CN-121979343-A - Control method of intelligent outdoor operation spraying unmanned aerial vehicle, spraying unmanned aerial vehicle and medium

CN121979343ACN 121979343 ACN121979343 ACN 121979343ACN-121979343-A

Abstract

The invention relates to a control method of an intelligent outdoor operation spraying unmanned aerial vehicle, the spraying unmanned aerial vehicle and a medium in the technical field of unmanned aerial vehicles. The control method comprises the steps of calculating to obtain wall surface characteristics according to wall surface images I shot by the unmanned aerial vehicle, and calculating spraying pressure compensation and corrected speed of the unmanned aerial vehicle according to the wall surface characteristics. The spray initial pressure is calculated based on the reference spray pressure. And compensating the interference factors of the unmanned aerial vehicle. And (5) carrying out weighted fusion on the spraying pressure compensation, the initial spraying pressure and the interference factor compensation to obtain the final spraying pressure. And calculating according to the corrected speed of the unmanned aerial vehicle to obtain the final spraying flow. According to the invention, the quality pre-judgment and the stable two-dimensional regulation and control of the system are realized through the newly designed spraying logic architecture, the adaptability of complex working conditions is improved, the uniformity of the coating and the spraying quality are ensured, and the novel spraying logic architecture has the advantages of compact structure, convenience in operation and strong anti-interference capability, and is suitable for the spraying operation of various outdoor walls, storage tanks and the like.

Inventors

CAI BIXIN
Wei Dongjuan
HU ZHENGHE
WANG MAOMAO
ZHAO WEN
PAN JIABAO
HUANG WEI
ZHOU LICHUN

Assignees

安徽工程大学

Dates

Publication Date: 20260505
Application Date: 20260203

Claims (10)

1. The control method of the intelligent outdoor operation spraying unmanned aerial vehicle is characterized by comprising the following steps of: Calculating according to a wall surface image I shot by the unmanned aerial vehicle to obtain wall surface characteristics, wherein the wall surface characteristics comprise roughness R mean , texture complexity T complex and reflectivity R ref ; Dividing the working surface grade of the wall surface according to the characteristics of the wall surface, and obtaining spraying pressure compensation delta P wall corresponding to the working surface grade through a preset rule; Calculating to obtain corrected speed V of the unmanned aerial vehicle according to T complex and reference flight speed V base of the unmanned aerial vehicle; Comparing the coordinate data of the unmanned aerial vehicle with a preset path to obtain a track deviation delta R of the unmanned aerial vehicle, correcting the track if the delta R is more than or equal to a threshold value, and calculating the initial spraying pressure P init if the delta R is less than the threshold value: P init =P base ×F; wherein P base is the reference spraying pressure, and F is the fusion decision coefficient; The method comprises the steps of compensating interference factors of the unmanned aerial vehicle, calculating gust compensation delta P wind according to the attitude offset delta theta of the unmanned aerial vehicle if gust interference is detected, calculating load compensation delta P load based on the current mass m real , the initial weight m 0 and the spray head spraying area S of the unmanned aerial vehicle if the mass change delta m of the unmanned aerial vehicle is detected to be larger than a threshold value, and calculating pipeline tension compensation delta P pipe based on F pipe if the pipeline tension F pipe of the unmanned aerial vehicle is detected to be larger than or equal to the threshold value; Calculating according to P init 、ΔP wall 、ΔP wind 、ΔP load 、ΔP pipe to obtain final spraying pressure P final ; and calculating according to v to obtain the final spraying flow Q.
2. The control method of the intelligent outdoor operation spraying unmanned aerial vehicle according to claim 1, wherein in the obtained wall surface characteristics, R mean is a gray gradient mean value of I extracted by adopting a Sobel horizontal gradient method Then, obtaining through linear mapping; T complex is obtained by extracting the number of 5×5 window edge pixels of I by Canny edge detection; r ref is obtained by carrying out gray value statistics on the I.
3. The control method of the intelligent outdoor operation spraying unmanned aerial vehicle according to claim 1, wherein the operation surface level comprises a first level, a second level and a third level, and the dividing method comprises the following steps: If R mean is less than or equal to a roughness threshold value I U T complex is less than or equal to a texture complexity threshold value I U R ref is more than or equal to a reflectivity threshold value I, dividing the texture into three stages; If the roughness threshold I is less than or equal to R mean and less than or equal to the roughness threshold II and the texture complexity threshold I is less than or equal to T complex and less than or equal to the texture complexity threshold II and the reflectivity threshold II is less than or equal to R ref and less than or equal to the reflectivity threshold I, dividing the texture complexity threshold I into two stages; If R mean > roughness threshold two U T complex > texture complexity threshold two U R ref < reflectivity threshold two, then divide into one stage.
4. The control method of an intelligent outdoor operation spraying unmanned aerial vehicle according to claim 1, wherein the calculation mode of v is: v=V base ×(1-k v ×T complex ); Wherein k v is a correction coefficient obtained from industry experience values; And/or, if P final ＞P base + correction value, v is increased by 0.02-0.05 m/s; If P final ＜P base is a correction value, v is reduced by 0.02-0.05 m/s; If P base -correction < P final ＜P base + correction, v is unchanged.
5. The control method of an intelligent outdoor work spraying unmanned aerial vehicle according to claim 1, wherein the method for obtaining Δr is: the deviation value obtained after the actual track is compared with the track of the preset path is delta R; The calculation mode of F is as follows: F=α·D norm +β·I feature +γ·A stab +δ·L acc ; ; Wherein alpha is distance data weight, beta is image feature weight, gamma is gesture data weight, delta is positioning data weight, D norm is optimal working distance of the unmanned aerial vehicle, I feature is comprehensive image feature value of I, A stab is gesture change rate of the unmanned aerial vehicle, and L acc is positioning error.
6. The control method of the intelligent outdoor operation spraying unmanned aerial vehicle according to claim 5, wherein the genetic algorithm is adopted to optimize alpha, beta, gamma and delta, the optimization target is to minimize the total error weighted sum J, the constraint condition is that alpha+beta+gamma+delta=1, and the optimization target function is: minJ=0.4ΔQ+0.3ΔD+0.3ΔA; Wherein DeltaQ is spray quality deviation related to beta, deltaD is distance deviation between the unmanned aerial vehicle related to alpha and a working surface, and DeltaA is attitude fluctuation deviation of the unmanned aerial vehicle related to gamma.
7. The method for controlling an intelligent outdoor work spraying unmanned aerial vehicle according to claim 6, further comprising dynamically correcting P final according to spraying quality feedback after spraying the wall surface based on P final and Q, wherein the method for dynamically correcting P final comprises: Calculating to obtain the coating thickness h according to the image of the wall surface after spraying, and calculating the difference delta Q real between the coating thickness h and the process target thickness; If the delta Q real is greater than the threshold, increasing the weight of the delta Q, and reducing the delta P wall by 0.01-0.03 MPa; If ΔQ real < threshold, ΔP wall is increased by 0.01 to 0.03MPa.
8. The control method of the intelligent outdoor operation spraying unmanned aerial vehicle according to claim 1, wherein in the process of compensating the interference factors of the unmanned aerial vehicle, the condition of detecting the interference of the gust is that the attitude change rate of the unmanned aerial vehicle is larger than a threshold value; The calculation formula of the delta P wind is that delta P wind =k wind ×Δθ;k wind is a gust compensation coefficient; And/or the calculation formula of the delta P load is that the delta P load =k load ×(m 0 -m real ) ×g/S;k load is a load compensation coefficient; and/or, the calculation formula of the delta P pipe is that the delta P pipe =k pipe ×F pipe ;k pipe is a tension compensation coefficient; and/or the calculation formula of P final is P final =P init ×ΔP wall +0.33·ΔP wind +0.33·ΔP load +0.33·ΔP pipe ; and/or, the calculation formula of Q is that q=k q ×v;k q is a flow correction coefficient.
9. Intelligence outdoor operation spraying unmanned aerial vehicle, its characterized in that, it includes: a body; The spraying assembly is used for spraying the wall surface; A controller for controlling a spray pressure and a spray flow of a spray assembly using the control method of the intelligent outdoor work spray drone of any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the steps of the control method of the intelligent outdoor work painting unmanned aerial vehicle according to any one of claims 1 to 8.

Description

Control method of intelligent outdoor operation spraying unmanned aerial vehicle, spraying unmanned aerial vehicle and medium Technical Field The invention relates to the technical field of unmanned aerial vehicles, in particular to a control method of an intelligent outdoor operation spraying unmanned aerial vehicle, the spraying unmanned aerial vehicle and a medium. Background The surface spraying operation of outdoor large-scale structures, including building outer walls, bridges and large-scale storage tanks, mainly depends on two traditional modes at present, namely, constructing a scaffold or using an overhead working truck, and is completed by manually holding a spray gun. These approaches have the common problems of low operating efficiency, high safety risk, and excessive reliance on personal experience of workers for spray quality. In the prior art, a scheme of carrying spraying equipment on an unmanned aerial vehicle to perform operation has appeared, however, such unmanned aerial vehicle-based spraying technology still has obvious limitations, for example, in the prior art, a simple unmanned aerial vehicle platform and spraying equipment integrated mode is adopted, and control logic is relatively primary. Most technologies only directly apply a general control model or a neural network model, and the self-adaption capability is often insufficient aiming at a specific scene of spraying operation. On the other hand, the existing method is used for linearly adjusting the spraying pressure only according to the distance between the unmanned aerial vehicle and the wall surface, and various dynamic interference factors actually existing in the outdoor environment, such as sudden gusts, wall surface roughness change, change of coating viscosity along with temperature and the like, can cause unstable spraying quality of the unmanned aerial vehicle during spraying operation, so that spraying defects are easily generated, and material waste and operation reworking are easily caused. Disclosure of Invention The invention provides a control method of an intelligent outdoor operation spraying unmanned aerial vehicle, the spraying unmanned aerial vehicle and a medium, and aims to solve the technical problem that the spraying quality of the existing unmanned aerial vehicle is unstable. In the first aspect, the invention provides a control method of an intelligent outdoor operation spraying unmanned aerial vehicle, which comprises the step of calculating according to a wall surface image I shot by the unmanned aerial vehicle to obtain wall surface characteristics, namely roughness R mean, texture complexity T complex and reflectivity R ref. And dividing the working surface grade of the wall surface according to the characteristics of the wall surface, and obtaining spraying pressure compensation delta P wall corresponding to the working surface grade through a preset rule. And calculating the corrected speed V of the unmanned aerial vehicle according to the T complex and the reference flight speed V base of the unmanned aerial vehicle. Comparing the coordinate data of the unmanned aerial vehicle with a preset path to obtain a track deviation delta R of the unmanned aerial vehicle, correcting the track if the delta R is more than or equal to a threshold value, and calculating the initial spraying pressure P init if the delta R is less than the threshold value: Pinit=Pbase×F; Wherein P base is the reference spraying pressure, and F is the fusion decision coefficient. The method comprises the steps of compensating interference factors of the unmanned aerial vehicle, calculating gust compensation delta P wind according to the attitude offset delta theta of the unmanned aerial vehicle if gust interference is detected, calculating load compensation delta P load based on the current mass m real, the initial weight m 0 and the spray head spraying area S of the unmanned aerial vehicle if the mass change delta m of the unmanned aerial vehicle is detected to be larger than a threshold value, and calculating pipeline tension compensation delta P pipe based on F pipe if the pipeline tension F pipe of the unmanned aerial vehicle is detected to be larger than or equal to the threshold value. The final spray pressure P final is calculated from P init、ΔPwall、ΔPwind、ΔPload、ΔPpipe. And calculating according to v to obtain the final spraying flow Q. In a second aspect, the invention also provides an intelligent outdoor operation spraying unmanned aerial vehicle, which comprises a machine body, a spraying assembly and a controller. Wherein, the spraying assembly is used for spraying the wall. The controller controls the spray pressure and the spray flow of the spray assembly using the control method of the intelligent outdoor work spray drone in the first aspect. In a third aspect, the present invention also proposes a computer readable storage medium storing a computer program, which when executed by a processor implements the ste