Collaborative design optimization method for forward design of water supply and drainage BIM

Abstract

The invention relates to the technical field of water supply and drainage collaborative design, in particular to a collaborative design optimization method for water supply and drainage BIM forward design, and the method comprises the steps: analyzing the difference between the clustering mean value of each clustering cluster and the maximum clustering mean value in all clustering clusters, determining the clustering weight of each clustering cluster at each moment, and combining with the conflict probability to obtain the clustering weight of each clustering cluster; determining a soft conflict risk index; and on the basis of the soft conflict risk indexes and the heating and ventilation pipeline vibration frequencies at all moments within a preset duration before each moment, a decision tree algorithm is adopted to obtain the urgency degree, a multi-objective genetic algorithm is combined for scoring, and the governance titer ratio is determined, so that collaborative design optimization is carried out on the forward design of the water supply and drainage BIM at the current moment. According to the method, the problem that cross-professional logic conflicts are difficult to cover through a single rule engine due to lack of a unified data association framework is solved, and the multi-professional collaborative efficiency and the resource utilization rate in collaborative design optimization of water supply and drainage BIM forward design are improved.

Description

Technical Field

[0001] This application relates to the field of collaborative design technology for water supply and drainage, specifically to a collaborative design optimization method for BIM-based forward design of water supply and drainage. Background Technology

[0002] Collaborative design in BIM-based forward design for water supply and drainage is an important practice in the digital transformation of the construction industry. In the traditional two-dimensional design stage, information from various disciplines is isolated and coordination efficiency is low, which can easily lead to problems such as pipeline collisions and construction rework. With the increasing complexity of building projects and the increasing requirements for green and energy-saving technologies, forward design with BIM technology at its core has become an inevitable trend. Forward design emphasizes full-discipline collaboration based on a three-dimensional model from the scheme stage. It breaks down professional barriers through information integration, and collaborative design is the core support for achieving efficient collaboration among multiple disciplines. Through model information sharing, collaborative design enables precise connection between water supply and drainage systems and building structures, HVAC, and other disciplines, which can improve space utilization and reduce construction costs.

[0003] In the collaborative design optimization of water supply and drainage BIM-based forward design, the insufficient accuracy and depth of conflict detection manifests itself in the fact that traditional tools are relatively mature in detecting geometric hard collisions, but weak in identifying logical soft collisions. These soft collisions include regulatory compliance, system performance inconsistencies, and cross-disciplinary logical conflicts. Existing technologies mainly address these issues through parametric association and dynamic feedback. However, cross-disciplinary logical conflicts are difficult to cover with a single rule engine due to the lack of a unified data association framework. Consequently, this reduces the efficiency and resource utilization of multi-disciplinary collaboration in the collaborative design optimization of water supply and drainage BIM-based forward design. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a collaborative design optimization method for water supply and drainage BIM-based forward design, thereby resolving the existing issues.

[0005] The collaborative design optimization method for water supply and drainage BIM-based forward design in this application adopts the following technical solution:

[0006] One embodiment of this application provides a collaborative design optimization method for water supply and drainage BIM-based forward design, the method comprising the following steps:

[0007] Real-time acquisition of fluid pipeline slope, flow velocity, support sharing rate, construction cost, and HVAC pipeline vibration frequency during the BIM forward design process of water supply and drainage;

[0008] Pipe slope and pipe flow velocity at each time point are grouped into pairs. All pairs within a preset time period before each time point are clustered. Based on the average distribution of all elements in the cluster center of each cluster, the cluster mean of each cluster is determined. The difference between the cluster mean of each cluster and the maximum cluster mean among all clusters is analyzed to determine the cluster weight of each cluster at each time point.

[0009] Based on the differences between the pipe slope and the preset standard slope in each binary group of each cluster at each time point, and the differences between the pipe flow velocity and the preset standard flow velocity, logistic regression analysis is used to obtain the conflict probability of each cluster at each time point, and combined with the cluster weight, the soft conflict risk index of the fluid pipeline at each time point is determined.

[0010] Based on the soft conflict risk index, support sharing rate, and construction cost at all times within a preset time period prior to each time point, a multi-objective genetic algorithm is used to obtain the multi-objective genetic algorithm score of the fluid pipeline at each time point; based on the soft conflict risk index and HVAC pipeline vibration frequency at all times within a preset time period prior to each time point, a decision tree algorithm is used to obtain the urgency, and combined with the multi-objective genetic algorithm score, the treatment cost-effectiveness ratio of the fluid pipeline at each time point is determined.

[0011] By comparing the cost-effectiveness ratio of the fluid pipeline at the current moment with the maximum cost-effectiveness ratio of the pipeline in the preset time period before the current moment, the priority reconstruction value of the fluid pipeline at the current moment is determined, so as to carry out collaborative design optimization of the water supply and drainage BIM forward design at the current moment.

[0012] Preferably, the distance metric used in the clustering process is the Euclidean distance between the tuples.

[0013] Preferably, the cluster mean of each cluster is the average of the normalized values ​​of the pipe slope and the normalized values ​​of the pipe flow velocity within the cluster center of each cluster.

[0014] Preferably, the clustering weight of each cluster at each time point is the ratio of the cluster mean of each cluster at each time point to the maximum cluster mean among all clusters.

[0015] Preferably, the method for obtaining the conflict probability of each cluster at each time point is as follows:

[0016] At each time point, in each cluster, the difference between the pipe slope and the preset standard slope and the difference between the pipe velocity and the preset standard velocity in each pair are calculated and denoted as the first deviation and the second deviation, respectively. The first deviation and the second deviation of all pairs in each cluster are used as inputs to the logistic regression analysis algorithm, and the output probability value is used as the conflict probability of each cluster at each time point.

[0017] Preferably, the method for determining the soft conflict risk index of the fluid pipeline at each time point is as follows:

[0018] Calculate the product of the clustering weight and the conflict probability of each cluster at each time step, and sum the products of all clusters at each time step as the soft conflict risk index of the fluid pipeline at each time step.

[0019] Preferably, the acquisition of urgency includes:

[0020] Historical soft conflict risk indices and historical HVAC duct vibration frequencies are obtained and used as inputs to a decision tree. Priority labels are set as urgent and deferred, and the decision tree is trained.

[0021] The soft conflict risk index and HVAC duct vibration frequency of all moments within a preset time period before each moment are used as input to the trained decision tree. The proportion of the number of leaf nodes with all emergency labels in the total number of leaf nodes is counted, and the proportion is used as the urgency of the fluid pipeline at each moment.

[0022] Preferably, the cost-effectiveness ratio of the fluid pipeline at each time point is the ratio of the multi-objective genetic algorithm score to the urgency of the fluid pipeline at each time point.

[0023] Preferably, the expression for the priority reconstruction value of the fluid pipeline at the current moment is: In the formula, Y represents the priority reconstruction value of the fluid pipeline at the current moment; B represents the cost-effectiveness ratio of the fluid pipeline at the current moment; B max This represents the maximum value among all the treatment cost-effectiveness ratios of the fluid pipeline within the preset time period prior to the current moment.

[0024] Preferably, the collaborative design optimization of the water supply and drainage BIM forward design at the current moment includes:

[0025] If the priority reconstruction value of the fluid pipeline at the current moment is greater than the preset first threshold, then the pipeline route will be reconstructed.

[0026] If the priority reconstruction value of the fluid pipeline at the current moment is between the preset second threshold and the preset first threshold, or the priority reconstruction value is equal to the preset second threshold, or the priority reconstruction value is equal to the preset first threshold, then cross-professional parameter linkage is executed, where the preset second threshold is less than the preset first threshold;

[0027] If the priority reconstruction value of the fluid pipeline at the current moment is less than the preset second threshold, the rule base will be iteratively updated.

[0028] This application has at least the following beneficial effects:

[0029] This application addresses the problem of insufficient quantification of logical soft conflicts by traditional methods. It employs fuzzy clustering analysis and logistic regression to map parameters such as pipe slope and flow velocity to risk levels, constructing a soft conflict risk index. This quantifies the comprehensive risk caused by deviations in collaborative design parameters, solving the problem of difficulty in accurately identifying hidden soft conflicts, reducing construction rework and maintenance risks, and thus improving the efficiency and resource utilization of multi-disciplinary collaboration in the collaborative design optimization of water supply and drainage BIM-based forward design. Furthermore, this application addresses the difficulty in balancing cross-disciplinary logical conflicts and multi-objective constraints by using a multi-objective genetic algorithm to quantify the comprehensive optimization potential of design schemes. Combined with decision tree analysis to assess the urgency of the problem, the application ultimately calculates the cost-effectiveness ratio of the remediation, eliminating the limitations of single-objective optimization and reflecting the global optimization potential under unit improvement costs. This approach enables a scientific assessment of the benefits of optimized resource input, effectively solving the challenges of traditional methods in balancing multi-objective constraints, quantifying optimization potential, and prioritizing tasks. This improves the efficiency and quality of collaborative design, thereby enhancing the multi-disciplinary collaborative efficiency and resource utilization in the collaborative design optimization of water supply and drainage BIM forward design. Furthermore, by comparing the current cost-effectiveness ratio with historical best values, this application quantifies the urgency and potential of design improvements and dynamically adjusts optimization strategies accordingly. This achieves data-driven, adaptive collaborative optimization decision-making, effectively addressing the problems of traditional methods relying on single rules and lacking dynamic adjustment basis. It significantly improves design efficiency and problem-solving capabilities, further enhancing the multi-disciplinary collaborative efficiency and resource utilization in the collaborative design optimization of water supply and drainage BIM forward design. Attached Figure Description

[0030] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 A flowchart illustrating the steps of a collaborative design optimization method for water supply and drainage BIM-based forward design, as provided in one embodiment of this application;

[0032] Figure 2 This is a schematic diagram of the governance cost-effectiveness extraction process provided in one embodiment of this application. Detailed Implementation

[0033] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a collaborative design optimization method for water supply and drainage BIM forward design proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0034] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0035] The following, in conjunction with the accompanying drawings, details the specific scheme of the collaborative design optimization method for water supply and drainage BIM forward design provided in this application.

[0036] This application provides an embodiment of a collaborative design optimization method for water supply and drainage BIM-based forward design. Specifically, it provides the following collaborative design optimization method for water supply and drainage BIM-based forward design. Please refer to [link to relevant documentation]. Figure 1 The method includes the following steps:

[0037] Step S1: Real-time acquisition of pipe slope, pipe velocity, support sharing rate, construction cost, and HVAC pipe vibration frequency during the water supply and drainage BIM forward design process.

[0038] In the forward design process of water supply and drainage BIM, the Revit API secondary development was used to collect pipe slope, the EPANET dynamic link library was used to generate pipe flow velocity, the IFC standard parsing engine was used to extract the support sharing rate, the construction cost was calculated based on the mapping between the bill of quantities and BIM model parameters, and the vibration frequency of HVAC pipes at the HVAC sensor data interface was obtained. Among these, all data acquisition frequencies were set to f, and all data acquisition was real-time and synchronous. Furthermore, in order to eliminate the influence of data dimensions, the five types of data collected were normalized respectively.

[0039] It should be noted that the data acquisition frequency f is set manually. In this embodiment, the data acquisition frequency f is 1 min / time. In actual applications, as other implementation methods, implementers can also set it according to specific circumstances. This embodiment does not impose any special restrictions.

[0040] Furthermore, it should be noted that there are many commonly used normalization methods. In this embodiment, the z-score normalization method is used to normalize the data. In practical applications, as other implementation methods, implementers may also use other normalization methods such as the maximum-minimum normalization method according to specific circumstances. This embodiment does not impose any special restrictions on the selection of normalization methods.

[0041] Among them, z-score normalization is a well-known technique, and the specific process of using it to normalize data will not be elaborated here.

[0042] It should be noted that the following analysis uses normalized data values, and the names are consistent with the original data names. In this embodiment, all content involving normalization processing adopts the z-score standardization method.

[0043] Step S2: Form pairs of pipe slope and pipe flow velocity at each time point. Cluster all pairs within a preset time period before each time point. Determine the cluster mean of each cluster based on the average distribution of all elements within the cluster center of each cluster. Analyze the difference between the cluster mean of each cluster and the maximum cluster mean among all clusters to determine the cluster weight of each cluster at each time point. Based on the differences between the pipe slope and the preset standard slope and the pipe flow velocity and the preset standard flow velocity within each pair of each cluster at each time point, use logistic regression analysis to obtain the conflict probability of each cluster at each time point. Combined with the cluster weights, determine the soft conflict risk index of the fluid pipeline at each time point.

[0044] In the collaborative optimization process of BIM-based forward design for water supply and drainage, traditional methods rely excessively on geometric hard collision detection. They lack quantitative analysis of logical soft conflicts such as insufficient drainage slope leading to flow velocity lower than self-cleaning capacity, and contradictions in system performance such as pipeline vibration transmission risk. This makes it difficult to accurately identify hidden risks during the design phase, which can easily lead to construction rework and maintenance hazards.

[0045] Therefore, in order to quantitatively analyze and identify those hard-to-capture logical soft conflicts and reduce the maintenance risks of construction rework, this embodiment forms a pair of pipe slope and pipe flow velocity at each time point. All pairs within a preset time period before each time point are clustered. Based on the average distribution of all elements within the cluster centers of each cluster, the cluster mean of each cluster is determined. The difference between the cluster mean of each cluster and the maximum cluster mean among all clusters is analyzed to determine the cluster weight of each cluster at each time point. Based on the differences between the pipe slope and the preset standard slope, and the differences between the pipe flow velocity and the preset standard flow velocity within each pair of each cluster at each time point, logistic regression analysis is used to obtain the conflict probability of each cluster at each time point. Combined with the cluster weights, the soft conflict risk index of the fluid pipeline at each time point is determined, specifically:

[0046] (1) In this embodiment, for all binary pairs clustered within a preset time period before each time point, the cluster mean of each cluster is determined based on the average distribution of all elements within the cluster center of each cluster, specifically as follows:

[0047] As one implementation method, in this embodiment, the pipe slope and pipe flow velocity at each time point are grouped into pairs, and all pairs within a preset time period before each time point are clustered. The metric distance is the Euclidean distance between the pairs. In this embodiment, in order to correspond to high risk, medium risk and low risk levels, the number of clusters k=3 is set, and three clusters are output to identify pipe segment clusters with similar soft conflict characteristics.

[0048] It should be noted that there are many commonly used clustering algorithms. In this embodiment, the k-means clustering algorithm is used to cluster the binary tuples. In practical applications, as other implementation methods, implementers may also choose other clustering algorithms such as fuzzy C-means clustering according to specific circumstances. This embodiment does not impose any special restrictions on the selection of clustering algorithms.

[0049] The k-means clustering algorithm and the Euclidean distance calculation method are both well-known techniques. In this embodiment, the specific process of using the k-means clustering algorithm to cluster binary groups and the Euclidean distance calculation process will not be described in detail.

[0050] It should be noted that the preset duration is set manually. In this embodiment, the preset duration is 30 days. In actual applications, as other implementation methods, implementers can also set it according to specific circumstances. This embodiment does not impose any special restrictions.

[0051] (2) Further, in this embodiment, based on the average distribution of all elements within the cluster centers of each cluster, the cluster mean of each cluster is determined, the difference between the cluster mean of each cluster and the maximum cluster mean among all clusters is analyzed, and the cluster weight of each cluster at each time point is determined, specifically as follows:

[0052] In this embodiment, the mean of the normalized values ​​of the pipe slope and the pipe flow velocity within the cluster center of each cluster is used as the cluster mean of each cluster.

[0053] Based on the cluster mean of each cluster, it can be understood that the slope and flow velocity of a single pipe are key parameters for measuring the rationality of its design. The slope affects drainage capacity, and the flow velocity affects hydraulic efficiency and pipe wear. Directly using the pipe slope or flow velocity for unilateral judgment makes it difficult to grasp the overall trend. Therefore, by calculating the mean of the normalized pipe slope value and the normalized pipe flow velocity value in each binary group in each cluster, the characteristics of the overall design status of the cluster are characterized. The larger the cluster mean, the greater the degree to which the design parameters of the pipes in the corresponding cluster deviate from the ideal state or specification requirements, thus reflecting the overall severity of the potential soft conflict risk or design defects of the corresponding cluster.

[0054] Furthermore, the ratio of the cluster mean of each cluster at each time step to the maximum cluster mean among all clusters is used as the cluster weight of each cluster at each time step.

[0055] Based on the cluster weights of each cluster at each time point, it can be understood that the cluster weights reflect the overall severity or representativeness of a pipeline segment cluster with a specific risk level relative to the pipeline segment cluster with the highest risk level. A higher cluster mean indicates a higher risk for the cluster. Therefore, in this embodiment, the cluster with the largest cluster mean is designated as a high-risk cluster, the cluster with the smallest cluster mean is designated as a low-risk cluster, and the remaining cluster is designated as a medium-risk cluster. The closer the ratio of the current cluster's cluster mean to the largest cluster mean among all clusters is to 1, the higher the risk level of the current cluster. Therefore, a higher cluster weight indicates a greater overall severity of the current pipeline segment cluster relative to the pipeline segment cluster with the highest risk level.

[0056] Conversely, the further the ratio of the current cluster mean to the maximum cluster mean among all clusters is from 1, that is, the smaller the ratio between cluster means, the lower the risk level of the current cluster. Therefore, the smaller the corresponding cluster weight, the less severe the overall situation of the current pipeline cluster compared to the pipeline cluster with the highest risk level.

[0057] (3) Further, in this embodiment, based on the differences between the pipe slope and the preset standard slope within each binary tuple of each cluster at each time point, and the differences between the pipe flow velocity and the preset standard flow velocity, logistic regression analysis is used to obtain the conflict probability of each cluster at each time point, specifically:

[0058] In this embodiment, at each time point, the difference between the pipe slope and the preset standard slope, and the difference between the pipe velocity and the preset standard velocity are calculated in each tuple within each cluster. These are denoted as the first deviation and the second deviation, respectively. The first deviation and the second deviation of all tuples in each cluster are used as inputs to the logistic regression analysis algorithm. The regularization coefficient is set to 1.0. The output probability value is used as the conflict probability of each cluster at each time point to characterize the possibility of soft conflict in a single pipe segment. The higher the conflict probability, the greater the possibility of soft conflict in a single pipe segment. Conversely, the lower the conflict probability, the lower the possibility of soft conflict in a single pipe segment.

[0059] It should be noted that the preset standard slope and preset standard flow velocity are both set manually. In this embodiment, the preset standard slope is 25° and the preset standard flow velocity is 0.75m / s. In actual applications, as other implementation methods, implementers can also set them according to specific circumstances. This embodiment does not impose any special restrictions.

[0060] Logistic regression analysis is a well-known technique, and the specific process of using it to predict probabilities will not be elaborated here.

[0061] (4) Further, this embodiment determines the soft conflict risk index of the fluid pipeline at each time point based on the conflict probability and the clustering weight, specifically as follows:

[0062] Calculate the product of the clustering weight and the conflict probability of each cluster at each time step, and sum the products of all clusters at each time step as the soft conflict risk index of the fluid pipeline at each time step.

[0063] Based on the soft conflict risk index of fluid pipelines at various times, it can be understood that the soft conflict risk index is used to characterize the overall severity of the regulatory compliance risk and system performance contradiction caused by deviations in water supply and drainage design parameters. The larger the soft conflict risk index, the more likely there are multiple high-probability soft conflicts in the entire water supply and drainage system, the higher the possibility of design deviations from specifications and optimal performance, and the greater the need for attention and optimization. Therefore, if the cluster weight of the current cluster is larger, it indicates that the cluster occupies a more important position in the soft conflict risk. The larger the cluster weight, the closer the slope and flow velocity of the current cluster are to the high-risk state, and thus the larger the corresponding soft conflict risk index. At the same time, if the conflict probability of the current cluster is larger, it indicates that the possibility of soft conflicts in the water supply and drainage system is higher, and thus the corresponding soft conflict risk index is larger.

[0064] Conversely, the smaller the cluster weight, the less important the cluster is in terms of soft conflict risk. Its design parameters, such as pipe slope and flow velocity, are closer to safe or standard conditions, contributing less to the overall risk index, thus resulting in a lower soft conflict risk index. Simultaneously, the lower the conflict probability of the cluster, the lower the likelihood of soft conflict. Even with some deviations in its design parameters, the actual risk of problems is lower, leading to a lower soft conflict risk index. Both scenarios reflect that the cluster's design is more in line with specifications, with a lower risk of serious soft conflict. Therefore, it has a relatively lower priority in overall risk assessment and optimization.

[0065] Thus, this embodiment uses cluster analysis of the pipe slope and flow velocity pairs, combined with logistic regression to assess the probability of conflict caused by deviation, and introduces weights to distinguish risk levels, thereby quantifying and identifying soft conflict risks that are difficult to capture by traditional methods, improving design compliance and system performance, reducing construction rework and maintenance risks, and thereby improving the efficiency of multi-disciplinary collaboration and resource utilization in the collaborative design optimization of water supply and drainage BIM positive design.

[0066] Step S3: Based on the soft conflict risk index, support sharing rate, and construction cost at all times within a preset time period prior to each time, a multi-objective genetic algorithm is used to obtain the multi-objective genetic algorithm score of the fluid pipeline at each time. Based on the soft conflict risk index and HVAC pipeline vibration frequency at all times within a preset time period prior to each time, a decision tree algorithm is used to obtain the urgency, and combined with the multi-objective genetic algorithm score, the treatment cost-effectiveness ratio of the fluid pipeline at each time is determined.

[0067] Due to cross-disciplinary logical conflicts in the collaborative optimization of water supply and drainage BIM forward design, such as when pipes and HVAC pipes share supports, the vibration of HVAC equipment may be transmitted to water supply and drainage pipes, affecting their stability or function. These cross-disciplinary logical conflicts, as well as the multiple objectives that the design needs to meet, such as reducing components, saving space, ensuring functionality, or complying with specifications, are difficult to balance and handle effectively by traditional methods. Therefore, traditional methods cannot systematically quantify optimization potential and formulate priorities.

[0068] Therefore, in order to systematically quantify and evaluate the improvement potential of the design scheme, this embodiment uses a multi-objective genetic algorithm to obtain the multi-objective genetic algorithm score of the fluid pipeline at each time point based on the soft conflict risk index, support sharing rate, and construction cost at all times within a preset time period prior to each time point; based on the soft conflict risk index and HVAC pipeline vibration frequency at all times within a preset time period prior to each time point, a decision tree algorithm is used to obtain the urgency, and combined with the multi-objective genetic algorithm score, the cost-effectiveness ratio of the fluid pipeline at each time point is determined, specifically:

[0069] First, this embodiment uses a multi-objective genetic algorithm to obtain the multi-objective genetic algorithm score of the fluid pipeline at each time point based on the soft conflict risk index, support sharing rate, and construction cost at all times within a preset time period prior to each time point. Specifically:

[0070] In this embodiment, the soft conflict risk index, stent sharing rate, and construction cost at all times within a preset time period before each time point are used as inputs to the multi-objective genetic algorithm. In this embodiment, the population size is set to 200, the number of iterations is 500, the crossover rate is 0.8, the mutation rate is 0.1, and the multi-objective genetic algorithm score is output. The higher the multi-objective genetic algorithm score, the greater the comprehensive optimization potential.

[0071] Among them, the multi-objective genetic algorithm is a well-known technology, and its specific principles will not be elaborated here.

[0072] Furthermore, this embodiment uses a decision tree algorithm to obtain the urgency level based on the soft conflict risk index and HVAC duct vibration frequency at all times within a preset time period prior to each time point. Specifically:

[0073] In this embodiment, historical soft conflict risk index and historical HVAC duct vibration frequency are obtained and used as input to the decision tree. The maximum depth is set to 5, the minimum sample split is set to 20, the information gain criterion is the Gini coefficient, and the priority labels are set to urgent and deferred. The urgent label is set to 1 and the deferred label is set to 0. The decision tree is then trained.

[0074] The soft conflict risk index and HVAC duct vibration frequency of all moments within a preset time period before each moment are used as input to the trained decision tree. The proportion of the number of leaf nodes with all emergency labels in the total number of leaf nodes is counted, and the proportion is used as the urgency of the fluid pipeline at each moment.

[0075] The training of decision trees and decision tree algorithms are well-known technologies, and their specific training processes and principles will not be elaborated here.

[0076] Furthermore, based on the urgency and the multi-objective genetic algorithm score, the cost-effectiveness ratio of the fluid pipeline at each time point is determined, specifically as follows:

[0077] In this embodiment, the ratio of the multi-objective genetic algorithm score to the urgency of the fluid pipeline at each time point is used as the cost-effectiveness ratio of the fluid pipeline at each time point.

[0078] Preferably, the schematic diagram of the treatment efficacy ratio extraction process provided in this embodiment is as follows: Figure 2 As shown.

[0079] Based on the governance cost-effectiveness ratio of the fluid pipeline at each time point, it can be understood that the governance cost-effectiveness ratio is used to measure the comprehensive benefits that can be brought about by investing optimization resources to solve the current urgent problem. The higher the multi-objective genetic algorithm score of the fluid pipeline at the current time point, the higher the comprehensive optimization potential of the current design scheme. It can achieve a better balance among multiple objectives such as conflict risk control, cost saving and space utilization, and obtain greater overall benefits. Therefore, the corresponding governance cost-effectiveness ratio is higher. At the same time, if the urgency is lower, it reflects that the problem faced by the current pipeline segment or design scheme is not urgent and can be dealt with later. In this case, even if the multi-objective genetic algorithm score is not high, the corresponding governance cost-effectiveness ratio is still high because the urgency is very low. This indicates that this is an ideal optimization object with great optimization potential and low risk.

[0080] Conversely, if the multi-objective genetic algorithm score of the fluid pipeline is smaller at the current moment, it indicates that the overall optimization potential of the current design scheme is lower, the balance between multiple objectives such as conflict risk control, cost saving, and space utilization is poor, and the overall benefits it can bring are limited. Therefore, the corresponding governance cost-effectiveness ratio is lower. At the same time, if the urgency is higher, it reflects that the problem faced by the current pipeline section or design scheme is very urgent and needs to be addressed first. In this case, even if the multi-objective genetic algorithm score is acceptable, the denominator is increased due to the high urgency, so the corresponding governance cost-effectiveness ratio is still very low. This indicates that this is an optimization object with relatively low optimization potential and urgent risks. Resources should be invested first to reduce its risks rather than pursuing its potential optimization benefits.

[0081] Thus, this embodiment quantifies the comprehensive optimization potential of the design scheme through a multi-objective genetic algorithm, combines decision tree analysis to assess the urgency of the problem, and finally calculates the governance cost-effectiveness ratio. This achieves a scientific evaluation of the benefits of optimizing resource input, effectively solving the problem that traditional methods struggle to balance multi-objective constraints, quantify optimization potential, and prioritize tasks. This improves the efficiency and quality of collaborative design, thereby enhancing the multi-disciplinary collaboration efficiency and resource utilization in the collaborative design optimization of water supply and drainage BIM forward design.

[0082] Step S4: Compare the treatment cost-effectiveness ratio of the fluid pipeline at the current moment with the maximum treatment cost-effectiveness ratio in the preset time period before the current moment, and determine the priority reconstruction value of the fluid pipeline at the current moment, so as to carry out collaborative design optimization of the water supply and drainage BIM forward design at the current moment.

[0083] The lack of a cross-disciplinary data association framework in the forward design of water supply and drainage BIM, coupled with insufficient accuracy in identifying logical soft conflicts, leads to low efficiency in collaborative design and high rates of construction rework. Traditional methods rely on a single rule engine, which is insufficient to cover multi-objective optimization needs, and dynamic adjustments lack quantitative basis, resulting in frequent problems such as pipeline co-laying conflicts and insufficient drainage slope, which seriously affect project costs and schedules.

[0084] Therefore, an improvement strategy needs to be designed based on the cost-effectiveness ratio (B) of the fluid pipeline treatment. In this embodiment, the priority reconstruction value of the fluid pipeline at the current moment is determined by comparing the cost-effectiveness ratio of the fluid pipeline at the current moment with the maximum cost-effectiveness ratio of the fluid pipeline in a preset period before the current moment. This is to perform collaborative design optimization on the water supply and drainage BIM forward design at the current moment. Specifically:

[0085] As one implementation method, in this embodiment, the expression for the priority reconstruction value of the fluid pipeline at the current moment is: In the formula, Y represents the priority reconstruction value of the fluid pipeline at the current moment; B represents the cost-effectiveness ratio of the fluid pipeline at the current moment; B maxThis represents the maximum value among all the treatment cost-effectiveness ratios of the fluid pipeline within the preset time period prior to the current moment.

[0086] It should be noted that the preset time period length is set manually. In this embodiment, the preset time period length is 30 days. In actual application, as other implementation methods, implementers can also set it according to specific circumstances. This embodiment does not impose any special restrictions.

[0087] Furthermore, if the priority reconstruction value of the fluid pipeline at the current moment is greater than the preset first threshold, then the pipeline route is reconstructed;

[0088] If the priority reconstruction value of the fluid pipeline at the current moment is between the preset second threshold and the preset first threshold, or the priority reconstruction value is equal to the preset second threshold, or the priority reconstruction value is equal to the preset first threshold, then cross-professional parameter linkage is executed, where the preset second threshold is less than the preset first threshold;

[0089] If the priority reconstruction value of the fluid pipeline at the current moment is less than the preset second threshold, the rule base is iteratively updated. The rule base is a set of business rules that store water supply and drainage design compliance standards, cross-professional coordination logic and optimization strategies. In the embodiment, when the priority reconstruction value is low, it indicates that the current design state is better. There is no need to directly modify the model. Instead, the rule base is updated, such as by adding or adjusting rules, to accumulate knowledge for subsequent optimization.

[0090] It should be noted that the values ​​of the preset first threshold and the preset second threshold are set manually. In this embodiment, the value of the preset first threshold is 0.8 and the value of the preset second threshold is 0.5. In actual application, as other implementation methods, implementers can also set them according to specific circumstances. This embodiment does not impose any special restrictions.

[0091] Thus, this embodiment, by comparing the current cost-effectiveness ratio with the historical best value, quantitatively assesses the urgency and potential of design improvement, and dynamically adjusts the optimization strategy accordingly. This achieves data-driven, adaptive collaborative optimization decision-making, effectively solving the problems of traditional methods relying on single rules and lacking dynamic adjustment basis. It significantly improves design efficiency and problem-solving capabilities, thereby enhancing the multi-disciplinary collaboration efficiency and resource utilization in the collaborative design optimization of water supply and drainage BIM forward design.

[0092] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments of this specification have been described above. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0093] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0094] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them; modifications to the technical solutions described in the foregoing embodiments, or equivalent substitutions of some of the technical features, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A collaborative design optimization method for water supply and drainage BIM-based forward design, characterized in that, The method includes the following steps: Real-time acquisition of fluid pipeline slope, flow velocity, support sharing rate, construction cost, and HVAC pipeline vibration frequency during the BIM forward design process of water supply and drainage; Pipe slope and pipe flow velocity at each time point are grouped into pairs. All pairs within a preset time period before each time point are clustered. Based on the average distribution of all elements in the cluster center of each cluster, the cluster mean of each cluster is determined. The difference between the cluster mean of each cluster and the maximum cluster mean among all clusters is analyzed to determine the cluster weight of each cluster at each time point. Based on the differences between the pipe slope and the preset standard slope in each binary group of each cluster at each time point, and the differences between the pipe flow velocity and the preset standard flow velocity, logistic regression analysis is used to obtain the conflict probability of each cluster at each time point, and combined with the cluster weight, the soft conflict risk index of the fluid pipeline at each time point is determined. Based on the soft conflict risk index, support sharing rate, and construction cost at all times within a preset time period prior to each time point, a multi-objective genetic algorithm is used to obtain the multi-objective genetic algorithm score of the fluid pipeline at each time point; based on the soft conflict risk index and HVAC pipeline vibration frequency at all times within a preset time period prior to each time point, a decision tree algorithm is used to obtain the urgency, and combined with the multi-objective genetic algorithm score, the treatment cost-effectiveness ratio of the fluid pipeline at each time point is determined. By comparing the cost-effectiveness ratio of the fluid pipeline at the current moment with the maximum cost-effectiveness ratio of the pipeline in the preset time period before the current moment, the priority reconstruction value of the fluid pipeline at the current moment is determined, so as to carry out collaborative design optimization of the water supply and drainage BIM forward design at the current moment.

2. The collaborative design optimization method for water supply and drainage BIM-based forward design as described in claim 1, characterized in that, In the clustering process, the distance metric is the Euclidean distance between the pairs.

3. The collaborative design optimization method for water supply and drainage BIM-based forward design as described in claim 1, characterized in that, The cluster mean of each cluster is the average of the normalized values ​​of the pipe slope and the normalized values ​​of the pipe velocity within the cluster center of each cluster.

4. The collaborative design optimization method for water supply and drainage BIM-based forward design as described in claim 1, characterized in that, The cluster weight of each cluster at each time point is the ratio of the cluster mean of each cluster at each time point to the maximum cluster mean among all clusters.

5. The collaborative design optimization method for water supply and drainage BIM-based forward design as described in claim 1, characterized in that, The method for obtaining the conflict probability of each cluster at each time point is as follows: At each time point, in each cluster, the difference between the pipe slope and the preset standard slope and the difference between the pipe velocity and the preset standard velocity in each pair are calculated and denoted as the first deviation and the second deviation, respectively. The first deviation and the second deviation of all pairs in each cluster are used as inputs to the logistic regression analysis algorithm, and the output probability value is used as the conflict probability of each cluster at each time point.

6. The collaborative design optimization method for water supply and drainage BIM-based forward design as described in claim 1, characterized in that, The method for determining the soft conflict risk index of the fluid pipeline at each time point is as follows: Calculate the product of the clustering weight and the conflict probability of each cluster at each time step, and sum the products of all clusters at each time step as the soft conflict risk index of the fluid pipeline at each time step.

7. The collaborative design optimization method for water supply and drainage BIM forward design as described in claim 1, characterized in that, The urgency level mentioned includes: Historical soft conflict risk indices and historical HVAC duct vibration frequencies are obtained and used as inputs to a decision tree. Priority labels are set as urgent and deferred, and the decision tree is trained. The soft conflict risk index and HVAC duct vibration frequency of all moments within a preset time period before each moment are used as input to the trained decision tree. The proportion of the number of leaf nodes with all emergency labels in the total number of leaf nodes is counted, and the proportion is used as the urgency of the fluid pipeline at each moment.

8. The collaborative design optimization method for water supply and drainage BIM-based forward design as described in claim 1, characterized in that, The cost-effectiveness ratio of the fluid pipeline at each time point is the ratio of the multi-objective genetic algorithm score to the urgency of the fluid pipeline at each time point.

9. The collaborative design optimization method for water supply and drainage BIM-based forward design as described in claim 1, characterized in that, The expression for the priority reconfiguration value of the fluid pipeline at the current moment is: In the formula, Y represents the priority reconstruction value of the fluid pipeline at the current moment; B represents the cost-effectiveness ratio of the fluid pipeline at the current moment; B max This represents the maximum value among all the treatment cost-effectiveness ratios of the fluid pipeline within the preset time period prior to the current moment.

10. The collaborative design optimization method for water supply and drainage BIM-based forward design as described in claim 1, characterized in that, The collaborative design optimization of the water supply and drainage BIM forward design at the current moment includes: If the priority reconstruction value of the fluid pipeline at the current moment is greater than the preset first threshold, then the pipeline route will be reconstructed. If the priority reconstruction value of the fluid pipeline at the current moment is between the preset second threshold and the preset first threshold, or the priority reconstruction value is equal to the preset second threshold, or the priority reconstruction value is equal to the preset first threshold, then cross-professional parameter linkage is executed, where the preset second threshold is less than the preset first threshold; If the priority reconstruction value of the fluid pipeline at the current moment is less than the preset second threshold, the rule base will be iteratively updated.

Images