Photovoltaic construction management system

Abstract

The invention relates to the related field of photovoltaic construction, in particular to a photovoltaic construction management system, which comprehensively analyzes video data and environmental sensor data, improves the accuracy and reliability of the monitoring effect, and can effectively reduce the blind area and false alarm rate of a single data source through the fusion of multi-modal data. According to the invention, a genetic algorithm and a decision tree algorithm are integrated, so that the system has strong learning ability, and the system can be continuously self-optimized according to historical data and operation logic to gradually adapt to different construction environments and working conditions; through regular updating and model training, the system can continuously improve the monitoring precision and the safety management level, and it is ensured that an efficient and stable operation state is always kept in long-term use; an analysis result is displayed through a visual platform, accurate defect positions and severity degree marks are provided, a detailed detection report can be automatically generated, long-term monitoring and data comparison are supported, and powerful technical support is provided for construction quality guarantee.

Description

Technical Field

[0001] The present invention relates to photovoltaic construction related fields, and in particular to a photovoltaic construction management system. Background Art

[0002] With the rapid development of the modern construction industry, the scale and complexity of construction sites are increasing, and construction safety issues are becoming more and more prominent. Every year, the number of casualties and economic losses caused by safety accidents at construction sites is staggering. Therefore, improving the level of safety monitoring at construction sites has become an urgent need. In recent years, the development of technologies such as artificial intelligence (AI), the Internet of Things (IoT), and big data has provided new solutions and opportunities for intelligent safety monitoring at construction sites.

[0003] Traditional construction site safety monitoring mainly relies on manual inspections and the experience of on-site managers. This method is not only inefficient, but also has a large degree of subjectivity and errors. In a complex construction environment, manual inspections are often difficult to monitor the site in real time and comprehensively. Summary of the invention

[0004] The purpose of the present invention is to provide a photovoltaic construction management system to solve the problems raised in the above background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a photovoltaic construction management system, comprising a data acquisition module, an intelligent planning tool module, a progress tracking module, a quality control module and a safety monitoring module, wherein the data acquisition module uses drones, sensors and GPS devices to collect images and data of the construction site in real time, and monitor weather conditions, equipment status and construction progress;

[0006] The intelligent planning tool module automatically plans the construction sequence and resource allocation based on artificial intelligence algorithms, and optimizes material usage and human resource allocation;

[0007] The progress tracker module dynamically displays the construction progress, updates deviations from the original plan in real time, and provides suggestions for adjustments;

[0008] The quality control module evaluates the construction quality by analyzing the data collected by the data acquisition module, automatically identifies potential quality problems and issues early warnings;

[0009] The safety monitoring module monitors the safety risks at the construction site, automatically detects illegal operations and potential dangers, and notifies management personnel in a timely manner.

[0010] Preferably, the data acquisition module includes a drone unit, a sensor unit and a GPS device unit, and the specific contents are as follows:

[0011] a. Drone unit: The drone is equipped with high-definition cameras and thermal imaging equipment to capture panoramic images and videos of the construction site from the air, providing a comprehensive perspective; the GPS device unit carried by the drone accurately records the geographic coordinates of the shooting location and generates accurate geographic information maps; the data collected by the drone is transmitted in real time to the intelligent planning tool module, progress tracking module and quality control module through wireless communication technology for immediate viewing and analysis by management personnel;

[0012] b. The sensor unit includes environmental sensors, equipment sensors and stress sensors. Environmental sensors include temperature, humidity, wind speed and precipitation sensors, which are used to monitor the environmental conditions of the construction site; equipment sensors include vibration sensors, pressure sensors and current sensors, which are used to monitor the operating status and health of photovoltaic equipment; stress sensors are installed on structural building materials to monitor the stress conditions of buildings and prevent structural risks;

[0013] c. The GPS device unit is used to obtain the precise location information of on-site equipment, materials and personnel in real time to prevent loss or misuse; and to record the movement trajectory of equipment and personnel through location information.

[0014] Preferably, the intelligent planning tool module specifically includes the following steps:

[0015] Step S1, task decomposition: decompose the entire construction project into multiple subtasks, each subtask includes specific construction steps, and automatically generate and optimize the construction sequence and resource allocation plan through genetic algorithms;

[0016] Step S2: According to the construction sequence and resource allocation plan generated in step S1, determine the type and quantity of materials required for each construction stage, and optimize the procurement and transportation of materials; determine the type and quantity of equipment required for each construction stage, and reasonably dispatch equipment to avoid idleness and conflict; reasonably allocate workers according to task requirements and worker skills to ensure efficient use of human resources;

[0017] Step S3: monitor the construction progress in real time, dynamically adjust the construction plan according to the actual situation, and ensure that the project is completed on schedule.

[0018] Preferably, the specific steps of automatically generating and optimizing the construction sequence and resource allocation plan by genetic algorithm in step S1 are as follows:

[0019] Step S11, initial population generation: Generate several initial solutions, i.e., initial plans for the construction plan. These plans can be generated randomly or preliminarily optimized based on historical data and experience;

[0020] Step S12: define a fitness function to evaluate the pros and cons of each solution. The fitness function comprehensively considers construction cost, time, and resource utilization factors. The fitness function formula is as follows:

[0021] [F(x)=w1·\frac{1}{C(x)}+w2·\frac{1}{T(x)}+w3·U(x)]

[0022] Among them, F(x) is the fitness value, C(x) is the total cost of plan x, T(x) is the total duration of plan x, U(x) is the resource utilization rate, w1, w2, w3 are weight parameters used to balance the importance of different factors;

[0023] Step S13, selecting a better solution to enter the next generation according to the fitness value, using a roulette selection method or a tournament selection method strategy;

[0024] Step S14: Combine the selected solutions through crossover operation to generate a new solution. Specifically, two parent solutions are selected for crossover to generate two child solutions:

[0025] [\text{Parent1}=[T1, T2, T3,..., Tn]]

[0026] Represents parent scheme 1, which contains n elements, namely T1, T2, T3, ..., Tn;

[0027] [\text{Parent2}=[T1′, T2′, T3′,..., Tn′]]

[0028] Represents parent scheme 2, which contains n elements, namely T1′, T2′, T3′, ..., Tn′;

[0029] [\text{Child1}=[T1, T1', T3,..., Tn]]

[0030] Represents sub-scheme 1, in which elements of parent scheme 1 and parent scheme 2 are selected alternately

[0031] [\text{Child2}=[T1′,T2,T3′,...,Tn′]]

[0032] Indicates sub-scheme 2, and also alternately selects elements of parent scheme 1 and parent scheme 2;

[0033] Step S15: mutate the crossover scheme and randomly adjust the order of certain tasks or resource allocation to increase the diversity of the population and avoid local optimality;

[0034] Step S16, repeat the above steps, after multiple generations of iterations, continuously optimize the solution until the preset number of iterations is reached or the fitness value meets the requirements.

[0035] Preferably, the progress tracker module includes a dynamic display unit, a deviation warning unit, and an adjustment suggestion unit, the specific contents of which are as follows:

[0036] The dynamic display unit collects various data of the construction site in real time based on the drone unit, sensor unit and GPS device unit collected by the data acquisition module, including the completion status of the construction task, the operation status of the equipment and the location of the personnel; the progress of each construction task is intuitively displayed using Gantt charts, progress bars and bar charts, so that managers can quickly grasp the construction progress;

[0037] The deviation warning unit compares the data collected by the data acquisition module in real time with the preset construction plan, and calculates the deviation between the actual progress and the planned progress. When the deviation exceeds the set value, the system automatically issues a warning notification to remind the management staff to pay attention;

[0038] The adjustment suggestion unit analyzes the causes of deviations and provides suggestions for optimization adjustments based on the actual conditions at the construction site.

[0039] Preferably, the quality control module includes a data analysis unit, an early warning unit and a decision support unit, specifically:

[0040] The data analysis unit uses the following methods for processing and analysis: calculate the mean and variance statistics of the data collected by the data acquisition module to evaluate the overall level of construction quality; use the decision tree model algorithm to predict and evaluate the construction quality and identify potential quality problems; use image processing and AI recognition technology to analyze drone image data and detect construction defects;

[0041] The early warning mechanism of the early warning unit is as follows: the early warning unit continuously monitors various quality indicators and immediately issues an early warning when an indicator exceeds the set threshold; according to the severity of the problem, the early warning is divided into different levels of warning, severe warning, and emergency warning, and the relevant personnel are notified in a timely manner through SMS, email, and App push;

[0042] The decision support unit generates a detailed quality problem analysis report, which includes: a detailed description of the identified quality problems and their causes; providing detailed data and analysis results to support problem identification, and providing specific improvement suggestions and measures based on the analysis results.

[0043] Preferably, the data analysis unit uses a decision tree model algorithm to predict and evaluate the construction quality, and the specific steps for identifying potential quality problems are as follows:

[0044] Step A: The data analysis unit performs data preprocessing on the data collected by the data collection module, including removing noise from the data, processing missing values, correcting erroneous data, and normalizing or standardizing the data;

[0045] Step B, extracting useful feature data from the data preprocessed in step A, and selecting the features that have the greatest impact on the evaluation of construction quality using the principal component analysis (PCA) algorithm, wherein the principal component analysis (PCA) feature selection formula is: [Z=XW], wherein Z is the feature data after dimensionality reduction, X is the useful feature data, and W is the feature vector matrix;

[0046] Step C: Divide the most influential feature data evaluated in step B into a training set and a test set, with 80% used for the training set and 20% used for the test set;

[0047] Step D: Calculate the Gini index of different split points for the feature data in the training set, and select the split point with the smallest Gini index as the split point of the current node. The Gini index calculation formula is: [\text{Gini index}=\frac{n L}{n}\text{Gini}{D L )+\frac{n R}\text{Gini}(D R )], where n L and n R are the number of samples of the left child node and the right child node, n R is the total number of samples of the current node, D L and D R They are the data sets of the left and right child nodes respectively;

[0048] Step E: Use the optimal split point determined in step D to divide the data set into two sub-nodes, and repeat the above process for each sub-node until the stopping condition is met;

[0049] Step F: Use the test set to evaluate the performance of the decision tree model, and then use the trained decision tree model to evaluate the quality of the new data collection module data and identify potential problem points to provide support for quality control.

[0050] Preferably, an electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0051] The processor executes a photovoltaic construction management system as described in any one of claims 1 to 7 by calling a computer program stored in the memory.

[0052] Preferably, a computer program product stored on a computer-readable medium includes a computer-readable program, which, when executed on an electronic device, provides a user input interface to implement a photovoltaic construction management system as described in any one of claims 1-7.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] Real-time monitoring and early warning: This system uses high-resolution cameras and a variety of environmental sensors (such as temperature sensors, smoke sensors, noise sensors, etc.) to achieve 24-hour real-time monitoring of the construction site. Combined with advanced video analysis algorithms, AI recognition algorithms and sensor data fusion technology, the system can detect and identify potential safety hazards and illegal operations in a timely manner. Once a dangerous situation is detected, the system will immediately issue an audible and visual alarm to notify on-site staff, and alert management personnel via SMS or APP to effectively prevent the occurrence of safety accidents.

[0055] Multimodal data fusion: This system conducts comprehensive analysis of video data and environmental sensor data to improve the accuracy and reliability of monitoring results. Through the collaborative processing of different data sources, the system can more comprehensively understand the real-time conditions of the construction site and make more accurate judgments. At the same time, the fusion of multimodal data can also effectively reduce the blind spots and false alarm rates of a single data source.

[0056] Intelligent learning and self-optimization: This system integrates genetic algorithms and decision tree algorithms, giving it a strong learning ability. The system can continuously optimize itself based on historical data and operating logic, and gradually adapt to different construction environments and working conditions. Through regular updates and model training, the system can continuously improve monitoring accuracy and safety management levels, ensuring that it always maintains an efficient and stable operating state during long-term use.

[0057] In summary, the intelligent safety monitoring system for construction sites proposed by the present invention has significant advantages in improving the efficiency, accuracy and real-time performance of safety monitoring, and can effectively protect the safety of personnel and property at the construction site and reduce the probability of accidents. At the same time, its flexible architecture and self-optimization capabilities ensure that the system can operate efficiently in different environments and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is a schematic diagram of the system structure of the present invention;

[0059] Figure 2 It is a schematic diagram of the steps of implementing the intelligent planning tool module of the present invention;

[0060] Figure 3 A flow chart of a decision tree model algorithm method used by a data analysis unit of the present invention;

[0061] Figure 4 The figure is a schematic diagram of the structure of an electronic device. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] Example 1

[0064] See also Figure 1-3 The present invention provides a technical solution: a photovoltaic construction management system, including a data acquisition module, an intelligent planning tool module, a progress tracking module, a quality control module and a safety monitoring module, characterized in that: the data acquisition module uses drones, sensors and GPS devices to collect images and data of the construction site in real time, monitor weather conditions, equipment status and construction progress; the data acquisition module includes a drone unit, a sensor unit and a GPS device unit, and the specific contents are as follows:

[0065] a. Drone unit: The drone is equipped with high-definition cameras and thermal imaging equipment to capture panoramic images and videos of the construction site from the air, providing a comprehensive perspective; the GPS device unit carried by the drone accurately records the geographic coordinates of the shooting location and generates accurate geographic information maps; the data collected by the drone is transmitted in real time to the intelligent planning tool module, progress tracking module and quality control module through wireless communication technology for immediate viewing and analysis by management personnel;

[0066] b. The sensor unit includes environmental sensors, equipment sensors and stress sensors. Environmental sensors include temperature, humidity, wind speed and precipitation sensors, which are used to monitor the environmental conditions of the construction site; equipment sensors include vibration sensors, pressure sensors and current sensors, which are used to monitor the operating status and health of photovoltaic equipment; stress sensors are installed on structural building materials to monitor the stress conditions of buildings and prevent structural risks;

[0067] It should be noted that the types and quantities of sensors included in the sensor unit of the present invention can be increased according to actual usage requirements.

[0068] c. GPS equipment unit is used to obtain the precise location information of on-site equipment, materials and personnel in real time to prevent loss or misuse; the movement trajectory of equipment and personnel is recorded through location information

[0069] The intelligent planning tool module automatically plans the construction sequence and resource allocation based on artificial intelligence algorithms, optimizes material usage and human resource allocation; the intelligent planning tool module specifically includes the following steps:

[0070] Step S1, task decomposition: decompose the entire construction project into multiple subtasks, each subtask includes specific construction steps, and automatically generate and optimize the construction sequence and resource allocation plan through genetic algorithms;

[0071] Step S2: According to the construction sequence and resource allocation plan generated in step S1, determine the type and quantity of materials required for each construction stage, and optimize the procurement and transportation of materials; determine the type and quantity of equipment required for each construction stage, and reasonably dispatch equipment to avoid idleness and conflict; reasonably allocate workers according to task requirements and worker skills to ensure efficient use of human resources;

[0072] Step S3: monitor the construction progress in real time and dynamically adjust the construction plan according to the actual situation to ensure that the project is completed on schedule;

[0073] The specific steps for automatically generating and optimizing the construction sequence and resource allocation plan by genetic algorithm in step S1 are as follows:

[0074] Step S11, initial population generation: Generate several initial solutions, i.e., initial plans for the construction plan. These plans can be generated randomly or preliminarily optimized based on historical data and experience;

[0075] Step S12: define a fitness function to evaluate the pros and cons of each solution. The fitness function comprehensively considers construction cost, time, and resource utilization factors. The fitness function formula is as follows:

[0076] [F(x)=w1·\frac{1}{C(x)}+w2·\frac{1}{T(x)}+w3·U(x)]

[0077] Among them, F(x) is the fitness value, C(x) is the total cost of plan x, T(x) is the total duration of plan x, U(x) is the resource utilization rate, w1, w2, w3 are weight parameters used to balance the importance of different factors;

[0078] Step S13, selecting a better solution to enter the next generation according to the fitness value, using a roulette selection method or a tournament selection method strategy;

[0079] Step S14: Combine the selected solutions through crossover operation to generate a new solution. Specifically, two parent solutions are selected for crossover to generate two child solutions:

[0080] [\text{Parent1}=[T1, T2, T3,..., Tn]]

[0081] Represents parent scheme 1, which contains n elements, namely T1, T2, T3, …, Tn;

[0082] [\text{parent2}=[T1′, T2′, T3′,..., Tn′]]

[0083] Represents parent scheme 2, which contains n elements, namely T1′, T2′, T3′, ..., Tn′;

[0084] [\text{Child1}=[T1, T1′, T3,..., Tn]]

[0085] Represents sub-scheme 1, in which elements of parent scheme 1 and parent scheme 2 are selected alternately

[0086] [\text{Child2}=[T1′, T2, T3′,..., Tn′]]

[0087] Indicates sub-scheme 2, and also alternately selects elements of parent scheme 1 and parent scheme 2;

[0088] Step S15: mutate the crossover scheme and randomly adjust the order of certain tasks or resource allocation to increase the diversity of the population and avoid local optimality;

[0089] Step S16: Repeat the above steps, and continuously optimize the solution after multiple generations of iterations until the preset number of iterations is reached or the fitness value meets the requirements.

[0090] The progress tracker module dynamically displays the construction progress, updates the deviation from the original plan in real time, and provides adjustment suggestions; the progress tracker module includes a dynamic display unit, a deviation warning unit, and an adjustment suggestion unit, and the specific contents are as follows: the dynamic display unit collects various data of the construction site in real time according to the drone unit, sensor unit and GPS device unit collected by the data acquisition module, including the completion status of the construction task, the equipment operation status and the location of the personnel; the progress of each construction task is intuitively displayed using Gantt charts, progress bars, and bar charts, so that management personnel can quickly grasp the construction progress; the deviation warning unit compares the data collected in real time by the data acquisition module with the preset construction plan, calculates the deviation between the actual progress and the planned progress, and when the deviation exceeds the set value, the system automatically issues a warning notification to remind the management personnel to pay attention; the adjustment suggestion unit analyzes the cause of the deviation, and provides optimization and adjustment suggestions based on the actual situation of the construction site;

[0091] The quality control module evaluates the construction quality by analyzing the data collected by the data acquisition module, automatically identifies potential quality problems and issues warnings; the quality control module includes a data analysis unit, an early warning unit and a decision support unit, specifically: the data analysis unit uses the following methods for processing and analysis: calculates the mean and variance statistics of the data collected by the data acquisition module to evaluate the overall level of construction quality; uses a decision tree model algorithm to predict and evaluate the construction quality and identify potential quality problems; uses image processing and AI recognition technology to analyze drone image data and detect construction defects; the early warning mechanism of the early warning unit is as follows: the early warning unit continuously monitors various quality indicators, and immediately issues a warning when an indicator exceeds a set threshold; according to the severity of the problem, different levels of warnings are divided into warnings, serious warnings, and emergency warnings, and timely notify relevant personnel through SMS, email, and App push; the decision support unit generates a detailed quality problem analysis report, which includes: a detailed description of the identified quality problems and their causes; provides detailed data and analysis results to support problem identification, and provides specific improvement suggestions and measures based on the analysis results;

[0092] It should be noted that AI recognition technology is an existing mature technology, which uses a well-trained deep learning model (such as convolutional neural network, CNN) to analyze the pre-processed image data. The AI ​​model can identify various construction defects, such as cracks, detachment, dislocation and surface unevenness. By learning a large amount of annotated data, AI can continuously improve the accuracy and detection rate of recognition, so this invention will not be described in detail.

[0093] The data analysis unit uses a decision tree model algorithm to predict and evaluate construction quality, and the specific steps for identifying potential quality problems are as follows:

[0094] Step A: The data analysis unit performs data preprocessing on the data collected by the data collection module, including removing noise from the data, processing missing values, correcting erroneous data, and normalizing or standardizing the data;

[0095] Step B, extracting useful feature data from the data preprocessed in step A, and selecting the features that have the greatest impact on the evaluation of construction quality using the principal component analysis (PCA) algorithm, wherein the principal component analysis (PCA) feature selection formula is: [Z=XW], wherein Z is the feature data after dimensionality reduction, X is the useful feature data, and W is the feature vector matrix;

[0096] Step C: Divide the most influential feature data evaluated in step B into a training set and a test set, with 80% used for the training set and 20% used for the test set;

[0097] Step D: Calculate the Gini index of different split points for the feature data in the training set, and select the split point with the smallest Gini index as the split point of the current node. The Gini index calculation formula is: [\text{Gini index}=\frac{n L}{n}\text{Gini}{D L )+\frac{n R}\text{Gini}(D R )], where n L and n R are the number of samples of the left child node and the right child node, n R is the total number of samples of the current node, D L and D R They are the data sets of the left and right child nodes respectively;

[0098] Step E: Use the optimal split point determined in step D to divide the data set into two sub-nodes, and repeat the above process for each sub-node until the stopping condition is met;

[0099] Step F: Use the test set to evaluate the performance of the decision tree model, and then use the trained decision tree model to evaluate the quality of the new data collection module data and identify potential problems to provide support for quality control;

[0100] The safety monitoring module monitors the safety risks at the construction site, automatically detects illegal operations and potential dangers, and notifies management personnel in a timely manner.

[0101] Example 2

[0102] An electronic device according to an exemplary embodiment includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0103] The processor executes the above-mentioned photovoltaic construction management system by calling the computer program stored in the memory.

[0104] Figure 4 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (Central Processing Units, CPU) and one or more memories, wherein at least one computer program is stored in the memory, and the at least one computer program is loaded and executed by the processor to implement a photovoltaic construction management system provided in the above-mentioned various method embodiments.

[0105] The electronic device may also include other components for realizing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input / output interface for input and output. The embodiments of the present application will not be described in detail here.

[0106] This embodiment also provides a computer program product stored on a computer-readable medium, including a computer-readable program, which, when executed on an electronic device, provides a user input interface to implement the photovoltaic construction management system.

[0107] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0108] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0109] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A photovoltaic construction management system, comprising a data acquisition module, an intelligent planning tool module, a progress tracking module, a quality control module and a safety monitoring module, characterized in that: The data acquisition module uses drones, sensors and GPS devices to collect images and data from the construction site in real time, monitoring weather conditions, equipment status and construction progress; The intelligent planning tool module automatically plans the construction sequence and resource allocation based on artificial intelligence algorithms, and optimizes material usage and human resource allocation; The progress tracker module dynamically displays the construction progress, updates deviations from the original plan in real time, and provides suggestions for adjustments; The quality control module evaluates the construction quality by analyzing the data collected by the data acquisition module, automatically identifies potential quality problems and issues early warnings; The safety monitoring module monitors the safety risks at the construction site, automatically detects illegal operations and potential dangers, and notifies management personnel in a timely manner.

2. A photovoltaic construction management system according to claim 1, characterized in that: The data acquisition module includes a drone unit, a sensor unit and a GPS device unit, and the specific contents are as follows: a. Drone unit: The drone is equipped with high-definition cameras and thermal imaging equipment to capture panoramic images and videos of the construction site from the air, providing a comprehensive perspective; the GPS device unit carried by the drone accurately records the geographic coordinates of the shooting location and generates accurate geographic information maps; the data collected by the drone is transmitted in real time to the intelligent planning tool module, progress tracking module and quality control module through wireless communication technology for immediate viewing and analysis by management personnel; b. The sensor unit includes environmental sensors, equipment sensors and stress sensors. Environmental sensors include temperature, humidity, wind speed and precipitation sensors, which are used to monitor the environmental conditions of the construction site; equipment sensors include vibration sensors, pressure sensors and current sensors, which are used to monitor the operating status and health of photovoltaic equipment; stress sensors are installed on structural building materials to monitor the stress conditions of buildings and prevent structural risks; c. The GPS device unit is used to obtain the precise location information of on-site equipment, materials and personnel in real time to prevent loss or misuse; and to record the movement trajectory of equipment and personnel through location information.

3. A photovoltaic construction management system according to claim 1, characterized in that: The intelligent planning tool module specifically includes the following steps: Step S1, task decomposition: decompose the entire construction project into multiple subtasks, each subtask includes specific construction steps, and automatically generate and optimize the construction sequence and resource allocation plan through genetic algorithms; Step S2: According to the construction sequence and resource allocation plan generated in step S1, determine the type and quantity of materials required for each construction stage, and optimize the procurement and transportation of materials; determine the type and quantity of equipment required for each construction stage, and reasonably dispatch equipment to avoid idleness and conflict; reasonably allocate workers according to task requirements and worker skills to ensure efficient use of human resources; Step S3: monitor the construction progress in real time, dynamically adjust the construction plan according to the actual situation, and ensure that the project is completed on schedule.

4. A photovoltaic construction management system according to claim 3, characterized in that: In step S1, the specific steps of automatically generating and optimizing the construction sequence and resource allocation plan by using a genetic algorithm are as follows: Step S11, initial population generation: Generate several initial solutions, i.e., initial plans for the construction plan. These plans can be generated randomly or preliminarily optimized based on historical data and experience; Step S12: define a fitness function to evaluate the pros and cons of each solution. The fitness function comprehensively considers construction cost, time, and resource utilization factors. The fitness function formula is as follows: [F(x)=w1·\frac{1}{C(x)}+w2·\frac{1}{T(x)}+w3·U(x)] Among them, F(x) is the fitness value, C(x) is the total cost of plan x, T(x) is the total duration of plan x, U(x) is the resource utilization rate, w1, w2, w3 are weight parameters used to balance the importance of different factors; Step S13, selecting a better solution to enter the next generation according to the fitness value, using a roulette selection method or a tournament selection method strategy; Step S14: Combine the selected solutions through crossover operation to generate a new solution. Specifically, two parent solutions are selected for crossover to generate two child solutions: [\text{Parent1}=[T1,T2,T3,...,Tn]] Represents parent scheme 1, which contains n elements, namely T1, T2, T3, ..., Tn; [\text{Parent2}=[T1′, T2′, T3′,..., Tn′]] Represents parent scheme 2, which contains n elements, namely T1′, T2′, T3′, ..., Tn′; [\text{Child1}=[T1, T1′, T3,..., Tn]] Represents sub-scheme 1, in which elements of parent scheme 1 and parent scheme 2 are selected alternately [\text{Child2}=[T1′, T2, T3′,..., Tn′]] Indicates sub-scheme 2, and also alternately selects elements of parent scheme 1 and parent scheme 2; Step S15: mutate the crossover scheme and randomly adjust the order of certain tasks or resource allocation to increase the diversity of the population and avoid local optimality; Step S16, repeat the above steps, after multiple generations of iterations, continuously optimize the solution until the preset number of iterations is reached or the fitness value meets the requirements.

5. A photovoltaic construction management system according to claim 1, characterized in that: The progress tracker module includes a dynamic display unit, a deviation warning unit, and an adjustment suggestion unit. The specific contents are as follows: The dynamic display unit collects various data of the construction site in real time based on the drone unit, sensor unit and GPS device unit collected by the data acquisition module, including the completion status of the construction task, the operation status of the equipment and the location of the personnel; the progress of each construction task is intuitively displayed using Gantt charts, progress bars and bar charts, so that managers can quickly grasp the construction progress; The deviation warning unit compares the data collected by the data acquisition module in real time with the preset construction plan, and calculates the deviation between the actual progress and the planned progress. When the deviation exceeds the set value, the system automatically issues a warning notification to remind the management staff to pay attention; The adjustment suggestion unit analyzes the causes of deviations and provides suggestions for optimization adjustments based on the actual conditions at the construction site.

6. A photovoltaic construction management system according to claim 1, characterized in that: The quality control module includes a data analysis unit, an early warning unit and a decision support unit, specifically: The data analysis unit uses the following methods for processing and analysis: calculate the mean and variance statistics of the data collected by the data acquisition module to evaluate the overall level of construction quality; use the decision tree model algorithm to predict and evaluate the construction quality and identify potential quality problems; use image processing and AI recognition technology to analyze drone image data and detect construction defects; The early warning mechanism of the early warning unit is as follows: the early warning unit continuously monitors various quality indicators and immediately issues an early warning when an indicator exceeds the set threshold; according to the severity of the problem, the early warning is divided into different levels of warning, severe warning, and emergency warning, and the relevant personnel are notified in a timely manner through SMS, email, and App push; The decision support unit generates a detailed quality problem analysis report, which includes: a detailed description of the identified quality problems and their causes; Provide detailed data and analysis results to support problem identification, and provide specific improvement suggestions and measures based on the analysis results.

7. A photovoltaic construction management system according to claim 6, characterized in that: The data analysis unit uses a decision tree model algorithm to predict and evaluate construction quality. The specific steps for identifying potential quality problems are as follows: Step A: The data analysis unit performs data preprocessing on the data collected by the data collection module, including removing noise from the data, processing missing values, correcting erroneous data, and normalizing or standardizing the data; Step B, extracting useful feature data from the data preprocessed in step A, and selecting the features that have the greatest impact on the evaluation of construction quality using the principal component analysis (PCA) algorithm, wherein the principal component analysis (PCA) feature selection formula is: [Z=XW], wherein Z is the feature data after dimensionality reduction, X is the useful feature data, and W is the feature vector matrix; Step C: Divide the most influential feature data evaluated in step B into a training set and a test set, with 80% used for the training set and 20% used for the test set; Step D: Calculate the Gini index of different split points for the feature data in the training set, and select the split point with the smallest Gini index as the split point of the current node. The Gini index calculation formula is: [\text{Gini index}=\frac{n L }{n}\text{Gini}(D L )+\frac{n R }\text{Gini}(D R )], where n L and n R are the number of samples of the left child node and the right child node, n R is the total number of samples of the current node, D L and D R They are the data sets of the left and right child nodes respectively; Step E: Use the optimal split point determined in step D to divide the data set into two sub-nodes, and repeat the above process for each sub-node until the stopping condition is met; Step F: Use the test set to evaluate the performance of the decision tree model, and then use the trained decision tree model to evaluate the quality of the new data collection module data and identify potential problem points to provide support for quality control.

8. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor executes a photovoltaic construction management system as described in any one of claims 1 to 7 by calling a computer program stored in the memory.

9. A computer program product stored on a computer readable medium, characterized in that: It comprises a computer-readable program, which, when executed on an electronic device, provides a user input interface to implement a photovoltaic construction management system as described in any one of claims 1-7.

Images