Rail transit full-scene intelligent construction management and control method and system based on resource constraint

Abstract

The invention discloses a rail transit full-scene intelligent construction management and control method and system based on resource constraint, and particularly relates to the technical field of rail transit construction management, and the method comprises the following steps: carrying out the matching analysis through obtaining construction site resource data and project demands, combining historical resource use records with the current demands, and generating a resource matching index; through comparison of the real-time data and the standard data, construction abnormity is evaluated, and a construction abnormity index is generated; judging whether an optimization mechanism needs to be triggered or not according to the resource matching index and the construction anomaly index; when an optimization mechanism is triggered, resource scheduling is optimized by using a genetic algorithm based on resource constraint conditions, resource idleness and waste are minimized, and an optimized scheduling scheme is applied to realize intelligent resource management and construction management and control and improve construction efficiency and accuracy; according to the method, resource allocation can be dynamically adjusted, resource idleness and waste are reduced to the maximum extent, and maximization of resource utilization efficiency is ensured on the premise that construction requirements are met.

Description

Technical Field

[0001] The present invention relates to the technical field of rail transit construction management, and more specifically, to a rail transit full-scenario intelligent construction management and control method and system based on resource constraints. Background Art

[0002] With the increasing number of rail transit construction projects and the continuous expansion of their scale, project management faces huge challenges, especially in terms of resource allocation and control of the construction process. In the existing rail transit construction management and control system, unreasonable resource allocation and improper construction scheduling have led to problems such as idle resources, waste and delayed construction progress. This not only affects the efficiency and cost of the project, but also increases the risks in the construction process. In traditional construction management methods, resource scheduling and exception handling rely on manual operation and experience judgment, lack of intelligent means, and difficulty in coping with complex changes in the construction environment. Therefore, how to optimize resource allocation and construction processes through automation and intelligent means to ensure the rational use of resources is an urgent problem to be solved in the current field of rail transit construction management. Summary of the invention

[0003] To achieve the above object, the present invention provides the following technical solutions: The rail transit full-scenario intelligent construction control method based on resource constraints includes the following steps: Obtain resource data at the construction site, extract resource requirements at each stage from project requirements, conduct resource and demand matching analysis based on historical resource usage records and current requirements in the database, and generate a resource matching index for judging the degree of satisfaction between resources and requirements; Obtain real-time construction data from the construction site, and compare it with standard data in the database to evaluate the degree of abnormality in the construction process in real time and generate a construction abnormality index; Based on the resource matching index and construction abnormality index, determine whether to trigger the optimization mechanism; When the optimization mechanism is triggered, the genetic algorithm is used to adjust resource scheduling according to resource constraints to minimize resource idleness and waste, and the optimized resource scheduling scheme is applied.

[0004] In a preferred embodiment, before performing the resource-demand matching analysis, a resource-demand matching model is established based on the historical resource usage records in the database, and the output result of the resource-demand matching model is the resource matching index.

[0005] In a preferred embodiment, the resource and demand matching model refers to: ; represents the resource matching index corresponding to time period t, represents the nonlinear function used by resource type i in time period t, It represents the real-time availability ratio of resource type i in time period t. The real-time availability ratio is obtained by calculating the ratio of the demand and allocation of resource type i. represents the preset measurement ratio coefficient corresponding to resource type i in time period t, and the sum of the preset measurement ratio coefficients corresponding to all resource types i in time period t is one. is an adjustment factor used to adjust the importance of resources during the period T, i.e., the period t. T represents the period. Indicates the total number of resource type i.

[0006] In a preferred embodiment, the time period T is determined by: In time period t, all demand data of resource type i are converted into frequency domain data through fast Fourier transform. The periodicity of demand data of resource type i is found by detecting frequency components, and the demand period xqi corresponding to each resource type i with periodicity is obtained. Then, the greatest common divisor rule or weighted average method is used to calculate the time period T of the overall resource demand.

[0007] In a preferred embodiment, the nonlinear function is an exponential function.

[0008] In a preferred embodiment, the logic for obtaining the construction abnormality index is: Obtain the real-time construction data of the construction site, then compare it with the standard data in the database, and mark the i-th real-time monitoring data, i.e. the real-time data of the construction site, as , the i-th construction standard data in the database is marked as , and then use the following formula to calculate the construction abnormality index: ; The i in the formula represents the type of construction project, and t represents the construction time period t. The construction time period t is divided according to the same criteria as the time period t in the matching analysis between resources and demand. The i in the above indicates that the real-time data corresponding to the construction project type i is obtained, and It represents the value of the distance between the current time and the starting time point in the construction time period t. Indicates the real-time monitoring duration corresponding to the construction time period t, represents the preset impact coefficient corresponding to the construction project type i, m represents the total number of construction project type i, Indicates the response delay of the construction control system.

[0009] In a preferred embodiment, judging whether to trigger the optimization mechanism based on the resource matching index and the construction abnormality index refers to: Fuzzy reasoning is used to obtain the resource matching index and the construction abnormality index respectively as input variables, and the probability value of triggering the optimization mechanism is used as the output variable. The input variables are fuzzified and the values ​​of the input variables are converted into fuzzy sets. The output variables are fuzzified and the output variables are converted into fuzzy sets. Fuzzy rules are formulated to describe the probability of triggering the optimization mechanism under different data type combinations. The fuzzified input variables are inferred through fuzzy rules to obtain the probability value of triggering the optimization mechanism. Then, the probability value of triggering the optimization mechanism is compared with the preset trigger threshold. If the probability value of triggering the optimization mechanism is greater than the preset trigger threshold, the optimization mechanism is triggered. If the probability value of triggering the optimization mechanism is less than or equal to the preset trigger threshold, the optimization mechanism is not triggered.

[0010] In a preferred embodiment, when the optimization mechanism is triggered, the resource scheduling is adjusted using a genetic algorithm according to resource constraints to minimize resource idleness and waste. This means: Coding and initial population: Encode the resource scheduling plan into chromosome form and randomly generate m chromosomes as the initial population; Fitness evaluation: The preset resource constraints are used as constraints in the fitness evaluation, and the fitness evaluation formula is established: ; ; represents the total amount of resources of resource type i, Indicates the amount of resources used by resource type i, Indicates the amount of resources allocated to resource type i, represents the demand for resource type i, n represents the total number of resource type i, , are all preset evaluation coefficients. is the fitness value, Indicates the comprehensive resource utilization rate of the current corresponding time period t, Indicates the comprehensive resource waste rate of the current corresponding time period t, Selection operation: Use the roulette wheel selection method to select offspring as new parents; Crossover operation: randomly exchange data in chromosomes of different parents; Mutation operation: randomly select data of different offspring chromosomes for adjustment; Iteration and termination conditions: When the pre-set termination conditions are reached, the chromosome with the highest fitness is selected from the final population for decoding to obtain the optimal resource allocation plan.

[0011] In a preferred embodiment, the rail transit full-scenario intelligent construction management and control system based on resource constraints includes: The database stores historical resource usage records, preset resource constraints, acquired construction site resource data, and real-time construction data of the construction site; The matching analysis module obtains resource data of the construction site and extracts resource requirements of each stage from the project requirements. It performs matching analysis between resources and requirements based on the historical resource usage records and current requirements in the database and generates a resource matching index for judging the degree of satisfaction between resources and requirements. The abnormality analysis module obtains the real-time construction data of the construction site and compares it with the standard data in the database to evaluate the abnormality of the construction process in real time and generate a construction abnormality index; The optimization mechanism trigger judgment module determines whether to trigger the optimization mechanism based on the resource matching index and the construction abnormality index; Optimization module,When the optimization mechanism is triggered, the genetic algorithm is used to adjust the resource scheduling according to the resource constraints to minimize resource idleness and waste, and the optimized resource scheduling scheme is applied.

[0012] Technical effects and advantages of the present invention: Based on the analysis of resource matching index, the present invention can dynamically adjust the allocation of resources to minimize the idleness and waste of resources. By using genetic algorithm to optimize resource scheduling, it is possible to ensure the maximization of resource utilization efficiency and improve construction efficiency while meeting construction needs.

[0013] The present invention can timely discover abnormal situations in the construction process through real-time calculation of the construction anomaly index, and quickly make adjustments based on system feedback, thereby reducing construction delays and unnecessary rework, and ensuring that the project proceeds smoothly as planned.

[0014] The present invention makes resource scheduling and construction abnormality management intelligent by introducing fuzzy reasoning and genetic algorithms. The system can analyze and optimize according to real-time data and historical records, automatically determine whether the optimization mechanism needs to be triggered, reduce dependence on manual experience, and greatly improve the intelligent level of construction management.

[0015] Through intelligent algorithms and real-time data feedback, the present invention can accurately grasp the resource status and construction progress of the construction site, ensure that resources can be reasonably scheduled according to the actual needs of the construction, and improve the accuracy and timeliness of construction management.

[0016] Through automated resource scheduling and exception management, the present invention effectively reduces various risks that may occur during the construction process, reduces manual intervention and resource waste, ultimately reduces construction costs, and improves the overall benefits of the construction project. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings; Figure 1 This is a schematic diagram of the resource-constrained rail transit full-scenario intelligent construction control method of the present invention.

[0018] Figure 2 This is a schematic diagram of the rail transit full-scenario intelligent construction management and control system based on resource constraints in the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] Reference Figure 1 - Figure 2 The following examples are obtained: Embodiment 1: A rail transit full-scenario intelligent construction management and control method based on resource constraints, comprising the following steps: Obtain resource data at the construction site, extract resource requirements at each stage from project requirements, perform resource and demand matching analysis based on historical resource usage records and current requirements in the database, and generate a resource matching index used to judge the degree of satisfaction between resources and requirements; the purpose of this step is to grasp the existing resource situation at the construction site in real time, including personnel, equipment, materials, etc. At the same time, by analyzing project requirements, clarify the types and quantities of resources required at each construction stage. The extraction and analysis of this data helps to ensure that resource supply can meet the actual construction needs and provide a basis for subsequent resource scheduling. The index is obtained by matching and analyzing current resources with project requirements at each stage, and is used to judge whether resources can effectively meet construction needs. The index can quantify the degree of matching between resources and requirements. The significance of this step is to provide data support for resource optimization and help decision makers to reasonably schedule resources during construction to avoid waste or shortages.

[0021] Acquire real-time construction data from the construction site, and by comparing it with the standard data in the database, evaluate the degree of abnormality in the construction process in real time and generate a construction abnormality index; by acquiring various data from the construction site (such as progress, equipment use, etc.) in real time and comparing it with the standard data in the database, the system can identify whether there are abnormalities in the construction process. The generated construction abnormality index can quantify the severity of the abnormality, which helps to quickly discover and solve problems and avoid greater impact on the project.

[0022] Based on the resource matching index and the construction anomaly index, determine whether to trigger the optimization mechanism; this step combines the resource matching index and the construction anomaly index to determine whether the existing construction and resource scheduling plans meet the needs, and triggers the optimization mechanism if they do not. By comprehensively evaluating these two indexes, it can ensure that the system intervenes at the moment when optimization is most needed to avoid resource waste or construction stagnation.

[0023] When the optimization mechanism is triggered, the genetic algorithm is used to adjust resource scheduling according to resource constraints to minimize resource idleness and waste, and the optimized resource scheduling scheme is applied. Once the optimization mechanism is triggered, the system uses genetic algorithms to optimize resource scheduling according to resource constraints. Genetic algorithm is an optimization method based on natural selection and genetic variation, which can help the system find the optimal solution in complex resource scheduling problems. Through genetic algorithms, the system can effectively reduce idleness and waste of resources, maximize the utilization of resources during the construction process, thereby improving construction efficiency and reducing costs. Finally, the optimized resource scheduling scheme will be applied to actual construction. This step ensures that the system can dynamically adjust according to real-time construction and resource conditions to make the construction process more efficient. Through this optimized scheme, the system can reduce the waste of resources in the project and improve the construction quality.

[0024] Before conducting resource and demand matching analysis, a resource and demand matching model is established based on the historical resource usage records in the database. The output of the resource and demand matching model is the resource matching index. The resource and demand matching model refers to: ; represents the resource matching index corresponding to time period t, represents the nonlinear function used by resource type i in time period t, It represents the real-time availability ratio of resource type i in time period t. The real-time availability ratio is obtained by calculating the ratio of the demand and allocation of resource type i. represents the preset measurement ratio coefficient corresponding to resource type i in time period t, and the sum of the preset measurement ratio coefficients corresponding to all resource types i in time period t is one. is an adjustment factor used to adjust the importance of resources during the period T, i.e., the period t. T represents the period. Indicates the total number of resource type i.

[0025] Resource Matching Index : It represents the degree of matching between resources and demand in time period t. Specifically, it is calculated by transforming the ratio of availability to demand of all resource types i through nonlinear function and combining weights and dynamic adjustment factors.

[0026] Nonlinear functions : represents the proportion of actually available resources of resource type i in time period t. This nonlinear function is used to transform the actual availability of resources to reflect the importance and scarcity of resources in different periods.

[0027] Weight : It represents the importance of resource type i in time period t. It is set according to the priority and demand of resources and plays an important role in overall resource matching.

[0028] Dynamic Adjustment Factor : This factor reflects the periodic fluctuation and adjustment of resources within time t. Parameters is the adjustment factor, indicating the fluctuation range of resource demand, and T is the time period, indicating the periodic changes in resource scheduling.

[0029] Get resource usage: Extract historical resource usage data from the database and calculate the actual availability of each resource in the current time period.

[0030] Demand analysis and ratio calculation: through the formula , a nonlinear calculation is performed on the demand and availability of each resource to obtain the ratio of actual availability to demand.

[0031] Introducing weights and adjustment factors: Based on the importance of resource types and the time period T, the matching of resources in the time period is calculated, and the results are dynamically modified in combination with the adjustment factors.

[0032] Generate resource matching index: Add up the matching conditions of all resource types to obtain the final resource matching index, which reflects the overall matching degree between resources and requirements.

[0033] The nonlinear function is an exponential function. , represents the adjustment parameter used to control the sensitivity of the matching function to the ratio of the demand and allocation of resource type i, The value of the exponential function changes dynamically with the matching of resource allocation and demand, and can effectively quantify the real-time availability of resources and the matching degree of demand. Specifically: When resource allocation completely matches demand: At this time, the ratio value is 1 and the exponential function value is 1, indicating that the supply and demand of resources are completely balanced and the project is progressing smoothly. When resources are in short supply, the ratio value is <1 and the exponential function decreases rapidly, reflecting the severity of resource shortage and indicating the need to adjust resource scheduling. When resources are in excess, although the ratio value is >1, the exponential function will not grow infinitely, ensuring that even if there is a slight excess of resources, it will not excessively affect the matching index, thereby avoiding unreasonable scheduling due to over-allocation.

[0034] When the resource matching index is large, it indicates that the allocation of resources has exceeded the demand, that is, the resource supply in the system is sufficient to fully meet the construction needs of the current stage.

[0035] Supply exceeds demand: If the resource matching index continues to increase, it means that the amount of resource allocation obviously exceeds the amount of demand, and there may be a situation of resource redundancy. Although the project will not be affected by insufficient resources, excessive resource allocation may lead to waste of resources.

[0036] Reasonableness of supply and demand balance: When the index is large and still within a reasonable range (for example, close to but slightly greater than 1), it can be considered that the current resource supply and demand are well matched, and the project progress and resource allocation are both in the optimal state. However, if the index is too large, it may indicate that some resource allocation needs to be reduced to avoid resource waste and management complexity.

[0037] The time period T is determined by: In time period t, all demand data of resource type i are converted into frequency domain data through fast Fourier transform. The periodicity of demand data of resource type i is found by detecting frequency components, and the demand period xqi corresponding to each resource type i with periodicity is obtained. Then, the greatest common divisor rule or weighted average method is used to calculate the time period T of the overall resource demand.

[0038] Fast Fourier Transform (FFT) is a mathematical method that converts time domain data into frequency domain data in order to reveal the frequency components in the data. In the periodic analysis of resource type i demand data, FFT can reveal periodic information through the following steps: Acquisition of time domain data: First, obtain the demand data of resource type i over a period of time. These data are arranged in chronological order and show the changes in resource demand.

[0039] Convert to frequency domain data: Convert the time domain data to the frequency domain through Fast Fourier Transform. Frequency domain data reflects the different frequency components (i.e. periodicity) in the time series. If there is some periodic fluctuation in the demand data, FFT will show the periodic fluctuation as a peak in the frequency domain.

[0040] Detect frequency components: In the frequency domain graph, each peak corresponds to a specific period in the time domain. By detecting the peaks of the main frequencies, it is possible to identify significant periods in resource demand and calculate the demand period for resource type i.

[0041] Periodicity identification: By detecting the peak value of the frequency component (i.e., the significant frequency), the period of resource demand data can be derived. The demand period xqi is equal to 1 divided by the frequency value. When determining the comprehensive cycle of multiple resource type requirements, there are usually two options: the greatest common divisor rule or the weighted average method. These two methods have different applicable scenarios, as described below: The greatest common divisor rule is usually applicable to situations where the demand cycles have a certain integer multiple relationship. For example, if the demand cycle of some resources is 3 days and the demand cycle of other resources is 6 days, their greatest common divisor is 3 days, which means that there will be a common peak in resource demand every 3 days.

[0042] Advantages: By adopting the greatest common divisor method, it can ensure that the scheduling and management of resource requirements are completed within the minimum cycle, avoiding unnecessary waste or redundant scheduling of resources over a long period.

[0043] When to use: When the demand cycles of multiple resource types are integer multiples (for example, 2 days, 4 days, or 8 days), the greatest common divisor rule can better capture the common periodicity and ensure the synchronization of resource scheduling.

[0044] Weighted average method applicable scenarios: The weighted average method is applicable to situations where the demand cycles of different resources vary greatly and there is no obvious integer multiple relationship. In this case, by assigning weights to the demand cycles of various resources, a comprehensive cycle can be smoothed out to ensure that the system can still operate efficiently without complete synchronization.

[0045] Advantages: The weighted average method ensures the flexibility of the scheduling cycle by assigning weights to different resources. Especially when the demand for certain types of resources is small but the cycle is short, the overall scheduling rhythm will not be affected by these short-cycle demands.

[0046] When to use: When the demand cycles of various resources vary greatly (for example, 3 days, 7 days, 10 days), and the common cycle cannot be found through the greatest common divisor method, the weighted average method is a better choice. It ensures moderate flexibility in resource scheduling while avoiding resource conflicts as much as possible.

[0047] Higher priority: Greatest common divisor rule. When the demand cycles of multiple resources show an obvious multiple relationship, the greatest common divisor rule can maximize the synchronous scheduling of resources and improve overall efficiency, so it has a higher priority.

[0048] Second-best choice: weighted average method. When the multiple relationship is not obvious or the demand cycles vary greatly, the weighted average method provides a more flexible comprehensive cycle selection, which is suitable for situations where resource demand diversity is strong. The weighted average method is an existing technology well known to people in this field and will not be elaborated on here.

[0049] The logic for obtaining the construction anomaly index is: Obtain the real-time construction data of the construction site, then compare it with the standard data in the database, and mark the i-th real-time monitoring data, i.e. the real-time data of the construction site, as , the i-th construction standard data in the database is marked as , and then use the following formula to calculate the construction abnormality index: ; The i in the formula represents the type of construction project, and t represents the construction time period t. The construction time period t is divided according to the same criteria as the time period t in the matching analysis between resources and demand. The i in the above indicates that the real-time data corresponding to the construction project type i is obtained, and It represents the value of the distance between the current time and the starting time point in the construction time period t. Indicates the real-time monitoring duration corresponding to the construction time period t, represents the preset impact coefficient corresponding to the construction project type i, m represents the total number of construction project type i, Indicates the response delay of the construction control system.

[0050] Calculation of construction abnormality index: This index is calculated by analyzing the real-time data of the construction site. Standard data in the database Comparative calculations are performed to reflect deviations between the construction site and the standard plan.

[0051] Core idea: Perform weighted average processing on the data deviations of each type of construction project to obtain the overall abnormal situation.

[0052] Introducing the time difference term It is used to consider the changes in data at different times, ensuring that not only the deviation of the current data but also the dynamic changes over time can be captured.

[0053] Weighting coefficient : Reflects the impact of different construction projects on the overall anomaly index. Certain critical construction tasks may have a greater impact on project progress and therefore have a higher weight, while non-critical tasks may have a lower weight.

[0054] The role of the construction anomaly index: This index is mainly used to evaluate the gap between the project construction progress and the expected goals. When the anomaly index is high, it means that there are more or more serious deviations in the project, and adjustments or corrections may be needed. By calculating the construction anomaly index, project managers can find problems in time and take corresponding corrective measures to prevent project delays or quality degradation.

[0055] The larger the construction abnormality index is, the more it usually indicates the following aspects: The deviation between the construction site data and the standard data is large: this means that there is a significant gap between the construction progress and the project plan, which may be due to insufficient resources, delayed construction progress or quality problems.

[0056] Construction abnormalities occur frequently: Time difference item Taking into account the dynamic changes of construction projects, if the index is larger, it means that the deviation of construction data has not been corrected for a long period of time and the abnormal situation persists.

[0057] Abnormalities in construction projects with higher weights: If abnormalities occur in key projects with higher weights, the abnormality index will be larger, prompting managers to focus on the progress of these key tasks.

[0058] In the actual construction monitoring process, it takes a certain amount of time to obtain and process real-time data. Here, the feedback delay factor τ reflects how long it takes the system to respond after receiving the monitoring data. If the feedback delay is large, the system's response speed will be slow, which may cause the actual adjustment to fail to keep up with the data changes. Therefore, the standard data The division by τ is to compensate for the response lag caused by feedback delay.

[0059] The standard data Dividing by τ can be considered as a correction to the system's feedback capability. This adjustment allows the system to respond more sensitively to rapidly changing data, especially when there is a large deviation in the monitored items. In other words, the greater the feedback delay, the less the system adjusts the standard data, which can avoid overreaction and ensure that the system does not cause abnormal feedback due to delay problems.

[0060] The introduction of the feedback delay factor τ can also help the system maintain a certain degree of stability in a rapidly changing environment. Scaling the standard data can prevent too frequent system adjustments, thereby avoiding frequent system feedback when data fluctuations are small. This ensures timely response to anomalies and avoids instability caused by excessive adjustments.

[0061] In actual construction, real-time data from the construction site is obtained and compared with the standard data in the database. The construction anomaly index can be calculated to evaluate the abnormal situation in the construction process in real time. The difference between the real-time data and the standard data of different projects is monitored, and the delay of system response is considered. Through weight adjustment and time difference, the system can respond and handle these anomalies faster, thereby maintaining the smooth progress of construction.

[0062] Based on the resource matching index and construction abnormality index, judging whether to trigger the optimization mechanism means: Fuzzy reasoning is used to obtain the resource matching index and the construction abnormality index respectively as input variables, and the probability value of triggering the optimization mechanism is used as the output variable. The input variables are fuzzified and the values ​​of the input variables are converted into fuzzy sets. The output variables are fuzzified and the output variables are converted into fuzzy sets. Fuzzy rules are formulated to describe the probability of triggering the optimization mechanism under different data type combinations. The fuzzified input variables are inferred through fuzzy rules to obtain the probability value of triggering the optimization mechanism. Then, the probability value of triggering the optimization mechanism is compared with the preset trigger threshold. If the probability value of triggering the optimization mechanism is greater than the preset trigger threshold, the optimization mechanism is triggered. If the probability value of triggering the optimization mechanism is less than or equal to the preset trigger threshold, the optimization mechanism is not triggered.

[0063] First, the system obtains the resource matching index and the construction abnormality index respectively and takes them as input variables. These two indexes reflect the rationality of resource allocation and the abnormal conditions in the construction process. Next, the input variables are fuzzified. The purpose of fuzzification is to convert clear numerical values ​​into fuzzy sets, such as fuzzy classifications such as "low", "medium", and "high". This is to deal with the uncertainty in reality, because the actual resource matching index and construction abnormality index may not always be clear. The output variable of the system is the probability value of triggering the optimization mechanism, which indicates the possibility that the system should trigger the optimization mechanism under specific circumstances. This also requires fuzzification and converting it into fuzzy sets, such as "low probability", "medium probability", "high probability", etc. Based on fuzzification, the system formulates a set of fuzzy rules. These rules describe the probability of triggering the optimization mechanism under different data combinations. For example, if the resource matching index is low and the construction abnormality index is high, the probability of triggering the optimization mechanism is large; conversely, if the resource matching index is high and the construction abnormality index is low, the probability of triggering the optimization is small. The system substitutes the fuzzified input variables (resource matching index and construction abnormality index) into the fuzzy rules and derives the final probability value of triggering the optimization mechanism through fuzzy reasoning method. Fuzzy reasoning can derive different probabilities based on different input combinations. Finally, the system compares the calculated probability value of triggering the optimization mechanism with the preset trigger threshold. If the probability value is greater than the preset threshold, the system considers that the optimization mechanism should be triggered; if the probability value is less than or equal to the threshold, the optimization mechanism is not triggered.

[0064] When the optimization mechanism is triggered, the genetic algorithm is used to adjust resource scheduling according to resource constraints to minimize resource idleness and waste. Coding and initial population: Encode the resource scheduling plan into chromosome form and randomly generate m chromosomes as the initial population; the set of initial solutions is the population. Each solution (individual) represents a resource scheduling plan, including the allocation of personnel, equipment, materials, etc. The size of the population can be set according to the complexity of the problem, generally dozens to hundreds of individuals. Each individual can be represented as a coded string (such as binary or real number coding), in which each position represents the allocation of a certain type of resource in a certain period of time.

[0065] Fitness evaluation: The fitness function is the key to measuring the quality of each individual. The fitness function should be designed to minimize resource idleness and waste while satisfying resource constraints. Specifically: Use the preset resource constraints as constraints in the fitness evaluation, and establish the fitness evaluation formula: ; ; represents the total amount of resources of resource type i, Indicates the amount of resources used by resource type i, Indicates the amount of resources allocated to resource type i, represents the demand for resource type i, n represents the total number of resource type i, , These are preset evaluation coefficients, which are weight coefficients to balance idleness and waste, and are adjusted according to actual needs. is the fitness value, Indicates the comprehensive resource utilization rate of the current corresponding time period t, Indicates the comprehensive resource waste rate of the current corresponding time period t, Related to resource utilization, indicating resource scheduling efficiency. The higher the resource utilization, the larger the value of this part. ; is related to the resource waste rate, indicating the current resource waste situation. The more resources are wasted, The larger the F value is, the more unused and wasted the resources are, indicating that there is a problem with the scheduling scheme. Therefore, the goal of optimizing scheduling is to minimize the F value. Ideally, when F approaches a smaller value, it means that the resources are fully utilized without obvious waste or shortage.

[0066] Selection operation: Use the roulette wheel selection method to select offspring as new parents; Crossover operation: randomly exchange data in chromosomes of different parents; crossover simulates the exchange of parental genes in biological inheritance. By exchanging some genes of two individuals, a new resource scheduling plan can be generated.

[0067] Mutation operation: Randomly select data from different offspring chromosomes for adjustment; mutation is used to introduce randomness to prevent the algorithm from falling into a local optimal solution. The mutation operation randomly changes certain genes in individuals (such as resource allocation) to generate new scheduling solutions. The probability of mutation is small, usually set to 1% to 5% to maintain the diversity of the population.

[0068] Iteration and termination conditions: When the pre-set termination conditions are reached, the chromosome with the highest fitness is selected from the final population for decoding to obtain the optimal resource allocation plan.

[0069] The genetic algorithm terminates when any of the following conditions is met: When the preset maximum number of iterations is reached or the fitness of the optimal individual no longer changes significantly, a stable state is reached, and the constraints are met. The optimal individual finally found, that is, the resource scheduling plan, will be used to minimize resource idleness and waste in actual construction. The system will dynamically adjust the allocation plan according to the resource constraints of the current construction site to ensure efficient use of resources.

[0070] Example 2: A rail transit full-scenario intelligent construction management and control system based on resource constraints, comprising: The database stores historical resource usage records, preset resource constraints, acquired construction site resource data, and real-time construction data of the construction site; The matching analysis module obtains resource data of the construction site and extracts resource requirements of each stage from the project requirements. It performs matching analysis between resources and requirements based on the historical resource usage records and current requirements in the database and generates a resource matching index for judging the degree of satisfaction between resources and requirements. The abnormality analysis module obtains the real-time construction data of the construction site and compares it with the standard data in the database to evaluate the abnormality of the construction process in real time and generate a construction abnormality index; The optimization mechanism trigger judgment module determines whether to trigger the optimization mechanism based on the resource matching index and the construction abnormality index; Optimization module,When the optimization mechanism is triggered, the genetic algorithm is used to adjust the resource scheduling according to the resource constraints to minimize resource idleness and waste, and the optimized resource scheduling scheme is applied.

[0071] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0072] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0073] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0074] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0075] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A full-scenario intelligent construction management and control method for rail transit based on resource constraints, characterized in that: The following steps are involved: Obtain resource data at the construction site, extract resource requirements at each stage from project requirements, conduct resource and demand matching analysis based on historical resource usage records and current requirements in the database, and generate a resource matching index for judging the degree of satisfaction between resources and requirements; Obtain real-time construction data from the construction site, and compare it with standard data in the database to evaluate the degree of abnormality in the construction process in real time and generate a construction abnormality index; Based on the resource matching index and construction abnormality index, determine whether to trigger the optimization mechanism; When the optimization mechanism is triggered, the genetic algorithm is used to adjust resource scheduling according to resource constraints to minimize resource idleness and waste, and the optimized resource scheduling scheme is applied.

2. The resource-constrained rail transit full-scenario intelligent construction management and control method according to claim 1 is characterized in that: Before conducting resource and demand matching analysis, a resource and demand matching model is established based on historical resource usage records in the database, and the output result of the resource and demand matching model is the resource matching index.

3. The resource-constrained rail transit full-scenario intelligent construction management and control method according to claim 2 is characterized in that: The resource and demand matching model refers to: ; represents the resource matching index corresponding to time period t, represents the nonlinear function used by resource type i in time period t, It represents the real-time availability ratio of resource type i in time period t. The real-time availability ratio is obtained by calculating the ratio of the demand and allocation of resource type i. represents the preset measurement ratio coefficient corresponding to resource type i in time period t, and the sum of the preset measurement ratio coefficients corresponding to all resource types i in time period t is one. is an adjustment factor used to adjust the importance of resources during the period T, i.e., the period t. T represents the period. Represents the total number of resource type i.

4. The resource-constrained rail transit full-scenario intelligent construction management and control method according to claim 3 is characterized in that: The time period T is determined by: In time period t, all demand data of resource type i are converted into frequency domain data through fast Fourier transform. The periodicity of demand data of resource type i is found by detecting frequency components, and the demand period xqi corresponding to each resource type i with periodicity is obtained. Then, the greatest common divisor rule or weighted average method is used to calculate the time period T of the overall resource demand.

5. The resource-constrained rail transit full-scenario intelligent construction management and control method according to claim 4 is characterized in that: The nonlinear function is an exponential function.

6. The resource-constrained rail transit full-scenario intelligent construction control method according to claim 5 is characterized in that: The logic for obtaining the construction anomaly index is: Obtain the real-time construction data of the construction site, then compare it with the standard data in the database, and mark the i-th real-time monitoring data, i.e. the real-time data of the construction site, as , the i-th construction standard data in the database is marked as , and then use the following formula to calculate the construction abnormality index: ; The i in the table represents the type of construction project, and t represents the construction time period t. The construction time period t is divided according to the same criteria as the time period t in the matching analysis of resources and demand. The i in the above indicates that the real-time data corresponding to the construction project type i is obtained, and It represents the value of the distance between the current time and the starting time point in the construction time period t. Indicates the real-time monitoring duration corresponding to the construction time period t, represents the preset impact coefficient corresponding to the construction project type i, m represents the total number of construction project type i, Indicates the response delay of the construction control system.

7. The resource-constrained rail transit full-scenario intelligent construction management and control method according to claim 6 is characterized in that: Based on the resource matching index and construction abnormality index, judging whether to trigger the optimization mechanism means: Fuzzy reasoning is used to obtain the resource matching index and the construction abnormality index respectively as input variables, and the probability value of triggering the optimization mechanism is used as the output variable. The input variables are fuzzified and the values ​​of the input variables are converted into fuzzy sets. The output variables are fuzzified and the output variables are converted into fuzzy sets. Fuzzy rules are formulated to describe the probability of triggering the optimization mechanism under different data type combinations. The fuzzified input variables are inferred through fuzzy rules to obtain the probability value of triggering the optimization mechanism. Then, the probability value of triggering the optimization mechanism is compared with the preset trigger threshold. If the probability value of triggering the optimization mechanism is greater than the preset trigger threshold, the optimization mechanism is triggered. If the probability value of triggering the optimization mechanism is less than or equal to the preset trigger threshold, the optimization mechanism is not triggered.

8. The resource-constrained rail transit full-scenario intelligent construction management and control method according to claim 7 is characterized in that: When the optimization mechanism is triggered, the genetic algorithm is used to adjust resource scheduling according to resource constraints to minimize resource idleness and waste. Coding and initial population: Encode the resource scheduling plan into chromosome form and randomly generate m chromosomes as the initial population; Fitness evaluation: The preset resource constraints are used as constraints in the fitness evaluation, and the fitness evaluation formula is established: ； ； represents the total amount of resources of resource type i, Indicates the amount of resources used by resource type i, Indicates the amount of resources allocated to resource type i, represents the demand for resource type i, n represents the total number of resource type i, , are all preset evaluation coefficients. is the fitness value, Indicates the comprehensive resource utilization rate of the current corresponding time period t, Indicates the comprehensive resource waste rate of the current corresponding time period t, Selection operation: Use the roulette wheel selection method to select offspring as new parents; Crossover operation: randomly exchange data in chromosomes of different parents; Mutation operation: randomly select data of different offspring chromosomes for adjustment; Iteration and termination conditions: When the pre-set termination conditions are reached, the chromosome with the highest fitness is selected from the final population for decoding to obtain the optimal resource allocation plan.

9. A rail transit full-scenario intelligent construction control system based on resource constraints, which is implemented based on the rail transit full-scenario intelligent construction control method based on resource constraints as described in any one of claims 1 to 8, characterized in that: include: The database stores historical resource usage records, preset resource constraints, acquired construction site resource data, and real-time construction data of the construction site; The matching analysis module obtains the resource data of the construction site and extracts the resource requirements of each stage from the project requirements. It performs matching analysis between resources and requirements based on the historical resource usage records and current requirements in the database and generates a resource matching index for judging the degree of satisfaction between resources and requirements. The abnormality analysis module obtains the real-time construction data of the construction site and compares it with the standard data in the database to evaluate the abnormality of the construction process in real time and generate a construction abnormality index; The optimization mechanism trigger judgment module determines whether to trigger the optimization mechanism based on the resource matching index and the construction abnormality index; Optimization module,When the optimization mechanism is triggered, the genetic algorithm is used to adjust the resource scheduling according to the resource constraints to minimize resource idleness and waste, and the optimized resource scheduling scheme is applied.

Images