EPC multi-dimensional data co-processing method for photovoltaic installation

Abstract

The invention relates to the technical field of data processing, in particular to a photovoltaic installation-oriented EPC multi-dimensional data co-processing method, which comprises the following steps of: constructing a credibility weighted coordinate error ellipsoid to explicitly quantify space-time uncertainty into an ellipsoid confidence domain; coupling multi-modal coordinate uncertainty and environment disturbance through a geometry-environment credible integrity index, measuring a structure safety margin by using normalized load deviation through a load-progress toughness index, and quantifying a structure risk and a construction progress risk in combination with progress deviation after nonlinear amplification; and the risk is quantified in a unified manner through coupled characteristics, namely time-space-load resonance potential energy, and a single-index controlled evaluation structure is formed, so that decision-making indexes are intuitive.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a multi-dimensional collaborative data processing method for photovoltaic installations in EPC projects. Background Technology

[0002] In distributed photovoltaic EPC projects, GIS data, BIM data, and UAV laser point cloud data need to be aligned with high accuracy before they can guide the on-site positioning of piles and the depth of foundation holes for supports. Frequent sudden rainstorms during the rainy season can soften the ground, affecting the construction progress and requiring real-time adjustments to material delivery plans. When the rainy season causes the slope of the foundation pit to slip, the initial BIM design benchmark becomes invalid and needs to be re-registered. The sudden surge in the amount of calculation data can reduce real-time performance. Terrain deformation and construction disturbances can cause deviations between the actual load and the design load, which can also prolong the on-site decision-making cycle and affect the construction progress.

[0003] Existing solutions either use only UAV point clouds as a baseline and employ ICP iteration to achieve coarse registration with GIS, or deploy benchmark stakes in the site and scan them daily to stitch the day's point cloud onto a fixed benchmark. These existing solutions focus on single-source or static weighting, lacking real-time Bayesian quantization of multimodal errors and failing to form ellipsoidal confidence regions. Furthermore, they cannot dynamically adjust coordinate weights when facing sudden terrain changes during the rainy season, leading to registration drift. Summary of the Invention

[0004] The main objective of this invention is to provide a multi-dimensional data collaborative processing method for EPC (Engineering, Procurement, and Construction) projects oriented towards photovoltaic installations. By constructing a confidence-weighted coordinate error ellipsoid, spatiotemporal uncertainties are explicitly quantified into an ellipsoidal confidence region. The geometric-environmental confidence integrity index couples multimodal coordinate uncertainties with environmental disturbances. The load-schedule resilience index measures structural safety margins using normalized load deviations and combines nonlinearly amplified schedule deviations to quantify structural and construction schedule risks. Furthermore, through the coupling characteristics, i.e., the unified quantification of risks using spatiotemporal-load resonance potential energy, a single-index control evaluation structure is formed, making decision-making indicators intuitive.

[0005] The technical solution of the present invention is as follows: Firstly, a multi-dimensional collaborative data processing method for photovoltaic installation EPC is proposed, which includes the following steps: S1. Synchronously collect real-time 3D point cloud coordinate data, geographic coordinate data of benchmark piles, center coordinate data of BIM components, real-time rainfall intensity data, real-time load data, and real-time actual construction progress data. S2. Based on real-time 3D point cloud coordinate data, geographic coordinate data of benchmark piles, and center coordinate data of BIM components, a three-source database is constructed. The three types of data sources are fused, and the real-time fused mean coordinates are solved by iterative nearest point combined with Gaussian mixture method. The real-time residual set of the three types of data sources relative to the real-time fused mean coordinates is calculated respectively. The real-time residual variance of the three types of data sources is calculated respectively and weights are assigned to the three types of data sources. The real-time fusion uncertainty covariance is further obtained. With the real-time fused mean coordinates as the center and the real-time fusion uncertainty covariance as the scale, a real-time reliability weighted coordinate error ellipsoid is constructed, and the error ellipsoid volume is output. S3. Based on real-time rainfall intensity data and error ellipsoid volume, calculate the geometric-environmental reliability integrity index; based on real-time load data and real-time actual construction progress data, calculate the load-progress resilience index. S4. Based on the geometric-environmental reliability integrity index and the load-schedule resilience index, the spatiotemporal-load resonance potential energy is coupled and calculated. The spatiotemporal-load resonance potential energy is compared with the first characteristic threshold. When the spatiotemporal-load resonance potential energy does not exceed the first characteristic threshold, the current construction progress is maintained. When the spatiotemporal-load resonance potential energy reaches the first characteristic threshold but does not exceed the second characteristic threshold, a mild warning is issued and the material delivery frequency is adjusted. When the spatiotemporal-load resonance potential energy exceeds the second characteristic threshold, a load reassessment is performed and the design reference load is updated.

[0006] Preferably, the real-time three-dimensional point cloud coordinate data in S1 is the real-time three-dimensional point cloud coordinates formed by the UAV lidar based on the construction terrain and the surface of the installed support; the geographic coordinate data of the benchmark pile is the geographic coordinate of the benchmark piles around the foundation pit; the center coordinate data of the BIM component is the center coordinate of the BIM component measured by the total station; the real-time rainfall intensity data is the real-time actual rainfall intensity at the construction site; the real-time load data is the real-time load of the FBG sensor array; and the real-time actual construction progress data is the real-time actual completion rate of the construction progress output by the MES system.

[0007] Preferably, step S2 includes the following specific steps: S21, Based on real-time 3D point cloud coordinate data Geographic coordinate data of benchmark piles BIM component center coordinate data Constructing a three-source database The value of d ranges from 1 to 3; S22. The three types of data sources are fused, and the real-time fused mean coordinates are solved using the iterative nearest point method combined with the Gaussian mixture method. The specific content of solving the real-time fused mean coordinates is: acquiring real-time 3D point cloud coordinate data. The geometric center is used as the initial centroid. The three source databases Centroid of all coordinate points in the current iteration r The sum of squared Euclidean distances between them is used as the loss function, and the updated centroid is obtained by minimizing the loss function. until the centroid of two adjacent iterations. and The iteration stops when the Euclidean distance between them is less than a preset threshold, and the final centroid is output as the real-time fused mean coordinate. t represents a time node; S23. For a single coordinate point in each type of data source, take the difference between the coordinates of that point and the coordinates of the real-time fused mean as the residual vector, and use the set of all residual vectors as the real-time residual set for that type of data source. The real-time residual set of this type of data source The ratio of the sum of squares of the lengths of all residual vectors to the number of coordinate points in that data source is used as the real-time residual variance of that data source. Output the real-time residual variances of the three types of data sources respectively.

[0008] Preferably, S2 further includes: S24. Based on the real-time residual variance of the three data sources, weights are assigned to the three data sources. The formula for calculating the weights is as follows: Further, the real-time fusion uncertainty covariance was obtained. ,in, express The identity matrix; S25, Real-time fusion of mean coordinates Centered on real-time fusion of uncertain covariance Construct a real-time reliability-weighted coordinate error ellipsoid for the scale, and output the error ellipsoid volume. .

[0009] Preferably, the formula for calculating the geometry-environment trustworthiness integrity index in S3 is: ; in, The geometric-environmental credibility integrity index represents the value at time t. The error ellipsoid volume represents the time node t. This represents the confidence ellipsoidal volume threshold for the construction project. This represents the actual rainfall intensity at time point t. Indicates the historical average rainfall intensity. This is an empirical coefficient, with a value ranging from 0.3 to 0.5.

[0010] Preferably, the formula for calculating the load-schedule toughness index in S3 is: ; in, The load-schedule toughness index represents the load-schedule resilience index at time point t. This represents the real-time load of the FBG sensor array at time point t. Indicates the design reference load. This represents the real-time actual completion rate of the construction progress at time node t. This represents the completion rate of the construction schedule at time point t. This is the schedule deviation weight, with a value ranging from 0.5 to 0.8. The non-linear amplification index has a value of 2.

[0011] Preferably, the formula for calculating the spatiotemporal-load resonance potential energy in S4 is: ; in, The spacetime-load resonance potential energy at time node t. The equivalent normalization exponent is 2.

[0012] Secondly, a computer-readable storage medium is proposed, on which a computer program is stored. When the computer program is executed by a processor, it implements the above-mentioned EPC multi-dimensional data collaborative processing method for photovoltaic installation.

[0013] Thirdly, an electronic device is proposed, including a memory for storing instructions and a processor for executing the instructions, causing the device to perform the above-described EPC multi-dimensional data collaborative processing method for photovoltaic installation.

[0014] The technical effects of this invention are as follows: A multi-dimensional data collaborative processing method for EPC photovoltaic installation was constructed. By constructing a confidence-weighted coordinate error ellipsoid, spatiotemporal uncertainty is explicitly quantified into an ellipsoidal confidence region. The geometric-environmental confidence integrity index couples multimodal coordinate uncertainty with environmental disturbances. The load-schedule toughness index measures structural safety margin with normalized load deviation and combines it with nonlinearly amplified schedule deviation to quantify structural risk and construction schedule risk. Furthermore, through the coupling characteristics, i.e., the unified quantification of risk by spatiotemporal-load resonance potential energy, a single-index control evaluation structure is formed, making the decision indicators intuitive. Attached Figure Description

[0015] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a flowchart illustrating the EPC multi-dimensional data collaborative processing method for photovoltaic installation according to Embodiment 1 of the present invention. Detailed Implementation

[0016] Example 1: This example proposes a multi-dimensional data collaborative processing method for EPC (Engineering, Procurement, and Construction) projects oriented towards photovoltaic installations. By constructing a confidence-weighted coordinate error ellipsoid, spatiotemporal uncertainties are explicitly quantified into an ellipsoidal confidence region. The geometric-environmental confidence integrity index couples multimodal coordinate uncertainties with environmental disturbances. The load-schedule resilience index measures structural safety margins using normalized load deviations and combines this with nonlinearly amplified schedule deviations to quantify structural and construction schedule risks. Furthermore, through the coupling characteristics—namely, the unified quantification of risks using spatiotemporal-load resonance potential energy—a single-index control assessment structure makes decision-making indicators intuitive. Specifically, for example... Figure 1 As shown, the EPC multi-dimensional data collaborative processing method for photovoltaic installation proposed in this embodiment includes the following specific steps: S1. Synchronously collect real-time 3D point cloud coordinate data, geographic coordinate data of benchmark piles, center coordinate data of BIM components, real-time rainfall intensity data, real-time load data, and real-time actual construction progress data. In this embodiment, the real-time 3D point cloud coordinate data is the real-time 3D point cloud coordinates formed by the UAV lidar based on the construction terrain and the surface of the installed support; the geographic coordinate data of the benchmark pile is the geographic coordinate of the benchmark piles around the foundation pit; the center coordinate data of the BIM component is the center coordinate of the BIM component measured by the total station; the real-time rainfall intensity data is the real-time actual rainfall intensity at the construction site; the real-time load data is the real-time load of the FBG sensor array; and the real-time actual construction progress data is the real-time actual completion rate of the construction progress output by the MES system.

[0017] S2. Based on real-time 3D point cloud coordinate data, geographic coordinate data of benchmark piles, and center coordinate data of BIM components, a three-source database is constructed. The three types of data sources are fused, and the real-time fused mean coordinates are solved by iterative nearest point combined with Gaussian mixture method. The real-time residual set of the three types of data sources relative to the real-time fused mean coordinates is calculated respectively. The real-time residual variance of the three types of data sources is calculated respectively and weights are assigned to the three types of data sources. The real-time fusion uncertainty covariance is further obtained. With the real-time fused mean coordinates as the center and the real-time fusion uncertainty covariance as the scale, a real-time reliability weighted coordinate error ellipsoid is constructed, and the error ellipsoid volume is output. In this embodiment, S2 includes the following specific steps: S21, Based on real-time 3D point cloud coordinate data Geographic coordinate data of benchmark piles BIM component center coordinate data Constructing a three-source database The value of d ranges from 1 to 3; S22. The three types of data sources are fused, and the real-time fused mean coordinates are solved using the iterative nearest point method combined with the Gaussian mixture method. The specific content of solving the real-time fused mean coordinates is: acquiring real-time 3D point cloud coordinate data. The geometric center is used as the initial centroid. The three source databases Centroid of all coordinate points in the current iteration r The sum of squared Euclidean distances between them is used as the loss function, and the updated centroid is obtained by minimizing the loss function. until the centroid of two adjacent iterations. and The iteration stops when the Euclidean distance between them is less than a preset threshold, and the final centroid is output as the real-time fused mean coordinate. t represents a time node; S23. For a single coordinate point in each type of data source, take the difference between the coordinates of that point and the coordinates of the real-time fused mean as the residual vector, and use the set of all residual vectors as the real-time residual set for that type of data source. The real-time residual set of this type of data source The ratio of the sum of squares of the lengths of all residual vectors to the number of coordinate points in that data source is used as the real-time residual variance of that data source. Output the real-time residual variances for the three types of data sources respectively; S24. Based on the real-time residual variance of the three data sources, weights are assigned to the three data sources. The formula for calculating the weights is as follows: Further, the real-time fusion uncertainty covariance was obtained. ,in, express The identity matrix; S25, Real-time fusion of mean coordinates Centered on real-time fusion of uncertain covariance Construct a real-time reliability-weighted coordinate error ellipsoid for the scale, and output the error ellipsoid volume. .

[0018] S3. Based on real-time rainfall intensity data and error ellipsoid volume, calculate the geometric-environmental reliability integrity index; based on real-time load data and real-time actual construction progress data, calculate the load-progress resilience index. In this embodiment, the formula for calculating the geometry-environment trustworthiness integrity index in S3 is as follows: ; in, The geometric-environmental credibility integrity index represents the value at time t. The error ellipsoid volume represents the time node t. This represents the confidence ellipsoidal volume threshold for the construction project. This represents the actual rainfall intensity at time point t. Indicates the historical average rainfall intensity. This is an empirical coefficient, with a value ranging from 0.3 to 0.5.

[0019] In this embodiment, the formula for calculating the load-schedule toughness index in S3 is: ; in, The load-schedule toughness index represents the load-schedule resilience index at time point t. This represents the real-time load of the FBG sensor array at time point t. Indicates the design reference load. This represents the real-time actual completion rate of the construction progress at time node t. This represents the completion rate of the construction schedule at time point t. This is the schedule deviation weight, with a value ranging from 0.5 to 0.8. The non-linear amplification index has a value of 2.

[0020] S4. Based on the geometric-environmental reliability integrity index and the load-schedule resilience index, the spatiotemporal-load resonance potential energy is coupled and calculated. The spatiotemporal-load resonance potential energy is compared with the first characteristic threshold. When the spatiotemporal-load resonance potential energy does not exceed the first characteristic threshold, the current construction progress is maintained. When the spatiotemporal-load resonance potential energy reaches the first characteristic threshold but does not exceed the second characteristic threshold, a mild warning is issued and the material delivery frequency is adjusted. When the spatiotemporal-load resonance potential energy exceeds the second characteristic threshold, a load reassessment is performed and the design reference load is updated.

[0021] In this embodiment, the formula for calculating the spatiotemporal-load resonance potential energy in S4 is: ; in, The spacetime-load resonance potential energy at time node t. The equivalent normalization exponent is 2.

[0022] The threshold and weight settings can be based on the default settings of this invention, or they can be set by the operator.

[0023] Example 2: This example provides an electronic device, including a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the above-mentioned EPC multi-dimensional data collaborative processing method for photovoltaic installation by calling the computer program stored in the memory.

[0024] The electronic device can vary considerably depending on its configuration or performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the EPC multi-dimensional data collaborative processing method for photovoltaic installations provided in the above-described embodiment. The electronic device may also include other components for implementing its functions; for example, it may have wired or wireless network interfaces and input / output interfaces for data input and output. Further details are omitted in this embodiment.

[0025] Those skilled in the art will recognize that this invention can be implemented as a system, method, or computer program product. Therefore, this disclosure can be embodied in the following forms: it can be entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, the invention can also be implemented as a computer program product contained in one or more computer-readable media, which includes computer-readable program code.

[0026] Any combination of one or more computer-readable media may be used. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0027] This invention is described with reference to flowchart illustrations and block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and block diagrams, as well as combinations of blocks in the flowchart illustrations and block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0028] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and boxes Figure 1 The steps of the function specified in one or more boxes.

[0029] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A multi-dimensional data collaborative processing method for EPC (Engineering, Procurement, and Construction) installations for photovoltaic (PV) projects, characterized by: The specific steps include the following: S1. Synchronously collect real-time 3D point cloud coordinate data, geographic coordinate data of benchmark piles, center coordinate data of BIM components, real-time rainfall intensity data, real-time load data, and real-time actual construction progress data. S2. Based on real-time 3D point cloud coordinate data, geographic coordinate data of benchmark piles, and center coordinate data of BIM components, a three-source database is constructed. The three types of data sources are fused, and the real-time fused mean coordinates are solved by iterative nearest point combined with Gaussian mixture method. The real-time residual set of the three types of data sources relative to the real-time fused mean coordinates is calculated respectively. The real-time residual variance of the three types of data sources is calculated respectively and weights are assigned to the three types of data sources. The real-time fusion uncertainty covariance is further obtained. With the real-time fused mean coordinates as the center and the real-time fusion uncertainty covariance as the scale, a real-time reliability weighted coordinate error ellipsoid is constructed, and the error ellipsoid volume is output. S3. Based on real-time rainfall intensity data and error ellipsoid volume, calculate the geometric-environmental reliability integrity index; based on real-time load data and real-time actual construction progress data, calculate the load-progress resilience index. S4. Based on the geometric-environmental reliability integrity index and the load-schedule resilience index, the spatiotemporal-load resonance potential energy is coupled and calculated. The spatiotemporal-load resonance potential energy is compared with the first characteristic threshold. When the spatiotemporal-load resonance potential energy does not exceed the first characteristic threshold, the current construction progress is maintained. When the spatiotemporal-load resonance potential energy reaches the first characteristic threshold but does not exceed the second characteristic threshold, a mild warning is issued and the material delivery frequency is adjusted. When the spatiotemporal-load resonance potential energy exceeds the second characteristic threshold, a load reassessment is performed and the design reference load is updated.

2. The EPC multi-dimensional data collaborative processing method for photovoltaic installation as described in claim 1, characterized in that: The real-time 3D point cloud coordinate data in S1 is the real-time 3D point cloud coordinates formed by the UAV lidar based on the construction terrain and the surface of the installed support; the geographic coordinate data of the benchmark pile is the geographic coordinate of the benchmark piles around the foundation pit; the center coordinate data of the BIM component is the center coordinate of the BIM component measured by the total station; the real-time rainfall intensity data is the real-time actual rainfall intensity at the construction site; the real-time load data is the real-time load of the FBG sensor array; and the real-time actual construction progress data is the real-time actual completion rate of the construction progress output by the MES system.

3. The EPC multi-dimensional data collaborative processing method for photovoltaic installation as described in claim 2, characterized in that: S2 includes the following specific steps: S21, Based on real-time 3D point cloud coordinate data Geographic coordinate data of benchmark piles BIM component center coordinate data Constructing a three-source database The value of d is 1-3; S22. The three types of data sources are fused, and the real-time fused mean coordinates are solved using the iterative nearest point method combined with the Gaussian mixture method. The specific content of solving the real-time fused mean coordinates is: acquiring real-time 3D point cloud coordinate data. The geometric center is used as the initial centroid. The three source databases Centroid of all coordinate points in the current iteration r The sum of squared Euclidean distances between them is used as the loss function, and the updated centroid is obtained by minimizing the loss function. until the centroid of two adjacent iterations. and The iteration stops when the Euclidean distance between them is less than a preset threshold, and the final centroid is output as the real-time fused mean coordinate. t represents a time node; S23. For a single coordinate point in each type of data source, take the difference between the coordinates of that point and the coordinates of the real-time fused mean as the residual vector, and use the set of all residual vectors as the real-time residual set for that type of data source. The real-time residual set of this type of data source The ratio of the sum of squared lengths of all residual vectors to the number of coordinate points in that data source is used as the real-time residual variance of that data source. Output the real-time residual variances of the three types of data sources respectively.

4. The EPC multi-dimensional data collaborative processing method for photovoltaic installation as described in claim 3, characterized in that: S2 further includes: S24. Based on the real-time residual variance of the three data sources, weights are assigned to the three data sources. The formula for calculating the weights is as follows: Further, the real-time fusion uncertainty covariance was obtained. ,in, express The identity matrix; S25, Real-time fusion of mean coordinates Centered on real-time fusion of uncertain covariance Construct a real-time reliability-weighted coordinate error ellipsoid for the scale, and output the error ellipsoid volume. .

5. The EPC multi-dimensional data collaborative processing method for photovoltaic installation according to claim 4, characterized in that: The formula for calculating the geometry-environment trustworthiness integrity index in S3 is as follows: ； in, The geometric-environmental credibility integrity index represents the value at time t. The error ellipsoid volume represents the time node t. This represents the confidence ellipsoidal volume threshold for the construction project. This represents the actual rainfall intensity at time point t. Indicates the historical average rainfall intensity. This is an empirical coefficient, with a value ranging from 0.3 to 0.

5.

6. The EPC multi-dimensional data collaborative processing method for photovoltaic installation according to claim 5, characterized in that: The formula for calculating the load-schedule toughness index in S3 is as follows: ； in, The load-schedule toughness index represents the load-schedule resilience index at time point t. This represents the real-time load of the FBG sensor array at time point t. Indicates the design reference load. This represents the real-time actual completion rate of the construction progress at time point t. This represents the completion rate of the construction schedule at time point t. This is the schedule deviation weight, with a value ranging from 0.5 to 0.

8. The non-linear amplification index has a value of 2.

7. The EPC multi-dimensional data collaborative processing method for photovoltaic installation as described in claim 6, characterized in that: The formula for calculating the spatiotemporal-load resonance potential energy in S4 is as follows: ； in, The spacetime-load resonance potential energy at time node t. The equivalent normalization exponent is 2.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the EPC multi-dimensional data collaborative processing method for photovoltaic installations as described in any one of claims 1-7.

9. An electronic device, characterized in that, It includes a memory for storing instructions; and a processor for executing the instructions, causing the device to perform the EPC multi-dimensional data collaborative processing method for photovoltaic installation as described in any one of claims 1 to 7.

Images