Review on automated condition assessment of pipelines with machine learning

Liu, Yiming; Bao, Yi

doi:10.1016/j.aei.2022.101687

Cited by 79 publications

(17 citation statements)

References 143 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(3) Data filtering: After interpolating GNSS data, to remove artificial low-frequency trends, high-pass filtering is performed on the LVA data to reduce random noise. (4) IRI calculation: To convert the LVA to displacement data, the FFT algorithm is used for transferring the data to the frequency domain (29).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of Smartphone-Based and Drone-Based Approaches for Assessing Road Roughness

Afsharnia

Ghavami

2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Continuous road-pavement condition monitoring is essential to maintain the effectiveness and performance of road infrastructure. It also helps to optimize resource allocation and prioritization for pavement rehabilitation programs. The traditional methods that have been used for assessing road pavement condition are high cost and time consuming. Contrary to conventional methods, low-cost and new emerging technologies such as smartphones and drones can be used. The study aims to investigate the merits of using two different types of device for assessing road roughness: the smartphone as a response-type and the drone as a non-contact-type device. To this end, firstly, linear vertical acceleration data is collected by using a smartphone that is mounted on a car dashboard. Then, the collected data is used for calculating vertical displacement data using a fast Fourier transform. The displacement data is used for calculating international roughness index (IRI) as a measure of road roughness. Secondly, a drone flies over the studied road to construct a 3D model, extract the longitudinal profile, and eventually calculate the accurate IRI values of the road. Finally, the results of the approaches above will be compared with the results of a road surface profiler (RSP) as a reference method. Although the results reveal a significant correlation (above 0.8) of both methods with the RSP method, from an operational point of view, the smartphone was more cost and time effective, and also an easy-to-use approach for the purpose.

show abstract

Section: Methodsmentioning

confidence: 99%

“…IRI calculation: To convert the LVA to displacement data, the FFT algorithm is used for transferring the data to the frequency domain ( 29 ). The converted data is a form of longitudinal profile that can be used to calculate IRI using an in-house code developed by Šroubek et al or a well-known software package such as ProVal ( 27 , 30 ).…”

Section: Methodsmentioning

confidence: 99%

Comparison of Smartphone-Based and Drone-Based Approaches for Assessing Road Roughness

Afsharnia

Ghavami

2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…Various defects such as wheel flats, spalling, chipping, and polygonization are common [ 9 , 10 ]. Advances in sensor technology, driven by the integration of the Internet of Things (IoT) and Artificial Intelligence (AI), have revolutionized monitoring and diagnostics in various industries, including construction [ 11 ], energy [ 12 ], healthcare [ 13 ], renewable energy [ 14 ], security [ 15 ], and transport [ 16 ]. Specifically in the railway context, a typical train bogie can house between 10 and 50 sensors.…”

Section: Introductionmentioning

confidence: 99%

Anomaly Detection in Railway Sensor Data Environments: State-of-the-Art Methods and Empirical Performance Evaluation

Bałdyga,

Barański,

Belter

et al. 2024

Sensors

View full text Add to dashboard Cite

To date, significant progress has been made in the field of railway anomaly detection using technologies such as real-time data analytics, the Internet of Things, and machine learning. As technology continues to evolve, the ability to detect and respond to anomalies in railway systems is once again in the spotlight. However, railway anomaly detection faces challenges related to the vast infrastructure, dynamic conditions, aging infrastructure, and adverse environmental conditions on the one hand, and the scale, complexity, and critical safety implications of railway systems on the other. Our study is underpinned by the three objectives. Specifically, we aim to identify time series anomaly detection methods applied to railway sensor device data, recognize the advantages and disadvantages of these methods, and evaluate their effectiveness. To address the research objectives, the first part of the study involved a systematic literature review and a series of controlled experiments. In the case of the former, we adopted well-established guidelines to structure and visualize the review. In the second part, we investigated the effectiveness of selected machine learning methods. To evaluate the predictive performance of each method, a five-fold cross-validation approach was applied to ensure the highest accuracy and generality. Based on the calculated accuracy, the results show that the top three methods are CatBoost (96%), Random Forest (91%), and XGBoost (90%), whereas the lowest accuracy is observed for One-Class Support Vector Machines (48%), Local Outlier Factor (53%), and Isolation Forest (55%). As the industry moves toward a zero-defect paradigm on a global scale, ongoing research efforts are focused on improving existing methods and developing new ones that contribute to the safety and quality of rail transportation. In this sense, there are at least four avenues for future research worth considering: testing richer data sets, hyperparameter optimization, and implementing other methods not included in the current study.

show abstract

“…The MFL detection device scans along the axial direction to acquire magnetic induction intensity data, referred to as MFL data [7]. In doing so, a significant amount of data would be gathered by the MFL detecting device to fulfill the requirements of high testing precision and long pipeline distances [8].…”

Section: Introductionmentioning

confidence: 99%

Magnetic flux leakage defect size estimation method based on physics-informed neural network

Xiong,

Liu,

Hou

et al. 2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

Magnetic flux leakage (MFL) is a magnetic method of non-destructive testing for in-pipe defect detection and sizing. Despite the fact that recent developments in machine learning have revolutionized disciplines like MFL defect size estimation, the most current methods for quantifying pipeline defects are primarily data-driven, which may violate the underlying physical knowledge. This paper proposes a physics-informed neural network-based method for MFL defect size estimation. The training process of neural network is guided by the MFL data and the physical constraints that is mathematically represented by the magnetic dipole model. We use synthetic MFL data produced by a virtual MFL testing of pipeline defects to validate the proposed method through a comparison to purely data-driven neural networks and support vector machines. The findings imply that the physics-informed strategy can both improve predictive accuracy and mitigate physical violations in MFL testing, providing us with a better knowledge of how neural networks perform in defect size estimation. This article is part of the theme issue ‘Physics-informed machine learning and its structural integrity applications (Part 2)’.

show abstract

Review on automated condition assessment of pipelines with machine learning

Cited by 79 publications

References 143 publications

Comparison of Smartphone-Based and Drone-Based Approaches for Assessing Road Roughness

Comparison of Smartphone-Based and Drone-Based Approaches for Assessing Road Roughness

Anomaly Detection in Railway Sensor Data Environments: State-of-the-Art Methods and Empirical Performance Evaluation

Magnetic flux leakage defect size estimation method based on physics-informed neural network

Contact Info

Product

Resources

About