High gain requirements and high field tokamak experiments

Cohn, D.R.

doi:10.1007/bf02215846

Cited by 5 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This factor is a measure of how close the thermonuclear system is to true ignition conditions. In a practical thermonuclear system it is expected that Q > 25, in order to be economically viable [26]. The gain value associated with the nearly ignited nominal operating point obtained with the resulting NN-dynamical system configuration here, is Q ≈ 180.…”

Section: Neural Network Training Processmentioning

confidence: 69%

See 1 more Smart Citation

Stabilization of burn conditions in a thermonuclear reactor using artificial neural networks

Vitela¹,

Martinell²

1998

Plasma Phys. Control. Fusion

View full text Add to dashboard Cite

In this work we develop an artificial neural network (ANN) for the feedback stabilization of a thermonuclear reactor at nearly ignited burn conditions. A volume-averaged zero-dimensional nonlinear model is used to represent the time evolution of the electron density, the relative density of alpha particles and the temperature of the plasma, where a particular scaling law for the energy confinement time previously used by other authors, was adopted. The control actions include the concurrent modulation of the D-T refuelling rate, the injection of a neutral He-4 beam and an auxiliary heating power modulation, which are constrained to take values within a maximum and minimum levels. For this purpose a feedforward multilayer artificial neural network with sigmoidal activation function is trained using a back-propagation throughtime technique. Numerical examples are used to illustrate the behaviour of the resulting ANNdynamical system configuration. It is concluded that the resulting ANN can successfully stabilize the nonlinear model of the thermonuclear reactor at nearly ignited conditions for temperature and density departures significantly far from their nominal operating values. The NN-dynamical system configuration is shown to be robust with respect to the thermalization time of the alpha particles for perturbations within the region used to train the NN.

show abstract

Section: Neural Network Training Processmentioning

confidence: 69%

“…∂Ŝ aux (25) and (26) for the relative importance of the normalized auxiliary heating. It is apparent that the importance of the different control variables is a function of the current state of the system.…”

Section: The Dynamical System Modelmentioning

confidence: 99%

Stabilization of burn conditions in a thermonuclear reactor using artificial neural networks

Vitela¹,

Martinell²

1998

Plasma Phys. Control. Fusion

View full text Add to dashboard Cite

show abstract

“…In order to be economically viable, a gain factor of Q G > 25 is desired in a practical thermonuclear reactor [16]. In figure 2 we show the behaviour of Q G under steadystate conditions as a function of the energy confinement time for the system described by equations ( 8)- (14).…”

Section: Thermonuclear Reactor Modelmentioning

confidence: 99%

Burn conditions stabilization with artificial neural networks of subignited thermonuclear reactors with scaling law uncertainties

Vitela

Martinell

2001

Plasma Phys. Control. Fusion

View full text Add to dashboard Cite

In this work it is demonstrated that robust burn control in long-pulse operations of subignited thermonuclear reactors can be achieved with radial basis neural networks (RBNNs) composed of Gaussian nodes in the hidden layer and sigmoidal units in the output layer. The results reported here correspond to a volume-averaged zero-dimensional nonlinear model of a subignited fusion reactor with design parameters corresponding to those of the ITER-EDA group. The control actions are implemented through the concurrent modulation of the D-T refuelling rate, a neutral 4 He beam and an auxiliary heating power, constrained to lie below maximum allowable levels.It is shown that the resulting network provides feedback stabilization over a wide range of energy confinement times for plasma density and temperature excursions significantly far from their nominal operating values. The results show that the RBNN feedback-controlled nonlinear system is stable regardless of any particular scaling law, as long as the confinement time lies within the scope of the training region. In addition, it also shows robustness with respect to noise in the energy confinement time value fed into the controller during simulated transients of a thermonuclear system using a particular ELMy scaling law, as well as with respect to the thermalization time of the alpha particles produced by fusion.

show abstract

“…The uncertainty of the plasma transport processes and alpha heating effectiveness, [2] at the required thermonuclear conditions, and the coupling between the confinement scaling and the characteristics of the machine design raise strong questions of program flexibility especially for a project as costly as ITER. It is therefore important that some of these questions be addressed prior to the design of a technology oriented fusion experiment.…”

Section: Introductory Remarksmentioning

confidence: 99%

Possibilities for long pulse ignited tokamak experiments using resistive magnets

Chaniotakis¹,

Bromberg²,

Cohn³

1994

J Fusion Energ

View full text Add to dashboard Cite

High gain requirements and high field tokamak experiments

Cited by 5 publications

References 6 publications

Stabilization of burn conditions in a thermonuclear reactor using artificial neural networks

Stabilization of burn conditions in a thermonuclear reactor using artificial neural networks

Burn conditions stabilization with artificial neural networks of subignited thermonuclear reactors with scaling law uncertainties

Possibilities for long pulse ignited tokamak experiments using resistive magnets

Contact Info

Product

Resources

About