scholarly journals A Survey on Data-Driven Predictive Maintenance for the Railway Industry

Sensors ◽  
2021 ◽  
Vol 21 (17) ◽  
pp. 5739
Author(s):  
Narjes Davari ◽  
Bruno Veloso ◽  
Gustavo de Assis Costa ◽  
Pedro Mota Pereira ◽  
Rita P. Ribeiro ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Predictive Maintenance ◽  
Data Driven ◽  
Industrial Plant ◽  
Future Research ◽  
Temporal Behavior ◽  
Industrial Equipment ◽  
Railway Industry ◽  
Different Parts

In the last few years, many works have addressed Predictive Maintenance (PdM) by the use of Machine Learning (ML) and Deep Learning (DL) solutions, especially the latter. The monitoring and logging of industrial equipment events, like temporal behavior and fault events—anomaly detection in time-series—can be obtained from records generated by sensors installed in different parts of an industrial plant. However, such progress is incipient because we still have many challenges, and the performance of applications depends on the appropriate choice of the method. This article presents a survey of existing ML and DL techniques for handling PdM in the railway industry. This survey discusses the main approaches for this specific application within a taxonomy defined by the type of task, employed methods, metrics of evaluation, the specific equipment or process, and datasets. Lastly, we conclude and outline some suggestions for future research.

Accountable algorithms? The ethical implications of data-driven business models

2020 ◽  
Vol 31 (2) ◽  
pp. 163-185 ◽  
Author(s):  
Christoph F. Breidbach ◽  
Paul Maglio
Keyword(s):  
Machine Learning ◽  
Business Models ◽  
Analytical Framework ◽  
Data Driven ◽  
Service Research ◽  
Future Research ◽  
Cost Models ◽  
Ethical Challenges ◽  
Content Type ◽  
Ethical Implications

PurposeThe purpose of this study is to identify, analyze and explain the ethical implications that can result from the datafication of service.Design/methodology/approachThis study uses a midrange theorizing approach to integrate currently disconnected perspectives on technology-enabled service, data-driven business models, data ethics and business ethics to introduce a novel analytical framework centered on data-driven business models as the general metatheoretical unit of analysis. The authors then contextualize the framework using data-intensive insurance services.FindingsThe resulting midrange theory offers new insights into how using machine learning, AI and big data sets can lead to unethical implications. Centered around 13 ethical challenges, this work outlines how data-driven business models redefine the value network, alter the roles of individual actors as cocreators of value, lead to the emergence of new data-driven value propositions, as well as novel revenue and cost models.Practical implicationsFuture research based on the framework can help guide practitioners to implement and use advanced analytics more effectively and ethically.Originality/valueAt a time when future technological developments related to AI, machine learning or other forms of advanced data analytics are unpredictable, this study instigates a critical and timely discourse within the service research community about the ethical implications that can arise from the datafication of service by introducing much-needed theory and terminology.

scholarly journals Linking intrinsic and apparent relationships between phytoplankton and environmental forcings using machine learning ‐ What are the challenges?

2020 ◽  
Author(s):  
Christopher Holder ◽  
Anand Gnanadesikan
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Complex Systems ◽  
Spatial Scale ◽  
Prior Knowledge ◽  
Systematic Study ◽  
The Other ◽  
Future Research ◽  
Laboratory Setting ◽  
Do So

Abstract. Controls on phytoplankton growth are typically determined in two ways: by varying one driver of growth at a time such as nutrient or light in a controlled laboratory setting (intrinsic relationships) or by observing the emergence of relationships in the environment (apparent relationships). However, challenges remain when trying to take the intrinsic relationships found in a lab and scaling them up to the size of ecosystems (i.e., linking intrinsic relationships in the lab to apparent relationships in large ecosystems). We investigated whether machine learning (ML) techniques could help bridge this gap. ML methods have many benefits, including the ability to accurately predict outcomes in complex systems without prior knowledge. Although previous studies have found that ML can find apparent relationships, there has yet to be a systematic study that has examined when and why these apparent relationships will diverge from the underlying intrinsic relationships. To investigate this question, we created three scenarios: one where the intrinsic and apparent relationships operate on the same time and spatial scale, another model where the intrinsic and apparent relationships have different timescales but the same spatial scale, and finally one in which we apply ML to actual ESM output. Our results demonstrated that when intrinsic and apparent relationships are closely related and operate on the same spatial and temporal timescale, ML is able to extract the intrinsic relationships when only provided information about the apparent relationships. However, when the intrinsic and apparent relationships operated on different timescales (as little separation as hourly to daily), the ML methods underestimated the biomass in the intrinsic relationships. This was largely attributable to the decline in the variation of the measurements; the hourly time series had higher variability than the daily, weekly, and monthly-averaged time series. Although the limitations found by ML were overestimated, they were able to produce more realistic shapes of the actual relationships compared to MLR. Future research may use this type of information to investigate which nutrients affect the biomass most when values of the other nutrients change. From our study, it appears that ML can extract useful information from ESM output and could likely do so for observational datasets as well.

Time series prediction using machine learning: a case of Bitcoin returns

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Irfan Haider Shakri
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Time Series Data ◽  
Time Series Prediction ◽  
Predictive Ability ◽  
Absolute Error ◽  
Data Driven ◽  
Series Data ◽  
Policy Uncertainty ◽  
Content Type

Purpose The purpose of this study is to compare five data-driven-based ML techniques to predict the time series data of Bitcoin returns, namely, alternating model tree, random forest (RF), multiple linear regression, multi-layer perceptron regression and M5 Tree algorithms. Design/methodology/approach The data used to forecast time series data of Bitcoin returns ranges from 8 July 2010 to 30 Aug 2020. This study used several predictors to predict bitcoin returns including economic policy uncertainty, equity market volatility index, S&P returns, USD/EURO exchange rates, oil and gold prices, volatilities and returns. Five statistical indexes, namely, correlation coefficient, mean absolute error, root mean square error, relative absolute error and root relative squared error are determined. The results of these metrices are used to develop colour intensity ranking. Findings Among the machine learning (ML) techniques used in this study, RF models has shown superior predictive ability for estimating the Bitcoin returns. Originality/value This study is first of its kind to use and compare ML models in the prediction of Bitcoins. More studies can be carried out by using further cryptocurrencies and other ML data-driven models in future.

scholarly journals Towards the Automation of Infrared Thermography Inspections for Industrial Maintenance Applications

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 613
Author(s):  
Pablo Venegas ◽  
Eugenio Ivorra ◽  
Mario Ortega ◽  
Idurre Sáez de Ocáriz
Keyword(s):  
Machine Learning ◽  
Infrared Thermography ◽  
Thermal Response ◽  
Estimation Algorithm ◽  
Learning System ◽  
Predictive Maintenance ◽  
Machine Learning Techniques ◽  
Normal Operation ◽  
Industrial Equipment ◽  
3D Object Detection

The maintenance of industrial equipment extends its useful life, improves its efficiency, reduces the number of failures, and increases the safety of its use. This study proposes a methodology to develop a predictive maintenance tool based on infrared thermographic measures capable of anticipating failures in industrial equipment. The thermal response of selected equipment in normal operation and in controlled induced anomalous operation was analyzed. The characterization of these situations enabled the development of a machine learning system capable of predicting malfunctions. Different options within the available conventional machine learning techniques were analyzed, assessed, and finally selected for electronic equipment maintenance activities. This study provides advances towards the robust application of machine learning combined with infrared thermography and augmented reality for maintenance applications of industrial equipment. The predictive maintenance system finally selected enables automatic quick hand-held thermal inspections using 3D object detection and a pose estimation algorithm, making predictions with an accuracy of 94% at an inference time of 0.006 s.

scholarly journals An Exploration and Forecast of COVID-19 in Mexico with Machine Learning

2020 ◽  
Author(s):  
Daniela A. Gomez-Cravioto ◽  
Ramon E. Diaz-Ramos ◽  
Francisco J. Cantu-Ortiz ◽  
Hector G. Ceballos
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Health Care Providers ◽  
Machine Learning Techniques ◽  
Future Research ◽  
Logistic Growth ◽  
Care Providers ◽  
Modern Approach ◽  
Logistic Regression Models ◽  
Feature Importance

Abstract Background: To understand and approach the COVID-19 spread, Machine Learning offers fundamental tools. This study presents the use of machine learning techniques for the projection of COVID-19 infections and deaths in Mexico. The research has three main objectives: first, to identify which function adjusts the best to the infected population growth in Mexico; second, to determine the feature importance of climate and mobility; third, to compare the results of a traditional time series statistical model with a modern approach in machine learning. The motivation for this work is to support health care providers in their preparation and planning. Methods: The methods used are linear, polynomial, and generalized logistic regression models to evaluate the growth of the COVID-19 incidents in the country. Additionally, machine learning and time-series techniques are used to identify feature importance and perform forecasting for daily cases and fatalities. The study uses the publicly available data sets from the John Hopkins University of Medicine in conjunction with mobility rates obtained from Google’s Mobility Reports and climate variables acquired from Weather Online. Results: The results suggest that the logistic growth model fits best the behavior of the pandemic in Mexico, that there is a significant correlation of climate and mobility variables with the disease numbers, and that LSTM is a more suitable approach for the prediction of daily cases. Conclusion: We hope that this study can make some contributions to the world’s response to this epidemic as well as give some references for future research.

Data-Driven Methods for Predictive Maintenance of Industrial Equipment: A Survey

2019 ◽  
Vol 13 (3) ◽  
pp. 2213-2227 ◽  
Author(s):  
Weiting Zhang ◽  
Dong Yang ◽  
Hongchao Wang
Keyword(s):  
Predictive Maintenance ◽  
Data Driven ◽  
Industrial Equipment

scholarly journals Data-driven monitoring of the gearbox using multifractal analysis and machine learning methods

2019 ◽  
Vol 252 ◽  
pp. 06006
Author(s):  
Andrzej Puchalski ◽  
Iwona Komorska
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Statistical Analysis ◽  
Multifractal Analysis ◽  
Diagnostic Methods ◽  
Data Driven ◽  
Support Vector ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Wavelet Leaders

Data-driven diagnostic methods allow to obtain a statistical model of time series and to identify deviations of recorded data from the pattern of the monitored system. Statistical analysis of time series of mechanical vibrations creates a new quality in the monitoring of rotating machines. Most real vibration signals exhibit nonlinear properties well described by scaling exponents. Multifractal analysis, which relies mainly on assessing local singularity exponents, has become a popular tool for statistical analysis of empirical data. There are many methods to study time series in terms of their fractality. Comparing computational complexity, a wavelet leaders algorithm was chosen. Using Wavelet Leaders Multifractal Formalism, multifractal parameters were estimated, taking them as diagnostic features in the pattern recognition procedure, using machine learning methods. The classification was performed using neural network, k-nearest neighbours’ algorithm and support vector machine. The article presents the results of vibration acceleration tests in a demonstration transmission system that allows simulations of assembly errors and teeth wear.

Sign in / Sign up

Export Citation Format

Share Document