Integrated systems required for renewable energy use are under development. These systems impose more stringent control requirements. It is quite challenging to control a pumped storage system (PSS), which is a key component of such power systems. Because of the S-characteristic area of the PSS pump turbine, traditional proportional-integral-derivative (PID) control induces considerable speed oscillation under medium and low water heads. PSSs are difficult to model because of their nonlinear characteristics. Therefore, we propose a machine learning (ML)-based model predictive control (MPC) method. The ML algorithm is based on Koopman theory and experimental data that includes PSS state variables, and is used to establish linear relationships between the variables in high-dimensional space. Subsequently, a simple, accurate mathematical PSS model is obtained. This mathematical model is used via the MPC method to obtain the predicted control quantity value quickly and accurately. The feasibility and effectiveness of this method are simulated and tested under various operating conditions. The results demonstrate that the proposed MPC method is feasible. The MPC method can reduce the speed oscillation amplitude and improve the system response speed more effectively than PID control.
With the increasing maturity of tubular turbine power generation technology, an increasing number of industrial applications use it to recover the rich back pressure energy of a circulating cooling water system (CCWS). However, the influence of tubular turbine runaway on the stability of CCWS is still unclear. This work combines the one-dimensional (1D) method of characteristics (MOC) with the three-dimensional (3D) computational fluid dynamics (CFD), develops a 1D CCWS and 3D tubular turbine coupling simulation method, and simulates the runaway and runaway shutdown processes of tubular turbine under small flow rate condition and large flow rate condition in the real system. Results show that the main operating parameters of the system slightly change when the tubular turbine transitions from the steady state to the runaway condition. The runner’s radial force substantially increases in the runaway condition of the tubular turbine, and the phenomenon of violent oscillation is observed compared with the steady state. During the shutdown process of the tubular turbine runaway condition, the valves in parallel and series with the faulty turbine adopt a reasonable cooperative control strategy, which allows for a smooth recovery of the system operating pressure to the original steady state conditions.
An energy hub (EH), consisting of a combination of electricity, heat power,
cooling power, natural gas, and other energy sources, is considered a key
component of the Energy Internet (EI). It requires quick and accurate
optimization and control as well as a standardized and programmable model.
This study proposes an intelligent modeling method based on a directed
multigraph. This method starts from an input-output model and then
establishes a directed multigraph in which a vertex indicates energy and an
edge indicates energy conversion equipment and its parameters. Then, an
adjacency matrix is obtained by processing and simplifying the directed
multigraph. This adjacency matrix is searched using an intelligent algorithm
to obtain the coupling matrix model of the EH. A hydrodynamic laboratory
consisting of electricity, natural gas, heating, and cooling energy is used
as a case study to verify the reliability and accuracy of the modeling
process and to provide standardized data for deep learning uses in the EI.
The obtained results show that the proposed method can quickly and
effectively establish the EH model. This method is also effective when an
energy storage device is added to or removed from the EH.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.