Evaluation of 1D CNN Autoencoders for Lithium-ion Battery Condition Assessment Using Synthetic Data

Valant, Christopher; Wheaton, Jay D.; Thurston, Michael; McConky, Sean P.; Nenadic, Nenad G.

doi:10.36001/phmconf.2019.v11i1.876

Cited by 12 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After collecting the data, a convolutional-based encoder-decoder network to determine where anomalies exist in the workpiece was trained. The ability to detect anomalies in time series by applying convolutions was successfully demonstrated by multiple publications [1,[7][8][9]]. An undercomplete autoencoder is a feedforward deep neural network that tries to reconstruct its input 𝒙 ϵ ℝ 𝑝 and consists of two parts being an encoder and a decoder [10].…”

Section: Methodsmentioning

confidence: 99%

Multivariate Time Series Dataset of Milling 16MnCr5 for Anomaly Detection

Schlagenhauf¹,

Wolf²,

Puchta³

2022

Preprint

View full text Add to dashboard Cite

Machine learning methods have widely been applied to detect anomalies in machine and cutting tool behavior during lathe or milling. However, detecting anomalies in the workpiece itself did not get the same attention by researchers. That is why in this article, the authors present a pub-licly available multivariate time series dataset which was recorded during milling of 16MnCr5. Due to artificially introduced, though realistic anomalies in the workpiece the dataset can be ap-plied for anomaly detection. By using a convolutional autoencoder as a first model good results in detecting the location of the anomalies in the workpiece were achieved. Furthermore, milling tools with two different diameters where used which led to a dataset eligible for transfer learn-ing. The objective of this article is to provide researchers with a real-world time series dataset of the milling process which is suitable for modern machine learning research topics like anomaly detection and transfer learning.

show abstract

Section: Methodsmentioning

confidence: 99%

Multivariate Time Series Dataset of Milling 16MnCr5 for Anomaly Detection

Schlagenhauf¹,

Wolf²,

Puchta³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…In battery SoC estimation, autoencoders have proven their unique performance, outperforming many other DD models, such as support vector regression and Bayesian regression techniques [101]. Their abilities to compress data, reduce noise, and diminish dimensionality boost their wide implementation for SoC estimation [99], battery modeling [102], and SoH predictions [103]. Often, AEs have been used in combination with several estimation approaches, such as LSTM neural networks [104], look-up tables [105], particle filters [106], and deep neural networks [107].…”

Section: Autoencoders (Aes)mentioning

confidence: 99%

Comparative Study-Based Data-Driven Models for Lithium-Ion Battery State-of-Charge Estimation

Hussein,

Esoofally,

Donekal

et al. 2024

Batteries

View full text Add to dashboard Cite

Batteries have been considered a key element in several applications, ranging from grid-scale storage systems through electric vehicles to daily-use small-scale electronic devices. However, excessive charging and discharging will impair their capabilities and could cause their applications to fail catastrophically. Among several diagnostic indices, state-of-charge estimation is essential for evaluating a battery’s capabilities. Various approaches have been introduced to reach this target, including white, gray, and black box or data-driven battery models. The main objective of this work is to provide an extensive comparison of currently highly utilized machine learning-based estimation techniques. The paper thoroughly investigates these models’ architectures, computational burdens, advantages, drawbacks, and robustness validation. The evaluation’s main criteria were based on measurements recorded under various operating conditions at the Energy Systems Research Laboratory (ESRL) at FIU for the eFlex 52.8 V/5.4 kWh lithium iron phosphate battery pack. The primary outcome of this research is that, while the random forest regression (RFR) model emerges as the most effective tool for SoC estimation in lithium-ion batteries, there is potential to enhance the performance of simpler models through strategic adjustments and optimizations. Additionally, the choice of model ultimately depends on the specific requirements of the task at hand, balancing the need for accuracy with the complexity and computational resources available and how it can be merged with other SoC estimation approaches to achieve high precision.

show abstract

“…The parallel computing of the convolution layer improves the running speed. At the same time, the hierarchical structure of CNN makes it convenient for the model to find the structural information in sentences [42][43][44]. It is also possible to use multi-step attention to connect encoder and decoder, i.e., to calculate attention separately for each layer of the decoder.…”

Section: Sequence To Sequence Modelmentioning

confidence: 99%

An Analytical Investigation of Anomaly Detection Methods Based on Sequence to Sequence Model in Satellite Power Subsystem

Jin

Zhang

Sun

et al. 2022

Sensors

View full text Add to dashboard Cite

The satellite power subsystem is responsible for all power supply in a satellite, and is an important component of it. The system’s performance has a direct impact on the operations of other systems as well as the satellite’s lifespan. Sequence to sequence (seq2seq) learning has recently advanced, gaining even more power in evaluating complicated and large-scale data. The potential of the seq2seq model in detecting anomalies in the satellite power subsystem is investigated in this work. A seq2seq-based scheme is given, with a thorough comparison of different neural-network cell types and levels of data smoothness. Three specific approaches were created to evaluate the seq2seq model performance, taking into account the unsupervised learning mechanism. The findings reveal that a CNN-based seq2seq with attention model under suitable data-smoothing conditions has a better ability to detect anomalies in the satellite power subsystem.

show abstract

Evaluation of 1D CNN Autoencoders for Lithium-ion Battery Condition Assessment Using Synthetic Data

Cited by 12 publications

References 9 publications

Multivariate Time Series Dataset of Milling 16MnCr5 for Anomaly Detection

Multivariate Time Series Dataset of Milling 16MnCr5 for Anomaly Detection

Comparative Study-Based Data-Driven Models for Lithium-Ion Battery State-of-Charge Estimation

An Analytical Investigation of Anomaly Detection Methods Based on Sequence to Sequence Model in Satellite Power Subsystem

Contact Info

Product

Resources

About