scholarly journals Self-Learning Controllers in the Oil and Gas Industry

2021 ◽  
Vol 11 (1) ◽  
pp. 18-35
Author(s):  
Dr. Seaar Al-Dabooni ◽  
Hussen Ali Mohammad Alshehab
Keyword(s):  
Control System ◽  
Oil And Gas ◽  
Learning Algorithm ◽  
Control Signal ◽  
Petroleum Exploration ◽  
The Real ◽  
Model Free ◽  
Network Provider ◽  
Matlab Programming ◽  
Self Learning

Recently, solving the optimization-control problems by using artificial intelligence has widelyappeared in the petroleum fields in exploration and production. This paper presents the stateof-the-art reinforcement-learning algorithm applying in the petroleum optimization-controlproblems, which is called a direct heuristic dynamic programming (DHDP). DHDP has twointeractive artificial neural networks, which are the critic network (provider acritique/evaluated signal) and the actor network (provider a control signal). This paper focuseson a generic on-line learning control system in Markov decision process principles.Furthermore, DHDP is a model-free learning design that does not require prior knowledgeabout a dynamic model; therefore, DHDP can be appllied with any petroleum equipment ordevise directly without needed to drive a mathematical model. Moreover, DHDP learns byitself (self-learning) without human intervention via repeating the interaction between anequipment and environment/process. The equipment receives the states of theenvironment/process via sensors, and the algorithm maximizes the reward by selecting thecorrect optimal action (control signal). A quadruple tank system (QTS) is taken as a benchmarktest problem, that the nonlinear model responses close to the real model, for three reasons:First, QTS is widely used in the most petroleum exploration/production fields (entire system orparts), which consists of four tanks and two electrical-pumps with two pressure control valves.Second, QTS is a difficult model to control, which has a limited zone of operating parametersto be stable; therefore, if DHDP controls on QTS by itself, DHDP can control on otherequipment in a fast and optimal manner. Third, QTS is designed with a multi-input-multioutput (MIMO) model for analysis in the real-time nonlinear dynamic system; therefore, theQTS model has a similar model with most MIMO devises in oil and gas field. The overalllearning control system performance is tested and compared with a proportional integralderivative (PID) via MATLAB programming. DHDP provides enhanced performancecomparing with the PID approach with 99.2466% improvement.

Applied Technology in Control System Design of Asphalt Concrete Mixer's Based on PLC

2014 ◽  
Vol 910 ◽  
pp. 433-436
Author(s):  
Jiao Yue Liu ◽  
Ji Chang Wang ◽  
Ya Bei Shi ◽  
Ju Qing Yang
Keyword(s):  
Control System ◽  
Asphalt Concrete ◽  
Learning Algorithm ◽  
Computer Control ◽  
Transmission Error ◽  
Computer Control System ◽  
Current Production ◽  
And Control ◽  
Measurement And Control ◽  
Self Learning

In view of current production technology of asphalt concrete mixing plant and technology, a distributed computer control system based on PLC and field bus is developed. The compensation iteration self-learning algorithm is adopted, the compensation amount of learning algorithm of the system is designed and the course program control algorithm is presented. Therefore the precision of the system’s measurement and control is improved and the transmission error is reduced.

PRESSURE CONTROL SYSTEM AT CEMENTATION OF WELLS

2017 ◽  
pp. 62-67
Author(s):  
V. G. Kuznetsov ◽  
O. A. Makarov
Keyword(s):  
Control System ◽  
Oil And Gas ◽  
Pressure Control ◽  
Poor Quality ◽  
Technical Solution ◽  
Cement Slurry ◽  
Automated Control ◽  
Injection Speed ◽  
Pressure Control System ◽  
Effective Life

At cementing of casing of oil and gas wells during the process of injecting of cement slurry in the casing column the slurry can move with a higher speed than it’s linear injection speed. A break of continuity of fluid flow occurs, what can lead to poor quality isolation of producing formations and shorten the effective life of the well. We need to find some technical solution to stabilize the linear velocity of the cement slurry in the column. This task can be resolved with an automated control system.

Operon Prediction Based On an Iterative Self-learning Algorithm*

2011 ◽  
Vol 38 (7) ◽  
pp. 642-651
Author(s):  
Wen-Qi Wu ◽  
Xiao-Bin ZHENG ◽  
Yong-Chu LIU ◽  
Kai TANG ◽  
Huai-Qiu ZHU
Keyword(s):  
Learning Algorithm ◽  
Operon Prediction ◽  
Self Learning

A Flatness Control System Design Based on Actuator Efficiency Factors for Cold Rolling Mill

2010 ◽  
Vol 139-141 ◽  
pp. 1889-1893 ◽  
Author(s):  
Peng Fei Wang ◽  
Dian Hua Zhang ◽  
Xu Li ◽  
Jia Wei Liu
Keyword(s):  
Control System ◽  
Rolling Force ◽  
Quantitative Description ◽  
Learning Model ◽  
Feed Forward Control ◽  
Flatness Control ◽  
Stand Type ◽  
Loop Feedback ◽  
Efficiency Factors ◽  
Self Learning

In order to improve the flatness of cold rolled strips, strategies of closed loop feedback flatness control and rolling force feed forward control were established respectively, based on actuator efficiency factors. As the basis of flatness control system, efficiencies of flatness actuators provide a quantitative description to the law of flatness control. For the purpose of obtaining accurate efficiency factors matrixes of actuators, a self-learning model of actuator efficiency factors was established. The precision of actuator efficiency factors could be improved continuously by correlative measurement flatness data inputs. Meanwhile, the self-learning model of actuator efficiency factors permits the application of this flatness control for all possible types of actuators and every stand type. The developed flatness control system has been applied to a 1250mm single stand 6-H reversible UCM cold mill. Applications show that the flatness control system based on actuator efficiency factors is capable to obtain good flatness.

Control System Design of the Vehicle Mounted Hammer Source Based on PLC

2012 ◽  
Vol 619 ◽  
pp. 302-305
Author(s):  
Hong Yan Wang ◽  
Wen Sheng Xiao ◽  
Xiu Juan Lin ◽  
Xian Feng Wang
Keyword(s):  
Control System ◽  
System Design ◽  
Software Design ◽  
High Velocity ◽  
Simple Structure ◽  
Oil And Gas ◽  
Basic Structure ◽  
Control System Design ◽  
Oil And Gas Exploration ◽  
Gas Consumption

Considering the pollution on the environment using dynamite source in oil and gas exploration, harm and damage to people and building, the vehicle mounted hammer source which can replace dynamite source is presented. This paper describes briefly the basic structure and working principles of the vehicle mounted hammer source. A typical pneumatic circuit is researched and designed. And the pneumatic circuit is designed with the powerful functions of PLC, the hardware and software design are introduced. The system has advantages of strong striking force, high velocity, small gas consumption, simple structure and convenient control.

scholarly journals A real-time HIL control system on rotary inverted pendulum hardware platform based on double deep Q-network

2021 ◽  
Vol 54 (3-4) ◽  
pp. 417-428
Author(s):  
Yanyan Dai ◽  
KiDong Lee ◽  
SukGyu Lee
Keyword(s):  
Control System ◽  
Reinforcement Learning ◽  
Inverted Pendulum ◽  
Learning Algorithm ◽  
Deep Understanding ◽  
Control Engineering ◽  
Experience Replay ◽  
Real Hardware ◽  
Rotary Inverted Pendulum ◽  
Reinforcement Learning Algorithm

For real applications, rotary inverted pendulum systems have been known as the basic model in nonlinear control systems. If researchers have no deep understanding of control, it is difficult to control a rotary inverted pendulum platform using classic control engineering models, as shown in section 2.1. Therefore, without classic control theory, this paper controls the platform by training and testing reinforcement learning algorithm. Many recent achievements in reinforcement learning (RL) have become possible, but there is a lack of research to quickly test high-frequency RL algorithms using real hardware environment. In this paper, we propose a real-time Hardware-in-the-loop (HIL) control system to train and test the deep reinforcement learning algorithm from simulation to real hardware implementation. The Double Deep Q-Network (DDQN) with prioritized experience replay reinforcement learning algorithm, without a deep understanding of classical control engineering, is used to implement the agent. For the real experiment, to swing up the rotary inverted pendulum and make the pendulum smoothly move, we define 21 actions to swing up and balance the pendulum. Comparing Deep Q-Network (DQN), the DDQN with prioritized experience replay algorithm removes the overestimate of Q value and decreases the training time. Finally, this paper shows the experiment results with comparisons of classic control theory and different reinforcement learning algorithms.

Smart-valve-assisted model-free predictive control system for chiller plants

2020 ◽  
pp. 110708
Author(s):  
Dasheng Lee ◽  
Chien-Jung Lin ◽  
Chih-Wei Lai ◽  
Tsai Huang
Keyword(s):  
Control System ◽  
Predictive Control ◽  
Model Free

Application of the Real-Time EtherCAT Technology in Wind Power Control System

2012 ◽  
Vol 580 ◽  
pp. 155-159
Author(s):  
Xiang Ming Wang ◽  
Jin Chao Wang ◽  
Dong Hua Sun
Keyword(s):  
Control System ◽  
Real Time ◽  
Wind Power ◽  
High Speed ◽  
Communication Protocol ◽  
Data Communication ◽  
Data Acquisition System ◽  
Slave System ◽  
The Real ◽  
Wind Power System

In this paper, the real-time EtherCAT technology is introduced in detail, which including operating principle, communication protocol and the superiority performance of EtherCAT i.e. synchronicity, simultaneousness and high speed. To show how to design a slave system that considering the characteristics of application, the method of developing systems based no EtherCAT technology are proposed. Finally, a data acquisition system based on EtherCAT technology is designed. Application of EtherCAT technology can improve the real-time characteristics of data communication in wind power system.

Sign in / Sign up

Export Citation Format

Share Document