU rRNA gene copies of (1) Dinophyceae, Bacillariophyceae and Alcanivorax were correlated with the level of petroleum-related compounds but not with other environmental variables, (2) bacteria closely related to Shewanella were correlated with the concentration of Ba, PAH, as well to percent of gravel, (3) Desulfobacteriales correlated with petroleum-related contaminants, but as well with percent of gravel and grain size.Findings from our study suggest that biomonitoring surveys of O&G activities on benthos could benefit from quantification of specific micro-fauna indicators that is simpler and faster than the methods currently used for impact assessment of benthos.

Determination of the Place Depressurization of Underground Pipelines in the Monitoring of Oil and Gas Enterprises

Determination of the Place Depressurization of Underground Pipelines in the Monitoring of Oil and Gas Enterprises

Forecasting Total Oil and Grease in produced water using Machine Learning methods in an oil extraction plant

On-line monitoring of Total Oil and Grease (TOG) in produced water of offshore platforms has been a challenge over the past decades. There are difficulties imposed by the sensitivity to various factors (e.g., fluid temperature, pressure, gas presence, oil type, drop size, process flow). This paper proposes a model based on Machine Learning that estimates, in real time, the approximated Total Oil and Grease value from instruments and valves data of water treatment process. Neural Networks, Support Vector Machines, Regression Tree and Bagged Trees models have been trained to infer TOG values. The proposed model was applied to an offshore oil extraction plant. The results obtained from the model were similar to those obtained by the on-site lab measurement, with the Bagged Trees having presented the best results, reaching a Mean Absolute Error (MAE) by 1.15 mg/L. The results suggest that the model used can be used for on-line detection of imminent risk situations of TOG contamination.

변압기 오일내 직접 삽입형 ZnO NRs:MoS2 기반의 저항형 습도센서 개발

A resistive humidity sensor was developed based on 3 dimensional (3D) ZnO nanorods (NDs):MoS2 sensing film and wheatstone bridge circuitry for real time monitoring of transformer insulation oil. Wheatstone bridge circuitry was employed to minimize interference due to ambient temperature changes, and 3D sensing film to enhance the sensitivity and the minimum detection resolution. A thick SiO2 passivation layer was covered all 3D structures except for the sensing film to eliminate any contacts with transformer insulating oil during measurement for the purpose of long term stability. The process for the 3D ZnO:MoS2 structures was optimized by varying the solution composition ratio, temperature, and growth time. The completed sensors were characterized in both air and oil and then its properties were compared. The evaluated sensitivity of the sensor in the air was about 15 mV/%RH, and little changes are observed with respect to ambient temperature variations. The sensitivity of the sensor in oil was evaluated to be about 6.8 mV/%RH, slightily lower than the one in air. Long term stability in the sensor performances and high sensing resolution were observed from the developed sensor.