Prognostic and health management (PHM) can ensure that a lithium-ion battery is working safely and reliably. The main approach of PHM evaluation of the battery is to determine the State of Health (SoH) and the Remaining Useful Life (RUL) of the battery. The advancements of computational tools and big data algorithms have led to a new era of data-driven predictive analysis approaches, using machine learning algorithms. This paper presents the preliminary development of the data-driven prognostic, using a Deep Neural Networks (DNN) approach to predict the SoH and the RUL of the lithium-ion battery. The effectiveness of the proposed approach was implemented in a case study with a battery dataset obtained from the NASA Ames Prognostics Center of Excellence (PCoE) database. The proposed DNN algorithm was compared against other machine learning algorithms, namely, Support Vector Machine (SVM), k-Nearest Neighbors (k-NN), Artificial Neural Networks (ANN), and Linear Regression (LR). The experimental results reveal that the performance of the DNN algorithm could either match or outweigh other machine learning algorithms. Further, the presented results could serve as a benchmark of SoH and RUL prediction using machine learning approaches specifically for lithium-ion batteries application.

A Data-Driven Predictive Prognostic Model for Lithium-ion Batteries based on a Deep Learning Algorithm

This article aims to present a comprehensive review of the recent efforts and advances in applying machine learning (ML) techniques in the area of diagnostics and prognostics of rolling element bearings. The significant goal of this study is to review, recognize and evaluate the performance of various ML techniques and compare them on criteria's such as reliability, accuracy, robustness to noise, data volume requirements and implementation aspects. The merits and demerits of the reviewed ML techniques have been comprehensively analyzed and discussed. A comparative benchmarking of the performance of the reviewed ML algorithms is provided both from the viewpoint of theoretical aspects and industrial applicability. Finally, the potential challenges that come along with the implementation of ML technology are discussed in detail that will likely play a major role in prognostics and health management of rolling element bearings. It is expected that this review would serve as a reference point for researchers to explore the opportunities for further improvement in the field of ML-based fault diagnosis and prognosis of rolling element bearings.

A systematic review of machine learning algorithms for prognostics and health management of rolling element bearings: fundamentals, concepts and applications

The dark side of Bitcoin: Do Emerging Asian Islamic markets help subdue the ethical risk?

http://manuscript.elsevier.com/S0378775322001495/pdf/S0378775322001495.pdf

Feature engineering for machine learning enabled early prediction of battery lifetime

Bitcoin is a major virtual currency. Using weekly data over the 2010-2013 period, we analyze a Bitcoin investment from the standpoint of a U.S. investor with a diversified portfolio including both traditional assets (worldwide stocks, bonds, hard currencies) and alternative investments (commodities, hedge funds, real estate). Over the period under consideration, Bitcoin investment had highly distinctive features, including exceptionally high average return and volatility. Its correlation with other assets was remarkably low. Spanning tests confirm that Bitcoin investment offers significant diversification benefits. We show that the inclusion of even a small proportion of Bitcoins may dramatically improve the risk-return trade-off of well-diversified portfolios. Results should however be taken with caution as the data may reflect early-stage behavior which may not last in the medium or long run.

Virtual Currency, Tangible Return: Portfolio Diversification with Bitcoin

Previous studies have shown that cryptocurrencies could hedge equities. However, most of those studies did not take into account the recent cryptocurrencies bubbles in 2018 and domestic currencies....

https://journals.sagepub.com/doi/pdf/10.1177/2158244020971609

Cryptocurrencies: Hedging Opportunities From Domestic Perspectives in Southeast Asia Emerging Markets:

Roller bearing is one of the vital parts of a rotating machine. Bearing failure can result in serious damage of the machine. This paper aims to develop a bearing fault diagnosis method using parameter evaluation technique to improve the diagnosis accuracy. The parameter evaluation technique is used to select five features that are used as predictors in multi-class support vector machine (SVM) classification. The purpose of this feature reduction was to avoid the curse of dimensionality and to increase the accuracy of the diagnosis. The diagnosis process was performed by classification of bearing states using one-against-one method multi-class SVM. Three types of kernel functions i.e., linear, polynomial, and Gaussian RBF were used in the SVM classification. The bearing conditions which is diagnosed in this paper were normal bearing, inner race fault, and outer race fault conditions. As a result, the classification performance of multiclass SVM using five selected features as the parameter have excellent p...

/pdf/fault-diagnosis-of-roller-bearing-using-parameter-evaluation-4amhr6pp0s.pdf

Fault diagnosis of roller bearing using parameter evaluation technique and multi-class support vector machine

Purpose: The purpose of this study is to explore the most significant profitability determinants of the manufacturing companies in Indonesia. Design/Methodology/Approach: Several independent variables examined for their influence on profitability were working capital, firm size, firm growth, capital structure, and non-debt tax shields. The sample of this study were manufacturing firms listed on the Indonesia Stock Exchange from 2010 to 2017. The number of samples were 350 manufacturing companies. Findings: The results of this study indicate that working capital, firm size and firm growth were positively related to profitability. Meanwhile, capital structure and non-debt tax shield did not affect profitability. The findings of this study were consistent with the pecking order theory and the financial agency theory. Practical implications: This study implies that managers need to adjust their investment needs with the profitability that has been achieved and the total assets of the company, and to maximize the value of the company by managing current assets so that the rate of the return on marginal investment is equal to or greater than the cost of capital used to finance the current assets. Furthermore, financial managers must be able to determine essential investment objectives by maximizing the use of assets and fixed assets which are expected to make the company to enjoy the sales growth in the future. Originality/Value: Although this study organically builds upon recent studies about the firms’ profitability, it conducted in the new administrative setting in Indonesia, which is the Widodo’s administration. Widodo’s administration supports the manufacturing industry to be able to compete globally.

https://www.um.edu.mt/library/oar/bitstream/123456789/54803/1/Profitability%20Determinants%20of%20Manufacturing%20Firms%20%20in%20Indonesia.pdf

Profitability determinants of manufacturing firms in Indonesia

Bearings are the critical part of any rotating machine. The catastrophic failure of the bearing can lead to fatal and harmful to the operation of the machine. Therefore, predictive maintenance based on condition monitoring of bearing is very important. The objective of this research is to apply Support Vector Machine (SVM) method for fault diagnosis of the ball bearing. The research was carried out at the bearing test rig. Four types of ball bearing condition, such as normal, inner race defect, ball defect, and outer race defect were measured of the vibration signals using data acquisition with a sampling frequency of 20 kHz at the constant speed of 1400 RPM. Various features were extracted from vibration signals in time domain, such as RMS, variance, standard deviation, crest factor, shape factor, skewness, kurtosis, log energy entropy and sure entropy. PCA transformation was employed to reduce the dimension of feature extracted data. SVM classification problems were solved using MATLAB 2016a. The results showed that the application of RBF kernel function with the C parameter =1 was the best configuration. The training model accuracy was 98.93% and the testing accuracy of SVM was 97.5%. Finally, the research results show that the SVM classification method can be used to diagnose the fault condition of the ball bearing. .

/pdf/diagnosa-kerusakan-bantalan-bola-menggunakan-metode-support-2kfgb4g29g.pdf

Diagnosa kerusakan bantalan bola menggunakan metode support vector machine

The purpose of this research is to examine the influence of the number and position of the carbon layer to the dynamic characteristic of carbon-glass fiber hybrid composite. The hybrid composite was consist of unsaturated polyester resin reinforced glass and carbon fiber with the volume fraction of 0.4 and made by hand lay-up method. The vibration test was conducted according to ASTM E756. The experiment variables studied were the number of carbon fiber layer (without carbon layer, 2 carbon layer, 4 carbon layer, and 6 carbon layer) and carbon layer position (layer 1 and 8, layer 2 and 7, layer 3 and 6, layer 4 and 5). The vibration data was acquired using Dynamic Signal Analyzer (DSA) system that consists of an accelerometer, an impact hammer, and a data acquisition. The result indicated that the number and position of carbon layer affected the natural frequency and the damping ratio of the carbon-glass fiber hybrid composite. The increase in the number of carbon layer would increase the natural frequenc...

/pdf/the-influence-of-the-number-and-position-of-the-carbon-fiber-55f6o2kgli.pdf

Didik Djoko Susilo

Papers

Cryptocurrencies: Hedging Opportunities From Domestic Perspectives in Southeast Asia Emerging Markets:

Fault diagnosis of roller bearing using parameter evaluation technique and multi-class support vector machine

Profitability determinants of manufacturing firms in Indonesia

Diagnosa kerusakan bantalan bola menggunakan metode support vector machine

The influence of the number and position of the carbon fiber lamina on the natural frequency and damping ratio of the carbon-glass hybrid composite