Advanced system for heightened situational awareness and risk management in construction projects

用于增强建筑项目态势感知和风险管理的先进系统

• 批准号: 506997-2016
• 负责人: Yu, JiaYuan
• 金额: $ 3.74万
• 依托单位: Concordia University
• 依托单位国家: 加拿大
• 项目类别: Collaborative Research and Development Grants
• 财政年份: 2019
• 资助国家: 加拿大
• 起止时间: 2019-01-01 至 2020-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=690295
• 关键词: Advanced; system; heightened; situational; awareness

The goal of this project is to improve the safety, efficiency, and accountability of large construction projects. Such projects are very complex, involving expensive heavy equipment and human resources, and typically very difficult to manage. We propose to design and develop a decision-support system that helps the management through automated safety alerts, performance metrics, and record keeping. The system takes as input data from internet-connected sensors, including cameras, deployed on the construction sites. With the help of domain experts from construction companies and GreenOwl, we develop algorithms for equipment, human, and event detection for use specifically in the construction domain. Our proposed system is a one-of-its-kind application of cutting edge machine learning to the area of construction projects. The record keeping feature of this system will also contribute indirectly to deter safety protocol violations, corruption, and inefficiencies in large-scale construction projects.

该项目的目标是提高大型建设项目的安全性、效率和问责制。此类项目非常复杂，涉及昂贵的重型设备和人力资源，并且通常非常难以管理。我们建议设计和开发一个决策支持系统，通过自动安全警报、绩效指标和记录保存来帮助管理层。该系统将来自部署在建筑工地的联网传感器（包括摄像头）的数据作为输入数据。在建筑公司和 GreenOwl 领域专家的帮助下，我们开发了专门用于建筑领域的设备、人员和事件检测算法。我们提出的系统是尖端机器学习在建筑项目领域的独一无二的应用。该系统的记录保存功能还将间接有助于阻止大规模建设项目中的安全协议违规、腐败和低效率行为。