Green construction evaluation method and system

Abstract

The invention belongs to the technical field of constructional engineering management, and particularly relates to a green construction evaluation method and system.The method comprises the steps that S101, energy consumption data, material use data and environmental parameters of a construction site are collected in real time through Internet of Things monitoring equipment; s102, constructing a multi-dimensional evaluation index system including resource utilization efficiency, carbon emission intensity and an environmental influence coefficient based on a BP neural network model; s103, calculating a dynamic weight coefficient by adopting an analytic hierarchy process in combination with a time factor; s104, generating a green construction comprehensive score by using a fuzzy comprehensive evaluation algorithm; and S105, carrying out iterative optimization on the evaluation model based on a reinforcement learning algorithm. Different from a traditional static evaluation mode, various data of a construction site are collected in real time by means of Internet of Things monitoring equipment, and dynamic monitoring of the construction process is achieved. From energy consumption data to environmental parameters, each link can be fed back in time, so that a manager can master the green construction condition of a project at any time, and is not limited to one-time evaluation at a completion acceptance stage any more.

Description

Technical Field

[0001] The present invention belongs to the technical field of construction engineering management, and in particular relates to a green construction evaluation method and system. Background Art

[0002] Currently, carbon emissions from the construction industry account for more than 40% of the global total. Traditional green construction evaluation has the following problems: Static evaluation mode: relying on a one-time evaluation at the completion acceptance stage (such as the Green Building Evaluation Standard GB / T50378), lacking dynamic monitoring of the construction process; Single data collection: mainly relying on manual reporting, which results in data lag and subjectivity; The evaluation model is rigid: the weight coefficient is fixed and cannot adapt to the differentiated needs of different regions and climate conditions; Low level of visualization: Results are mainly presented in text reports, lacking intuitive expression of spatial information.

[0003] Existing technologies such as "A Green Construction Evaluation System Based on BIM" disclosed in CN113052446A only realize the simple association between BIM models and evaluation indicators, and do not solve the problems of dynamic data fusion and model self-optimization. Therefore, an improved green construction evaluation method and system are designed. Summary of the invention

[0004] In view of the above-mentioned deficiencies in the prior art, the present invention provides a green construction evaluation method and system to solve the above-mentioned problems in the background technology.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions: A green construction evaluation method comprises the following steps: S101. Collect energy consumption data, material usage data and environmental parameters of the construction site in real time through IoT monitoring equipment; S102. Construct a multi-dimensional evaluation index system including resource utilization efficiency, carbon emission intensity and environmental impact coefficient based on the BP neural network model; S103. Calculate the dynamic weight coefficient by using the analytic hierarchy process combined with the time factor; S104. Generate a comprehensive score of green construction using a fuzzy comprehensive evaluation algorithm; S105. Iteratively optimize the evaluation model based on the reinforcement learning algorithm.

[0006] Furthermore, the Internet of Things monitoring device includes: Energy consumption monitoring sensors to collect data on water and electricity used at the construction site; RFID material identification devices, used to identify and track construction materials; Environmental monitoring module, including PM2.5 sensor and noise sensor, is used to monitor the air quality and noise intensity at the construction site.

[0007] Furthermore, the construction of the multi-dimensional evaluation index system includes: Resource Dimension: Main material loss rate , which means calculating the total amount of main material input M in (Unit: tons) and actual usage M out The difference in tons is used as a percentage of the total input to measure the loss of main materials; The calculation formula of water resource reuse rate is: , that is, the amount of water reused W reuse (Unit: cubic meter) Percentage of total water consumption W total (Unit: cubic meter) percentage; Environmental Dimension: Dust concentration C d (Unit: μg / m³); The noise mean is given by the formula Calculate, where N i is the noise value collected each time (unit: dB), and N is the number of collections; Carbon Dimension: Mechanical carbon emissions F c =∑E j ×f j (Unit: kgCO2 / kWh), E j is the energy consumption of the jth machine (unit: kWh), f j is the carbon emission coefficient of the jth machine (unit: kgCO2 / kWh), and the total carbon emission of the machine is obtained by summing the product of the energy consumption of different machines and the corresponding carbon emission coefficient; Transport Carbon Emissions E trans =∑D t,k × k ×e trans (Unit: kgCO2), D t,k is the transportation distance of the kth material (unit: km), w k is the weight of the kth material (unit: tons), e trans is the transport carbon emission coefficient (unit: kgCO2 / (t km)), and the total carbon emissions during material transportation are obtained by multiplying and summing the three, reflecting the impact of the transportation link on carbon emission intensity.

[0008] Furthermore, the calculation of the dynamic weight coefficient includes: , where w i (t) is the dynamic weight of the ith indicator at time t, which reflects the impact of the indicator on the green construction evaluation results at the current moment, and w i 0 is the initial weight of the ith indicator, which is the weight value determined based on experience or preliminary analysis at the beginning of the evaluation. is the adjustment coefficient (value range 0.1-0.3), which is used to control the adjustment range of indicator weights over time or indicator scores to adapt to the dynamic changes in the importance of each indicator in different stages or scenarios. i (t) is the score change rate of the i-th indicator at time t. The weight is dynamically adjusted according to the change of the indicator score at different times; Normalization processing; , through normalization, the sum of all indicator weights is made to be 1, ensuring the rationality and comparability of the weights, and finally obtaining the dynamic weight coefficient for green construction evaluation.

[0009] Furthermore, the fuzzy comprehensive evaluation includes: Using normal distribution membership function: This function is used to measure the degree of membership of carbon emission intensity x (unit: kg / m²) in green building evaluation, with 50 as the center value and 15 as the standard deviation. The μ(x) value calculated by this function represents the membership level of carbon emission intensity x in green building evaluation. The closer the value is to 1, the more the carbon emission intensity meets the requirements of green building. Comprehensive score calculation: S1=∑B j ×c j , where B = W × R, W is the indicator weight vector, which is determined by the dynamic weight coefficient and reflects the relative importance of each evaluation indicator; R is the fuzzy relationship matrix, which is composed of the membership of each indicator to different comment sets; B j is the element in the fuzzy evaluation result vector, obtained by matrix operation W×R; c j is the comment score (in percentage). The green construction comprehensive score S1 is calculated by this formula, which fully reflects the overall level of the green construction project.

[0010] Furthermore, the iterative optimization of the evaluation model based on the reinforcement learning algorithm includes: Reward function: , R t is the reward value at the tth moment, which is used to evaluate the optimization effect of the model at that moment, ΔS t is the comprehensive score change rate, which reflects the change of the green construction comprehensive score at different times and reflects the contribution of the model to the optimization of the overall evaluation results; ΔEt is the environmental parameter improvement value, which is calculated by calculating the change value ΔE of each environmental parameter. t,k With the corresponding weight β k The sum of the products is obtained, which reflects the effect of the model on optimizing the environment-related indicators; Q-learning update: , Q(s t ,a t ) is in state s t Take action a t The state-action value function records the expected long-term return of taking a specific action in a specific state. γ is the discount factor, ranging from 0.8 to 0.95, which is used to balance the impact of current rewards and future rewards on model decisions. The closer γ is to 1, the more the model values ​​future rewards. t is the system state at time t, which is composed of various evaluation index values ​​and fully reflects the various characteristics of the current green construction project; a t The action taken at the tth moment is continuously updated through the formula, so that the model can continuously optimize the decision according to the reward feedback and realize the iterative optimization of the evaluation model.

[0011] Furthermore, the comment set V in the fuzzy comprehensive evaluation is {excellent, good, medium, qualified, unqualified}, and the corresponding score c j They are {95, 85, 75, 65, 55} respectively. The comment set and corresponding scores are clarified to make the evaluation results more standardized and accurate, facilitate the classification and evaluation of green construction projects, and enhance the operability and consistency of the evaluation method.

[0012] A green construction evaluation system, comprising: M1. Data acquisition module: including IoT monitoring equipment, responsible for real-time and accurate collection of various data on the construction site, providing a data basis for subsequent analysis and evaluation; M2. Evaluation model module: Integrate BP neural network and analytic hierarchy process, use the powerful nonlinear fitting ability of BP neural network to model the multi-dimensional evaluation index system, and analytic hierarchy process is used to determine the weight of each index. The combination of the two can achieve a comprehensive and accurate evaluation of green construction projects; M3. Dynamic adjustment module: Updates model parameters based on the reinforcement learning algorithm and continuously optimizes the evaluation model according to the feedback of the reward function, so that it can adapt to the green construction evaluation needs of different projects and different stages, and improve the accuracy and effectiveness of the evaluation; M4. Visualization module: The evaluation results are displayed through a 3D GIS platform, presenting the evaluation results of green construction projects in an intuitive and visual way, including the spatial distribution of the projects, the performance of various indicators, etc., to facilitate user understanding and decision-making.

[0013] Furthermore, the 3D GIS platform supports: 1:500 detailed modeling: It is capable of high-precision modeling of the construction project and the surrounding environment at a scale of 1:500, showing the project's terrain, building structure, and facility layout information in detail to ensure the accuracy and reliability of the model. The real-time data dashboard is linked with the 3D simulation model to display optimization suggestions: The real-time data dashboard displays the evaluation index data of the project in real time and is linked with the 3D simulation model. When the index data is abnormal or does not meet the green construction requirements, the optimization suggestions can be intuitively displayed on the 3D simulation model to guide the improvement and optimization of the project.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. Dynamic monitoring and real-time evaluation: Different from the traditional static evaluation mode, the present invention uses the Internet of Things monitoring equipment to collect various data on the construction site in real time, realizing dynamic monitoring of the construction process. From energy consumption data to environmental parameters, every link can be fed back in time, allowing managers to grasp the green construction status of the project at any time, no longer limited to a one-time evaluation at the completion acceptance stage, greatly improving the timeliness and accuracy of the evaluation.

[0015] 2. Multi-source data fusion and accurate collection: The use of a variety of sensors and identification devices has achieved diversified and automated data collection. Energy consumption monitoring sensors, RFID material identification devices and environmental monitoring modules work together to avoid the lag and subjectivity caused by manual data reporting. The real-time and accuracy of the data provides a reliable basis for subsequent evaluation and decision-making, ensuring that the evaluation results can truly reflect the actual situation of the project.

[0016] 3. Adaptive evaluation model: The dynamic weight coefficient is calculated by combining the hierarchical analysis method with the time factor, so that the evaluation model can adapt to the differentiated needs of different regions, climate conditions and different stages of the project. The weight is no longer fixed, but is dynamically adjusted according to the actual performance and importance of each indicator, which improves the scientificity and flexibility of the evaluation. Whether it is a resource-rich area or an environmentally sensitive area, the evaluation system of the present invention can give reasonable and accurate evaluation results.

[0017] 4. Intuitive visual presentation: Through the visualization of the 3D GIS platform, the green construction evaluation results are presented in the form of intuitive spatial information. The linkage between the real-time data dashboard and the 3D simulation model allows users to understand at a glance the performance of various indicators of the project, as well as the specific location of the problem and the corresponding optimization suggestions. This visualization method greatly improves the efficiency of information transmission, facilitates managers to make decisions, and promotes the project to develop in a greener and more environmentally friendly direction.

[0018] 5. Model self-optimization and continuous improvement: The iterative optimization mechanism based on the reinforcement learning algorithm enables the evaluation model to be continuously optimized according to the feedback during the project implementation process. The design of the reward function encourages the adoption of measures that are conducive to improving the level of green construction. By continuously adjusting the model parameters, the evaluation results are becoming more and more accurate, and at the same time, it also provides strong support for the continuous improvement of the project. As the project progresses, the evaluation system can continuously adapt to new situations and maintain the effectiveness and advancement of the evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flow chart of a green construction evaluation method of the present invention; Figure 2 A block diagram of a green construction evaluation method of the present invention; Figure 3 This is a diagram showing the structure of the Internet of Things monitoring device in the present invention; DETAILED DESCRIPTION In order to enable those skilled in the art to better understand the present invention, the technical solution of the present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0020] Among them, the drawings are only used for illustrative explanations, and they only represent schematic diagrams rather than actual pictures, and should not be understood as limitations on the present invention. In order to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of actual products. For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0021] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "inside", "outside", etc. appear to indicate the orientation or position relationship, it is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the terms describing the position relationship in the drawings are only used for illustrative purposes and cannot be understood as a limitation on the present invention. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0022] In the description of the present invention, unless otherwise clearly specified and limited, if the term "connection" or the like appears to indicate the connection relationship between components, the term should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two components or the interaction relationship between two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0023] Embodiment 1: like Figure 1-3 Specifically, a green construction evaluation method includes the following steps: S101. Collect energy consumption data, material usage data and environmental parameters of the construction site in real time through IoT monitoring equipment; S102. Construct a multi-dimensional evaluation index system including resource utilization efficiency, carbon emission intensity and environmental impact coefficient based on the BP neural network model; S103. Calculate the dynamic weight coefficient by using the analytic hierarchy process combined with the time factor; S104. Generate a comprehensive score of green construction using a fuzzy comprehensive evaluation algorithm; S105. Iteratively optimize the evaluation model based on the reinforcement learning algorithm.

[0024] Furthermore, the Internet of Things monitoring device (T1) includes: Energy consumption monitoring sensor (T11), used to collect water and electricity data used at the construction site; RFID material identification device (T12), used to identify and track construction materials; Environmental monitoring module (T13), including PM2.5 sensor and noise sensor, is used to monitor the air quality and noise intensity at the construction site.

[0025] Furthermore, the construction of the indicator system (I1) includes: Resource Dimension: Main material loss rate , which means calculating the total input of main materials M in (Unit: tons) and actual usage M out The difference in tons is used as a percentage of the total input to measure the loss of main materials; The calculation formula of water resource reuse rate is: , that is, the amount of water reused W reuse (Unit: cubic meter) Percentage of total water consumption W total (Unit: cubic meter) percentage; Environmental Dimension: Dust concentration C d (Unit: μg / m³); The noise mean is given by the formula Calculate, where N i is the noise value collected each time (unit: dB), and N is the number of collections; Carbon Dimension: Mechanical carbon emissions F c =∑E j ×f j (Unit: kgCO2 / kWh), E j is the energy consumption of the jth machine (unit: kWh), f j is the carbon emission coefficient of the jth machine (unit: kgCO2 / kWh), and the total carbon emission of the machine is obtained by summing the product of the energy consumption of different machines and the corresponding carbon emission coefficient; Transport Carbon Emissions E trans =∑D t,k × k ×e trans (Unit: kgCO2), D t,k is the transportation distance of the kth material (unit: km), w k is the weight of the kth material (unit: tons), e trans is the transport carbon emission coefficient (unit: kgCO2 / (t km)), and the total carbon emissions during material transportation are obtained by multiplying and summing the three, reflecting the impact of the transportation link on carbon emission intensity.

[0026] Furthermore, the calculation of the dynamic weight coefficient (W1) includes: , where w i (t) is the dynamic weight of the ith indicator at time t, which reflects the impact of the indicator on the green construction evaluation results at the current moment, and w i 0 is the initial weight of the ith indicator, which is the weight value determined based on experience or preliminary analysis at the beginning of the evaluation. is the adjustment coefficient (value range 0.1-0.3), which is used to control the adjustment range of indicator weights over time or indicator scores to adapt to the dynamic changes in the importance of each indicator in different stages or scenarios. i (t) is the score change rate of the i-th indicator at time t. The weight is dynamically adjusted according to the change of the indicator score at different times; Normalization processing; , through normalization, the sum of all indicator weights is made to be 1, ensuring the rationality and comparability of the weights, and finally obtaining the dynamic weight coefficient (W1) for green construction evaluation.

[0027] Furthermore, the fuzzy comprehensive evaluation (M3) includes: Using normal distribution membership function: This function is used to measure the degree of membership of carbon emission intensity x (unit: kg / m²) in green building evaluation, with 50 as the center value and 15 as the standard deviation. The μ(x) value calculated by this function represents the membership level of carbon emission intensity x in green building evaluation. The closer the value is to 1, the more the carbon emission intensity meets the requirements of green building. Comprehensive score calculation: S1=∑B j ×c j , where B = W × R, W is the indicator weight vector, which is determined by the dynamic weight coefficient (W1) and reflects the relative importance of each evaluation indicator; R is the fuzzy relationship matrix, which is composed of the membership of each indicator to different comment sets; B j is the element in the fuzzy evaluation result vector, obtained by matrix operation W×R; c j is the comment score (in percentage). The green construction comprehensive score S1 is calculated by this formula, which fully reflects the overall level of the green construction project.

[0028] Furthermore, the reinforcement learning optimization (U1) includes: Reward function: , R t is the reward value at the tth moment, which is used to evaluate the optimization effect of the model at that moment, ΔS t is the comprehensive score change rate, which reflects the change of the green construction comprehensive score at different times and reflects the contribution of the model to the optimization of the overall evaluation results; ΔE t is the environmental parameter improvement value, which is calculated by calculating the change value ΔE of each environmental parameter. t,k With the corresponding weight β k The sum of the products is obtained, which reflects the effect of the model on optimizing the environment-related indicators; Q-learning update: , Q(s t ,a t ) is in state s t Take action a tThe state-action value function records the expected long-term return of taking a specific action in a specific state. γ is the discount factor, ranging from 0.8 to 0.95, which is used to balance the impact of current rewards and future rewards on model decisions. The closer γ is to 1, the more the model values ​​future rewards. t is the system state at time t, which is composed of various evaluation index values ​​and fully reflects the various characteristics of the current green construction project; a t The action taken at the tth moment is continuously updated through the formula, so that the model can continuously optimize the decision according to the reward feedback and realize the iterative optimization of the evaluation model.

[0029] Furthermore, the comment set V in the fuzzy comprehensive evaluation (M3) is {excellent, good, medium, qualified, unqualified}, and the corresponding score c j They are {95, 85, 75, 65, 55} respectively. The comment set and corresponding scores are clarified to make the evaluation results more standardized and accurate, facilitate the classification and evaluation of green construction projects, and enhance the operability and consistency of the evaluation method.

[0030] In the specific application, the data collection link uses the Internet of Things monitoring equipment (T1) for data collection. The energy consumption monitoring sensor (T11) collects water and electricity data at the construction site with high precision, every 5 minutes, and accurately records the water and electricity consumption during the construction process. Within one month of the project construction, through the analysis of water and electricity data, it was found that the electricity consumption in a certain construction area was abnormally high during a specific time period. After investigation, it was found that the energy consumption increased due to the aging of the equipment. After the equipment was replaced in time, the energy consumption in the area returned to normal levels.

[0031] The RFID material identification device (T12) performs real-time identification and tracking of construction materials. When materials enter the site, the material label information is automatically read to record the type, quantity, supplier and other information of the materials, and the flow and use of the materials are tracked during the use of the materials. For example, during the use of steel, the RFID material identification device found that a batch of steel was used too quickly. After inspection, it was found that the waste was caused by unreasonable construction technology. After timely adjustment of the construction technology, the loss of steel was reduced.

[0032] The PM2.5 sensor and noise sensor in the environmental monitoring module (T13) monitor the air quality and noise intensity at the construction site in real time. During an earthwork excavation operation, the PM2.5 sensor detected a sharp increase in dust concentration, exceeding the specified threshold, and the noise sensor also detected that the noise intensity was too high. Based on these data, the construction party immediately took measures such as sprinkling water to reduce dust and adjusting the operating time of construction equipment, which effectively reduced the dust concentration and noise intensity and reduced the impact on the surrounding environment.

[0033] Evaluation index system construction and weight calculation Based on the collected data, a multi-dimensional evaluation index system (I1) was constructed using the BP neural network model (M1). In the resource dimension, the main material loss rate and water resource reuse rate were calculated. The project invested 500 tons of steel, of which 480 tons were actually used, and the main material loss rate was ×100%=4%; the total water consumption is 1000 cubic meters, the reused water volume is 450 cubic meters, and the water resource reuse rate is ×100%=45%.

[0034] In terms of the environment, the dust concentration and noise average are monitored in real time. During a week of project construction, the average dust concentration was 50μg / m³, and the average noise was calculated to be 65dB through multiple collections.

[0035] In the carbon dimension, calculate the carbon emissions of machinery and transportation. Assuming that the project uses 5 types of construction machinery, the energy consumption and carbon emission coefficient of each machine are known, and the formula F c =∑E j ×f j The total mechanical carbon emissions are calculated to be 500kgCO2 / kWh. At the same time, the transportation distance, weight and transportation carbon emission coefficient of various materials are known. According to the formula E trans =∑D t,k × k ×e trans Calculation shows that the total carbon emissions from transportation is 300kgCO2.

[0036] The dynamic weight coefficient (W1) is calculated by using the analytic hierarchy process (M2) combined with the time factor. In the early stage of the project, resource utilization efficiency has a greater impact on the green construction level of the project. The initial weight of each indicator is determined by the analytic hierarchy process. As the project progresses, the importance of environmental impact and carbon emissions gradually increases, and the weight is dynamically adjusted according to the time factor. For example, in the middle of the project, the initial weight of an environmental indicator is 0.2. Due to the obvious changes in environmental parameters caused by construction activities, the score change rate of this indicator is 0.1, and the adjustment coefficient α i Take 0.2, according to the formula Calculate the new weight w i (t) = 0.2 × (1 + 0.2 × 0.1) = 0.204. After normalization, the dynamic weight coefficient (W1) for green construction evaluation is obtained.

[0037] Fuzzy comprehensive evaluation and comprehensive score calculation The fuzzy comprehensive evaluation algorithm (M3) is used to generate the green construction comprehensive score (S1). The normal distribution membership function is used Measure the degree of membership of carbon emission intensity x to green construction evaluation. Assuming the carbon emission intensity of the project is 40kg / m², by calculating the membership μ(40)=exp ≈0.69, indicating that the carbon emission intensity has a high level in the green construction evaluation.

[0038] Construct the fuzzy relationship matrix R, combine the indicator weight vector W determined by the dynamic weight coefficient (W1), and calculate the fuzzy evaluation result vector B = W × R. The comment set {excellent, good, medium, qualified, unqualified}, the corresponding score c j They are {95, 85, 75, 65, 55} respectively. By formula S1=∑B j ×c j The green construction comprehensive score S1 is calculated to fully reflect the overall level of the green construction project. After calculation, the green construction comprehensive score of the project is 80 points, and the evaluation result is good.

[0039] Reinforcement Learning Optimization The evaluation model is iteratively optimized (U1) based on the reinforcement learning algorithm (A1). During the project implementation, according to the reward function Calculate the reward value. When the construction party takes measures such as optimizing the construction process and increasing investment in environmental protection equipment, the comprehensive score change rate ΔS t And environmental parameter improvement value ΔE t All have been improved, the reward value R t For example, at a certain stage, by optimizing the construction process, the dust concentration was reduced, the noise intensity was reduced, and the comprehensive score was increased from 80 points to 85 points, ΔS t = =0.0625, and the environmental parameter improvement value ΔE t Also increases accordingly, and the reward value R is calculated t =0.6×0.0625+0.4×ΔE t (Assuming ΔE t After calculation, it is 0.1) = 0.0375 + 0.04 = 0.0775.

[0040] Update formula through Q-learning The state-action value function is continuously updated so that the model can continuously optimize decisions based on reward feedback. In this project, the discount factor γ is set to 0.9. After multiple iterations of optimization, the evaluation model can more accurately evaluate the green construction level of the project, and can promptly identify problems in the project and provide optimization suggestions.

[0041] Visualization The evaluation results are displayed through a 3D GIS platform. The 3D GIS platform performs high-precision modeling of the construction project and the surrounding environment at a scale of 1:500, and displays the topography, building structure, and facility layout information of the project in detail. The real-time data dashboard is linked to the 3D simulation model to display the various evaluation index data of the project in real time. When the index data is abnormal or does not meet the requirements of green construction, the optimization suggestions are intuitively displayed on the 3D simulation model. For example, when the dust concentration in a certain area exceeds the standard, the 3D simulation model will mark a warning in the area and display corresponding dust reduction measures, such as increasing the number of watering times, setting up dust nets, etc., to guide the improvement and optimization of the project.

[0042] The above are only embodiments of the present invention, and the circuits, electronic components and modules involved are all prior art, which can be fully implemented by those skilled in the art. It is needless to say that the content protected by this application does not involve improvements to software and methods. The common sense such as the known specific structures and characteristics in the scheme is not described in detail here. Ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all the prior art in the field, and have the ability to apply conventional experimental means before that date. Ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the scope of protection of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent.

Claims

1. A green construction evaluation method, characterized in that: The following steps are involved: S101. Collect energy consumption data, material usage data and environmental parameters of the construction site in real time through IoT monitoring equipment; S102. Construct a multi-dimensional evaluation index system including resource utilization efficiency, carbon emission intensity and environmental impact coefficient based on the BP neural network model; S103. Calculate the dynamic weight coefficient by using the analytic hierarchy process combined with the time factor; S104. Generate a comprehensive score of green construction using a fuzzy comprehensive evaluation algorithm; S105. Iteratively optimize the evaluation model based on the reinforcement learning algorithm.

2. A green construction evaluation method as claimed in claim 1, characterized in that: The Internet of Things monitoring equipment includes: Energy consumption monitoring sensors to collect data on water and electricity used at the construction site; RFID material identification devices, used to identify and track construction materials; Environmental monitoring module, including PM2.5 sensor and noise sensor, is used to monitor the air quality and noise intensity at the construction site.

3. A green construction evaluation method as claimed in claim 1, characterized in that: The construction of the multi-dimensional evaluation index system includes: Resource Dimension: Main material loss rate , which means calculating the total amount of main material input M in The actual usage M out The percentage of the difference in the total input is used to measure the loss of main materials; The calculation formula of water resource reuse rate is: , that is, the amount of water reused W reuse Total water consumption W total percentage of Environmental Dimension: Dust concentration C d ; The noise mean is given by the formula Calculate, where N i is the noise value collected each time, and N is the number of collections; Carbon Dimension: Mechanical carbon emissions F c =∑E j ×f j , E j is the energy consumption of the jth machine, f j is the carbon emission coefficient of the jth machine, and the total carbon emission of the machine is obtained by summing the product of the energy consumption of different machines and the corresponding carbon emission coefficient; Transport Carbon Emissions E trans =∑D t,k × k ×e trans , D t,k is the transportation distance of the kth material, w k is the weight of the kth material, e trans is the transportation carbon emission coefficient. By multiplying the three and adding them together, we can get the total carbon emissions during material transportation, which reflects the impact of the transportation link on carbon emission intensity.

4. A green construction evaluation method as claimed in claim 3, characterized in that: The calculation of the dynamic weight coefficient includes: , where w i (t) is the dynamic weight of the ith indicator at time t, which reflects the impact of the indicator on the green construction evaluation results at the current moment, and w i 0 is the initial weight of the ith indicator, which is the weight value determined based on experience or preliminary analysis at the beginning of the evaluation. is the adjustment coefficient, with a value range of 0.1-0.3, which is used to control the adjustment range of the indicator weight over time or the indicator score change to adapt to the dynamic changes in the importance of each indicator in different stages or scenarios. i (t) is the score change rate of the i-th indicator at time t. The weight is dynamically adjusted according to the change of the indicator score at different times; Normalization processing; , through normalization, the sum of all indicator weights is made to be 1, ensuring the rationality and comparability of the weights, and finally obtaining the dynamic weight coefficient for green construction evaluation.

5. A green construction evaluation method as claimed in claim 4, characterized in that: The fuzzy comprehensive evaluation includes: Using normal distribution membership function: This function is used to measure the degree of membership of carbon emission intensity x (unit: kg / m²) in green building evaluation, with 50 as the center value and 15 as the standard deviation. The μ(x) value calculated by this function represents the membership level of carbon emission intensity x in green building evaluation. The closer the value is to 1, the more the carbon emission intensity meets the requirements of green building. Comprehensive score calculation: S1=∑B j ×c j , where B = W × R, W is the indicator weight vector, which is determined by the dynamic weight coefficient and reflects the relative importance of each evaluation indicator; R is the fuzzy relationship matrix, which is composed of the membership of each indicator to different comment sets; B j is the element in the fuzzy evaluation result vector, obtained by matrix operation W×R; c j The green construction comprehensive score S1 is calculated by this formula, which fully reflects the overall level of the green construction project.

6. A green construction evaluation method as claimed in claim 5, characterized in that: The iterative optimization of the evaluation model based on the reinforcement learning algorithm includes: Reward function: , R t is the reward value at the tth moment, which is used to evaluate the optimization effect of the model at that moment, ΔS t is the comprehensive score change rate, which reflects the change of the green construction comprehensive score at different times and reflects the contribution of the model to the optimization of the overall evaluation results; ΔE t is the environmental parameter improvement value, which is calculated by calculating the change value ΔE of each environmental parameter. t,k With the corresponding weight β k The sum of the products is obtained, which reflects the effect of the model on optimizing the environment-related indicators; Q-learning update: ， Q(s t ,a t ) is in state s t Take action a t The state-action value function, γ is the discount factor, ranging from 0.8 to 0.95, which is used to balance the impact of current rewards and future rewards on model decisions; s t is the system state at time t, which is composed of various evaluation index values ​​and fully reflects the various characteristics of the current green construction project; a t The action taken at the tth moment is continuously updated through the formula, so that the model can continuously optimize the decision according to the reward feedback and realize the iterative optimization of the evaluation model.

7. A green construction evaluation method as claimed in claim 6, wherein the comment set V in the fuzzy comprehensive evaluation is {excellent, good, medium, qualified, unqualified}, and the corresponding score c j They are {95, 85, 75, 65, 55} respectively. The comment set and corresponding scores are clarified to make the evaluation results more standardized and accurate, facilitate the classification and evaluation of green construction projects, and enhance the operability and consistency of the evaluation method.

8. A green construction evaluation system, characterized in that: include: M1. Data acquisition module: comprising the Internet of Things monitoring device as described in claim 2, responsible for real-time and accurate collection of various data at the construction site, providing a data basis for subsequent analysis and evaluation; M2. Evaluation model module: Integrate BP neural network and analytic hierarchy process, use the powerful nonlinear fitting ability of BP neural network to model the multi-dimensional evaluation index system, and analytic hierarchy process is used to determine the weight of each index. The combination of the two can achieve a comprehensive and accurate evaluation of green construction projects; M3. Dynamic adjustment module: Updates model parameters based on the reinforcement learning algorithm and continuously optimizes the evaluation model according to the feedback of the reward function, so that it can adapt to the green construction evaluation needs of different projects and different stages, and improve the accuracy and effectiveness of the evaluation; M4. Visualization module: The evaluation results are displayed through a 3D GIS platform, presenting the evaluation results of green construction projects in an intuitive and visual way, including the spatial distribution of the projects, the performance of various indicators, etc., to facilitate user understanding and decision-making.

9. A green building evaluation system as claimed in claim 8, characterized in that: The 3D GIS platform supports: 1:500 detailed modeling: It can carry out high-precision modeling of the construction project and the surrounding environment at a scale of 1:500, showing the topography, building structure, and facility layout information of the project in detail to ensure the accuracy and reliability of the model; The real-time data dashboard displays the various evaluation index data of the project in real time and is linked to the 3D simulation model. When the index data is abnormal or does not meet the green construction requirements, the optimization suggestions can be intuitively displayed on the 3D simulation model to guide the improvement and optimization of the project.

Images