Comparison of Data-driven Prognostics Models: A Process Perspective

Li, Rui; Verhagen, Wim J. C.; Curran, Richard

doi:10.3850/978-981-11-2724-3_0503-cd

Cited by 3 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These raw data signals were first preprocessed (i.e., via data cleaning, feature scaling, and pruning) (Li, Verhagen, & Curran, 2019), since raw data are subject to missing information, outliers, sensor and process noise, and different scales . This heterogeneous dataset, in combination with information from the computerized maintenance management system, was used to identify potential condition indicators for the CPs.…”

Section: Online Monitoringmentioning

confidence: 99%

Development of an End State Vision to Implement Digital Monitoring in Nuclear Plants

Walker

Agarwal²,

Ramuhalli³

et al. 2022

PHM_CONF

View full text Add to dashboard Cite

Nuclear plant sites collect and store large volumes of data gathered from various equipment and systems. These datasets typically include plant process parameters, maintenance records, technical logs, online monitoring data, and equipment failure data. The collection of such data affords an opportunity to leverage data-driven machine learning (ML) and artificial intelligence (AI) technologies to provide diagnostic and prognostic capabilities within the nuclear power industry, thus reducing operations and maintenance (O&M) costs. In this way, nuclear energy can become more economically competitive with other energy sources, and premature plant closures can be avoided. From a maintenance standpoint, savings can be achieved by leveraging ML and AI technologies to develop data-driven algorithms that better diagnose and predict potential faults within the system. Improved model accuracy can help reduce unnecessary maintenance and foster more efficient planning of future maintenance, thereby lowering the costs associated with parts, labor, and costly planned, forced, or extended outages. From an operations perspective, cost savings can be generated by shifting from routine-based monitoring to online monitoring by taking advantage of advancements in sensors and wireless communication technologies. Advancements in data storage, mapping, management, and analytics would inform the transition from onsite- to cloud-based computing and storage services. Online monitoring would reduce the number of operator manhours required for taking routine measurements, while cloud computing services would generate cost savings by reducing the amount of hardware needing to be purchased and maintained all while scaling to both computational and storage demands. This paper summarizes an end state vision of how to shift from costly, labor-intensive preventative maintenance to cost-effective predictive maintenance.

show abstract

Section: Online Monitoringmentioning

confidence: 99%

Development of an End State Vision to Implement Digital Monitoring in Nuclear Plants

Walker

Agarwal²,

Ramuhalli³

et al. 2022

PHM_CONF

View full text Add to dashboard Cite

show abstract

“…Many of these issues can be mitigated via filtering, replacing, or scaling, thereby reducing their effects on model performance. Data preprocessing includes data cleaning, feature scaling, and feature selection (Li, Verhagen, & Curran, 2019). The data preprocessing steps implemented in this research are described in the subsections below.…”

Section: Data Preprocessingmentioning

confidence: 99%

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

Walker¹,

Ramuhalli²,

Agarwal³

et al. 2022

IJPHM

View full text Add to dashboard Cite

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.

show abstract

A Hybrid Data-Driven Approach for Forecasting the Characteristics of Production Disruptions and Interruptions

Bazargan‐Lari

Taghipour

2022

Int. J. Info. Tech. Dec. Mak.

View full text Add to dashboard Cite

Manufacturing companies sometimes suffer from unexpected production disruptions/interruptions events (DIEs), affecting the production performance and cost. Since DIEs vary in type and cause, predicting the characteristics of their corresponding production downtimes is a challenging task. Although efforts have been devoted to forecast/prevent specific types of DIEs, such as machine-related events, it is still difficult to deal with the uncertainty caused by a combination of production DIEs of various types. Moreover, the absence of a realistic scenario generator incorporating DIEs has been a challenge in production scheduling under uncertainty. This study investigates the potential use of a hybrid data-driven approach in incorporating the uncertainties of a wide range of DIEs. In this approach, a random forest (RF) method and probability distributions are integrated to forecast the DIEs. The study was carried out based on the recorded DIEs in a Canadian company producing assembly parts for automotive industry. The performance of the proposed methodology for forecasting the production DIEs is evaluated by determining the predicted total downtime (TD) in percent of the expected processing time. The proposed hybrid model yields an overall accuracy of 92.82% in predicting the TD, compared to an overall accuracy of 75.64% when a single RF is used for prediction.

show abstract

Comparison of Data-driven Prognostics Models: A Process Perspective

Cited by 3 publications

References 11 publications

Development of an End State Vision to Implement Digital Monitoring in Nuclear Plants

Development of an End State Vision to Implement Digital Monitoring in Nuclear Plants

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

A Hybrid Data-Driven Approach for Forecasting the Characteristics of Production Disruptions and Interruptions

Contact Info

Product

Resources

About