Prefabricated building prefabricated part transportation scheduling system and method

Abstract

The invention relates to the technical field of logistics distribution, and discloses a prefabricated building prefabricated part transportation scheduling system and method.The prefabricated building prefabricated part transportation scheduling method comprises the steps that the shape information of prefabricated parts is coded to obtain numerical feature vectors, carrying out grid processing on the vehicle space structure information to obtain a discretized space unit set; calculating the matching degree of the prefabricated part and the vehicle; analyzing the matching degree of the vehicle based on a deep learning model to obtain an optimal transportation matching scheme of the prefabricated part and the vehicle; according to the method, the matching degree of the prefabricated part and the vehicle space is accurately calculated, so that the vehicle loading space is efficiently utilized. And meanwhile, an intelligent matching mechanism based on deep learning can optimize a combination scheme of the prefabricated part and the vehicle, and the comprehensive transportation cost is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics distribution, and more specifically, it relates to a transportation scheduling system and method for precast components of prefabricated buildings. Background Art

[0002] Prefabricated buildings are an important trend in the current development of the construction industry. The transportation scheduling of precast components is a key link in the entire construction process of prefabricated buildings. Currently, the following technical problems mainly exist in the transportation scheduling of precast components: Due to the diverse shapes and sizes of precast components, the traditional manual matching method is difficult to accurately evaluate the suitability between precast components and transport vehicles, resulting in low vehicle space utilization and high transportation costs. At the same time, precast components often need to be temporarily stored during transportation, but the existing technology lacks a scientific layout method for storage sites. And during the hoisting process of precast components at the construction site, due to the lack of intelligent path planning, there is an easy risk of collision and the hoisting efficiency is not high. Finally, the layout of workstations on the precast component production line often depends on experience for arrangement, lacking a scientific decision-making method supported by data, which affects production efficiency. Summary of the Invention

[0003] The purpose of the present invention is to provide a transportation scheduling system and method for precast components of prefabricated buildings to solve the above problems.

[0004] The present invention provides a transportation scheduling method for precast components of prefabricated buildings, including the following steps: Encoding the shape information of precast components to obtain a numerical feature vector, and performing grid processing on the vehicle space structure information to obtain a set of spatial units; Calculating the matching degree between precast components and vehicles according to the numerical feature vector and the set of spatial units, including size matching degree, weight matching degree, shape matching degree and comprehensive matching degree; Analyzing the matching degree of vehicles based on a deep learning model to obtain the optimal transportation matching plan for precast components and vehicles.

[0005] Further, the size matching degree is calculated by the ratio of the length, width and height of the precast component to the maximum size of the vehicle space, and its calculation method is: ; Wherein, is the size matching degree, , , respectively represent the maximum sizes of the vehicle space in the length, width and height directions, , , are the length, width and height dimensions of the precast component respectively, The function represents taking the minimum value among multiple proportional values within the brackets. The function represents taking the maximum value among multiple proportional values within the brackets.

[0006] Furthermore, the weight matching degree is calculated by the ratio of the weight of the precast component to the vehicle's load-carrying capacity, and its calculation method is: ; Wherein, is the weight matching degree, is the weight of the precast component, is the vehicle's load-carrying capacity. When it means the vehicle can carry the precast component, and the closer the value is to , the higher the matching degree in terms of weight.

[0007] Furthermore, the shape matching degree is obtained by comparing the shape feature vector of the precast component with the set of spatial discrete elements of the vehicle ; the calculation formula for the shape matching degree is: ; Wherein, is the shape matching degree, is the similarity calculation function, which is used to measure the similarity between the shape feature vector and the set of spatial discrete elements of the vehicle . The larger the value, the higher the shape matching degree.

[0008] Furthermore, the dimension matching degree, weight matching degree, and shape matching degree are weighted and calculated to obtain the comprehensive matching degree, and its calculation method is: ; Wherein, , , are the weight coefficients, satisfying .

[0009] Furthermore, the deep learning model includes multiple fully connected layers and an attention mechanism, which are used to learn the relationships between different matching degree features.

[0010] Furthermore, it also includes: Calculating the matching degree between the precast component and the site space, including the dimension matching degree, weight matching degree, shape matching degree, and stability matching degree; Analyzing the matching degree based on the deep learning model to obtain the optimal layout plan of the precast component in the temporary storage site.

[0011] Furthermore, it also includes: Evaluate the feasibility of hoisting precast components, including dimensional feasibility and weight feasibility; Analyze the obstacle information in the hoisting space and mark the risk areas; Plan the hoisting route based on the improved A* algorithm, where the improved A* algorithm takes into account shape matching degree and risk assessment.

[0012] Furthermore, it also includes: Calculate the matching degree between the precast component and the production line station, including dimensional matching degree, weight matching degree and shape matching degree; Analyze the matching degree based on the deep learning model to obtain the optimal layout plan of the precast component on the production line.

[0013] The present invention provides a transportation scheduling system for precast components of an assembled building, which is used to execute the aforementioned transportation scheduling method for precast components of an assembled building, including: A data preprocessing module encodes the shape information of the precast component to obtain a numerical feature vector, and grids the vehicle space structure information to obtain a set of spatial units; A matching degree calculation module calculates the matching degree between the precast component and the vehicle according to the numerical feature vector and the set of spatial units, including dimensional matching degree, weight matching degree, shape matching degree and comprehensive matching degree; An intelligent matching module analyzes the matching degree of the vehicle based on the deep learning model to obtain the optimal transportation matching plan between the precast component and the vehicle.

[0014] The beneficial effects of the present invention are as follows: By accurately calculating the matching degree between the precast component and the vehicle space, the efficient utilization of the vehicle loading space is realized. At the same time, the intelligent matching mechanism based on deep learning can optimize the combination plan of the precast component and the vehicle, reducing the comprehensive transportation cost; By optimizing the temporary storage site layout of the precast component and the hoisting route at the construction site, the number of component handling times and waiting time are reduced; The system can also be applied to the optimization of the automated production line layout in the precast component factory, improving production efficiency and reducing production costs. Description of the Drawings

[0015] Figure 1 is a flowchart of a transportation scheduling method for precast components of an assembled building according to the present invention; Figure 2 is an example of the basic information of the precast component according to the present invention; Figure 3 is an example of the transportation vehicle information according to the present invention; Figure 4 is an example of the calculation of the dimensional matching degree according to the present invention; Figure 5 is an example of the calculation of the weight matching degree according to the present invention; Figure 6 is an example of the shape matching degree calculation of the present invention; Figure 7 is an example of the comprehensive matching degree calculation of the present invention; Figure 8 is an example of the optimal matching result predicted by the deep learning model of the present invention. Detailed implementation manners

[0016] Now, the subject matter described herein will be discussed with reference to example embodiments. It should be understood that discussing these embodiments is only to enable those skilled in the art to better understand and thus implement the subject matter described herein. Without departing from the scope of protection of the content of this specification, changes can be made to the functions and arrangements of the elements discussed. Each example can omit, substitute, or add various processes or components as needed. Additionally, the features described relative to some examples can also be combined in other examples.

[0017] An assembled building precast component transportation scheduling system and method, including the following embodiments: Embodiment 1 An assembled building precast component transportation scheduling method, as Figure 1 shown, includes the following steps: Step 101: Data preprocessing. The obtained shape information of the precast component is converted into a quantifiable numerical feature vector through a specific coding rule ; the shape information of the precast component includes the three-dimensional geometric model, surface features, edge contours, corner point distributions, and non-regularity quantification indexes of the precast component, etc.; among them, the specific coding rule can use common coding methods such as one-hot coding to quantify and represent the shape information; the vehicle space structure information is subjected to grid processing, and the vehicle space is divided into grid cells with uniform sizes to obtain a set of discretized space units .

[0018] Step 102: Matching degree calculation. Calculate the size matching degree between the precast component size and the vehicle space, and its calculation formula is:

[0019] wherein, is the size matching degree, , , respectively represent the maximum sizes of the vehicle space in the length, width, and height directions, , , are the length, width, and height sizes of the precast component respectively, The function represents taking the minimum value among multiple proportional values within the brackets. The function represents taking the maximum value among multiple proportional values within the brackets; by comparing the proportional relationship between the dimensions of the precast component and the corresponding maximum dimensions of the vehicle space, the dimension matching degree is measured, and the value range is between 0 and 1. The larger the value, the higher the dimension matching degree.

[0020] Calculate the weight matching degree , and its calculation formula is:

[0021] Among them, is the weight of the precast component, is the vehicle's load-carrying capacity. When , it means that the vehicle can carry the precast component. The closer the value is to , the higher the matching degree in terms of weight.

[0022] Calculate the shape matching degree , which is obtained by comparing the shape feature vector of the precast component with the set of discrete elements in the vehicle space . The calculation formula for the shape matching degree is:

[0023] Among them, is the similarity calculation function. Select a suitable algorithm according to the actual situation, such as the cosine similarity algorithm, etc., to measure the similarity between the shape feature vector and the set of discrete elements in the vehicle space . The larger the value, the higher the shape matching degree.

[0024] Finally, calculate the comprehensive matching degree , and its calculation formula is:

[0025] Among them, , , are weight coefficients, satisfying , and can be adjusted according to actual needs.

[0026] Step 103: Intelligent matching based on deep learning. Set up a deep neural network model, which receives the matching degree features calculated in step 102 ( , , , ) as input. The network structure of the deep neural network model includes multiple fully connected layers and an attention mechanism, and its mathematical expression is as follows: First, the input feature vector The calculation formula is:

[0027] The calculation expression of the first fully connected layer is:

[0028] Where, represents the output of the first fully connected layer, is the weight matrix, is the bias vector, is the activation function.

[0029] The calculation expression of the attention mechanism is:

[0030]

[0031] Where, represents the attention weight vector, represents the feature representation after being weighted by the attention mechanism, is the attention weight matrix, represents element-wise multiplication, represents the normalization function.

[0032] The calculation expression of the last fully connected layer is:

[0033] Where, is the output matching score, represents the weight matrix of the last layer, represents the bias vector of the last layer.

[0034] The loss function uses the mean squared error:

[0035] Where, represents the mean squared error value, represents the number of training samples, is the true optimal matching result, is the model prediction result.

[0036] For the new precast component and vehicle matching task, input the matching degree features of all possible vehicle and carrier combinations into the trained deep learning model, and select the combination with the highest output score as the final matching result to achieve intelligent matching decision-making.

[0037] Through the above steps, this method can achieve intelligent matching and scheduling of precast components of assembled buildings and transport vehicles, improve the space utilization rate of vehicles, and reduce transportation costs.

[0038] Figures 2 - 8 It is the example data in the actual application of the precast component transportation scheduling system for assembled buildings; Through Figures 2 - 8 , the effect of the precast component transportation scheduling system for assembled buildings in actual application can be obtained; this system calculates the dimension matching degree, weight matching degree, and shape matching degree between precast components and transport vehicles, combines with a deep learning model for intelligent matching, and finally obtains the optimal transportation scheduling plan, improving transportation efficiency and reducing transportation costs and environmental impacts.

[0039] Embodiment 2 Based on Embodiment 1, this embodiment provides a method for layout planning of the temporary storage site of precast components of assembled buildings, including the following steps: Step 201: Data preprocessing. For the obtained shape information of precast components Convert it into a quantifiable numerical feature vector through a specific coding rule . Among them, the specific coding rule needs to be determined in combination with the actual situation of the storage scenario. For example, a topological coding method more suitable for the storage scenario is used to quantitatively represent the shape information. For the site space structure information Perform grid processing, divide the site space into grid cells with uniform sizes, and obtain a set of discretized space units .

[0040] Step 202: Matching degree calculation. Calculate the matching degree between the dimensions of precast components and the site space , and its calculation formula is:

[0041] Among them, , , are the maximum dimensions of the site space in the length, width, and height directions, , , are the length, width, and height dimensions of the precast component. This formula measures the dimension matching degree by comparing the proportional relationship between the dimensions of the precast component in each dimension and the corresponding maximum dimension of the site space, and the value range is between and , and the larger the value, the higher the dimension matching degree.

[0042] Calculate the weight matching degree , and its calculation formula is:

[0043] Among them, is the weight of the precast component, is the site bearing capacity. This formula represents the proportional relationship between the weight of the precast component and the site bearing capacity. When , it means that the site can bear the precast component. The closer the value is to 1, the higher the matching degree in terms of weight.

[0044] Calculate the shape matching degree , which is obtained by comparing the shape feature vector of the precast component with the set of discrete spatial units of the site. Assume that the similarity calculation function is , then the formula for calculating the shape matching degree is:

[0045] The similarity calculation function needs to select an appropriate algorithm according to the characteristics of the storage site space, such as the similarity algorithm based on space filling curve, etc., to measure the similarity between the shape feature vector and the set of discrete spatial units of the site. The larger the value, the higher the shape matching degree.

[0046] Calculate the stability matching degree after the precast component is placed on the site . Considering the relationship between the centroid position of the precast component and the site bearing distribution, assume that the centroid coordinates of the precast component are , and the stability is determined by calculating the distribution of the centroid projection within the site bearing area. Let the stability calculation function be , then the formula for calculating the stability matching degree is:

[0047] Among them, is the set of discrete spatial units of the site, is the site bearing capacity. The function calculates the stability matching degree based on the centroid coordinates, the set of discrete spatial units of the site and the site bearing capacity, and the value range is between and . The larger the value, the higher the stability.

[0048] Finally, calculate the comprehensive matching degree , and its calculation formula is:

[0049] Among them, , , , are the weight coefficients, satisfying , which can be adjusted according to actual needs. This formula combines dimensions, weight, shape, and stability matching degree through weighted summation to obtain an index comprehensively measuring the matching degree between precast components and the site.

[0050] Step 203: Intelligent layout based on deep learning. Set up an intelligent layout model that receives the matching degree features calculated in step 202 ( , , , , ) as input. The network structure includes three fully connected layers, and the calculation expressions for the first and second layers are:

[0051]

[0052] Among them, and represent the outputs of the first and second fully connected layers in the intelligent layout model, is the matching degree feature vector input to the intelligent layout model, , are the weight matrices of the intelligent layout model, , are the bias vectors of the intelligent layout model, is the activation function.

[0053] The calculation expression for the last fully connected layer is:

[0054] Among them, is the output layout score, is the weight matrix of the last fully connected layer of the intelligent layout model, is the bias vector of the last fully connected layer of the intelligent layout model.

[0055] The loss function uses the mean squared error:

[0056] Among them, is the loss value of the intelligent layout model, is the true optimal layout result, is the model prediction result.

[0057] For a new precast component layout task, input the matching degree features of all possible combinations of site positions into the trained intelligent layout model, and select the combination with the highest output score as the final layout result to achieve intelligent layout decision-making.

[0058] Through the above steps, the method can obtain a reasonable layout plan for precast components in the temporary storage site of precast components in prefabricated buildings. Under this plan, the site space is efficiently utilized, and the placement of precast components fully considers factors such as size, weight, shape, and stability, ensuring storage stability.

[0059] Example 3 Based on Example 1, this example provides a method for planning the lifting route of precast components of a prefabricated building at the construction site, including the following steps: Step 301: Data preprocessing. For the obtained shape information of precast components Convert it into a quantifiable numerical feature vector through a specific coding rule . For the lifting space information at the construction site Perform grid processing to obtain a set of discretized space units .

[0060] Step 302: Lifting feasibility assessment. Calculate the feasibility index of the precast component size and the lifting space , and its calculation formula is:

[0061] Among them, , , are the maximum dimensions of the lifting space in the length, width, and height directions, , , are the length, width, and height dimensions of the precast component. This formula determines whether the dimensions of each dimension of the precast component are within the allowable range of the lifting space. 1 indicates that the dimension is feasible, and 0 indicates that it is not feasible.

[0062] Calculate the weight feasibility index , and its calculation formula is:

[0063] Among them, is the weight of the precast component, is the load-bearing capacity of the lifting equipment. This formula determines whether the weight of the precast component is within the load-bearing capacity range of the lifting equipment. 1 indicates that the weight is feasible, and 0 indicates that it is not feasible.

[0064] Calculate the comprehensive feasibility index , and its calculation formula is:

[0065] Among them, , are the weight coefficients, satisfying , which can be adjusted according to actual needs. This formula comprehensively evaluates the feasibility indicators of size and weight through weighted summation to assess the basic feasibility of lifting. If , then the basic lifting is feasible; if , then it is not feasible.

[0066] Step 303: Preparation for path planning. Calculate the shape matching degree , which is obtained by comparing the shape feature vectors of precast components with the set of discrete elements in the lifting space . Assuming that the similarity calculation function is , the formula for calculating the shape matching degree is:

[0067] Analyze the obstacle information in the lifting space, mark the risk areas, and combine the risk area information with to obtain the set of spatial units with risk assessment . The determination of the risk area can be obtained by analyzing the real-time monitoring data and historical accident data of the construction site.

[0068] Step 304: Lifting route planning. Based on the set of spatial units with risk assessment and the shape matching degree , an improved A* algorithm is used for lifting route planning. The improved heuristic function is:

[0069] where is the heuristic function of the original A* algorithm, is the weight coefficient, which can be adjusted. During the planning process, the path with low risk and high shape matching degree is preferred.

[0070] Dynamically adjust the planned path, use edge intelligence collaborative computing to obtain the change information of the construction site in real time (such as newly added obstacles, etc.), re-evaluate the feasibility and risk according to the new information, and adjust the path again.

[0071] Through the above steps, this method can plan a lifting route that conforms to the characteristics of precast components and adapts to the lifting space and lifting equipment carrying capacity of the construction site. This route fully considers the size, weight, shape, and risk factors in the lifting space, effectively reducing safety risks while improving the lifting efficiency.

[0072] Example 4 Based on Example 1, this example provides an optimization method for the layout of an automated production line in a precast component factory of an assembled building, including the following steps: Step 401: Data preprocessing. It is converted into a quantifiable numerical feature vector through specific encoding rules . Information on the spatial capacity of each station on the production line Perform grid processing to obtain a set of discretized spatial units .

[0073] Step 402: Calculate the matching degree. Calculate the matching degree between the size of the prefabricated component and the space of the production line station. , and its calculation formula is:

[0074] in, , , It is the maximum size of the production line workstation space in length, width and height. , , is the length, width and height of the prefabricated component. This formula measures the degree of size matching by comparing the proportional relationship between the dimensions of the prefabricated component and the corresponding maximum dimensions of the production line workstation space. The value range is between 0 and 1. The larger the value, the higher the size matching degree.

[0075] Calculate weight match , and its calculation formula is:

[0076] in, is the weight of the prefabricated component, is the processing capacity of the production line station. This formula expresses the proportional relationship between the weight of the prefabricated component and the processing capacity of the production line station. It means that the workstation can process the prefabricated component. The closer the value is to , indicating a higher degree of match in weight.

[0077] Calculate shape matching , by comparing the shape feature vectors of prefabricated components Discrete unit set with production line workstation space The feature similarity is obtained. Assume that the similarity calculation function is , then the shape matching calculation formula is:

[0078] Similarity calculation function An appropriate algorithm can be selected according to actual conditions, such as the cosine similarity algorithm, which is used to measure the similarity between the shape feature vector and the set of discrete units in the production line station space. The larger the value, the higher the shape matching degree.

[0079] Finally, calculate the comprehensive matching degree , and its calculation formula is:

[0080] wherein, 、 、 are weight coefficients, satisfying , and can be adjusted according to actual needs. This formula combines the size, weight, and shape matching degrees through weighted summation to obtain an index comprehensively measuring the matching degree between the precast component and the production line station.

[0081] Step 403: Optimization of the production line layout based on deep learning. Set up a production line layout optimization model, and the production line layout optimization model receives the matching degree features calculated in Step 402 、 、 、 )as inputs. The forward propagation process of the network is as follows: First, perform non-linear transformation on the input features through multiple fully connected layers:

[0082]

[0083]

[0084] wherein, is the input feature vector of the production line layout optimization model, 、 、 are the outputs of the first, second, and third layers of the production line layout optimization model respectively, 、 、 are the weight matrices of the fully connected layers of the production line layout optimization model, 、 、 are the bias vectors of the fully connected layers of the production line layout optimization model.

[0085] Then, introduce the attention mechanism to calculate the feature weights:

[0086]

[0087]

[0088] wherein, 、 To calculate the attention scores obtained for the nd layer of the production line layout optimization model, is the output of the th layer of the production line layout optimization model, is the total number of layers of the production line layout optimization model, is the transpose of the weight vector in the attention mechanism, is the index variable, represents the exponential operation, and are the weight matrix and bias vector in the attention mechanism of the production line layout optimization model, is the attention weight, is the weighted feature representation of the production line layout optimization model, is function.

[0089] Finally, the layout score is obtained through the output layer:

[0090] where, is the production line layout score, is the weight matrix of the output layer of the production line layout optimization model, is the bias vector of the output layer of the production line layout optimization model; The loss function uses the mean squared error:

[0091] where, is the loss value of the production line layout optimization model, is the predicted score of the model, is the score of the actual optimal layout; The network parameters are optimized through the backpropagation algorithm, and finally a production line layout optimization model that can accurately evaluate the pros and cons of the layout scheme is obtained.

[0092] Through the above steps, this method can obtain an optimized automated production line layout scheme for precast concrete component factories in prefabricated buildings. This scheme realizes a better match based on the characteristics and capabilities of precast components and production line workstations, can improve the automated production efficiency of the factory, and reduce production costs. In terms of improving efficiency, precast components can be more reasonably allocated to each workstation, reducing waiting time and transportation distance, and improving the fluency of the overall production process. In terms of reducing costs, it avoids equipment idleness or overuse caused by unreasonable layout, and reduces energy consumption and equipment wear.

[0093] In at least one embodiment of the present invention, a transportation scheduling system for prefabricated components of an assembled building is provided, which is used to store computer-readable instructions that can execute the aforementioned transportation scheduling method for prefabricated components of an assembled building when the computer-readable instructions are read.

[0094] The embodiments of the present invention have been described above, but these embodiments are not limited to the above specific implementation manners. The above specific implementation manners are merely illustrative rather than restrictive. Under the inspiration of this embodiment, those of ordinary skill in the art can also make more equivalent embodiments in various forms, all of which fall within the protection scope of this embodiment.

Claims

1. A method for transporting and scheduling prefabricated components for assembled buildings, characterized in that: include: The shape information of the prefabricated components is encoded to obtain a numerical feature vector, and the spatial structure information of the vehicle is gridded to obtain a set of spatial units; Calculate the matching degree between the prefabricated component and the vehicle according to the numerical characteristic vector and the set of spatial units, including size matching degree, weight matching degree, shape matching degree and comprehensive matching degree; The matching degree of vehicles is analyzed based on the deep learning model to obtain the optimal transportation matching solution between prefabricated components and vehicles.

2. A method for transporting and dispatching prefabricated components for assembled buildings according to claim 1, characterized in that: The size matching degree is calculated by the ratio of the length, width and height of the prefabricated component to the maximum size of the vehicle space, and the calculation method is: ； in, For size matching, , , Respectively represent the maximum dimensions of the vehicle space in length, width, and height. , , are the length, width and height of the prefabricated component. The function means taking the minimum value among multiple proportion values ​​in brackets. The function takes the maximum value among the multiple proportion values ​​in the brackets.

3. A method for transporting and scheduling prefabricated components for assembled buildings according to claim 1, characterized in that: The weight matching degree is calculated by the ratio of the weight of the prefabricated component to the vehicle carrying capacity, and the calculation formula is: ； in, is the weight matching degree, is the weight of the prefabricated component, is the vehicle carrying capacity, when It means that the vehicle can carry the prefabricated component. The closer the value is to , the higher the match in terms of weight.

4. A method for transporting and dispatching prefabricated components for assembled buildings according to claim 1, characterized in that: The shape matching degree is calculated by comparing the shape feature vectors of the prefabricated components and the vehicle space discrete unit set The feature similarity is obtained; The shape matching calculation formula is: ； in, is the shape matching degree, is a similarity calculation function used to measure the shape feature vector and the vehicle space discrete unit set The larger the value, the higher the shape matching degree.

5. The method for transporting and dispatching prefabricated components for assembled buildings according to claim 1, characterized in that: The size matching degree, weight matching degree and shape matching degree are weighted and calculated to obtain the comprehensive matching degree, which is calculated as follows: ； in, , , is the weight coefficient, satisfying .

6. A method for transporting and scheduling prefabricated components for assembled buildings according to claim 1, characterized in that: The deep learning model includes multiple fully connected layers and attention mechanisms to learn the relationship between features with different matching degrees.

7. A method for transporting and scheduling prefabricated components for assembled buildings according to claim 1, characterized in that: Also includes: Calculate the matching degree between prefabricated components and site space, including size matching degree, weight matching degree, shape matching degree and stability matching degree; The matching degree is analyzed based on a deep learning model to obtain an optimal layout plan for prefabricated components in a temporary storage site.

8. The method for transporting and dispatching prefabricated components for assembled buildings according to claim 1, characterized in that: Also includes: Evaluate the feasibility of lifting precast components, including size feasibility and weight feasibility; Analyze obstacle information in the lifting space and mark risk areas; The lifting route planning is performed based on the improved A* algorithm, wherein the improved A* algorithm takes shape matching and risk assessment into consideration.

9. The method for transporting and dispatching prefabricated components for assembled buildings according to claim 1, characterized in that: Also includes: Calculate the matching degree between prefabricated components and production line stations, including size matching, weight matching and shape matching; The matching degree is analyzed based on a deep learning model to obtain an optimal layout plan for the prefabricated components on the production line.

10. A transport and dispatching system for prefabricated components of assembled buildings, characterized in that: It is used to execute a method for transporting and scheduling prefabricated components for assembled buildings as described in any one of claims 1 to 9, comprising: The data preprocessing module encodes the shape information of the prefabricated components to obtain a numerical feature vector, and grids the vehicle spatial structure information to obtain a set of spatial units; A matching degree calculation module calculates the matching degree between the prefabricated component and the vehicle according to the numerical feature vector and the set of spatial units, including size matching degree, weight matching degree, shape matching degree and comprehensive matching degree; The intelligent matching module analyzes the matching degree of vehicles based on a deep learning model and obtains the optimal transportation matching solution between prefabricated components and vehicles.

Images