A Novel Torque Distribution Strategy Based on Deep Recurrent Neural Network for Parallel Hybrid Electric Vehicle

Kong, Huifang; Yao, Fang; Fan, Lei; Wang, Hai; Zhang, Xiaoxue; Hu, Jie

doi:10.1109/access.2019.2917545

Cited by 20 publications

(10 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the LSTM algorithm overcomes the problems of RNN gradient vanishing and gradient explosion, its structure is too complex and the model parameters are too many, so the training time is doubled. Especially in the face of largescale data set analysis and processing requirements, this method is difficult to meet the actual computing speed requirements [20,21]. erefore, in order to solve the practical application problems of the above industrial big data technology and the performance problems of data mining algorithms, this paper constructs a small private cloud platform, which is built on the current mainstream Hadoop distributed computing platform.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Visualization Optimization Management Simulation of Big Data Stream on Industrial Heritage Cloud Platform

Gao

2020

Complexity

View full text Add to dashboard Cite

Recently, the development and utilization of industrial heritage resources by using big data has gradually attracted attention. This paper proposes a real-time visualization optimization management simulation of an industrial heritage cloud platform, which realizes the high reliability and diversified storage and utilization of industrial big data by the cloud data distributed storage subsystem. The big data prediction model of the GRU neural network based on a spark distributed framework is constructed to realize the prediction of industrial genetic data. Finally, visualization technology can provide information supporting for industrial production by displaying effective information intuitively. The model’s effectiveness and reliability are verified by simulation.

show abstract

Section: Introductionmentioning

confidence: 99%

Real-Time Visualization Optimization Management Simulation of Big Data Stream on Industrial Heritage Cloud Platform

Gao

2020

Complexity

View full text Add to dashboard Cite

show abstract

“…An energy management strategy model based on a deep recursive neural network was proposed for the optimal [65]. Better performance in terms of fuel economy and accuracy was provided.…”

Section: Parallel Hybrid Powertrainmentioning

confidence: 99%

Review and Development of Electric Motor Systems and Electric Powertrains for New Energy Vehicles

et al. 2021

View full text Add to dashboard Cite

This paper presents a review on the recent research and technical progress of electric motor systems and electric powertrains for new energy vehicles. Through the analysis and comparison of direct current motor, induction motor, and synchronous motor, it is found that permanent magnet synchronous motor has better overall performance; by comparison with converters with Si-based IGBTs, it is found converters with SiC MOSFETs show significantly higher efficiency and increase driving mileage per charge. In addition, the pros and cons of different control strategies and algorithms are demonstrated. Next, by comparing series, parallel, and power split hybrid powertrains, the series–parallel compound hybrid powertrains are found to provide better fuel economy. Different electric powertrains, hybrid powertrains, and range-extended electric systems are also detailed, and their advantages and disadvantages are described. Finally, the technology roadmap over the next 15 years is proposed regarding traction motor, power electronic converter and electric powertrain as well as the key materials and components at each time frame.

show abstract

“…Among them, LSTM, a kind of cyclic neural network, can integrate long information and short information well and solve the problems of gradient dispersion and gradient explosion. LSTM is widely used in time series prediction [28]. Literature [29] developed a powerful adaptive online gradient learning algorithm based on LSTM to predict time series with outliers.…”

Section: Stock Forecastingmentioning

confidence: 99%

A Novel Stock Index Intelligent Prediction Algorithm Based on Attention‐Guided Deep Neural Network

Yuan

2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The stock market is affected by economic market, policy, and other factors, and its internal change law is extremely complex. With the rapid development of the stock market and the expansion of the scale of investors, the stock market has produced a large number of transaction data, which makes it more difficult to obtain valuable information. Because deep neural network is good at dealing with the prediction problems with large amount of data and complex nonlinear mapping relationship, this paper proposes an attention-guided deep neural network stock prediction algorithm. This paper synthesizes the daily stock social media text emotion index and stock technology index as the data source and applies them to the long-term and short-term memory neural network (LSTM) model to predict the stock market. The stock emotion index is extracted by constructing a social text classification emotion model of bidirectional long-term and short-term memory neural network (Bi-LSTM) based on attention mechanism and glove word vector representation algorithm. In addition, a dimensionality reduction model based on decision tree (DT) and principal component analysis (PCA) is constructed to reduce the dimensionality of stock technical indicators and extract the main data information. Furthermore, this paper proposes a model based on nasNet for pattern recognition. The recognition results can be used to automatically identify short-term K-line patterns, predict reliable trading signals, and help investors customize short-term high-efficiency investment strategies. The experimental results show that the prediction accuracy of the proposed algorithm can reach 98.6%, which has high application value.

show abstract

A Novel Torque Distribution Strategy Based on Deep Recurrent Neural Network for Parallel Hybrid Electric Vehicle

Cited by 20 publications

References 40 publications

Real-Time Visualization Optimization Management Simulation of Big Data Stream on Industrial Heritage Cloud Platform

Real-Time Visualization Optimization Management Simulation of Big Data Stream on Industrial Heritage Cloud Platform

Review and Development of Electric Motor Systems and Electric Powertrains for New Energy Vehicles

A Novel Stock Index Intelligent Prediction Algorithm Based on Attention‐Guided Deep Neural Network

Contact Info

Product

Resources

About