123 results about "Solar azimuth angle" patented technology

The present invention relates to a solar azimuth estimation method and system based on multi-channel feature enhancement and region-aware attention, belonging to the technical field of intelligent navigation for low-altitude economy unmanned systems. Aiming at the problem of decreased accuracy in solar azimuth estimation based on polarization images under complex cloud cover conditions, the present invention proposes a deep learning framework integrating multi-channel features and direction-aware attention. First, based on polarization light field information acquired by a division-of-focal-plane polarization camera, a three-channel composite input feature composed of a polarization intensity map, an adaptive threshold gradient map, and high-frequency residual edge information is constructed. Second, a ResNet backbone network embedded with a squeeze-and-excitation mechanism is adopted, and a direction-aware polarization attention module is introduced to achieve adaptive fusion of multi-scale features through luminance guidance, deep feature enhancement, and a gradient edge branch.

The invention relates to the technical field of solar irradiance prediction, and discloses a solar irradiance prediction method and system based on data fusion, and the method comprises the steps: obtaining a cloud layer gray image, a wind speed vector, a terrain elevation, a slope inclination angle, a solar azimuth angle and an elevation angle, calculating the movement speed and direction of a cloud layer based on the cloud layer image and the wind speed vector, and obtaining a prediction result. Calculating a shielding path in combination with a terrain elevation and a sun position; generating a terrain shielding influence coefficient matrix; fusing a gradient and shielding data to generate a dynamic effect graph; performing cloud-ground shielding analysis based on the dynamic effect graph and a cloud trajectory to obtain cloud-ground coupling influence distribution; using a random forest algorithm to fuse the coupling distribution and the shielding coefficient to calculate an initial irradiance probability, and forming a preliminary prediction result; and inputting the time sequence prediction model, the cloud trajectory and the shielding coefficient into a trained time sequence prediction network, and outputting an optimization result. According to the method, prediction requirements under complex terrains and rapid weather changes can be met.

The invention discloses a photovoltaic power generation intelligent control system of photovoltaic panels in an optical storage direct flexible system, and relates to the technical field of photovoltaic power generation, the intelligent control system comprises a plurality of photovoltaic panel assemblies, the plurality of photovoltaic panel assemblies comprise main node assemblies, one main node assembly is arranged every 5-10 groups of photovoltaic panel assemblies, and the main node assemblies are connected with the photovoltaic panel assemblies; the master node assembly is configured with a high-precision double-axis sun sensor and an edge calculation module and is responsible for collecting a solar azimuth angle, a current inclination angle of the assembly and environment temperature and humidity data in real time, and the slave node assembly is configured with a single-axis inclination angle sensor and adjusts a tracking angle by receiving a master node instruction. Specifically, a master-slave node heterogeneous design is adopted, the slave node only needs a single-axis tilt angle sensor and a wireless communication module, the hardware configuration number is reduced, and cost control is achieved. According to the method for photovoltaic panel tracking optimization, the control instruction quantity of the system is reduced, the central control pressure is remarkably reduced, and the problems of cost and complexity during large-scale application of photovoltaic panel tracking are solved.

It discloses an atmospheric polarized light orientation method using a solar azimuth region, provides an angle of polarization (AOP) vision-modulated model in a pixel frame, and gives an orientation strategy utilizing the solar azimuth region; a horizontal attitude angle is introduced into the AOP in the pixel frame, and orientation is implemented by utilizing a separation point and a principal point of photograph; specifically, a seed line extraction algorithm is given to update the solar azimuth in real time, a morphological expression and an AOP expression of the solar azimuth are fused for an optimum estimation to the solar azimuth, and ultimately the orientation is achieved by using an external sensor such as an inertial navigation system to input the horizontal attitude angle.

The invention discloses a radiation correction method and system for an airborne hyperspectral imager. The radiation correction method and system are used for improving the radiation correction precision in complex weather. The method comprises the following steps: calculating a theoretical sun position based on unmanned aerial vehicle initial coordinates, ephemeris data and atmospheric parameters; performing course and differential compensation on a solar azimuth angle by combining IMU course and wind speed and direction data, performing refraction correction on an elevation angle, and outputting a high-precision sun position parameter; hyperspectral images and irradiance data are synchronously acquired, quaternion interpolation is combined with IMU data to realize space-time alignment, and attitude disturbance is eliminated; a hemispherical space irradiance model is constructed based on alignment data, cloud layer modes (clear sky, thin cloud and thick cloud) are divided according to atmospheric optical thickness variance, and Lambert body proportion correction, a discrete longitudinal standard method or a deep convolutional spectral network are respectively adopted for radiation correction. The method remarkably improves the correction precision and generalization ability, supports large-area image splicing, and is suitable for quantitative application of geological exploration, environment monitoring and the like.

The invention provides an intelligent light following control method and system for a photovoltaic support, a medium and a program product, and relates to the technical field of intelligent control. The method comprises the following steps: acquiring local geography and current time information, and acquiring current illumination intensity through a plurality of light sensors; and when the illumination intensity exceeds the preset starting threshold value, controlling a plurality of image acquisition devices on the photovoltaic panel to shoot a shadow of a measuring marker post located at the center of the photovoltaic panel, and obtaining image data. And then, geography, time and shadow image data are input into a shadow benchmark analysis model, and the model is trained and constructed through a deep learning algorithm based on a local solar azimuth change rule, an actually measured benchmark shadow and optimal power generation angle data of the photovoltaic panel, so that photovoltaic panel adjustment parameters are determined. And finally, a control instruction is sent to the motor according to the parameters, so that the photovoltaic panel automatically faces the sun. By implementing the method, the motor can be driven to enable the photovoltaic panel to accurately follow light, and solar energy is fully utilized, so that the power generation efficiency is improved.

The invention discloses an eye protection display control method and system based on ambient light, a medium and a product, and relates to the field of data processing. The method comprises the following steps: acquiring data such as vehicle internal environment illumination, a solar azimuth angle, a driving posture and relative positions of eyes of a driver and a display screen; based on the data, determining an estimated glare area and corresponding intensity within a preset time by analyzing the reflection condition of external illumination on the surface of the display screen; defining a target dimming area from a polymer dispersed liquid crystal dimming layer on the surface of the display screen according to the pre-estimated glare area; determining a driving voltage parameter of the target dimming area according to the estimated glare intensity so as to adjust the scattering degree of the target dimming area; and dynamically optimizing the display effect of the pre-estimated glare area in combination with the environment illumination data, the display content of the glare area and the scattering degree. The problem that the eyesight of a driver and the driving safety are affected due to the fact that a glare area is formed on the surface of the vehicle-mounted display screen by ambient light can be relieved.

The invention discloses a wind power plant light and shadow effect evaluation method and device and a medium. The problem that deviation exists in calculation of the shadow effect influence range of a traditional wind turbine generator is solved. The method comprises the following steps of: determining a shadow influence range of a wind wheel surface of each wind turbine generator at each moment in a year by taking true sun time at a machine location point of each wind turbine generator as a time standard; counting the total influence duration of each grid point according to the shadow influence ranges of all the wind turbine generators; and determining whether the design scheme meets a preset specification requirement or not according to the total influence duration of each grid point. According to the method, the wind power plant influence area is divided, the solar elevation angle and the solar azimuth angle are calculated point by point and moment by moment, so that the wind wheel surface shadow ellipse range of each wind turbine generator is calculated, the maximum influence duration of each point in the annual theory is obtained, the wind power plant shadow effect influence range calculation precision is improved, and the wind power plant shadow effect calculation efficiency is improved. And detailed data support is provided for environmental impact assessment of the wind power plant.

The invention is suitable for the technical field of security and protection, and provides an azimuth angle determination method and device of image acquisition equipment, electronic equipment and a product. The method comprises the following steps: acquiring an image acquired by image acquisition equipment; determining a solar azimuth angle of the position of the image acquisition equipment; and determining the azimuth angle of the image acquisition equipment based on the solar azimuth angle and the image. According to the invention, the azimuth angle of the image acquisition equipment can be determined.

The invention provides a photovoltaic tracking support angle optimization and power generation efficiency improvement method for meteorological prediction, and relates to the technical field of meteorological prediction, and the method comprises the steps: building a deep neural network model through receiving meteorological data, predicting future meteorological data, calculating a solar azimuth angle and an elevation angle, and building a photovoltaic tracking support motion constraint model for safety risk avoidance. And an optimal angle sequence is optimized and solved by adopting an improved dynamic programming algorithm, and an angle adjusting instruction is generated to control the bracket to adjust. According to the invention, the power generation efficiency of the photovoltaic module is improved, and the safety of the system in severe weather is ensured.

The invention discloses a building sunshade control method and system, and is applied to the technical field of sunshade equipment, and the method comprises the steps: determining a plurality of pieces of sunshade equipment and a plurality of indoor areas of a target building; for each piece of sunshade equipment, determining a plurality of control areas in the plurality of indoor areas according to the solar elevation angle, the solar azimuth angle and the window illumination value of each indoor area, and obtaining target control parameters of the sunshade equipment according to control parameters of each control area relative to the sunshade equipment; wherein the control area is an indoor area which is located in a direct solar radiation area and has a window illumination value larger than a preset illumination threshold value under the condition that solar rays directly enter a room of the target building; and according to the target control parameter of each piece of sunshade equipment, controlling each piece of sunshade equipment so as to shade each control area. According to the invention, cooperative sunshade control of a plurality of control areas and a plurality of sunshade devices is realized, and the sunshade control precision is improved.

The invention discloses a navigation method based on underwater polarized light detection, which belongs to the technical field of navigation, is used for underwater navigation, and comprises the following steps: collecting polarization images by a polarization camera, calculating a polarization angle by combining with a single scattering model, and outputting a pitch angle and an azimuth angle of the polarization camera by a three-dimensional electronic compass; the polarization angle and the position of the polarization camera are input into a sun position resolving module together for processing, a sun azimuth angle and a sun zenith angle are obtained, and then latitude and longitude are output through a latitude and longitude resolving module. Underwater navigation is realized by combining polarized light, and longitude and latitude errors of navigation are respectively 0.17609 degrees and 0.24156 degrees by combining the result of the embodiment, so that a novel underwater navigation method is successfully realized.

The invention discloses an urban green land carbon sink dynamic monitoring method based on multi-source remote sensing data. The method comprises the following steps: acquiring spectral data, a solar azimuth angle and an elevation angle corresponding to the spectral data, meteorological data and vegetation state data; processing the spectral data by using a two-channel convolution model to obtain a vegetation parameter vector; processing the spectral data and the solar azimuth angle and the elevation angle corresponding to the spectral data by using a photosynthetically active radiation dynamic model to obtain photosynthetically active radiation; and according to the meteorological data, the photosynthetically active radiation, the vegetation state data and the vegetation parameter vector, calculating the carbon sink intensity by using a dual-time scale LSTM network. The method is high in calculation timeliness and calculation accuracy.

The invention belongs to the technical field of photovoltaic power generation, and provides a photovoltaic module dip angle and azimuth angle optimization method and system based on hour electricity price, and the method comprises the steps: firstly determining a solar elevation angle and a solar azimuth angle according to a geographic position; determining an incident angle between sunlight and the surface of the photovoltaic module according to the solar elevation angle and the solar azimuth angle; then, according to the incident angle and the irradiation data, the hour effective radiation power of the photovoltaic module under any angle combination is determined, so that the total generation power is obtained; constructing a unit area annual income objective function by using the hour electricity price as a weight; and finally, according to the objective function, determining an optimal combination of the inclination angle and the azimuth angle of the photovoltaic module. Hour-level sun position calculation and incident angle radiation modeling are introduced, and a revenue function is constructed by taking the hour-by-hour electricity price as a weight, so that the optimal combination of the dip angle and the azimuth angle of the photovoltaic module under the optimal economical efficiency is realized.

The invention discloses a fan height measuring method and device based on a high-resolution satellite image shadow. The method comprises the following steps: extracting a fan shadow by using a shadow extraction model based on a high-resolution satellite image containing a fan; the method comprises the following steps of: segmenting and removing a shadow mask of a fan blade by combining solar azimuth information with a straight line-by-line scanning method, and retaining a shadow mask of a fan tower; and calculating the shadow length of the fan tower according to the shadow mask of the fan tower, and calculating the fan height according to the shadow length of the fan tower. According to the invention, the fan height information can be rapidly obtained in a large range, the fan height can be accurately measured and calculated, and manpower and cost can be saved.

The invention relates to the technical field of vehicle control, in particular to a sunlight intensity acquisition method, intelligent equipment, a vehicle and a vehicle-mounted air conditioner, and aims to solve the technical problem of how to acquire effective sunlight intensity based on information such as environment temperature, environment brightness and real-time position when the vehicle cannot acquire the effective sunlight intensity from a sunlight sensor. In order to achieve the purpose, the method comprises the steps of obtaining a relative solar azimuth angle and a relative solar altitude angle based on a real-time position; acquiring a sunlight intensity basic value based on the ambient brightness and the ambient temperature; and correcting the sunlight intensity basic value based on the relative solar azimuth angle, the relative solar altitude angle and the current time. By means of the method, under the condition that the vehicle cost does not need to be increased, the sunlight intensity capable of reflecting the real condition can be obtained according to the real-time position, the environment brightness, the environment temperature and other information, the sunlight intensity is used for automatic control over the vehicle-mounted air conditioner, the control effect of the vehicle-mounted air conditioner can be improved, and the comfort of a driver and passengers can be improved.

The invention discloses a town building planning and designing method and system based on surveying and mapping modeling, and the method comprises the steps: obtaining vector data, a digital elevation model and a digital orthoimage of a planning region, and carrying out the coordinate projection and attribute information preprocessing; performing batch three-dimensional modeling on the vector data by using a CityEngine platform and a CGA rule file to generate a planning three-dimensional model including roads, buildings and greening facilities, and realizing detail iteration through a cascade rule; the planning three-dimensional model and the live-action three-dimensional oblique photography model are fused, and seamless splicing of the models is ensured through local terrain leveling processing and elevation adjustment; performing sunshine analysis based on the fused three-dimensional scene, calculating a solar altitude angle, a solar azimuth angle and a time angle, simulating sunshine time and a shadow area, and optimizing the building layout; and finally, through a three-dimensional line-of-sight analysis algorithm, assessing intervisibility conditions and view fields of the key nodes, generating a view field body model, and adjusting the building layout and density.

The invention relates to a near space low earth orbit satellite and satellite constellation luminosity spectral measurement method, which comprises the following steps: acquiring a low earth orbit satellite and satellite constellation model, and carrying out two-dimensional surface element grid division on the low earth orbit satellite and satellite constellation model; reconstructing a low earth orbit satellite and a satellite constellation model by using the divided surface element data, establishing different satellite and satellite constellation model scenes, and obtaining vector data of the satellite and the satellite constellation changing along with the solar altitude angle and the solar azimuth angle; and calculating the luminosity spectrums of satellites and satellite constellations in different observation scenes according to the vector data in combination with a bidirectional reflection distribution function model and an atmospheric radiation transmission model. The invention aims to improve the precision and stability of observation data, and compared with a space-based observation platform, the deployment and recovery cost of the near space observation platform is lower, and the observation position and angle are easier to adjust. The limitation of foundation observation and space-based observation is overcome, the observation precision and flexibility are improved, and an important means of diversified research is supported.

The invention relates to the technical field of automobile body paint weather resistance testing, in particular to a sunlight self-following reflection system and a control method, and the sunlight self-following reflection system comprises a buried support, a rotation driving mechanism, a rotation platform and a mirror reflection mechanism. The rotary driving mechanism rotates by 360 degrees in a horizontal plane through a driving unit, so that the direction of a vehicle head is always aligned with a solar azimuth angle; the mirror reflection mechanism adjusts the pitching angle of a reflection plate through a micro motor, and it is ensured that sunlight is projected to the surface of a vehicle body with a preset standard irradiance value. The system further comprises an air supply mechanism and an online measuring instrument which are used for cooling, dedusting and tracking the position of the sun in real time. According to the invention, test errors caused by solar altitude changes and regional differences can be eliminated, and the comparability and repeatability of test results are significantly improved.

The present invention belongs to the field of architectural design and discloses a method for calculating a building's solar energy acquisition potential index. The method comprises the following steps: obtaining the solar azimuth and solar altitude corresponding to sunrise and sunset to form a fan-shaped calculation range, and obtaining a plurality of calculation line segments within the fan-shaped calculation range; obtaining the tangent value of the solar altitude at the time corresponding to the calculation line segment, and the ratio of the height of the blocking building to the distance between the blocking building and the building to be measured, and subtracting the tangent value of the solar altitude from the ratio to obtain a difference; obtaining the approximate direct solar irradiance at the time corresponding to the calculation line segment, and assigning the approximate direct solar irradiance as a weight to the difference to obtain a weighted value; obtaining the central angle ratio of the area to be measured, and obtaining the building shielding factor of the building to be measured based on the central angle ratio and the weighted value. The present invention can be used to compare, select, and optimize different building complex layout plans from the perspective of solar energy acquisition potential.

The invention provides an unmanned aerial vehicle path planning method and system based on adaptive dynamic planning. The method comprises the following steps: calculating a solar azimuth angle according to an atmospheric polarization mode, compensating course drift of a visual odometer by using the solar azimuth angle, and generating corrected unmanned aerial vehicle position information; according to the illumination invariant edge information, combining a convolutional neural network, segmenting a key landmark in the texture enhanced image, and generating a semantic navigation landmark point sequence in a constraint space of the key landmark by adopting a bidirectional fast random tree; constructing a model prediction controller according to the semantic navigation road sign point sequence; and through the corrected position information, the flight path of the unmanned aerial vehicle is optimized in a rolling manner through adaptive dynamic planning under the constraint of a dynamic window, and the field angle and exposure parameters of the dual-band imaging unit are adjusted. According to the invention, the autonomous navigation precision and semantic understanding capability of the unmanned aerial vehicle in a complex light environment are improved, and anti-interference and high-precision autonomous path planning and flight control are realized.

The invention belongs to the technical field of photovoltaic power generation, and discloses a distributed roof photovoltaic module maximum generating capacity arrangement method and system, and the method comprises the steps: obtaining the position information and image information of a project location, and carrying out the calculation to obtain a solar altitude angle and a solar azimuth angle; calculating to obtain a shadow union set according to the altitude angle and the azimuth angle of the sun; based on the shadow union set, obtaining an available area of the final arrangeable component; and after the available area is obtained, carrying out optimal position arrangement on the photovoltaic module by taking the maximum generating capacity and the highest coverage rate as targets. According to the distributed roof photovoltaic module maximum generating capacity arrangement method, on the premise that design safety is guaranteed, the photovoltaic module arrangement design period can be greatly shortened, and the land utilization rate and the generating efficiency can be further improved through algorithm optimization.

The application provides a method, device, equipment and medium for reducing image shooting requirements, and relates to the field of computer vision. The method comprises: collecting multi-view images of a scene to be rendered; sampling on a camera ray corresponding to a given pixel point to obtain a sampling point coordinate and a view direction; calculating a hour angle h, an declination δ' and a solar elevation angle θ s , a solar azimuth angle Φ s , obtaining a global light direction vector, and encoding; encoding the shooting time of the image; inputting the sampling point coordinate, the view direction, the light encoding and the time encoding into a neural network to obtain the color and the volume density of the sampling point under the corresponding view; obtaining the final predicted pixel color by using volume rendering, calculating the color loss; and updating the neural network parameters by back propagation. The application can weaken or even eliminate the influence of light changes on outdoor shooting, and reduce the shooting requirements of neural radiance field images.

The present invention discloses a high-precision engineering calculation method and device for the back irradiance of a bifacial photovoltaic module, wherein the calculation method comprises the following steps: (1) inputting relevant parameter information of a photovoltaic power station; (2) simplifying the array into a two-dimensional diagram and calculating the sun position, including the zenith angle and azimuth angle; (3) calculating the ground shadow situation according to the module geometric information and the sun position; (4) calculating the sky viewing factor between rows that can be seen by each ground segment according to the array geometric parameters; calculating the incident angle according to the inclination angle, the module azimuth angle, the solar azimuth angle, and the zenith angle; using the Perez model to decompose the input horizontal direct irradiance and horizontal diffuse irradiance into direct, isotropic diffuse, circumsolar diffuse part, horizon scattering part, and ground reflection part; using the Perez model to calculate the inclined surface diffuse irradiance; (5) calculating the back irradiance after all the above steps are completed. This method simplifies the three-dimensional scene into two dimensions, and simplifies the View Factor method, back shadow analysis, sky view factor algorithm, accurately considers the irradiance received by the ground, and uses the angle-by-angle incidence loss to calculate the irradiance received by the back. It has both high accuracy and high efficiency.

The invention provides a shadow area judgment method and system for a terrain triangular surface. The method comprises the following steps: acquiring terrain elevation point data and longitude and latitude values of a selected land parcel and a solar elevation angle and a solar azimuth angle at the current moment; based on the terrain elevation point data, revit software is used for modeling, and a 3d model of the land parcel is obtained; according to the solar elevation angle and the solar azimuth angle at the current moment, determining the ray emitting direction of each triangular surface in the 3d model along the solar ray direction; and on the basis that each triangular surface emits rays in the ray emitting direction of the solar ray direction, whether the rays emitted by each triangular surface coincide with the 3d model in the three-dimensional rectangular coordinate system or not is judged, and if yes, it is judged that the triangular surface is a shadow area. According to the technical scheme provided by the invention, the shadow area can be simply and quickly determined, and guidance is provided for construction of a photovoltaic power station.

The invention discloses a short-term irradiance prediction method and device based on multi-source data fusion, and the method comprises the following steps: (1) data collection: obtaining meteorological data, actual measurement data of a radiation sensor and astronomical calculation data, and extracting time features; (2) data preprocessing: carrying out ADF unit root test on a global level irradiance sequence; (3) feature selection: screening features having a causal relationship with GHI through Granger causal test; based on XGBoost feature importance analysis, selecting an irradiance historical value and a solar azimuth angle as core input features; (4) model construction and training: processing a multivariable nonlinear relationship by adopting an XGBoost model, and dividing a training set and a test set according to a time sequence; time sequence cross validation is carried out to divide a validation set, and hyper-parameter tuning is carried out through grid search and random search; and (5) evaluation and optimization: using MAE, RMSE and MAPE index evaluation models to visualize a predicted value and actual value time sequence curve. According to the method, a night invalid data screening mechanism, ADF test and Granger causality analysis are introduced to perform feature selection, and time sequence cross validation is combined to perform hyper-parameter adjustment and optimization, so that the irradiance prediction model with high precision and strong generalization ability is realized, and the method is suitable for various photovoltaic application scenes and has wide application prospects. And reliable support is provided for power prediction and power station intelligent scheduling.

A method and a solar panel system (100) are disclosed. Each solar assembly (110) comprises a respective solar panel (200) arranged to rotate, using a hinge assembly (203) connecting to a horizontal rotation axis (HR) of said each solar assembly (110), from a predefined angular position of the solar panel (200) about the horizontal rotation axis (HR) due to wind. The system (100) vertically tracks (A110) the position of the sun by adjusting a tracking azimuth of the solar assembly (110) based on a solar azimuth. The system (100) obtains (A120) a measure of wind in proximity of the solar panel system (100).

The invention discloses a polar axis type solar direct radiation spectrum measurement method and system, belongs to the technical field of solar direct radiation spectrum measurement, and aims to solve the problems that an existing measurement system depends on complex double-axis tracking, has many errors, is high in maintenance cost and is insufficient in latitude adaptability. The system comprises a polar axis rotating reflector and a solar spectrum measurement system, the polar axis rotating reflector directly radiates and reflects the sun with the solar elevation angle of + / -23.5 degrees and the solar azimuth angle of + / -90 degrees to the measurement system, and measurement is achieved in combination with a spectrum reconstruction model. The spectral resolution is superior to 2 nm, the single-point error ranges from-6.83% to 6.61%, the area error ranges from-0.03% to 0.05%, the space-time uniformity is larger than or equal to 99.92%, the structure is simplified, all-year-round all-latitude high-precision measurement without moving tracking is achieved, and the method is suitable for the fields of solar energy development, climate change research and the like.

The invention relates to the technical field of unmanned aerial vehicle remote sensing, in particular to an observation geometric parameter acquisition method and device based on an unmanned aerial vehicle sensor image, and the method can accurately calculate the observation geometric parameter of each observation pixel according to the data during the shooting of the unmanned aerial vehicle sensor image. Comprise a solar zenith angle, a solar azimuth angle, an unmanned aerial vehicle zenith angle, an unmanned aerial vehicle azimuth angle and a relative azimuth angle. According to the technical scheme, the calculation accuracy is high, the result precision of unmanned aerial vehicle image inversion can be improved when the calculation result is substituted into a corresponding model for inversion, and technical support is provided for application of unmanned aerial vehicle remote sensing to crops.

The invention discloses a method for establishing a temperature gradient of a double-layer steel truss girder under solar radiation, which comprises the following steps of: S1, calculating a solar elevation angle alpha s (t) and a solar azimuth angle gamma (t) according to the latitude and longitude of a bridge site, an hour angle and a solar declination; projecting the solar ray vector to the cross section of the main beam according to the included angle xi between the axis of the main beam and the east-west direction to obtain a solar incident angle theta (t) in the cross section; s2, respectively deducing solar radiation areas of an upper-layer bridge floor, a lower-layer bridge floor and web members on the basis of a solar incident angle theta (t) and geometric parameters of the bridge; s3, establishing a temperature field formula related to the solar radiation duration, the air temperature, the material attribute, the surface direction and the coating; s4, temperature gradients of the upper-layer bridge floor, the lower-layer bridge floor and the web members are calculated according to the solar radiation area and a temperature field formula, and the most unfavorable temperature gradient and the corresponding moment are determined; according to the scheme, a reliable temperature working condition basis is provided for temperature effect analysis, stress evaluation and structural design of the double-layer steel truss girder.