Dynamic Predictive Maintenance Scheduling Using Deep Learning Ensemble for System Health Prognostics

Chen, Chuang; Zhu, Zheng H.; Jun, Shi; Lu, Ningyun; Jiang, Bin

doi:10.1109/jsen.2021.3119553

Cited by 37 publications

(12 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the most common DL method for feature extraction is the Autoencoder (AE), in which the data are compressed or reduced to lower dimensions and then decoded to the desired dimension. Examples of AE in the context of feature extraction are found in Mishra and Huhtala (2019) and Chen, Zhu, et al (2021), extracting in all cases operating profiles from time‐series. Pillai and Vadakkepat (2021) utilize a multilayer convolutional AE based on a multiloss objective function.…”

Section: Data Mining In Predictive Maintenancementioning

confidence: 99%

“…Specifically, three types of RNNs are studied: simple RNN, Gated Recurrent Unit (GRU), and LSTM, with GRU and LSTM obtaining a similar performance in all cases. Attending to multiclass problems, different LSTM configurations are studied in Nguyen and Medjaher (2019), Fernandes et al (2020), Zhang, Zhang, and Li (2019), Chen, Zhu, et al (2021) to obtain the probability of future failure from time‐series sorted operating records. Specifically, in Nguyen and Medjaher (2019), the LSTM predicts the failure probability in different time‐windows, while in Fernandes et al (2020), Zhang, Zhang, and Li (2019), Chen, Zhu, et al (2021), it is predicted the state of degradation of the system.…”

Section: Data Mining In Predictive Maintenancementioning

confidence: 99%

“…Attending to multiclass problems, different LSTM configurations are studied in Nguyen and Medjaher (2019), Fernandes et al (2020), Zhang, Zhang, and Li (2019), Chen, Zhu, et al (2021) to obtain the probability of future failure from time‐series sorted operating records. Specifically, in Nguyen and Medjaher (2019), the LSTM predicts the failure probability in different time‐windows, while in Fernandes et al (2020), Zhang, Zhang, and Li (2019), Chen, Zhu, et al (2021), it is predicted the state of degradation of the system. In Wu et al (2018), it is proposed a hybrid DL model that combines a first stage of CNN layer that extracts spatial and short‐term temporal features of the multidimensional signals inside a segmented time window, and then several LSTM layers are stacked to learn the internal long‐term temporal features of each subsequence.…”

Section: Data Mining In Predictive Maintenancementioning

confidence: 99%

“…Regression‐based LSTM to predict RUL can be found in Zhang, Wang, et al (2018), Zschech et al (2019), Chen, Liu, et al (2021), and Xiong et al (2021). Two decision support systems are proposed in Lepenioti et al (2020) and Chen, Zhu, et al (2021) based on the RUL estimation produced by LSTM, among other components. In Kamat et al (2021), different LSTMs configurations are studied to predict RUL, with the particularity of using only the last section of the signal from the detection of the first anomalous point, thus the computational load is reduced.…”

Section: Data Mining In Predictive Maintenancementioning

confidence: 99%

See 3 more Smart Citations

Data mining in predictive maintenance systems: A taxonomy and systematic review

Esteban

Zafra

Ventura

2022

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Predictive maintenance is a field of study whose main objective is to optimize the timing and type of maintenance to perform on various industrial systems. This aim involves maximizing the availability time of the monitored system and minimizing the number of resources used in maintenance. Predictive maintenance is currently undergoing a revolution thanks to advances in industrial systems monitoring within the Industry 4.0 paradigm. Likewise, advances in artificial intelligence and data mining allow the processing of a great amount of data to provide more accurate and advanced predictive models. In this context, many actors have become interested in predictive maintenance research, becoming one of the most active areas of research in computing, where academia and industry converge. The objective of this paper is to conduct a systematic literature review that provides an overview of the current state of research concerning predictive maintenance from a data mining perspective. The review presents a first taxonomy that implies different phases considered in any data mining process to solve a predictive maintenance problem, relating the predictive maintenance tasks with the main data mining tasks to solve them. Finally, the paper presents significant challenges and future research directions in terms of the potential of data mining applied to predictive maintenance. This article is categorized under: Application Areas > Industry Specific Applications Technologies > Internet of Things

show abstract

Section: Data Mining In Predictive Maintenancementioning

confidence: 99%

Section: Data Mining In Predictive Maintenancementioning

confidence: 99%

Section: Data Mining In Predictive Maintenancementioning

confidence: 99%

Section: Data Mining In Predictive Maintenancementioning

confidence: 99%

See 2 more Smart Citations

Data mining in predictive maintenance systems: A taxonomy and systematic review

Esteban

Zafra

Ventura

2022

WIREs Data Min & Knowl

View full text Add to dashboard Cite

show abstract

“…Auto-encoder technology is an important branch of deep learning theory and can be regarded as a feature extraction method of isodimensional mapping [21]. A basic autoencoder consists of two main parts: an encoder and a decoder.…”

Section: Degradation Feature Extraction Using a Deep Auto-encodermentioning

confidence: 99%

Deep Auto-Encoder and Deep Forest-Assisted Failure Prognosis for Dynamic Predictive Maintenance Scheduling

Yu¹,

Chen

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Prognostics and health management (PHM) with failure prognosis and maintenance decision-making as the core is an advanced technology to improve the safety, reliability, and operational economy of engineering systems. However, studies of failure prognosis and maintenance decision-making have been conducted separately over the past years. Key challenges remain open when the joint problem is considered. The aim of this paper is to develop an integrated strategy for dynamic predictive maintenance scheduling (DPMS) based on a deep auto-encoder and deep forest-assisted failure prognosis method. The proposed DPMS method involves a complete process from performing failure prognosis to making maintenance decisions. The first step is to extract representative features reflecting system degradation from raw sensor data by using a deep auto-encoder. Then, the features are fed into the deep forest to compute the failure probabilities in moving time horizons. Finally, an optimal maintenance-related decision is made through quickly evaluating the costs of different decisions with the failure probabilities. Verification was accomplished using NASA’s open datasets of aircraft engines, and the experimental results show that the proposed DPMS method outperforms several state-of-the-art methods, which can benefit precise maintenance decisions and reduce maintenance costs.

show abstract

Revolutionizing Structural Engineering: Applications of Machine Learning for Enhanced Performance and Safety

Chitkeshwar

2024

Arch Computat Methods Eng

View full text Add to dashboard Cite

Dynamic Predictive Maintenance Scheduling Using Deep Learning Ensemble for System Health Prognostics

Cited by 37 publications

References 37 publications

Data mining in predictive maintenance systems: A taxonomy and systematic review

Data mining in predictive maintenance systems: A taxonomy and systematic review

Deep Auto-Encoder and Deep Forest-Assisted Failure Prognosis for Dynamic Predictive Maintenance Scheduling

Revolutionizing Structural Engineering: Applications of Machine Learning for Enhanced Performance and Safety

Contact Info

Product

Resources

About