Unsupervised deep learning approach using a deep auto-encoder with a one-class support vector machine to detect damage

Zilong Wang, Young‐Jin Cha

Structural Health Monitoring 2020 article cited by 336

importance 6/10 ai assisted Structural Health Monitoring Techniques infrastructure monitoring stage: research

Problem

Detecting structural damage normally requires labeled data from many damage scenarios, which is time-consuming, costly, and often impractical for infrastructure in service.

Why it matters

Undetected structural damage threatens infrastructure safety, while labeling damage-scenario data is costly and impractical.

What the AI did

An unsupervised deep auto-encoder combined with a one-class SVM was trained only on acceleration data from intact/baseline structures to detect future structural damage.

Results

not stated in source

Impact

Enables damage detection without labeled damage-scenario data, using only baseline intact-structure measurements.

Record

Venue	Structural Health Monitoring
Published	2020
Work type	article
Authors	Zilong Wang, Young‐Jin Cha
Citations	336 (OpenAlex, at import time)
References	40
Model or method	deep auto-encoder with one-class support vector machine
Organization	not stated in source
Primary source	https://doi.org/10.1177/1475921720934051
Open access	closed
Keywords	structural health monitoring, deep auto-encoder, one-class SVM, unsupervised learning, damage detection

Importance rating

6 / 10

significant — thousands to millions affected

Undetected structural damage threatens infrastructure safety; removing costly labeled damage-scenario data enables monitoring of structures in service; no scale stated.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: not stated in source. Method and limits.

More in Engineering & Materials

#	Paper	Year	Citations	Importance
1	Scaling deep learning for materials discovery Amil Merchant, Simon Batzner, Samuel S. Schoenholz, Muratahan Aykol, G...	2023	1,471	8
2	Application of Machine Learning in Material Synthesis and Property Prediction Guannan Huang, Yani Guo, Ye Chen, Zhengwei Nie	2023	165	7
3	Machine learning-guided discovery of ionic polymer electrolytes for lithium metal batteries Kai Li, Jifeng Wang, Yuanyuan Song, Ying Wang	2023	115	7
4	Machine Learning for Structural Health Monitoring of Aerospace Structures: A Review Gennaro Scarselli, Francesco Nicassio	2025	44	7
5	Power System Transient Stability Assessment Based on Machine Learning Algorithms and Grid Topology Mihail D. Senyuk, Murodbek Safaraliev, Firuz Kamalov, Hana Sulieman	2023	42	7