Remaining useful life prediction in embedded systems using an online auto-updated machine learning based modeling

Djedidi, Oussama; Djeziri, Mohand; Benmoussa, Samir

doi:10.1016/j.microrel.2021.114071

Cited by 9 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These three factors can be determined through calculations, as shown in detail by [41]. Further predictions using embedded systems have been undertaken by [42,43,103].…”

Section: Remaining Useful Life (Rul)mentioning

confidence: 99%

A Review on the Lifecycle Strategies Enhancing Remanufacturing

2021

View full text Add to dashboard Cite

Remanufacturing is a domain that has increasingly been exploited during recent years due to its numerous advantages and the increasing need for society to promote a circular economy leading to sustainability. Remanufacturing is one of the main end-of-life (EoL) options that can lead to a circular economy. There is therefore a strong need to prioritize this option over other available options at the end-of-life stage of a product because it is the only recovery option that maintains the same quality as that of a new product. This review focuses on the different lifecycle strategies that can help improve remanufacturing; in other words, the various strategies prior to, during or after the end-of-life of a product that can increase the chances of that product being remanufactured rather than being recycled or disposed of after its end-of-use. The emergence of the fourth industrial revolution, also known as industry 4.0 (I4.0), will help enhance data acquisition and sharing between different stages in the supply chain, as well boost smart remanufacturing techniques. This review examines how strategies like design for remanufacturing (DfRem), remaining useful life (RUL), product service system (PSS), closed-loop supply chain (CLSC), smart remanufacturing, EoL product collection and reverse logistics (RL) can enhance remanufacturing. We should bear in mind that not all products can be remanufactured, so other options are also considered. This review mainly focuses on products that can be remanufactured. For this review, we used 181 research papers from three databases; Science Direct, Web of Science and Scopus.

show abstract

“…These three factors can be determined through calculations, as shown in detail by [41]. Further predictions using embedded systems have been undertaken by [42,43,103].…”

Section: Remaining Useful Life (Rul)mentioning

confidence: 99%

A Review on the Lifecycle Strategies Enhancing Remanufacturing

2021

View full text Add to dashboard Cite

show abstract

“…Additionally, nonlinear autoregressive (NAR) neural networks solely rely on the observed variable's information, eliminating the need for exogenous variables. Recent studies in areas such as agriculture [34,35], economy [36], sustainability [37][38][39][40], energy [41], traffic flow [42], waste management [43], SARS-CoV-2 analysis [44,45], and other sectors [46][47][48][49][50] have demonstrated the effectiveness of NAR networks.…”

Section: Introductionmentioning

confidence: 99%

Elevating Univariate Time Series Forecasting: Innovative SVR-Empowered Nonlinear Autoregressive Neural Networks

Borrero,

Mariscal

2023

Algorithms

View full text Add to dashboard Cite

Efforts across diverse domains like economics, energy, and agronomy have focused on developing predictive models for time series data. A spectrum of techniques, spanning from elementary linear models to intricate neural networks and machine learning algorithms, has been explored to achieve accurate forecasts. The hybrid ARIMA-SVR model has garnered attention due to its fusion of a foundational linear model with error correction capabilities. However, its use is limited to stationary time series data, posing a significant challenge. To overcome these limitations and drive progress, we propose the innovative NAR–SVR hybrid method. Unlike its predecessor, this approach breaks free from stationarity and linearity constraints, leading to improved model performance solely through historical data exploitation. This advancement significantly reduces the time and computational resources needed for precise predictions, a critical factor in univariate economic time series forecasting. We apply the NAR–SVR hybrid model in three scenarios: Spanish berry daily yield data from 2018 to 2021, daily COVID-19 cases in three countries during 2020, and the daily Bitcoin price time series from 2015 to 2020. Through extensive comparative analyses with other time series prediction models, our results substantiate that our novel approach consistently outperforms its counterparts. By transcending stationarity and linearity limitations, our hybrid methodology establishes a new paradigm for univariate time series forecasting, revolutionizing the field and enhancing predictive capabilities across various domains as highlighted in this study.

show abstract

“…Fast and accurate thermal measurements are needed in biomedical applications, , wearables, robotics, environmental monitoring, and safety-critical machine management . Hence, realizing temperature sensors on ultrathin, conformal, and flexible substrates is important to allow for improved interfacing with biological tissue such as skin, and it simplifies the integration in disposable packaging (e.g., for food monitoring) , or tight spaces in machines or electronic components (e.g., power electronics) .…”

mentioning

confidence: 99%

Fast-Response Flexible Temperature Sensors with Atomically Thin Molybdenum Disulfide

et al. 2022

View full text Add to dashboard Cite

Real-time thermal sensing on flexible substrates could enable a plethora of new applications. However, achieving fast, submillisecond response times even in a single sensor is difficult, due to the thermal mass of the sensor and encapsulation. Here, we fabricate flexible monolayer molybdenum disulfide (MoS 2 ) temperature sensors and arrays, which can detect temperature changes within a few microseconds, over 100× faster than flexible thin-film metal sensors. Thermal simulations indicate the sensors' response time is only limited by the MoS 2 interfaces and encapsulation. The sensors also have high temperature coefficient of resistance, ∼1−2%/K and stable operation upon cycling and long-term measurement when they are encapsulated with alumina. These results, together with their biocompatibility, make these devices excellent candidates for biomedical sensor arrays and many other Internet of Things applications.

show abstract

Remaining useful life prediction in embedded systems using an online auto-updated machine learning based modeling

Cited by 9 publications

References 36 publications

A Review on the Lifecycle Strategies Enhancing Remanufacturing

A Review on the Lifecycle Strategies Enhancing Remanufacturing

Elevating Univariate Time Series Forecasting: Innovative SVR-Empowered Nonlinear Autoregressive Neural Networks

Fast-Response Flexible Temperature Sensors with Atomically Thin Molybdenum Disulfide

Contact Info

Product

Resources

About