Research On Cooperative Inspection Of Indoor Substation Multi-UAV Based On UWB

In recent years,due to the continuous growth of the scale of cities and the continuous increase of electricity consumption,the number of indoor and underground substations has been increasing,resulting in increasing pressure for daily inspections.Traditional manual inspections are time-consuming,laborious,and inefficient.Robot inspections are severely restricted by terrain.At this stage,the use of flexible single UAVs for inspections is limited by factors such as insufficient battery life and limited load capacity.The inspection efficiency of the machine.Therefore,based on the above problems,this paper proposes the use of multi-UAV collaborative inspection to solve the shortcomings of single-UAV inspection,robot inspection and manual inspection.And for the complex indoor substation environment,a UWB positioning system with a fault-tolerant mechanism is proposed to provide a guarantee for the stable,safe and efficient coordinated inspection of multiple drones.The main research contents of this paper are as follows:By analyzing the research status of UWB positioning technology,it is concluded that the current research on UWB fault-tolerant positioning is still in its infancy,but for the complex indoor substation environment,its switch cabinets,transformers,bus bars and many other obstacles are likely to cause collapse of UWB positioning Therefore,it is imperative to conduct fault-tolerant positioning research on UWB.In this regard,this article considers the abnormal situation of UWB base stations,and proposes a positioning method based on improved least squares support vector machines.Firstly,bilateral ranging is adopted to collect UWB positioning data,which is divided into training set and test set,and the training set does not contain dynamic data.Then the training set is used to train the location model of the Least-squares support vector machine and particle swarm optimization is used to optimize the penalty factor and kernel function of the least-squares support vector machine.Finally,static experiment,dynamic experiment and comparison experiment of different algorithms are carried out to verify the effectiveness of the proposed localization algorithm.Experimental results show that UWB positioning accuracy is up to 4.7cm under all normal anchor conditions,which is greatly improved compared with traditional UWB positioning algorithm.In the case of abnormal anchor,the fault-tolerant positioning accuracy of UWB is within12.9cm.Compared with other current UWB fault-tolerant positioning algorithms,the positioning accuracy has been greatly improved.From the current research status of power UAV inspection and multi-UAV path planning as an entry point,the feasibility of applying multi-UAV to indoor substation inspection is clarified.The static obstacles of the indoor substation can be modeled by using the Maklink diagram method to complete the establishment of barrier-free and passable paths.Using Djikstra algorithm to find the shortest inspection path for each UAV,the total inspection path distances of the three UAVs are: 107.12 m,118.01 m and 117.97 m.An improved artificial potential field method is proposed to realize the real-time obstacle avoidance of UAVs considering the synergetics among UAVs.Finally,ROS is used to design the control program of multi-UAV,and the effectiveness of the proposed multi-UAVs collaborative patrol scheme is verified in Gazebo 3D simulation environment.At the same time,the improved artificial potential field method is compared with the traditional artificial potential field method,and the results show that the improved artificial potential field method is more safe and stable for the control of multi-UAVs collaborative inspection.In summary,this paper conducts fault-tolerant positioning research on UWB in a complex indoor environment,aiming to provide high-precision positioning information for drones and robots in real time,and on the basis of this positioning,proposes a multi-UAV coordinated inspection of indoor substation inspections.The inspection solution solves the shortcomings of battery life and insufficient load in the current single-machine inspection of electric UAVs.