Dynamic Simulation Model Research Articles

Dynamic modeling and experimental validation of a standalone hybrid microgrid system in Fukuoka, Japan

Microgrids are essential for creating next-generation energy systems because they allow loads, energy storage systems (ESS), and distributed energy resources (DER) to be efficiently and seamlessly integrated. This study presents the dynamic modeling and simulation of an off-grid direct current (DC) microgrid consisting of the photovoltaic (PV) panel, wind turbine, battery, and a DC load incorporating simple, comprehensible, and well-established component-based power control strategies for quality power output. In addition, the main emphasis is on the real-time experimental validation of the dynamic simulation model achieved by designing and developing an indoor test system architecture. A 48-hourly meteorological dataset from Fukuoka, Japan, was used to validate the developed model. The results show a reasonable range of Root-mean-square deviation (RMSE), suggesting that the simulation model can precisely depict the model the dynamic operation of a hybrid DC microgrid system. Furthermore, detailed scenario analysis for sunny, windy, rainy, and cloudy considering real-time meteorological conditions for 72 h of simulation reveals that the proposed microgrid system can effectively meet the load in any situation with a sufficiency factor above 1, making it a self-sustaining hybrid renewable microgrid for residential areas in Japan. The study highlights the significance of understanding microgrid operation energy management with actual implementation.

A pressure-node based dynamic model for simulation and control of aircraft air-conditioning systems

The aircraft air-conditioning system, which consumes the engine bleed air to provide stable and comfort environment for passengers, has a high demand of system reliability and energy efficiency. For analyzing system performance and control effect under a wide range of operating scenarios, this paper presents a dynamic model of the aircraft air-conditioning system. A pressure-node based method is proposed to decouple the system architecture, and a modelling framework is established with reflecting the interdependencies between component-level modules. Dynamic sub-models including pressure nodes, heat exchangers and the air cycle machine are built to predict all major dynamics in the system. The model is verified by the measured data of an airborne testing. The predicted temperatures show good agreement with the measured data, of which the average deviations at the compressor outlet and system outlet are 4.60 °C and 3.49 °C, respectively. The effectivity of the proposed model is investigated under various conditions, including different control signal inputs, standard pull up/pull down conditions and an entire flight case. The simulation results indicate that the model can be successfully applied for a wide range of aircraft operating scenarios, and provide insight towards control design and fault detection of the aircraft air-conditioning system.

Forecasting Trends in the Tuberculosis Epidemic Situation in the Region of the Russian Federation by Dynamic Simulation Model.

The spread of a new coronavirus infection in the last two years together with HIV infection preserves and even increases the potential for the spread of tuberculosis in the world. Sverdlovsk oblast (SO) of Russian Federation is the region with high levels of HIV and tuberculosis (TB). The search for new methods of forecasting of the future epidemic situation for tuberculosis has become particularly relevant. The aim was to develop an effective method for predicting the epidemic situation of tuberculosis using an artificial intelligence (AI) method in the format of a dynamic simulation model based on AI technologies. Statistical data was loaded from the state statistical reporting on TB patients for the period 2007-2017. The parameters were controlled through a system of inequalities. The proposed SDM made it possible to identify and reliably calculate trends of TB epidemiological indicators. Comparison of the predicted values made in 2017 with the actual values of 2018-2021 revealed a reliable coincidence of the trend of movement of TB epidemiological indicators in the region, the maximum deviation was no more than 14.82%. The forecast results obtained with SDM are quite suitable for practical use. Especially, in operational resource planning of measures to counteract the spread of tuberculosis at the regional level.

A CFD Validation Effect of YP/PV from Laboratory-Formulated SBMDIF for Productive Transport Load to the Surface

Several technical factors contribute to the flow of cuttings from the wellbore to the surface of the well, some of which are fundamentally due to the speed and inclination of the drill pipe at different positions (concentric and eccentric), the efficacy of the drilling mud considers plastic viscosity (PV) and yield point (YP), the weight of the cuttings, and the deviation of the well. Moreover, these overlaying cutting beds breed destruction in the drilling operation, some of which cause stuck pipes, reducing the rate of rotation and penetration. This current study, while it addresses the apropos of artificial intelligence (AI) with symmetry, employs a three-dimensional computational fluid dynamic (CFD) simulation model to validate an effective synthetic-based mud-drilling and to investigate the potency of the muds’ flow behaviours for transporting cuttings. Furthermore, the study examines the ratio effects of YP/PV to attain the safe transport of cuttings based on the turbulence of solid-particle suspension from the drilling fluid and the cuttings, and its velocity–pressure influence in a vertical well under a concentric and eccentric position of the drilling pipe. The resulting CFD analysis explains that the YP/PV of SBM and OBM, which generated the required capacity to suspend the cuttings to the surface, are symmetric to the experimental results and hence, the position of the drill pipe at the concentric position in vertical wells required a lower rotational speed. A computational study of the synthetic-based mud and its potency of not damaging the wellbore under an eccentric drill pipe position can be further examined.

Numerical simulation of radiant floor cooling systems using PCM for naturally ventilated buildings in a hot and humid climate

This study constructs a coupled simulation model of heat balance analysis and computational fluid dynamics (CFD) for naturally ventilated buildings with installed phase change materials (PCMs), and demonstrates a modeling method for the thermal storage effect of PCM in the simulation. Then, the constructed model was applied to a sensitivity analysis to clarify the key parameters of a radiant floor cooling system using PCMs. The simulation was conducted for the target building, where the radiant floor cooling system was installed, and the results were validated with field measurements in the hot and humid climate of Indonesia. The results showed that the coupled simulation model can evaluate both the temperature and heat balance of PCMs in naturally ventilated buildings, where air temperature and air flow distribution are not uniform, with higher accuracy. The temperature and heat flux on the floor surface showed good correlations between the simulation and measurement, with the root mean square errors of 0.3–0.5 °C and 4.0 W/m2, respectively. In particular, coupling with radiative heat transfer calculation increased the simulation accuracy in terms of floor surface and PCM temperatures by 0.3 °C when the surface temperature difference between the floor and the other surfaces, i.e., the wall and ceiling, was considerable owing to the thermal storage effect of the PCMs. The following sensitivity analysis showed that a PCM thickness of 6 mm and ventilation during nighttime are the optimum settings for the radiant floor cooling system under the given hot and humid conditions.

Analysis of Wake Turbulence for a Savonius Turbine for Malaysia’s Slow-Moving Current Flow

With Malaysia being surrounded by water bodies, tidal energy could be used for energy extraction. While several turbine designs and technologies have been used for tidal energy extraction, information on the use of vertical-axis tidal turbines (VATTs) for shallow-water applications is scarce. However, implementing horizontal-axis tidal turbines (HATTs) is not feasible due to Malaysian ocean depths. Hence, examining the wake-flow characteristics of VATTs in a shallow water-working environment in Malaysia is essential. The wake turbulence of the Savonius turbine model was compared with that of a hypothetical ‘actuator' cylinder, a VATT representation. Subsequently, the wake turbulences of a Savonius turbine model in static and dynamic simulations were compared to understand the flow distinction. Compared with that exhibited by the hypothetical actuator cylinder of 2.5 m, the hypothetical actuator cylinder of 5 m exhibits greater velocity deceleration. Additionally, the modelled Savonius turbine exhibits significantly more deceleration than that exhibited by the hypothetical actuator cylinder. Finally, the analysis of the static model of the Savonius turbine shows deceleration that is greater than that of the dynamic model.

Optimization of Patient Flow through EMT Facilities Applying Dynamic Behavioral Simulation Models

Background/Introduction:The effectiveness of care provided by EMTs is directly linked to the ability to ensure a controlled, coordinated, and safe patient flow through the post, especially in case of MCIs or disease outbreak. Currently, there are neither frameworks nor tools to analyze such flow that is often visualized on paper using arrows or simply connected to the care pathway, thus missing the impact of people’s interactions with the facility.Objectives:This study aims at exploring the use of a behavioral-design-based approach in simulating patient flow through EMTs.1Method/Description:It provides a dynamic behavioral simulation model to assess the interactions between patients, staff members, and the related dynamic movements/interactions with the health care facility, each of them having specific features also in relation to the emergency condition faced.2 Data used in this study consist of literature-based information concerning patient characteristics (eg, age), the variation of expected medical conditions and severity in relation to the time and typology of the emergency,3 layouts of existing facilities (eg, UKMed T1), and experimental activities (eg, exercise).Results/Outcomes:The analysis of the results will allow to simulate different scenarios and improve the design of health care facilities layouts in order to prevent overcrowding situation, avoid disease spreading, estimate the optimal number of staff for each task, and investigate interactions between patients and staff.Conclusion:Optimizing patient flow encompasses quickly, efficiently, and effectively movement meeting the demand for care by moving patients through care pathways while improving coordination of care, patient safety, and health outcomes.

Stochastic gradient descent algorithm for the predictive modelling of grate combustion and boiler dynamics

Pressure and water level control are quite challenging in grate-fired boilers due to higher combustion lag. Fluctuation in the pressure and the water level is more evident in the coal-fired grate boilers due to the presence of lower volatile and higher char. This results in suboptimal operation and poor performance of the boiler. This paper presents a novel predictive and dynamic simulation model for the drum dynamics analysis of a grate-fired boiler by combining a data-driven model and a thermodynamic model. A data-driven methodology is employed for the estimation of combustion, heat transfers, and circulation performance of the boiler. A novel thermodynamic model is proposed for the boiler dynamics of a hybrid boiler. The proposed data-driven model has been integrated with the thermodynamic model to reduce the randomness and improve consistency. Pressure and water level errors are estimated by comparing the predicted value and experimental result and the multi-objective optimisation technique is employed for the minimisation of errors. The Stochastic Gradient Descent algorithm is proposed for its ability to quick learning and adaptation to variations in fuel and combustion characteristics. The model demonstrates good accuracy in predicting the combustion and boiler dynamics of a grate-fired boiler. The proposed model has good potential to be used for the reciprocating grate solid-fuel boiler control in fluctuating load conditions.

Oncology Simulation Model: A Comprehensive and Innovative Approach to Estimate and Project Prevalence and Survival in Oncology.

We demonstrate a new model framework as an innovative approach to more accurately estimate and project prevalence and survival outcomes in oncology. We developed an oncology simulation model (OSM) framework that offers a customizable, dynamic simulation model to generate population-level, country-specific estimates of prevalence, incidence of patients progressing from earlier stages (progression-based incidence), and survival in oncology. The framework, a continuous dynamic Markov cohort model, was implemented in Microsoft Excel. The simulation runs continuously through a prespecified calendar time range. Time-varying incidence, treatment patterns, treatment rates, and treatment pathways are specified by year to account for guideline-directed changes in standard of care and real-world trends, as well as newly approved clinical treatments. Patient cohorts transition between defined health states, with transitions informed by progression-free survival and overall survival as reported in published literature. Model outputs include point prevalence and period prevalence, with options for highly granular prevalence predictions by disease stage, treatment pathway, or time of diagnosis. As a use case, we leveraged the OSM framework to estimate the prevalence of bladder cancer in the United States. The OSM is a robust model that builds upon existing modeling practices to offer an innovative, transparent approach in estimating prevalence, progression-based incidence, and survival for oncologic conditions. The OSM combines and extends the capabilities of other common health-economic modeling approaches to provide a detailed and comprehensive modeling framework to estimate prevalence in oncology using simulation modeling and to assess the impacts of new treatments on prevalence over time.

Повышение эффективности возврата уноса в котлах со слоевыми топками

A significant disadvantage of grate stokers is great carbon loss. To reduce these losses, the ash caught in the flue is returned to the furnace for afterburning. The effectiveness of this measure depends on the thermal characteristics of coal, the size of the pieces of coal and ash, the degree of carbon elimination, and the design features of the combustion chamber. Normative techniques to calculate and design grate stokers do not consider the features of coal combustion with ash return. Thus, it is relevant to develop the models that describe the creation of ash flows in the boiler path depending on its design, properties and dispersed composition of the burned coal and the aerodynamics of the combustion chamber. Mathematic simulation of the processes of particle size classification has been carried out to describe the creation of ash mass flows on the grate and in the convection chamber. To evaluate the parameters of mathematical models, simulation modeling of gas dynamics of flue gases in the combustion chamber has been carried out with SolidWorks software. The authors have developed a mathematical model and the method to identify its parameters. It allows us to obtain quantitative estimates of the economic efficiency of boilers with grate firing of coal. Thus, a computer program has been developed. The authors have used the program and the Neryungri brown coal to burn in the KV-TS-30-150 boiler. The results have shown that carbon loss without fly ash reinjection is 11,27 %. Introduction of fly-coke return unit reduces the loss up to 10,45 %. It is established that elimination of slit windows in the rotary baffle will lead to a change of the trajectories of ash particles and carbon losses reduction up to 10,17 %. Limiting the maximum size of coal pieces to 50 mm will lead to a more noticeable increase of boiler efficiency. The calculations have showed that in case the value of the carbon burn out factor equals 0,935, the carbon loss when the system of fly ash reinjection is turned off, its commissioning and, in addition, an increase of the gas density of the rotary screen will be 4 ,88%, 4,44% and 4,3% respectively. In case of a more careful assessment of the burnout factor at the level of 0,9, the carbon loss will be 7,51%, 6,87% and 6,65% respectively. The developed mathematical model makes it possible to evaluate the effect of the operation of the fly ash reinjection unit on the efficiency of the operation of a boiler with a grate stoker. Validation of a model for adequacy and for accuracy increase can be carried out after field testing of the boiler equipment.

Magnetomechanical degradation of sintered NdFeB induced by impact in eddy current recoil brake

The permanent magnet eddy current brakes (PMECBs) are widely used due to the advantages of no noise and simple structure. And the emergence of high-performance sintered NdFeB has greatly improved its energy consumption density. Based on this, it is a bold attempt to apply the basic principle of PMECB to the artillery launch environment. However, the harsh working environment is a great challenge to the sintered NdFeB. To tackle this, a series of experiments are conducted to investigate the magnetomechanical characteristics of materials under dynamic conditions and corresponding theoretical models are developed in this paper. Specifically, the basic principle of eddy current recoil brake is firstly introduced and the principle prototype tests are carried out. Then the experiments of dynamic mechanical and impact demagnetization behavior are conducted in combination with the application requirements. Different from the previous researches in quasi-static environment, the experiments and the corresponding theoretical models have typical dynamic characteristics and are more suitable for the ever-expanding application of materials. Based on the basic structure and theoretical models, the dynamic numerical simulation model of the eddy current recoil brake is established and the magnetomechanical characteristics during the working process are analyzed. Corresponding research conclusions can provide theoretical basis for the use and maintenance of eddy current recoil brakes.

Analysis of start-up behavior based on the dynamic simulation of an SOFC–engine hybrid system

A dynamic simulation model of a hybrid power generation system of a solid oxide fuel cell and a homogeneous charge compression ignition engine was developed to investigate the behavior of the system during the start-up process. The stack, reformer, catalytic burner, and heat exchanger were implemented as dynamic models based on physical equations. For the engine, an experimental data-based mapping model was developed. The dynamic model was simulated on a Matlab/Simulink platform. Individually developed component models were assembled as an integrated system model and operated at the system level. The hybrid system was designed to generate approximately 4 kW of electricity from the SOFC stack and 1 kW from the engine, resulting in a total system power of 5 kW, with an electrical efficiency of 50.6%. The integrated model was operated using a four-step start-up procedure for 50 h, during which the temperature and composition of the stream were observed in time. Based on this, the dynamic behavior of the system was analyzed at each stage throughout the entire start-up process from ambient to high operating temperature. Validation of key results suggests a close resemblance between the model and an actual system. Therefore, the proposed model is expected to exceed the limitations of the existing static model analysis method.

Dynamic characteristics and control strategies of the supercritical CO2 Brayton cycle tailored for the new generation concentrating solar power

The supercritical CO2 (sCO2) Brayton cycle has the advantages of high efficiency, good flexibility and compact equipment, and is widely regarded as the ideal power cycle for the new generation concentrating solar power (CSP). The application scenario of the CSP determines that the unit's fast peak shaving capability must be considered. In this paper, a dynamic simulation model was developed for an indirect-heated 800 °C/550 °C sCO2 CSP test plant, containing a particle heat storage system. The effects of control modes of heating power, cooling power, mass flow rate (m), turbine rotational speed and sCO2 inventory on the system dynamic characteristics were researched. It was found that the control mode of changing particle/water mass flow rate had a significantly faster response speed than changing temperature. Using the turbine optimal rotational speed control mode could improve the net cycle efficiency from 15.30% to 16.12%, in a continuous linear load reduction process. The sCO2 inventory control module played a crucial role in limiting the fluctuation of compressor inlet pressure. The regulation mode of changing m and turbine inlet temperature (T4) synchronously and that of changing m with constant T4 were all proved to achieve the goal of fast peak shaving well, but the latter one was safer, which could greatly limit the temperature change rate of sCO2 and equipment in the fast peak shaving process. Our work not only offers an operation solution for the sCO2 CSP test plant, but also gives guidance for the efficient, flexible and safe design of the third generation CSP plants.

Simulation analysis on the operational characteristics of a novel wind-to-heat system

The growing demand for energy and the pressure of carbon emission increase the proportion of renewable energy in the global energy consumption. In the wind-to-heat system, the compressor is utilized to replace the generator in the wind turbine to allow the wind energy driving heat pump directly, which simplifies the energy conversion process. In this study, a dynamic simulation model of the wind-to-heat system is proposed, which consists of the following six parts: wind turbine, compressor, condenser, thermal expansion valve, evaporator, and controller. Validations of this model was conducted by comparing the simulation result with the experimental data from a 100 kW wind-to-heat system. Effects of different operational conditions, such as hot water flow rate, inlet water temperature and types of refrigerants, on the characteristics of the system are explored and analyzed. The conclusion is drawn that the hot water flow rate is optimized as 3 kg/s, lower inlet water temperature led to lower heating capacity and lower COP, R245fa and R717 have good performances in heating production, which is in favor of the further design and optimize of the system. After debugging the simulation model for different design alternatives, different performances will be acquired to improve the efficiency of the design.

The loads developed by epicondylar and epitrochlear muscles across the elbow joint. A dynamic simulated model

The radio-humeral joint has traditionally been believed to support most of the loads transmitted through the elbow. Load transfer through the elbow has been a controversial issue since the publication of the first biomechanical studies on the subject, most of which were based on extrinsic forces acting on the extended joint. The present study analyzes load distribution across the six different compartments in the elbow while the joint is flexed, as well as the intrinsic forces generated in the epicondylar and epitrochlear muscles.Ten cadaveric elbows were positioned at 90° of flexion, forearm in a neutral position and wrist at 0°. Tekscan sensors were used for measuring intraarticular pressures.Forces generated by epitrochlear muscles results in a series of loads that affect mainly the anteromedial facet (40%), followed by the posterolateral facet (34%) of the ulnohumeral joint, with the flexor carpi ulnaris generating the heaviest loads (43% on the anteromedial and 38% on the posterolateral facets). Conversely, the forces generated by the epicondylar muscles, similar in behavior but with an opposite direction, convey heavier loads to the elbow’s anterolateral facet (45%), followed by the radiohumeral joint (26%) with the extensor carpi ulnaris generating the heaviest loads (54% on the anterolateral facet and 17% on the radiohumeral joint).Our results indicate that the elbow joint exhibits a characteristic load distribution pattern that depends on the muscles, as intrinsic forces are generated by the epicondylar and epitrochlear muscles. The anterior portion of the ulnohumeral joint is the area bearing the heaviest loads.

Scalable Marginalization of Correlated Latent Variables with Applications to Learning Particle Interaction Kernels

Marginalization of latent variables or nuisance parameters is a fundamental aspect of Bayesian inference and uncertainty quantification. In this work, we focus on scalable marginalization of latent variables in modeling correlated data, such as spatio-temporal or functional observations. We first introduce Gaussian processes (GPs) for modeling correlated data and highlight the computational challenge, where the computational complexity increases cubically fast along with the number of observations. We then review the connection between the state space model and GPs with Matérn covariance for temporal inputs. The Kalman filter and Rauch-Tung-Striebel smoother were introduced as a scalable marginalization technique for computing the likelihood and making predictions of GPs without approximation. We introduce recent efforts on extending the scalable marginalization idea to the linear model of coregionalization for multivariate correlated output and spatio-temporal observations. In the final part of this work, we introduce a novel marginalization technique to estimate interaction kernels and forecast particle trajectories. The computational progress lies in the sparse representation of the inverse covariance matrix of the latent variables, then applying conjugate gradient for improving predictive accuracy with large data sets. The computational advances achieved in this work outline a wide range of applications in molecular dynamic simulation, cellular migration, and agent-based models.

A three-region movable-boundary helical coil once-through steam generator model for dynamic simulation and controller design

A simple but accurate mathematical model is crucial for dynamic simulations and controller design of helical coil once-through steam generator (OTSG). This paper presents a three-region movable boundary dynamic model of the helical coil OTSG. Based on the secondary side fluid conditions, the OTSG is divided into subcooled region (two control volumes), two-phase region (two control volumes) and superheated region (three control volumes) with movable boiling boundaries between each region. The nonlinear dynamic model is derived based on mass, energy and momentum conservation equations. And the linear model is obtained by using the transfer function and state space transformation, which is a 37-order model of five input and three output. Validations are made under full-power steady-state condition and four transient conditions. Results show good agreements among the nonlinear model, linear model and the RELAP5 model, with acceptable errors. This model can be applied to dynamic simulations and controller design of helical coil OTSG with constant primary-side flow rate.

Simulation and forecasting models of COVID-19 taking into account spatio-temporal dynamic characteristics: A review.

The COVID-19 epidemic has caused more than 6.4 million deaths to date and has become a hot topic of interest in different disciplines. According to bibliometric analysis, more than 340,000 articles have been published on the COVID-19 epidemic from the beginning of the epidemic until recently. Modeling infectious diseases can provide critical planning and analytical tools for outbreak control and public health research, especially from a spatio-temporal perspective. However, there has not been a comprehensive review of the developing process of spatio-temporal dynamic models. Therefore, the aim of this study is to provide a comprehensive review of these spatio-temporal dynamic models for dealing with COVID-19, focusing on the different model scales. We first summarized several data used in the spatio-temporal modeling of the COVID-19, and then, through literature review and summary, we found that the existing COVID-19 spatio-temporal models can be divided into two categories: macro-dynamic models and micro-dynamic models. Typical representatives of these two types of models are compartmental and metapopulation models, cellular automata (CA), and agent-based models (ABM). Our results show that the modeling results are not accurate enough due to the unavailability of the fine-grained dataset of COVID-19. Furthermore, although many models have been developed, many of them focus on short-term prediction of disease outbreaks and lack medium- and long-term predictions. Therefore, future research needs to integrate macroscopic and microscopic models to build adaptive spatio-temporal dynamic simulation models for the medium and long term (from months to years) and to make sound inferences and recommendations about epidemic development in the context of medical discoveries, which will be the next phase of new challenges and trends to be addressed. In addition, there is still a gap in research on collecting fine-grained spatial-temporal big data based on cloud platforms and crowdsourcing technologies to establishing world model to battle the epidemic.

Research on the Obstacle-Avoidance Steering Control Strategy of Tracked Inspection Robots

Tracked inspection robots possess prominent advantages in dealing with severe environment rescue, safety inspection, and other important tasks, and have been used widely. However, tracked robots are affected by skidding and slipping, so it is difficult to achieve accurate control. For example, the control parameters of a tracked robot are the same during driving, but the pressure, shear force and steering resistance of the robot on the road surface are different, which affects the steering characteristics of the robot on complex terrain. Based on analysis of the structural parameters and steering radius of the robot, the traction force and resistance torque models of the tracked robot were established, and the plane dynamics of the robot’s steering were analyzed and solved. The corresponding relationships between the road parameters, relative steering radius, and lateral relative offset of the robot on three typical roads were obtained. Mathematical models of the robot’s track speed and relative steering radius with and without skid and slip were established. Through simulation analysis of Matlab software, the corresponding relationship between the relative steering radius of the robot and the velocity difference of the two tracks were obtained. Taking angular obstacles as an example, three obstacle-avoidance steering control strategies, once turning in situ center, twice turning in situ center, and large-radius steering were developed. The tracked robot and obstacle multi-body dynamic simulation models were constructed using ADAMS simulation software. The simulation results show that all three methods can complete the steering tasks according to the requirements; however, under the influence of skid and slip, the trajectory of the robot deviates from the ideal trajectory, which has a great impact on large-radius steering, even though the large-radius obstacle-avoidance steering control strategy has the advantages of a smooth trajectory, fast steering speed, and high efficiency. The obstacle-avoidance steering experiments were completed by the robot prototype, which verifies the rationality of robot steering theory, which could provide the corresponding theoretical basis for autonomous obstacle-avoidance navigation control of a tracked robot.

Application of machine learning algorithm to forecast production for fracture basement formation, Central arch, Bach Ho field

Oil production forecast is a big challenge in the oil and gas industry. Simulation model and prediction results play an important role in field operation and management. Currently, dynamic simulation model, decline curve analysis are popular tools applied to forecast production. The dynamic simulation model shows a remarkable effect for sedimentary objects. However, production forecasting by this method for fracture basement formation sometimes gives unreliable results because the fracture basement formation is a complex of geological objects, which causes difficulties in predicting the geological characteristics. The decline curve analysis (DCA) method uses simple extrapolated mathematical functions to forecast oil production, therefore the results do not reflect the production operations such as opening/closing production interval.To avoid the disadvantages of these traditional methods, Vietnam Petroleum Institute (VPI) has studied the applicability of machine learning to forecast oil production for fracture basement formation of Bach Ho field. The study results show that the random forest model has improved the production forecast with low relative error (4%).