Engineering supervision system and method based on machine vision
By using a machine vision-based engineering supervision system that combines multispectral cameras and drone inspections, and employing advanced algorithms for real-time data analysis, the system solves the problems of low efficiency and data lag in traditional engineering supervision, and achieves efficient and real-time quality monitoring and management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-12
- Publication Date
- 2026-03-13
AI Technical Summary
Traditional engineering supervision relies on manual inspections, which are inefficient and susceptible to human factors. It is difficult to acquire and process large amounts of on-site data in real time, resulting in delayed problem detection and inability to take timely corrective measures, which may lead to rework, delays and increased costs.
The system employs a machine vision-based engineering supervision system, which includes data acquisition, processing, and analysis modules. It combines multispectral cameras, high-precision 3D scanners, and drone inspections, and uses convolutional neural networks and multi-scale feature fusion algorithms for real-time data analysis to generate quality inspection reports and issue alarms. It also supports BIM system integration and cloud storage.
It enables real-time and accurate quality monitoring, improves data utilization efficiency and information transmission speed, reduces rework risks, supports long-term quality tracking and problem tracing, and enhances the effectiveness and efficiency of construction management.
Smart Images
Figure CN121661482A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of engineering management technology, specifically to an engineering supervision system and method based on machine vision. Background Technology
[0002] In modern engineering construction, quality monitoring is a crucial link in ensuring the safety, stability, and longevity of projects. Traditional engineering supervision mainly relies on manual inspections and records, which, while capable of identifying quality problems to some extent, has many shortcomings. First, manual inspections are inefficient and susceptible to human factors, leading to omissions or misjudgments, especially in complex and large-scale projects where manual monitoring struggles to comprehensively cover all critical areas. Furthermore, traditional supervision methods cannot acquire and process large amounts of on-site data in real time, resulting in delayed problem detection and an inability to take timely corrective measures, potentially leading to rework, delays, and increased costs.
[0003] With the development of Building Information Modeling (BIM) technology, engineering supervision has been improved to some extent. BIM technology can provide visualization support and data integration for the construction process, but in practical applications, the integration of BIM technology with real-time data from the construction site is still limited, especially in terms of automated detection and real-time feedback, where existing systems lack effective solutions.
[0004] Therefore, those skilled in the art provide an engineering supervision system and method based on machine vision to solve the problems mentioned in the background art. Summary of the Invention
[0005] To address the shortcomings of existing technologies, this invention provides an engineering supervision system and method based on machine vision, which solves the problem of mismatch between building information modeling technology and real-time data.
[0006] To achieve the above objectives, the present invention provides the following technical solution: an engineering supervision system based on machine vision, comprising:
[0007] The data acquisition module is used to capture images and 3D data of concrete surfaces, building material appearances, and construction processes at the construction site in real time.
[0008] The data processing and analysis module is used to process and analyze the raw data provided by the data acquisition module;
[0009] The intelligent alarm and report generation module is used to generate quality inspection reports based on the analysis results provided by the data processing and analysis module, and to issue alarms when an anomaly is detected.
[0010] The system integration and user interface module is used to provide an interactive interface between users and the system, and to view and manage quality inspection data.
[0011] Preferably, the data acquisition module further includes a multispectral camera, a high-precision 3D scanner, and a drone inspection system, wherein the drone inspection system has a built-in range cruise function.
[0012] Preferably, the data processing and analysis module further includes a defect identification algorithm, a material identification and evaluation algorithm, and a process compliance detection algorithm, wherein the defect identification algorithm adopts a convolutional neural network, the material identification and evaluation algorithm adopts a multi-scale feature fusion algorithm, and the process compliance detection algorithm adopts an image registration algorithm.
[0013] Preferably, the calculation steps of the convolutional neural network algorithm are as follows:
[0014] Input layer: The collected concrete surface and building structure are used as input, and the image will be set as height × width × number of channels;
[0015] Convolutional layer: Performs convolution operation on the input image using multiple convolutional kernels to generate local features of edges, textures, and corners in the image;
[0016] Activation layer: The ReLU activation function is used to set all negative values to 0 and retain positive values, thereby introducing non-linear features;
[0017] Pooling layer: The feature map is downsampled through average pooling operation to reduce data dimensionality and computational cost, while retaining the main features;
[0018] Fully connected layer: Flattens the output of the last convolutional layer into a one-dimensional vector and inputs it into one or more fully connected layers;
[0019] Output layer: Passes the output of the fully connected layer to Softmax to generate probability distributions or classification results.
[0020] Preferably, the multi-scale feature fusion algorithm is calculated as follows:
[0021]
[0022] Among them, F i It is the feature map of the i-th layer. This involves upsampling the feature map of the i-th layer to match its resolution with the target resolution. W i F is the weight matrix used for the feature map of the i-th layer, which is used to weight the feature map at each scale. fused It is the fused feature map.
[0023] Preferably, the intelligent alarm and report generation module includes real-time monitoring and early warning, and automatic report generation;
[0024] Real-time monitoring and early warning are used to analyze data in real time. When surface defects, non-conforming materials, or non-compliant processes are detected, an alarm is immediately generated and relevant personnel are notified.
[0025] Automatic report generation is used to automatically generate quality inspection reports, including defect location, severity, material quality assessment, and process compliance inspection results.
[0026] Preferably, the system integration and user interface module further includes;
[0027] BIM integration is used for building information modeling system integration, allowing users to directly view quality inspection results and related alarm information in the BIM model;
[0028] Mobile applications are used to develop mobile applications;
[0029] Data storage and traceability are used to support cloud storage, where all test data and analysis results can be stored for a long time to facilitate long-term quality tracking and problem tracing.
[0030] Preferably, the data acquisition module and the data processing and analysis module are electrically connected, the data processing and analysis module and the intelligent alarm and report generation module are network connected, and the system integration and user interface module is network connected to the data acquisition module, the data processing and analysis module, and the intelligent alarm and report generation module.
[0031] A machine vision-based engineering supervision method, used in a machine vision-based engineering supervision system, includes the following steps:
[0032] Before the project begins, the construction site is first set up, including installing multispectral cameras, setting up high-precision 3D scanners, and arranging the flight path for drone inspections. Then, the project supervision system is activated, and the system begins to capture various data of the construction site in real time, including the concrete surface, the appearance of building materials, and the progress of construction technology.
[0033] During construction, the system continuously collects images and 3D data of the construction site through cameras and drones. Data collection is carried out in real time to ensure that every key link and detail on site is recorded. Drones regularly patrol to obtain data from high-altitude perspectives, covering areas that are difficult for ground equipment to reach.
[0034] Once the collected data enters the system, it is immediately processed and analyzed. The system conducts a detailed inspection of the concrete quality, building material condition, and implementation of construction techniques at the construction site. The system automatically analyzes this data to determine if any problems exist.
[0035] During data processing, if the system detects any non-compliance with standards or construction processes that do not conform to design specifications, the system will immediately trigger an alarm, and the relevant project supervisors will be notified. The alarm will specify the exact location and severity of the problem.
[0036] Based on the collected and analyzed data, the system automatically generates engineering quality reports, including surface defect detection, material evaluation, and process compliance checks. These reports are automatically generated and sent to the engineering management team and other relevant parties within a predetermined time.
[0037] All test results, alarm information, and generated reports are automatically stored in the cloud. As the project progresses, the system continuously accumulates data to form a complete project quality archive. This data can be traced at any time, facilitating quality audits, problem tracing, and long-term trend analysis for managers.
[0038] This invention provides an engineering supervision system and method based on machine vision. It has the following beneficial effects:
[0039] 1. The system integration and user interface module of this invention, through integration with the BIM system, tightly combines complex inspection data with the 3D building model, allowing users to view quality inspection results and alarm information in an intuitive 3D environment. This integration not only improves the accuracy of problem localization but also enables the presentation of complex algorithm analysis results in a more intuitive and understandable way, thereby improving data utilization efficiency. By embedding the algorithm's inspection results into the BIM model, users can directly understand and evaluate quality issues within the context of architectural design, thereby optimizing the decision-making process and reducing the risk of rework.
[0040] 2. The algorithm of this invention continuously processes on-site data in the background and presents the analysis results and alerts instantly on mobile devices, enabling managers to obtain key quality information in real time at the construction site or any remote location. By pushing the complex algorithm analysis results to mobile devices in real time, the system improves the speed of information transmission and the timeliness of response, ensuring that on-site problems can be quickly reported and handled, significantly improving the effectiveness and efficiency of construction management.
[0041] 3. By supporting the persistent storage of large amounts of historical data generated by complex algorithms, this invention provides a solid foundation for long-term quality tracking and problem tracing. Managers can use the algorithm results to analyze long-term quality trends, identify potential problems, prevent recurrence, and feed lessons learned into future projects. This data management approach not only enhances the depth of quality management but also provides crucial support for continuous improvement. Attached Figure Description
[0042] Figure 1 This is a schematic diagram of the engineering supervision system framework of the present invention;
[0043] Figure 2 This is a schematic diagram of the data acquisition module framework of the present invention;
[0044] Figure 3 This is a schematic diagram of the data processing and analysis module framework of the present invention;
[0045] Figure 4 This is a schematic diagram of the framework of the intelligent alarm and report generation module of the present invention;
[0046] Figure 5 This is a schematic diagram of the system integration and user interface framework of the present invention;
[0047] Figure 6 This is a schematic diagram of the method steps of the present invention. Detailed Implementation
[0048] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0049] Example 1:
[0050] Please see the appendix Figure 1 This invention provides an engineering supervision system and method based on machine vision. The data acquisition module and the data processing and analysis module are electrically connected, the data processing and analysis module and the intelligent alarm and report generation module are network connected, and the system integration and user interface module is network connected to the data acquisition module, the data processing and analysis module, and the intelligent alarm and report generation module.
[0051] Specifically, in this project supervision system, the data acquisition module interacts directly with the data processing and analysis module via an electrical connection. This connection ensures that real-time data acquired from the construction site can be transmitted to the data processing and analysis module efficiently and stably, thereby guaranteeing data integrity and accuracy. The electrical connection eliminates potential delays and interference during data transmission, enabling the system to respond promptly to changes on-site and perform real-time analysis. Furthermore, the data processing and analysis module communicates with the intelligent alarm and report generation module via a network connection. This network connection allows processed data and analysis results to be rapidly transmitted to the alarm and report generation module. The network connection not only supports high-speed local data transmission but also enables remote communication via LAN or WAN, ensuring seamless information sharing between system components in different geographical locations, thereby improving the overall responsiveness and synergy of the supervision system.
[0052] The system integration and user interface module is fully integrated through network connectivity and data acquisition modules, data processing and analysis modules, and intelligent alarm and report generation modules. This network connectivity method makes collaboration between system modules more flexible and efficient, and allows the user interface module to access the data and status of all modules within the system at any time. This not only improves the overall connectivity of the system but also enhances the user experience, enabling managers to monitor the construction site in real time, view analysis results, receive alarm information, and generate and manage quality inspection reports. Through this structured network layout, the system can support complex multi-point control and information sharing, while also possessing strong scalability and flexibility to adapt to engineering projects of different sizes and needs, thereby ensuring the comprehensiveness, accuracy, and timeliness of engineering supervision.
[0053] Please see the appendix Figure 2 The data acquisition module is used to capture images and 3D data of concrete surfaces, building material appearances, and construction processes at the construction site in real time; it also includes a multispectral camera, a high-precision 3D scanner, and a drone inspection system, in which the drone inspection system has a built-in range cruise function.
[0054] Specifically, this module integrates a variety of advanced data acquisition devices, including multispectral cameras, high-precision 3D scanners, and drone inspection systems. The multispectral cameras can acquire rich surface information across different spectra, helping to identify subtle differences and potential defects in materials; the high-precision 3D scanner captures three-dimensional structural data on-site, providing precise spatial positioning and geometric information; and the drone inspection system has a built-in range cruise function, covering a wide construction area, especially high-altitude and long-distance scenarios that are difficult for traditional equipment to access. Through the collaborative work of these devices, the data acquisition module can provide detailed and accurate basic data for subsequent data processing and analysis, thereby significantly improving the efficiency and reliability of construction quality monitoring.
[0055] Please see the appendix Figure 3 The data processing and analysis module is used to process and analyze the raw data provided by the data acquisition module; it also includes a defect identification algorithm, a material identification and evaluation algorithm, and a process compliance detection algorithm. The defect identification algorithm uses a convolutional neural network, the material identification and evaluation algorithm uses a multi-scale feature fusion algorithm, and the process compliance detection algorithm uses an image registration algorithm.
[0056] The computation steps of the convolutional neural network algorithm are as follows:
[0057] Input layer: The collected concrete surface and building structure are used as input, and the image will be set as height × width × number of channels;
[0058] Convolutional layer: Performs convolution operation on the input image using multiple convolutional kernels to generate local features of edges, textures, and corners in the image;
[0059] Activation layer: The ReLU activation function is used to set all negative values to 0 and retain positive values, thereby introducing non-linear features;
[0060] Pooling layer: The feature map is downsampled through average pooling operation to reduce data dimensionality and computational cost, while retaining the main features;
[0061] Fully connected layer: Flattens the output of the last convolutional layer into a one-dimensional vector and inputs it into one or more fully connected layers;
[0062] Output layer: Passes the output of the fully connected layer to Softmax to generate probability distributions or classification results.
[0063] The multi-scale feature fusion algorithm is calculated as follows:
[0064]
[0065] Among them, F i It is the feature map of the i-th layer. This involves upsampling the feature map of the i-th layer to match its resolution with the target resolution. W i F is the weight matrix used for the feature map of the i-th layer, which is used to weight the feature map at each scale. fused It is the fused feature map.
[0066] Specifically, firstly, through defect identification algorithms, the system can automatically process and identify potential concrete surface cracks or other non-compliant phenomena in images. This process helps to detect potential quality problems early and prevent them from escalating. Secondly, material identification and evaluation algorithms conduct detailed analysis of the appearance and quality of building materials to ensure that all materials used comply with design and construction specifications. This step is crucial because the quality of materials directly affects the safety and durability of the entire project. Finally, process compliance detection algorithms analyze the execution of construction processes, comparing the actual construction results with design drawings or specification requirements to confirm whether the construction process strictly follows the design requirements.
[0067] The data processing and analysis module provides detailed and accurate analysis results to the intelligent alarm and report generation module through a series of automated analysis steps, ensuring that every step of the construction process is under the system's close monitoring. Through in-depth data analysis, this module not only improves the efficiency of supervision work but also significantly reduces the risk of human error, ensuring that project quality meets expected standards.
[0068] Please see the appendix Figure 4The intelligent alarm and report generation module is used to generate quality inspection reports based on the analysis results provided by the data processing and analysis module, and to issue alarms when an anomaly is detected; including real-time monitoring and early warning, and automatic report generation;
[0069] Real-time monitoring and early warning are used to analyze data in real time. When surface defects, non-conforming materials, or non-compliant processes are detected, an alarm is immediately generated and relevant personnel are notified.
[0070] Automatic report generation is used to automatically generate quality inspection reports, including defect location, severity, material quality assessment, and process compliance inspection results.
[0071] Specifically, in terms of real-time monitoring and early warning, the module continuously analyzes real-time data transmitted from the data processing and analysis module. When the system detects surface defects, substandard materials, or deviations in construction techniques at the construction site, it immediately triggers an alarm. The alarm is not only displayed on the system's user interface but also promptly notifies relevant project supervisors through pre-defined communication channels (such as SMS, email, or mobile application notifications). This immediate response mechanism effectively prevents the spread of problems, ensuring that issues are addressed in their early stages and minimizing the impact on the overall project schedule and quality.
[0072] The automated report generation function is responsible for periodically generating detailed quality inspection reports in the system backend. These reports integrate all detected defects, including their specific location and severity, material quality assessment results, and compliance inspection results of construction processes. Reports are automatically generated at predetermined intervals or after major inspection events and can be exported in various formats for easy review and archiving by management. Through this automated report generation mechanism, project supervisors can obtain accurate and comprehensive quality status summaries, supporting them in making more informed management decisions.
[0073] The intelligent alarm and report generation module ensures that the entire supervision system not only identifies problems but also takes swift and appropriate action upon discovery, providing comprehensive documentation support for subsequent quality management. This significantly improves the efficiency of construction management and the rigor of quality control, ensuring the successful completion of projects to high standards.
[0074] Please see the appendix Figure 5 The system integration and user interface module provides an interactive interface for users to view and manage quality inspection data. It also includes: BIM integration for building information modeling system integration, allowing users to directly view quality inspection results and related alarm information within the BIM model; mobile application for developing mobile applications; and data storage and traceability to support cloud storage, ensuring all inspection data and analysis results are stored for extended periods for long-term quality tracking and problem tracing.
[0075] Specifically, firstly, the module seamlessly integrates with the Building Information Modeling (BIM) system through BIM integration capabilities. Users can directly view quality inspection results and real-time alarm information collected from the site within the BIM model. This integration method tightly links all inspection data with the building model, allowing users to intuitively locate and analyze problem points in a 3D visualization environment. This helps in better understanding inspection results and construction quality status, thereby optimizing the decision-making process.
[0076] Secondly, the mobile application functionality provides users with the ability to access the system anytime, anywhere. Through a specially developed mobile application, project supervisors can view real-time monitoring data, analysis results, and alarm notifications from the construction site on their mobile devices. This mobile solution greatly improves the system's flexibility and responsiveness, especially in on-site management, enabling rapid response and handling of emergencies and ensuring the continuity and effectiveness of construction quality management.
[0077] Furthermore, the system integration and user interface module includes data storage and traceability functions, supporting cloud storage of all testing data and analysis results. This function not only ensures data security and persistence but also allows for easy retrieval of all historical data, supporting long-term quality tracking and problem tracing. Managers can access historical data at any time for review, analyze long-term quality trends, identify the root causes of potential problems, and provide valuable experience and data support for future projects.
[0078] By integrating these functions, the system integration and user interface module effectively improves the operational efficiency and user experience of the entire engineering supervision system. It ensures that users can easily manage and analyze complex quality data, monitor construction progress at any time, and obtain necessary information through various channels, providing solid technical support for achieving high-standard engineering quality management.
[0079] Example 2:
[0080] Please see the appendix Figure 6 This invention provides a machine vision-based engineering supervision method, comprising the following steps:
[0081] Before the project begins, the construction site is first set up, including installing multispectral cameras, setting up high-precision 3D scanners, and arranging the flight path for drone inspections. Then, the project supervision system is activated, and the system begins to capture various data of the construction site in real time, including the concrete surface, the appearance of building materials, and the progress of construction technology.
[0082] During construction, the system continuously collects images and 3D data of the construction site through cameras and drones. Data collection is carried out in real time to ensure that every key link and detail on site is recorded. Drones regularly patrol to obtain data from high-altitude perspectives, covering areas that are difficult for ground equipment to reach.
[0083] Once the collected data enters the system, it is immediately processed and analyzed. The system conducts a detailed inspection of the concrete quality, building material condition, and implementation of construction techniques at the construction site. The system automatically analyzes this data to determine if any problems exist.
[0084] During data processing, if the system detects any non-compliance with standards or construction processes that do not conform to design specifications, the system will immediately trigger an alarm, and the relevant project supervisors will be notified. The alarm will specify the exact location and severity of the problem.
[0085] Based on the collected and analyzed data, the system automatically generates engineering quality reports, including surface defect detection, material evaluation, and process compliance checks. These reports are automatically generated and sent to the engineering management team and other relevant parties within a predetermined time.
[0086] All test results, alarm information, and generated reports are automatically stored in the cloud. As the project progresses, the system continuously accumulates data to form a complete project quality archive. This data can be traced at any time, facilitating quality audits, problem tracing, and long-term trend analysis for managers.
[0087] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.
Claims
1. A machine vision-based engineering supervision system, characterized in that, include: The data acquisition module is used to capture images and 3D data of concrete surfaces, building material appearances, and construction processes at the construction site in real time. The data processing and analysis module is used to process and analyze the raw data provided by the data acquisition module; The intelligent alarm and report generation module is used to generate quality inspection reports based on the analysis results provided by the data processing and analysis module, and to issue alarms when an anomaly is detected. The system integration and user interface module is used to provide an interactive interface between users and the system, and to view and manage quality inspection data.
2. The engineering supervision system based on machine vision according to claim 1, characterized in that, The data acquisition module also includes a multispectral camera, a high-precision 3D scanner, and a drone inspection system, wherein the drone inspection system has a built-in range cruise function.
3. The engineering supervision system based on machine vision according to claim 1, characterized in that, The data processing and analysis module also includes a defect identification algorithm, a material identification and evaluation algorithm, and a process compliance detection algorithm. The defect identification algorithm uses a convolutional neural network, the material identification and evaluation algorithm uses a multi-scale feature fusion algorithm, and the process compliance detection algorithm uses an image registration algorithm.
4. The engineering supervision system based on machine vision according to claim 3, characterized in that, The calculation steps of the convolutional neural network algorithm are as follows: Input layer: The collected concrete surface and building structure are used as input, and the image will be set as height × width × number of channels; Convolutional layer: Performs convolution operation on the input image using multiple convolutional kernels to generate local features of edges, textures, and corners in the image; Activation layer: The ReLU activation function is used to set all negative values to 0 and retain positive values, thereby introducing non-linear features; Pooling layer: The feature map is downsampled through average pooling operation to reduce data dimensionality and computational cost, while retaining the main features; Fully connected layer: Flattens the output of the last convolutional layer into a one-dimensional vector and inputs it into one or more fully connected layers; Output layer: Passes the output of the fully connected layer to Softmax to generate probability distributions or classification results.
5. The machine vision-based engineering supervision system according to claim 3, characterized in that, The multi-scale feature fusion algorithm is calculated as follows: Among them, F i It is the feature map of the i-th layer. This involves upsampling the feature map of the i-th layer to match its resolution with the target resolution. W i F is the weight matrix used for the feature map of the i-th layer, which is used to weight the feature map at each scale. fused It is the fused feature map.
6. The engineering supervision system based on machine vision according to claim 1, characterized in that, The intelligent alarm and report generation module includes real-time monitoring and early warning, and automatic report generation; Real-time monitoring and early warning are used to analyze data in real time. When surface defects, non-conforming materials, or non-compliant processes are detected, an alarm is immediately generated and relevant personnel are notified. Automatic report generation is used to automatically generate quality inspection reports, including defect location, severity, material quality assessment, and process compliance inspection results.
7. The engineering supervision system based on machine vision according to claim 1, characterized in that, The system integration and user interface module also includes; BIM integration is used for building information modeling system integration, allowing users to directly view quality inspection results and related alarm information in the BIM model; Mobile applications are used to develop mobile applications; Data storage and traceability are used to support cloud storage, where all test data and analysis results can be stored for a long time to facilitate long-term quality tracking and problem tracing.
8. The engineering supervision system based on machine vision according to claim 1, characterized in that, The data acquisition module and the data processing and analysis module are electrically connected, the data processing and analysis module and the intelligent alarm and report generation module are network connected, and the system integration and user interface module is network connected to the data acquisition module, the data processing and analysis module, and the intelligent alarm and report generation module.
9. A machine vision-based engineering supervision method, used in the machine vision-based engineering supervision system described in any one of claims 1-8, characterized in that, Includes the following steps: Before the project begins, the construction site is first set up, including installing multispectral cameras, setting up high-precision 3D scanners, and arranging the flight path for drone inspections. Then, the project supervision system is activated, and the system begins to capture various data of the construction site in real time, including the concrete surface, the appearance of building materials, and the progress of construction technology. During construction, the system continuously collects images and 3D data of the construction site through cameras and drones. Data collection is carried out in real time to ensure that every key link and detail on site is recorded. Drones regularly patrol to obtain data from high-altitude perspectives, covering areas that are difficult for ground equipment to reach. Once the collected data enters the system, it is immediately processed and analyzed. The system conducts a detailed inspection of the concrete quality, building material condition, and implementation of construction techniques at the construction site. The system automatically analyzes this data to determine if any problems exist. During data processing, if the system detects any non-compliance with standards or construction processes that do not conform to design specifications, the system will immediately trigger an alarm, and the relevant project supervisors will be notified. The alarm will specify the exact location and severity of the problem. Based on the collected and analyzed data, the system automatically generates engineering quality reports, including surface defect detection, material evaluation, and process compliance checks. These reports are automatically generated and sent to the engineering management team and other relevant parties within a predetermined time. All test results, alarm information, and generated reports are automatically stored in the cloud. As the project progresses, the system continuously accumulates data to form a complete project quality archive. This data can be traced at any time, facilitating quality audits, problem tracing, and long-term trend analysis for managers.