VRLA battery state of health estimation based on charging time

Zainuri, Akhmad; Wibawa, Unggul; Rusli, Mochammad; Hasanah, Rini Nur; Harahap, Rosihan Arby

doi:10.12928/telkomnika.v17i3.12241

Cited by 11 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Precision means the percentage of your results which are relevant. On the other hand, recall refers to the percentage of total relevant results correctly classified by your algorithm [31].…”

Section: Evaluation Metricsmentioning

confidence: 99%

A technical review and comparative analysis of machine learning techniques for intrusion detection systems in MANET

Laqtib

Yassini

Hasnaoui

2020

IJECE

View full text Add to dashboard Cite

Machine learning techniques are being widely used to develop an intrusion detection system (IDS) for detecting and classifying cyber attacks at the network-level and the host-level in a timely and automatic manner. However, Traditional Intrusion Detection Systems (IDS), based on traditional machine learning methods, lacks reliability and accuracy. Instead of the traditional machine learning used in previous researches, we think deep learning has the potential to perform better in extracting features of massive data considering the massive cyber traffic in real life. Generally Mobile Ad Hoc Networks have given the low physical security for mobile devices, because of the properties such as node mobility, lack of centralized management and limited bandwidth. To tackle these security issues, traditional cryptography schemes can-not completely safeguard MANETs in terms of novel threats and vulnerabilities, thus by applying Deep learning methods techniques in IDS are capable of adapting the dynamic environments of MANETs and enables the system to make decisions on intrusion while continuing to learn about their mobile environment. An IDS in MANET is a sensoring mechanism that monitors nodes and network activities in order to detect malicious actions and malicious attempt performed by Intruders. Recently, multiple deep learning approaches have been proposed to enhance the performance of intrusion detection system. In this paper, we made a systematic comparison of three models, Inceprtion architecture convolutional neural network Inception-CNN, Bidirectional long short-term memory (BLSTM) and deep belief network (DBN) on the deep learning-based intrusion detection systems, using the NSL-KDD dataset containing information about intrusion and regular network connections, the goal is to provide basic guidance on the choice of deep learning methods in MANET.

show abstract

Section: Evaluation Metricsmentioning

confidence: 99%

A technical review and comparative analysis of machine learning techniques for intrusion detection systems in MANET

Laqtib

Yassini

Hasnaoui

2020

IJECE

View full text Add to dashboard Cite

show abstract

“…The study is based on the manufacturer's data that characterizes the life of the battery by the number of cycles depending on the depth of discharge of each. The types of lead-acid batteries most commonly used for hybrid electrification systems are open conventional stationary batteries and VRLA (Valve Regulated Lead Acid) sealed batteries [10][11][12][13][14][15][16]. In each class, two different internal architectures are used: flat plate technology and tube plate technology.…”

Section: A) Modelling the Life Cycle Of The Batterymentioning

confidence: 99%

Aging study of a lead-acid storage bank in a multi-source hybrid system

Laadissi

Khalfi

Belhora

et al. 2020

IJEECS

View full text Add to dashboard Cite

Autonomous and grid-connected systems play an important role in the massive integration of renewable energy sources necessary for the global development of a sustainable society. In this regard, the analysis of the behavior of electrochemical storage devices such as lead-acid batteries installed on hybrid energy systems and microgrids in terms of lifespan and economic profitability is an important research subject. The purpose of this article is to present a methodology for calculating the aging rate of a storage battery inserted in a hybrid multisource system. The approach consists in first knowing the solicitations of the battery during a year knowing at every moment its state of charge. This curve is obtained from a dynamic simulator taking into account the intermittences of the sources and the load. The second step is to determine the number of cycles and the depth of discharge of each from the stat of charge. Finally, based on the battery life characteristic given by the manufacturer (cycle number vs. discharge depth), the aging rate of the battery for one year of operation is determined.

show abstract

“…The SOH will serve to determine the limit of its operation, that is, it is the parameter that defines the end of life of a battery in each application. In the literature on this subject, there are experimental tests carried out in laboratories where programmed tests have been performed under specific conditions and patterns to analyze the aging of batteries and other related parameters [49,50,51,52,53].…”

Section: Supervision and Predictive Fault Diagnosis Of Batteriesmentioning

confidence: 99%

Marine NMEA 2000 Smart Sensors for Ship Batteries Supervision and Predictive Fault Diagnosis

García

Quiles

Correcher

et al. 2019

Sensors

View full text Add to dashboard Cite

In this paper, an application for the management, supervision and failure forecast of a ship’s energy storage system is developed through a National Marine Electronics Association (NMEA) 2000 smart sensor network. Here, the NMEA 2000 network sensor devices for the measurement and supervision of the parameters inherent to energy storage and energy supply are reviewed. The importance of energy storage systems in ships, the causes and models of battery aging, types of failures, and predictive diagnosis techniques for valve-regulated lead-acid (VRLA) batteries used for assisted and safe navigation are discussed. In ships, battery banks are installed in chambers that normally do not have temperature regulation and therefore are significantly conditioned by the outside temperature. A specific method based on the analysis of the time-series data of random and seasonal factors is proposed for the comparative trend analyses of both the battery internal temperature and the battery installation chamber temperature. The objective is to apply predictive fault diagnosis to detect any undesirable increase in battery temperature using prior indicators of heat dissipation process failure—to avoid the development of the most frequent and dangerous failure modes of VRLA batteries such as dry out and thermal runaway. It is concluded that these failure modes can be conveniently diagnosed by easily recognized patterns, obtained by performing comparative trend analyses to the variables measured onboard by NMEA sensors.

show abstract

VRLA battery state of health estimation based on charging time

Cited by 11 publications

References 19 publications

A technical review and comparative analysis of machine learning techniques for intrusion detection systems in MANET

A technical review and comparative analysis of machine learning techniques for intrusion detection systems in MANET

Aging study of a lead-acid storage bank in a multi-source hybrid system

Marine NMEA 2000 Smart Sensors for Ship Batteries Supervision and Predictive Fault Diagnosis

Contact Info

Product

Resources

About