Mohammad Mostafa Soltani

Localization of RFID-equipped assets during the operation phase of facilities

Indoor localization has gained importance as it has the potential to improve various processes related to the lifecycle management of facilities and to deliver personalized and location-based services (LBSs). Radio Frequency Identification (RFID) based systems, on the other hand, have been widely used in different applications in construction and maintenance. This paper investigates the usage of RFID technology for indoor localization of RFID equipped assets during the operation phase of facilities. The location-related data on RFID tags attached to assets are extracted from a Building Information Model (BIM) and can provide context-aware information inside the building which can improve Facilities Management (FM) processes. First, using the current location of the assets saved on the tags attached to fixed assets, an FM personnel is able to read tags from a distance and locate them on a floor plan. Fixed tags with known positions act as reference tags for RFID reader localization techniques. In this scenario, the user can also estimate his/her location by scanning the surrounding reference tags. Furthermore, the paper investigates an approach to locate moveable assets using received signals from available reference tags in the building based on pattern matching and clustering algorithms. As a result, a user equipped with an RFID reader is able to estimate his/her location, as well as the location of target assets, without having access to any Real-Time Location System (RTLS) infrastructure. Several case studies are used to demonstrate the feasibility of the proposed methods.

Extending IFC to incorporate information of RFID tags attached to building elements

We discussed the needs for adding definitions of RFID components to a BIM.We investigated scenarios to identify the related attributes of RFID system components.We investigated the relationships of RFID components with the assets/spaces.We proposed an IFC extension to incorporate the new definitions of RFID components.We validated and demonstrated the applicability of the proposed method through a real-world case study. Building Information Modeling (BIM) is emerging as a method of creating, sharing, exchanging and managing the building information throughout the lifecycle between all stakeholders. Radio Frequency Identification (RFID), on the other hand, has emerged as an automatic data collection and information storage technology, and has been used in different applications in the AEC/FM (Architecture, Engineering, Construction, and Facilities Management) industry. RFID tags are attached to building assets throughout their lifecycle and used to store lifecycle and context aware information taken from a BIM. Consequently, there is a need for a standard and formal definition of RFID technology components in BIM. The goal of this paper is to add the definitions for RFID components to the BIM standard and to map the data to be stored in RFID memory to the associated entries in a BIM database. The paper defines new entities, data types, and properties to be added to the BIM. Furthermore, the paper identifies the relationships between RFID tags and building elements. These predefined relationships facilitate the linkage between BIM data and RFID data. Eventually, the data that are required to be saved on RFID tags can be automatically selected using the defined relationships in a BIM. A real-world case study has been implemented to validate the proposed method using available BIM software.

High Level Framework for Bridge Inspection Using LiDAR-Equipped UAV

According to Statistics Canada, bridges in Canada have a service life of approximately 43 years. With the majority of bridges passing half of their expected service life, a large amount of investment needs to be made to inspect and maintain them in a safe condition. Manual inspection methods are both time-consuming and costly, which may discourage further inspections and follow-up of defects. Thus, there is a great need for using an automated data collection system. Surface defects (e.g. cracks) in concrete bridges can be inspected using 3D Light Detection and Ranging (LiDAR) scanner as a Non-Destructive Testing (NDT) method. However, the commonly used terrestrial LiDAR is limited to stationary data collection, which reduces the accessibility to some components of the bridges. To tackle this limitation, a LiDAR attached to an Unmanned Aerial Vehicle (UAV) provides more flexibility and accessibility for inspecting large surface areas without threatening inspectors’ safety. After providing a comprehensive literature review about the usage of UAVs and LiDAR for the inspection of different types of structures, this paper proposes a high level framework for bridge inspection using LiDAR-equipped UAV. The framework includes the following steps: (1) planning a collisionfree optimized path with respect to the minimum cost and maximum coverage considering a variety of constrains and requirements related to the hardware and the inspection task, and (2) data analysis for detecting the surface defects based on the collected

Evaluating the Performance of Convolutional Neural Network for Classifying Equipment on Construction Sites

Estimating the productivity of construction operations is one of the most challenging tasks for project managers. Therefore, the construction industry always looks toward new advancements for automating this process. New automated methods for productivity estimation aim to detect the types, locations, and activities of construction equipment based on sensory data. Computer Vision (CV) is one of the most promising automated methods and it provides an affordable opportunity for estimating the productivity since it only requires regular surveillance cameras for data collection, which are available on many construction sites. One of the widely used CV methods for classifying equipment is Histogram of Oriented Gradient (HOG). Additionally, Bag of Words (BoWs) and Local Binary Pattern (LBP) are other types of descriptors widely used for the object classification. However, these methods reduce the dimensions of the image features to train the classifiers for object detection, which may reduce the reliability of the results. Convolutional Neural Networks (CNN), which are a special type of Artificial Neural Networks (ANN) with deeper layer structure, provide a better approach for object detection compared to the conventional methods due to their deeper understanding of the object features. Furthermore, the advancements in Graphical Processing Units (GPU) made this computationally heavy method more applicable in practice. This paper aims to evaluate the performance of CNN for detecting equipment on construction sites. Several configurations of CNN are trained for detecting multiple equipment (i.e. dump trucks, excavators and loaders). The results of these configurations are compared with those of conventional detectors.