Lithium-ion battery remaining useful life prediction with Deep Belief Network and Relevance Vector Machine

Zhao, Guangbo; Zhang, Guohui; Liu, Yuefeng; Zhang, Bin; Hu, Cong

doi:10.1109/icphm.2017.7998298

Cited by 72 publications

(39 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It mainly includes neuro‐fuzzy approaches, SVM, regression technique, and other machine learning methods. Further analysis are as follows, such as artificial neural network (AN), fuzzy neural network (FNN), support vector machine (SVM), relevant vector machine (RVM), autoregressive model (AR), and Gaussian PROCESS REGRESSION (GPR) . However, such algorithms rely on a large amount of experimental data for parameter integration to obtain better accuracy, resulting in long training time and low generalization ability.…”

Section: Model‐based Bms Applicationmentioning

confidence: 99%

A review on battery management system from the modeling efforts to its multiapplication and integration

2019

View full text Add to dashboard Cite

Summary Progress in battery technology accelerates the transition of battery management system (BMS) from a mere monitoring unit to a multifunction integrated one. It is necessary to establish a battery model for the implementation of BMS's effective control. With more comprehensive and faster battery model, it would be accurate and effective to reflect the behavior of the battery level to the vehicle. On this basis, to ensure battery safety, power, and durability, some key technologies based on the model are advanced, such as battery state estimation, energy equalization, thermal management, and fault diagnosis. Besides, the communication of interactions between BMS and vehicle controllers, motor controllers, etc is an essential consideration for optimizing driving and improving vehicle performance. As concluded, a synergistic and collaborative BMS is the foundation for green‐energy vehicles to be intelligent, electric, networked, and shared. Thus, this paper reviews the research and development (R&D) of multiphysics model simulation and multifunction integrated BMS technology. In addition, summary of the relevant research and state‐of‐the‐art technology is dedicated to improving the synergy and coordination of BMS and to promote the innovation and optimization of new energy vehicle technology.

show abstract

Section: Model‐based Bms Applicationmentioning

confidence: 99%

A review on battery management system from the modeling efforts to its multiapplication and integration

2019

View full text Add to dashboard Cite

show abstract

“…Gugulothu (2017) employed a recurrent neural network (RNN) for RUL estimation. Malhotra (2016), Zhao (2016), Yuan (2016), Zheng (2017), Zhao (2017), Wu (2017), Aydin (2017), and Zhao (2017) all employ long short-term memory (LSTM) networks to estimate RUL. Ren (2017) incorporates feature extraction coupled with a deep neural network for RUL estimation.…”

Section: Introductionmentioning

confidence: 99%

A Deep Adversarial Approach Based on Multi-Sensor Fusion for Semi-Supervised Remaining Useful Life Prognostics

Verstraete

Droguett

Modarres

2019

Sensors

View full text Add to dashboard Cite

Multi-sensor systems are proliferating the asset management industry and by proxy, the structural health management community. Asset managers are beginning to require a prognostics and health management system to predict and assess maintenance decisions. These systems handle big machinery data and multi-sensor fusion and integrate remaining useful life prognostic capabilities. We introduce a deep adversarial learning approach to damage prognostics. A non-Markovian variational inference-based model incorporating an adversarial training algorithm framework was developed. The proposed framework was applied to a public multi-sensor data set of turbofan engines to demonstrate its ability to predict remaining useful life. We find that using the deep adversarial based approach results in higher performing remaining useful life predictions.

show abstract

“…Comparing with the applications of DBN in fault diagnosis, the applications of DBN in fault prognostics are rarely reported. Zhao et al [29] proposed a fusion fault prognostics approach based on DBN and the Relevance Vector Machine in which DBN is only responsible for extracting features. These successful applications provide ideas for us to apply an optimized DBN to the fault prognosis of hydraulic pump.…”

Section: Introductionmentioning

confidence: 99%

Fault Prognosis of Hydraulic Pump Based on Bispectrum Entropy and Deep Belief Network

Tian

et al. 2019

Measurement Science Review

View full text Add to dashboard Cite

Fault prognosis plays a key role in the framework of Condition-Based Maintenance (CBM). Limited by the inherent disadvantages, most traditional intelligent algorithms perform not very well in fault prognosis of hydraulic pumps. In order to improve the prediction accuracy, a novel methodology for fault prognosis of hydraulic pump based on the bispectrum entropy and the deep belief network is proposed in this paper. Firstly, the bispectrum features of vibration signals are analyzed, and a bispectrum entropy method based on energy distribution is proposed to extract the effective feature for prognostics. Then, the Deep Belief Network (DBN) model based on the Restrict Boltzmann Machine (RBM) is proposed as the prognostics model. For the purpose of accurately predicting the trends and the random fluctuations during the performance degradation of the hydraulic pump, the Quantum Particle Swarm Optimization (QPSO) is introduced to search for the optimal value of initial parameters of the network. Finally, analysis of the hydraulic pump degradation experiment demonstrates that the proposed algorithm has a satisfactory prognostics performance and is feasible to meet the requirements of CBM.

show abstract

Lithium-ion battery remaining useful life prediction with Deep Belief Network and Relevance Vector Machine

Cited by 72 publications

References 20 publications

A review on battery management system from the modeling efforts to its multiapplication and integration

A review on battery management system from the modeling efforts to its multiapplication and integration

A Deep Adversarial Approach Based on Multi-Sensor Fusion for Semi-Supervised Remaining Useful Life Prognostics

Fault Prognosis of Hydraulic Pump Based on Bispectrum Entropy and Deep Belief Network

Contact Info

Product

Resources

About