Stacking planning control system and method for building aluminum formworks

Abstract

The invention relates to the technical field of aluminum formwork stacking planning, in particular to a stacking planning control system and method for building aluminum formworks. The method comprises the following steps: acquiring a multi-angle monitoring image of a building aluminum template to be stacked, performing structural feature point visual identification on the multi-angle monitoring image of the building aluminum template, performing three-dimensional form point cloud modeling, and constructing a three-dimensional structure model of each aluminum template; obtaining a building aluminum template production operation log; physical state feature analysis is carried out based on the building aluminum formwork production operation log, stacking planning constraint rule evolution is carried out, and therefore an aluminum formwork overall stacking planning constraint rule is obtained; and intelligent stacking planning is carried out on each aluminum template three-dimensional structure model based on an aluminum template overall stacking planning constraint rule, optimal stacking planning evaluation is carried out, and an optimal aluminum template stacking planning scheme is extracted. According to the invention, stacking planning control with high space utilization rate and high efficiency is realized.

Description

Technical Field

[0001] The invention relates to the technical field of aluminum formwork stacking planning, and in particular to a stacking planning control system and method for building aluminum formworks. Background Art

[0002] With the continuous development of the construction industry, improving construction efficiency has become a vital part of major engineering projects. In construction, aluminum formwork, as an important building component, has the advantages of light weight, high strength, and reusability, and is widely used in the casting of building structures. The use of aluminum formwork can not only improve the construction quality, but also effectively shorten the construction period and reduce costs. However, the storage, handling and stacking of aluminum formwork has always been a major problem in construction site management. Due to the large size, heavy weight and irregular shape of aluminum formwork, it is often easy to have problems such as low space utilization, unstable stacking, and difficulty in equipment handling during the stacking process.

[0003] At present, the stacking planning of aluminum formwork mainly relies on manual experience. The traditional stacking method is usually randomly arranged according to the actual situation on site, lacking systematic and optimized design. This traditional method has problems such as low stacking efficiency, insufficient space utilization, and much manual intervention, which not only affects the construction efficiency, but also increases the labor intensity and safety risks of operators. With the continuous expansion of the scale of construction projects, the number and types of aluminum formworks are also increasing. How to scientifically and reasonably stack and transport aluminum formworks in a limited space has become an important issue to improve the logistics efficiency, reduce costs and ensure safety of the construction site. In order to solve the various problems existing in the stacking of traditional aluminum formworks, an intelligent stacking planning method for architectural aluminum formworks is urgently needed. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a stacking planning control system and method for building aluminum formwork to solve at least one of the above technical problems.

[0005] To achieve the above object, the present invention provides a method for stacking planning and controlling of building aluminum formwork, comprising the following steps:

[0006] Step S1: obtaining a multi-angle monitoring image of the building aluminum formwork to be stacked, visually identifying the structural feature points of the multi-angle monitoring image of the building aluminum formwork, and performing three-dimensional morphological point cloud modeling to construct a three-dimensional structural model of each aluminum formwork;

[0007] Step S2: Obtain the production and operation log of the building aluminum formwork; perform physical state characteristic analysis based on the production and operation log of the building aluminum formwork, and evolve the stacking planning constraint law, so as to obtain the overall stacking planning constraint law of the aluminum formwork;

[0008] Step S3: Based on the overall stacking planning constraint law of the aluminum formwork, intelligent stacking planning is performed on each aluminum formwork three-dimensional structure model, and the optimal stacking planning evaluation is performed to extract the optimal aluminum formwork stacking planning scheme;

[0009] Step S4: Perform dynamic stacking simulation on each aluminum formwork three-dimensional structure model according to the optimal aluminum formwork stacking planning scheme, and perform dynamic loading and unloading simulation to generate the equipment loading and unloading behavior difficulty value and the aluminum formwork handling path efficiency;

[0010] Step S5: Dynamically adjust the stacking planning according to the difficulty value of equipment loading and unloading behavior and the efficiency of the aluminum template handling path, and build a dynamic stacking planning adjustment strategy;

[0011] Step S6: Perform multi-scenario transfer learning on the dynamic palletizing planning adjustment strategy, fine-tune the adaptive palletizing planning parameters, and build an adaptive aluminum template palletizing planning engine.

[0012] The present invention performs visual recognition of structural feature points and three-dimensional morphological point cloud modeling on multi-angle monitoring images of architectural aluminum templates, accurately obtains the three-dimensional structural information of each aluminum template, and constructs a three-dimensional structural model of each aluminum template, which helps to more accurately consider the shape and size of each aluminum template in the subsequent intelligent stacking planning process, improves the accuracy and efficiency of the planning, and performs physical state feature analysis and stacking planning constraint law evolution based on the architectural aluminum template production operation log, which helps to understand the characteristics and laws in the aluminum template production process, and obtains the overall stacking planning constraint law of the aluminum template, which can provide important constraint conditions and guidance for subsequent intelligent stacking planning, improves the rationality and feasibility of the planning, and performs intelligent stacking planning based on the overall stacking planning constraint law, generates the optimal stacking planning scheme according to the constraint conditions and the aluminum template structure model, and evaluates the optimal stacking planning. It helps to select the best aluminum formwork palletizing solution, improve palletizing efficiency and reduce transportation costs. Through dynamic palletizing simulation and loading and unloading simulation, the actual execution effect of the optimal planning solution is evaluated, including the difficulty of equipment loading and unloading and the efficiency of the transportation path. The generated difficulty value and efficiency data help optimize the planning solution and improve the efficiency and safety of actual operations. Dynamic planning adjustments are made according to the difficulty of equipment loading and unloading and the transportation efficiency. The planning solution is optimized and adjusted according to actual conditions. The construction of a dynamic planning adjustment strategy helps to adapt to changes in the production environment and improve the flexibility and practicality of the planning solution. Through multi-scenario transfer learning and adaptive parameter fine-tuning, an adaptive aluminum formwork palletizing planning engine is constructed to automatically adjust the planning parameters according to different situations. The construction of an adaptive planning engine helps to improve the intelligence level and adaptability of the system and improve planning efficiency and accuracy.

[0013] Preferably, step S1 comprises the following steps:

[0014] Step S11: acquiring a multi-angle monitoring image of the building aluminum formwork to be stacked, globally reconstructing the image details of the multi-angle monitoring image of the building aluminum formwork, and constructing a globally reconstructed optimized image;

[0015] Step S12: performing visual recognition of the three-dimensional structural feature points of the aluminum template on the detail-enhanced multi-angle image, and marking a plurality of structural feature points of the aluminum template;

[0016] Step S13: performing three-dimensional geometric dimension analysis on multiple aluminum template structural feature points to generate three-dimensional geometric features of each aluminum template;

[0017] Step S14: Calculating the radian of the corners of the templates one by one for the structural feature points of the multiple aluminum templates, and extracting the radian value of the corners of each aluminum template;

[0018] Step S15: performing a topological morphological structure analysis on the three-dimensional geometric features of each aluminum template based on the corner radian value of each aluminum template to generate the topological morphological structure features of each aluminum template;

[0019] Step S16: Perform three-dimensional point cloud modeling on the topological morphological structural features of each aluminum template to construct a three-dimensional structural model of each aluminum template.

[0020] The present invention globally reconstructs the image details of the multi-angle monitoring images of the building aluminum formwork to improve the image quality and clarity, which is helpful for subsequent visual analysis and processing. The construction of the globally reconstructed optimized image is helpful to reduce information loss and improve the accuracy of image recognition and analysis. The three-dimensional structural feature points of the aluminum formwork are visually recognized through the detail-enhanced multi-angle images, and the key feature points of the aluminum formwork are marked, which is helpful for subsequent structural analysis and modeling. The marking of the structural feature points of the aluminum formwork is helpful to quickly identify the features and shape of the aluminum formwork, and provide accurate data for subsequent dimensional analysis. The three-dimensional geometric dimension analysis is performed on multiple structural feature points of the aluminum formwork, and the three-dimensional geometric features of each aluminum formwork are generated to provide basic data for modeling and comparison. The three-dimensional geometric feature analysis is helpful to understand the geometric features of the aluminum formwork, including size, shape, etc., and provides for subsequent structural analysis and optimization. Support, calculate and extract the radian of each template corner, obtain the radian value of each aluminum template corner, which is used to describe the curvature and shape characteristics of the edge. The extraction of the radian value of the corner helps to describe the edge characteristics of the aluminum template in more detail, and provide richer data for the subsequent topological morphological structure analysis. Perform topological morphological structure analysis based on the radian value of the aluminum template corner, generate the topological morphological structure characteristics of each aluminum template, and help identify the structural differences between different templates. The topological morphological structure analysis helps to understand the overall morphological structure of the aluminum template, and provides support for subsequent modeling and structural identification. Perform three-dimensional morphological point cloud modeling on the topological morphological structure characteristics of each aluminum template, and construct a three-dimensional structural model of each aluminum template to achieve accurate modeling of the template. The modeling of the three-dimensional structural model helps to visualize the structure of the aluminum template and provide reliable basic data for intelligent stacking planning and control.

[0021] Preferably, the specific steps of step S11 are:

[0022] Calculate the average brightness of the whole image of the multi-angle monitoring image of the building aluminum formwork;

[0023] Detecting the dark image area of ​​the multi-angle monitoring image of the building aluminum formwork based on the average brightness of the whole image;

[0024] Performing local brightness enhancement processing on the dark image area to obtain a brightness enhanced monitoring image;

[0025] Perform edge texture feature analysis on the brightness enhanced monitoring image and extract edge texture features of the aluminum template;

[0026] According to the edge texture features of the aluminum template, non-local mean filter optimization is performed to generate mean filter optimized edge texture features;

[0027] Extract edge texture area in the image based on edge texture features of aluminum template;

[0028] Performing super-resolution detail enhancement on the edge texture region in the image to generate a super-resolution enhanced edge texture region;

[0029] Based on super-resolution enhancement of edge texture areas and mean filtering to optimize edge texture features, the image details of the brightness enhanced monitoring image are globally reconstructed to construct a globally reconstructed optimized image.

[0030] The present invention obtains the brightness level of the overall image by calculating the average brightness of the whole image, which is helpful for subsequent dark area detection and brightness enhancement processing. The dark image area is detected based on the average brightness of the whole image, which is helpful for accurately locating the shadow or low brightness area in the aluminum template image, providing a target area for subsequent processing, and performing local brightness enhancement processing on the dark image area to improve the visualization effect inside the area, enhance the clarity of details and contours, and help extract more accurate feature information. By performing edge texture feature analysis on the brightness enhanced monitoring image, the texture information of the edge of the aluminum template is extracted, which is helpful for distinguishing the edge features of different parts. According to the edge texture features of the aluminum template, the edge texture information of the aluminum template is extracted. Non-local mean filtering optimization of the features helps to smooth the texture information in the image, reduce noise and improve the clarity of edge features. The edge texture area in the image is extracted based on the edge texture features of the aluminum template, which helps to accurately locate the edge contour of the aluminum template and provide a basis for subsequent analysis and processing. Super-resolution detail enhancement is performed on the edge texture area to improve the clarity and detail display of the image, and the expressiveness of the edge texture features is enhanced. Based on the super-resolution enhanced edge texture area and mean filtering to optimize the texture features, the image details are globally reconstructed for the brightness enhanced monitoring image, which improves the image quality and detail expression, and provides more accurate data for subsequent analysis and modeling.

[0031] Preferably, the specific steps of step S2 are:

[0032] Step S21: Obtaining the production operation log of the building aluminum formwork;

[0033] Step S22: extracting all aluminum formwork parameter information based on the architectural aluminum formwork production operation log; performing physical state characteristic analysis on all aluminum formwork parameter information to generate physical state characteristics of each aluminum formwork;

[0034] Step S23: Perform environmental storage space analysis on the production operation log of the building aluminum formwork to obtain production environment storage space data;

[0035] Step S24: quantifying the equipment lifting capacity of the building aluminum formwork production operation log to generate the equipment lifting capacity value;

[0036] Step S25: performing stacking stability requirement analysis on each aluminum template three-dimensional structure model according to the physical state characteristics of each aluminum template, thereby generating overall stacking stability requirement data;

[0037] Step S26: Based on the production environment storage space data and the equipment lifting capacity value, the overall stacking stability demand data is subjected to stacking planning constraint law evolution, thereby obtaining the overall stacking planning constraint law of the aluminum formwork.

[0038] The present invention obtains the production and operation log of the building aluminum formwork, records the key information and events in the production process, provides basic data for subsequent data analysis and planning, extracts all aluminum formwork parameter information and performs physical state feature analysis, helps to understand the characteristics and state of each aluminum formwork, provides a basis for subsequent planning and analysis, generates physical state features to help identify the characteristics of the aluminum formwork, so as to better perform stacking stability demand analysis, and obtains space data on storage and stacking by analyzing the storage space of the production environment, provides space restrictions and information for stacking planning, helps to optimize storage space utilization, ensures space efficiency and safety during the stacking process, and quantifies the lifting capacity value of the equipment to help determine the maximum load-bearing capacity of the equipment. It provides important physical constraints for palletizing planning, ensuring that the actual capacity of the equipment is taken into account during the palletizing process to avoid overloading and safety issues. It analyzes the stacking stability requirements based on the physical state characteristics of the aluminum template, which helps to determine the stability requirements of each aluminum template during the stacking process, providing a basis for safe palletizing, ensuring that the stability and stacking requirements of the aluminum template are taken into account during the palletizing process to avoid collapse and damage. By evolving the palletizing planning constraint laws for the overall stacking stability demand data, it formulates planning constraints suitable for the production environment and equipment capabilities, improves palletizing efficiency and safety, and helps to comprehensively consider the production environment, equipment capabilities and aluminum template characteristics, and generate overall palletizing planning constraint laws to achieve efficient and intelligent palletizing control.

[0039] Preferably, the specific steps of step S22 are:

[0040] Extract the weight, structural strength and material characteristics of each aluminum formwork based on all aluminum formwork parameter information;

[0041] Perform stability requirement analysis on the weight and structural strength to generate stability requirement data for the aluminum formwork;

[0042] Calculate the surface fragility of the material characteristics to generate the surface fragility of each aluminum template;

[0043] Extract the order of using aluminum formwork according to the production and operation log of architectural aluminum formwork;

[0044] Calculating the stacking position priority of the access sequence to obtain the stacking position priority of each aluminum template;

[0045] The physical state characteristics of each aluminum template are evaluated on the surface fragility, aluminum template stability requirement data and the stacking position priority of each aluminum template to generate the physical state characteristics of each aluminum template.

[0046] The present invention extracts the weight, structural strength and material characteristics from the aluminum template parameter information to fully understand the physical properties of each aluminum template. This information is crucial for the subsequent stability requirement analysis, vulnerability calculation and stacking position priority calculation. The weight and structural strength of the aluminum template are analyzed to determine the stability requirements to ensure the safety and stability of the aluminum template during the stacking process. The generation of stability requirement data is helpful to formulate a reasonable stacking planning strategy to avoid tilting or collapse problems during aluminum template stacking. The surface vulnerability of the aluminum template is calculated to evaluate the wear resistance and vulnerability of each aluminum template surface to avoid surface damage during the stacking process. These data are helpful to design appropriate protection measures and stacking methods to ensure the appearance quality of the aluminum template. The quantity and service life of the aluminum formwork are determined by extracting the order of aluminum formwork use through the production and operation log of the building aluminum formwork, and understanding the usage history and order of each aluminum formwork. The order of use information is very important for determining the stacking position priority and the physical state characteristic evaluation. The stacking position priority of each aluminum formwork is calculated to determine the optimal stacking position according to the order of use and physical characteristics, thereby improving stacking efficiency and convenience. Priority calculation helps to reasonably plan the stacking layout, reduce handling time and improve work efficiency. Through a comprehensive evaluation of surface fragility, stability requirements and stacking position priority, the physical state characteristics of each aluminum formwork are generated. The physical state characteristic evaluation helps to formulate an intelligent stacking planning control strategy to ensure the safe stacking and effective use of aluminum formwork.

[0047] Preferably, step S3 specifically comprises the following steps:

[0048] Step S31: coding and marking each aluminum template three-dimensional structure model to generate a coded aluminum template structure model;

[0049] Step S32: performing intelligent stacking planning on the coded aluminum template structure model based on the overall stacking planning constraint law of the aluminum template, thereby generating multiple initial aluminum template stacking planning schemes;

[0050] Step S33: Calculating the space utilization rate of each of the multiple initial aluminum template stacking planning schemes to obtain the stacking space utilization rate of each scheme;

[0051] Step S34: performing a global stability assessment of the aluminum formwork for a plurality of initial aluminum formwork stacking planning schemes to generate aluminum formwork stability data for each scheme;

[0052] Step S35: Based on the stacking space utilization rate of each plan and the aluminum template stability data of each plan, the optimal stacking planning evaluation is performed to extract the optimal aluminum template stacking planning plan.

[0053] The present invention realizes the digital representation of the aluminum template structure by coding and marking each aluminum template three-dimensional structure model, which is convenient for subsequent algorithm processing and analysis. The generation of the coded aluminum template structure model is helpful to accurately describe the shape and characteristics of each aluminum template, and provides a data basis for intelligent stacking planning. Based on the overall stacking planning constraint law of the aluminum template, intelligent stacking planning is performed to generate multiple initial schemes, which improves the diversity and flexibility of planning. The generation of multiple initial schemes is helpful to explore different stacking layouts and provide more choices for optimal planning. The space utilization efficiency of each scheme is evaluated by calculating the space utilization rate of each scheme, which helps to select the optimal stacking layout. The stacking density of the aluminum template is optimized by calculating the space utilization rate, and the space utilization efficiency of the warehouse is improved. The global stability evaluation of the aluminum template is performed on multiple initial schemes to evaluate the stability and safety of each scheme. The generation of aluminum template stability data is helpful to eliminate unstable schemes and ensure the safe stacking of the aluminum template during the stacking process. The optimal stacking planning evaluation is performed in combination with the stacking space utilization rate and the aluminum template stability data to find the most suitable scheme. Extracting the optimal aluminum template stacking planning scheme is helpful to achieve efficient stacking layout and improve warehouse space utilization rate and work efficiency.

[0054] Preferably, the specific steps of step S4 are:

[0055] Step S41: performing dynamic stacking simulation on each aluminum template three-dimensional structure model according to the optimal aluminum template stacking planning scheme, thereby constructing an aluminum template stacking planning model;

[0056] Step S42: performing dynamic loading and unloading simulation on the aluminum template stacking planning model to generate dynamic loading and unloading simulation response data of the aluminum template;

[0057] Step S43: performing equipment loading and unloading movement trajectory evolution on the aluminum template dynamic loading and unloading simulation response data, and extracting the equipment loading and unloading movement trajectory;

[0058] Step S44: analyzing the equipment loading and unloading action sequence of the aluminum formwork dynamic loading and unloading simulation response data, and extracting multiple-stage loading and unloading action sequences;

[0059] Step S45: perform loading and unloading behavior difficulty assessment on multiple stage loading and unloading action sequences to generate equipment loading and unloading behavior difficulty values; calculate the handling path efficiency of the equipment loading and unloading movement trajectory to obtain the aluminum formwork handling path efficiency.

[0060] The present invention simulates the actual stacking process of the optimal aluminum template stacking planning scheme through dynamic stacking simulation, verifies the feasibility of the planning scheme, and constructs an aluminum template stacking planning model, which is helpful to optimize the stacking layout, improve stacking efficiency, and reduce errors and damages. The dynamic loading and unloading simulation simulates the loading and unloading process of the aluminum template, generates loading and unloading simulation response data, and helps to evaluate the efficiency and safety of the operation process. The generated response data is helpful to identify potential problems and optimize the loading and unloading process, improve production efficiency and reduce risks. The loading and unloading simulation response data is subjected to the evolution of the equipment loading and unloading movement trajectory to display the movement path of the equipment during the operation, which helps to optimize equipment scheduling and path planning. The extraction of equipment movement trajectory helps to improve the loading and unloading operation process and reduce unnecessary movement and time waste. The dynamic loading and unloading simulation response data is subjected to action sequence analysis to extract loading and unloading action sequences of multiple stages, which helps to understand the operation process and optimization steps. The analysis of action sequences helps to identify bottlenecks and improvement points in the operation, improve operation efficiency and reduce loading and unloading time. The difficulty assessment of the multi-stage loading and unloading action sequence helps to evaluate the complexity of the operation, guide training and improve the operation process. The calculation of the handling path efficiency helps to optimize the path planning, reduce unnecessary movement and improve the handling efficiency.

[0061] Preferably, the specific steps of step S5 are:

[0062] Step S51: dynamically optimizing the loading and unloading path of the equipment based on the aluminum template handling path efficiency, thereby generating an optimized loading and unloading path;

[0063] Step S52: adjusting the stacking position of the aluminum template based on the equipment loading and unloading behavior difficulty value, thereby generating stacking position adjustment data;

[0064] Step S53: dynamically adjust the optimal aluminum template stacking planning scheme according to the loading and unloading optimization path and the stacking position adjustment data, and construct a dynamic stacking planning adjustment strategy.

[0065] The present invention improves the moving efficiency of the equipment and reduces the idling time, thereby reducing the production cost by optimizing the loading and unloading path based on the efficiency of the aluminum template handling path; generating the loading and unloading optimization path helps to optimize the path planning of the equipment, improve the loading and unloading efficiency, reduce energy consumption and equipment wear; adjusting the stacking position based on the difficulty value of the equipment loading and unloading behavior optimizes the stacking layout, thereby improving the operator's work efficiency and reducing operating errors; generating stacking position adjustment data helps to adjust the stacking position of the aluminum template, reduce repeated movements during loading and unloading and improve the smoothness of operation; performing dynamic stacking planning adjustment according to the loading and unloading optimization path and the stacking position adjustment data realizes real-time stacking planning optimization, adapts to changes in the production environment, and constructs a dynamic stacking planning adjustment strategy that helps to quickly respond to changes in production demand and improves production flexibility and adaptability.

[0066] Preferably, the specific steps of step S6 are:

[0067] Step S61: Acquire multiple preset storage scenes;

[0068] Step S62: Analyze the scene operation change characteristics of multiple preset storage scenes to generate each storage scene operation characteristic;

[0069] Step S63: performing multi-scenario transfer learning on the dynamic palletizing planning adjustment strategy according to the operation characteristics of each storage scenario, thereby obtaining multi-scenario palletizing planning parameters;

[0070] Step S64: fine-tune the adaptive palletizing planning parameters based on the multi-scenario palletizing planning parameters, and build an adaptive aluminum template palletizing planning engine.

[0071] The present invention provides a variety of working environment conditions through multiple preset warehousing scenarios, which is conducive to the comprehensive training and testing of the model, enhances the adaptability and robustness of the system, and analyzes the scene operation change characteristics of multiple warehousing scenarios to identify the operation characteristics in different scenarios, so as to provide a basis for subsequent planning and parameter adjustment. Generating the operation characteristics of each warehousing scenario is helpful to understand the demand differences in different scenarios, and provide support for intelligent planning and decision-making. Multi-scenario transfer learning is performed according to the operation characteristics of each warehousing scenario to transfer the knowledge and experience in different scenarios, so as to improve the adaptability and generalization ability of the system in new scenarios. Obtaining multi-scenario palletizing planning parameters is helpful to establish a more intelligent and flexible planning system, which is suitable for diversified production scenarios. Adaptive planning parameter fine-tuning is performed based on the multi-scenario palletizing planning parameters to adjust and optimize the system according to actual production needs and scene changes, so as to improve the adaptability and performance of the system. Constructing an adaptive aluminum template palletizing planning engine is helpful to realize automatic optimization and adjustment of the planning process, and improve planning efficiency and accuracy.

[0072] In this specification, a palletizing planning and control system for building aluminum formwork is provided, which is used to execute the palletizing planning and control method for building aluminum formwork as described above, including:

[0073] A three-dimensional structure module is used to obtain multi-angle monitoring images of the building aluminum formwork to be stacked, perform visual recognition of structural feature points on the multi-angle monitoring images of the building aluminum formwork, perform three-dimensional morphological point cloud modeling, and construct a three-dimensional structural model of each aluminum formwork;

[0074] The stacking constraint module is used to obtain the production and operation log of the building aluminum formwork; based on the production and operation log of the building aluminum formwork, the physical state characteristics are analyzed, and the stacking planning constraint law is evolved, so as to obtain the overall stacking planning constraint law of the aluminum formwork;

[0075] Intelligent stacking planning module, which is used to perform intelligent stacking planning for each aluminum formwork three-dimensional structure model based on the overall stacking planning constraint rules of the aluminum formwork, and to evaluate the optimal stacking planning and extract the optimal aluminum formwork stacking planning scheme;

[0076] Dynamic loading and unloading simulation module, used to perform dynamic stacking simulation on each aluminum formwork three-dimensional structure model according to the optimal aluminum formwork stacking planning scheme, and perform dynamic loading and unloading simulation to generate the equipment loading and unloading behavior difficulty value and aluminum formwork handling path efficiency;

[0077] Dynamic palletizing adjustment module, which is used to adjust the dynamic palletizing planning according to the difficulty value of equipment loading and unloading behavior and the efficiency of aluminum template handling path, and build a dynamic palletizing planning adjustment strategy;

[0078] The multi-scenario migration module is used to conduct multi-scenario migration learning of dynamic palletizing planning adjustment strategies, fine-tune adaptive palletizing planning parameters, and build an adaptive aluminum template palletizing planning engine.

[0079] The present invention acquires multi-angle monitoring images, visually identifies structural feature points, and models three-dimensional morphological point clouds, accurately acquires the three-dimensional structural information of each aluminum template, provides accurate basic data for subsequent palletizing planning, performs physical state feature analysis and evolution of palletizing planning constraint laws based on production operation logs, extracts the palletizing planning constraint laws of the entire aluminum template, helps constrain and optimize the planning process, performs intelligent palletizing planning on the three-dimensional structural model of each aluminum template according to the palletizing planning constraint laws, can achieve optimal palletizing planning for each aluminum template, improves palletizing efficiency and accuracy, evaluates the actual effect of the optimal palletizing planning scheme through dynamic palletizing simulation and loading and unloading simulation, extracts the difficulty value of equipment loading and unloading behavior and the efficiency of the handling path, helps optimize the planning scheme, performs dynamic palletizing planning adjustment according to the difficulty value of equipment loading and unloading behavior and the efficiency of the handling path, constructs a dynamic palletizing planning adjustment strategy, realizes real-time optimization of palletizing planning, and improves production efficiency, constructs an adaptive palletizing planning engine through multi-scenario transfer learning and adaptive palletizing planning parameter fine-tuning, and the system automatically adjusts planning parameters in different scenarios to improve adaptability and intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Figure 1 A schematic flow chart of the steps of a stacking planning and control method for building aluminum formwork according to the present invention;

[0081] Figure 2 Detailed implementation flow chart of step S1;

[0082] Figure 3 Detailed implementation flow chart of step S2;

[0083] Figure 4Detailed implementation flow chart of step S3. DETAILED DESCRIPTION

[0084] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0085] The example of the present application provides a stacking planning control system and method for architectural aluminum formwork. The execution subjects of the system and method include but are not limited to: mechanical equipment, data processing platform, cloud server nodes, network uploading equipment, etc. equipped with the system, which can be regarded as general computing nodes of the present application. The data processing platform includes but is not limited to: at least one of an audio and image management system, an information management system, and a cloud data management system.

[0086] See also Figures 1 to 4 The present invention provides a stacking planning and control method for building aluminum formwork, and the stacking planning and control method for building aluminum formwork comprises the following steps:

[0087] Step S1: obtaining a multi-angle monitoring image of the building aluminum formwork to be stacked, visually identifying the structural feature points of the multi-angle monitoring image of the building aluminum formwork, and performing three-dimensional morphological point cloud modeling to construct a three-dimensional structural model of each aluminum formwork;

[0088] Step S2: Obtain the production and operation log of the building aluminum formwork; perform physical state characteristic analysis based on the production and operation log of the building aluminum formwork, and evolve the stacking planning constraint law, so as to obtain the overall stacking planning constraint law of the aluminum formwork;

[0089] Step S3: Based on the overall stacking planning constraint law of the aluminum formwork, intelligent stacking planning is performed on each aluminum formwork three-dimensional structure model, and the optimal stacking planning evaluation is performed to extract the optimal aluminum formwork stacking planning scheme;

[0090] Step S4: Perform dynamic stacking simulation on each aluminum formwork three-dimensional structure model according to the optimal aluminum formwork stacking planning scheme, and perform dynamic loading and unloading simulation to generate the equipment loading and unloading behavior difficulty value and the aluminum formwork handling path efficiency;

[0091] Step S5: Dynamically adjust the stacking planning according to the difficulty value of equipment loading and unloading behavior and the efficiency of the aluminum template handling path, and build a dynamic stacking planning adjustment strategy;

[0092] Step S6: Perform multi-scenario transfer learning on the dynamic palletizing planning adjustment strategy, fine-tune the adaptive palletizing planning parameters, and build an adaptive aluminum template palletizing planning engine.

[0093] The present invention performs visual recognition of structural feature points and three-dimensional morphological point cloud modeling on multi-angle monitoring images of architectural aluminum templates, accurately obtains the three-dimensional structural information of each aluminum template, and constructs a three-dimensional structural model of each aluminum template, which helps to more accurately consider the shape and size of each aluminum template in the subsequent intelligent stacking planning process, improves the accuracy and efficiency of the planning, and performs physical state feature analysis and stacking planning constraint law evolution based on the architectural aluminum template production operation log, which helps to understand the characteristics and laws in the aluminum template production process, and obtains the overall stacking planning constraint law of the aluminum template, which can provide important constraint conditions and guidance for subsequent intelligent stacking planning, improves the rationality and feasibility of the planning, and performs intelligent stacking planning based on the overall stacking planning constraint law, generates the optimal stacking planning scheme according to the constraint conditions and the aluminum template structure model, and evaluates the optimal stacking planning. It helps to select the best aluminum formwork palletizing solution, improve palletizing efficiency and reduce transportation costs. Through dynamic palletizing simulation and loading and unloading simulation, the actual execution effect of the optimal planning solution is evaluated, including the difficulty of equipment loading and unloading and the efficiency of the transportation path. The generated difficulty value and efficiency data help optimize the planning solution and improve the efficiency and safety of actual operations. Dynamic planning adjustments are made according to the difficulty of equipment loading and unloading and the transportation efficiency. The planning solution is optimized and adjusted according to actual conditions. The construction of a dynamic planning adjustment strategy helps to adapt to changes in the production environment and improve the flexibility and practicality of the planning solution. Through multi-scenario transfer learning and adaptive parameter fine-tuning, an adaptive aluminum formwork palletizing planning engine is constructed to automatically adjust the planning parameters according to different situations. The construction of an adaptive planning engine helps to improve the intelligence level and adaptability of the system and improve planning efficiency and accuracy.

[0094] In the embodiment of the present invention, refer to Figure 1 , is a schematic flow chart of the steps of a stacking planning and control method for a building aluminum formwork according to the present invention. In this example, the steps of the method include:

[0095] Step S1: obtaining a multi-angle monitoring image of the building aluminum formwork to be stacked, visually identifying the structural feature points of the multi-angle monitoring image of the building aluminum formwork, and performing three-dimensional morphological point cloud modeling to construct a three-dimensional structural model of each aluminum formwork;

[0096] In this embodiment, the shooting position and angle of the aluminum template are determined to ensure that all important viewing angles, such as the front, side, and top, are covered. A high-resolution camera is used for shooting to ensure image quality for subsequent analysis. Multi-angle shooting is implemented. It is recommended to shoot at least 10-15 images at different angles for each template to improve modeling accuracy. Shooting is ensured under uniform lighting conditions to avoid the effects of shadows and reflections on image quality. The collected images are preprocessed, including denoising, contrast enhancement, and brightness adjustment, to improve the accuracy of feature point recognition. An image processing library (such as OpenCV) is used to implement the preprocessing function. A feature point detection algorithm (such as SIFT, SURF, or ORB) is applied to process each image to identify key structural feature points, which are usually edges, corners, and other important parts of the aluminum template. To identify shape features, match feature points in images at different angles, use algorithms (such as FLANN or BFMatcher) to find the same feature points, record the matching results, and then build a 3D model. Use the matched feature points to prepare for 3D reconstruction. Select a suitable 3D reconstruction algorithm, such as structured light, beam method, or multi-view stereo (MVS). Use the 3D reconstruction algorithm to convert feature points in the 2D image into point cloud data in 3D space. Generate a 3D point cloud based on the matched feature points and camera position information. The position of each point in space is determined by its corresponding relationship in each image. Use tools (such as Open3D or PCL) to generate and process point clouds. Filter and denoise the generated point clouds to remove unnecessary points and stray noise. Use voxel grid filtering (Voxel Grid Filter) and other methods are used to reduce the density of the point cloud, thereby improving the processing speed. The processed point cloud data is converted into a three-dimensional grid model, and a triangulation algorithm (such as Delaunay Triangulation) is used to generate the surface. The generated three-dimensional model is exported to a common format (such as STL, OBJ) for subsequent use. The generated three-dimensional structural model is verified to ensure the accuracy and completeness of the model. The accuracy of the model can be confirmed by comparing it with the actual aluminum template.

[0097] Step S2: Obtain the production and operation log of the building aluminum formwork; perform physical state characteristic analysis based on the production and operation log of the building aluminum formwork, and evolve the stacking planning constraint law, so as to obtain the overall stacking planning constraint law of the aluminum formwork;

[0098] In this embodiment, the types of logs to be collected are determined, including production time, aluminum template in and out of storage records, equipment operation status, operators, production environment and other information, and relevant operation logs are exported from the production management system or database, usually in the format of CSV, Excel or database query results. Data processing tools (such as Python's Pandas or R) are used to clean and organize the collected log data, remove duplicate records and missing values, standardize timestamps, ensure the consistency of all time data for subsequent analysis, and store the cleaned and organized data in a suitable database or data file to ensure data traceability and easy access. Indicators of physical state characteristics, such as the frequency of use, damage, cleanliness, stability, etc. of the aluminum template, set analysis goals, and clarify which characteristics have an impact on palletizing planning. Data related to physical state characteristics are extracted from the production operation log, for example: frequency of use: calculate the number of times the aluminum template is used through the in and out of storage records, damage records: analyze the damage report of each template and calculate the damage rate, cleanliness: evaluate the cleanliness of the template based on the cleaning record, and use statistical analysis methods (such as descriptive statistics, correlation analysis, etc.) Analyze the extracted physical state characteristics, identify the key features that affect the palletizing planning, use visualization tools (such as Matplotlib, Seaborn) to display the relationship between the features, help understand the influencing factors, organize the results of the physical state characteristic analysis into a report, and store it in the database for subsequent use. According to the results of the physical state characteristic analysis, define the preliminary palletizing planning constraints, such as: maximum stacking height, placement order of aluminum templates, number limit of templates per layer, stacking limit of damaged templates, evolution model design, design an evolution model to dynamically adjust the palletizing planning constraints according to the physical state characteristics, use genetic algorithms, optimization algorithms or machine learning models for evolution, determine the objective function of the evolution, such as maximizing space utilization or minimizing damage risk, apply the evolution model in a simulation environment, test the palletizing effect under different constraints, observe its impact on space utilization and operating efficiency, perform multiple simulations, collect data for optimization, adjust and optimize the constraints according to the results of the simulation test, and record the final overall aluminum template palletizing planning constraints, and store the evolved constraints in the database for subsequent palletizing planning.

[0099] Step S3: Based on the overall stacking planning constraint law of the aluminum formwork, intelligent stacking planning is performed on each aluminum formwork three-dimensional structure model, and the optimal stacking planning evaluation is performed to extract the optimal aluminum formwork stacking planning scheme;

[0100] In this embodiment, the three-dimensional structural model data of each aluminum template is collected to ensure the accuracy and integrity of the model, and the previously defined overall stacking planning constraints of the aluminum template are sorted out, including the maximum stacking height, the number of layers, the template placement order, etc. The three-dimensional model data and the constraint rules of the aluminum template are integrated into the same data structure to facilitate subsequent calculations and analysis. A suitable intelligent algorithm is selected for stacking planning. Commonly used algorithms include genetic algorithms, ant colony algorithms, particle swarm optimization, etc. The objective function of the algorithm is determined, such as maximizing storage space utilization or minimizing loading and unloading time, and a stacking planning model is constructed. The three-dimensional structure of the aluminum template and related constraint information are input, and relevant parameters are set according to the selected algorithm, such as population size, The algorithm will automatically explore different stacking methods, meet the constraints and optimize the objective function, record multiple stacking schemes generated in the process, ensure that each scheme complies with the set constraints, determine the evaluation indicators, including space utilization, operational safety, loading and unloading efficiency and stability, etc., apply the evaluation model to each generated stacking scheme, calculate various indicators and make a comprehensive score, use the weighted scoring method to assign weights to different evaluation indicators to obtain a comprehensive score, and select the stacking scheme with the highest score as the optimal aluminum template stacking planning scheme based on the comprehensive score, and record the detailed information of the selected optimal scheme, including the stacking position, number of layers and the specific position of each template.

[0101] Step S4: Perform dynamic stacking simulation on each aluminum formwork three-dimensional structure model according to the optimal aluminum formwork stacking planning scheme, and perform dynamic loading and unloading simulation to generate the equipment loading and unloading behavior difficulty value and the aluminum formwork handling path efficiency;

[0102] In this embodiment, a suitable simulation software (such as AnyLogic, MATLAB Simulink, Blender or Unity) is selected to build a dynamic stacking simulation environment, import the three-dimensional structural model of each aluminum template, ensure that the scale and details of the model are accurate, set the simulation parameters, set the simulation parameters, including gravity, friction coefficient, collision detection and physical properties of the aluminum template (such as mass and volume), define the initial conditions in the stacking process, such as the initial position, stacking order and stacking height of the aluminum template, run the dynamic simulation, observe the behavior of the aluminum template during the stacking process, record the position change and force conditions during the stacking process, monitor the simulation process, ensure that no collision or instability occurs, record the data generated during the simulation process, including the final position, stability and stacking height of each aluminum template, analyze the simulation results, evaluate the stability and safety of the stacking, ensure that it meets the design requirements, add loading and unloading equipment (such as forklifts, cranes, etc.) in the simulation environment, configure its motion parameters and operating capabilities, determine the starting position, target position and path of the equipment during the loading and unloading process, define the steps of the loading and unloading operation, including lifting, moving, placing and other actions, ensure that each action conforms to the requirements of the design. According to the actual operation process, the movement speed and acceleration of the loading and unloading equipment are set to simulate the dynamic response in the real operation, run the dynamic loading and unloading simulation, observe how the equipment takes the aluminum template from the stack and places it at the target position, and record the data in the loading and unloading process, including loading and unloading time, equipment load, path selection and other information. According to the data in the loading and unloading process, the difficulty of each action is analyzed, including lifting height, distance, load condition, etc., and the difficulty value of the loading and unloading behavior is calculated. The loading and unloading difficulty value of each aluminum template is recorded to form a data set of the difficulty of loading and unloading behavior. The moving path data of the loading and unloading equipment is extracted from the dynamic loading and unloading simulation, including the starting position, target position and the path information passed. The timestamp and location information of each path are recorded to form a complete path data set. The efficiency of the handling path is calculated, the efficiency of different paths is evaluated, the bottlenecks and improvement points are identified, and the loading and unloading behavior difficulty value and the handling path efficiency results are organized into a report for subsequent analysis and optimization. Visualization tools (such as Matplotlib or Tableau) are used to display the analysis results to help understand the key factors in the loading and unloading process.

[0103] Step S5: Dynamically adjust the stacking planning according to the difficulty value of equipment loading and unloading behavior and the efficiency of the aluminum template handling path, and build a dynamic stacking planning adjustment strategy;

[0104] In this embodiment, the data of the difficulty value of equipment loading and unloading behavior and the efficiency of aluminum template handling path generated in the previous step are collected. Organize the data to ensure that all information is stored in a unified format for subsequent analysis. Use statistical analysis tools (such as Python's Pandas or R) to analyze the difficulty value of loading and unloading behavior and the efficiency of the handling path. Identify the relationship between high-difficulty loading and unloading operations and low-efficiency handling paths, and find out the key factors affecting stacking efficiency. Determine the main factors affecting dynamic stacking planning, for example: loading and unloading actions with high difficulty values ​​need to be avoided or optimized. The situation of low handling path efficiency needs to be adjusted to improve efficiency. According to the data analysis results, set the goal of dynamic stacking planning adjustment, for example: improve loading and unloading efficiency, reduce loading and unloading difficulty, optimize the stacking order and position of aluminum templates, and select appropriate adjustment methods. The options include: redesigning the stacking order to ensure that the easily accessible templates are placed on the upper layer. Adjust the stacking height and number of layers to reduce the complexity of the loading and unloading process. Optimize the handling path to ensure that the path is as short as possible and avoid obstacles. According to the set goals and the selected adjustment methods, a dynamic adjustment model is constructed. Use optimization algorithms (such as linear programming, genetic algorithms, etc.) to determine the best adjustment plan. Implement adjustments based on the new palletizing solution generated by the dynamic adjustment model. Update the palletizing planning information in the warehouse management system to reflect the new stacking order and location. Verify the new dynamic palletizing plan in the simulation environment and observe its performance in actual operations. Record the new loading and unloading behavior difficulty value and handling path efficiency to ensure that the adjusted plan is better than the previous plan. Evaluate the implementation effect of the new plan, including loading and unloading efficiency, operational safety, and user feedback. Collect data to provide a basis for subsequent dynamic adjustments.

[0105] Step S6: Perform multi-scenario transfer learning on the dynamic palletizing planning adjustment strategy, and fine-tune the adaptive palletizing planning parameters to build an adaptive aluminum template palletizing planning engine;

[0106] In this embodiment, multiple warehousing scenarios are defined, including different layouts, equipment configurations, and operating procedures. Palletizing planning data, loading and unloading behavior difficulty values, and handling path efficiency in each scenario are collected to ensure data diversity and representativeness. The collected multi-scenario data are organized into a unified format, and redundant information and missing values ​​are removed to ensure data quality. Data processing tools (such as Pandas) are used for data cleaning and preprocessing. Key features, including environmental variables, operating conditions, and performance indicators, are extracted from multi-scenario data to ensure that the features can reflect the palletizing and loading and unloading characteristics in different scenarios, which is convenient for subsequent transfer learning. A suitable transfer learning framework (such as TensorFlow, PyTorch) is selected for model construction to determine the basic architecture of the model, such as Neural network or ensemble learning model, adapted to the characteristics of multi-scenario data, divide data from different scenarios into training set and validation set, use training set for model training, use transfer learning method, apply the model trained on one or more source scenarios to the target scenario, perform fine-tuning, evaluate the performance of the model on the validation set, check its adaptability and accuracy in different scenarios, adjust model parameters to ensure that it can be effectively migrated to new warehousing scenarios, design an adaptive fine-tuning framework that can dynamically adjust palletizing planning parameters based on real-time data and feedback, determine the goal of fine-tuning, such as improving loading and unloading efficiency or reducing operation difficulty, integrate data from real-time loading and unloading process into the fine-tuning framework, including the difficulty value and path efficiency of loading and unloading behavior, use stream processing tools (such as Apache Kafka or Spark Streaming) for real-time data processing, use online learning algorithms (such as incremental learning or reinforcement learning) to fine-tune the model, dynamically adjust the palletizing planning parameters to adapt to new operating conditions and environmental changes, monitor the performance of the fine-tuned model in actual operations, collect feedback on loading and unloading efficiency and safety, adjust the fine-tuning strategy based on the feedback, ensure continuous optimization of the model, design the architecture of the adaptive aluminum template palletizing planning engine, including data input module, planning algorithm module and result output module, ensure that the engine can handle multi-scenario input and adapt to different warehousing needs, integrate the trained transfer learning model and fine-tuning algorithm into the engine to ensure real-time and flexibility, design a user interface to facilitate operators to input data for new scenarios and obtain palletizing planning solutions, test the adaptive palletizing planning engine in different warehousing scenarios, evaluate its effect in actual operations, optimize it according to the test results, and ensure the efficiency and stability of the engine.

[0107] In this embodiment, refer to Figure 2 , is a flowchart of detailed implementation steps of step S1. In this embodiment, the detailed implementation steps of step S1 include:

[0108] Step S11: acquiring a multi-angle monitoring image of the building aluminum formwork to be stacked, globally reconstructing the image details of the multi-angle monitoring image of the building aluminum formwork, and constructing a globally reconstructed optimized image;

[0109] Step S12: performing visual recognition of the three-dimensional structural feature points of the aluminum template on the detail-enhanced multi-angle image, and marking a plurality of structural feature points of the aluminum template;

[0110] Step S13: performing three-dimensional geometric dimension analysis on multiple aluminum template structural feature points to generate three-dimensional geometric features of each aluminum template;

[0111] Step S14: Calculating the radian of the corners of the templates one by one for the structural feature points of the multiple aluminum templates, and extracting the radian value of the corners of each aluminum template;

[0112] Step S15: performing a topological morphological structure analysis on the three-dimensional geometric features of each aluminum template based on the corner radian value of each aluminum template to generate the topological morphological structure features of each aluminum template;

[0113] Step S16: Perform three-dimensional point cloud modeling on the topological morphological structural features of each aluminum template to construct a three-dimensional structural model of each aluminum template.

[0114] In this embodiment, a high-resolution camera or a drone is used to shoot the aluminum template to be stacked from multiple angles to ensure that images are obtained from multiple angles (such as the front, side, top, etc.) to capture all the details of the template, ensure that the lighting conditions during shooting are good, avoid shadows and reflections to improve the image quality, pre-process the acquired images, including denoising, contrast enhancement, and brightness adjustment to improve the accuracy of subsequent reconstruction, use an image processing library (such as OpenCV) to perform image denoising and enhancement processing, perform global reconstruction on the multi-angle monitoring images, use structured light, stereo vision, or multi-view geometry to reconstruct the global shape of the aluminum template, and use a multi-view reconstruction algorithm (such as SfM-Structure from Motion) to extract feature points and generate a 3D point cloud, extract feature points from the reconstructed 3D point cloud, use algorithms (such as SIFT, SURF, or ORB) to identify the key feature points of the aluminum template, ensure that the extracted feature points can represent the geometric shape and structural features of the aluminum template, mark the identified feature points, store the 3D coordinates of the feature points and related information (such as normal vectors, feature descriptors), use visualization tools (such as Matplotlib, PCL) to display the marked feature points, ensure accurate recognition, perform 3D geometric dimension analysis on the marked multiple aluminum template structural feature points, calculate the distance, angle, and area between each feature, use a geometric calculation library (such as CGAL, Open3D) to perform 3D geometric feature analysis, generate detailed 3D geometric feature data for each aluminum template, including size, shape, spatial distribution and other information, store the results in a structured data format (such as JSON, CSV) for subsequent analysis, analyze the feature points of each aluminum template, calculate the radian value of the corners, The radian is calculated through the normal vector and feature point position of the three-dimensional point cloud, and the radian of the corners is calculated using trigonometric functions and vector operations. The extracted radian values ​​of the corners are recorded in the data set, ensuring that the number of each template and the corresponding radian value information are included. Based on the radian values ​​of the corners of each aluminum template, a topological morphological structure analysis model is constructed, and the topological data analysis (TDA) method is used for analysis to identify the connection relationship, shape characteristics and geometric constraints of the aluminum template, generate the topological morphological structure characteristics of each aluminum template, record its geometric characteristics and structural relationship, and store the topological characteristics in a structured form for subsequent processing and visualization. The topological morphological structure characteristics of each aluminum template are modeled in three-dimensional morphological point cloud, and point cloud processing tools (such as PCL and Meshlab) are used for modeling. A three-dimensional model of each aluminum template is generated through feature points and topological information. The generated three-dimensional structure model is optimized, including simplifying polygons, smoothing surfaces, etc., to improve the visualization effect and calculation efficiency of the model, and modeling software (such as Blender, Fusion 360) for post-processing and optimization, and the final generated 3D aluminum formwork model is stored in a standard file format (such as STL, OBJ) for subsequent use and sharing.

[0115] In this embodiment, the specific steps of step S11 are:

[0116] Calculate the average brightness of the whole image of the multi-angle monitoring image of the building aluminum formwork;

[0117] Detecting the dark image area of ​​the multi-angle monitoring image of the building aluminum formwork based on the average brightness of the whole image;

[0118] Performing local brightness enhancement processing on the dark image area to obtain a brightness enhanced monitoring image;

[0119] Perform edge texture feature analysis on the brightness enhanced monitoring image and extract edge texture features of the aluminum template;

[0120] According to the edge texture features of the aluminum template, non-local mean filter optimization is performed to generate mean filter optimized edge texture features;

[0121] Extract edge texture area in the image based on edge texture features of aluminum template;

[0122] Performing super-resolution detail enhancement on the edge texture region in the image to generate a super-resolution enhanced edge texture region;

[0123] Based on super-resolution enhancement of edge texture areas and mean filtering to optimize edge texture features, the image details of the brightness enhanced monitoring image are globally reconstructed to construct a globally reconstructed optimized image.

[0124] In this embodiment, an image processing library (such as OpenCV or PIL) is used to read a multi-angle monitoring image, and the image is converted into a grayscale image to simplify the brightness calculation. The global brightness of the image is calculated, and a threshold is set according to the average brightness of the whole image, which is usually a certain ratio of the average brightness (such as 0.5 times) to distinguish the dark area. The image is binarized using the threshold, and the area with brightness lower than the threshold is identified. The binarization is performed by applying the cv2.threshold function of OpenCV, and a mask of the dark area is output. The dark area is extracted from the original image according to the detected dark area mask, and the local brightness of the dark area is enhanced. The contrast limit adaptive The CLAHE object is created in OpenCV using cv2.createCLAHE and applied to the extracted dark area. The enhanced dark area is synthesized with other parts of the original image to obtain a brightness enhanced monitoring image. The edge detection is performed on the brightness enhanced monitoring image. Common algorithms include Canny edge detection. The cv2.Canny function of OpenCV is used to extract edge texture features in the image. The coordinates and intensity information of the detected edge texture features are extracted to provide data support for subsequent processing. The edge features are visualized to ensure the effectiveness of the extraction. Non-Local Mean Filtering is selected. Means (NLM) algorithm is used to smooth the image while retaining edge texture details. Filter parameters such as search window size and similarity measure between pixels are determined. The extracted edge texture features are filtered using OpenCV's cv2.fastNlMeansDenoising function to generate edge texture features optimized by mean filtering. Based on the edge texture features optimized by mean filtering, the edge texture region in the image is located using contour extraction or region growing algorithm. The edge region contour is found using OpenCV's cv2.findContours function. The located edge texture region information is marked and saved for subsequent processing. A suitable super-resolution algorithm is selected, such as a convolutional neural network (C A super-resolution generative adversarial network (SRGAN) of a neural network (NN) is used to prepare a trained model for super-resolution reconstruction. A super-resolution algorithm is applied to the located edge texture region to generate a higher resolution detail-enhanced image. A deep learning framework (such as TensorFlow or PyTorch) is used to load the model and perform inference. The super-resolution-enhanced edge texture region is merged with the edge texture features optimized by the mean filter to form complete image detail information. An image reconstruction algorithm (such as weighted averaging and total variation denoising) is used to perform global detail reconstruction of the brightness-enhanced monitoring image to ensure that important structures and details are retained during the reconstruction process. The final globally reconstructed optimized image is output to ensure that the image achieves the expected effects in terms of brightness, contrast, and details.

[0125] In this embodiment, refer to Figure 3 , is a flowchart of detailed implementation steps of step S2. In this embodiment, the detailed implementation steps of step S2 include:

[0126] Step S21: Obtaining the production operation log of the building aluminum formwork;

[0127] Step S22: extracting all aluminum formwork parameter information based on the architectural aluminum formwork production operation log; performing physical state characteristic analysis on all aluminum formwork parameter information to generate physical state characteristics of each aluminum formwork;

[0128] Step S23: Perform environmental storage space analysis on the production operation log of the building aluminum formwork to obtain production environment storage space data;

[0129] Step S24: quantifying the equipment lifting capacity of the building aluminum formwork production operation log to generate the equipment lifting capacity value;

[0130] Step S25: performing stacking stability requirement analysis on each aluminum template three-dimensional structure model according to the physical state characteristics of each aluminum template, thereby generating overall stacking stability requirement data;

[0131] Step S26: Based on the production environment storage space data and the equipment lifting capacity value, the overall stacking stability demand data is subjected to stacking planning constraint law evolution, thereby obtaining the overall stacking planning constraint law of the aluminum formwork.

[0132] In this embodiment, the production operation log of the architectural aluminum formwork is collected from the production system to ensure that the record includes information such as timestamp, operator, equipment status, production parameters, etc., and an automated script or log management tool (such as ELK Stack, Splunk) is used to extract the log from the database or file system, and the collected log data is stored in a structured database (such as MySQL, PostgreSQL) or a data warehouse to facilitate subsequent query and analysis, ensure that the data format is unified, and facilitate subsequent processing, use a data processing tool (such as Pandas) to analyze the production operation log, extract parameter information of all aluminum formworks, such as size, weight, material properties, etc., clean the extracted data to ensure that there are no missing values ​​and outliers, perform physical state characteristic analysis on the extracted aluminum formwork parameter information, calculate the physical characteristics of each aluminum formwork (such as volume, density, center of gravity position, etc.), and generate each Physical state characteristic data of aluminum formwork, ensure data structured storage, extract storage space related information from production operation log, including available space, storage layout, storage temperature and humidity, etc., ensure data accuracy and completeness, remove irrelevant or redundant information, use data analysis tools to analyze storage space data, evaluate the impact of the current storage environment on aluminum formwork storage, generate production environment storage space data report, including storage efficiency, space utilization and other indicators, extract equipment lifting capacity related information from production operation log, including equipment type, rated lifting capacity, actual usage, etc., calculate the actual load capacity of the equipment, and consider the performance of different equipment under different conditions Performance, generate the lifting capacity value of each device, record the maximum lifting capacity of the equipment under specific conditions, ensure the accuracy of the capacity value, facilitate subsequent analysis and decision-making, establish a three-dimensional structural model of the aluminum formwork based on the physical state characteristics of each aluminum formwork, ensure that the model can reflect the real physical properties, use modeling software (such as CAD, SolidWorks) to build the model, conduct stacking stability demand analysis based on the three-dimensional structural model and physical state characteristics, evaluate the stability of the aluminum formwork under stacking conditions, use finite element analysis (FEA) tools (such as ANSYS, ABAQUS) to simulate the stability performance of the aluminum formwork under different stacking conditions, and generate the overall stacking Stability requirement data, according to the production environment storage space data and equipment lifting capacity value, define the constraints of aluminum formwork stacking, such as maximum stacking height, bottom bearing capacity, etc., combined with stability requirement data, consider the physical properties and environmental impact of different aluminum formworks, use optimization algorithms (such as genetic algorithms, particle swarm optimization) to evolve the overall stacking planning constraint law, find the optimal stacking plan, generate the overall stacking planning constraint law data of aluminum formwork, ensure that the planning plan is reasonable and efficient, verify the generated stacking planning plan, ensure that it can meet the stability and safety requirements in actual applications, conduct simulation tests, evaluate the feasibility of the planning plan, and adjust and optimize it according to the test results.

[0133] In this embodiment, the specific steps of step S22 are:

[0134] Extract the weight, structural strength and material characteristics of each aluminum formwork based on all aluminum formwork parameter information;

[0135] Perform stability requirement analysis on the weight and structural strength to generate stability requirement data for the aluminum formwork;

[0136] Calculate the surface fragility of the material characteristics to generate the surface fragility of each aluminum template;

[0137] Extract the order of using aluminum formwork according to the production and operation log of architectural aluminum formwork;

[0138] Calculating the stacking position priority of the access sequence to obtain the stacking position priority of each aluminum template;

[0139] The physical state characteristics of each aluminum template are evaluated on the surface fragility, aluminum template stability requirement data and the stacking position priority of each aluminum template to generate the physical state characteristics of each aluminum template.

[0140] In this embodiment, the size (length, width, height) and material density of each aluminum template are extracted from the production operation log and the aluminum template parameter data. According to the material properties of the aluminum template (such as yield strength and tensile strength), the structural strength of the aluminum template is calculated using the knowledge of material mechanics. It is necessary to consult the material manual or use the material database to obtain the mechanical performance indicators of the aluminum alloy, extract the material characteristics of the aluminum template, including information such as alloy type, thickness, coating, etc., and record them. According to the weight and structural strength of the aluminum template, the stability requirements are defined, including bearing capacity, bending strength, etc., and relevant building codes and standards (such as "Building Structure Load Code") are used for reference. Finite element analysis (FEA) is performed on the aluminum template to evaluate the stability performance under specific loads. Simulation software (such as ANSYS, ABAQUS) is used to establish and analyze the model, generate stability requirement data for the aluminum template, define characteristic indicators related to surface fragility, such as hardness, wear resistance, corrosion resistance, etc., obtain relevant characteristics by consulting material data or experimental results, and calculate the stability requirements according to material characteristics and environmental factors (such as humidity, temperature, chemical corrosion). ) Calculate the surface fragility of each aluminum template, use the weighted scoring method to quantify different features, generate a fragility score for each aluminum template, extract the order of aluminum template use from the production operation log, usually recorded in the material outbound or handling record, ensure the accuracy of the extracted data, sort by timestamp to reflect the actual order of use, define the priority standard of the stacking position according to the order of use, surface fragility and stability requirements of the aluminum template, set the priority calculation formula, priority = frequency of use - fragility score + stability requirements, calculate the stacking position priority of each aluminum template, generate the stacking position priority data of each aluminum template, use a sorting algorithm (such as quick sort, merge sort) to sort the aluminum templates by priority, establish a comprehensive evaluation model according to the surface fragility, stability requirement data and stacking position priority of the aluminum template, use the weighted average method to assign different weights to each feature for comprehensive scoring, calculate the physical state feature score of each aluminum template, generate the comprehensive physical state feature data of each aluminum template, and record the evaluation results in the database for subsequent query and analysis.

[0141] In this embodiment, refer to Figure 4 , is a flowchart of detailed implementation steps of step S3. In this embodiment, the detailed implementation steps of step S3 include:

[0142] Step S31: coding and marking each aluminum template three-dimensional structure model to generate a coded aluminum template structure model;

[0143] Step S32: performing intelligent stacking planning on the coded aluminum template structure model based on the overall stacking planning constraint law of the aluminum template, thereby generating multiple initial aluminum template stacking planning schemes;

[0144] Step S33: Calculating the space utilization rate of each of the multiple initial aluminum template stacking planning schemes to obtain the stacking space utilization rate of each scheme;

[0145] Step S34: performing a global stability assessment of the aluminum formwork for a plurality of initial aluminum formwork stacking planning schemes to generate aluminum formwork stability data for each scheme;

[0146] Step S35: Based on the stacking space utilization rate of each plan and the aluminum template stability data of each plan, the optimal stacking planning evaluation is performed to extract the optimal aluminum template stacking planning plan.

[0147] In this embodiment, it is ensured that the three-dimensional structural models of all aluminum templates have been generated. CAD or 3D modeling software (such as SolidWorks, AutoCAD) is usually used for modeling. A coding system is designed to uniquely identify each aluminum template structural model. The code is generated based on the characteristics of the template (such as size, material, type). For example, the coding format is AL-XXX-YY, where A represents the category, L represents the length, XXX represents the width, and YY represents other features. The coding mark of each aluminum template is applied to the corresponding three-dimensional structural model, and the coding information is stored in a database or file for subsequent query and management. Based on the overall stacking planning constraint law of the aluminum template generated in the early stage, the constraints of the stacking are defined, including the maximum stacking height, stability requirements, etc., and an appropriate intelligent planning algorithm is selected, such as a genetic algorithm, an ant colony algorithm or a deep learning model, to perform preliminary stacking planning. These algorithms can explore different stacking methods under given constraints to optimize space utilization and stability. Multiple initial aluminum template stacking planning schemes are generated according to the planning algorithm. Each scheme should comply with the set constraint law. A space utilization calculation model is established for each initial planning scheme to calculate the required stacking aluminum template volume and the actual stacking area. The space utilization rate can be calculated by the following formula: Space utilization rate = (total volume of aluminum formwork / stacked area volume) × 100%. The space utilization rate of each scheme is recorded and the results are stored in the database for subsequent evaluation and comparison. For each initial planning scheme, finite element analysis (FEA) is used to conduct a global stability assessment, considering the stress of the aluminum formwork in the stacked state. The model should include factors such as the material properties of the aluminum formwork, the stacking method, and the external load. Simulation software (such as ANSYS, ABAQUS) is used to test the stability of each scheme to evaluate its stability under different loads. Stability performance, generate aluminum formwork stability data for each solution, establish a comprehensive evaluation model, consider the space utilization and aluminum formwork stability data of each solution, use weighted scoring method to quantify different indicators, and calculate the comprehensive score of each solution according to the evaluation model. Priority is given to solutions with high space utilization and good stability. Comprehensive score = w1×space utilization+w2×stability score, where w1 and w2 are weight coefficients. Select the solution with the highest comprehensive score as the optimal aluminum formwork stacking planning solution, and record the detailed information of the solution. Organize the implementation details of the optimal solution into a document for subsequent execution and monitoring.

[0148] In this embodiment, step S4 includes the following steps:

[0149] Step S41: performing dynamic stacking simulation on each aluminum template three-dimensional structure model according to the optimal aluminum template stacking planning scheme, thereby constructing an aluminum template stacking planning model;

[0150] Step S42: performing dynamic loading and unloading simulation on the aluminum template stacking planning model to generate dynamic loading and unloading simulation response data of the aluminum template;

[0151] Step S43: performing equipment loading and unloading movement trajectory evolution on the aluminum template dynamic loading and unloading simulation response data, and extracting the equipment loading and unloading movement trajectory;

[0152] Step S44: analyzing the equipment loading and unloading action sequence of the aluminum formwork dynamic loading and unloading simulation response data, and extracting multiple-stage loading and unloading action sequences;

[0153] Step S45: perform loading and unloading behavior difficulty assessment on multiple stage loading and unloading action sequences to generate equipment loading and unloading behavior difficulty values; calculate the handling path efficiency of the equipment loading and unloading movement trajectory to obtain the aluminum formwork handling path efficiency.

[0154] In this embodiment, it is ensured that the optimal aluminum template stacking planning scheme has been determined, and a three-dimensional structural model of each aluminum template is prepared. A three-dimensional modeling software (such as Blender, Maya or Unity) is used to import the three-dimensional model of the aluminum template. A dynamic simulation environment is configured in the simulation software, including gravity, collision detection and physical properties (such as friction coefficient). The initial position, stacking order and contact relationship between the aluminum templates during the stacking process are defined. The dynamic simulation is run to observe the behavior of the aluminum templates during the stacking process to ensure that the simulation can reflect the actual stacking situation. The data during the simulation process, including position changes, force conditions, etc., are recorded. On the basis of the dynamic stacking simulation model, loading and unloading equipment (such as forklifts, cranes, etc.) are added and their motion parameters are set. The loading and unloading areas of the loading and unloading equipment are determined. A dynamic loading and unloading simulation is performed to simulate how the equipment takes the aluminum template from the stack and places it at the target position. The response data during the loading and unloading process is recorded, including the loading and unloading time, equipment load and position change of the aluminum template. The response data generated by the dynamic loading and unloading simulation is stored in a database for subsequent analysis. The movement of the loading and unloading equipment is extracted from the dynamic loading and unloading simulation response data. The moving trajectory includes the starting position, target position and path of the equipment, and the timestamp and location information of each trajectory are recorded to form a moving trajectory dataset. The moving trajectory is analyzed by data analysis tools (such as Python's Pandas or Matplotlib) to identify the optimal path and obstacles. The extracted equipment loading and unloading moving trajectory data is sorted and stored to facilitate subsequent efficiency calculation and optimization. The action sequence of the loading and unloading equipment is extracted from the dynamic loading and unloading simulation response data, including lifting, moving, placing and other actions. The time, position and status information of each action are recorded to form an action sequence dataset. The loading and unloading process is divided into multiple stages (such as preparation stage, loading stage, transportation stage, unloading stage, etc.), and the actions of each stage are marked to ensure that the action sequence of each stage is complete and accurate. The difficulty evaluation standard of loading and unloading behavior is formulated, including factors such as action complexity, time consumption and equipment load. Each action sequence is scored by weighted scoring method to generate the difficulty value of equipment loading and unloading behavior. According to the extracted equipment loading and unloading moving trajectory, the efficiency of the handling path is calculated, the efficiency of different paths is evaluated, and the calculation results are recorded.

[0155] In this embodiment, the specific steps of step S5 are:

[0156] Step S51: dynamically optimizing the loading and unloading path of the equipment based on the aluminum template handling path efficiency, thereby generating an optimized loading and unloading path;

[0157] Step S52: adjusting the stacking position of the aluminum template based on the equipment loading and unloading behavior difficulty value, thereby generating stacking position adjustment data;

[0158] Step S53: dynamically adjust the optimal aluminum template stacking planning scheme according to the loading and unloading optimization path and the stacking position adjustment data, and construct a dynamic stacking planning adjustment strategy.

[0159] In this embodiment, the efficiency data of the handling path calculated in the early stage is used to analyze the efficiency of different loading and unloading movement trajectories, including the moving distance, the dwelling time and the load condition, and the less efficient path is identified as the focus of optimization. A suitable path optimization algorithm is selected, such as the Dijkstra algorithm or the A* search algorithm, to find the shortest and most efficient loading and unloading path, and the optimization goal is defined, such as minimizing the distance, time or energy consumption. The equipment loading and unloading movement trajectory is calculated according to the optimization algorithm to generate a dynamic loading and unloading optimization path, ensuring that the new path takes into account the obstacles in the environment and the operating limitations of the equipment. The generated loading and unloading optimization path data is stored in a database for subsequent use and analysis. Based on the previously evaluated loading and unloading behavior difficulty value, the impact of the stacking position of each aluminum template on the loading and unloading efficiency is analyzed, and the stacking position that is likely to cause loading and unloading difficulties is determined. As the focus of adjustment, a stacking position adjustment strategy is formulated, and the stacking position of the aluminum template is re-planned according to the loading and unloading behavior difficulty value. The adjustment includes placing templates with high vulnerability. Place it in a more accessible position, or optimize the stacking order according to the order of retrieval. After completing the adjustment, record the new stacking position data to ensure that the new position of each aluminum template is clear and in line with the new optimization strategy. According to the loading and unloading optimization path and stacking position adjustment data, build a dynamic stacking planning adjustment strategy to ensure that the new planning strategy can effectively combine the optimized path with the new position to improve the overall loading and unloading efficiency. Use simulation software (such as AnyLogic, FlexSim) to simulate the new dynamic stacking plan and evaluate its performance in actual operation. Check whether the new strategy can reduce loading and unloading time, improve efficiency, and ensure the safety of aluminum templates. According to the simulation results, evaluate the effectiveness of the dynamic stacking planning adjustment strategy. If necessary, further optimize and adjust, record the adjustment results of the dynamic stacking plan, and formulate an implementation plan to implement the adjusted dynamic stacking plan into actual operations, and establish a monitoring mechanism to track the execution effect and efficiency, regularly evaluate the implementation effect, and make adjustments again when necessary to ensure continuous optimization.

[0160] In this embodiment, the specific steps of step S6 are:

[0161] Step S61: Acquire multiple preset storage scenes;

[0162] Step S62: Analyze the scene operation change characteristics of multiple preset storage scenes to generate each storage scene operation characteristic;

[0163] Step S63: performing multi-scenario transfer learning on the dynamic palletizing planning adjustment strategy according to the operation characteristics of each storage scenario, thereby obtaining multi-scenario palletizing planning parameters;

[0164] Step S64: fine-tune the adaptive palletizing planning parameters based on the multi-scenario palletizing planning parameters, and build an adaptive aluminum template palletizing planning engine.

[0165] In this embodiment, the types of warehouse scenarios that need to be analyzed are determined, such as different warehouse layouts, equipment configurations, and operating procedures. Each scenario should cover different variables, such as the size of the storage area, the width of the channel, the type and quantity of loading and unloading equipment. Multiple preset warehouse scenario data are obtained from the existing warehouse management system or design software to ensure that the collected data includes detailed parameters and operation processes of each scenario for subsequent analysis. The obtained multiple warehouse scenario data are stored in a database for subsequent analysis and processing. The operation change characteristics of each warehouse scenario are analyzed to extract key operation parameters, such as operation efficiency, space utilization, and equipment load. Data analysis tools (such as Python's Pandas or R) are used to perform statistical analysis on the scenario data. Operation characteristic data is generated for each warehouse scenario, including multiple performance indicators (such as loading and unloading time, stacking density, channel smoothness, etc.). The analysis results are recorded for subsequent use. A suitable transfer learning framework (such as TensorFlow, PyTorch) is selected. A model is constructed based on the existing dynamic palletizing planning adjustment strategy. The goal of transfer learning is determined. Ensure that the model can be effectively adjusted in different scenarios. Input the operation feature data of each warehousing scenario as training data into the transfer learning model. Use the previous dynamic palletizing planning parameters as the initial weights for model training. Train the model to optimize the palletizing planning parameters of the warehousing scenario to ensure that it can adapt to different scenarios. Verify and ensure the prediction accuracy of the model in new scenarios. Design an adaptive fine-tuning mechanism based on the palletizing planning parameters of multiple scenarios. Use online learning or incremental learning to continuously update the parameters to ensure that the model can adapt to changes in the warehousing environment in real time. Select a suitable fine-tuning algorithm, such as stochastic gradient descent (SGD) or Adam optimizer, to fine-tune the parameters and define the target indicators for fine-tuning, such as improving loading and unloading efficiency or reducing losses. Based on the fine-tuned parameters, build an adaptive aluminum template palletizing planning engine and integrate it into the warehouse management system to ensure that the engine can calculate the best palletizing solution in real time and adapt to different operation scenarios. Monitor the performance of the adaptive engine in actual applications, collect feedback data for subsequent optimization, regularly evaluate the performance of the engine, and retrain or fine-tune it when necessary to maintain its adaptability and efficiency.

[0166] In this embodiment, a palletizing planning and control system for building aluminum formwork is provided, which is used to execute the palletizing planning and control method for building aluminum formwork as described above, including:

[0167] A three-dimensional structure module is used to obtain multi-angle monitoring images of the building aluminum formwork to be stacked, perform visual recognition of structural feature points on the multi-angle monitoring images of the building aluminum formwork, perform three-dimensional morphological point cloud modeling, and construct a three-dimensional structural model of each aluminum formwork;

[0168] The stacking constraint module is used to obtain the production and operation log of the building aluminum formwork; based on the production and operation log of the building aluminum formwork, the physical state characteristics are analyzed, and the stacking planning constraint law is evolved, so as to obtain the overall stacking planning constraint law of the aluminum formwork;

[0169] Intelligent stacking planning module, which is used to perform intelligent stacking planning for each aluminum formwork three-dimensional structure model based on the overall stacking planning constraint rules of the aluminum formwork, and to evaluate the optimal stacking planning and extract the optimal aluminum formwork stacking planning scheme;

[0170] Dynamic loading and unloading simulation module, used to perform dynamic stacking simulation on each aluminum formwork three-dimensional structure model according to the optimal aluminum formwork stacking planning scheme, and perform dynamic loading and unloading simulation to generate the equipment loading and unloading behavior difficulty value and aluminum formwork handling path efficiency;

[0171] Dynamic palletizing adjustment module, which is used to adjust the dynamic palletizing planning according to the difficulty value of equipment loading and unloading behavior and the efficiency of aluminum template handling path, and build a dynamic palletizing planning adjustment strategy;

[0172] The multi-scenario migration module is used to perform multi-scenario migration learning on the dynamic palletizing planning adjustment strategy, fine-tune the adaptive palletizing planning parameters, and build an adaptive aluminum template palletizing planning engine.

[0173] The present invention acquires the three-dimensional structural information of each aluminum template accurately by acquiring multi-angle monitoring images, visual recognition of structural feature points and three-dimensional morphological point cloud modeling, provides accurate basic data for subsequent palletizing planning, performs physical state feature analysis and evolution of palletizing planning constraint laws based on production operation logs, extracts the palletizing planning constraint laws of the entire aluminum template, helps constrain and optimize the planning process, performs intelligent palletizing planning on the three-dimensional structural model of each aluminum template according to the palletizing planning constraint laws, can achieve optimal palletizing planning for each aluminum template, improves palletizing efficiency and accuracy, evaluates the actual effect of the optimal palletizing planning scheme through dynamic palletizing simulation and loading and unloading simulation, extracts the difficulty value of equipment loading and unloading behavior and the efficiency of the handling path, helps optimize the planning scheme, performs dynamic palletizing planning adjustment according to the difficulty value of equipment loading and unloading behavior and the efficiency of the handling path, constructs a dynamic palletizing planning adjustment strategy, realizes real-time optimization of palletizing planning, improves production efficiency, constructs an adaptive palletizing planning engine through multi-scenario transfer learning and adaptive palletizing planning parameter fine-tuning, and the system automatically adjusts planning parameters in different scenarios to improve adaptability and intelligence.

[0174] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0175] What has been described above is only a specific implementation mode of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art. The general principles defined in this article can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown in this article, but will conform to the widest scope consistent with the principles and novel features invented in this article.

Claims

1. A stacking planning and control method for building aluminum formwork, characterized in that: The following steps are involved: Step S1: obtaining a multi-angle monitoring image of the building aluminum formwork to be stacked, visually identifying the structural feature points of the multi-angle monitoring image of the building aluminum formwork, and performing three-dimensional morphological point cloud modeling to construct a three-dimensional structural model of each aluminum formwork; Step S2: Obtaining the production and operation log of the building aluminum formwork; Based on the production and operation log of architectural aluminum formwork, the physical state characteristics are analyzed, and the stacking planning constraint law is evolved to obtain the overall stacking planning constraint law of aluminum formwork; Step S3: Based on the overall stacking planning constraint law of the aluminum formwork, intelligent stacking planning is performed on each aluminum formwork three-dimensional structure model, and the optimal stacking planning evaluation is performed to extract the optimal aluminum formwork stacking planning scheme; Step S4: Perform dynamic stacking simulation on each aluminum formwork three-dimensional structure model according to the optimal aluminum formwork stacking planning scheme, and perform dynamic loading and unloading simulation to generate the equipment loading and unloading behavior difficulty value and the aluminum formwork handling path efficiency; Step S5: Dynamically adjust the stacking planning according to the difficulty value of equipment loading and unloading behavior and the efficiency of the aluminum template handling path, and build a dynamic stacking planning adjustment strategy; Step S6: Perform multi-scenario transfer learning on the dynamic palletizing planning adjustment strategy, fine-tune the adaptive palletizing planning parameters, and build an adaptive aluminum template palletizing planning engine.

2. The stacking planning and control method of architectural aluminum formwork according to claim 1 is characterized in that: The specific steps of step S1 are: Step S11: acquiring a multi-angle monitoring image of the building aluminum formwork to be stacked, globally reconstructing the image details of the multi-angle monitoring image of the building aluminum formwork, and constructing a globally reconstructed optimized image; Step S12: performing visual recognition of the three-dimensional structural feature points of the aluminum template on the detail-enhanced multi-angle image, and marking a plurality of structural feature points of the aluminum template; Step S13: performing three-dimensional geometric dimension analysis on multiple aluminum template structural feature points to generate three-dimensional geometric features of each aluminum template; Step S14: Calculating the radian of the corners of the templates one by one for the structural feature points of the multiple aluminum templates, and extracting the radian value of the corners of each aluminum template; Step S15: performing a topological morphological structure analysis on the three-dimensional geometric features of each aluminum template based on the corner radian value of each aluminum template to generate the topological morphological structure features of each aluminum template; Step S16: Perform three-dimensional point cloud modeling on the topological morphological structural features of each aluminum template to construct a three-dimensional structural model of each aluminum template.

3. The stacking planning and control method of architectural aluminum formwork according to claim 2 is characterized in that: The specific steps of step S11 are: Calculate the average brightness of the whole image of the multi-angle monitoring image of the building aluminum formwork; Detecting the dark image area of ​​the multi-angle monitoring image of the building aluminum formwork based on the average brightness of the whole image; Performing local brightness enhancement processing on the dark image area to obtain a brightness enhanced monitoring image; Perform edge texture feature analysis on the brightness enhanced monitoring image and extract edge texture features of the aluminum template; According to the edge texture features of the aluminum template, non-local mean filter optimization is performed to generate mean filter optimized edge texture features; Extract edge texture area in the image based on edge texture features of aluminum template; Performing super-resolution detail enhancement on the edge texture region in the image to generate a super-resolution enhanced edge texture region; Based on super-resolution enhancement of edge texture areas and mean filtering to optimize edge texture features, the image details of the brightness enhanced monitoring image are globally reconstructed to construct a globally reconstructed optimized image.

4. The stacking planning and control method of architectural aluminum formwork according to claim 1 is characterized in that: The specific steps of step S2 are: Step S21: Obtaining the production operation log of the building aluminum formwork; Step S22: extracting all aluminum formwork parameter information based on the architectural aluminum formwork production operation log; performing physical state characteristic analysis on all aluminum formwork parameter information to generate physical state characteristics of each aluminum formwork; Step S23: Perform environmental storage space analysis on the production operation log of the building aluminum formwork to obtain production environment storage space data; Step S24: quantifying the equipment lifting capacity of the building aluminum formwork production operation log to generate the equipment lifting capacity value; Step S25: performing stacking stability requirement analysis on each aluminum template three-dimensional structure model according to the physical state characteristics of each aluminum template, thereby generating overall stacking stability requirement data; Step S26: Based on the production environment storage space data and the equipment lifting capacity value, the overall stacking stability demand data is subjected to stacking planning constraint law evolution, thereby obtaining the overall stacking planning constraint law of the aluminum formwork.

5. The stacking planning and control method of architectural aluminum formwork according to claim 4 is characterized in that: The specific steps of step S22 are: Extract the weight, structural strength and material characteristics of each aluminum formwork based on all aluminum formwork parameter information; Perform stability requirement analysis on the weight and structural strength to generate stability requirement data for the aluminum formwork; Calculate the surface fragility of the material characteristics to generate the surface fragility of each aluminum template; Extract the order of using aluminum formwork according to the production and operation log of architectural aluminum formwork; Calculating the stacking position priority of the access sequence to obtain the stacking position priority of each aluminum template; The physical state characteristics of each aluminum template are evaluated on the surface fragility, aluminum template stability requirement data and the stacking position priority of each aluminum template to generate the physical state characteristics of each aluminum template.

6. The stacking planning and control method of architectural aluminum formwork according to claim 1 is characterized in that: The specific steps of step S3 are: Step S31: coding and marking each aluminum template three-dimensional structure model to generate a coded aluminum template structure model; Step S32: performing intelligent stacking planning on the coded aluminum template structure model based on the overall stacking planning constraint law of the aluminum template, thereby generating multiple initial aluminum template stacking planning schemes; Step S33: Calculating the space utilization rate of each of the multiple initial aluminum template stacking planning schemes to obtain the stacking space utilization rate of each scheme; Step S34: performing a global stability assessment of the aluminum formwork for a plurality of initial aluminum formwork stacking planning schemes to generate aluminum formwork stability data for each scheme; Step S35: Based on the stacking space utilization rate of each plan and the aluminum template stability data of each plan, the optimal stacking planning evaluation is performed to extract the optimal aluminum template stacking planning plan.

7. The stacking planning and control method of architectural aluminum formwork according to claim 1 is characterized in that: The specific steps of step S4 are: Step S41: performing dynamic stacking simulation on each aluminum template three-dimensional structure model according to the optimal aluminum template stacking planning scheme, thereby constructing an aluminum template stacking planning model; Step S42: performing dynamic loading and unloading simulation on the aluminum template stacking planning model to generate dynamic loading and unloading simulation response data of the aluminum template; Step S43: performing equipment loading and unloading movement trajectory evolution on the aluminum template dynamic loading and unloading simulation response data, and extracting the equipment loading and unloading movement trajectory; Step S44: analyzing the equipment loading and unloading action sequence of the aluminum formwork dynamic loading and unloading simulation response data, and extracting multiple-stage loading and unloading action sequences; Step S45: perform loading and unloading behavior difficulty assessment on multiple stage loading and unloading action sequences to generate equipment loading and unloading behavior difficulty values; calculate the handling path efficiency of the equipment loading and unloading movement trajectory to obtain the aluminum formwork handling path efficiency.

8. The stacking planning and control method of architectural aluminum formwork according to claim 1 is characterized in that: The specific steps of step S5 are: Step S51: dynamically optimizing the loading and unloading path of the equipment based on the aluminum template handling path efficiency, thereby generating an optimized loading and unloading path; Step S52: adjusting the stacking position of the aluminum template based on the equipment loading and unloading behavior difficulty value, thereby generating stacking position adjustment data; Step S53: dynamically adjust the optimal aluminum template stacking planning scheme according to the loading and unloading optimization path and the stacking position adjustment data, and construct a dynamic stacking planning adjustment strategy.

9. The stacking planning and control method of architectural aluminum formwork according to claim 1 is characterized in that: The specific steps of step S6 are: Step S61: Acquire multiple preset storage scenes; Step S62: Analyze the scene operation change characteristics of multiple preset storage scenes to generate each storage scene operation characteristic; Step S63: performing multi-scenario transfer learning on the dynamic palletizing planning adjustment strategy according to the operation characteristics of each storage scenario, thereby obtaining multi-scenario palletizing planning parameters; Step S64: fine-tune the adaptive palletizing planning parameters based on the multi-scenario palletizing planning parameters, and build an adaptive aluminum template palletizing planning engine.

10. A stacking planning and control system for building aluminum formwork, characterized in that: The method for executing the stacking planning and control of the building aluminum formwork according to claim 1 comprises: A three-dimensional structure module is used to obtain multi-angle monitoring images of the building aluminum formwork to be stacked, perform visual recognition of structural feature points on the multi-angle monitoring images of the building aluminum formwork, perform three-dimensional morphological point cloud modeling, and construct a three-dimensional structural model of each aluminum formwork; The stacking constraint module is used to obtain the production and operation log of the building aluminum formwork; based on the production and operation log of the building aluminum formwork, the physical state characteristics are analyzed, and the stacking planning constraint law is evolved, so as to obtain the overall stacking planning constraint law of the aluminum formwork; Intelligent stacking planning module, which is used to perform intelligent stacking planning for each aluminum formwork three-dimensional structure model based on the overall stacking planning constraint rules of the aluminum formwork, and to evaluate the optimal stacking planning and extract the optimal aluminum formwork stacking planning scheme; Dynamic loading and unloading simulation module, used to perform dynamic stacking simulation on each aluminum formwork three-dimensional structure model according to the optimal aluminum formwork stacking planning scheme, and perform dynamic loading and unloading simulation to generate the equipment loading and unloading behavior difficulty value and aluminum formwork handling path efficiency; Dynamic palletizing adjustment module, which is used to adjust the dynamic palletizing planning according to the difficulty value of equipment loading and unloading behavior and the efficiency of aluminum template handling path, and build a dynamic palletizing planning adjustment strategy; The multi-scenario migration module is used to perform multi-scenario migration learning on the dynamic palletizing planning adjustment strategy, fine-tune the adaptive palletizing planning parameters, and build an adaptive aluminum template palletizing planning engine.

Images