Station building construction cost optimization method based on genetic algorithm

Abstract

The invention discloses a station building construction cost optimization method based on a genetic algorithm, and relates to the technical field of building construction cost optimizing.The optimization method comprises the specific steps that S100, on-site data acquisition is conducted, specifically, Internet of Things sensors are arranged in a logistics vehicle channel, a cargo stacking area and a material processing area of a station building construction site, through deep fusion of the Internet of Things technology and the genetic algorithm, fine management and dynamic optimization of the construction cost are realized, and in a field data acquisition stage, an Internet of Things sensor is utilized to capture logistics vehicle running tracks, cargo loading and unloading states and quantity key data in real time, so that the real-time management of the logistics vehicle is realized. According to the method, the multi-source data are acquired and transmitted to the data processing center through the wireless network, the accuracy and timeliness of the data are ensured, then the multi-source data are converted into feature quantized values through data processing and conversion, the association degree between various cost factors and multi-source data features is deeply mined, and a scientific basis is provided for subsequent cost optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of building construction cost optimization, and in particular to a station building construction cost optimization method based on genetic algorithm. Background Art

[0002] In the field of station building construction, cost control has always been a key link in project management. With the continuous development of advanced technologies such as the Internet of Things, big data, and artificial intelligence, how to effectively apply these technologies to the cost optimization of station building construction to improve the accuracy and efficiency of cost control has become a hot issue of concern in the industry. At present, data collection, processing, and cost optimization in the process of station building construction mostly rely on manual experience judgment and traditional algorithms, which to a certain extent limits the depth and breadth of cost optimization. Therefore, exploring a method that can automatically and intelligently optimize the cost of station building construction is of great significance to improving project management level and reducing construction costs.

[0003] Traditional station building construction cost optimization methods have many shortcomings. On the one hand, manual experience and judgment are easily affected by subjective factors, resulting in inaccurate cost prediction and optimization results; on the other hand, traditional algorithms often exhibit low computational efficiency and limited optimization effects when processing complex and changeable construction cost data. In addition, traditional methods also lack sufficient consideration of external environmental factors, such as weather changes, policy adjustments, and market fluctuations. These factors may have a significant impact on station building construction costs. Therefore, traditional cost optimization methods are often difficult to achieve the expected optimization effects in actual applications.

[0004] Therefore, the development of a station building construction cost optimization method based on genetic algorithm not only improves the accuracy and efficiency of station building construction cost optimization, but also provides more scientific and convenient tools and means for project management. Summary of the Invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a station building construction cost optimization method based on genetic algorithm. The method integrates Internet of Things technology, genetic algorithm and BIM technology to realize intelligent optimization and visualization of construction costs. It collects field data in real time through Internet of Things sensors, and uses genetic algorithms to conduct in-depth analysis and optimization of multi-source data to construct a cost optimization model covering the entire construction process. At the same time, the present invention can also automatically adjust algorithm parameters according to changes in weather, policies, and market environment factors to ensure the timeliness and accuracy of the cost optimization plan. Finally, with the help of BIM technology, three-dimensional visualization of cost information is realized, providing strong support for project management decisions.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a station building construction cost optimization method based on genetic algorithm, the specific steps of the optimization method are: S100, On-site Data Collection: IoT sensors are deployed in the logistics vehicle passages, cargo storage areas, and material processing areas at the station construction site to collect real-time data on logistics vehicle operation trajectories, cargo loading and unloading status, and quantity, and transmit the data to the data processing center via the wireless network; S200, Data Processing and Conversion: The data processing center cleans and standardizes the collected raw data, converts the multi-source data into quantitative feature values, and explores the degree to which various cost factors are affected by the multi-source data features. The cost-related factors of the entire construction process are sorted out and converted into a form suitable for genetic algorithm analysis. S300, build an optimization model: Incorporate the processed cost data into the fitness function of the genetic algorithm, perform iterative operations through the genetic algorithm, optimize the cost allocation plan for each construction link, and build a cost optimization model covering the entire construction process; S400, environment-driven optimization: During the station building construction period, data on weather, policies, and market environmental factors are continuously monitored. Once environmental factors change, the new data is automatically input into the genetic algorithm, the genetic algorithm parameters are adjusted, the fitness function is recalculated, and the cost optimization model is revised; S500, BIM fusion presentation: With the help of BIM software, a three-dimensional model of the station building construction is constructed according to the design drawings and construction plan. The cost data of the cost optimization model is imported into the BIM model. At the same time, the dynamic real-time optimization results of the genetic algorithm are synchronously updated to the BIM model. The cost distribution and optimization changes at each stage of construction are displayed by changing the color, material and transparency.

[0007] Furthermore, in the S100, the sensors used in the field data collection are: logistics vehicle channel: positioning sensor and speed sensor; cargo stacking area: weight sensor and counting sensor; material processing area: cutting length sensor and current and voltage sensor.

[0008] Furthermore, in the data processing and conversion in S200, the multi-source data feature extraction and quantification formula is used to convert the data into feature quantization values, and the formula is: ,in, Represents the feature quantization value extracted from multi-source data, is the number of data source types, It is The current data value of the data source, and They are the maximum and minimum values of the historical data of the data source, It is The weight parameter of a data source indicates the weight of the data source in feature quantization.

[0009] Furthermore, in the step S200, the cost factor correlation influence formula is used in data processing and conversion to mine the degree to which various cost factors are affected by multi-source data features. The formula is: ,in, Indicates the degree to which a certain cost factor is affected by the characteristics of multi-source data. is the number of cost factor types, It is The influence coefficient of various cost factors, It is The power parameter of the cost factor, is the mean of the quantized feature values, Represents the quantitative value of features extracted from multi-source data.

[0010] Furthermore, in said S200, the cost-related factors of the whole construction process in the data processing and conversion are: labor cost, material cost, equipment cost and site layout cost; The labor costs include: the number of workers of different types, working hours and salary standards; The material cost is: the purchase price, usage and loss rate of various building materials; The equipment costs include: rental fees, maintenance costs and operating hours of construction equipment; The site layout costs include: site occupation fees and temporary facility construction fees.

[0011] Furthermore, in the step S300, the calculation formula for the fitness function of the genetic algorithm in the optimization model is: ,in, is the optimized cost target value, is the number of construction links, It is The initial cost of each construction stage, is the degree to which the cost of this link is affected by the characteristics of multi-source data, is the adjustment coefficient related to the construction phase time, is the current construction time, It is The ideal completion time for each construction link, and are the maximum and minimum allowed completion time of this link respectively.

[0012] Furthermore, in the S300, the optimization model is constructed by performing iterative operations through a genetic algorithm. The genetic algorithm starts from a set initial population, and each individual corresponds to a construction cost configuration scheme. During the iterative operation, the roulette wheel selection method is used to select individuals for crossover operation according to the selection probability converted from the fitness value. The fitness value is calculated by the fitness function. The value is determined, and the crossover operation exchanges individual gene fragments with a crossover probability of 0.7-0.9 to generate new individuals. The mutation operation is performed with a probability of 0.01-0.05 to randomly change individual gene fragments. After repeated iterations, the individual fitness values of the population are continuously improved, and finally the optimal solution is screened out to construct a cost optimization model covering the entire process of station building construction.

[0013] Furthermore, in said S400, the environmental factor data in the environment-driven optimization are: weather data, policy data and market data; The weather data is collected by using meteorological monitoring equipment; Collection of the aforementioned policy data: collected through official websites, authoritative industry information platforms and policy and regulatory databases; Collection of the market data: collected through market research agencies and online data platforms.

[0014] Furthermore, in the above S400, the parameters of the genetic algorithm are automatically adjusted by the environment-driven optimization formula, and the calculation formula is: ,in, and are the parameters of the genetic algorithm before and after adjustment, is the number of types of environmental change factors, It is The amount of change in environmental factors, is the mean value of the variation of the environmental factor, is its standard deviation, It is the influence weight of the corresponding environmental factors on the adjustment of algorithm parameters.

[0015] Compared with the existing technology, the station building construction cost optimization method based on genetic algorithm has the following beneficial effects: 1. The present invention realizes the refined management and dynamic optimization of construction costs through the deep integration of Internet of Things technology and genetic algorithms. During the on-site data collection stage, the present invention uses Internet of Things sensors to capture the operation trajectory of logistics vehicles, cargo loading and unloading status and quantity key data in real time, and transmits them to the data processing center through wireless networks, ensuring the accuracy and timeliness of the data. Subsequently, through data processing and transformation, multi-source data is converted into feature quantification values, and the correlation between various cost factors and multi-source data features is deeply explored, providing a scientific basis for subsequent cost optimization, not only improving the efficiency and accuracy of data processing, but also providing the possibility for accurate prediction and optimization of station construction costs, effectively avoiding the blindness and uncertainty existing in traditional cost management.

[0016] 2. The present invention can monitor the changes of environmental factors such as weather, policies and markets in real time by introducing an environment-driven optimization mechanism, and automatically adjust the parameters of the genetic algorithm through the environment-driven optimization formula, thereby ensuring that the cost optimization model can keep pace with changes in the external environment and improving the accuracy and practicality of the optimization results. At the same time, with the help of the integrated presentation function of BIM technology, the present invention intuitively displays the detailed data of the cost optimization model in the form of a three-dimensional model, and clearly reflects the distribution of costs and optimization effects at each stage of construction through changes in visual elements such as color, material and transparency, providing project managers with more convenient and efficient decision-making support.

[0017] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0019] Figure 1 This is a flowchart of the station building construction cost optimization method based on genetic algorithm; Figure 2 This is the framework diagram of the station building construction cost optimization method based on genetic algorithm. DETAILED DESCRIPTION

[0020] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the specific implementation method, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0021] Example 1: Construction cost optimization of a high-speed railway station On-site data collection: At the high-speed railway station construction site, in order to comprehensively and accurately obtain data related to construction costs, meticulous sensor deployment work has been carried out. In the logistics vehicle channel, the positioning sensor is like installing an "electronic tracker" on the vehicle, accurately recording the complete running trajectory of each logistics vehicle from entering the construction site to leaving. Through high-precision positioning technology, the specific position coordinates of the vehicle in the construction site can be accurately determined, and the error is controlled within a very small range. The speed sensor monitors the vehicle's speed in real time. Once the speed is abnormal, such as speeding in a narrow channel, the system will immediately issue an alarm. In the cargo stacking area, the weight sensor is installed under the pallet or shelf where the cargo is stored. It can accurately measure the weight change of the cargo, and can accurately sense even the increase or decrease of a small amount of cargo. The counting sensor adopts advanced Image recognition and laser counting technology are used to accurately count the loading and unloading quantities of goods. Whether it is small bolts and nuts or large steel beams and plates, they can be accurately counted to avoid errors that may occur in manual counting. In the material processing area, cutting length sensors are installed on the cutting equipment. During the material cutting process, the cutting length is monitored in real time to ensure that the size of each piece of processed material meets the design requirements and reduce material waste caused by dimensional deviation. Current and voltage sensors are used to monitor the power consumption of the processing equipment. By analyzing the power consumption of the equipment and evaluating the operating efficiency of the equipment, data support is provided for equipment maintenance and energy management. The data collected by these sensors are transmitted to the data processing center in real time through a stable wireless network in an encrypted manner to ensure the security and timeliness of the data.

[0022] Data processing and conversion: After receiving a large amount of raw data, the data processing center first performs cleaning work. Using data cleaning algorithms, it removes noise points, outliers, and duplicate data from the data. For example, it filters and corrects abnormal speed data caused by occasional signal interference from sensors. Then, it uses multi-source data feature extraction and quantification formulas to convert multi-source data into feature quantification values. The formula is: ,in, Represents the feature quantization value extracted from multi-source data, is the number of data source types, It is The current data value of the data source, and They are the maximum and minimum values of the historical data of the data source, It is The weight parameter of a data source indicates the importance of the data source in feature quantification. It is The index parameters of the data sources are used to adjust the nonlinear degree of feature quantification. Taking the steel usage data source as an example, the maximum and minimum values are determined based on its historical data. Combined with the current actual usage, as well as the weights and index parameters determined according to the importance of steel in construction and data characteristics, its feature quantification value is calculated. When mining the degree to which various cost factors are affected by the characteristics of multi-source data, the cost factor correlation influence formula is used to mine the degree to which various cost factors are affected by the characteristics of multi-source data: ,in, Indicates the degree to which a certain cost factor is affected by the characteristics of multi-source data. is the number of cost factor types, It is The influence coefficient of various cost factors, It is The power parameter of the cost factor, is the mean of the quantized feature values, It represents the characteristic quantitative value extracted from multi-source data. After analysis, it is found that when the characteristic quantitative value of steel usage is high and close to the historical maximum value, the impact on material cost increases significantly, which means that during the construction process, it is necessary to pay close attention to the use of steel, avoid waste, and reasonably adjust the procurement plan.

[0023] Construct an optimization model and incorporate the processed cost data into the fitness function of the genetic algorithm, which is calculated as follows: ,in, is the optimized cost target value, is the number of construction links, It is The initial cost of each construction stage, is the degree to which the cost of this link is affected by the characteristics of multi-source data, is the adjustment coefficient related to the construction phase time, is the current construction time, It is The ideal completion time for each construction link, and are the maximum and minimum allowed values of the completion time of this link respectively. The genetic algorithm starts iterative operation from a carefully set initial population. Each individual in the initial population corresponds to a construction cost configuration plan. These plans cover the allocation of manpower, materials, and equipment resources in each link of the construction. In the iterative process, the roulette selection method is used to select individuals for crossover operation based on the selection probability of fitness value conversion. The fitness value is calculated by the fitness function. The value is determined, and the crossover probability is set to 0.8, which means that there is an 80% probability of exchanging individual gene fragments to produce new individuals. The mutation operation is performed with a probability of 0.03, randomly changing individual gene fragments, introducing new gene combinations for the algorithm to avoid falling into local optimal solutions. After multiple iterations, the individual fitness values of the population continue to improve, and finally a better solution is screened out to construct a cost optimization model covering the entire construction process. For example, through the optimization model, it is found that during the construction stage of the main structure, the number of skilled technical workers should be appropriately increased. Although the labor cost will increase in the short term, the overall construction period will be shortened due to the improvement of construction efficiency, the equipment rental cost and management cost will be reduced, and the comprehensive cost will be effectively controlled.

[0024] Environmentally driven optimization: During the construction period of the high-speed railway station building, data on weather, policies, and market environmental factors are continuously and closely monitored. High-precision meteorological monitoring equipment is used to collect weather data in real time, including information on temperature, precipitation, wind speed, and wind direction. Policy data is regularly collected from official websites, authoritative industry information platforms, and policy and regulatory databases to ensure the latest policy developments, such as adjustments to tax policies in the construction industry and restrictions on construction imposed by environmental protection policies. Market data is collected with the help of professional market research institutions and well-known online data platforms, covering information on fluctuations in construction material prices, changes in labor market supply and demand, and trends in construction equipment rental prices. If new local policies on the transportation of construction materials impose strict restrictions on the emission standards and routes of transportation vehicles, resulting in increased material transportation costs, the new data will be promptly input into the genetic algorithm, and the parameters of the genetic algorithm will be automatically adjusted using the environmentally driven optimization formula. The calculation formula is: ,in, and are the parameters of the genetic algorithm before and after adjustment, is the number of types of environmental change factors, It is The amount of change in environmental factors, is the mean value of the variation of the environmental factor, is its standard deviation, It is the weight of the influence of corresponding environmental factors on the adjustment of algorithm parameters, such as crossover probability and mutation probability, recalculating the fitness function and correcting the cost optimization model. After adjustment, the model may increase the procurement proportion of local material suppliers, reduce the amount of materials transported over long distances, or optimize the transportation routes and select transportation methods that meet policy requirements and have lower costs to reduce transportation costs.

[0025] BIM integration and presentation: With the help of professional BIM software, a 3D construction model of the station building is constructed based on detailed design drawings and a scientific and reasonable construction plan. During the model construction process, every structure and component of the station building is accurately modeled to ensure that the model is highly consistent with the actual construction situation. Detailed cost data for the cost optimization model is imported, including the specific values of labor costs, material costs, equipment costs, and site layout costs at each construction stage. At the same time, the dynamic optimization results of the genetic algorithm are updated synchronously, and the cost distribution and optimization changes at each construction stage are displayed by changing the color, material, and transparency. For example, in the BIM model, red represents high-cost areas, such as the construction area of large-span steel structures, which are relatively costly due to the large amount of steel used and the high construction difficulty. Green represents low-cost areas, such as the construction area of some simple ancillary facilities. Through this intuitive display method, construction personnel and management personnel can clearly understand the cost distribution during the construction process and promptly identify the key points and difficulties of cost control. During the construction process, as the optimization plan is implemented, the model will update the cost changes in real time, allowing all parties to grasp the cost optimization results at any time and provide strong support for construction decision-making.

[0026] In summary, during the construction of a high-speed railway station building, data was collected through multi-type sensors on site, converted into feature quantitative values through data processing, and the influence of cost factors was explored. Then, a cost optimization model was constructed with the help of genetic algorithms, and the cost configuration plan was optimized by considering the construction time factor. During the construction period, environmental data was collected through various channels, and the algorithm parameters were automatically adjusted according to environmental changes to correct the model. Finally, cost data was visualized with the help of BIM software. This method comprehensively integrates data, algorithms and technologies, accurately controls construction costs, and provides strong support for the efficient and rational use of resources and improvement of economic benefits in the construction of high-speed railway station buildings. It has significant advantages and promotion value in the cost management of large-scale station building construction.

[0027] Example 2: Construction cost optimization of a subway station On-site data collection: At the subway station construction site, adapted sensors are installed according to the different characteristics of logistics vehicle channels, cargo storage areas, and material processing areas. In the logistics vehicle channels, positioning sensors and speed sensors work together. The positioning sensor uses a combination of satellite positioning and base station positioning to ensure accurate tracking of vehicle positions in complex indoor and outdoor environments. The speed sensor can not only monitor vehicle speed in real time, but also record the average speed of vehicles in different road sections to provide data for analyzing vehicle driving efficiency. In the cargo storage area, the installation of weight sensors and counting sensors has been carefully designed. For small goods, high-precision electronic scale-type weight sensors are used to ensure accurate measurement of small weight changes; for large goods, For goods, pressure-sensitive weight sensors are used, which can withstand large weights with reliable accuracy. Counting sensors use advanced machine vision technology to identify the shape and color characteristics of goods to accurately count the number of goods loaded and unloaded. In the material processing area, cutting length sensors are installed at key positions of the cutting equipment. Using the laser ranging principle, they can accurately measure the cutting length with an error control at the millimeter level. Current and voltage sensors monitor the power parameters of the processing equipment in real time. By analyzing the changes in current and voltage, they can determine whether the equipment is operating normally and whether there is any energy waste. The data collected by these sensors are stably and quickly transmitted to the data processing center through a specially built wireless network on the construction site.

[0028] Data processing and conversion: After receiving the raw data collected on-site, the data processing center first performs comprehensive data cleaning. The data cleaning algorithm removes erroneous and abnormal data caused by sensor failure and signal interference. For example, the occasional weight sensor jump data is smoothed by the data filtering algorithm. Then, the multi-source data feature extraction and quantification formula is applied. The formula is as follows: , converting multi-source data into characteristic quantitative values. Taking labor cost-related data as an example, the number of workers of different types, working hours, and salary standard data are used as data sources. The maximum and minimum values of each data source are determined based on historical data. Combined with current actual data and corresponding weights and index parameters, the characteristic quantitative value of labor cost is calculated. When mining the degree to which cost factors are affected by the characteristics of multi-source data, the cost factor correlation influence formula is used to mine the degree to which various cost factors are affected by the characteristics of multi-source data. The formula is: After analysis, it was found that in a certain construction stage, increasing the working hours of skilled electricians, although the labor cost increased, the equipment cost and overall construction cost decreased due to the reduction of downtime caused by electrical equipment failure. This shows that the cost structure can be effectively optimized by rationally allocating human resources.

[0029] Build an optimization model and substitute the processed cost data into the fitness function of the genetic algorithm. The calculation formula of the fitness function is: The genetic algorithm starts iterative operations from the set initial population. The individuals in the initial population represent a variety of different construction cost configuration schemes, which cover the resource allocation of each link in the construction process. During the iteration process, the roulette wheel selection method is used to select individuals to enter the crossover operation. The crossover probability is set to 0.75 and the mutation probability is set to 0.02. In the crossover operation, two individuals are randomly selected and their gene fragments are exchanged according to certain rules to generate new individuals, simulating the gene recombination process in biological evolution. The mutation operation randomly changes the gene fragments of the individuals with a lower probability, introducing new change factors into the algorithm to prevent the algorithm from falling into the local optimal solution. After multiple iterations, a better construction cost configuration scheme is screened out and a cost optimization model is constructed. For example, through the optimization model, it is found that during the platform layer construction phase of the subway station building, the reasonable adjustment of the rental time and maintenance plan of the construction equipment can reduce the equipment cost. The large excavation equipment originally planned to be rented for one month was adjusted to a 25-day lease based on the actual construction progress, and equipment maintenance was arranged in advance to avoid additional maintenance costs and downtime losses caused by equipment failure.

[0030] Environment-driven optimization: During the construction of subway station buildings, weather, policy, and market environment data are continuously collected. Weather data is obtained through cooperation with local meteorological departments to obtain high-precision weather forecasts and real-time monitoring data, including the impact of heavy rain, strong winds and severe weather on construction. Policy data is collected by paying attention to urban construction plans and subway construction-related policies and regulations released by official departments. Market data is collected with the help of professional market research institutions and well-known online data platforms in the industry, such as information on price fluctuations in the construction material market and changes in wage levels in the labor market. If there are large fluctuations in the price of construction materials in the market, such as a 20% increase in steel prices, this data is input into the genetic algorithm, and the parameters of the genetic algorithm are automatically adjusted using the environment-driven optimization formula. The formula for the environment-driven optimization formula is: , recalculate the fitness function and revise the cost optimization model. After the adjustment, the model may use some new composite materials with relatively stable prices to replace part of the steel, or optimize the construction process and reduce the use of steel to cope with the cost pressure brought by rising material prices.

[0031] BIM integration presentation uses professional BIM software to build a three-dimensional construction model of the subway station building, and accurately models the platform, station hall, and tunnel of the subway station building. In the model, the structural changes and construction processes in different construction stages are displayed in detail, and detailed cost data of the cost optimization model and the dynamic optimization results of the genetic algorithm are imported. By changing the color, material, and transparency, the cost distribution and optimization changes in each construction stage are intuitively displayed. For example, in the BIM model, different colors are used to distinguish the costs of different construction areas. Red represents high-cost areas and blue represents low-cost areas. During the construction process, as the cost optimization plan is implemented, the model updates the cost changes in real time. Through this visual method, construction personnel and managers can clearly see the effect of cost optimization. For example, the cost of a certain area has been reduced by 15% by optimizing the construction process, which can be intuitively reflected in the model, providing an intuitive and accurate basis for subsequent construction decisions.

[0032] To summarize, a complete cost optimization process is used in the construction of subway station buildings. From collecting data from sensors in various areas of the site to data processing and conversion analysis of the correlation between various cost factors, genetic algorithms are used to iteratively screen out better cost configuration solutions to build models. At the same time, weather, policies and market environments are continuously monitored. When the environment changes, algorithm parameters are adjusted in a timely manner to optimize the model. Cost data and model optimization results are intuitively presented through BIM software, making it easier for all parties to control costs. This method effectively addresses the cost management challenges in the complex environment of subway station construction, achieves refined cost control, ensures the smooth progress of the project within budget, and provides a good example for cost control in urban rail transit station construction.

[0033] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Although the present invention has been disclosed as above in terms of a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can, without departing from the scope of the technical solution of the present invention, make some changes or modifications to equivalent embodiments using the technical contents disclosed above. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A station building construction cost optimization method based on genetic algorithm, characterized in that: The specific steps of this optimization method are: S100, On-site Data Collection: IoT sensors are deployed in the logistics vehicle passages, cargo storage areas, and material processing areas at the station construction site to collect real-time data on logistics vehicle operation trajectories, cargo loading and unloading status, and quantity, and transmit the data to the data processing center via the wireless network; S200, Data Processing and Conversion: The data processing center cleans and standardizes the collected raw data, converts the multi-source data into quantitative feature values, and explores the degree to which various cost factors are affected by the multi-source data features. The cost-related factors of the entire construction process are sorted out and converted into a form suitable for genetic algorithm analysis. S300, build an optimization model: Incorporate the processed cost data into the fitness function of the genetic algorithm, perform iterative operations through the genetic algorithm, optimize the cost allocation plan for each construction link, and build a cost optimization model covering the entire construction process; S400, environment-driven optimization: During the station building construction period, data on weather, policies, and market environmental factors are continuously monitored. Once environmental factors change, the new data is automatically input into the genetic algorithm, the genetic algorithm parameters are adjusted, the fitness function is recalculated, and the cost optimization model is revised; S500, BIM fusion presentation: With the help of BIM software, a three-dimensional model of the station building construction is constructed according to the design drawings and construction plan. The cost data of the cost optimization model is imported into the BIM model. At the same time, the dynamic real-time optimization results of the genetic algorithm are synchronously updated to the BIM model. The cost distribution and optimization changes at each stage of construction are displayed by changing the color, material and transparency.

2. The method for optimizing station building construction cost based on genetic algorithm according to claim 1, characterized in that: In the S100 , the sensors used in field data collection are: logistics vehicle channel: positioning sensor and speed sensor; cargo stacking area: weight sensor and counting sensor; material processing area: cutting length sensor and current and voltage sensor.

3. The method for optimizing station building construction cost based on genetic algorithm according to claim 1, characterized in that: In the above S200, in data processing and conversion, multi-source data feature extraction and quantification formula are used to convert data into feature quantification values, and the formula is: ,in, Represents the feature quantization value extracted from multi-source data, is the number of data source types, It is The current data value of the data source, and They are the maximum and minimum values of the historical data of the data source, It is The weight parameter of a data source indicates the importance of the data source in feature quantification. It is The exponential parameter of the data source is used to adjust the nonlinearity of feature quantization.

4. The method for optimizing station building construction cost based on genetic algorithm according to claim 1, characterized in that: In the aforementioned S200, the cost factor correlation influence formula is used in data processing and conversion to mine the degree to which various cost factors are affected by multi-source data features. The formula is: ,in, Indicates the degree to which a certain cost factor is affected by the characteristics of multi-source data. is the number of cost factor types, It is The influence coefficient of various cost factors, It is The power parameter of the cost factor, is the mean of the quantized feature values, Represents the quantitative value of features extracted from multi-source data.

5. The method for optimizing station building construction cost based on genetic algorithm according to claim 1, characterized in that: The cost-related factors of the entire construction process in the data processing and conversion in S200 are: labor cost, material cost, equipment cost and site layout cost; The labor costs include: the number of workers of different types, working hours and salary standards; The material cost is: the purchase price, usage and loss rate of various building materials; The equipment costs include: rental fees, maintenance costs and operating hours of construction equipment; The site layout costs include: site occupation fees and temporary facility construction fees.

6. The method for optimizing station building construction cost based on genetic algorithm according to claim 1, characterized in that: The calculation formula of the fitness function of the genetic algorithm in the optimization model in S300 is: ,in, is the optimized cost target value, is the number of construction links, It is The initial cost of each construction stage, is the degree to which the cost of this link is affected by the characteristics of multi-source data, is the adjustment coefficient related to the construction phase time, is the current construction time, It is The ideal completion time for each construction link, and are the maximum and minimum allowed completion time of this link respectively.

7. The method for optimizing station building construction cost based on genetic algorithm according to claim 1, characterized in that: In the above S300, the optimization model is constructed by performing iterative operations through a genetic algorithm. The genetic algorithm starts from a set initial population, and each individual corresponds to a construction cost configuration scheme. During the iterative operation, the roulette wheel selection method is used to select individuals for crossover operation according to the selection probability converted from the fitness value. The fitness value is calculated by the fitness function. The value is determined, and the crossover operation exchanges individual gene fragments with a crossover probability of 0.7-0.9 to generate new individuals. The mutation operation is performed with a probability of 0.01-0.05 to randomly change individual gene fragments. After repeated iterations, the individual fitness values of the population are continuously improved, and finally the optimal solution is screened out to construct a cost optimization model covering the entire process of station building construction.

8. The method for optimizing station building construction cost based on genetic algorithm according to claim 1, characterized in that: In the aforementioned S400 , the environmental factor data in the environment-driven optimization include: weather data, policy data, and market data; The weather data is collected by using meteorological monitoring equipment; Collection of the aforementioned policy data: collected through official websites, authoritative industry information platforms and policy and regulatory databases; Collection of the market data: collected through market research agencies and online data platforms.

9. The method for optimizing station building construction cost based on genetic algorithm according to claim 1, characterized in that: In the above-mentioned S400, the parameters of the genetic algorithm are automatically adjusted by the environment-driven optimization formula in the environment-driven optimization. The calculation formula is: ,in, and are the parameters of the genetic algorithm before and after adjustment, is the number of types of environmental change factors, It is The amount of change in environmental factors, is the mean value of the variation of the environmental factor, is its standard deviation, It is the influence weight of the corresponding environmental factors on the adjustment of algorithm parameters.

Images