The Midwest Transportation Center (MTC) sponsors a competitive research program to fund projects focused on State of Good Repair in infrastructure with attention to safety and Data Driven Performance Measures for Enhanced Infrastructure Condition.
The following details one project led by Iowa State University. Stay up to date on research conducted by the MTC here.
Iowa State University
Terrestrial Laser Scanning-Based Bridge Structural Condition Assessment
Project PI: Yelda Turkan Project Co-PI: Simon Laflamme
Objective, accurate, and fast assessment of a bridge’s structural condition is critical to the timely assessment of safety risks. Current practices for bridge condition assessment rely on visual observations and manual interpretation of reports and sketches prepared by inspectors in the field. Visual observation, manual reporting, and interpretation have several drawbacks, such as being labor intensive, subject to personal judgment and experience, and prone to error. Terrestrial laser scanners (TLS) are promising sensors for automatically identifying structural condition indicators, such as cracks, displacements, and deflected shapes, because they are able to provide high coverage and accuracy at long ranges. However, limited research has been conducted on employing laser scanners to detect cracks for bridge condition assessment, and the research has mainly focused on manual detection and measurement of cracks, displacements, or shape deflections from the laser scan point clouds.
This research project proposed to measure the performance of TLS for the automatic detection of cracks for bridge structural condition assessment. Laser scanning is an advanced imaging technology that is used to rapidly measure the three-dimensional (3D) coordinates of densely scanned points within a scene. The data gathered by a laser scanner are provided in the form of point clouds, with color and intensity data often associated with each point within the cloud. Point cloud data can be analyzed using computer vision algorithms to detect cracks for the condition assessment of reinforced concrete structures. In this research project, adaptive wavelet neural network (WNN) algorithms for detecting cracks from laser scan point clouds were developed based on the state-of-the-art condition assessment codes and standards. Using the proposed method for crack detection would enable automatic and remote assessment of a bridge’s condition. This would, in turn, result in reducing the costs associated with infrastructure management and improving the overall quality of our infrastructure by enhancing maintenance operations.
Some key findings of this research included the following:
- The National Department of Roads (NDOR) and the Iowa Department of Transportation (DOT) bridge inspection procedures involve visual inspection and some nondestructive testing protocols, with inspections typically performed every 24 months. NDOR indicated that detecting small hairline cracks is challenging, and some small cracks may close up in certain weather conditions.
- For the experimental data, the compact representation created using the adaptive WNN algorithm provided a good fit of the 3D point cloud and included the crack feature. The algorithm was found to be capable of replacing a set of 8,170 3D coordinates into a set of 59 functions while preserving the key features of the scan data.
- A strategy to sequentially construct a compact representation of a 3D point cloud can be used to transform thousands of 3D point cloud data obtained from TLS into a small set of functions.
- Comparing root mean square (RMS) error and the number of nodes in the network showed that there is a point at which the algorithm provides an optimal representation in term of minimizing RMS error. The accuracy decreased as the number of nodes in the network increased because the network parameters become mistuned. When the network contains more nodes and the initial bandwidth is large, a relatively longer training period would be expected to obtain an acceptable level of accuracy
- The strategy of identifying regions of wavelets (or nodes) of lower bandwidths was found to approximately localize the damage features and estimate their geometry.