Laboratory intelligent layout optimization method and system for multi-energy experimental building

Abstract

The application discloses a laboratory intelligent layout optimization method and system for a multi-energy experiment building, and relates to the technical field of auxiliary layout optimization. The method comprises the following steps: S1, collecting space energy flow data and performing data preprocessing; S2, identifying the pollution source influence intensity in the experiment area, judging the leakage trend and retention tendency, and extracting the energy flow coupling relationship between regions; S3, evaluating the minimum exhaust boundary required by the experiment area, and performing dynamic correction on adjacent regions; S4, mapping the exhaust volume to the fan operating frequency and the end valve opening degree, and optimizing the equipment selection, pipe diameter ratio and end arrangement; S5, constructing a candidate layout generation and integrated evaluation mechanism, screening and obtaining an optimization scheme, and writing back to the BIM model. The problems of gas retention, energy waste and inability to dynamically respond to the operating state under the cross ventilation path due to the difficulty of traditional ventilation design to adapt to the differentiated working conditions of multi-energy regions are solved.

Description

Technical Field

[0001] This invention relates to the field of auxiliary layout optimization technology, specifically to a method and system for intelligent layout optimization of laboratories for multi-energy experimental buildings. Background Technology

[0002] In the development of modern architecture, the diversification of spatial functions, the expansion of building volume, and the integration of equipment systems have led to increasingly high-density, complex, and multi-faceted collaborative characteristics in the spatial layout of buildings. The geometric structure of a building, its room organization, pipeline architecture, and equipment layout not only affect the efficiency of space utilization and the movement paths of people, but also directly relate to ventilation organization, environmental quality, energy utilization, and the overall level of operation and maintenance. As building scale continues to increase and functional requirements become increasingly refined, the spatial coupling relationships between different areas, pipeline connectivity methods, and equipment layout strategies become more complex, placing higher demands on the rationality assessment, parametric management, and intelligent optimization of building layouts.

[0003] For example, the invention patent with announcement number CN109992913B announced a DC layout planning method based on communication building resources, including the following steps: (1) adding CO building resources and providing basic data; (2) CO value assessment and scoring; (3) DC resource estimation; (4) DC layout site selection: DC layout site selection is based on the attributes of CO building, IDC building or newly built DC building; (5) DC resource allocation: based on DC layout site selection, combined with DC resource estimation, the new carrying requirements of each target DC are implemented, compared with its current equipment room resources, and reserved equipment room floor space is allocated. By adopting the above technical solution, all DC groups are allocated and operated, which makes it easier to coordinate various new requirements to be truly implemented on each DC. Only by realizing the unified layout of DC and realizing full modularization can the operator's investment be fully protected, investment saved, and implementation distributed on demand, so as to achieve rapid response.

[0004] For example, invention patent CN115917549A discloses an equipment layout anomaly determination device and method. The building traffic flow setting device includes: a database unit storing data from the building's BIM model; a pedestrian flow simulator unit simulating the traffic flow within the building as shown in the BIM model stored in the database unit; and an elevator simulator unit simulating the operation of elevators installed in the building based on the traffic flow obtained from the pedestrian flow simulator unit's simulation. Here, the pedestrian flow simulator unit includes: a simulation evaluation unit that calculates evaluation indicators of pedestrian flow in a specific area when the elevator simulator unit simulates the operation of the elevators; and an anomaly determination unit that outputs an alarm when the calculated evaluation indicators for the specific area exceed a preset threshold.

[0005] However, in experimental building scenarios involving multi-energy coupling, unresolved issues of layout and ventilation coordination remain. Thermal, hydrogen, and energy storage laboratories in various regions generally have differentiated requirements for high temperature, high humidity, and explosion-proof conditions. Ventilation paths between areas are prone to intersecting, leading to the retention of pollutants, reduced exhaust and ventilation efficiency, or localized energy waste. Traditional building ventilation layouts are mostly based on fixed flow rates and fixed directions, making it impossible to adjust in real time according to the dynamic operating status of multi-energy systems. Furthermore, it is difficult to balance safety, energy efficiency, and localized risk distribution. Layout decisions and equipment configuration still heavily rely on manual experience, failing to meet the requirements of new multi-energy experimental environments for intelligence, collaboration, and adjustability.

[0006] Therefore, in order to address the above issues, there is an urgent need for intelligent layout optimization methods and systems for multi-energy experimental buildings. Summary of the Invention

[0007] Technical problems to be solved

[0008] To address the shortcomings of existing technologies, this invention provides a method and system for optimizing the intelligent layout of laboratories in multi-energy experimental buildings. It solves the problems of gas stagnation, energy waste, and inability to dynamically respond to operating conditions caused by the fixed ventilation design of traditional ventilation systems, which are difficult to adapt to the different operating conditions of multi-energy areas.

[0009] Technical solution

[0010] To achieve the above objectives, this invention provides the following technical solution: a laboratory intelligent layout optimization method for multi-energy experimental buildings, comprising the following steps: S1, based on a BIM-constructed multi-source spatial data system, analyzing the geometric structure of the experimental area, equipment source items, and design indicators to form spatial energy flow data, and preprocessing the spatial energy flow data; S2, based on the spatial energy flow data, identifying the impact intensity of pollution sources within the experimental area, judging leakage trends and retention tendencies, quantifying the risk status of the experimental area, and extracting the energy flow coupling relationship between areas; S3, based on the impact intensity of pollution sources, Based on the integrated spatial energy flow data, the minimum exhaust boundary required for the experimental area to achieve the target conditions is evaluated, and dynamic corrections are performed on adjacent areas in combination with the energy flow coupling relationship between areas to form an exhaust demand distribution; S4, combining the exhaust demand distribution and spatial energy flow data, the exhaust volume is mapped to the fan operating frequency and the terminal valve opening to generate an execution vector; based on the execution vector, the equipment selection, pipe diameter ratio and terminal layout are optimized; S5, a candidate layout generation and source strength, exhaust and execution vector integrated evaluation mechanism is constructed under multi-objective constraints, the optimized scheme is screened and obtained, and the optimized scheme is written back to the BIM model.

[0011] Furthermore, based on the multi-source spatial data system constructed using BIM, the geometric structure, equipment source items, and design indicators of the experimental area are analyzed to form spatial energy flow data. The specific process of data preprocessing for spatial energy flow data is as follows: Spatial geometric parameters of each experimental area are obtained by analyzing the BIM geometric model, including room volume, spatial connectivity area, door and window grille geometry, pipe network topology, and net height. Based on the door and window grille geometry, the equivalent airflow area is obtained by multiplying the physical opening area of ​​the door and window grille by the structure type correction coefficient, and different initial outflow coefficients are assigned according to the structure type. Equipment source item characteristics are extracted through equipment samples and design specifications, including the rated frequency of the fans in the experimental area, the heat dissipation and emission characteristics of each device at rated power, the maximum effective flow area of ​​various terminal devices, and the valve damping coefficient. These characteristics are then combined with design specifications. The target indicators for the experimental area include target concentration, target pressure difference, minimum air change rate, and cleanliness. A numerical model of the ventilation network is used, combined with a network flow solution algorithm based on the pipe network topology, to predict and collect a rapid field prediction set, including gas concentration, pressure difference, supply air concentration, supply air flow rate, and exhaust air flow rate. Air density is determined based on the design temperature and humidity curve. Spatial geometric parameters, equipment source term characteristics, target indicators, rapid field prediction set, and air density are uniformly recorded as spatial energy flow data. The time step of the spatial energy flow data is uniformly aligned with the coordinate system, and outliers are removed using the median absolute deviation method and quantile detection method. Missing data is smoothed and completed using spline interpolation and moving average. At the same time, the spatial energy flow data is normalized. A layout optimization database is established, and the preprocessed spatial energy flow data is written into the layout optimization database.

[0012] Furthermore, the specific process for identifying the intensity of pollution source impact within the experimental area based on spatial energy flow data is as follows: acquire spatial energy flow data; for each experimental area, calculate the gas concentration difference between the current moment and the previous moment, divide by the time step to obtain the gas concentration change rate; multiply the gas concentration change rate by the room volume to obtain the concentration accumulation; multiply the non-negative pressure difference by twice the air density, take the square root, and then multiply by the equivalent airflow area and the initial outflow coefficient to obtain the leakage flow rate; add the leakage flow rate to the exhaust flow rate and multiply by the gas concentration at the current moment to obtain the effective emission rate; multiply the supply air flow rate by the supply air concentration to obtain the supply air dilution offset; add the concentration accumulation to the effective emission rate and subtract the supply air dilution offset to obtain the equivalent source strength value.

[0013] Furthermore, the specific process for judging leakage trends and retention tendencies, quantifying the risk status of the experimental area, and extracting the energy flow coupling relationship between regions is as follows: The equivalent source strength value of each experimental area is calculated; the equivalent source strength value is smoothed and trend-fitted on the time axis to identify the peak period and duration of the equivalent source strength value, forming a source strength fluctuation curve; and retention-sensitive areas where the equivalent source strength value exceeds the intensity threshold and the gas concentration change rate is higher than the average gas concentration change rate in the region are marked; the ratio of the peak value to the average value of the equivalent source strength value of each experimental area is calculated to obtain the regional risk value; when the regional risk value exceeds the risk threshold, the region is marked. The risk zone is defined; a heat map of airflow stagnation is generated; for any adjacent experimental zones, the pressure gradient and concentration gradient are calculated respectively, and the square root of the non-negative pressure gradient is multiplied by twice the air density, and then multiplied by the equivalent airflow area and the initial outflow coefficient to obtain the net cross-regional airflow; when both the pressure gradient and concentration gradient exceed the corresponding gradient threshold and there is an actual net cross-regional airflow, the experimental zone is determined to constitute a cross-influence area; the product of the net cross-regional airflow, pressure gradient, and concentration gradient is used as the coupling strength value to construct the energy-fluid coupling matrix; the equivalent source strength value, regional risk value, and energy-fluid coupling matrix are uniformly encapsulated into a source strength feature data package and written into the layout optimization database.

[0014] Furthermore, based on the intensity of pollution source impact and comprehensive spatial energy flow data, the specific process for assessing the minimum exhaust boundary required for the experimental area to reach the target conditions is as follows: receiving source strength characteristic data packets and acquiring spatial energy flow data; for each experimental area, multiplying the difference between the supply air concentration and the target concentration by the supply air flow rate to obtain the supply air load deduction value; multiplying the target pressure difference by twice the air density, taking the square root, and then multiplying by the equivalent airflow area, the initial outflow coefficient, and the target concentration to obtain the pressure difference compensation value; adding the pressure difference compensation value to the difference between the equivalent source strength value and the supply air load deduction value, and dividing by the target concentration to obtain the minimum exhaust volume assessment value, and performing a non-negative operation on the minimum exhaust volume assessment value.

[0015] Furthermore, the specific process of dynamically correcting adjacent areas based on the energy flow coupling relationship between regions to form the exhaust demand distribution is as follows: Calculate the minimum exhaust volume assessment value of each experimental area. Based on the energy flow coupling matrix, for each experimental area, extract the coupling strength value between the current experimental area and other experimental areas, and select the maximum value as the regional coupling strength index. When an experimental area is marked as a risk area or a stagnation sensitive area, and the coupling strength index between it and adjacent experimental areas exceeds the coupling threshold, a dynamic correction factor greater than 1 is introduced into the minimum exhaust volume assessment value of the experimental area. After completing the dynamic correction, the minimum exhaust volume assessment value of each experimental area is used as the target exhaust volume, and the target exhaust volume distribution result is written into the layout optimization database.

[0016] Furthermore, combining the exhaust demand distribution and spatial energy flow data, the exhaust volume is mapped to the fan operating frequency and the terminal valve opening. The specific process for generating the execution vector is as follows: read the target exhaust volume and spatial energy flow data of each experimental area from the layout optimization database, and summarize the target exhaust volume to obtain the total exhaust demand; summarize the exhaust flow of each experimental area to obtain the actual total exhaust volume; multiply the fan rated frequency by the ratio of the total exhaust demand to the actual total exhaust volume to obtain the nominal fan frequency value; for each experimental area, calculate twice the target pressure difference divided by the square root of the air density, and then multiply by the initial outflow coefficient and the maximum effective flow area to obtain the maximum theoretical exhaust volume; divide the target exhaust volume of the experimental area by the maximum theoretical exhaust volume to obtain the required flow ratio, and subtract the required flow ratio from the constant, take the natural logarithm, and then multiply by the negative reciprocal of the valve damping coefficient to obtain the nominal valve opening value; combine the nominal fan frequency value and the nominal valve opening value of each experimental area to form the execution vector.

[0017] Furthermore, the specific process for optimizing equipment selection, pipe diameter ratio, and terminal layout based on execution vectors is as follows: Layout suggestions are generated based on execution vectors: Based on the maximum airflow output capacity corresponding to the nominal frequency value of the fan, a range of fan models covering the requirements is selected from the fan equipment sample library; the fan operating margin is assessed based on the difference between the nominal frequency value and the rated frequency of the fan, generating a list of recommended models for different capacity levels; if multiple fans can operate in parallel, parallel combination suggestions are provided; the target exhaust volume is converted into the minimum equivalent cross-sectional area under the recommended flow velocity conditions, and combined with the nominal valve opening value and the maximum effective flow area, the actual performance of the experimental area is determined. If the flow capacity meets the requirements, generate pipe diameter enlargement suggestions and output pipe diameter matching schemes when the capacity is insufficient; determine the required number of terminal devices based on the nominal valve opening value, the target exhaust volume of the experimental area, and the rated emission characteristics of a single terminal device; combine the stagnation sensitive area and the cross-area energy flow path reflected by the energy flow coupling matrix to prioritize the placement of terminal devices in key locations, generating a layout scheme for the number of terminals, terminal types, and specific spatial coordinates; perform consistency verification by combining the nominal frequency value of the fan with the nominal valve opening value of each experimental area, and perform layout correction for experimental areas that fail the consistency verification; write the execution vector and layout suggestions into the layout optimization database.

[0018] Furthermore, the specific process of constructing a candidate layout generation and source strength, exhaust volume, and execution vector integrated evaluation mechanism under multi-objective constraints, screening and obtaining optimized schemes, and writing the optimized schemes back to the BIM model is as follows: Spatial geometric parameters, equipment source characteristics, target exhaust volume distribution, valve nominal opening values, and layout suggestions are read from the layout optimization database to construct layout constraints. Candidate layout schemes are generated through an automated layout generation method. For each candidate layout scheme, the equivalent source strength value, minimum exhaust volume evaluation value, and execution vector calculation steps are called to obtain the corresponding source strength characteristic data, target exhaust volume distribution, and execution vector, and generate scheme evaluation results. Based on the scheme evaluation results, multi-objective non-dominated sorting is performed to obtain the Pareto optimized scheme set, and a recommended layout scheme is selected from the Pareto optimized scheme set. Based on the recommended layout scheme, the fan selection results, pipe diameter configuration, number of terminal equipment, and spatial coordinate parameters are written back to the BIM model to generate design parameter tables, installation sequence suggestions, and operation and maintenance delivery data for construction and commissioning.

[0019] The second aspect of this invention provides a laboratory intelligent layout optimization system for multi-energy experimental buildings, comprising: a data base and preprocessing module, used to analyze the geometric structure, equipment source items, and design indicators of the experimental area based on a BIM-constructed multi-source spatial data system, forming spatial energy flow data, and performing data preprocessing on the spatial energy flow data; an equivalent source strength identification module, used to identify the influence intensity of pollution sources in the experimental area based on the spatial energy flow data, and determine the leakage trend and retention tendency, while quantifying the risk status of the experimental area and extracting the energy flow coupling relationship between areas; and a minimum exhaust volume synthesis module, used to synthesize the spatial energy flow data based on the influence intensity of pollution sources. According to the evaluation, the minimum exhaust boundary required for the experimental area to achieve the target conditions is assessed, and dynamic corrections are performed on adjacent areas in combination with the energy flow coupling relationship between areas to form an exhaust demand distribution; the execution vector and terminal mapping module is used to combine the exhaust demand distribution and spatial energy flow data to map the exhaust volume to the fan operating frequency and terminal valve opening to generate an execution vector; based on the execution vector, the equipment selection, pipe diameter ratio and terminal layout are optimized; the multi-scheme optimization and BIM write-back module is used to build a candidate layout generation and source strength, exhaust and execution vector integrated evaluation mechanism under multi-objective constraints, screen and obtain optimized schemes, and write the optimized schemes back to the BIM model.

[0020] Beneficial effects

[0021] The present invention has the following beneficial effects:

[0022] (1) This invention uses a BIM-driven multi-source spatial data system to map geometric structures, equipment source terms, flow field predictions and environmental indicators into spatial energy flow data, so that layout decisions are transformed from relying on human experience to relying on measurable and calculable physical quantities. This realizes the digital, visual and measurable expression of laboratory energy flow status in multi-energy scenarios, and provides a unified mathematical basis for subsequent exhaust boundary assessment and layout optimization.

[0023] (2) This invention utilizes the concentration change rate, pressure difference to drive leakage flow, and supply and exhaust air counteracting effect to construct an equivalent source strength, thereby realizing the quantitative judgment of pollution diffusion trend, retention sensitive area and regional risk. Furthermore, it identifies the energy flow coupling relationship through cross-regional pressure difference gradient and concentration gradient, breaking through the traditional mode of calculating exhaust air based only on single-region load, and realizing the automatic identification and risk quantification of energy flow coupling between multiple regions.

[0024] (3) This invention integrates the factors of equivalent source strength, supply air deduction and pressure difference compensation into the exhaust boundary calculation formula, and performs dynamic correction on adjacent areas based on the energy flow coupling matrix, thereby obtaining an exhaust demand distribution that accurately reflects the spatial interaction influence, overcoming the shortcomings of traditional fixed air volume in adapting to multi-energy scenarios and highly coupled spaces, and improving the scientificity, energy efficiency and safety of exhaust configuration.

[0025] (4) In this invention, by mapping the exhaust demand to the nominal frequency of the fan and the nominal opening degree of the valve to form an execution vector, the fan selection, pipe diameter ratio and terminal layout are generated based on the execution vector, and the Pareto optimization scheme is obtained through multi-objective non-dominated sorting. Finally, it is written back to the BIM model to realize the digital closed-loop linkage of design data, calculation process and layout results, which greatly improves the automation and verifiability of laboratory layout planning.

[0026] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0027] Figure 1 A flowchart illustrating the intelligent layout optimization method for laboratories in multi-energy experimental buildings;

[0028] Figure 2 Structure diagram of a laboratory intelligent layout optimization system for multi-energy experimental buildings;

[0029] Figure 3 This is a distribution map of equivalent source strength values;

[0030] Figure 4 This is a heat map of airflow retention based on risk zones and retention-sensitive zones. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. As those skilled in the art will understand, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] Please see Figures 1-4 This invention provides a technical solution: a method and system for optimizing the intelligent layout of laboratories in multi-energy experimental buildings, such as... Figure 1 As shown, the process includes the following steps: S1, based on the multi-source spatial data system constructed by BIM, analyze the geometric structure, equipment source items, and design indicators of the experimental area to form spatial energy flow data, and perform data preprocessing on the spatial energy flow data; S2, based on the spatial energy flow data, identify the impact intensity of pollution sources in the experimental area, determine the leakage trend and retention tendency, quantify the risk status of the experimental area, and extract the energy flow coupling relationship between regions; S3, based on the impact intensity of pollution sources, comprehensively analyze the spatial energy flow data, evaluate the minimum exhaust boundary required for the experimental area to achieve the target conditions, and perform dynamic correction on adjacent areas in combination with the energy flow coupling relationship between regions to form the exhaust demand distribution; S4, combining the exhaust demand distribution and spatial energy flow data, map the exhaust volume to the fan operating frequency and the terminal valve opening to generate an execution vector; optimize the equipment selection, pipe diameter ratio, and terminal layout based on the execution vector; S5, construct a candidate layout generation and source strength, exhaust, and execution vector integrated evaluation mechanism under multi-objective constraints, screen and obtain optimized solutions, and write the optimized solutions back to the BIM model.

[0033] Specifically, based on the multi-source spatial data system constructed using BIM, the geometric structure, equipment source items, and design indicators of the experimental area are analyzed to form spatial energy flow data. The specific process of data preprocessing for spatial energy flow data is as follows: Spatial geometric parameters of each experimental area are obtained by analyzing the BIM geometric model, including room volume, spatial connectivity area, door and window grille geometry, pipe network topology, and net height. Based on the door and window grille geometry, the equivalent airflow area is obtained by multiplying the physical opening area of ​​the door and window grille by the structure type correction coefficient. Different initial outflow coefficients are assigned according to ventilation engineering standard parameters based on the structure type, with values ​​ranging from 0.45 to 0.85. Equipment source item characteristics are extracted through equipment samples and design specifications, including those of the experimental area. The system includes: rated frequency of the fan; heat dissipation and emission characteristics of each device at rated power; maximum effective flow area of ​​various terminal devices; and valve damping coefficients. Target indicators for the experimental area are defined according to design specifications, including target concentration, target pressure difference, minimum air changes per minute, and cleanliness. A numerical model of the ventilation network is used, combined with a network flow solving algorithm based on the pipe network topology to predict and collect a rapid field prediction set, including gas concentration, pressure difference, supply air concentration, supply air flow rate, and exhaust air flow rate. Air density is determined based on the design temperature and humidity curves. Spatial geometric parameters, equipment source term characteristics, target indicators, rapid field prediction set, and air density are uniformly recorded as spatial energy flow data. During the analysis of the BIM geometric model, room boundaries, component attributes, and spatial connectivity are automatically obtained through the standard Revit API interface, ensuring that all geometric quantities are directly quantifiable data sources. When calculating the equivalent airflow area, the structural type correction coefficient is set based on the flow resistance characteristics of different structures such as door gaps, grilles, and louvers, with a value range between 0.45 and 0.85, ensuring the equivalent area has repeatable calculation capabilities and compatibility with actual laboratory scenarios. When using a numerical model of the ventilation network, the model constructs airflow balance equations based on the node and pipe segment network structure. These equations are solved using continuity equations, nodal pressure difference equations, and resistance characteristic equations, ensuring a rapid acquisition of the steady-state field distribution and meeting the needs of rapid prediction and real-time iteration in practical engineering. When executing the network flow solution algorithm based on the pipe network topology, a Newton-Raphson iteration method is employed, with fan characteristic curves and valve flow opening curves used as boundary parameter inputs. This ensures that the prediction results accurately reflect the ventilation response characteristics under different operating conditions. During the rapid field prediction dataset acquisition process, predictions and recordings are performed at uniform time steps, such as 30s to 300s, ensuring that data at each moment can be used for subsequent time-series analysis and risk trend inference.The spatial energy flow data were aligned with the coordinate system and time step was uniformly executed. Outliers were removed using the median absolute deviation method and quantile detection method. Instantaneous spike noise and extreme anomalies in flow and concentration were eliminated. Missing data were smoothed and completed using spline interpolation and moving average. Cubic splines were used to maintain temporal continuity, and drastic fluctuations were further smoothed by moving average with a fixed window length, such as 3 to 5 time steps, to ensure the stability of subsequent calculations. At the same time, the spatial energy flow data were normalized using Min–Max to ensure that energy flow data from different experimental areas and time periods could be directly compared across experiments. A layout optimization database was established, and the preprocessed spatial energy flow data was written into the layout optimization database.

[0034] This implementation plan constructs a BIM-based multi-source spatial data system to uniformly quantify the experimental area's geometric structure, equipment source items, and design indicators. Combined with a ventilation network numerical model and a pipe network topology solving algorithm, it enables rapid field prediction of gas concentration, pressure difference, and supply and exhaust air flow rates. By using boundary parameters such as door and window grille structure correction coefficients and fan and valve operating curves, the prediction results accurately reflect actual operating conditions. Preprocessing methods such as median absolute deviation, quantile detection, spline interpolation, and moving average are employed to ensure the stability, continuity, and comparability of energy flow data. Through normalization and database management, a high-quality data foundation is provided for exhaust demand calculation, risk identification, and layout optimization, thereby significantly improving the accuracy, real-time performance, and feasibility of laboratory layout optimization.

[0035] Specifically, the process of identifying the intensity of pollution source impact within the experimental area based on spatial energy flow data is as follows: Spatial energy flow data is acquired. For each experimental area, the gas concentration difference between the current and previous moments is calculated and divided by the time step to obtain the gas concentration change rate. This reflects the instantaneous accumulation trend of pollutants in the space and is the most direct dynamic indicator for judging the strength of pollution sources. A preset uniform sampling period is used for the time step to ensure the consistency of time-series data calculations. The gas concentration change rate is multiplied by the room volume to obtain the concentration accumulation amount, which represents the cumulative effect of pollutants in the entire room space caused by the pollution source per unit time and can be used as the basis for source strength changes. The pressure difference is multiplied by twice the air density (taking a non-negative value), and the square root is taken. This square root is then multiplied by the equivalent area of ​​the airflow and the initial outflow coefficient to obtain the leakage flow rate. The leakage flow rate is used to characterize the effect of the pollution source's influence on the airflow intensity. Passive leakage caused by structures such as door gaps and grilles plays a crucial role in determining whether pollution will spread to adjacent areas. The effective emission amount is obtained by adding the leakage flow rate to the exhaust flow rate and multiplying it by the current gas concentration. The effective emission amount represents the combined removal capacity of pollutants by "natural leakage and mechanical exhaust," and is a key indicator of pollution purification effectiveness. The supply air flow rate is multiplied by the supply air concentration to obtain the supply air dilution offset, which reflects the dilution effect introduced by the supply air and is an important reverse contribution to reducing pollutant concentration. The equivalent source strength value is obtained by adding the concentration accumulation to the effective emission amount and subtracting the supply air dilution offset. The equivalent source strength value is constructed based on the mass conservation principle and is used to quantitatively characterize the true impact of pollution sources on overall air quality in the current experimental area. It can eliminate fluctuations caused by exhaust and supply air, reflecting the net contribution of pollution sources.

[0036] The specific formula for the equivalent source strength value is as follows:

[0037] ;

[0038] In the formula, It represents the equivalent source strength value, used to identify the overall pollution release intensity of any experimental area Z at the current moment, and to determine how strong the pollution source is now actually generated in this area. This indicates room volume and is used to convert changes in concentration into changes in pollutant quality. This indicates the gas concentration at the current moment. This represents the gas concentration at the previous moment, used to calculate the rate of concentration change, and to deduce the size of the internal source term. Indicates the time step; This indicates the exhaust airflow rate, used to calculate the amount of pollution being removed. This represents the initial outflow coefficient, reflecting the flow resistance characteristics of gaps and channels, and serves as a proportionality coefficient for calculating leakage flow. It represents the equivalent area of ​​the airflow, the flow capacity of the region's outer shell, and determines the magnitude of the leakage flow rate driven by the pressure difference; This indicates air density and affects the flow rate driven by pressure difference. It represents the pressure difference and is used to determine whether a leak has occurred. Indicates the supply air volume and calculates the fresh air dilution capacity; This indicates the supply air concentration, used to calculate the supply air dilution effect.

[0039] In this embodiment, Table 1 is a table of equivalent source strength values. The time step is set to 60, the air density is 1.2, and the initial outflow coefficient is 0.65. The table records in detail the room volume, current gas concentration, previous gas concentration, exhaust flow rate, equivalent airflow area, pressure difference, supply air flow rate, supply air concentration, and equivalent source strength value of five different experimental areas. Among them, the room volume corresponding to experimental area 1 is 150, the current gas concentration is 2.5, the previous gas concentration is 2.0, the exhaust air flow rate is 0.40, the equivalent airflow area is 0.08, the pressure difference is 10, the supply air flow rate is 0.35, the supply air concentration is 0.5, and the equivalent source strength value is 2.7119; the room volume corresponding to experimental area 2 is 220, the current gas concentration is 1.8, the previous gas concentration is 1.5, the exhaust air flow rate is 0.55, the equivalent airflow area is 0.10, the pressure difference is 15, the supply air flow rate is 0.50, the supply air concentration is 0.4, and the equivalent source strength value is 2.5920; the room volume corresponding to experimental area 3 is 90, the current gas concentration is 3.2, the previous gas concentration is 2.8, and the exhaust air flow rate is 0. 30. The equivalent airflow area is 0.06, the pressure difference is 8, the supply air flow rate is 0.25, the supply air concentration is 0.6, and the equivalent source strength is 1.9568; the room volume corresponding to experimental area 4 is 300, the current gas concentration is 1.2, the previous gas concentration is 1.1, the exhaust air flow rate is 0.70, the equivalent airflow area is 0.12, the pressure difference is 5, the supply air flow rate is 0.80, the supply air concentration is 0.2, and the equivalent source strength is 1.5042; the room volume corresponding to experimental area 5 is 180, the current gas concentration is 2.0, the previous gas concentration is 1.7, the exhaust air flow rate is 0.50, the equivalent airflow area is 0.09, the pressure difference is 12, the supply air flow rate is 0.45, the supply air concentration is 0.5, and the equivalent source strength is 2.3029.

[0040] Table 1. Equivalent Source Strength Value Data Table

[0041]

[0042] like Figure 3 The figure shows the distribution of equivalent source intensity values. The horizontal axis represents the experimental area number, and the vertical axis represents the equivalent source intensity value at the corresponding time. The intensity threshold is marked with dashed lines to distinguish areas with stronger and weaker pollution source influence. Based on Table 1 and... Figure 3It can be seen that the equivalent source intensity values ​​of Experimental Zones 1 and 2 are close to or even exceed the threshold, indicating that the accumulation or leakage trend of pollution sources in these two areas is relatively obvious, and they should be considered as key areas of concern. The source intensity of Experimental Zone 5 is moderately high, but does not reach the threshold, indicating that there is some pollution accumulation, but the risk is relatively controllable. The source intensity values ​​of Experimental Zones 3 and 4 are significantly low, indicating that the gas diffusion is faster, the ventilation and discharge are more sufficient, and the degree of pollution retention is weaker. Overall, there are significant differences in pollution source intensity between regions, reflecting significant differences in source terms, airflow organization, pressure difference, and terminal flow capacity in different experimental zones.

[0043] In this implementation plan, an equivalent source strength model is constructed by considering multiple factors such as concentration accumulation, leakage flow, exhaust purging, and supply air dilution. This model can eliminate interference from changes in ventilation conditions and accurately quantify the net contribution intensity of pollution sources. Compared with traditional methods that rely on a single concentration or exhaust volume, this method achieves dynamic and accurate assessment of the impact intensity of pollution sources, improving the accuracy and controllability of pollution risk identification.

[0044] Specifically, the process of judging leakage trends and retention tendencies, quantifying the risk status of experimental areas, and extracting energy flow coupling relationships between regions is as follows: The equivalent source strength value of each experimental area is calculated. This equivalent source strength value is then smoothed and trend-fitted on the time axis. Smoothing uses moving averages to eliminate instantaneous noise, and trend fitting uses linear fitting to obtain a stable direction of change, ensuring the reliability of trend judgment. The peak periods and durations of the equivalent source strength values ​​are identified, forming source strength fluctuation curves to reflect the persistence and phased characteristics of pollution source release, serving as an important basis for subsequent risk labeling. Retention-sensitive areas where the equivalent source strength value exceeds the intensity threshold and the gas concentration change rate is higher than the average gas concentration change rate within the region are marked. This ensures that retention risk is only identified when both conditions of "high source strength and rapid concentration increase" are met simultaneously, thereby improving the accuracy of identification. The ratio of the peak value to the average value of the equivalent source strength value in each experimental area is calculated to obtain the regional risk value. The peak value reflects the most unfavorable instantaneous operating condition, while the average value represents the background level. The ratio characterizes whether there is an abnormal increase in pollution source intensity. When the regional risk value exceeds the risk threshold... When the value is calculated, the area is marked as a risk zone and will be a key focus in subsequent optimization suggestions; an airflow retention heat map is generated to show the retention degree and risk level of different experimental areas; for any adjacent experimental areas, the pressure gradient and concentration gradient are calculated respectively. The pressure gradient is used to reflect the direction of air driving force, and the concentration gradient is used to reflect the direction of pollution diffusion. The non-negative pressure gradient is multiplied by twice the air density, the square root is taken, and then multiplied by the equivalent area of ​​the airflow and the initial outflow coefficient to obtain the net cross-zone airflow rate, which is derived from the basic ventilation flow equation to ensure that the cross-zone airflow rate has practical applicability. Measurability and engineering feasibility: When both the pressure gradient and concentration gradient exceed their corresponding gradient thresholds and there is an actual net cross-regional airflow, the experimental areas are determined to constitute a cross-influence area, i.e., a pollution diffusion path may occur between the areas. The product of the net cross-regional airflow, pressure gradient, and concentration gradient is used as the coupling strength value to construct an energy flow coupling matrix, which is used to quantify the pollution influence relationship between different experimental areas and is an important input for subsequent multi-objective layout optimization. The equivalent source strength value, regional risk value, and energy flow coupling matrix are uniformly encapsulated into a source strength feature data package and written into the layout optimization database.

[0045] like Figure 4The image shows a heat map of airflow retention based on risk zones and retention-sensitive zones. It illustrates the distribution of airflow retention risk in each experimental zone. The horizontal axis represents the experimental zone number, and the colors, from dark to light, indicate the trend from safe zones to high-risk retention-sensitive zones. The heat map value is composed of two indicators: whether the equivalent source strength exceeds the threshold and whether the gas concentration change rate is higher than the regional average change rate. As can be seen from the image, experimental zones 1 and 2 are the lightest, indicating significantly higher source strength levels and a significant upward trend in gas concentration, classifying them as key risk retention zones. Experimental zones 3 and 5 are in the middle color range, indicating a moderate risk level and a certain degree of retention sensitivity, classifying them as critically sensitive zones. Experimental zone 4 is the darkest, indicating a safe state with stable gas diffusion and exhaust effects. The heat map visually reflects the gas accumulation and retention trends in different experimental zones, providing a basis for subsequent ventilation configuration optimization and risk warning strategies.

[0046] In this implementation plan, by jointly analyzing the temporal changes, concentration trends, and pressure difference driving characteristics of equivalent source strength values, the precise identification of leakage trends, retention tendencies, and risk zones is achieved. A regional risk quantification index is constructed using the peak-to-mean ratio, providing a clear threshold basis for risk assessment. Furthermore, by combining pressure difference gradients, concentration gradients, and net cross-regional gas flow to construct an energy-fluid coupling matrix, potential pollution propagation paths between experimental zones can be effectively identified. The overall method combines measurability, computability, and visualization capabilities, not only improving the accuracy of pollution diffusion risk identification but also providing structured and quantitative risk characteristic inputs for subsequent layout optimization, thereby significantly enhancing feasibility and safety assurance capabilities.

[0047] Specifically, based on the intensity of pollution source impact and comprehensive spatial energy flow data, the process of assessing the minimum exhaust boundary required for the experimental area to reach the target conditions is as follows: 1) Receiving source strength characteristic data packets and acquiring spatial energy flow data; 2) For each experimental area, multiplying the difference between the supply air concentration and the target concentration by the supply air flow rate to obtain the supply air load deduction value, reflecting the dilution capacity of the supply air for pollutants, which is the main contributor to reducing the exhaust load. The supply air concentration and supply air flow rate are both obtained from the rapid field prediction set obtained by solving the ventilation network numerical model and duct topology; 3) Multiplying the target pressure difference by twice the air density, taking the square root, and then multiplying it by the equivalent area of ​​the airflow, the initial outflow coefficient, and the target concentration to obtain the desired exhaust load. Differential pressure compensation value: The difference between the equivalent source strength value and the supply air load deduction value is added to the differential pressure compensation value and divided by the target concentration to obtain the minimum exhaust volume assessment value. The minimum exhaust volume assessment value is derived from the mass conservation relationship and represents the minimum exhaust boundary required to maintain the target concentration level under the current source strength. It is the basic calculation quantity for subsequent exhaust control and equipment selection. The minimum exhaust volume assessment value is non-negative. If the calculation result is non-negative, the original calculation result is taken; otherwise, it is taken as zero. This avoids unreasonable situations of negative exhaust volume when the supply air deduction is too large or the source strength is low, ensuring that the calculation result meets the engineering feasibility requirements and can be directly used in the subsequent mapping process of fan frequency and valve opening.

[0048] The specific formula for the minimum exhaust volume assessment value is as follows:

[0049] ;

[0050] In the formula, This represents the minimum exhaust volume assessment value, used to comprehensively calculate the minimum exhaust volume that can meet the cleanliness and differential pressure requirements within the experimental zone Z. In other words, it obtains the lowest exhaust boundary value that meets air quality and differential pressure safety under the current conditions, and serves as the basis for subsequent exhaust configuration recommendations. This represents the equivalent source strength value, which is the main load that the exhaust air must bear. The exhaust air volume must cover the emissions from the source item; otherwise, the concentration will continue to rise. This indicates the supply air volume, which is used to calculate the dilution effect of the supply air on the concentration of pollutants, thereby offsetting part of the exhaust air volume requirement. It indicates the concentration of pollutants in the supplied air; This indicates the target concentration, reflecting the highest permissible pollution concentration that the experimental area hopes to maintain. This represents the initial outflow coefficient, which determines the magnitude of the natural flow rate driven by the pressure difference, and thus determines the pressure difference compensation value; It represents the equivalent area of ​​airflow, the flow capacity of the region's outer shell, and affects the magnitude of the pressure difference compensation value; This indicates air density and affects the natural ventilation capacity driven by pressure difference; This represents the target pressure difference, which is the pressure difference required to ensure that pollution does not escape and to form a negative pressure isolation. It is included in the pressure difference compensation item, resulting in additional exhaust ventilation requirements.

[0051] In this implementation plan, by unifying the pollution source intensity, the dilution effect of the supplied air, and the pressure difference compensation mechanism into the mass conservation framework, a quantifiable assessment of the minimum exhaust volume required to achieve the target concentration and pressure difference conditions in the experimental area is realized. All data in the calculation process comes from spatial energy flow data and fast field prediction sets, ensuring that the parameters are clearly sourced, repeatable, and engineering-applicable. At the same time, unreasonable exhaust results are eliminated through non-negative constraints, so that the obtained minimum exhaust boundary has both physical meaning and can be directly used for subsequent optimization of fan frequency, valve opening, and exhaust configuration, significantly improving the reliability and practicality of exhaust demand calculation.

[0052] Specifically, the process of dynamically correcting adjacent regions based on the energy flow coupling relationship to form the exhaust demand distribution is as follows: The minimum exhaust volume assessment value for each experimental zone is calculated. Based on the energy flow coupling matrix, for each experimental zone, the coupling strength value between the current experimental zone and other experimental zones is extracted, and the maximum value is selected as the regional coupling strength index. The regional coupling strength index is used to quantify the degree of cross-regional airflow disturbance caused by the combined effect of pressure gradient and concentration gradient between adjacent experimental zones, and is a key parameter for determining whether cross-regional exhaust compensation is needed. When an experimental zone is marked as a risk zone or a stagnation-sensitive zone, and the coupling strength index between it and adjacent experimental zones exceeds the coupling threshold, then... The minimum exhaust volume assessment value of the experimental area is subject to a dynamic correction factor greater than 1. This dynamic correction factor reflects the amplification effect of cross-regional energy flow on the pollution diffusion risk of the local area. It is derived from the ventilation network numerical model and simplified CFD proxy model constructed based on the BIM geometric model and pipeline topology. It is obtained by applying unit source intensity pulses to adjacent areas and statistically analyzing the concentration gain. The range is set between 1.05 and 1.30 based on multi-condition simulation statistics. This is used to increase exhaust capacity when cross-regional pollution may backflow or diffuse, forming an active anti-diffusion mechanism. After completing the dynamic correction, the minimum exhaust volume assessment value of each experimental area is used as the target exhaust volume, and the target exhaust volume distribution results are written into the layout optimization database.

[0053] In this implementation plan, by introducing an energy flow coupling matrix and a dynamic correction factor, the pressure difference disturbances and concentration diffusion factors across regions are explicitly quantified, realizing the transformation of exhaust demand from "independent calculation in a single zone" to "coordinated perception across multiple zones." After identifying risk zones or sensitive retention areas, the exhaust capacity is automatically increased, effectively preventing backflow of pollution and cross-zone diffusion, making the exhaust demand distribution more closely match the real physical scenario. Simultaneously, the dynamic correction mechanism maintains data link consistency with subsequent execution vector calculations, equipment selection, and layout optimization, enabling exhaust demand to serve as a directly executable input parameter, enhancing the engineering feasibility and robustness of the overall layout optimization process.

[0054] Specifically, combining exhaust demand distribution and spatial energy flow data, the exhaust volume is mapped to the fan operating frequency and terminal valve opening. The specific process for generating the execution vector is as follows: The target exhaust volume and spatial energy flow data for each experimental zone are read from the layout optimization database; the target exhaust volume is summarized to obtain the total exhaust demand; the exhaust flow rate of each experimental zone is summarized to obtain the actual total exhaust volume; the fan's rated frequency is multiplied by the ratio of the total exhaust demand to the actual total exhaust volume to obtain the fan's nominal frequency value. To ensure operational feasibility, a frequency saturation limit is set during the process of calculating the fan's nominal frequency value. When the fan's nominal frequency value exceeds the fan's maximum allowable operating frequency (1.05 to 1.15 times the rated frequency), it is automatically truncated to the upper limit to avoid... To avoid unexecutable overclocking commands, for each experimental zone, the maximum theoretical exhaust volume is calculated by dividing twice the target pressure difference by the square root of the air density, then multiplying by the initial outflow coefficient and the maximum effective flow area. The required flow ratio is obtained by dividing the target exhaust volume of the experimental zone by the maximum theoretical exhaust volume. The natural logarithm of the required flow ratio is then taken by subtracting it from a constant, and multiplied by the negative reciprocal of the valve damping coefficient to obtain the nominal valve opening value. The valve damping coefficient is derived from the equipment sample parameters to ensure that the opening and flow relationship are consistent with the actual device. The nominal frequency value of the fan and the nominal valve opening value of each experimental zone are combined into an execution vector to provide an executable operating benchmark for subsequent equipment selection, pipe diameter ratio adjustment, and terminal layout optimization.

[0055] The specific formula for the execution vector is as follows:

[0056] ;

[0057] In the formula, Represents the execution vector; This represents the nominal frequency value of the fan, used to map the total exhaust demand to the nominal frequency at which the fan should operate, so that the output capacity of the fan just meets the total exhaust demand of all test areas. This represents the nominal valve opening value. It calculates the flow opening required to meet the exhaust demand, ensuring that the exhaust terminal of each area has exactly the corresponding flow capacity. This indicates the rated frequency of the fan, which serves as a frequency reference so that the nominal frequency can be obtained by scaling it proportionally. This represents the total exhaust ventilation demand, which is the demand side of the fan load. This represents the actual total exhaust volume, which, as the supply side, is used to construct the proportional scaling relationship between supply and demand. This represents the target exhaust volume, i.e., the minimum exhaust volume assessment value, which serves as the primary driving force. This represents the initial outflow coefficient, used to convert the differential pressure driving capacity into the corresponding flow rate limit; This represents the maximum effective circulation area and the maximum theoretical exhaust volume of the affected area. Indicates air density; This represents the target pressure difference, the effective pressure difference that the area can use to drive exhaust ventilation, and determines the maximum achievable exhaust ventilation capacity. This represents the valve damping coefficient. Different valve damping will result in different flow response curves at different opening degrees.

[0058] In this implementation scheme, by mapping the distribution of exhaust demand with spatial energy flow data to the nominal frequency of the fan and the nominal opening of the valve, the quantifiable and executable conversion of exhaust control parameters is achieved. The introduction of fan frequency saturation limits and physical constraints on valve opening ensures that all generated control commands are within the feasible range of the equipment, effectively avoiding unfeasible situations such as over-frequency operation or valve over-limit. Simultaneously, the flow ratio solution constructed based on the maximum theoretical exhaust volume and damping coefficient ensures that valve adjustment is consistent with exhaust demand, thereby achieving accurate matching of exhaust capacity. This mapping mechanism provides a reliable operating benchmark for subsequent equipment selection, pipe diameter optimization, and terminal layout, significantly improving the engineering feasibility and dynamic adaptability of the exhaust system design.

[0059] Specifically, the process of optimizing equipment selection, pipe diameter ratio, and terminal layout based on execution vectors is as follows: Layout suggestions are generated based on execution vectors: According to the maximum air volume output capacity corresponding to the nominal frequency value of the fan, the range of fan models that can cover the requirements is selected from the fan equipment sample library; the fan equipment sample library comes from the manufacturer's technical parameter table, which includes the fan air volume frequency characteristic curve, rated power and efficiency parameters, and can be automatically queried and matched through indexing. The fan's operating margin is assessed based on the difference between its nominal frequency and rated frequency, generating a list of recommended models for different capacity levels. If multiple fans can operate in parallel, parallel combination suggestions are provided. For scenarios with multiple fans operating in parallel, the nominal frequency value of the fans is allocated according to the proportion of each fan's operating margin based on the airflow distribution matrix, avoiding overload operation of a single fan and ensuring that the overall airflow meets the total exhaust demand. The target exhaust volume is converted into the minimum equivalent cross-sectional area under the recommended flow velocity conditions, and combined with the nominal valve opening value and the maximum effective flow area, it is determined whether the actual flow capacity of the experimental area meets the requirements. If the capacity is insufficient, pipe diameter enlargement suggestions are generated, and pipe diameter matching schemes are output. The minimum equivalent cross-sectional area is based on the exhaust system design requirements in the Ventilation and Air Conditioning Engineering Design Code and the Laboratory Building Technical Code, selecting a branch pipe design velocity range of 6 to 9 m / s. The equivalent cross-sectional area is calculated based on the surrounding area. 6 m / s is used as the lower limit for noise and energy-constrained spaces, and 9 m / s is used as the upper limit for branch pipes to avoid excessive wind resistance and pipeline vibration, ensuring that the wind speed range is feasible and verifiable. The maximum effective flow area is derived from the sample parameters of the terminal equipment, ensuring that the calculation is reproducible and consistent with engineering requirements. The required number of terminal equipment is determined based on the nominal valve opening value, the target exhaust volume of the experimental area, and the rated emission characteristics of a single terminal equipment. Combined with the stagnant sensitive area and the cross-area energy flow path reflected by the energy flow coupling matrix, the terminal equipment is preferentially placed in key locations, generating a layout scheme for the number of terminals, terminal types, and specific spatial coordinates. The rated emission characteristics of the terminal equipment are derived from the product sample parameters. The spatial coordinates are automatically located based on the spatial topology in the BIM model, ensuring that the terminal layout results can be directly used to generate construction layout drawings. The nominal frequency value of the fan is combined with the nominal valve opening value of each test area for consistency verification. Test areas that fail the consistency verification are subject to layout correction. The consistency verification includes exhaust volume balance verification, valve 0-100% executability range verification, and main pipeline differential pressure backflow risk verification. The verification algorithm is based on recalculation of the fast field prediction set, thereby ensuring that the layout scheme is actually executable. The execution vector and layout suggestions are written into the layout optimization database.

[0060] This implementation plan automates, parametricizes, and verifies the optimization of fan selection, pipe diameter matching, and terminal layout. It can generate layout schemes that meet exhaust requirements based on fan operating margin, minimum equivalent cross-sectional area, valve opening, and terminal discharge capacity, ensuring that flow capacity, equipment operating range, and differential pressure direction all meet the feasibility of the project. At the same time, the plan improves the operational safety and stability of the scheme through differential pressure backflow testing and exhaust balance verification, so that the layout results can be directly written into the BIM model for construction, commissioning, and operation and maintenance, realizing full-link controllability and efficient closed-loop of layout design from calculation to implementation.

[0061] Specifically, the process of constructing a candidate layout generation and source strength, exhaust, and execution vector integrated evaluation mechanism under multi-objective constraints, screening and obtaining optimized solutions, and writing the optimized solutions back to the BIM model is as follows: Spatial geometric parameters, equipment source characteristics, target exhaust volume distribution, nominal valve opening values, and layout suggestions are read from the layout optimization database. Layout constraints are constructed, including at least the following three categories: First, spatial safety constraints, defining the minimum safe distance between equipment and walls, passageways, and hazardous sources, preferably not less than 0.4m, to avoid affecting personnel evacuation and maintenance operations after equipment layout; second, pipeline performance constraints, limiting the maximum allowable pressure loss of branch pipes and main pipes, preferably not exceeding the design specification recommended values ​​such as 80 to 120Pa, to ensure that the exhaust system operates within a controllable resistance range; third, equipment operation and environmental constraints, including the upper limit of fan power, noise limits, and the maximum number of terminal equipment that can be installed, to ensure that the layout scheme meets the actual building acoustic environment and energy consumption limitations. Candidate layout schemes are generated through an automated layout generation method. This method, based on BIM spatial grid generation, a terminal layout rule base, and a collision detection algorithm, automatically generates different terminal layout arrangements, pipe diameter combinations, and equipment selection combinations while meeting layout constraints. This enables rapid layout scheme formation and ensures the legality of spatial boundaries and the absence of component intersection conflicts. For each candidate layout scheme, equivalent source strength values, minimum exhaust volume assessment values, and execution vector calculation steps are invoked to obtain the corresponding source strength characteristic data, target exhaust volume distribution, and execution vector, generating scheme evaluation results. Based on the scheme evaluation results, a multi-objective non-dominated sorting is performed to obtain a Pareto optimal scheme set. The multi-objective evaluation includes dimensions such as pollution purification efficiency, energy consumption cost, equipment quantity, pipeline complexity, and exhaust balance to ensure that the selected Pareto schemes have comprehensive engineering optimality. A recommended layout scheme is then selected from the Pareto optimal scheme set. Based on the recommended layout scheme, the fan selection results, pipe diameter configuration, number of terminal equipment, and spatial coordinate parameters are written back to the BIM model to generate design parameter tables, installation sequence suggestions, and operation and maintenance delivery data for construction and commissioning. The layout write-back is automatically completed through the BIM interface of the Revit API, ensuring that the parameters, components and coordinate positions correspond one-to-one with the construction model, realizing a practical application from the algorithm to the construction end.

[0062] This implementation plan achieves closed-loop optimization of the entire process from layout scheme generation and evaluation to BIM back-writing by introducing quantifiable layout constraints, an automated layout generation mechanism, and a multi-objective integrated evaluation based on source strength, exhaust ventilation, and execution vectors. Verifiable constraints such as minimum safety distance, pressure loss limit, and equipment operation restrictions ensure the engineering feasibility of the layout results. By using multi-objective non-dominated sorting to obtain the Pareto scheme that balances safety, energy efficiency, and layout rationality, the final layout achieves a balance between pollution control, energy consumption cost, and installation accessibility, significantly improving the reliability, intelligence, and feasibility of laboratory ventilation layout optimization.

[0063] Reference Figure 2 As shown, the second aspect of the present invention provides a laboratory intelligent layout optimization system for multi-energy experimental buildings, applied to the aforementioned laboratory intelligent layout optimization method for multi-energy experimental buildings, including: a data base and preprocessing module, used to analyze the geometric structure of the experimental area, equipment source items and design indicators based on a multi-source spatial data system constructed by BIM, to form spatial energy flow data, and to perform data preprocessing on the spatial energy flow data; an equivalent source strength identification module, used to identify the influence intensity of pollution sources in the experimental area based on the spatial energy flow data, and to determine the leakage trend and retention tendency, while quantifying the risk status of the experimental area and extracting the energy flow coupling relationship between areas; and a minimum exhaust volume synthesis module, used to synthesize based on the pollution source strength. The system assesses the intensity of pollution source impact, integrates spatial energy flow data, evaluates the minimum exhaust boundary required for the experimental area to meet target conditions, and dynamically corrects adjacent areas based on energy flow coupling relationships between regions to form an exhaust demand distribution. The execution vector and terminal mapping module combines the exhaust demand distribution with spatial energy flow data to map exhaust volume to fan operating frequency and terminal valve opening, generating execution vectors. Based on these execution vectors, it optimizes equipment selection, pipe diameter ratios, and terminal layout. The multi-scheme optimization and BIM write-back module constructs a candidate layout generation and integrated evaluation mechanism for source strength, exhaust, and execution vectors under multi-objective constraints, filters and obtains optimized schemes, and writes these optimized schemes back to the BIM model.

[0064] This implementation plan quantifies the entire process of pollution source intensity identification, regional risk assessment, cross-regional coupling analysis, minimum exhaust volume calculation, and dynamic correction by constructing a multi-source spatial data system covering geometric structure, equipment source items, and ventilation parameters. By mapping exhaust demand to fan frequency and valve opening, and further optimizing equipment selection, pipe diameter ratio, and terminal layout, ventilation design is transformed from a static experience-based model to a refined decision-making system based on source strength, energy flow, and execution vectors. Finally, layout schemes are selected through multi-objective non-dominated ranking and written back to BIM, achieving a closed-loop optimization of the entire chain from data modeling and evaluation calculation to scheme generation, significantly improving the safety, adaptability, and feasibility of laboratory layout.

[0065] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0066] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. As those skilled in the art will understand, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A method for optimizing the intelligent layout of laboratories in multi-energy experimental buildings, characterized in that, Includes the following steps: S1, based on the multi-source spatial data system constructed by BIM, analyzes the geometric structure, equipment source items and design indicators of the experimental area to form spatial energy flow data, and performs data preprocessing on the spatial energy flow data; S2, based on spatial energy flow data, identify the intensity of pollution source impact in the experimental area, determine leakage trends and retention tendencies, quantify the risk status of the experimental area, and extract the energy flow coupling relationship between regions; The specific process of judging leakage trends and retention tendencies, quantifying the risk status of the experimental area, and extracting the energy flow coupling relationship between regions is as follows: The equivalent source strength value of each experimental area is calculated. The equivalent source strength value is smoothed and trend-fitted on the time axis to identify the peak period and duration of the equivalent source strength value, forming a source strength fluctuation curve. The stagnation sensitive area where the equivalent source strength value exceeds the intensity threshold and the gas concentration change rate is higher than the average gas concentration change rate in the region is marked. The regional risk value is obtained by calculating the ratio of the peak value of the equivalent source strength to the average value of the equivalent source strength in each experimental area. When the regional risk value exceeds the risk threshold, the area is marked as a risk area; and a heat map of airflow stagnation is generated. For any adjacent experimental zones, the pressure gradient and concentration gradient are calculated respectively. The pressure gradient is multiplied by twice the air density and the square root is taken. Then, the square root is multiplied by the equivalent area of ​​the airflow and the initial outflow coefficient to obtain the net cross-zone airflow. When both the pressure gradient and the concentration gradient exceed the corresponding gradient threshold and there is an actual net cross-zone airflow, the experimental zones are determined to constitute a cross-influence region. The product of the net cross-zone airflow, the pressure gradient, and the concentration gradient is used as the coupling strength value to construct the energy-fluid coupling matrix. The equivalent source strength value, regional risk value and energy flow coupling matrix are uniformly encapsulated into a source strength feature data package and written into the layout optimization database; S3, based on the intensity of pollution source impact and comprehensive spatial energy flow data, assesses the minimum exhaust boundary required for the experimental area to reach the target conditions, and performs dynamic correction on adjacent areas in combination with the energy flow coupling relationship between regions to form the exhaust demand distribution; The specific process of dynamically correcting adjacent regions based on the energy flow coupling relationship between combined regions to form the exhaust demand distribution is as follows: The minimum exhaust volume assessment value of each experimental zone is calculated. Based on the energy flow coupling matrix, for each experimental zone, the coupling strength value between the current experimental zone and other experimental zones is extracted, and the maximum value is selected as the regional coupling strength index. When an experimental zone is marked as a risk zone or a stagnation sensitive zone, and the coupling strength index between it and the adjacent experimental zone exceeds the coupling threshold, a dynamic correction factor greater than 1 is introduced into the minimum exhaust volume assessment value of the experimental zone. After the dynamic correction is completed, the minimum exhaust volume assessment value of each experimental zone is used as the target exhaust volume, and the target exhaust volume distribution results are written into the layout optimization database. S4, combining exhaust demand distribution and spatial energy flow data, maps exhaust volume to fan operating frequency and terminal valve opening to generate execution vector; Optimize equipment selection, pipe diameter ratio, and terminal layout based on execution vectors; S5 constructs a candidate layout generation and source strength, exhaust and execution vector integrated evaluation mechanism under multi-objective constraints, screens and obtains the optimized solution, and writes the optimized solution back to the BIM model.

2. The intelligent layout optimization method for multi-energy experimental buildings according to claim 1, characterized in that, The multi-source spatial data system based on BIM analyzes the geometric structure, equipment source items, and design indicators of the experimental area to form spatial energy flow data. The specific process of preprocessing the spatial energy flow data is as follows: By analyzing the BIM geometric model, the spatial geometric parameters of each experimental area are obtained, including room volume, spatial connectivity area, door and window grid geometry, pipe network topology and net height. Based on the door and window grid geometry, the airflow equivalent area is obtained by multiplying the physical opening area of ​​the door and window grid by the structure type correction coefficient, and different initial outflow coefficients are assigned according to the structure type. Equipment source features were extracted from equipment samples and design specifications, including the rated frequency of the fans in the experimental area, the heat dissipation and emission characteristics of each device at rated power, the maximum effective flow area of ​​various terminal devices, and the valve damping coefficient. Target indicators for the experimental area were defined based on design specifications, including target concentration, target pressure difference, minimum air change rate, and cleanliness. A numerical model of the ventilation network was used, combined with a network flow solving algorithm based on the pipe network topology, to predict and collect a fast field prediction set, including gas concentration, pressure difference, supply air concentration, supply air flow rate, and exhaust air flow rate. Air density was determined based on the design temperature and humidity curves. Spatial geometric parameters, equipment source term characteristics, target indicators, fast field prediction sets, and air density are uniformly recorded as spatial energy flow data; The spatial energy flow data is aligned with the coordinate system by uniform time step, and outliers are removed by median absolute deviation and quantile detection. Missing data are smoothed and filled by spline interpolation and moving average. At the same time, the spatial energy flow data is normalized. A layout optimization database is established and the preprocessed spatial energy flow data is written into the layout optimization database.

3. The intelligent layout optimization method for multi-energy experimental buildings according to claim 1, characterized in that, The specific process for identifying the intensity of pollution source impact within the experimental area based on spatial energy flow data is as follows: Acquire spatial energy flow data, calculate the gas concentration difference between the current time and the previous time for each experimental area, divide by the time step to obtain the gas concentration change rate, and multiply the gas concentration change rate by the room volume to obtain the concentration accumulation. Multiply the non-negative pressure difference by twice the air density, take the square root, and then multiply by the equivalent area of ​​the airflow and the initial outflow coefficient to obtain the leakage flow rate; add the leakage flow rate to the exhaust flow rate and multiply by the gas concentration at the current moment to obtain the effective emission rate; Multiply the supply air flow rate by the supply air concentration to obtain the supply air dilution offset; add the concentration accumulation to the effective emission and subtract the supply air dilution offset to obtain the equivalent source strength value.

4. The intelligent layout optimization method for multi-energy experimental buildings according to claim 1, characterized in that, The specific process of assessing the minimum exhaust boundary required for the experimental area to achieve the target conditions based on the intensity of pollution source impact and comprehensive spatial energy flow data is as follows: Receive source strength characteristic data packets and acquire spatial energy flow data; for each experimental zone, multiply the difference between the supply air concentration and the target concentration by the supply air flow rate to obtain the supply air load deduction value; multiply the target pressure difference by twice the air density, take the square root, and then multiply by the equivalent area of ​​the airflow, the initial outflow coefficient, and the target concentration to obtain the pressure difference compensation value. The minimum exhaust volume assessment value is obtained by adding the pressure difference compensation value to the difference between the equivalent source strength value and the supply air load deduction value, and then dividing by the target concentration. The minimum exhaust volume assessment value is then subjected to a non-negative operation.

5. The intelligent layout optimization method for multi-energy experimental buildings according to claim 1, characterized in that, The specific process of combining exhaust demand distribution and spatial energy flow data to map exhaust volume to fan operating frequency and terminal valve opening to generate execution vectors is as follows: Read the target exhaust volume and spatial energy flow data of each experimental area from the layout optimization database, summarize the target exhaust volume to obtain the total exhaust demand; summarize the exhaust flow of each experimental area to obtain the actual total exhaust volume; multiply the rated frequency of the fan by the ratio of the total exhaust demand to the actual total exhaust volume to obtain the nominal frequency value of the fan. For each experimental zone, the maximum theoretical exhaust volume is obtained by dividing twice the target pressure difference by the square root of the air density, multiplying by the initial outflow coefficient and the maximum effective flow area; the required flow ratio is obtained by dividing the target exhaust volume of the experimental zone by the maximum theoretical exhaust volume, and the natural logarithm is obtained by subtracting the required flow ratio from the constant, multiplying by the negative reciprocal of the valve damping coefficient, and obtaining the nominal valve opening value; the nominal fan frequency value and the nominal valve opening value of each experimental zone are combined to form an execution vector.

6. The intelligent layout optimization method for multi-energy experimental buildings according to claim 1, characterized in that, The specific process for optimizing equipment selection, pipe diameter ratio, and terminal layout based on execution vectors is as follows: Layout recommendations are generated based on execution vectors: Based on the maximum air volume output capacity corresponding to the nominal frequency value of the fan, the range of fan models that can cover the requirements is selected from the fan equipment sample library; the fan operating margin is evaluated based on the difference between the nominal frequency value and the rated frequency of the fan, and a list of recommended models for different capacity levels is generated; if multiple fans can be operated in parallel, parallel combination suggestions are given. The target exhaust volume is converted into the minimum equivalent cross-sectional area under the recommended flow rate conditions. Combined with the nominal valve opening value and the maximum effective flow area, it is determined whether the actual flow capacity of the experimental area meets the requirements. If the capacity is insufficient, a pipe diameter enlargement suggestion is generated and a pipe diameter matching scheme is output. The required number of terminal devices is determined based on the nominal valve opening value, the target exhaust volume of the experimental area, and the rated emission characteristics of a single terminal device. Combined with the cross-area energy flow path reflected by the stagnation sensitive area and the energy flow coupling matrix, the terminal devices are preferentially arranged in key locations to generate an arrangement scheme for the number of terminals, terminal types, and specific spatial coordinates. The nominal frequency value of the fan is combined with the nominal valve opening value of each test area for consistency verification. For test areas that fail the consistency verification, layout correction is performed. The execution vector and layout suggestions are written into the layout optimization database.

7. The intelligent layout optimization method for multi-energy experimental buildings according to claim 1, characterized in that, The specific process of constructing a candidate layout generation and integrated evaluation mechanism based on source strength, ventilation, and execution vector under multi-objective constraints, screening and obtaining optimized solutions, and writing the optimized solutions back to the BIM model is as follows: The system reads spatial geometric parameters, equipment source term characteristics, target exhaust volume distribution, nominal valve opening values, and layout suggestions from the layout optimization database to construct layout constraints. Candidate layout schemes are generated using an automated layout generation method. For each candidate layout scheme, the system calls the equivalent source strength value, minimum exhaust volume evaluation value, and execution vector calculation steps to obtain the corresponding source strength feature data, target exhaust volume distribution, and execution vector, and generates scheme evaluation results. Based on the scheme evaluation results, a multi-objective non-dominated ranking is performed to obtain a Pareto optimization scheme set, and a recommended layout scheme is selected from the Pareto optimization scheme set. Based on the recommended layout scheme, the wind turbine selection results, pipe diameter configuration, number of terminal equipment and spatial coordinate parameters are written back to the BIM model to generate design parameter tables, installation sequence suggestions and operation and maintenance delivery data for construction and commissioning.

8. A laboratory intelligent layout optimization system for multi-energy experimental buildings, used to implement the laboratory intelligent layout optimization method for multi-energy experimental buildings as described in any one of claims 1-7, characterized in that, include: The data base and preprocessing module are used to analyze the geometric structure, equipment source items and design indicators of the experimental area based on the multi-source spatial data system built by BIM, form spatial energy flow data, and perform data preprocessing on the spatial energy flow data; The equivalent source strength identification module is used to identify the intensity of pollution source impact in the experimental area based on spatial energy flow data, and to determine the leakage trend and retention tendency. At the same time, it quantifies the risk status of the experimental area and extracts the energy flow coupling relationship between regions. The minimum exhaust volume synthesis module is used to assess the minimum exhaust boundary required for the experimental area to reach the target conditions based on the intensity of pollution source impact and comprehensive spatial energy flow data. It also performs dynamic correction on adjacent areas in combination with the energy flow coupling relationship between regions to form the exhaust demand distribution. The execution vector and terminal mapping module is used to combine the exhaust demand distribution and spatial energy flow data to map the exhaust volume to the fan operating frequency and terminal valve opening, and generate the execution vector. Optimize equipment selection, pipe diameter ratio, and terminal layout based on execution vectors; The multi-scheme optimization and BIM write-back module is used to build a candidate layout generation and source strength, ventilation and execution vector integrated evaluation mechanism under multi-objective constraints, screen and obtain optimized schemes, and write the optimized schemes back to the BIM model.

Images