Browse
Records Added in 2023
Records added in 2023
Filter by month: January | February | March | April | May | June | July | August | September | October | November | December
24492. LAPSE:2023.12417
Design and Implementation of a Wireless Charging System Connected to the AC Grid for an E-Bike
February 28, 2023 (v1)
Subject: Process Design
Keywords: e-bikes, forward converter, inductive power transfer, wireless charging
This paper aims to design an IPT for wireless charging of an e-bike and to control the charge of the e-bike from the primary-side. Optimum IPT design has been made according to the 36 V battery bank requirements. The no-load condition test has been performed before charging started in the IPT system connected to the AC grid. The primary-side DC-link voltage of 4−5 V required for this test is provided by the designed forward converter. The charge control has been also made from the forward converter on the primary-side. For this, the forward converter’s operation in peak current mode (PCM) has been used. Finally, a prototype has been implemented that works at a maximum DC/DC efficiency of 87.52% in full alignment and 83.63% in 3 cm misalignment. The proposed control algorithm has been tested in this prototype at different load stages.
24493. LAPSE:2023.12416
Methane Adsorption Properties in Biomaterials: A Possible Route to Gas Storage and Transportation
February 28, 2023 (v1)
Subject: Materials
Keywords: agricultural wastes, gas adsorption, methane hydrate, natural gas storage
Methane can be stored in biomaterials rapidly in hydrate form with low energy consumption. Considering the high cost of biomaterials (vegetables or fruits), agricultural wastes may be more practical. In this work, the characteristics of methane storage in two low-cost agricultural wastes, eggplant, and static water, are studied and compared. The methane adsorption rates and capacities were greatly enhanced in three biomaterials compared with that in the static water, while only corncob pith maintained relatively high gas adsorption capacity (72 v/v) and adsorption rate (~0.0300 MPa/min) in repeatable gas adsorption-desorption processes. Further investigations on the gas adsorption behavior in the corncob pith revealed that the porous structure of corncob pith generates larger specific surface areas, providing more nucleation sites for hydrate nucleation. In addition, the hydrophobic and hydrophilic performance of corncob pith components also affect the hydrate formation. The porous str... [more]
24494. LAPSE:2023.12415
The Characteristics of Gliding Arc Plasma and Its Activating Effect for Ramjet Combustion
February 28, 2023 (v1)
Subject: Process Design
Keywords: discharge characteristics, gliding arc discharge, ignition and assisted combustion, kerosene activate, ramjet
In order to improve the combustion performance of a ramjet under low temperature and pressure, a gliding arc plasma actuator was designed based on a typical evaporation flameholder. The discharge characteristics, as well as the activating effect of single-channel and three-channel gliding arc plasma under different carrier gas flow rates, were studied. Results show that with the increase in the carrier gas flow rate, the average duration of the gliding arc discharge becomes shorter, while the average power increases, and the specific input energy decreases. Compared with single-channel discharge, three-channel discharge has higher discharge power and energy injection rate, which makes a bigger actuated space. Through gliding arc plasma, the kerosene is cracked and H2, CH4, C2H2, C2H4, C3H6 and other small molecule components are produced. For three-channel gliding arc discharge, the effective cracking rate and the production rate of each component are higher than those of the single-ch... [more]
24495. LAPSE:2023.12414
Improving the Efficiency of Curved Wells’ Operation by Means of Progressive Cavity Pumps
February 28, 2023 (v1)
Subject: Process Operations
Keywords: centralizer, directional wellbore profile, progressive cavity pump, reduced disc, sucker-rod string
This paper proposes a solution to the problem of improving the reliability of the operation of progressive cavity pump units in deviated and directional wells. High dogleg severity significantly contributes to rod breakage; rods often break close to the “elbows” with a dogleg severity of 2 deg/10 m or higher. Statistical analyses were used to identify the frequency of failures and their impact on the reliability of a PCP unit. The design layout and mathematical model for pump rods’ torsional vibrations in the curved section of a wellbore were developed. A simulation of the curved section was performed. This article provides the basic formulas needed to design a rotating rod string using two reduced discs. The creation of an additional crooked section resulted in multiple reductions in the “resonant” rotational speed and rigidity in the mathematical model. Determining the moment of inertia of the reduced discs’ mass made it possible to determine the sucker-rod string’s stiffness, the ci... [more]
24496. LAPSE:2023.12413
Influence of Densification on the Pyrolytic Behavior of Agricultural Biomass Waste and the Characteristics of Pyrolysis Products
February 28, 2023 (v1)
Subject: Environment
Keywords: Biomass, densification, environmental chemistry, pyrolysis, volatile-char interaction
TG/FT-IR techniques, UV-spectroscopy, microwave extraction, XRD and SEM were used to study how densification of the three types of agricultural biomass wastes (wheat straw, soft wood, and sunflower husk) changes the composition and structure of their pyrolysis products. It was determined that densification changes the composition of volatile products of pyrolysis at the temperature of 420 °C: sunflower husk emits 4.9 times less saturated and unsaturated hydrocarbons and 1.9 times less compounds with carbonyl group; soft wood emits 1.8 times more saturated and unsaturated hydrocarbons and compounds with carbonyl groups and 1.3 times more alcohols and phenols; and wheat straw emits 2 times more compounds with carbonyl groups. These changes are probably caused by the differences in interaction of formed volatiles with the surface of chars. These differences can be caused by distinct places of cumulation of inorganic components in the densified samples. In the densified char, the inorganic... [more]
24497. LAPSE:2023.12412
Film Boiling Conjugate Heat Transfer during Immersion Quenching
February 28, 2023 (v1)
Subject: Energy Systems
Keywords: boiling curve, conjugate heat transfer, eulerian two-fluid model, immersion quenching, partitioned coupling, stability
Boiling conjugate heat transfer is an active field of research encountered in several industries, including metallurgy, power generation and electronics. This paper presents a computational fluid dynamics approach capable of accurately modelling the heat transfer and flow phenomena during immersion quenching: a process in which a hot solid is immersed into a liquid, leading to sudden boiling at the solid−liquid interface. The adopted methodology allows us to couple solid and fluid regions with very different physics, using partitioned coupling. The energy equation describes the solid, while the Eulerian two-fluid modelling approach governs the fluid’s behaviour. We focus on a film boiling heat transfer regime, yet also consider natural convection, nucleate and transition boiling. A detailed overview of the methodology is given, including an analytical description of the conjugate heat transfer between all three phases. The latter leads to the derivation of a fluid temperature and Biot... [more]
24498. LAPSE:2023.12411
Methodology for the Estimation of Electrical Power Consumed by Locomotives on Undocumented Railroad Tracks
February 28, 2023 (v1)
Subject: Energy Systems
Keywords: energy consumption, energy generation, estimation, locomotive, railway track geometry
The energy consumption estimation of a locomotive for a particular route is important for the selection of a locomotive technology, the improvement of the energy management system, the evaluation of the locomotive’s potential energy generation, among others. The methodologies reported in the literature usually assume that the information of the railway track is available; however, in some cases, the track information is incomplete, not available, or the route is still in a planning stage. Therefore, this paper proposes a methodology to estimate the energy consumption and the potential energy generation of a locomotive when the railway track information is not available or incomplete. The methodology begins by extracting the main technical information of the locomotive to be analyzed. Then, the route is traced on Google Earth with steps of 100 m and the obtained information is processed to generate the longitude, latitude, elevation, and distance of the points along the route. From such... [more]
24499. LAPSE:2023.12410
Analysis of the Dynamic Characteristics of the Pump Valve System of an Ultra-High Pressure Liquid Hydrogen Reciprocating Pump
February 28, 2023 (v1)
Subject: Modelling and Simulations
Keywords: dynamic grid, liquid hydrogen, preload force, reciprocating pump, valve
This paper developed a 3D physical model of the hydraulic end of a high-pressure liquid hydrogen reciprocating pump to research the dynamic characteristics of the pump valve system. Based on dynamic mesh technology, we analyzed the coupling characteristics of pump valve and plunger motion and spool force considering the leakage model, closure model of valve gap, and compressibility of liquid hydrogen. Further, we analyzed the effect of the spring stiffness and preload force on the laws of motion of the pump valve. Finally, a liquid hydrogen pressurization test was conducted to revise the simulation model and verify the accuracy of the simulation. The results of the simulation and test show that the simulation method in this paper can simulate the liquid hydrogen pressurization process more accurately and obtain the motion law of the suction and discharge valves. Both the suction and discharge valves have an opening hysteresis angle of about 40°, and there is a strong coupling relations... [more]
24500. LAPSE:2023.12409
A Modified SOGI-PLL with Adjustable Refiltering for Improved Stability and Reduced Response Time
February 28, 2023 (v1)
Subject: Energy Systems
Keywords: phase-locked loop, processor-in-the-loop, renewable energy resources, synchronization
The controls of most power electronic inverters connected to an electrical power system (EPS) rely on the precise determination of the voltage magnitude, frequency, and phase angle at the point of common coupling. One of the most widely used approaches for measuring these quantities is the phase-locked loop (PLL); however, the precision of this measurement is affected during transients in the EPS and is a function of the type of event and the architecture of the PLL. PLLs based on the second-order generalized integrator (SOGI) are widely used in power converter synchronization, offering an adaptive or fixed-parameter prefilter with low-pass and band-pass characteristics. This article proposes a variant of the SOGI-PLL that offers improved stability and a faster response time. This is accomplished by decoupling the effect of the SOGI’s gains and adding feedback. The modification is carried out in the state space model of the SOGI. Manipulating the attenuation moves the poles of the SOGI... [more]
24501. LAPSE:2023.12408
Research on Directional Controllability of Cracking in Hydraulic Fracturing of Hard Overburden Based on Local Stress Field Intervention
February 28, 2023 (v1)
Subject: Energy Systems
Keywords: directional hydraulic fracturing, gob-side entry, hard overburden, pressure relief mechanism, roadway coal pillar
As a widely-used method of digging roadways in China, gob-side entry driving features specific advantages, such as a high recovery rate and good isolation effects. However, under the condition of hard overburden, the excessive bearing pressure of small coal pillars will easily cause serious internal damage in the coal and the run-through of the plastic zone, leading to harmful gas leakage in the goaf. Therefore, based on the engineering background of small coal pillars in the 18506 working face of Xiqu Coal Mine, this paper comprehensively adopts theoretical analysis, numerical simulation, industrial tests, and other methods, analyzes the evolution mechanism of isolated bearing and plastic fracture areas of small coal pillar under hard overburden, studies the influence law of hard overburden cutting parameters on the isolation and stability of small coal pillars, and puts forward the technology of actively cutting the top to weaken the stress concentration of coal pillars under hard ov... [more]
24502. LAPSE:2023.12407
Lattice Boltzmann Modeling of Spontaneous Imbibition in Variable-Diameter Capillaries
February 28, 2023 (v1)
Subject: Modelling and Simulations
Keywords: lattice Boltzmann modeling, pore-throat tortuosity, snap-off, spontaneous imbibition, variable-diameter capillary
Previous micro-scale studies of the effect of pore structure on spontaneous imbibition are mainly limited to invariable-diameter capillaries. However, in real oil and gas reservoir formations, the capillary diameters are changing and interconnected. Applying the lattice Boltzmann color gradient two-phase flow model and the parallel computation of CPUs, we simulated the spontaneous imbibition in variable-diameter capillaries. We explored the reasons for the nonwetting phase snap-off and systematically studied the critical conditions for the snap-off in spontaneous imbibition. The effects of pore-throat aspect ratio, throat diameter, and the pore-throat tortuosity of the capillary on spontaneous imbibition were studied. Through analyzing the simulated results, we found that the variation in the capillary diameter produces an additional resistance, which increases with the increase in the pore-throat ratio and the pore-throat tortuosity of a capillary. Under the action of this additional... [more]
24503. LAPSE:2023.12406
Experimental Investigation of Heat Transfer and Flow Characteristics of Split Natural Cooling System for Data Center Based on Micro Heat Pipe Array
February 28, 2023 (v1)
Subject: Process Design
Keywords: data center, energy efficiency ratio, heat transfer, micro heat pipe array, pressure drop, split natural cooling system
This paper presents a new type of split natural cooling system that maximizes the use of natural cold energy to significantly reduce the power consumption of the air conditioning system in data centers. A split natural cooling system module, which consisted of indoor and outdoor heat exchanger based on micro heat pipe arrays connected by liquid circulation system, was selected for experimental research. The heat transfer process and flow characteristics were analyzed under different outdoor environment temperatures, air and water flow rates, and different ratios of heat transfer components (N) of indoor and outdoor heat exchangers. To improve the utilization of natural cold energy, two kinds of heat dissipation conditions, namely room and heat channel-based, were proposed. The indoor temperature of two conditions at 28 °C and 38 °C were simulated in the laboratory at constant temperature-humidity, respectively. Results indicated that the air flow rate had a greater influence on the hea... [more]
24504. LAPSE:2023.12405
An Experimental Study of Drift Caused by Partial Shading Using a Modified DC-(P&O) Technique for a Stand-Alone PV System
February 28, 2023 (v1)
Subject: Process Control
Keywords: ARM Cortex M4 32-bit Microcontroller (STM32F407VGT6), MATLAB Simulink, modified DC-(P&O), partial shedding, PSIM
There is tremendous potential in solar energy to meet future electricity demands. Partial shading (PS) and drift are two major problems that must be addressed simultaneously to achieve the maximum power point (MPP) of a stand-alone PV system, which are discussed in this paper. Both of these factors contribute to the voltage drop due to heavy steady-state oscillation. The partial shading and drift problem are associated with severe rapid changes in the insolation. A modified drift-control perturbation and observation DC-(P&O) approach was investigated using a low-cost programmable hardware solution, i.e., the ARM Cortex M4 32-bit Microcontroller (MC) (STM32F407VGT6), with efficient embedded programming and Waijung block sets for real-time solutions. The experimental setup was accomplished on a 40-watt solar panel. It was found that the proposed method had a significant impact on drift control during abrupt changes in current and voltage caused by shading effects, with the controller con... [more]
24505. LAPSE:2023.12404
Exploring Increasing Urban Resident Electricity Consumption: The Spatial Spillover Effect of Resident Income
February 28, 2023 (v1)
Subject: Energy Policy
Keywords: average wage, China, residential electricity consumption, spatial Durbin model, spatial spillover effect
The impact of average wages on electricity consumption among urban residents in China has generated many fascinating debates for scholarly research, but only a few studies have considered the spatial spillover effect of average wages on residential electricity consumption. With the use of city-level panel data from 278 Chinese cities spanning 2005 to 2016, this preliminary study explores the impacts of the average wage on residential electricity consumption. Specifically, based on the spatial Durbin model with fixed effects, three different spatial weight matrices (the economic distance, the inverse distance, and the four nearest neighbours) are utilised to check the robustness of the results under different standards. The results show that the residential electricity consumption of each city increased during the observation period, presenting obvious spatial correlations. Secondly, the average wage of residents had a positive spatial spillover effect, which promoted the residential el... [more]
24506. LAPSE:2023.12403
Thermoelectric Generators as an Alternative Energy Source in Shipboard Microgrids
February 28, 2023 (v1)
Subject: Energy Management
Keywords: alternative energy source, ship energy efficiency, thermoelectric generator, waste heat recovery
In recent years, the usage potential of alternative energy sources has been gaining importance to increase the efficiency of ships within the scope of the obligations brought by international maritime regulations. The possibility of using alternative energy sources such as solar energy, wind energy, fuel cells, and waste heat recovery technologies on ships has been evaluated in the literature. Today, ships also have waste heat recovery systems as standard equipment for this purpose, and this method is suitable for thermoelectric generators that generate electricity from temperature differences on shipboards. This article aims to review the thermal technologies for the power generation of shipboards. By conducting a case study, an energy efficiency increase was obtained when functional areas were selected on a practical ship, and the effect of this efficiency increase on emissions was examined. As a result of the research, it was discovered that thermoelectric generators increased onboa... [more]
24507. LAPSE:2023.12402
Diagnosing Improper Membrane Water Content in Proton Exchange Membrane Fuel Cell Using Two-Dimensional Convolutional Neural Network
February 28, 2023 (v1)
Subject: Numerical Methods and Statistics
Keywords: 2D-CNN, dehydration, flooding, improper membrane water content, PEMFC
In existing proton exchange membrane fuel cell (PEMFC) applications, improper membrane water management will cause PEMFC performance decay, which restricts the reliability and durability of PEMFC systems. Therefore, diagnosing improper water content in the PEMFC membrane is the key to taking appropriate mitigations to guarantee its operating safety. This paper proposes a novel approach for diagnosing improper PEMFC water content using a two-dimensional convolutional neural network (2D-CNN). In the analysis, the collected PEMFC voltage signal is transformed into 2D image data, which is then used to train the 2D-CNN. Data enhancement and pre-processing techniques are applied to PEMFC voltage data before the training. Results demonstrate that with the trained model, the diagnostic accuracy for PEMFC membrane improper water content can reach 97.5%. Moreover, by comparing it with a one-dimensional convolutional neural network (1D-CNN), the noise robustness of the proposed method can be bett... [more]
24508. LAPSE:2023.12401
Collaborative Optimized Operation Model of Multi-Character Distribution Network Considering Multiple Uncertain Factors and Demand Response
February 28, 2023 (v1)
Subject: Energy Management
Keywords: collaborative operation, distribution network reconfiguration, electric vehicle, Energy Storage, multi-character system, renewable energy source
As many new devices and factors, such as renewable energy sources, energy storage (ESs), electric vehicles (EVs), and demand response (DR), flood into the distribution network, the characteristics of the distribution network are becoming complicated and diversified. In this study, a two-layer collaborative optimized operation model for the multi-character distribution network considering multiple uncertain factors is proposed to achieve optimal dispatching of ES and EV and obtain the optimal grid structure of the distribution network. Based on basic device models of distribution network, the upper layer distribution network reconfiguration (DNR) model is established and solved by the particle swarm optimization (PSO) based on the Pareto optimality and the Prim algorithm. Then, the lower layer optimal dispatching model of ES and EV is established and solved by the binary PSO. The upper layer model and the lower layer model are integrated to form the collaborative optimized operation mod... [more]
24509. LAPSE:2023.12400
Low Power Sensor Location Prediction Using Spatial Dimension Transformation and Pattern Recognition
February 28, 2023 (v1)
Subject: Environment
A method of positioning a location on a specific object using a wireless sensor has been developed for a long time. However, due to the error of wavelengths and various interference factors occurring in three-dimensional space, accurate positioning is difficult, and predicting future locations is even more difficult. It uses IoT-based node pattern recognition technology to overcome positioning errors or inaccurate predictions in wireless sensor networks. It developed a method to improve the current positioning accuracy in a sensor network environment and a method to learn a pattern of position data directly from a wavelength receiver. The developed method consists of two steps: The first step is a method of changing location data in 3D space to location data in 2D space in order to reduce the possibility of positioning errors in 3D space. The second step is to reduce the range of the moving direction angle in which the data changed in two dimensions can be changed in the future and to... [more]
24510. LAPSE:2023.12399
Reduction of the Electromagnetic Torque Oscillation during the Direct on Line (DOL) Starting of a 6 kV Motor by Means of a Controlled Vacuum Circuit-Breaker
February 28, 2023 (v1)
Subject: Process Control
Keywords: direct on line (DOL) starting of induction motors, oscillations of the electromagnetic torque, vacuum circuit breaker
This article deals with the issue of the reduction of the oscillation of electromagnetic torque in the case of a direct on line (DOL) starting of a 6 kV induction motor. Such engines are used in drive systems where frequent starting may be required. Direct starting in such systems may reduce the mechanical and thermal durability. Therefore, the article presents a method of DOL starting of a 6 kV induction motor with the use of vacuum circuit-breakers and appropriate switching of the voltages supplying the electric machine. To confirm the advantages of the proposed solution, computer simulation and experimental tests were carried out, which are presented and discussed in the article. The obtained results confirm the advantages of the proposed solution, compared to the classic starting known from the literature.
24511. LAPSE:2023.12398
Modified Master−Slave Controller for Stable Power Supply of Energy Storage Based Microgrid
February 28, 2023 (v1)
Subject: Process Control
Keywords: Energy Storage, island operation, microgrid, power sharing, stable frequency
This paper presents a method for supplying stable electricity using renewable energy sources and energy storage systems (ESSs) in a small-scale microgrid (MG) such as an island. Traditional control methods, such as master−slave control and droop control, have focused on equalizing power sharing among a small number of generators and do not deal well with emergencies such as unplanned generator failures. This paper proposes a control method that can stably maintain the frequency of the MG in various situations by combining the advantages of master−slave control and droop control and complementing the disadvantages. Simulations were performed under various conditions to verify the proposed control method.
24512. LAPSE:2023.12397
Immobilization of Alcohol Dehydrogenase, Acetaldehyde Lyase, and NADH Oxidase for Cascade Enzymatic Conversion of Ethanol to Acetoin
February 28, 2023 (v1)
Subject: Materials
Keywords: acetaldehyde lyase, acetoin, alcohol dehydrogenase, cascade enzymatic reactions, immobilization, NADH oxidase
Acetoin, a four-carbon hydroxyl-keto compound, is used in the food, pharmaceutical, and chemical industries. The cascade enzymatic production is considered a promising and efficient method to produce acetoin. However, the stability and compatibility of the enzymes under the same catalytic conditions are challenges that need to be resolved. In this work, alcohol dehydrogenase, acetaldehyde lyase, and NADH oxidase were selected to work at the same conditions to efficiently convert ethanol into acetoin. These three enzymes were immobilized on epoxy-modified magnetic nanomaterials to obtain highly stable biocatalysts. The stability and the immobilization conditions, including temperature, pH, enzyme−carrier ratio, and immobilization time, were optimized to obtain the immobilized enzymes with a high catalytic activity. The cascade reactions catalyzed by the immobilized enzymes yielded a high conversion of 90%, suggesting that the use of immobilized enzymes is a promising way to produce acet... [more]
24513. LAPSE:2023.12396
Enhanced Flow Control for Low Latency in QUIC
February 28, 2023 (v1)
Subject: Process Control
Keywords: flow control, low latency, QUIC
Low-latency communication is becoming more popular as applications that demand real-time interaction, such as autonomous mobile vehicles and tactile Internet, have recently gained prominence. In this paper, we propose a fast autotuning algorithm to support low-latency communication in the Quick UDP Internet Connection (QUIC) protocol. The transmission rate is adjusted by the fast autotuning based on the quantity of unused buffers. If the buffer has large free space, the receive window is quickly enlarged to increase the transmission rate and reduce the transmission delay. The fast autotuning is evaluated in this paper through extensive simulations, and the results show that the fast autotuning effectively reduces the transmission latency and increases throughput.
24514. LAPSE:2023.12395
A Grey-System Theory Approach to Assess the Safety of Gas-Supply Systems
February 28, 2023 (v1)
Subject: Energy Management
Keywords: failure, gas-supply system, grey-system theory, safety
The continuity of gas-supply service is a major concern for all gas-supply operators. A safety review of a gas-supply system could help to mitigate the potential repercussions of supply disruptions. Disruptions occur at random due to systemic failures in gas distribution networks. Assessing the operational safety of gas distribution networks is challenging and complex, especially when operational data are limited or associated with high uncertainty. This paper focuses on gas leak incidents. Natural gas leaks disrupt the production process and endanger the ecosystem. Mechanically originated damage in pipelines is found to be the major cause of leaks, according to our investigations. This paper proposes a three-parameter risk matrix to be used in the safety analysis of gas-supply systems. This paper then raises the possibility of using grey-system theory. Grey-system theory has been used to overcome the limitations of the conventional matrix method. This choice is motivated by two facts:... [more]
24515. LAPSE:2023.12394
Safety and Work Organization Management in the Early Days of the COVID-19 Pandemic in the Lignite Mining and Energy Sector in Poland
February 28, 2023 (v1)
Subject: Energy Management
Keywords: COVID-19, hybrid work, interpersonal relations, pandemic, remote work, work safety
The paper presents the results of sociological qualitative research on safety management in work organization. The focus was on how to adapt the workforce to the sanitary regime during the time of the COVID-19 pandemic in the lignite mining and energy sector in the Bełchatów poviat (Łódź voivodeship, Poland). The study aimed to identify the dimensions of safety and the work culture created in crisis conditions as perceived by workers. Based on the conducted analysis, the process of adapting employees to the new rules of work organization was reported, including the transition from fear and anxiety to control over threats and negative emotions. The essence of the research was to support institutional memory to consolidate the existing knowledge and use it in the future.
24516. LAPSE:2023.12393
An Improved U-Net Segmentation Model That Integrates a Dual Attention Mechanism and a Residual Network for Transformer Oil Leakage Detection
February 28, 2023 (v1)
Subject: Modelling and Simulations
Keywords: channel-wise attention, oil leakage detection, residual block, spatial attention, U-net segmentation
Accurately detecting oil leakage from a power transformer is important to maintain its normal operation. Deep learning (DL) methods have achieved satisfactory performance in automatic oil detection, but challenges remain due to the small amount of training data and oil targets with large variations in position, shape, and scale. To manage these issues, we propose a dual attention residual U-net (DAttRes-Unet) within a U-net architecture that extensively uses a residual network as well as spatial and channel-wise attention modules. To overcome the vanishing gradient problem due to deeper layers and a small amount of training data, a residual module from ResNet18 is used to construct the encoder path in the U-net framework. Meanwhile, to overcome the issue of training difficulty for the network, inspired by the advantage of transfer learning, initial network parameters in the encoder are obtained from the pre-trained ResNet18 on the ImageNet dataset. Further, in the decoder path, spatial... [more]

