POD Evaluation: The Key Performance Indicator for NDE 4.0

Rentala, Vamsi Krishna; Kanzler, Daniel; Fuchs, Patrick

doi:10.1007/s10921-022-00843-8

Cited by 7 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Under the absence of identifying the variances due to each different HF, one of the alternatives to account for the scatter is by obtaining literature information on variabilities due to HF and estimating the POD curves [15]. In addition to accounting for the total variance due to human factors, Rentala et al [10], [15] have also introduced a factor of bias in their work. This bias can be attributed to lack of motivation, lack of concentration, mood swings, or any other random variations that might happen.…”

Section: Statistical Methods For Incorporating Hf Into the Podmentioning

confidence: 99%

“…In the case of decreasing the reliability, it is extremely important to understand that how much the reliability of NDT techniques can be decreased due to the influence of different human factors. In spite of the extreme importance in understanding the influence of human factors in reliability assessments or POD studies of NDT techniques, this topic seems to be rarely investigated [10]. Even though, human factors are well researched qualitatively by several researchers, lack of proper information on the quantification of human factors possess huge difficulty for carrying out the reliability assessments by including the human factors [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Inclusion of human factors in POD assessments: a theoretical approach

Rentala¹,

Kanzler²

2023

8th International Workshop on Reliability of NDT/NDE

View full text Add to dashboard Cite

Even though, POD assessments of NDT techniques have been well demonstrated in various industrial sectors such as aviation, nuclear, oil and gas, railways, etc., they lack the inclusion of several influences as explained from the modular model. Influences due to intrinsic capabilities or due to application/environmental parameters can somehow be demonstrated under controlled laboratory and field inspection procedures. However, nowadays the biggest challenge lies in the inclusion of human factors and the organization context into the POD assessments and this can be mainly due to not being able to quantify the human factors. Hence, in the current work on accounting human factors influence on POD curves, the main idea is based on identifying majority of the human related tasks while carrying out the inspection procedures in terms of various statistical metrics. This topic on quantification of human factors is a part of the ongoing WIPANO project "normPOD", for the standardization of reliability assessment in Germany. This method of representation in terms of statistical metrics would enable holistic inclusion of human related influences in the form of the scatter parameters required for POD assessments. Efforts towards inclusion of these quantified human factor parameters into the POD assessments were shown by the adoption of Monte-Carlo approaches.

show abstract

Section: Statistical Methods For Incorporating Hf Into the Podmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Inclusion of human factors in POD assessments: a theoretical approach

Rentala¹,

Kanzler²

2023

8th International Workshop on Reliability of NDT/NDE

View full text Add to dashboard Cite

show abstract

“…For this reason, there is a need to assess the performance of the NDE method to evaluate if a defect can be found or not. This is normally done with probability of detection (POD) curves [20]. These, however, give no information on why a single defect may not be found.…”

Section: Neural Network Architectures For Probabilistic Segmentationmentioning

confidence: 99%

On the uncertainty in the segmentation of ultrasound images reconstructed with the total focusing method

2023

View full text Add to dashboard Cite

This study presents an investigation into the uncertainty of images reconstructed by the total focusing method (TFM) using non-destructive evaluation (NDE) and phased array probes. Four neural network architectures based on the U-Net model are used to probabilistically segment TFM images and evaluate the uncertainty of the segmentation results. The models are trained on three simulated phased-array datasets, which contain various sources of uncertainty from the simulated defects or surrounding material. Physical limitations, such as the defect’s shadow zone, led to high uncertainty. Results demonstrate that probabilistic segmentation can be helpful in determining the source of uncertainty within segmented TFM images. The model performance is investigated based on several metrics, and the influence of defect size on model performance is shown. The probabilistic U-Net shows the highest F1-score overall test datasets. This study contributes to the advancement of NDE using TFM by providing insights into the uncertainty of the reconstructed images and proposing a solution for addressing it.

show abstract

“…Thus, depending on the expected damage mechanism for a specific component, its material, location, and loading, the most suitable inspection method and corresponding intervals are integrated into the inspection program [7]. The most relevant reliability metric for this purpose is the probability of detection (POD) curve [8]. It applies to the use of a defined inspection method only under defined conditions.…”

Section: Introductionmentioning

confidence: 99%

“…On the AI side, additional factors such as the development of training, validation, and qualification data sets must be considered. Depending on the applied evaluation algorithm, additional reliability metrics (e.g., intersection of unity, receiver operating characteristic, probability of sizing) must be considered in addition to the POD curve [5,8]. On the SHM side, not only more sources of uncertainty must be considered, but also the time dimension for all IPs.…”

Section: Introductionmentioning

confidence: 99%

A framework for assessing the reliability of crack luminescence: an automated fatigue crack detection system

Gerards

Ratkovac

Schneider

et al. 2023

NDE 4.0, Predictive Maintenance, Communication, and Energy Systems: The Digital Transformation of NDE

View full text Add to dashboard Cite

The new crack luminescence method offers the possibility of making fatigue surface cracks in metallic materials more visible during inspections through a special coating system. This coating system consists of two layers, whereby the first layer has fluorescent properties and emits visible light as soon as it is irradiated by UV light. The top layer is black and is designed to prevent the fluorescent layer from emitting if no crack develops in the underlying material.The technique proved particularly useful in a wide variety of fatigue tests of steel components under laboratory conditions. Moreover, it has the potential to be used in various industrial applications. To enable industrial deployment and integration into maintenance strategies, a concept study is developed in this contribution, resulting in a qualification framework that can serve as a foundation for determining the reliability of the crack luminescence system in terms of a probability of detection curve. Within this study, factors causing measurement variability and uncertainty are being determined and their influences assessed. Due to the extension of the system by a moving computer vision system for automated crack detection using artificial intelligence, additional long-term effects associated with structural health monitoring systems need to be incorporated into an extended probability of detection study as part of the technical justification.Finally, important aspects and findings related to design of experiments are discussed, and a framework for reliability assessment of a new optical crack monitoring method is presented, emphasizing the influence of various uncertainty parameters, including long-term effects such as system ageing.

show abstract

POD Evaluation: The Key Performance Indicator for NDE 4.0

Cited by 7 publications

References 23 publications

Inclusion of human factors in POD assessments: a theoretical approach

Inclusion of human factors in POD assessments: a theoretical approach

On the uncertainty in the segmentation of ultrasound images reconstructed with the total focusing method

A framework for assessing the reliability of crack luminescence: an automated fatigue crack detection system

Contact Info

Product

Resources

About