Survey on coke oven gas-collector pressure control

Liu, Xinming; Gao, Xianwen; Wang, Wei; Wang, Jiesheng

doi:10.1109/ccdc.2011.5968238

Cited by 2 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fig. 2 Step responses of the system The step response model denoted as a ij =[ a ij (1), ..., a ij (N)] T can be obtained from Figure 2 by a sampling period T. Let y i = ∆P i , u j = ∆R j , equation ( 2) and ( 3) are the prediction model, where a model period N, a predictive period P and a control period M are chosen.…”

Section: Prediction Modelmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Matrix Control for Multiple Gas Collectors of Coke Ovens

Dong

Jiang

2014

AMM

View full text Add to dashboard Cite

The pressure of gas collector in coke oven is an important industrial parameter in coking process, even in the whole metallurgical industry. Due to the complex characteristics of the multiple gas collectors pressure system, conventional control strategies meet challenges when the pressures in collector pipes are required to be kept at the appropriate operating point. Dynamic matrix control (DMC), which focus on the complicated industril process and has achieved successful and mature applications, is the most widely-used model predictive control (MPC). This paper introduce DMC to the multiple gas collectors pressure system. The simulation results in a three-ovens system show the feasibility and effectiveness of DMC.

show abstract

Section: Prediction Modelmentioning

confidence: 99%

“…The coke quality will deteriorate and the architectural material of the oven will be eroded by chemical reaction with air. Normally, the pressure in gas collector pipe should be controlled in the set point within a range of 20 ± Pa [1].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Matrix Control for Multiple Gas Collectors of Coke Ovens

Dong

Jiang

2014

AMM

View full text Add to dashboard Cite

show abstract

“…In this paper, a distributed reinforcement learning control algorithm based on AHC (adaptive heuristic critic) and radial basis function (RBF) was proposed for the gas collector pressure of coke ovens. Compared with other methods [8][9][10][11], minimal computation is required for selecting actions and learning the explicit representation of stochastic strategies. Also, the MATLAB simulation results show that the algorithm for the gas collector pressure of coke ovens has better stability.…”

mentioning

confidence: 99%

“…There is a coupling relationship in the gas collecting process. It often makes the interference between each control variable and causes wide fluctuations, which seriously affect the normal production of coke ovens [8,12].…”

mentioning

confidence: 99%

Reinforcement learning control for gas collector pressure of coke ovens

Qin

Leqiang

et al. 2014

The 26th Chinese Control and Decision Conference (2014 CCDC)

View full text Add to dashboard Cite

The gas collector pressure control of coke ovens is a complex industrial process, which has nonlinear, time-varying and strong coupling characteristics. Moreover, the gas collector pressure is sensitive to environment, and the pressure values vary irregularly and dramatically. Keeping the gas collector pressure values in a given range has important effects on the gas utilization efficiency and safety production. Recently years, many intelligent control technologies have been applied to the actual industrial production, and achieve good control effect. A hybrid multilevel intelligent control strategy was proposed in Ref [1]: a fuzzy control algorithm with variable and adjustable factors was adopted in the loop control level, and a manifold suction supervisory control was adopted in the main control level, as well as in-group and between-group decoupling rules in the decoupling level. According to the characteristics of suction control and gas pressure of a coke oven blast cooling system, a new fuzzy adaptive PID control algorithm for gas collector pressure control of coke ovens was presented in Ref [2], in which a fuzzy decoupling method was adopted for decoupling control. In Ref [3], on the analysis of complex pressure coupling relationship between gas collectors, a compensation decoupling algorithm based on rules for parallel production of coke ovens was proposed. The reinforcement learning is widely used in the field of artificial intelligent and machine learning [4][5][6][7]. The reinforcement learning algorithm provides reinforcement signals for the current action through environment and evaluates its effect on the future without mathematical models and prior knowledge of dynamic models. Due to rare external environment information, the reinforcement learning must rely on its

show abstract

Survey on coke oven gas-collector pressure control

Cited by 2 publications

References 7 publications

Dynamic Matrix Control for Multiple Gas Collectors of Coke Ovens

Dynamic Matrix Control for Multiple Gas Collectors of Coke Ovens

Reinforcement learning control for gas collector pressure of coke ovens

Contact Info

Product

Resources

About