Fault diagnosis for lithium-ion batteries in electric vehicles based on signal decomposition and two-dimensional feature clustering

Li, Shuowei; Zhang, Caiping; Du, Jingcai; Cong, Xinwei; Zhang, Linjing; Jiang, Yan; Wang, Leyi

doi:10.1016/j.geits.2022.100009

Cited by 68 publications

(16 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conversely, it will make the decomposed mode components sharper, thus causing spurious mode components and retaining many redundant frequency components. Therefore, in view of the abovementioned facts, according to the pertinent literature [8,37], to consider both the decomposition performance and computational efficiency, in this paper, the search range of the decomposed mode number K and the penalty factor α are set to be [2,8] and [100, 3000], respectively. Besides, the search step of K and α are 1 and 50, respectively.…”

Section: Spavmdmentioning

confidence: 99%

“…Rolling bearings, as one of the crucial components in mechanical systems, are widely used in various rotating equipment, not only lead to a decline in the performance of mechanical equipment, but also may lead to serious accidents, posing a serious threat to production and personnel safety [2]. Consequently, effective data processing, feature extraction and intelligent fault identification of the raw signals collected from rolling bearings are of great significance for speculating the working status of rolling bearings, preventing the occurrence of accidents and improving the operational efficiency of mechanical equipment.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel robust intelligent fault diagnosis method for rolling bearings based on SPAVMD and WOA-LSSVM under noisy conditions

Yan,

Hua,

Jiang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Aiming at the problem that the fault information of rolling bearings under harsh operation environment is easily submerged by strong noise interference, which causes the traditional method to be difficult to identify bearing faults effectively, this paper proposes a novel robust intelligent fault diagnosis method for rolling bearings based on sparsity-assisted parameter adjustable variational mode decomposition (SPAVMD) and whale optimization algorithm-based optimized least-squares support vector machine (WOA-LSSVM). Firstly, a sparsity measurement named the improved Gini index (IGINI) is introduced as the fitness function of grid search algorithm (GSA) to adaptively adjust and search for the optimal decomposed mode number K and penalty factor α of VMD. Additionally, VMD containing the optimal parameters is adopted to decompose the original bearing vibration signal into several intrinsic mode function (IMF), and the effective signal reconstruction is performed by screening the sensitive IMF components according to the effective weighted kurtosis Gini index criterion (EWKGI). Subsequently, the refined composite multiscale dispersion entropy (RCMDE) of the reconstructed signal is further calculated to establish a multi-dimensional feature vector set. Finally, the constructed feature vector set is fed into the whale optimization algorithm-based optimized least squares support vector machine (WOA-LSSVM) to achieve automatic fault identification of rolling bearings. The effectiveness of the proposed method is verified by two experimental examples. Experimental results show that the proposed method has higher fault recognition accuracy and better robustness against noise than other homologous methods in noisy conditions. This study provides a new perspective for the developing of robust diagnosis methods.

show abstract

Section: Spavmdmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A novel robust intelligent fault diagnosis method for rolling bearings based on SPAVMD and WOA-LSSVM under noisy conditions

Yan,

Hua,

Jiang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Nevertheless, they suffer from various limitations, including finite lifetimes, the need for periodic replacement, and environmental pollution. Consequently, they prove unsuitable for enabling wireless self-powering in rotating components, such as turbine blades [5][6][7]. If the vibrations in rotating machinery can be effectively harnessed and converted into electrical energy, it would pave the way for achieving self-powering capabilities for micro and small sensors [8,9].…”

Section: Introductionmentioning

confidence: 99%

Characterization of magnetostrictive bi-stable rotational vibration energy harvester with integrated centrifugal effect

Dong,

Liang,

Liu

et al. 2024

Smart Mater. Struct.

View full text Add to dashboard Cite

Rotational machinery is a common presence in dust still production, and the occurrence of operational failures in components like engines and turbine blades necessitates effective measures. To solve this challenge, remote structural health monitoring using energy harvesting and wireless sensors has been widely employed to realize the self-powered sensing. This study proposes a magnet-induced bi-stable rotational energy harvester (REH), which utilizes the centrifugal effect to broaden the effective frequency bandwidth, enabling efficient energy harvesting in complex environments. A comprehensive mathematical model has been established to facilitate the dynamic characteristics of the bi-stable system, taking into account the centrifugal effect. The theoretical results demonstrate that the gap distance of magnetic configuration has great effects on the bi-stable system. Additionally, the centrifugal effect decided by the centrifugal radius and rotational speeds also affects the stable high-energy orbit oscillations. Furthermore, experimental results indicate that the proposed REH can effectively operate within the frequency range of 230-290 rpm, with a maximum RMS voltage of 780 mV and corresponding power of 4.35 mW. These findings validate the performance of the bi-stable magnetostrictive REH with the centrifugal effect and indicate its potential to effectively address the power supply challenges for wireless sensors. Overall, this study presents a promising solution for enhancing the energy harvesting performance of REH and also provides insights into the design of high-efficiency REH by magnet-induced nonlinearity and the centrifugal effect.

show abstract

“…2 Many experts have conducted systematic research on the performance of LIBs. [3][4][5] Meanwhile, LIBs have become one of the growing primary power sources due to their lightweight, high specific energy, and pollution-free characteristics. 6 The behavior of overcharge and overdischarge can lead to the failure of LIBs operation and even some safety accidents.…”

Section: Introductionmentioning

confidence: 99%

“…Lithium‐ion batteries (LIBs) are widely utilized in the industrial field, similar to the aerospace 1 and the automotive 2 . Many experts have conducted systematic research on the performance of LIBs 3–5 . Meanwhile, LIBs have become one of the growing primary power sources due to their lightweight, high specific energy, and pollution‐free characteristics 6 .…”

Section: Introductionmentioning

confidence: 99%

An improved fractional‐order state estimation algorithm based on an unscented particle filter for state of charge estimation of lithium‐ion batteries with adaptive estimations of unknown parameters

Jiao,

Gao,

Chai

et al. 2023

Circuit Theory & Apps

View full text Add to dashboard Cite

SummaryAn adaptive fractional‐order unscented particle filter (FOUPF) and an adaptive FOUPF with the estimations of the noise covariance matrices (NCMs) are proposed to estimate the state of charge (SOC) of lithium‐ion batteries (LIBs) in this study. The Grünwald–Letnikov difference is employed to establish the corresponding discrete‐time equation of the fractional‐order system (FOS). The order and SOC of FOS of LIBs are controlled within an appropriate interval by a mapping function. In order to achieve a joint estimation of order and unknown parameters for a FOS, an augmented vector method is applied in this study. Compared with the adaptive fractional‐order unscented Kalman filter and adaptive fractional‐order cubature Kalman filter, the proposed adaptive FOUPF has a higher accuracy for estimating SOC. Besides, an iterative approach that accommodates the NCMs is proposed to improve the estimation accuracy of SOC. Finally, the availability of the proposed algorithms is tested by several experiments.

show abstract

Fault diagnosis for lithium-ion batteries in electric vehicles based on signal decomposition and two-dimensional feature clustering

Cited by 68 publications

References 36 publications

A novel robust intelligent fault diagnosis method for rolling bearings based on SPAVMD and WOA-LSSVM under noisy conditions

A novel robust intelligent fault diagnosis method for rolling bearings based on SPAVMD and WOA-LSSVM under noisy conditions

Characterization of magnetostrictive bi-stable rotational vibration energy harvester with integrated centrifugal effect

An improved fractional‐order state estimation algorithm based on an unscented particle filter for state of charge estimation of lithium‐ion batteries with adaptive estimations of unknown parameters

Contact Info

Product

Resources

About