Technological advancements in unmanned aerial vehicles(UAVs)have revolutionized various industries,enabling the widespread adoption of UAV-based solutions.In engineering management,UAV-based inspection has emerged as ...Technological advancements in unmanned aerial vehicles(UAVs)have revolutionized various industries,enabling the widespread adoption of UAV-based solutions.In engineering management,UAV-based inspection has emerged as a highly efficient method for identifying hidden risks in high-risk construction environments,surpassing traditional inspection techniques.Building on this foundation,this paper delves into the optimization of UAV inspection routing and scheduling,addressing the complexity introduced by factors such as no-fly zones,monitoring-interval time windows,and multiple monitoring rounds.To tackle this challenging problem,we propose a mixed-integer linear programming(MILP)model that optimizes inspection task assignments,monitoring sequence schedules,and charging decisions.The comprehensive consideration of these factors differentiates our problem from conventional vehicle routing problem(VRP),leading to a mathematically intractable model for commercial solvers in the case of large-scale instances.To overcome this limitation,we design a tailored variable neighborhood search(VNS)metaheuristic,customizing the algorithm to efficiently solve our model.Extensive numerical experiments are conducted to validate the efficacy of our proposed algorithm,demonstrating its scalability for both large-scale and real-scale instances.Sensitivity experiments and a case study based on an actual engineering project are also conducted,providing valuable insights for engineering managers to enhance inspection work efficiency.展开更多
The inspection of engine lubricating oil can give an indication of the internal condition of an engine. By means of the Object-Oriented Programming (OOP), an expert system is developed in this paper to computerize the...The inspection of engine lubricating oil can give an indication of the internal condition of an engine. By means of the Object-Oriented Programming (OOP), an expert system is developed in this paper to computerize the inspection. The traditional components of an expert system, such us knowledge base, inference engine and user interface are reconstructed and integrated, based on the Microsoft Foundation Class (MFC) library. To testify the expert system, an inspection example is given at the end of this paper.展开更多
The lack of care related to maintenance management is directly linked to the absence of plans for maintenance of buildings. Because of that, there is a big incidence of building accidents caused by the negligence of m...The lack of care related to maintenance management is directly linked to the absence of plans for maintenance of buildings. Because of that, there is a big incidence of building accidents caused by the negligence of managers and the lack of investment. The research has shown that, although building inspection is a consolidated building maintenance tool, managers do not prepare their building maintenance plan, nor use building inspection as a tool, leading the buildings to the premature obsolescence. The research calls attention to the building inspection technique that can be used to evaluate building maintenance and conservation. It is also a tool for analysis and investment planning based on actions to solve failures and anomalies that might come out during the building inspection. Those failures and anomalies are classified according to their degree of risk, determining the technical priorities of the investment adjustment in the maintenance plan. The paper presents a risk analysis methodology which classifies inspect elements in a building, determining the priority order of services to be executed on a scale from minimum risk （1） to imminent risk （5）. The method shows a tool for building inspection, and it serves as a guideline for building maintenance interventions.展开更多
Based on analysis of the present situation and problems of course project of the Internet of Things engineering,we propose a relational integrated course project pattern around three levels of perception layer,network...Based on analysis of the present situation and problems of course project of the Internet of Things engineering,we propose a relational integrated course project pattern around three levels of perception layer,network layer,application layer of the Internet of Things system.The realization of a complete Internet of Things system is divided into three course projects to complete three key points,which may eventually make a complete system of things.Through the link among the three integrated course projects,knowledge of four years will be connected together and form an organic whole.We use a team performance and examination methods of the process-oriented examination,project paper and oral examination for the integrated course project in order to improve students’cooperation ability,expression ability,communication ability and other integrated quality.展开更多
为解决危大工程中吊装作业安全管理的问题,基于深度学习构建目标检测算法(You Only Look Once version 5,YOLOv5)网络模型,针对进入吊装作业区域内人员的防护装备进行多目标融合检测,并对吊钩在施工过程中的状态进行检测。在原始的检测...为解决危大工程中吊装作业安全管理的问题,基于深度学习构建目标检测算法(You Only Look Once version 5,YOLOv5)网络模型,针对进入吊装作业区域内人员的防护装备进行多目标融合检测,并对吊钩在施工过程中的状态进行检测。在原始的检测网络模型中引入4种注意力机制,并通过5种训练模型的结果对比分析,进而选择卷积块注意力模块(Convolutional Block Attention Module,CBAM)最优模型。优化后的检测模型对安全帽的平均识别精度达86.5%,对反光衣的平均识别精度达83.0%,对吊钩的状态识别精度达92.0%。将训练好的人员检测模型和吊钩检测模型打包成exe执行文件,应用到施工安全管理人员的中控平台,可帮助管理人员更好地判断吊装作业的工作情况,进而及时进行风险管控。展开更多
基金supported by the National Natural Science Foundation of China(72201229,72025103,72394360,72394362,72361137001,72071173,and 71831008).
文摘Technological advancements in unmanned aerial vehicles(UAVs)have revolutionized various industries,enabling the widespread adoption of UAV-based solutions.In engineering management,UAV-based inspection has emerged as a highly efficient method for identifying hidden risks in high-risk construction environments,surpassing traditional inspection techniques.Building on this foundation,this paper delves into the optimization of UAV inspection routing and scheduling,addressing the complexity introduced by factors such as no-fly zones,monitoring-interval time windows,and multiple monitoring rounds.To tackle this challenging problem,we propose a mixed-integer linear programming(MILP)model that optimizes inspection task assignments,monitoring sequence schedules,and charging decisions.The comprehensive consideration of these factors differentiates our problem from conventional vehicle routing problem(VRP),leading to a mathematically intractable model for commercial solvers in the case of large-scale instances.To overcome this limitation,we design a tailored variable neighborhood search(VNS)metaheuristic,customizing the algorithm to efficiently solve our model.Extensive numerical experiments are conducted to validate the efficacy of our proposed algorithm,demonstrating its scalability for both large-scale and real-scale instances.Sensitivity experiments and a case study based on an actual engineering project are also conducted,providing valuable insights for engineering managers to enhance inspection work efficiency.
文摘The inspection of engine lubricating oil can give an indication of the internal condition of an engine. By means of the Object-Oriented Programming (OOP), an expert system is developed in this paper to computerize the inspection. The traditional components of an expert system, such us knowledge base, inference engine and user interface are reconstructed and integrated, based on the Microsoft Foundation Class (MFC) library. To testify the expert system, an inspection example is given at the end of this paper.
文摘The lack of care related to maintenance management is directly linked to the absence of plans for maintenance of buildings. Because of that, there is a big incidence of building accidents caused by the negligence of managers and the lack of investment. The research has shown that, although building inspection is a consolidated building maintenance tool, managers do not prepare their building maintenance plan, nor use building inspection as a tool, leading the buildings to the premature obsolescence. The research calls attention to the building inspection technique that can be used to evaluate building maintenance and conservation. It is also a tool for analysis and investment planning based on actions to solve failures and anomalies that might come out during the building inspection. Those failures and anomalies are classified according to their degree of risk, determining the technical priorities of the investment adjustment in the maintenance plan. The paper presents a risk analysis methodology which classifies inspect elements in a building, determining the priority order of services to be executed on a scale from minimum risk （1） to imminent risk （5）. The method shows a tool for building inspection, and it serves as a guideline for building maintenance interventions.
文摘Based on analysis of the present situation and problems of course project of the Internet of Things engineering,we propose a relational integrated course project pattern around three levels of perception layer,network layer,application layer of the Internet of Things system.The realization of a complete Internet of Things system is divided into three course projects to complete three key points,which may eventually make a complete system of things.Through the link among the three integrated course projects,knowledge of four years will be connected together and form an organic whole.We use a team performance and examination methods of the process-oriented examination,project paper and oral examination for the integrated course project in order to improve students’cooperation ability,expression ability,communication ability and other integrated quality.
文摘为解决危大工程中吊装作业安全管理的问题,基于深度学习构建目标检测算法(You Only Look Once version 5,YOLOv5)网络模型,针对进入吊装作业区域内人员的防护装备进行多目标融合检测,并对吊钩在施工过程中的状态进行检测。在原始的检测网络模型中引入4种注意力机制,并通过5种训练模型的结果对比分析,进而选择卷积块注意力模块(Convolutional Block Attention Module,CBAM)最优模型。优化后的检测模型对安全帽的平均识别精度达86.5%,对反光衣的平均识别精度达83.0%,对吊钩的状态识别精度达92.0%。将训练好的人员检测模型和吊钩检测模型打包成exe执行文件,应用到施工安全管理人员的中控平台,可帮助管理人员更好地判断吊装作业的工作情况,进而及时进行风险管控。
