On Improving Algorithm Efficiency of Gas-Kick Simulations toward Automated Influx Management: A Robertson Differential-Algebraic-Equation Problem Approach

2021 ◽  
pp. 1-24
Author(s):  
Chen Wei ◽  
Yuanhang Chen
Keyword(s):  
Decision Making ◽  
Real Time ◽  
Model Prediction ◽  
Computational Efficiency ◽  
Prediction Accuracy ◽  
Numerical Scheme ◽  
Computational Time ◽  
Numerical Efficiency ◽  
Flow Models ◽  
Gas Kick

Summary Improved numerical efficiency in simulating wellbore gas-influx behaviors is essential for realizing real-time model-prediction-based gas-influx management in wells equipped with managed-pressure-drilling (MPD) systems. Currently, most solution algorithms for high-fidelitymultiphase-flow models are highly time consuming and are not suitable for real-time decision making and control. In the application of model-predictive controllers (MPCs), long calculation time can lead to large overshoots and low control efficiency. This paper presents a drift-flux-model (DFM)-based gas-influx simulator with a novel numerical scheme for improved computational efficiency. The solution algorithm to a Robertson problem as differential algebraic equations (DAEs) was used as the numerical scheme to solve the control equations of the DFM in this study. The numerical stability and computational efficiency of this numerical scheme and the widely used flux-splitting methods are compared and analyzed. Results show that the Robertson DAE problem approach significantly reduces the total number of arithmetic operations and the computational time compared with the hybrid advection-upstream-splitting method (AUSMV) while maintaining the same prediction accuracy. According to the “Big-O notation” analysis, the Robertson DAE approach shows a lower-order growth of computational complexity, proving its good potential in enhancing numerical efficiency, especially when handling simulations with larger scales. The validation of both the numerical schemes for the solution of the DFM was performed using measured data from a test well drilled with water-based mud (WBM). This study offers a novel numerical solution to the DFM that can significantly reduce the computational time required for gas-kick simulation while maintaining high prediction accuracy. This approach enables the application of high-fidelity two-phase-flow models in model-prediction-based decision making and automated influx management with MPD systems.

scholarly journals Land subsidence modelling for decision making on groundwater abstraction under emergency situation

2020 ◽  
Vol 382 ◽  
pp. 403-408
Author(s):  
Masaatsu Aichi
Keyword(s):  
Decision Making ◽  
Monte Carlo ◽  
Uncertainty Analysis ◽  
Real Time ◽  
Land Subsidence ◽  
Null Space ◽  
Emergency Situation ◽  
Computational Time ◽  
Groundwater Abstraction ◽  
Emergency Situations

Abstract. This study presents an inversion scheme with uncertainty analysis for a land subsidence modelling by a Monte Carlo filter in order to contribute to the decision-making on the groundwater abstraction. For real time prediction and uncertainty analysis under the limited computational resources and available information in emergency situations, one dimensional vertical land subsidence simulation was adopted for the forward modelling and the null-space Monte Carlo method was applied for the effective resampling. The proposed scheme was tested with the existing land subsidence monitoring data in Tokyo lowland, Japan. The results demonstrated that the prediction uncertainty converges and the prediction accuracy improves as the observed data increased with time. The computational time was also confirmed to be acceptable range for a real time execution with a laptop.

scholarly journals Moving Time UCAV Maneuver Decision Based on the Dynamic Relational Weight Algorithm and Trajectory Prediction

2021 ◽  
Vol 2021 ◽  
pp. 1-19
Author(s):  
Xie Lei ◽  
Ding Dali ◽  
Wei Zhenglei ◽  
Xi Zhifei ◽  
Tang Andi
Keyword(s):  
Decision Making ◽  
Real Time ◽  
Prediction Accuracy ◽  
Control Variable ◽  
Trajectory Prediction ◽  
Constant Weight ◽  
Adaptive Boosting ◽  
Time Performance ◽  
Correlation Degree ◽  
Air Combat

To improve the accuracy and real-time performance of autonomous decision-making by the unmanned combat aerial vehicle (UCAV), a decision-making method combining the dynamic relational weight algorithm and moving time strategy is proposed, and trajectory prediction is added to maneuver decision-making. Considering the lack of continuity and diversity of air combat situation reflected by the constant weight in situation assessment, a dynamic relational weight algorithm is proposed to establish an air combat situation system and adjust the weight according to the current situation. Based on the dominance function, this method calculates the correlation degree of each subsituation and the total situation. According to the priority principle and information entropy theory, the hierarchical fitting function is proposed, the association expectation is calculated by using if-then rules, and the weight is dynamically adjusted. In trajectory prediction, the online sliding input module is introduced, and the long- and short-term memory (LSTM) network is used for real-time prediction. To further improve the prediction accuracy, the adaptive boosting (Ada) method is used to build the outer frame and compare with three traditional prediction networks. The results show that the prediction accuracy of Ada-LSTM is better. In the decision-making method, the moving time optimization strategy is adopted. To solve the problem of timeliness and optimization, each control variable is divided into 9 gradients, and there are 729 control schemes in the control sequence. Through contrast pursuit simulation experiments, it is verified that the maneuver decision method combining the dynamic relational weight algorithm and moving time strategy has a better accuracy and real-time performance. In the case of using prediction and not using prediction, the adaptive countermeasure simulation is carried out with the current more advanced Bayesian inference maneuvering decision-making scheme. The results show that the UCAV maneuvering decision-making ability combined with accurate prediction is better.

scholarly journals Wastewater treatment modelling: dealing with uncertainties

2009 ◽  
Vol 60 (8) ◽  
pp. 1929-1941 ◽  
Author(s):  
E. Belia ◽  
Y. Amerlinck ◽  
L. Benedetti ◽  
B. Johnson ◽  
G. Sin ◽  
...  
Keyword(s):  
Decision Making ◽  
Wastewater Treatment ◽  
Model Prediction ◽  
Prediction Accuracy ◽  
Future Research ◽  
Research Needs ◽  
Problem Statement ◽  
Engineering Project ◽  
Sources Of Uncertainty ◽  
Comprehensive Discussion

This paper serves as a problem statement of the issues surrounding uncertainty in wastewater treatment modelling. The paper proposes a structure for identifying the sources of uncertainty introduced during each step of an engineering project concerned with model-based design or optimisation of a wastewater treatment system. It briefly references the methods currently used to evaluate prediction accuracy and uncertainty and discusses the relevance of uncertainty evaluations in model applications. The paper aims to raise awareness and initiate a comprehensive discussion among professionals on model prediction accuracy and uncertainty issues. It also aims to identify future research needs. Ultimately the goal of such a discussion would be to generate transparent and objective methods of explicitly evaluating the reliability of model results, before they are implemented in an engineering decision-making context.

A Highly Efficient and Optimised Simulation Based Multi objective Decision-Making for FMS Control

2018 ◽  
Vol 6 (6) ◽  
pp. 98
Author(s):  
Shreyanshu Parhi ◽  
S. C. Srivastava
Keyword(s):  
Decision Making ◽  
Real Time ◽  
Manufacturing Industry ◽  
Simulation Software ◽  
Shop Floor ◽  
Simulation Tool ◽  
Routing Flexibility ◽  
Decision System ◽  
Multi Objective ◽  
Arena Simulation

Optimized and efficient decision-making systems is the burning topic of research in modern manufacturing industry. The aforesaid statement is validated by the fact that the limitations of traditional decision-making system compresses the length and breadth of multi-objective decision-system application in FMS.  The bright area of FMS with more complexity in control and reduced simpler configuration plays a vital role in decision-making domain. The decision-making process consists of various activities such as collection of data from shop floor; appealing the decision-making activity; evaluation of alternatives and finally execution of best decisions. While studying and identifying a suitable decision-making approach the key critical factors such as decision automation levels, routing flexibility levels and control strategies are also considered. This paper investigates the cordial relation between the system ideality and process response time with various prospective of decision-making approaches responsible for shop-floor control of FMS. These cases are implemented to a real-time FMS problem and it is solved using ARENA simulation tool. ARENA is a simulation software that is used to calculate the industrial problems by creating a virtual shop floor environment. This proposed topology is being validated in real time solution of FMS problems with and without implementation of decision system in ARENA simulation tool. The real-time FMS problem is considered under the case of full routing flexibility. Finally, the comparative analysis of the results is done graphically and conclusion is drawn.

scholarly journals BattleNet: Capturing Advantageous Battlefield in RTS Games (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13849-13850
Author(s):  
Donghyeon Lee ◽  
Man-Je Kim ◽  
Chang Wook Ahn
Keyword(s):  
Artificial Intelligence ◽  
Decision Making ◽  
Real Time ◽  
Large Scale ◽  
Outcome Predictor ◽  
Short Term ◽  
Rts Game

In a real-time strategy (RTS) game, StarCraft II, players need to know the consequences before making a decision in combat. We propose a combat outcome predictor which utilizes terrain information as well as squad information. For training the model, we generated a StarCraft II combat dataset by simulating diverse and large-scale combat situations. The overall accuracy of our model was 89.7%. Our predictor can be integrated into the artificial intelligence agent for RTS games as a short-term decision-making module.

Sign in / Sign up

Export Citation Format

Share Document