CN113567454A - A UAV-based Port Crane Health Detection System - Google Patents

Abstract

Translated fromChinese

本发明公开了一种基于无人机的港口起重机健康检测系统，包括远程控制设备、图像采集设备、图像处理装置和检测报告生成装置，所述远程控制设备包括飞行任务规划装置、无线通讯模块和存储模块，所述图像采集设备包括无人机、机载探测装置、机器避障装置和无线通信模块，其中机载探测装置包括红外线成像仪和高清可见光相机，所述图像处理装置包括缺陷检测模块、无线通讯模块和存储模块，所述检测报告生成装置包括缺陷位置获取模块、缺陷类型获取模块、缺陷程度获取模块、检测信息汇总模块、报告输出模块和无线通讯模块，本发明具有图像采集效率高、缺陷识别效率高、缺陷检测更加准确、安全、快捷等优点。

The invention discloses a port crane health detection system based on unmanned aerial vehicle, comprising remote control equipment, image acquisition equipment, image processing device and detection report generation device. The remote control equipment includes a flight mission planning device, a wireless communication module and a A storage module, the image acquisition device includes an unmanned aerial vehicle, an airborne detection device, a machine obstacle avoidance device and a wireless communication module, wherein the airborne detection device includes an infrared imager and a high-definition visible light camera, and the image processing device includes a defect detection module , a wireless communication module and a storage module, the detection report generation device includes a defect location acquisition module, a defect type acquisition module, a defect degree acquisition module, a detection information summary module, a report output module and a wireless communication module. The present invention has the advantages of high image acquisition efficiency. , high defect recognition efficiency, more accurate defect detection, safety, and speed.

Description

Port crane health detection system based on unmanned aerial vehicle

Technical Field

The invention relates to the technical field of port crane detection, in particular to a port crane health detection system based on an unmanned aerial vehicle.

Background

The port crane is a logistics device widely applied to ports and mainly comprises three types, namely a shore bridge crane, a portal crane and a portal crane. Due to their frequent alternating loads and long term exposure to harbour environments with varying temperatures and humidity, cranes are prone to fatigue cracking, corrosion, wear, plastic deformation, damage to connecting parts, and other forms of safety defects. The existence of these potential safety hazards easily causes safety accidents and damages workers and equipment. Regular health detection of the port crane is an effective mode for preventing safety accidents, and can timely find dangerous defects and timely treat the dangerous defects to prevent the dangerous defects from evolving into safety accidents. Therefore, regular health checks of port cranes are essential for safe and efficient operation in ports.

At present, the health detection of the port crane is mainly checked in a traditional manual mode. The port staff inspects the metal structure surface of the port crane by visual inspection or by assisting a small amount of detection equipment. The detection mode has the defects of easy judgment error, low efficiency and safety risk to detection personnel. In addition, there are some parts which are difficult to reach and are extremely important for workers on the port crane, such as a main beam lower cover plate of a shore bridge crane and a portal crane, a bridge of a portal crane and the like. Therefore, a novel efficient, flexible and safe detection mode is urgently needed for health detection of the port crane.

In recent years, the unmanned aerial vehicle technology has been rapidly developed, it has the flexibility ratio height, maneuverability is strong, can carry on the advantage of multiple sensor and check out test set, the detection field of hoist has been applied to at present, chinese patent "bank bridge crane structure detecting system based on four rotor unmanned aerial vehicle" of publication No. CN106598073B takes a picture and passes ground through unmanned aerial vehicle to hoist metallic structure surface and detect, but this system also has some defects to the detection technology of hoist. Firstly, the image acquisition and detection efficiency is low, and a path planning module and a track planning module of an unmanned aerial vehicle in a detection system need to be improved; secondly, the defect recognition efficiency is low, the error is large, the unmanned aerial vehicle collects images and then recognizes the images by naked eyes, the recognition efficiency is low, the subjectivity is strong, and the error is large; thirdly, the defect of defect detection leakage exists when the image collected by the high-definition visible light camera is identified independently.

Disclosure of Invention

Aiming at the defects and shortcomings in the prior art, the invention provides the port crane health detection system based on the unmanned aerial vehicle, and the system has the advantages of high image acquisition efficiency, high defect identification efficiency, more accurate, safe and rapid defect detection and the like.

In order to achieve the purpose, the invention provides a port crane health detection system based on an unmanned aerial vehicle, which comprises a remote control device, an image acquisition device, an image processing device and a detection report generation device.

The remote control equipment comprises a flight mission planning device, a wireless communication module and a storage module. The flight mission planning device comprises a model input module, a coordinate module, a detection viewpoint generation module, a global path planning module, a global track planning module and a track output module, wherein remote control equipment is used for global path planning and global track planning of the unmanned aerial vehicle, the generated track of the unmanned aerial vehicle is transmitted to a flight controller of the unmanned aerial vehicle through a wireless communication module, and image information transmitted back to the surface of the port crane is stored.

Image acquisition equipment, it includes unmanned aerial vehicle, machine carries detection device, machine and keeps away barrier device and wireless communication module. Unmanned aerial vehicle includes organism structure and flight control ware, machine carries detection device and includes infrared imager and high definition visible light camera, the machine keeps away the barrier device and includes binocular vision sensor, local path planning module, local track planning module and local track output module, and image acquisition equipment is used for carrying out the flight task that remote control equipment conveys, at the in-process of carrying out the task, avoids real-time barrier, and final completion is detected the image of treating the position to port crane and is gathered to the storage module who sends the image information who gathers to the remote control equipment in stores.

The image processing device comprises a defect detection module, a wireless communication module and a storage module. The defect detection module comprises an image preprocessing unit, a feature extraction unit and a defect intelligent identification unit, and the image processing device is used for detecting the defects of the surface image of the port crane and storing defect information.

The detection report generating device comprises a defect position acquiring module, a defect type acquiring module, a defect degree acquiring module, a detection information summarizing module, a report output module and a wireless communication module. The detection report generating device is used for acquiring and summarizing defect position, type and degree information obtained after image processing, and outputting a report.

Further, the remote control device is connected with the image acquisition device through a wireless communication module, the remote control device is connected with the image processing device through the wireless communication module, and the image processing device is connected with the detection report generation device through the wireless communication module.

Further, a model input module of the flight mission planning device in the remote control equipment is an input module of a three-dimensional model of the port crane.

Further, a coordinate module of the flight mission planning device in the remote control equipment establishes a three-dimensional coordinate system for the input three-dimensional model of the port crane, and obtains a start point coordinate and an end point coordinate of the flight mission.

Further, a detection viewpoint generating module of the flight mission planning device in the remote control device is used for acquiring the position and coordinates of the shooting point of the unmanned aerial vehicle.

Further, unmanned aerial vehicle among the image acquisition equipment adopts four rotor unmanned aerial vehicle to unmanned aerial vehicle is equipped with protector, prevents to collide.

Further, an airborne detection device and a machine obstacle avoidance device in the image acquisition equipment are both carried on the unmanned aerial vehicle body.

Further, the unmanned aerial vehicle adopts binocular vision sensor and GPS positioning system to fix a position the unmanned aerial vehicle.

Further, the binocular vision sensors of the obstacle avoidance device of the machine in the image acquisition equipment are uniformly arranged in six directions of the unmanned aerial vehicle body, namely, one binocular vision sensor is arranged in each direction.

The invention has the beneficial effects that:

aiming at the characteristics of low efficiency, low defect recognition efficiency, large error and incomplete defect detection of the conventional port crane health detection, the invention provides a port crane health detection system based on an unmanned aerial vehicle. In addition, the unmanned aerial vehicle's route planning module and trajectory planning module have been added to this detecting system for the collection of image is more high-efficient.

Drawings

The invention is further illustrated by the following examples in conjunction with the accompanying drawings:

FIG. 1 is a schematic structural diagram of a port crane health detection system based on an unmanned aerial vehicle according to the invention;

FIG. 2 is a schematic diagram of the working flow of a port crane health detection system based on an unmanned aerial vehicle according to the present invention;

fig. 3 is a schematic view of a work flow of an image processing device in the unmanned aerial vehicle-based port crane health detection system.

Detailed Description

The following detailed description of embodiments of the invention refers to the accompanying drawings.

Referring to fig. 1, a port crane health detection system based on an unmanned aerial vehicle includes a remote control device, an image acquisition device, an image processing device and a detection report generation device, wherein the remote control device and the image acquisition device are connected through a wireless communication module, the remote control device and the image processing device are connected through a wireless communication module, and the image processing device and the detection report generation device are connected through a wireless communication module.

Furthermore, the remote control equipment comprises a flight mission planning device, a wireless communication module and a storage module, wherein the flight mission planning device comprises a model input module, a coordinate module, a detection viewpoint generation module, a global path planning module, a global trajectory planning module and a trajectory output module, the remote control equipment transmits the unmanned aerial vehicle trajectory planned by the system to the unmanned aerial vehicle through the wireless communication module, and receives the image information transmitted back by the unmanned aerial vehicle through the wireless communication module.

Further, image acquisition equipment keeps away barrier device and wireless communication module including unmanned aerial vehicle, machine carries detection device, machine. Unmanned aerial vehicle includes organism structure and flight control ware, machine carries detection device and includes infrared imager and high definition visible light camera, the machine keeps away the barrier device and includes binocular vision sensor, local path planning module, local orbit planning module and local orbit output module, and image acquisition equipment mainly used carries out the flight task that remote control equipment conveys, accomplishes the image acquisition who detects the position to port crane to the storage module who sends the image information who gathers to among the remote control equipment stores. Wherein, the barrier device is kept away to the machine is in order to avoid the unpredictable barrier of unmanned aerial vehicle flight in-process, when the barrier was monitored to binocular vision sensor among the device, the device was timely carries out local path planning and local track planning to give unmanned aerial vehicle's flight controller with the flight track, after unmanned aerial vehicle avoided the barrier smoothly, get back to unmanned aerial vehicle's global flight orbit again on, continue to carry out the image acquisition task, reach the task terminal point until unmanned aerial vehicle, the image acquisition task ends.

Further, the image processing device comprises a defect detection module, a wireless communication module and a storage module. The defect detection module comprises an image preprocessing unit, a feature extraction unit and a defect intelligent identification unit, wherein an image acquired by the unmanned aerial vehicle is subjected to noise reduction, blurring, shaking and distortion interference reduction on the image through the image preprocessing unit, then the defect area is identified through the feature extraction unit, the image of the defect area is subjected to graying and binaryzation processing, finally, the image data subjected to the feature extraction unit is compared with the image data in a historical database, the defect is intelligently identified, the defect information is stored in the storage module, and the defect information is sent to the detection report generation device.

Further, the detection report generation device comprises a defect position acquisition module, a defect type acquisition module, a defect degree acquisition module, a detection information summarizing module, a wireless communication module and a report output module. The detection report generating device firstly receives the defect information sent by the image processing device, then the defect position acquiring module, the defect type acquiring module and the defect degree acquiring module respectively acquire the position, the type and the degree of the defect from the defect information, and finally the detection information summarizing module summarizes the defect information of each position and outputs a report.

As shown in fig. 2, the present invention is implemented by the following steps:

the method comprises the following steps: selecting a three-dimensional model of a port crane of a corresponding type to input the three-dimensional model into a model input module aiming at the port crane to be detected;

step two: establishing a coordinate system for the three-dimensional model of the port crane through a coordinate module, and acquiring coordinates of a starting point and an end point of a flight task of the unmanned aerial vehicle;

step three: aiming at the structural surface of the port crane needing to be detected, generating a detection viewpoint of the unmanned aerial vehicle through a detection viewpoint generating module, wherein the detection viewpoint is positioned in the outward normal direction passing through the midpoint of the detection surface;

step four: planning an optimal path passing through all the detection viewpoints by a global path planning module;

step five: optimizing the generated global path through a global trajectory planning module to enable the generated global path to meet the speed and acceleration constraints of the unmanned aerial vehicle;

step six: the planned unmanned aerial vehicle track is transmitted to a flight controller of the unmanned aerial vehicle through a track output module and a wireless communication module, so that the unmanned aerial vehicle flies along the specified track until the unmanned aerial vehicle flies to the terminal point of the unmanned aerial vehicle, all image information is transmitted to remote control equipment, the flight task is finished, and real-time obstacles in the flight process are avoided through a machine obstacle avoidance device in the flight process;

step seven: transmitting the image data to an image processing device, acquiring defect information through an image preprocessing unit, a feature extraction unit and a defect intelligent identification unit, and storing the defect information in a storage module, wherein the specific flow is shown in fig. 3;

step eight: the method comprises the steps of respectively obtaining the position, type and degree of a defect from defect information through a defect position obtaining module, a defect type obtaining module and a defect degree obtaining module, and finally summarizing the defect information of each position through a detection information summarizing module to further generate a detection report.

Claims (5)

Translated fromChinese

1.一种基于无人机的港口起重机健康检测系统，包括远程控制设备、图像采集设备、图像处理装置和检测报告生成装置。其中，所述远程控制设备和图像采集设备通过无线通信模块进行连接，所述远程控制设备和图像处理装置通过无线通信模块连接，所述图像处理装置与检测报告生成装置通过无线通信模块连接。1. An unmanned aerial vehicle-based port crane health detection system, comprising a remote control device, an image acquisition device, an image processing device and a detection report generation device. The remote control device and the image acquisition device are connected through a wireless communication module, the remote control device and the image processing device are connected through a wireless communication module, and the image processing device and the detection report generation device are connected through a wireless communication module.2.根据权利要求1所述的一种基于无人机的港口起重机健康检测系统，所述远程控制设备，包括飞行任务规划装置、无线通讯模块和存储模块，所述飞行任务规划装置包括模型输入模块、坐标模块、检测视点生成模块、全局路径规划模块、全局轨迹规划模块和轨迹输出模块，远程控制设备用于无人机的全局路径规划、全局轨迹规划，将生成的无人机轨迹通过无线通讯模块传达给无人机的飞行控制器，并储存传送回来的港口起重机表面的图像信息。2. A UAV-based port crane health detection system according to claim 1, the remote control device comprises a flight mission planning device, a wireless communication module and a storage module, and the flight mission planning device comprises a model input module, coordinate module, detection viewpoint generation module, global path planning module, global trajectory planning module and trajectory output module. The communication module communicates to the flight controller of the drone and stores the image information of the surface of the port crane transmitted back.3.根据权利要求1所述的一种基于无人机的港口起重机健康检测系统，所述图像采集设备，包括无人机、机载探测装置、机器避障装置和无线通信模块，所述无人机包括机体结构和飞行控制器，所述机载探测装置包括红外线成像仪和高清可见光相机，所述机器避障装置包括双目视觉传感器、局部路径规划模块、局部轨迹规划模块和局部轨迹输出模块，图像采集设备用于执行远程控制设备传送来的飞行任务，在执行任务的过程中，对实时障碍物进行躲避，最终完成对港口起重机待检测部位的图像采集，并将采集的图像信息传送给远程控制设备中的存储模块进行储存。3. A UAV-based port crane health detection system according to claim 1, wherein the image acquisition device comprises an UAV, an airborne detection device, a machine obstacle avoidance device and a wireless communication module, the unmanned aerial vehicle The man-machine includes a body structure and a flight controller, the airborne detection device includes an infrared imager and a high-definition visible light camera, and the machine obstacle avoidance device includes a binocular vision sensor, a local path planning module, a local trajectory planning module and a local trajectory output. Module, the image acquisition device is used to execute the flight mission sent by the remote control device. During the execution of the mission, the real-time obstacles are avoided, and finally the image acquisition of the part to be detected of the port crane is completed, and the acquired image information is transmitted. To store the storage module in the remote control device.4.根据权利要求1所述的一种基于无人机的港口起重机健康检测系统，所述图像处理装置，包括缺陷检测模块、无线通讯模块和存储模块。所述缺陷检测模块包括图像预处理单元、特征提取单元和缺陷智能识别单元，图像处理装置用于港口起重机表面图像的缺陷检测和缺陷信息储存。4. The drone-based port crane health detection system according to claim 1, wherein the image processing device comprises a defect detection module, a wireless communication module and a storage module. The defect detection module includes an image preprocessing unit, a feature extraction unit and an intelligent defect identification unit, and the image processing device is used for defect detection and defect information storage of the surface image of the port crane.5.根据权利要求1所述的一种基于无人机的港口起重机健康检测系统，所述检测报告生成装置，包括缺陷位置获取模块、缺陷类型获取模块、缺陷程度获取模块、检测信息汇总模块、报告输出模块和无线通讯模块，检测报告生成装置用于经过图像处理后获得的缺陷位置、类型、程度信息的获取与汇总，并将报告输出。5. A drone-based port crane health detection system according to claim 1, wherein the detection report generating device comprises a defect location acquisition module, a defect type acquisition module, a defect degree acquisition module, a detection information summary module, The report output module and the wireless communication module, and the detection report generation device are used for obtaining and summarizing the defect position, type and degree information obtained after image processing, and outputting the report.

Images