Predicting the compressive strength of unreinforced brick masonry using machine learning techniques validated on a case study of a museum through nondestructive testing

Mishra, Mayank; Bhatia, Amanjeet Singh; Maity, Damodar

doi:10.1007/s13349-020-00391-7

Cited by 42 publications

(13 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Less applications are found for all the other methods. Machine learning techniques are useful for making estimations and predictions based on past data and project cases [76,105,112]. These techniques have the ability the ability to handle large amounts of datasets [34].…”

Section: Discussionmentioning

confidence: 99%

Decision Support in Building Construction: A Systematic Review of Methods and Application Areas

2020

View full text Add to dashboard Cite

Decision making is a relevant task in the building construction sector, and various systems and methods for decision support are emerging. By means of a systematic literature review, this article identifies the methods for decision making in building construction and the lifecycle phases for which decision support systems are proposed. The selected articles are analyzed and grouped according to the adopted decision-making methods and the defined lifecycle phases. The findings show that multiple criteria decision analysis is the most used method for decision support in building construction and that the construction phase is the most addressed phase within the relevant existing works. The findings related to the construction phase are further refined by grouping the articles into application areas and by reviewing in detail the proposed methods therein. The scarce availability of data and project cases is identified as the most common barrier for the successful development and implementation of decision support systems in the building construction sector. This work provides a basis for scientists and practitioners for identifying suitable methods for decision-making support in a specific lifecycle phase of a building.

show abstract

Section: Discussionmentioning

confidence: 99%

Decision Support in Building Construction: A Systematic Review of Methods and Application Areas

2020

View full text Add to dashboard Cite

show abstract

“…where , and are multipliers for the water speed, , shear speed, , and longitudinal speed, , used in Eqs. (2)(3)(4)(5)(6). These values are larger than the true variation in material sound speed is likely to be; for example, carbon steel experiences less than a 10% variation in sound speed [31] across the full temperature range an inline pipe inspection tool is able to operate in (−10 to 50°C [32]).…”

Section: E Sound Speed Variationmentioning

confidence: 99%

“…Shallow learning in NDE dates back to at least 1991 with the use of decision trees to detect defects using the loss in amplitude of ultrasonic wall reflections [1] and has continued to be an active area of research [2]. For example, fullyconnected neural networks have been used to classify defects [3], [4] and estimate material properties [5], [6] from ultrasonic measurements and support vector machines used to size cracks from eddy current field peaks [7].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning for Ultrasonic Crack Characterization in NDE

Pyle

Bevan

Hughes

et al. 2021

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

View full text Add to dashboard Cite

Machine learning for Non-Destructive Evaluation (NDE) has the potential to bring significant improvements in defect characterization accuracy due to its effectiveness in pattern recognition problems. However, the application of modern machine learning methods to NDE has been obstructed by the scarcity of real defect data to train on. This paper demonstrates how an efficient, hybrid finite element and ray-based simulation can be used to train a Convolutional Neural Network (CNN) to characterize real defects. To demonstrate this methodology, an inline-pipe inspection application is considered. This uses four plane wave images from two arrays, and is applied to the characterization of cracks of length 1-5 mm and inclined at angles of up to 20° from the vertical. A standard image-based sizing technique, the 6 dB drop method, is used as a comparison point. For the 6 dB drop method the average absolute error in length and angle prediction is ±1.1 mm, ±8.6° while the CNN is almost four times more accurate at ±0.29 mm, ±2.9°. To demonstrate the adaptability of the deep-learning approach, an error in sound speed estimation is included in the training and test set. With a maximum error of 10% in shear and longitudinal sound speed the 6 dB drop method has an average error of ±1.5 mm, ±12° while the CNN has ±0.45 mm, ±3.0°. This demonstrates far superior crack characterization accuracy by using deep learning rather than traditional image-based sizing.

show abstract

“…Historic masonry structures were an essential part of China’s cultural heritage 6 , 7 . They played a vital role in the cultural inheritance, crystallized the working people’s wisdom in different periods, and had high artistic and scientific value 8 . However, historical changes fostered long-term erosion of the natural environment 9 – 11 , and human beings’ improper short-sighted use in reconstruction, the masonry structure of modern buildings suffered various degrees of damage 12 – 14 .…”

Section: Introductionmentioning

confidence: 99%

Experimental study on the properties of modern blue clay brick for Kaifeng People's Conference Hall

Bao

2021

Sci Rep

View full text Add to dashboard Cite

This article presents building assessment research comprising on-site inspections, indoor scientific tests, and material performance studies on the wall blue clay bricks in the Kaifeng People’s Conference Hall, objectively developing an enhanced scientific understanding to renovate modern buildings. Using X-ray diffraction (XRD), scanning electron microscopy (SEM), alongside a parametric study of density, moisture content, water absorption, void ratio, frosting, compressive strength, and softening coefficient in assessing the material health of the blue clay bricks and it’s non-key parts, in developing “appropriate and compatible renovation” to repair contemporaneous buildings. The composition, pore characteristics, weathering degree, and mechanical properties of the blue clay brick samples were analyzed. These parameters showed that blue clay brick fired at less than 1000 °C; the main mineral composition as quartz, followed by albite, mica, and anorthite. Its density was 1.573 g/cm3, less than the 1.70 g/cm3 of ordinary clay brick. According to the standards, the water absorption was greater than that of regular sintered bricks by more than 18% and was slightly frosted. Compressive strength being less than MU10 did not meet the current design specifications for masonry. Its softening coefficient was between 0.70 and 0.85, but its water resistance was relatively good. The research results provide an essential reference for judging the health and longevity of modern buildings to achieve scientific guidelines for practical protection.

show abstract

Predicting the compressive strength of unreinforced brick masonry using machine learning techniques validated on a case study of a museum through nondestructive testing

Cited by 42 publications

References 74 publications

Decision Support in Building Construction: A Systematic Review of Methods and Application Areas

Decision Support in Building Construction: A Systematic Review of Methods and Application Areas

Deep Learning for Ultrasonic Crack Characterization in NDE

Experimental study on the properties of modern blue clay brick for Kaifeng People's Conference Hall

Contact Info

Product

Resources

About