Intelligent coordinated controller design for a 600MW supercritical boiler unit based on expanded-structure neural network inverse models

Ma, Liangyu; Lee, Kwang Y.; Wang, Zhiyan

doi:10.1016/j.conengprac.2015.09.002

Cited by 37 publications

(16 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Linearization method is usually then employed to reduce the computational requirements. Theory presents many advanced controllers based on model predictive , genetic, neural , adaptive, backstepping and sliding mode algorithms . However, the cascade enhanced PID algorithm is the most popular scheme being used to control commercial boilers mainly due to its ability to handle large modeling errors/assumptions and unforeseen disturbances.…”

Section: Modelmentioning

confidence: 99%

Comprehensive dynamic modeling, simulation, and validation for an industrial boiler incident investigation

Taimoor

Alghamdi

Farooqi

et al. 2019

Process Safety Progress

View full text Add to dashboard Cite

Industrial boilers simulation can serve number of purposes like training, optimization, HAZOP studies, and incident investigation. Simulation including trip logics, interlockings, safety devices, start‐up and shutdown procedure is presented in this work. Simulation is directly accomplished in dynamic mode to benefit from the holdup approach to avoid anomalies because of recycling. The industrial DCS/PLC diagrams are replicated to imitate the boiler‐integrated behavior. Trip logics, start‐up and shutdown procedures are programmed using event scheduler. The inbuilt pressure relief module validates the simulated PSVs and rupture disc capacities. The model is then verified at three stages including ‘steady state’ achievement in dynamic mode, controller validation by start‐up and shut down procedures and finally by direct industrial data under deviant conditions. Where an unfortunate event is a concern, it also provides an opportunity to ponder and to evolve at various levels. Operational simulation of any such incident may help in getting a deep insight and thus to take accurate countermeasures. One such attempt is done in this work. A boiler accident has been reported. The complete response of the controllers and interlockings/trip system is imitated. The obtained results were compared with the chain of events that took place. © 2019 American Institute of Chemical Engineers Process Saf Prog: e12040 2019

show abstract

Section: Modelmentioning

confidence: 99%

Comprehensive dynamic modeling, simulation, and validation for an industrial boiler incident investigation

Taimoor

Alghamdi

Farooqi

et al. 2019

Process Safety Progress

View full text Add to dashboard Cite

show abstract

“…Furthermore, even if the accurate model of the original system was acquired, it is often quite difficult to solve the inverse model [22]. At the same time, artificial neural networks (ANNs) have been widely applied in modeling and control of complex dynamic systems with impressive adaptive learning capability and strong fault tolerance ability [23]. Combining them, the inverse control method based on ANNmodel could overcome the difficulty of solving the inverse problem, thus showing a promising future in applications.…”

Section: Introductionmentioning

confidence: 99%

Output Voltage Control of BESS Inverter in Stand-Alone Micro-Grid Based on Expanded Inverse Model

Wang

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

This paper investigates robust output voltage control of battery energy storage systems (BESS) inverter in stand-alone micro-grid. The transfer function model between the output voltage and duty cycle of the BESS inverter is established, base on which the main factors affecting the output voltage are analyzed theoretically. Then, the expanded inverse model of the BESS inverter is developed based on BP neural network, and the gravity search algorithm (GSA) is employed to search the initial values of the network's parameters in the training process. Further, a control method for the output voltage of BESS inverter is proposed by putting the expanded inverse model in series with the original system as well as performing the single-loop control with PI controller. Both simulation experiment results and prototype experiment results show that the proposed expanded inverse model control method has a strong capability of disturbance rejection and could ensure the high power quality for the output voltage of the BESS inverter. INDEX TERMS BESS inverter, inverse model, BP neural network, gravity search algorithm, load disturbance.

show abstract

“…However, it is extremely challenging to control a USC boiler-turbine unit because of the nonlinearity, the coupling among multi-variables, and the hard constraints on the manipulated variables. To overcome these issues, various control strategies for a boiler-turbine system have been studied, such as robust control [2], optimal control [3], intelligent control [4], sliding model control [5], active disturbance rejection control [6], model predictive control (MPC) [7], etc. The aforementioned methods have significantly improved the performance in some respects but also suffer from some deficiencies.…”

Section: Introductionmentioning

confidence: 99%

A Sustainable Power Plant Control Strategy Based on Fuzzy Extended State Observer and Predictive Control

et al. 2018

View full text Add to dashboard Cite

The control of an ultra-supercritical (USC) boiler–turbine power plant is critical in maintaining the safety of the sustainable power grid. However, it is challenging due to the internal nonlinearity, hard manipulation constraints, and widespread uncertainties. To this end, a fuzzy extended state observer (FESO)-based stable fuzzy predictive control (SFPC) approach is developed in this paper. First, the control difficulties of the USC boiler–turbine unit are analyzed. Then, based on a Takagi–Sugeno (T–S) fuzzy model, a new FESO is developed for nonlinear systems to achieve a more precise observation performance. The gain of FESO is determined by solving a series of linear matrix inequalities, while guaranteeing the stability of FESO. Then, by combining the proposed FESO with the SFPC, an integrated FESO–SFPC algorithm is devised. The disturbance rejection ability of the FESO–SFPC algorithm is analyzed theoretically. Simulation results on a 1000 MW USC boiler–turbine power plant model further validate the effectiveness of the proposed method.

show abstract

Intelligent coordinated controller design for a 600MW supercritical boiler unit based on expanded-structure neural network inverse models

Cited by 37 publications

References 21 publications

Comprehensive dynamic modeling, simulation, and validation for an industrial boiler incident investigation

Comprehensive dynamic modeling, simulation, and validation for an industrial boiler incident investigation

Output Voltage Control of BESS Inverter in Stand-Alone Micro-Grid Based on Expanded Inverse Model

A Sustainable Power Plant Control Strategy Based on Fuzzy Extended State Observer and Predictive Control

Contact Info

Product

Resources

About