1篇
您的检索式：作者名="Wilhelm Tegethoff"
|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Quasi-optimal control of a solar thermal system via neural networks✩显示文摘The optimal control of complex thermal energy systems is a challenge due to their dynamic behavior andconstantly changing boundary conditions. To maximize the energy efficiency of such a dynamic system, optimaltrajectories for the controlled variables are needed. Extensive system knowledge is required to model the systemaccurately enough to be able to compute optimal trajectories. The high computational cost of computingoptimal control solutions with traditional approaches, especially with changing boundary conditions, oftenmakes this approach unusable for applications with limited computational power, such as real-time applicationson electronic control units (ECUs). This study investigates a possible solution to this challenge using a simplifiedexample system. Optimal control solutions for different boundary and initial conditions are generated forthe selected solar thermal system using a direct multiple shooting algorithm. Based on Bellman’s optimalityprinciple, the generated solutions are transformed into a data set of optimal state–action pairs. On this basis,different types of neural networks are trained, specifically a feed-forward, a recurrent, and a radial basisfunction network. Thus, data generation and training can be performed offline, and the required online computations are significantly reduced since the evaluation of a trained neural network requires comparatively lowcentral processing unit (CPU) power. The trained neural network controllers are tested for their ability to outputnear-optimal control actions based on the current system state. The feed-forward and recurrent neural networksshow promising initial results in this regard. Open questions and the need for improvements are discussed. | Jana Friese Niklas Brandt Andreas Schulte Christian Kirches Wilhelm Tegethoff Jürgen Köhler | 2023 | Energy and AI2023，12，2： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员