Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Extracting structural components of concrete buildings from laser scanning point clouds from construction sites

Change detection of urban objects using 3D point clouds: A review

Automated extraction of structural beam lines and connections from point clouds of steel buildings

It is important to assess existing reinforced concrete (RC) structures with damages. This task, however, is traditionally empirical and time‐consuming. To improve assessment accuracy and efficiency, this study proposed an approach to semantic model damaged RC beams based on point clouds. A slice‐based method for automatically modeling deformed beams and a color‐based crack detection method were developed for generating building information modeling (BIM) and finite element (FE) models. Furthermore, to enhance structural assessment and decision‐making by providing both damage and loading performance analysis data, a framework to extend the existing IFC standard was proposed for interoperability issues between FE models and BIM, aiming to integrate semantic‐enrichment damages and FE analysis results in the as‐is BIM model. Experiments were carried out on a simply supported RC beam subjected to a concentrated load. As a result, the improvement of the developed as‐is BIM model for damage visualization and structural assessment was confirmed.

IFC‐based semantic modeling of damaged RC beams using 3D point clouds

The use of Building Information Modeling (BIM) is a growing reality in the civil industry. Merging 3D geometric information with engineering data, the BIM model combines geometry, spatial relationships, and other properties used at all stages of the building’s life cycle. With the need to apply such methodology to existing buildings, researchers have focused on how to automatically generate or update such models from 3D point clouds provided by laser scanning sensors or photogrammetry methods. Most of this research has focused on the recognition of either planar (e.g., floor, walls) or cylindrical (e.g., piping) structures. Few works have dealt with the detection of steel structural elements, due to its particular shape, and only recently focused on detecting their geometric specifications. However, in these approaches, the point cloud of each structural element was manually separated from the point cloud of the entire building. This situation creates a challenge since the manual segmentation of a point cloud is a long and subjective process. In addition to geometric information, recent research has focused on automatically detecting anomalies in structures. Such information, incorporated into the BIM model, allows the structural element to be evaluated using structural analysis applications. The availability of the results of this analysis to BIM professionals is essential for the correct planning of possible interventions. Unfortunately, open-source BIM model visualization tools restrict their functionalities to design review and construction analysis. In this work, we propose an extension of a previous automated method to detect steel elements to identify and measure deformations and a visualization tool that shows the quality of an existing building’s structural elements directly in the 3D point cloud. With the results of deformation detection, we compute the quality level of structural elements and present it directly in the 3D view of the building, preserving its spatial context, with the use of colors and annotations.

Automatic Deformation Detection and Analysis Visualization of 3D Steel Structures in As-Built Point Clouds

From the perspective of offshore installations, corrosion is the most common form of damage and the main factor affecting the longevity and reliability of assets. Maintenance plans based on risk and reliability are modern approaches. For a complex technical system such as a platform, maintenance management can use different approaches, such as reliability centered maintenance (RCM) that uses failure mode and effect analysis (FMEA) in determining the criticality of failure modes by the ranking of risks (e.g. related to corrosion rates and remaining life of the asset). However, in some practical cases, the implementation of the traditional FMEA may not be realistic due to the subjectivity of the dimensioning the risk factors. In this sense, this research aims to propose a more robust and practical methodology to assess the criticality of risks of external corrosion failures by the system. This methodology combines fuzzy scale method, risk space diagram and weighted Euclidean distance and is applied based on the perception of specialists in external corrosion. From an academic point of view, this research highlights the importance of using RCM for corrosion management in an empirical case. From the practitioner’s perspective, we seek to provide a tool, based on the RCM and the combination of fuzzy logic and multicriteria approach to rank systems to be inspected. Therefore, this new FMEA model can help to save time, cost and reduce fieldwork, considering gains related to quality, safety, technical efficiency in inspection and maintenance processes.

Marina Polonia Rios

Papers

Automatic Deformation Detection and Analysis Visualization of 3D Steel Structures in As-Built Point Clouds

Fuzzy Criticality Assessment of Systems External Corrosion Risks in the Petroleum Industry—A Case Study