A new adaptive controller based on distributed deep reinforcement learning for PEMFC air supply system

Li, Jiawen; Yu, Tao

doi:10.1016/j.egyr.2021.02.043

Cited by 62 publications

(24 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, as the PEMFC system is a complex system with multiple inputs and outputs, nonlinear, approximately east, with random disturbances, time-varying and high order (Yang et al, 2019b;Li and Yu, 2021a), it is difficult to achieve satisfactory control results with traditional PID control (Li et al, 2021). In order to obtain accurate and fast response results, various advanced control strategies have been applied in the research of PEMFC output control strategies.…”

Section: Introductionmentioning

confidence: 99%

Control Method for PEMFC Using Improved Deep Deterministic Policy Gradient Algorithm

2021

Front. Energy Res.

Self Cite

View full text Add to dashboard Cite

A data-driven PEMFC output voltage control method is proposed. Moreover, an Improved deep deterministic policy gradient algorithm is proposed for this method. The algorithm introduces three techniques: Clipped multiple Q-learning, policy delay update, and policy smoothing to improve the robustness of the control policy. In this algorithm, the hydrogen controller is treated as an agent, which is pre-trained to fully interact with the environment and obtain the optimal control policy. The effectiveness of the proposed algorithm is demonstrated experimentally.

show abstract

Section: Introductionmentioning

confidence: 99%

Control Method for PEMFC Using Improved Deep Deterministic Policy Gradient Algorithm

2021

Front. Energy Res.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The air compressors (AC) play a significant role in essential functions like fuel injection and metal finishing in the aircraft's design [1]. The ACs are used widely in thermal plants [2], power generation systems [3], vehicle propulsion [4] and pipeline systems [5], etc. In building an effective quality control system, the compressor simulation plays an essentialrole in evaluating the tolerable pressure by the different components of the aircraft while in transit [6].…”

Section: Introductionmentioning

confidence: 99%

Modeling a Fault Detection Predictor in Compressor using Machine Learning Approach based on Acoustic Sensor Data

N¹,

K²,

L³

2021

IJACSA

View full text Add to dashboard Cite

Proper functioning of the air compressor ensures stability for many critical systems. The ill-effect of the breakdown caused by the wear and tear in the system can be mitigated if there exists an effective automated fault classification system. Traditionally, the simulation-based methods help to extend to identify the faults; however, those systems are not so effective enough to build real-time adaptive methods for the fault detection and its type. This paper proposes an effective model for the fault classification in the air compressor based on the realtime empirical acoustic sensor time-series data were taken on a sampling frequency of 50Khz. In the proposed work, the timeseries datais transformedinto the frequency domain using fast Fourier transforms,where half of the signals are considered due to its symmetric representation. Afterward, a masking operation is carried out to extract significant feature vectors fed to the multilayer perception neural network. The uniqueness of the proposed system is that it requires less trainable parameters, thus reduces the training time and imposes lower memory overhead. The model is benchmarked with performance metric accuracy, and it is found that the proposed masked feature setbased MLP-ANN exhibits an accuracy of 91.32%. In contrast, the LSTM based fault classification model gives only 83.12% accuracy, takes more training time, and consumes more memory. Thus, the proposed model is realistic enough to be considered a real-time monitoring system of the fault and control. However, other performance metrics like precision, recall, and F1-Score are also promising with the LSTM based fault classifier.

show abstract

“…Proportional-Integral-Derivative-PID [29,46,[48][49][50][51][52][53]. Adding an integrator to PD control means PID control [54].…”

mentioning

confidence: 99%

“…PIDs and derivative algorithms are more practical since they operate with basic control methods [53]. The simplicity and ease of installation of this controller are its main advantages [58].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Voltage and Reactive Power Algorithms in Low Voltage Networks

Stanelytė

Radziukynas

2022

Energies

View full text Add to dashboard Cite

The rapid development of renewable energy sources and electricity storage technologies is further driving the change and evolution of traditional energy systems. The aim is to interconnect the different electricity systems between and within countries to ensure greater reliability and flexibility. However, challenges are faced in reaching it, such as the power grid complexity, the system control, voltage fluctuations due to the reverse power flow, equipment overloads, resonance, incorrect island setting, and the diversity of user needs. The electricity grid digitalization in the market also requires the installation of smart devices to enable real-time information exchange between the generator and the user. Inverter-based distributed generation (DG) may be used to control the grid voltage. Smart PV inverters have the capability to supply both inductive and capacitive reactive power to control the voltage at the point of interconnection with the grid, and only technical parameters of smart PV inverters limit this capability. Reactive power control is related to ensuring the quality of voltage in the electricity distribution network and compensating reactive power flows, which is a technical–economic aspect. The goal of this research is to present an analysis of controllers that supply reactive power to the electrical grid via PV systems. This research analyzes recent research on local, centralized, distributed, and decentralized voltage control models in distribution networks. The article compares various approaches and highlights their advantages and disadvantages. The voltage control strategies and methodologies mentioned in the article can serve as a theoretical foundation and provide practical benefits for PV system development in distribution networks. The results of the research show that the local voltage control approach, as well as linear and intelligent controllers, has great potential.

show abstract

A new adaptive controller based on distributed deep reinforcement learning for PEMFC air supply system

Cited by 62 publications

References 41 publications

Control Method for PEMFC Using Improved Deep Deterministic Policy Gradient Algorithm

Control Method for PEMFC Using Improved Deep Deterministic Policy Gradient Algorithm

Modeling a Fault Detection Predictor in Compressor using Machine Learning Approach based on Acoustic Sensor Data

Analysis of Voltage and Reactive Power Algorithms in Low Voltage Networks

Contact Info

Product

Resources

About