Wood hole-damage detection and classification via contact ultrasonic testing
Source abstract
Abstract
Abstract Damage detection in wood materials has numerous applications in different industries, such as construction and forestry. Wood is generally a complex medium due to its orthotropic and random properties, which increases the difficulty of non-destructive damage testing. However, machine learning algorithms can be employed to overcome this problem. In this paper, hole-defect classification problems of two common types of wood materials, namely hard (marbau) and soft (pine) wood, are studied using a naive Bayes classification technique. To this end, the results of contact ultrasonic tests conducted on these types of woods in different directions, i.e. tangential and radial to the growth rings of wood, were investigated. The various states of the intact, small defect, and large defect of each type of wood were considered in the testing regime. It is known that contact ultrasonic tests are highly sensitive to different aspects of the test, such as the amount of couplant gel applied to surfaces, the amount of pressure applied to the transducer and receiver, and misalignment of the transducer and receiver. Therefore, 50 replicates of each test were implemented. First, an advanced signal decomposition algorithm termed Variational Mode Decomposition (VMD) was exploited to derive some features from the recorded ultrasonic signals. Then, the derived features were used in a set of classification problems using a naive Bayes classifier to classify the damage state of the specimens. Different types of naive Bayes classifiers, namely Gaussian and kernel, along with combinations of different types of features were employed to improve the results, ultimately achieving nearly 100% 10-fold cross-validation accuracy in all cases individually. However, when cases from different types of wood and direction of the tests were mixed, 93.6% 10-fold cross-validation accuracy was achieved for the classification problem based on the health state of the cases, using kernel naive Bayes classifier and a mixture of two types of features.
Source: openaire · Quality: candidate unverified · Source record ↗
Research context
OpenAlex topics: Wood Treatment and Properties · Industrial Vision Systems and Defect Detection · Tree Root and Stability Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (54)
Show source-provided references
1. Cost saving benefits of wood structure maintenance [for power overhead lines]
2. R&d of NDTs for timber utility poles in service-challenges and applications (extension for bridge sub-structures and wharf structures)
3. Damage detection of in service timber poles using Hilbert-Huang transform10.1016/j.ndteint.2019.102141 ↗
4. Wavelet packet energy–based damage identification of wood utility poles using support vector machine multi-classifier and evidence theory10.1177/1475921718798622 ↗
5. Green · 1999
6. EN 408:2010+A1:2012 · 2010
7. The wood from the trees: The use of timber in construction10.1016/j.rser.2016.09.107 ↗
8. A comparative study of using static and ultrasonic material testing methods to determine the anisotropic material properties of wood10.1016/j.conbuildmat.2015.07.195 ↗
9. Mechanical properties of wood materials using near-infrared spectroscopy based on correlation local embedding and partial least-squares10.1007/s11676-019-01031-7 ↗
10. Wood defect detection based on depth extreme learning machine10.3390/app10217488 ↗
11. Analysis of a wooden specimen’s mechanical properties through acoustic measurements in the very near field10.1121/10.0001030 ↗
12. Nondestructive evaluation of bending strength of wood with artificial holes by employing air-coupled ultrasonics10.1016/j.conbuildmat.2016.02.020 ↗
13. Development of a wood damage monitoring system for mechanized harvesting
14. Guided wave–based condition assessment of in situ timber utility poles using machine learning algorithms10.1177/1475921714521269 ↗
15. Automated health condition diagnosis of in situ wood utility poles using an intelligent non-destructive evaluation (NDE) framework10.1142/S021945542042002X ↗
16. A 2D numerical model of ultrasonic wave propagation in wooden utility poles using embedded waveguide excitation technique10.22382/wfs-2020-008 ↗
17. Condition assessment tool for timber utility poles using stress wave propagation technique10.1080/10589759.2020.1728267 ↗
18. An architectural evaluation method for conservation of traditional dwellings10.1016/j.buildenv.2005.02.009 ↗
19. Guidelines for on-site assessment of historic timber structures10.1080/15583058.2013.774070 ↗
20. Use of ultrasound as a nondestructive evaluation technique for sustainable interventions on wooden structures10.1016/j.buildenv.2014.07.022 ↗
21. Assessment of standing wood and fiber quality using ground and airborne laser scanning: A review10.1016/j.foreco.2011.01.032 ↗
22. Comparison of machine learning algorithms for forest parameter estimations and application for forest quality assessments10.1016/j.foreco.2018.12.019 ↗
23. Feature extraction of wood-hole defects using wavelet-based ultrasonic testing10.1007/s11676-016-0297-z ↗
24. Impact of internal structure on water-resistance of plywood studied using neutron radiography and X-ray tomography10.1016/j.conbuildmat.2014.09.095 ↗
25. Estimation of wood density using infrared thermography10.1016/j.conbuildmat.2013.01.001 ↗
26. Air-coupled ultrasonic nde: Experiments in the frequency range 750 kHz–2 MHz10.1016/S0963-8695(02)00012-9 ↗
27. Senalik · 2014 · 1
28. Changes of propagation velocity of ultrasonic waves and partial compression strength of decay-treated woods relationship between decrease of propagation velocity of ultrasonic waves and remaining strength10.2488/jwrs.57.359 ↗
29. Basic study on nondestructive evaluation of artificial deterioration of a wooden rafter by ultrasonic measurement10.1007/s10086-011-1186-x ↗
30. A novel methodology for condition assessment of wood poles using ultrasonic testing10.1016/j.ndteint.2012.08.002 ↗
31. Evaluation of compression and bending strength properties of wood damaged from bio-deterioration10.2472/jsms.62.280 ↗
32. Indirect detection of internal defects in wooden rafter with ultrasound10.5658/WOOD.2013.41.2.164 ↗
33. Prediction of modulus of elasticity of poplar wood using ultrasonic technique by applying empirical correction factors10.1016/j.measurement.2018.11.076 ↗
34. Basic study on nondestructive evaluation of artificial deterioration of a wooden rafter by ultrasonic measurement10.1007/s10086-011-1186-x ↗
35. Ultrasonic technique for evaluation of bio-defects in wood: Part 1–Influence of the position, extent and degree of internal artificial rots10.1179/2042645311Y.0000000019 ↗
36. Hirao · 2013
37. Drain · 2019
38. NDE applications of air-coupled ultrasonic transducers
39. Review of the use of air-coupled ultrasonic technologies for nondestructive testing of wood and wood products10.1016/j.compag.2017.03.015 ↗
40. Review of air-coupled ultrasonic materials characterization10.1016/j.ultras.2014.02.006 ↗
41. Modeling of delamination detection utilizing air-coupled ultrasound in wood-based composites10.1016/j.ndteint.2018.05.012 ↗
42. Operating instructions · 2013 · p16
43. Feature extraction of wood-hole defects using empirical mode decomposition of ultrasonic signals10.1016/j.ndteint.2020.102282 ↗
44. Variational mode decomposition10.1109/TSP.2013.2288675 ↗
45. Zosso · 2020
46. Research on variational mode decomposition and its application in detecting rub-impact fault of the rotor system10.1016/j.ymssp.2015.02.020 ↗
47. I. Rish, et al. An empirical study of the naive Bayes classifier, in: IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence, Vol. 3, 2001, pp. 41–46.
48. Adaptive mode decomposition methods and their applications in signal analysis for machinery fault diagnosis: A review with examples10.1109/ACCESS.2017.2766232 ↗
49. On the performance of variational mode decomposition-based radio frequency fingerprinting of bluetooth devices10.3390/s20061704 ↗
50. Matlab Machine Learning and Deep Learning Toolbox
51. Theory of communication. Part 1: The analysis of information
52. Beam damage detection using synchronisation of peaks in instantaneous frequency and amplitude of vibration data
53. Nondestructive testing of wood hole defect by ultrasonic spectrum analysis
54. Non-destructive wood density assessment of scots pine (Pinus sylvestris L.) using resistograph and pilodyn10.1371/journal.pone.0204518 ↗