Hotspot and Sampling Analysis for Effective Maintenance Management and Performance Monitoring (Research Brief]

Liu, Xiaoyue Cathy; Chen, Zhuo

i

Hotspot and Sampling Analysis for Effective Maintenance Management and Performance Monitoring (Research Brief]

2019-07-01
By Liu, Xiaoyue Cathy ; Chen, Zhuo

File Language:

English

Details

Creators:

Liu, Xiaoyue Cathy ; Chen, Zhuo
Corporate Creators:

University of Utah. Department of Civil and Environmental Engineering ; Mountain-Plains Consortium
Corporate Contributors:

United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
Subject/TRT Terms:

Algorithms Asset Management Cluster Analysis Condition Surveys Data Analysis Highway Maintenance Inspection Literature Reviews Maintenance Management Performance Measurement
Publication/ Report Number:

MPC 19-392
Resource Type:

Brief
Geographical Coverage:

United States ; Utah
Edition:

Research Brief
Corporate Publisher:

Mountain-Plains Consortium
Abstract:

Researchers developed a sampling method utilizing machine learning techniques to suggest the location and frequency of sampling roadway assets. The method strives to choose proper highway segments where the conditions of sampled assets can represent the maintenance performance of the full inventory within the network. To this end, the researchers present a high-dimensional clustering-based stratified sampling (HDCSS) method for roadway asset inspection. The method allows transportation agencies to adjust parameters, such as sample size, inspection frequency, and assets of interest. The HDCSS method integrates asset deterioration prediction, high-dimensional clustering, and locality-sensitive hashing (LSH). The sampling method can also incorporate various features of the asset network, such as asset condition, geographic information, traffic condition, and geometric design, as the information upon which samples can be selected. The method is adaptable to any asset changes, as the sampling process is constantly updated with previous inspection results and maintenance records.
Format:

PDF
Funding:

528
Collection(s):

University Transportation Centers
Main Document Checksum:

urn:sha-512:845b5a0eff079116716f872cd230de986eb0f1130787b4934c96ab7715f17da7e18df208228f11ee7bd9294a9039569240b49883231c99392a38733be120062d
Download URL:

https://rosap.ntl.bts.gov/view/dot/92935/dot_92935_DS1.pdf
File Type:

[PDF - 335.62 KB ]

File Language:

English

ON THIS PAGE

Details

Found an issue?

Send us an email at:

publishinghd@cdc.gov

ROSA P serves as an archival repository of USDOT-published products including scientific findings, journal articles, guidelines, recommendations, or other information authored or co-authored by USDOT or funded partners. As a repository, ROSA P retains documents in their original published format to ensure public access to scientific information.