Systems Modeling Using Deep Elman Neural Network

Salah, Latifa Belhaj; Fourati, Fathi

doi:10.48084/etasr.2455

Cited by 10 publications

(8 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where α, β 1 and β 2 are the self-connected feedback gain factors of the three context layers. Equations (16)(17)(18) can combine past information with information at the current time step, and α, β 1 and β 2 can adjust the weight of past information. The inheritance of historical state is superimposed on the context layer of the current time step through a parameter, which can realize the memory of the historical state.…”

Section: Methods Of Full Feedbackmentioning

confidence: 99%

“…Same as the Jordan-NARX mode, the x k and y k at each time step is related to the state and output at last time step. If it goes back all the way, it will be related to the output at previous time step, for the reason that t d can be set to 1, If so, the context layer can be simplified to one-step time delay feedback, (16)(17)(18) are simplified as…”

Section: Methods Of Full Feedbackmentioning

confidence: 99%

“…Many scholars have researched and improved it. Salah et al proved that the deep ENN with two hidden layers can better simulate dynamic systems [16]. Li et al proposed a hybrid Elman-long short-term memory (LSTM) for predicting the remaining battery life [17].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Full Feedback Dynamic Neural Network with Exogenous Inputs for Dynamic Data‐Driven Modeling in Nonlinear Dynamic Power Systems

Zhang

Zhao

et al. 2023

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Dynamic neural networks (DNNs) are widely used in data‐driven modeling of nonlinear control systems. Due to the complexity of the actual operating nonlinear power systems, rigorous dynamic models are always unknown. DNNs can focus on methods that only use input and output information to establish accurate dynamic models and reduce noise in measured data, which is called data‐driven modeling. The core of the DNN is the feedback with memory function. This paper analyzes the traditional Elman neural network (ENN) and nonlinear auto‐regression with exogenous input (NARX) neural network with different structure feedback structures, and proposes a full feedback dynamic neural network (FF‐DNN) with exogenous input. Eight different kinds of neural networks (including ENN, NARX, etc.) are compared and analyzed. The eight kinds of neural networks are applied on the experimental data of the DC‐AC inverter and the power system of Zhejiang Juchuang Smart Technology Company Park in Wenzhou. The experimental results are used to compare the performance of the data‐driven models established by eight different kinds of neural networks under different noise conditions, verify the robustness and generalization performance of dynamic data‐driven modeling based on FF‐DNN, and demonstrate the feasibility and effectiveness of FF‐DNN in actual power systems. © 2023 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

show abstract

Section: Methods Of Full Feedbackmentioning

confidence: 99%

Section: Methods Of Full Feedbackmentioning

confidence: 99%

See 1 more Smart Citation

Full Feedback Dynamic Neural Network with Exogenous Inputs for Dynamic Data‐Driven Modeling in Nonlinear Dynamic Power Systems

Zhang

Zhao

et al. 2023

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

show abstract

“…A. Plant Network Neural networks are known as a powerful technique to model a system with a mathematical model unknown or difficult to build [20,21]. In this section, a neural network is used to model the plant which consists of the pile, the excavator, and the tracking controller.…”

Section: Network Training and Simulationmentioning

confidence: 99%

Recurrent Neural Network-based Path Planning for an Excavator Arm under Varying Environment

Tran

Nguyen

2021

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

This paper proposes an algorithm to generate the reference trajectory based on recurrent neural networks for an excavator arm working in a dynamic environment. Firstly, the dynamic of the plant which includes the tracking controller, the arm, and the pile is appropriated by a recurrent neural network. Next, the recurrent neural network combined with a Model Reference Adaptive Controller (MRAC) is used to calculate the reference trajectory for the system. In this paper, the generated trajectory is changed depending on the variation of the pile to maximize the dug weight. This algorithm is simple but effective because it only needs information about the weight at each duty cycle of the excavator. The efficiency of the overall system is verified through simulations. The results show that the proposed scheme gives a good performance, i.e. the dug weight always remains at the desired value (nominal load) as the pile changes its shape during working time.

show abstract

“…The Gated Recurrent Unit (GRU), a variant of RNN, is selected as the basic ML model for the proposed E2E architecture. RNN is selected due to its efficient information handling with smaller context [19]. GRU is computationally simpler as compared to other RNN variants.…”

Section: B the E2e ML Modelmentioning

confidence: 99%

An End-to-End Machine Learning based Unified Architecture for Non-Intrusive Load Monitoring

Wali

Haq

Kazmi

et al. 2021

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

Non-Intrusive Load Monitoring (NILM) or load disaggregation aims to analyze power consumption by decomposing the energy measured at the aggregate level into constituent appliances level. The conventional load disaggregation framework consists of signal processing and machine learning-based pipelined architectures, respectively for explicit feature extraction and decision making. Manual feature selection in such load disaggregation frameworks leads to biased decisions that eventually reduce system performance. This paper presents an efficient End-to-End (E2E) approach-based unified architecture using Gated Recurrent Units (GRU) for NILM. The proposed approach eliminates explicit feature engineering and has a unified classification and prediction model for appliance power. This eventually reduces the computational cost and enhances response time. The performance of the proposed system is compared with conventional algorithms' with the use of recall, precision, accuracy, F1 score, the relative error in total energy and Mean Absolute Error (MAE). These evaluation metrics are calculated on the power consumption of top priority appliances of Reference Energy Disaggregation Dataset (REDD). The proposed architecture with an overall accuracy of 91.2 and MAE of 25.23 outperforms conventional methods for all electrical appliances. It has been showcased through a series of experiments that feature extraction and event-based approaches for NILM can readily be replaced with E2E deep learning techniques allowing simpler and cost-efficient implementation pathways.

show abstract

Systems Modeling Using Deep Elman Neural Network

Cited by 10 publications

References 34 publications

Full Feedback Dynamic Neural Network with Exogenous Inputs for Dynamic Data‐Driven Modeling in Nonlinear Dynamic Power Systems

Full Feedback Dynamic Neural Network with Exogenous Inputs for Dynamic Data‐Driven Modeling in Nonlinear Dynamic Power Systems

Recurrent Neural Network-based Path Planning for an Excavator Arm under Varying Environment

An End-to-End Machine Learning based Unified Architecture for Non-Intrusive Load Monitoring

Contact Info

Product

Resources

About