A BIM-based intelligent processing method and system for water pipes

Abstract

The present invention relates to the technical field of BIM water pipe processing, and specifically to an intelligent water pipe processing method and system based on BIM. The present invention obtains the second pipeline data of the water pipe line data and the water pipe laying and processing plan in the BIM model data, and identifies the abnormal characteristics of the historical water pipe data with abnormalities through the water pipe anomaly matching model and maps them to the second pipeline data; calls the abnormal laying and processing plan in the water pipe laying and processing plan to obtain the first abnormal parameter, optimizes the laying and processing plan of the third pipeline data through the particle swarm optimization model and the first abnormal parameter, and performs water pipe processing according to the optimized plan; through this method, it is possible to perform data mapping on the existing water pipe line data based on the historical water pipe line data with problems, obtain the water pipe line data that may have problems for optimizing the water pipe processing plan, avoid waste of materials and costs during the water pipe processing process, and alleviate the current difficulties in processing management problems.

Description

Technical Field

[0001] The present invention relates to the technical field of BIM water pipe processing, and specifically provides a BIM-based intelligent water pipe processing method and system. Background Art

[0002] BIM technology is a digital management method in the construction field. By converting a building into a three-dimensional virtual model, it can quantify and visualize data for each construction step before construction, facilitating the formulation of corresponding construction plans and management plans, and improving the efficiency of subsequent construction.

[0003] As an indispensable part of a building, the layout of water pipes not only affects the normal use of water facilities in the building after completion, but also has a certain impact on the subsequent progress of the construction process.

[0004] In the actual water pipe construction process, situations such as overly long water pipes, water pipe laying being blocked by other pipelines, and water pipe laying being blocked by other construction materials in the building are likely to occur, resulting in the need for on-site secondary processing of water pipes. Due to the poor accuracy of on-site secondary processing, situations such as the water pipe being cut too short or the water pipe bursting may occur, easily causing a large amount of waste of water pipe materials, increasing costs, and making the processing management of water pipes relatively difficult.

[0005] Therefore, a BIM-based intelligent water pipe processing method and system are proposed. Summary of the Invention

[0006] The purpose of the present invention is to provide a BIM-based intelligent water pipe processing method and system. By obtaining the second pipeline data of the water pipe line data and the water pipe laying and processing plan in the BIM model data, the first pipeline data is generated by marking the historical water pipe line data according to the abnormal line points of the historical water pipe line data; the abnormal characteristics of the first pipeline data are identified by the water pipe anomaly matching model and the second pipeline data is marked; and the abnormal laying and processing plan corresponding to the first pipeline data in the water pipe laying and processing plan is called to obtain the first abnormal parameter. The laying and processing plan of the third pipeline data is optimized by the particle swarm optimization model and the first abnormal parameter, and the water pipe is processed according to the optimized plan. Through this method, the existing water pipe line data can be data-mapped based on the historical water pipe line data with problems, and the water pipe line data that may have problems can be obtained for optimizing the water pipe processing plan, avoiding waste of materials and costs during the water pipe processing process, and alleviating the current processing management difficulties.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A BIM-based intelligent water pipe processing method, including:

[0009] Call the BIM model data of the building, and obtain the water pipe line data and the water pipe laying and processing plan according to the BIM model data;

[0010] Obtain the abnormal line points of the water pipe line data of the historical BIM model data, and generate the first pipeline data by marking the historical water pipe line data according to the abnormal line points; Generate the second pipeline data according to the water pipe line data;

[0011] Further, establish a three-dimensional coordinate system according to the BIM model data of the input water pipe line, where the input water pipe line includes the water pipe line data and the historical water pipe line data; Map the historical water pipe line onto the three-dimensional coordinate system to generate the input water pipe line coordinates; Segment the input water pipe line coordinates to generate an input water pipe line coordinate set;

[0012] Map the three-dimensional coordinate system to a two-dimensional coordinate system, project the coordinates of the input water pipe line coordinate set into the two-dimensional coordinate system to generate an input water pipe line transposed coordinate set; Generate multiple segments of input water pipe line curves according to the coordinates of the input water pipe line transposed coordinate set; The input water pipe line curve includes the second pipeline data and the historical water pipe line;

[0013] If the input water pipe line is the historical water pipe line, transpose the coordinates of the abnormal line points marked by the historical water pipe line coordinates into abnormal line transposed points, and mark multiple segments of the input water pipe line curves according to the abnormal line transposed points to generate the first pipeline data;

[0014] Further, the abnormal line transposed points include multiple groups of data, and every 2 abnormal line transposed points are a group of data;

[0015] Establish a water pipe anomaly matching model, match the data anomaly characteristics of the first pipeline data according to the second pipeline data, and mark the second pipeline data according to the anomaly matching result to generate the third pipeline data and the fourth pipeline data;

[0016] The water pipe anomaly matching model includes a line data compression unit, a line feature extraction unit, a line feature classification unit, and an abnormal line output unit;

[0017] The line data compression unit standardizes and encodes the data of the second pipeline data;

[0018] The line feature extraction unit extracts the data features of the standardized second pipeline data; the line feature extraction unit includes a residual convolutional network, an LSTM network, and a feature fusion layer. The residual convolutional network performs data feature enhancement and morphological feature analysis on the second pipeline data. The LSTM network extracts the trend features of the second pipeline data. The feature fusion layer fuses the data features of the residual convolutional network and the LSTM network;

[0019] Further, the number of residual convolutional networks is 2, the number of LSTM networks is 6, the feature fusion layer is Relu, and the line feature classification unit includes a fully connected layer and a Bayesian classifier;

[0020] The line feature classification unit classifies the features of the second pipeline data according to the feature labels of the first pipeline data, and matches the feature labels of the first pipeline data according to the classification results;

[0021] The abnormal line output unit generates and outputs the feature labels of the second pipeline data;

[0022] Obtain the first target parameter according to the water pipe laying and processing plan; extract the laying and processing plan of the third pipeline data in the water pipe laying and processing plan; call the corresponding abnormal laying and processing plan of the first pipeline data according to the third pipeline data, and extract the first abnormal parameter according to the abnormal laying and processing plan;

[0023] Establish a particle swarm optimization model, and optimize the laying and processing plan of the third pipeline data according to the first target parameter and the first abnormal parameter to generate an abnormal optimized water pipe laying and processing plan;

[0024] Further, set the priority weight for the first target parameter according to the water pipe laying and processing plan, and initialize the velocity and position of the particle swarm with the first target parameter; use the priority weight and the target first abnormal parameter as penalty coefficients, and use the parameters of the water pipe laying and processing plan as target conditions, and iterate the position and velocity of the particle swarm multiple times until the particle swarm reaches the parameters of the water pipe laying and processing plan, and generate the abnormal optimized water pipe laying and processing plan according to the first target parameter corresponding to the optimized particle swarm;

[0025] Further, the priority weight is a cost weight and a length weight, the first target parameter is the number of water pipes and the length of the water pipes; the target first abnormal parameter includes the number of abnormal water pipes and the length of the abnormal water pipes; the parameter of the water pipe laying and processing plan is the total length of the third pipeline data to be optimized;

[0026] Process the water pipes of the third pipeline data according to the abnormal optimized water pipe laying processing plan, and process the fourth pipeline data according to the water pipe laying processing plan;

[0027] The present invention also proposes a BIM-based intelligent water pipe processing system, including a water pipe line acquisition module, an abnormal line acquisition module, an abnormal line matching module, an abnormal parameter extraction module, an abnormal line optimization module, and a normal and abnormal line processing plan generation module; specifically:

[0028] The water pipe line acquisition module acquires the BIM model data of a building, and acquires the water pipe line data and the water pipe laying processing plan according to the BIM model data; generates second pipeline data according to the water pipe line data;

[0029] The abnormal line acquisition module acquires the abnormal line points of the water pipe line data of the historical BIM model data, and generates first pipeline data by marking the historical water pipe line data according to the abnormal line points;

[0030] The abnormal line matching module establishes a water pipe abnormal matching model, matches the data abnormal characteristics of the first pipeline data according to the second pipeline data, marks the second pipeline data according to the abnormal matching result, and generates third pipeline data and fourth pipeline data;

[0031] Further, the water pipe abnormal matching model includes a line data compression unit, a line feature extraction unit, a line feature classification unit, and an abnormal line output unit. The line feature extraction unit includes 2 residual convolutional networks, 6 LSTM networks, and 1 Relu feature fusion layer; the line feature classification unit includes a fully connected layer and a Bayesian classifier;

[0032] The abnormal parameter extraction module obtains the first target parameter according to the water pipe laying processing plan; extracts the laying processing plan of the third pipeline data in the water pipe laying processing plan; calls the corresponding abnormal laying processing plan of the first pipeline data according to the third pipeline data, and extracts the first abnormal parameter according to the abnormal laying processing plan;

[0033] The abnormal line optimization module establishes a particle swarm optimization model, optimizes the laying processing plan of the third pipeline data according to the first target parameter and the first abnormal parameter, and generates an abnormal optimized water pipe laying processing plan;

[0034] The normal and abnormal line processing plan generation module processes the water pipes of the third pipeline data according to the abnormal optimized water pipe laying processing plan, and processes the fourth pipeline data according to the water pipe laying processing plan;

[0035] Further, the abnormal line optimization module includes: setting priority weights for the first target parameters according to the water pipe laying processing plan, and initializing the velocity and position of the particle swarm with the first target parameters; using the priority weights and the target first abnormal parameter as penalty coefficients, and using the parameters of the water pipe laying processing plan as target conditions, iterating the position and velocity of the particle swarm multiple times until the particle swarm reaches the parameters of the water pipe laying processing plan, and generating the abnormal optimized water pipe laying processing plan according to the first target parameters corresponding to the optimized particle swarm.

[0036] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0037] 1. The present invention extracts historical water pipe line data and water pipe line data through BIM model data, reduces the dimension of the data through the established three-dimensional coordinates, generates a two-dimensional curve and marks the abnormal line points of the historical water pipe line data. Through this method, the dimension of the original data can be reduced, the data feature matching of the water pipe line can be carried out through the two-dimensional data, the calculation amount of the data can be reduced from the data dimension, and at the same time, more accurate data can be provided for the subsequent matching of the third pipeline data, improving the accuracy of the third pipeline data matching and providing a data basis for the subsequent water pipe processing plan.

[0038] 2. The present invention uses a water pipe anomaly matching model and adopts a method for analyzing time series data anomalies. By transforming the actual line laying problem into a time series anomaly classification problem, it analyzes the classification matching degree of the water pipe line data after dimension reduction and the historical third pipeline data. Through this method, it can match whether there are lines with difficult line laying in the current building water pipe line compared with the historical water pipe line, so as to determine the positions of the water pipe lines that may have difficult line laying in the current plan, facilitating subsequent plan optimization and analysis, providing a more accurate processing plan for the same problem, and solving the problem of difficult processing management.

[0039] 3. The present invention is based on the particle swarm algorithm. Based on the mined abnormal points of the water pipe lines that may have difficult laying, by taking the water pipe processing parameters as the particle swarm, using the weight of the cost data and the water pipe parameters with the same difficult laying as the penalty function, and taking the cost and the number of water pipes in the laying processing plan as the optimization objectives for optimization. Through this method, various parameters of the difficult water pipe laying mined can be used as empirical data, and at the same time, combined with the cost data, the difficult laying part of the existing plan can be re-formulated to avoid the same water pipe laying difficult problems, and at the same time reduce the cost to form a new plan, so as to solve the problem of difficult processing management. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic flow chart of the method of the present invention;

[0041] Figure 2 A schematic diagram of mapping the three-dimensional coordinate axis of the present invention into a two-dimensional coordinate axis;

[0042] Figure 3 This is a schematic diagram of BIM water pipe line mapping time series data of the present invention;

[0043] Figure 4 Schematic diagram of the flow of the water pipe anomaly matching model of the present invention;

[0044] Figure 5 This is a schematic diagram of the accuracy of the training set and test set of the water pipe anomaly matching model of the present invention;

[0045] Figure 6 Schematic diagram of the loss function of the training set and test set of the water pipe anomaly matching model of the present invention;

[0046] Figure 7 Schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0048] In the process of laying water pipes according to the BIM model, various problems may occur during the construction process, resulting in the water pipes not being laid according to the predetermined laying and processing plan. Workers will cut these water pipes for secondary processing. During the secondary processing, it is easy to increase the material and cost of the water pipes due to problems such as worker errors. The length and thickness of the water pipes are managed according to the plan, but because the above problems often occur, it also makes it difficult to manage the water pipe processing according to the plan. Therefore, a water pipe intelligent processing method based on BIM is proposed. Figure 1 As shown, the technical solution is as follows:

[0049] Calling the BIM model data of the building, and obtaining the water pipe line data and water pipe laying processing plan based on the BIM model data;

[0050] Obtain abnormal line points of the water pipeline line data of the historical BIM model data, mark the historical water pipeline line data according to the abnormal line points to generate first pipeline data; and generate second pipeline data based on the water pipeline line data;

[0051] Build a water pipe anomaly matching model, match the data anomaly features of the first pipeline data based on the second pipeline data, mark the second pipeline data according to the anomaly matching result, and generate the third pipeline data and the fourth pipeline data;

[0052] Obtain the first target parameter according to the water pipe laying and processing plan; extract the laying and processing plan of the third pipeline data in the water pipe laying and processing plan; call the corresponding abnormal laying and processing plan of the first pipeline data according to the third pipeline data, and extract the first abnormal parameter according to the abnormal laying and processing plan;

[0053] Build a particle swarm optimization model, optimize the laying and processing plan of the third pipeline data based on the first target parameter and the first abnormal parameter, and generate an abnormal optimized water pipe laying and processing plan;

[0054] Process the water pipes of the third pipeline data according to the abnormal optimized water pipe laying and processing plan, and process the fourth pipeline data according to the water pipe laying and processing plan.

[0055] Perform anomaly marking on the water pipe line data with problems in the historical water pipe laying and processing plan, and map the abnormal data with problems to the water pipe line data of the current plan through data mapping. To achieve this goal, learn the characteristics of each water pipe line data after anomaly marking through the water pipe anomaly matching model, and at the same time extract the characteristics of the water pipe line data of the current plan. Identify the water pipe lines with the same characteristics in the current plan through the comparison and classification of the two data characteristics; through this method, the model can automatically identify and classify the water pipe lines in the current plan with the same design as the water pipe lines with problems, which is convenient for subsequent optimization of the processing plan and reduces the problem of difficult water pipe processing management.

[0056] Based on the water pipe lines in the current plan identified as having the same characteristics as the problem plan, call the corresponding parameters of the water pipe laying and processing plan with problems through the plan, and compare them with the corresponding parameters of the water pipe lines in the current plan with the same characteristics. Through the particle swarm model, use the water pipe laying and processing plan and the parameters of the water pipe lines with problems as the penalty coefficient and the target condition to optimize the parameters of the water pipe lines in the current plan. Through this method, the parameters of the existing plan can be optimized, and according to the optimized plan, the same plan parameters as the historical problems can be avoided, and the same problems can be prevented from occurring again, reducing the difficulty of water pipe processing management.

[0057] Embodiment 1

[0058] For specific illustration, it will be elaborated in combination with the following embodiments:

[0059] Obtain the BIM model data of a building, and obtain the water pipe line data and the water pipe laying and processing plan based on the BIM model data; obtain the abnormal line points of the water pipe line data of the historical BIM model data, and generate the first pipeline data by marking the historical water pipe line data according to the abnormal line points; generate the second pipeline data based on the water pipe line data; the first pipeline data is the historical abnormal water pipe line data, and the second pipeline data is the target water pipe line data; both the first pipeline data and the second pipeline data are the water pipe routing data of the water pipe in the BIM model.

[0060] Further, establish a three-dimensional coordinate system based on the BIM model data of the input water pipe line, where the input water pipe line includes the water pipe line data and the historical water pipe line data; map the historical water pipe line onto the three-dimensional coordinate system to generate the input water pipe line coordinates; segment the input water pipe line coordinates to generate an input water pipe line coordinate set; the segmentation rule for segmenting the input water pipe line coordinates is determined by the specific use content of the water pipe and the water pipe length. For example, when analyzing the sewer pipe, extract all the sewer pipe line data. For example, when performing data analysis, the line data will be segmented to facilitate subsequent feature extraction. The data segmentation will be divided according to the water pipe processing length during processing. For example, if processing is carried out in 6-meter lengths, it will be segmented in integer multiples of 6. If processing is carried out in 4-meter and 6-meter lengths, it will be segmented according to the least common multiple of 6 and 4; map the three-dimensional coordinate system to a two-dimensional coordinate system, and project the coordinates of the input water pipe line coordinate set into the two-dimensional coordinate system to generate an input water pipe line transposed coordinate set; the mapping of the three-dimensional coordinate system to the two-dimensional coordinate system is as follows Figure 2 shown, and the specific calculation is as follows:

[0061] ;

[0062] Among them, is the x-axis of the mapping of the three-dimensional coordinate system to the two-dimensional coordinate system, x is the x-axis of the three-dimensional coordinate system, and z is the z-axis of the three-dimensional coordinate system. is the y-axis of the mapping of the three-dimensional coordinate system to the two-dimensional coordinate system, y is the y-axis of the three-dimensional coordinate system. is the mapping angle between x and , as shown in Figure 2 in shown. is the mapping angle between y and , as shown in Figure 2 in shown;

[0063] and The sizes of are set according to the specific implementation situation. The direction is consistent with the water flow direction in the water pipe during actual use after the water pipe is laid; the purpose of the consistent water flow direction is to map the water flow direction into the time direction in the time series data; the purpose of this method is to determine the positions of the x-axis and z-axis in the three-dimensional coordinates through the water flow direction, so as to facilitate data unification, convenient for unified data mapping, and avoid data pollution caused by different coordinate system origins and the positions of each coordinate axis; Refer to Figure 3 as shown Figure 3 A in Figure 3 is the three-dimensional water pipe line of the BIM model, and Figure 3 B in

[0064] Generate multiple input water pipe line curves according to the coordinates of the input water pipe line transposed coordinate set; the input water pipe line curves include the second pipeline data and the historical water pipe line;

[0065] If the input water pipe line is the historical water pipe line, transpose the coordinates of the abnormal line points marked by the historical water pipe line coordinates into abnormal line transposed points, and mark multiple input water pipe line curves according to the abnormal line transposed points to generate the first pipeline data;

[0066] By converting the three-dimensional coordinate data of the BIM model into two-dimensional coordinate data, and at the same time based on the characteristics of the water pipe line, based on the characteristics of its two-dimensional coordinate data, it becomes one-dimensional linear data; through this method, the water pipe data of the BIM model can be feature dimensionally reduced, and at the same time, combined with the characteristics of the data itself, the data is changed into one-dimensional data. Through this method, the feature dimension of the original data can be reduced, and the maximum data characteristics of the data can be ensured; at the same time, this data is also convenient for subsequent feature analysis of water pipe data, providing an accurate and reliable data basis for subsequent scheme optimization;

[0067] Furthermore, the abnormal line transposed points include multiple groups of data, and every 2 abnormal line transposed points are a group of data; the abnormal line transposed points are marked according to expert experience, and the 2 abnormal line transposed points of each group of data are the coordinate starting point of the historical abnormal water pipe line and the coordinate ending point of the historical abnormal water pipe line; among them, the coordinate starting point and the coordinate ending point are also divided according to the water pipe processing length during processing. For example, if it is processed at 6 meters, it is set according to 6 meters; the water pipe line data will be marked with 0 for normal data and 1 for abnormal data for feature marking; specifically, different types of data labels can be marked according to the specific implementation situation;

[0068] By taking every two of the abnormal line transposition points as a group of data, the abnormal water pipes are marked, which is convenient for extracting the data of the abnormal water pipe lines, and also convenient for unified data management and data label marking of these abnormal data, facilitating the classification and recognition of subsequent models and the matching of data features, and providing an accurate and reliable data basis for subsequent scheme optimization;

[0069] A water pipe anomaly matching model is established. According to the data anomaly characteristics of the second pipeline data to match the first pipeline data, the second pipeline data is marked according to the anomaly matching result, and the third pipeline data and the fourth pipeline data are generated; the third pipeline data is the abnormal line of the water pipe, and the fourth pipeline data is the normal line of the water pipe;

[0070] The water pipe anomaly matching model includes a line data compression unit, a line feature extraction unit, a line feature classification unit, and an abnormal line output unit, as shown in Figure 4 shown;

[0071] The line data compression unit standardizes and encodes the second pipeline data; the data standardization uses Z-score standardization to compress the data between 0 and 1 to reduce the interference of the data coordinate size on recognition while preserving the data form; the data encoding uses one-hot encoding;

[0072] The line feature extraction unit extracts the data features of the standardized second pipeline data; the line feature extraction unit includes a residual convolutional network, an LSTM network, and a feature fusion layer. The residual convolutional network performs data feature enhancement and morphological feature analysis on the second pipeline data, the LSTM network extracts the trend features of the second pipeline data, and the feature fusion layer fuses the data features of the residual convolutional network and the LSTM network;

[0073] Furthermore, the number of the residual convolutional networks is 2, the number of the LSTM networks is 6, the feature fusion layer is Relu, and the line feature classification unit includes a fully connected layer and a Bayesian classifier; the morphological anomaly features of the time series data converted from the water pipe lines are extracted through the residual convolutional network, and the key anomaly features can be marked to improve the accuracy of anomaly feature recognition; combined with the advantages of LSTM in the trend features of time series data, the trend features of the water pipe lines are recognized to perform anomaly detection in combination with the overall change trend of the water pipe lines, and the similar features between the current water pipe lines and the historical water pipe lines are fully recognized from the dimensions of spatial morphology and trend features, improving the accuracy of abnormal water pipe line recognition;

[0074] In this embodiment, 80,000 water pipe line data are marked in combination with experts, and the training set and the test set are divided according to the ratio of 8:2 for training. The number of iterations is 100. The actual training results of the water pipe anomaly matching model are shown inFigure 5 and Figure 6 as shown Figure 5 are the accuracy data of the training set and the test set Figure 6 are the loss functions of the training set and the test set, and the L1 loss function is adopted for the loss function; in this embodiment, some pipeline data that did not participate in the training were also marked in combination with expert experience. There are a total of 5 groups of data, and each group of data includes 100 water pipe lines. The water pipe data includes abnormal lines and normal lines. Through the model of this embodiment, the real environment is simulated for identification, and the specific identification results are shown in Table 1:

[0075] Table 1 Accuracy of the water pipe anomaly matching model for abnormal lines and normal lines

[0076]

[0077] As can be seen from Table 1, although the accuracy of anomaly recognition is only 85% - 86%, the precision of anomaly recognition is as high as over 90%, and the precision of identifying anomalies is relatively high;

[0078] The line feature classification unit classifies the features of the second pipeline data according to the feature labels of the first pipeline data, and matches the feature labels of the first pipeline data according to the classification results; the abnormal line output unit generates and outputs the feature labels of the second pipeline data;

[0079] By establishing a water pipe anomaly matching model, the dimension-reduced water pipe line data is classified into time-series data. According to the recognition method of the time-series data anomaly recognition model, the abnormal water pipe line data is classified into abnormal time-series data, and the current water pipe line data is classified into unrecognized time-series data. By combining the method of time-series data anomaly detection to detect the feature similarity between the current water pipe line data and the abnormal water pipe line data, the water pipe lines in the current water pipe line data that are the same as the historical abnormal water pipe line data can be identified; through this method, the water pipe lines can be automatically detected for abnormal water pipe lines by the method of time-series data detection, so as to realize the automatic identification of abnormal water pipe lines, provide a water pipe line basis for the optimization of subsequent solutions, facilitate the calling of corresponding parameters to realize solution optimization, and reduce the difficulty of water pipe processing management;

[0080] Obtain the first target parameter according to the water pipe laying and processing plan; extract the laying and processing plan of the third pipeline data in the water pipe laying and processing plan; call the corresponding abnormal laying and processing plan of the first pipeline data according to the third pipeline data, and extract the first abnormal parameter according to the abnormal laying and processing plan; the first abnormal parameter is the water pipe parameter of the historical abnormal water pipe line data; the first target parameter is the water pipe parameter of the target water pipe line data;

[0081] Build a particle swarm optimization model, and optimize the laying and processing plan of the third pipeline data according to the first target parameter and the first abnormal parameter to generate an abnormal optimized water pipe laying and processing plan;

[0082] Furthermore, set the priority weight for the first target parameter with the water pipe laying and processing plan, and initialize the velocity and position of the particle swarm with the first target parameter; use the priority weight and the target first abnormal parameter as penalty coefficients, and use the parameters of the water pipe laying and processing plan as target conditions, and iterate the position and velocity of the particle swarm multiple times until the particle swarm reaches the parameters of the water pipe laying and processing plan, and generate the abnormal optimized water pipe laying and processing plan according to the first target parameter corresponding to the optimized particle swarm;

[0083] Through the particle swarm optimization algorithm, use the corresponding parameters of the abnormal water pipe lines extracted from the historical data as penalty coefficients to avoid the occurrence of the same parameter data in the current plan, use the corresponding parameters of the water pipe lines that are the same as the abnormal water pipe lines in the historical data as the initial data of the particle swarm algorithm, and optimize with the parameters of the water pipe laying and processing plan as the target conditions. Through this method, it is possible to avoid the occurrence of the same problems under the constraints of the existing plan to reduce the difficulty of water pipe processing management;

[0084] Furthermore, the priority weight is the cost weight and the length weight, the first target parameter is the number of water pipes and the length of the water pipes; the target first abnormal parameter includes the number of abnormal water pipes and the length of the abnormal water pipes; the parameter of the water pipe laying and processing plan is the total length of the third pipeline data to be optimized; form a constraint condition based on the cost data of the water pipes as the penalty coefficient, and use the plan content as the optimization target, which can reduce the cost input of the water pipes during the optimization process, and at the same time the optimization result will not exceed the content of the original water pipe design plan, so as to improve the quality and reliability of the optimization result and further reduce the problem of the difficulty of water pipe processing management;

[0085] Process the water pipes of the third pipeline data according to the abnormal optimized water pipe laying and processing plan, and process the fourth pipeline data according to the water pipe laying and processing plan.

[0086] Embodiment 2

[0087] The present invention also proposes a BIM-based intelligent water pipe processing system, including a water pipe line acquisition module, an abnormal line acquisition module, an abnormal line matching module, an abnormal parameter extraction module, an abnormal line optimization module, and a normal and abnormal line processing plan generation module, as shown in Figure 7 shown; specifically:

[0088] A water pipe line acquisition module acquires the BIM model data of a building, and obtains the water pipe line data and the water pipe laying and processing plan according to the BIM model data; generates second pipeline data according to the water pipe line data;

[0089] An abnormal line acquisition module acquires the abnormal line points of the water pipe line data of the historical BIM model data, and generates first pipeline data by marking the historical water pipe line data according to the abnormal line points;

[0090] An abnormal line matching module establishes a water pipe abnormal matching model, matches the data abnormal characteristics of the first pipeline data according to the second pipeline data, and marks the second pipeline data according to the abnormal matching result to generate third pipeline data and fourth pipeline data;

[0091] Further, the water pipe abnormal matching model includes a line data compression unit, a line feature extraction unit, a line feature classification unit and an abnormal line output unit. The line feature extraction unit includes 2 residual convolutional networks, 6 LSTM networks and 1 Relu feature fusion layer; the line feature classification unit includes a fully connected layer and a Bayesian classifier;

[0092] An abnormal parameter extraction module obtains a first target parameter according to the water pipe laying and processing plan; extracts the laying and processing plan of the third pipeline data in the water pipe laying and processing plan; calls the abnormal laying and processing plan of the corresponding first pipeline data according to the third pipeline data, and extracts a first abnormal parameter according to the abnormal laying and processing plan;

[0093] An abnormal line optimization module establishes a particle swarm optimization model, and optimizes the laying and processing plan of the third pipeline data according to the first target parameter and the first abnormal parameter to generate an abnormal optimized water pipe laying and processing plan;

[0094] A normal and abnormal line processing plan generation module processes the water pipes of the third pipeline data according to the abnormal optimized water pipe laying and processing plan, and processes the fourth pipeline data according to the water pipe laying and processing plan;

[0095] Further, the abnormal line optimization module includes: setting a priority weight for the first target parameter according to the water pipe laying and processing plan, and initializing the velocity and position of the particle swarm with the first target parameter; using the priority weight and the target first abnormal parameter as penalty coefficients, and using the parameters of the water pipe laying and processing plan as target conditions, iterating the position and velocity of the particle swarm multiple times until the particle swarm reaches the parameters of the water pipe laying and processing plan, and generating the abnormal optimized water pipe laying and processing plan according to the first target parameter corresponding to the optimized particle swarm;

[0096] In this embodiment, some untrained historical data is used for optimized simulation of processing. The final solutions in the historical data are compared with the solutions after model optimization. There are a total of two groups of data, and the comparison results are shown in Table 2:

[0097] Table 2 Comparison Table of Historical Data Processing Schemes

[0098]

[0099] It can be seen from the optimized solution that the optimized solution is basically the same as the historical final solution, and the optimized solution gives a more reasonable solution. At the same time, cost data is also given, and the cost data is lower than the historical initial solution.

[0100] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent processing method for water pipes based on BIM, characterized in that, Including: Invoking the BIM model data of the building, and obtaining the water pipe line data and the water pipe laying and processing plan according to the BIM model data; Obtaining the abnormal line points of the water pipe line data of the historical BIM model data, and generating the first pipeline data by marking the historical water pipe line data according to the abnormal line points; generating the second pipeline data according to the water pipe line data; Establishing a three-dimensional coordinate system according to the BIM model data of the input water pipe line, where the input water pipe line includes the water pipe line data and the historical water pipe line data; mapping the historical water pipe line onto the three-dimensional coordinate system to generate the input water pipe line coordinates; segmenting the input water pipe line coordinates to generate an input water pipe line coordinate set; Mapping the three-dimensional coordinate system to a two-dimensional coordinate system, projecting the coordinates of the input water pipe line coordinate set into the two-dimensional coordinate system to generate an input water pipe line transposed coordinate set; generating multiple segments of input water pipe line curves according to the coordinates of the input water pipe line transposed coordinate set; the input water pipe line curves include the second pipeline data and the historical water pipe line; if the input water pipe line is the historical water pipe line, transposing the coordinates of the abnormal line points marked by the historical water pipe line coordinates into abnormal line transposed points, and marking multiple segments of the input water pipe line curves according to the abnormal line transposed points to generate the first pipeline data; Establishing a water pipe anomaly matching model, matching the data anomaly characteristics of the first pipeline data according to the second pipeline data, and marking the second pipeline data according to the anomaly matching result to generate the third pipeline data and the fourth pipeline data; The water pipe anomaly matching model includes a line data compression unit, a line feature extraction unit, a line feature classification unit, and an abnormal line output unit; the line data compression unit performs data standardization and data encoding on the second pipeline data; the line feature extraction unit extracts the data features of the standardized second pipeline data; the line feature extraction unit includes a residual convolutional network, an LSTM network, and a feature fusion layer, the residual convolutional network performs data feature enhancement and morphological feature analysis on the second pipeline data, the LSTM network extracts the trend features of the second pipeline data, and the feature fusion layer fuses the data features of the residual convolutional network and the LSTM network; the line feature classification unit classifies the features of the second pipeline data according to the feature labels of the first pipeline data, and matches the feature labels of the first pipeline data according to the classification result; the abnormal line output unit generates and outputs the feature labels of the second pipeline data; Obtaining the first target parameters according to the water pipe laying and processing plan; extracting the laying and processing plan of the third pipeline data in the water pipe laying and processing plan; calling the abnormal laying and processing plan of the corresponding first pipeline data according to the third pipeline data, and extracting the first abnormal parameters according to the abnormal laying and processing plan; the first abnormal parameters are the number of water pipes and the length of the water pipes of the historical abnormal water pipe line data; the first target parameters are the number of water pipes and the length of the water pipes of the target water pipe line data; Establish a particle swarm optimization model, and optimize the laying and processing plan of the third pipeline data according to the first target parameter and the first abnormal parameter to generate an abnormal optimized water pipe laying and processing plan; Process the water pipes of the third pipeline data according to the abnormal optimized water pipe laying and processing plan, and process the fourth pipeline data according to the water pipe laying and processing plan.

2. The intelligent processing method of water pipes based on BIM according to claim 1, characterized in that, The abnormal line transposition points include multiple groups of data, and every 2 abnormal line transposition points are a group of data.

3. A BIM-based intelligent pipe processing method according to claim 1, characterized in that, The number of residual convolutional networks is 2, the number of LSTM networks is 6, the feature fusion layer is Relu, and the line feature classification unit includes a fully connected layer and a Bayesian classifier.

4. A BIM-based intelligent pipe processing method according to claim 1, characterized in that, Establishing a particle swarm optimization model, and optimizing the laying and processing plan of the third pipeline data according to the first target parameter and the target first abnormal parameter to generate an abnormal optimized water pipe laying and processing plan includes: setting a priority weight for the first target parameter according to the water pipe laying and processing plan, and initializing the velocity and position of the particle swarm with the first target parameter; using the priority weight and the target first abnormal parameter as penalty coefficients, and using the parameters of the water pipe laying and processing plan as target conditions, iterating the position and velocity of the particle swarm multiple times until the particle swarm reaches the parameters of the water pipe laying and processing plan, and generating the abnormal optimized water pipe laying and processing plan according to the first target parameter corresponding to the optimized particle swarm.

5. A BIM-based intelligent pipe processing method according to claim 4, characterized in that The priority weights are cost weight and length weight, the first target parameters are the number of water pipes and the length of water pipes; the target first abnormal parameters include the number of abnormal water pipes and the length of abnormal water pipes; the parameter of the water pipe laying and processing plan is the total length of the third pipeline data to be optimized.

6. An intelligent processing system for water pipes based on BIM, characterized in that, Execute a BIM-based intelligent water pipe processing method as described in claim 1, including: A water pipe line acquisition module, which acquires the BIM model data of a building, and acquires the water pipe line data and the water pipe laying and processing plan according to the BIM model data; generates second pipeline data according to the water pipe line data; An abnormal line acquisition module, which acquires the abnormal line points of the water pipe line data of the historical BIM model data, and generates first pipeline data by marking the historical water pipe line data according to the abnormal line points; An abnormal line matching module, which establishes a water pipe abnormal matching model, matches the data abnormal features of the first pipeline data according to the second pipeline data, marks the second pipeline data according to the abnormal matching result, and generates third pipeline data and fourth pipeline data; An abnormal parameter extraction module, which acquires the first target parameter according to the water pipe laying and processing plan; extracts the laying and processing plan of the third pipeline data in the water pipe laying and processing plan; calls the abnormal laying and processing plan of the corresponding first pipeline data according to the third pipeline data, and extracts the first abnormal parameter according to the abnormal laying and processing plan; An abnormal line optimization module, which establishes a particle swarm optimization model, and optimizes the laying and processing plan of the third pipeline data according to the first target parameter and the first abnormal parameter to generate an abnormal optimized water pipe laying and processing plan; The normal and abnormal line processing scheme generation module processes the water pipes of the third pipeline data according to the abnormal optimized water pipe laying processing scheme, and processes the fourth pipeline data according to the water pipe laying processing scheme.

7. The intelligent water pipe processing system based on BIM according to claim 6, characterized in that, The water pipe anomaly matching model includes a line data compression unit, a line feature extraction unit, a line feature classification unit, and an abnormal line output unit. The line feature extraction unit includes 2 residual convolutional networks, 6 LSTM networks, and 1 Relu feature fusion layer; the line feature classification unit includes a fully connected layer and a Bayesian classifier.

8. The intelligent processing system for water pipes based on BIM according to claim 6, characterized in that, The abnormal line optimization module includes: setting priority weights for the first target parameters according to the water pipe laying processing scheme, and initializing the velocity and position of the particle swarm with the first target parameters; using the priority weights and the target first abnormal parameters as penalty coefficients, and using the parameters of the water pipe laying processing scheme as target conditions, iterating the position and velocity of the particle swarm multiple times until the particle swarm reaches the parameters of the water pipe laying processing scheme, and generating the abnormal optimized water pipe laying processing scheme according to the first target parameters corresponding to the optimized particle swarm.

Images