Refine
Document Type
Language
- English (6)
Has Fulltext
- no (6)
Reviewed
Keywords
- current control (2)
- deep deterministic policy gradient (DDPG) (2)
- deep reinforcement learning (2)
- permanent magnet synchronous machine (PMSM) (2)
- power electronics (2)
- Couplings ; Switches; Predictive models ; Mathematical model ; Rotors ; Real-time systems ; Prediction algorithmso (1)
- Model predictive control, FCS-MPC, VSP2CC, VV-MPC, multi-phase, PMS (1)
- Multi-phase machines (1)
- Open science (1)
Institute
This article presents a flux linkage-based direct model predictive current control approach that achieves favorable performance both during steady-state and transient operation. The former is achieved by computing the optimal time instants at which a new switch position is applied to the converter. To this end, the future current behavior is not computed based on the machine inductances or inductance look-up tables; instead, flux linkage maps are utilized to predict the trajectory of the magnetic flux linkage, and subsequently of the current. This is advantageous for electric drives with noticeable magnetic nonlinearity in terms of saturation and/or cross-coupling effects. Hence, by using flux linkage maps in the prediction process, the evolution of the stator current can be calculated more accurately, enabling the controller to make better switching decisions. Moreover, the discussed predictive controller exhibits excellent dynamic performance owing to its direct control nature, i.e., the control and modulation tasks are performed in one computational stage rendering a dedicated modulation stage redundant. Three different drive systems based on permanent magnet synchronous motors are examined to demonstrate the effectiveness of the presented control approach.
Control of multi-phase machines is a challenging topic due to the high number of controlled variables. Conventional control methods, such as field-oriented control (FOC), address this issue by introducing more control loops. This, however, increases the controller design complexity, while the tuning process can become cumbersome. To tackle the above, this paper proposes a deep deterministic policy gradient algorithm based controller that fulfills all the control objectives in one computational stage. More specifically, the proposed approach aims to learn a suitable current control policy for six-phase permanent magnet synchronous machines to simplify the commissioning of the drive system. In doing so, physical limitations of the drive system can be accounted for, while the compensation of imbalances between the two three-phase subsystems is rendered possible. After validating the training results in a controller-in-the-loop environment, test bench measurements are provided to demonstrate the effectiveness of the proposed controller. As shown, favorable steady-state and dynamic performance is achieved that is comparable to that of FOC. Therefore, as indicated by the presented results, reinforcement learning-based control approaches for multi-phase machines is a promising research area.
This paper presents a current control approach for permanent magnet synchronous machines (PMSMs) using the deep reinforcement learning algorithm deep deterministic policy gradient (DDPG). The proposed method is designed by examining different training setups regarding the reward function, the observation vector, and the actor neural network. In doing so, the impact of the different design factors on the steady-state and dynamic behavior of the system is assessed, thus facilitating the selection of the setup that results in the most favorable performance. Moreover, to provide the necessary insight into the controller design, the entire path from training the agent in simulation, through testing the control in a controller-in-the-loop (CIL) environment, to deployment on the test bench is described. Subsequently, experimental results are provided, which show the efficacy of the presented algorithm over a wide range of operating points. Finally, in an attempt to promote open science and expedite the use of deep reinforcement learning in power electronic systems, the trained agents, including the CIL model, are rendered openly available and accessible such that reproducibility of the presented approach is possible.
In this paper, a flux linkage-based direct model predictive current control approach is presented for small permanent magnet synchronous motor (PMSM) drives. The method aims to minimize the current ripples at steady state by deciding on the optimal switching instant, while exhibiting fast dynamic behavior during transients. To this end, the future trajectory of the stator current is not computed based on the machine inductances or inductance look-up tables, but on the changes of the magnetic flux linkage by utilizing flux linkage maps. As shown, the proposed method can be particularly advantageous for electric drives with a noticeable nonlinearity in terms of saturation and/or cross-coupling effects since it allows for a significantly increased prediction accuracy, which leads to an improved steady-state performance as indicated by the reduced current distortions.
This paper presents two rapid control prototyping (RCP) use cases facilitated by the open-source platform UltraZohm. The openly available UltraZohm development frame-
work eases the transition from simulation to the test bench. The framework offers the integration of automatic code generation for field-programmable gate arrays (FPGAs), either by using Simulink models based on the HDL Coder, or by synthesizing C++ code into VHDL via the Vivado high-level synthesis tool. The first use case focuses on the implementation details of an on-chip controller-in-the-loop setup, where a permanent magnetsynchronous machine is emulated in the FPGA with a sampling frequency of 2 MHz. The second use case presents an efficient real-time implemen-tation of the sphere decoding algorithm employed to solve the long-horizon finite control set model predictive control problem for a three-level neutral point clamped inverter driving an induction machine. Experimental results based on a small-scale prototype confirm that the algorithm can be executed in real time on the FPGA, with an execution time of a few tens of microseconds. Both use cases highlight the benefits of using a high-performance RCP platform for research in power electronics and their control.
Finite control set model predictive control (FCS-MPC) is a promising method for the control of multi-phase machines, due to its capability to directly account for nonlinearities and multiple controlled variables. To overcome the drawback of high current ripples and excitation of harmonic currents in the so-called xy-subsystem, several methods have been proposed in the literature so far. This paper proposes an MPC-based method that achieves high granularity of switching by not only switching at the discrete time steps, but also within the sampling interval. In doing so, the discussed algorithm, referred to as variable switching point current control (VSP 2 CC), produces low current distortions, while still keeping the advantages of conventional FCS-MPC, such as fast dynamic behavior during transients. To highlight the above, VSP 2 CC is applied to a six-phase permanent magnet synchronous machine (PMSM) and compared with conventional FCS-MPC and MPC that employs virtual voltage vectors (VV-MPC).
