Multi-model based predictive sliding mode control for bed temperature regulation in circulating fluidized bed boiler

Zhu, Hongxia; Shen, Jiong; Lee, Kwang Y.; Sun, Li

doi:10.1016/j.conengprac.2020.104484

Cited by 28 publications

(7 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be noted that the critic network only guides the update of the policy network during the training phase, once the TD3 completes the training process, only the policy network is used to implement control in the actual application. In TD3 the critic network is defined as, (20) In the set point tracking task, the purpose of designing dynamic control cost is to make the controlled output track the set point as quickly as possible while the control input does not change significantly. Therefore, the reward function in this paper defined by Equation 18 is a function of the dynamic control cost.…”

Section: Dynamic Costmentioning

confidence: 99%

“…As a result of the development of data-driven technologies, data-driven-based predictive control algorithms are broadly utilized in the optimization control of coal-fired power plants . Moreover, in order to adapt to the wide range of variable load operation conditions, fuzzy clustering algorithm, , subspace technology, and multimodel strategy , were introduced into the MPC framework to achieve the optimization control of coal-fired power units.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Integration Scheme for Economic Load Dispatching and Optimization Control in Coal-Fired Plants Based on Sparse Gaussian Process Model and Deep Reinforcement Learning

Dai,

Chang,

Wang

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

The economic load dispatching and optimization control of coal-fired plants are of utmost importance to achieve carbon peaking and carbon neutrality for China. This article proposes an integrated scheme for combining the economic load dispatching and optimization control of power plants as a whole. In this scheme, both dynamic cost and static cost are employed to develop the model of plant-level economic load dispatching compared with the traditional method in that only static cost is considered. Specifically, the average coal consumption rate under steady-state operation conditions is applied to represent the static cost, and the sparse Gaussian process model that can effectively balance the modeling accuracy and the modeling cost is employed to establish the coal consumption rate model, faced with the big data characteristics of the historical operation data of coal-fired units. To properly evaluate dynamic cost, the Q function that comes from the process knowledge-assisted deep reinforcement learning control method is applied, according to the definition of the Q function and the designed reward function in the reinforcement learning. Moreover, different optimization strategies are designed for operators to choose according to actual dispatching requirements. Finally, the simulation cases that are similar to the actual dispatching scenarios are designed to verify the feasibility and effectiveness of the proposed integrated scheme. The simulation results show that compared with the traditional dispatching method, the proposed integration load dispatching and optimization control method in this paper can improve both the dynamic performance of transient conditions and the economic benefits of steady-state conditions and enhance the safety and economy of power plants.

show abstract

Section: Dynamic Costmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Integration Scheme for Economic Load Dispatching and Optimization Control in Coal-Fired Plants Based on Sparse Gaussian Process Model and Deep Reinforcement Learning

Dai,

Chang,

Wang

et al. 2023

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…When the environment or operating conditions of the system change, it is expected that the controller can quickly switch to the local model that most fits the current system state. A function of error is used as a criterion to evaluate which local model is optimal [22]:…”

Section: Model Switching Rulesmentioning

confidence: 99%

Multi-Model-Based Predictive Control for Divisional Regulation in the Direct Air-Cooling Condenser

Luo

Yao

2022

Energies

View full text Add to dashboard Cite

Flow distortions caused by ambient wind can have complex negative effects on the performance of direct air-cooling condensers, which use air as their cooling medium. A control-oriented model of the direct air-cooling condenser model, considering fan volumetric effectiveness and plume recirculation rate, was developed, and its linearization model was derived. The influences of fan volumetric effectiveness and plume recirculation rate on backpressure were analyzed, and the optimal backpressure was calculated. To improve both the transient performance and steady-state energy saving of the condenser, a multi-model-based predictive control strategy was proposed to divisionally adjust the fan array. Four division schemes of the direct air-cooling fan array constituted the local models, and in each division scheme, axial fans were divided into three groups according to the wind direction: windward fans, leeward fans, and other fans. The simulation results showed that the turbine backpressure can be increased by 15 kPa under the influence of plume recirculation and the reduction of the fan volumetric efficiency. The fan division adjustment strategy can achieve satisfactory control performance with switching rules.

show abstract

“…At present, there are many technologies to deal with uncertainty and disturbance, including sliding mode control (SMC), neural network, adaptive fuzzy control, etc. Among them, SMC is widely used as an excellent robust control method due to its mature performance in system uncertainty and disturbance rejection [3][4][5][6]. In [7], the hierarchical SMC based on backstepping is presented to realize the balance and movement of the ballbot with model uncertainty and disturbance.…”

Section: Introductionmentioning

confidence: 99%

A Novel Decentralized Fixed-time Tracking Control for Modular Robot Manipulators: Theoretical and Experimental Verification

2023

Int. J. Control Autom. Syst.

View full text Add to dashboard Cite

This paper proposes a novel decentralized fixed-time tracking control approach, which realizes the advantages of modular robot manipulators (MRMs) with fixed-time convergence, strong robustness, and high tracking performance. First, to estimate the total uncertainty of MRMs, the fixed-time disturbance observer based on the extended state is developed. Then, combined with the disturbance observer, a novel decentralized control method based on fixed-time control strategy was developed to achieve the global fixed-time convergence of MRMs. And, stability analysis based on Lyapunov is used to obtain the fixed-time stability and convergence time of MRMs. Finally, numerical analysis and experiment respectively verify the excellent tracking ability of the proposed decentralized fixed-time tracking control algorithm.

show abstract

Multi-model based predictive sliding mode control for bed temperature regulation in circulating fluidized bed boiler

Cited by 28 publications

References 45 publications

Integration Scheme for Economic Load Dispatching and Optimization Control in Coal-Fired Plants Based on Sparse Gaussian Process Model and Deep Reinforcement Learning

Integration Scheme for Economic Load Dispatching and Optimization Control in Coal-Fired Plants Based on Sparse Gaussian Process Model and Deep Reinforcement Learning

Multi-Model-Based Predictive Control for Divisional Regulation in the Direct Air-Cooling Condenser

A Novel Decentralized Fixed-time Tracking Control for Modular Robot Manipulators: Theoretical and Experimental Verification

Contact Info

Product

Resources

About