An Automated Monitoring and Control System for Construction Projects using Advanced Technologies

施工项目进度监测和结构尺寸合规控制是使决策者能够识别项目计划状态和竣工状态之间的差异，并在需要时及时采取措施的关键。在实践中，监测是人工进行的，这是一项耗时、容易出错和劳动密集型的任务，特别是在大型项目中。为了减少人工监控的时间和成本，收集有限的现场数据，限制项目管理团队及时确定延误、成本超支和返工的原因。平均而言，返工的直接成本为总施工成本的5%，主要是由于施工过程中的错误造成的。此外，项目绩效的正确确定在很大程度上取决于监测过程中收集的数据的准确性。目前，现场监督人员仅花费30%-50%的时间来手动检查和控制手动积累的现场数据的质量。为了提高采集数据的质量，目前的研究目标是使用激光雷达和相机等遥感技术来获取建筑元素的三维点云；然而，最近的研究使用计划模型作为先验知识，将累积的点云分配给相应的结构元素，当计划和实际不同和/或计划模型没有足够的细节时，会提供不准确的结果。因此，在PI之前作为NSERC发现拨款的一部分所做的工作中，开发了一个独立于计划模型的细节的自动竣工模型生成系统。尽管该系统解决了当前文献的一些主要局限性，但为了提供自动化监控过程的全面解决方案，必须解决三个主要问题：1)自动实时数据采集；2)项目结果的随机预测和决策支持解决方案，以满足项目限制；以及3)项目结果的全息可视化和数据有效性控制。该提案期望通过设计和实施三个相互关联的项目来克服这些限制。这项研究计划与卡尔加里大学于2016年10月启动的“新地球空间技术”研究战略相一致，专门针对5项已确定的研究挑战中的1项--地理空间通信。该系统的有效实施可以使建筑业受益于：1)改善数据收集和分析的时间、成本和质量；2)及时识别返工和延误；以及3)最大限度地减少施工索赔和纠纷。

Construction project progress monitoring and structural dimensional compliance control are essential to allow decision makers to identify discrepancies between the planned and the as-built states of a project, and take timely measures where required. In practice, monitoring is performed manually, a time consuming, error-prone and labour intensive task, particularly in large scale projects. To reduce the time and cost of manual monitoring, limited onsite data is collected, restricting the project management team to identify the causes of delays, cost overruns, and rework on time. On average, the direct cost of rework is 5% of the total construction cost, mainly caused by errors during construction. In addition, the correct determination of the project's performance relies heavily on the accuracy of the collected data during the monitoring process. Currently, site supervisory personnel spend 30-50% of their time just to manually inspect and control the quality of the manually accumulated onsite data. To improve the quality of the collected data, current research has aimed to use remote sensing technologies such as LiDAR and cameras to acquire 3D point clouds of the construction element; however, recent research studies use the planned model as a priori knowledge to assign the accumulated point clouds to their corresponding structural element, which provide inaccurate results when the planned and the actual differ and /or the planned model is not available with sufficient detail. Therefore, in the PI's previous work as a part of the NSERC Discovery grant, an automated as-built model generation system, independent from the details of the planned model, was developed. Although this system addresses some of the main limitations of the current literature, three main concerns must be solved in order to provide a comprehensive solution to automating the monitoring and control process: 1) automatic real-time data acquisition; 2) stochastic prediction of project outcomes and decision support solution to meet project constraints; and 3) holographic visualisation of the project outcomes and data validity control. This proposal expects to overcome these limitations through the design and implementation of three interrelated projects. This research program aligns with the “New Earth Space Technologies” research strategy of the University of Calgary launched in October 2016, specifically targeting 1 of 5 identified research challenges, the Geospatial Communication. The efficient implementation of this system can benefit the construction industry by: 1) improving the time, cost and quality of data collection and analysis; 2) timely identification of rework and delays; and 3) minimizing construction claims and disputes.