Status diagnosis and feature tracing of the natural gas pipeline weld based on improved random forest model

Wang, Lin; Mao, Zhihao; Hu, Xuan; Ma, Tianjiao; Cheng, Hui‐Ming; Chen, Jiaxin; You, Xiaohu

doi:10.1016/j.ijpvp.2022.104821

Cited by 22 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can also manage missing data and outliers and is less susceptible to overfitting than other decision tree-based algorithms, making it more accurate at predicting the outcomes of new data (Liu et al, 2020). In addition, it can provide estimates of variable relevance, which facilitates the identification of the most pertinent factors for producing correct forecasts (Wang et al, 2022b).…”

Section: Algorithm Type Descriptionmentioning

confidence: 99%

Leveraging machine learning algorithms for improved disaster preparedness and response through accurate weather pattern and natural disaster prediction

Jain,

Dhupper,

Shrivastava

et al. 2023

Front. Environ. Sci.

View full text Add to dashboard Cite

Globally, communities and governments face growing challenges from an increase in natural disasters and worsening weather extremes. Precision in disaster preparation is crucial in responding to these issues. The revolutionary influence that machine learning algorithms have in strengthening catastrophe preparation and response systems is thoroughly explored in this paper. Beyond a basic summary, the findings of our study are striking and demonstrate the sophisticated powers of machine learning in forecasting a variety of weather patterns and anticipating a range of natural catastrophes, including heat waves, droughts, floods, hurricanes, and more. We get practical insights into the complexities of machine learning applications, which support the enhanced effectiveness of predictive models in disaster preparedness. The paper not only explains the theoretical foundations but also presents practical proof of the significant benefits that machine learning algorithms provide. As a result, our results open the door for governments, businesses, and people to make wise decisions. These accurate predictions of natural catastrophes and emerging weather patterns may be used to implement pre-emptive actions, eventually saving lives and reducing the severity of the damage.

show abstract

Section: Algorithm Type Descriptionmentioning

confidence: 99%

Leveraging machine learning algorithms for improved disaster preparedness and response through accurate weather pattern and natural disaster prediction

Jain,

Dhupper,

Shrivastava

et al. 2023

Front. Environ. Sci.

View full text Add to dashboard Cite

show abstract

“…There is a lack of research on the comprehensive risk assessment of long-distance pipelines in mountainous areas. Indeed, some scholars have begun to use machine learning methods for pipeline risk assessment, such as artificial neural networks, 11,12 support vector machines, 13,14 random forests, 15,16 and XGBoost. 17 While these methods can learn from large amounts of data and extract patterns and features related to pipeline risks, they do require substantial data support and rely on prior data.…”

Section: Introductionmentioning

confidence: 99%

Integrated Risk Assessment of Mountainous Long-Distance Oil and Gas Pipelines Based on Multisource Spatial Data

Wang,

Li,

Zhu

et al. 2024

ACS Omega

View full text Add to dashboard Cite

Pipeline risk assessment is crucial for pipeline safety management and operation. The aim of this study is to develop a comprehensive assessment model that accurately evaluates pipeline risks and ensures the safe and reliable operation of the pipeline system. The model is based on multisource spatial data and is primarily applicable to long-distance oil and gas pipelines that traverse complex geological conditions in mountainous areas. The research is conducted using the example of the Jinliwen natural gas pipeline in Zhejiang Province, China. By analyzing the geological data of the study area and the potential risks that the pipeline may encounter, a comprehensive risk assessment indicator system for the pipeline was developed using slope units to divide pipeline sections. The pipeline risk levels are classified using the K-means clustering-entropy weighted-random forest algorithm. The model is evaluated using accuracy (Acc), precision (Pre), recall (R), F1-score, and the ROC curve. The results show that the model has an accuracy of 0.917, a precision of 0.92, a recall of 0.916, an F1-score of 0.914, and an AUC (Area Under Curve) of 0.93, indicating its strong predictive capability. The risk assessment results demonstrate a strong consistency when compared with actual incident events. This indicates that the constructed model effectively reflects the influencing factors of pipeline risk, providing a basis for pipeline risk assessment and disaster prevention and mitigation efforts in similar regions.

show abstract

“…16 It does not depend on the specific degradation patterns and only needs sufficient historical data, which is more suitable for RUL prediction of complex modeling systems. Traditional machine learning methods to predict the RUL of rolling bearings by extracting shallow features of the data, such as using support vector machine (SVM), 17 artificial neural network (ANN) 18 and random forest regression (RFR) 19,20 to predict the RUL have also achieved some success. However, traditional machine learning methods rely on complex feature engineering techniques, with limited deep-seated data mining features.…”

Section: Introductionmentioning

confidence: 99%

A CNN‐BiLSTM‐Bootstrap integrated method for remaining useful life prediction of rolling bearings

Guo

Wang

et al. 2023

Quality & Reliability Eng

View full text Add to dashboard Cite

Rolling bearings, an essential fundamental component in machinery and equipment, have been widely used. Predicting the remaining useful life (RUL) of rolling bearings helps maintain the reliability of mechanical systems. Accurate prediction of RUL requires extracting deep features in complex non-linear vibration signals, the prediction results often vary widely. This paper proposes a RUL prediction method based on convolutional neural network (CNN), bi-directional long-short term memory (BiLSTM), and bootstrap method (CNN-BiLSTM-Bootstrap) to model the forecasting uncertainty. The first step is to extract the first prediction time (FPT) of the degradation phase of rolling bearings using an adaptive method for the 3𝜎 intervals of rolling bearing vibration signal kurtosis. The model extracts the spatio-temporal features through CNN and BiLSTM, and combines the bootstrap method to quantify the RUL prediction interval (PI) of rolling bearings. The comparison with existing models verified the effectiveness and generalization of the proposed model.

show abstract

Status diagnosis and feature tracing of the natural gas pipeline weld based on improved random forest model

Cited by 22 publications

References 27 publications

Leveraging machine learning algorithms for improved disaster preparedness and response through accurate weather pattern and natural disaster prediction

Leveraging machine learning algorithms for improved disaster preparedness and response through accurate weather pattern and natural disaster prediction

Integrated Risk Assessment of Mountainous Long-Distance Oil and Gas Pipelines Based on Multisource Spatial Data

A CNN‐BiLSTM‐Bootstrap integrated method for remaining useful life prediction of rolling bearings

Contact Info

Product

Resources

About