Power infrastructure construction progress adaptive scheduling method based on digital twinning

Abstract

The invention provides an electric power infrastructure construction progress self-adaptive scheduling method based on digital twinning. The method comprises the steps that a construction progress digital twinning model is constructed according to preset historical data and construction data fed back in real time on a construction site; predicting a construction progress trend based on the construction progress digital twinborn model to obtain construction progress prediction data; performing construction safety assessment according to the construction progress prediction data in combination with uncertainty of human factors, a construction process and environmental conditions to obtain a construction safety assessment result; designing an adaptive scheduling method according to the construction safety evaluation result and the construction progress prediction data to optimize a construction progress scheduling scheme; performing iterative optimization on the optimized construction progress scheduling scheme by using an optimization algorithm to obtain an optimal scheduling scheme; and applying the optimal scheduling scheme to actual construction management. According to the method, the adaptive scheduling algorithm is combined with the digital twinborn model, so that intelligent progress management in power infrastructure construction can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twins, and particularly to an adaptive scheduling method for the construction progress of power infrastructure based on digital twins. Background Art

[0002] Power infrastructure refers to construction projects carried out by a country to meet the needs of economic and social development, mainly focusing on the supply and distribution of electricity. These projects include the construction of transmission and distribution networks, substations, and transmission equipment. With the development of the economy, the demand for power resources has been increasing, and the number of power infrastructure projects has also risen accordingly. However, these projects not only have a long construction period but also face uncertainties such as external environmental interference and differences in the ability levels of workers. Traditional construction progress management methods often struggle to cope with the dynamically changing construction environment and diverse conditions, resulting in problems such as project delays, cost overruns, and substandard quality. Therefore, in the field of power infrastructure, there is an urgent need for an efficient and intelligent construction progress management method.

[0003] Currently, research on construction progress management mainly adopts two methods: construction progress monitoring and construction progress simulation. At present, some scholars have proposed a real-time construction progress monitoring method based on BIM and video monitoring technology, achieving three-dimensional visual analysis of the deviation between the actual construction progress and the planned progress. In addition, some scholars have proposed an approximate real-time simulation framework for real-time update and simulation analysis calculation of the simulation model based on real-time data collected on-site. Despite certain progress, traditional methods still have deficiencies in dynamically adapting to changes in the construction environment and uncertainties, often resulting in low efficiency in scheduling and resource allocation. To address these limitations, adaptive scheduling methods have emerged. Adaptive scheduling methods refer to systems that can automatically adjust scheduling parameters or strategies based on real-time data and environmental changes to adapt to external changes and uncertainties. Some existing research has applied adaptive scheduling to construction progress control. Some scholars have also proposed a construction scheduling and resource allocation method based on actual status data, using dynamic data-driven simulation for adaptive scheduling calculations during short-term construction processes. In the construction of power infrastructure, adaptive scheduling can help managers promptly address challenges brought about by human factors, construction processes, and environmental uncertainties, thereby optimizing construction progress and resource utilization to ensure the successful completion of projects.

[0004] The rise of digital twin technology has provided new opportunities for solving many challenges in the construction of power infrastructure. Digital twin technology evolved from the mirror space model proposed by Professor Michael Grieves of the University of Michigan in the United States and was later supplemented and improved by NASA. It is defined as a digital virtual space constructed based on physical models, historical operation data, and sensor data. Digital twin technology uses multi-physics, multi-scale, and probabilistic simulation technologies to map the entire life cycle of physical entities. This technology can not only quickly collect system information and achieve remote real-time monitoring but also perform predictive analysis and timely adjust the system operation status. Digital twin technology has achieved remarkable results in the construction field. For example, some researchers have proposed a digital twin application framework for spatial dimension modeling during the construction process of prefabricated buildings, verifying the feasibility and effectiveness of digital twin modeling methods in managing the safety risks of component hoisting. Similarly, some researchers have currently proposed an intelligent prestressed steel structure cable tensioning method driven by digital twin and artificial intelligence, solving the problems in multi-dimensional, large-scale, and complex tensioning resource scheduling. However, the current research mainly focuses on the construction of digital twin models and data collection, and relatively little research has been done on construction progress control. Summary of the Invention

[0005] In order to overcome the deficiencies of the prior art, the purpose of the present invention is to provide an adaptive scheduling method for the construction progress of power infrastructure based on digital twins, which combines an adaptive scheduling algorithm with a digital twin model to achieve intelligent progress management in the construction of power infrastructure.

[0006] To achieve the above objective, the present invention provides the following solutions:

[0007] An adaptive scheduling method for the construction progress of power infrastructure based on digital twins, comprising:

[0008] Construct a construction progress digital twin model according to preset historical data and construction data obtained from real-time feedback at the construction site;

[0009] Predict the construction progress trend based on the construction progress digital twin model to obtain construction progress prediction data;

[0010] Combining the uncertainties of human factors, construction processes, and environmental conditions, conduct a construction safety assessment based on the construction progress prediction data to obtain a construction safety assessment result;

[0011] Design an adaptive scheduling method according to the construction safety assessment result and the construction progress prediction data to optimize the construction progress scheduling plan;

[0012] Use an optimization algorithm to iteratively optimize the optimized construction progress scheduling plan to obtain an optimal scheduling plan;

[0013] Apply the optimal scheduling plan to the actual construction management.

[0014] Preferably, the construction progress digital twin model includes: a 3D model, a behavior model, and a rule model.

[0015] Preferably, based on the construction progress digital twin model, predict the construction progress trend to obtain construction progress prediction data, including:

[0016] Based on the construction progress digital twin model, realize the real-time synchronization of the construction data and the virtual space through low-latency and high-bandwidth information interaction;

[0017] Perform real-time calculation and analysis through the construction progress digital twin model, and feedback the calculation and analysis results to the cloud data platform and update the historical data.

[0018] Preferably, combining the uncertainties of human factors, construction processes, and environmental conditions, conduct a construction safety assessment based on the construction progress prediction data to obtain a construction safety assessment result, including:

[0019] Based on the actual situation of the construction site, collect data related to human factors, construction process factors, and environmental factors;

[0020] Based on the job hazard analysis method and the safety checklist analysis method, identify the uncertain risk factors in the construction process according to the data related to human factors, construction process factors, and environmental factors, and obtain a list of uncertain risk factors;

[0021] According to the list of uncertain risk factors, use the grey relational analysis method to quantify the impact of each risk factor on the safety level in the construction project to construct an initial safety assessment model;

[0022] Define evaluation indicators according to the evaluation results of the initial safety assessment model, and use the entropy weight method to adjust the weights of each evaluation indicator to form a comprehensive safety assessment model;

[0023] Introduce a shutdown mechanism into the comprehensive safety assessment model, and conduct a construction safety assessment on the construction progress prediction data according to the comprehensive safety assessment model to obtain the construction safety assessment result.

[0024] Preferably, the calculation formula of the job hazard analysis method is: R = f(L, S); where R is the possibility of safety risk, L is the probability of an accident occurring, S is the severity of the accident consequences, and R is divided into multiple levels.

[0025] Preferably, the evaluation indicators include a positive indicator Q and a negative indicator U; the calculation formula of the positive indicator Q is: The calculation formula of the negative indicator U is: Among them, x i is the sequence of index observation values, and x m is the measured value of the evaluation index.

[0026] Preferably, the calculation formula of the entropy weight method is: Among them, B is the entropy weight, and E i is the information entropy of x i .

[0027] Preferably, the expression of the shutdown mechanism is: Among them, z i is the construction variable. When z i = 0, it means shutdown. When z i = 1, it means normal construction; F is the lower limit value of the comprehensive score F. The calculation formula of the comprehensive score F is: Among them, Q i is the positive index of x i , B i is the entropy weight of x i , and n is the sum of the number of indicators.

[0028] Preferably, an adaptive scheduling method is designed according to the construction safety assessment result and the construction progress prediction data to optimize the construction progress scheduling plan, including:

[0029] Taking the shortest construction period as the goal, making decisions on the initial construction plan variables, and considering the uncertainty of environmental factors, taking the minimum construction total cost as the goal, making decisions on the plan adjustment variables to obtain a two-stage objective function; the initial construction plan variables include construction task allocation and resource allocation; the plan adjustment variables include construction task adjustment amount and resource adjustment amount; the expression of the objective function is: Among them, Φ / Θ are the decision variable sets in the first stage / second stage respectively; T is the construction period; K is the set of types of resources required for construction, including material resources and human resources; is the unit cost of resource k; is the usage amount of resource k on the t-th day of the construction plan; z t is the construction indication variable. When z t = 1, the construction proceeds normally; when z t = 0, the construction stops; is the unit adjustment cost of resource k; represents the usage adjustment amount of resource k on the t-th day due to environmental impact; f(T) and f(E) are the penalty-reward functions for the construction period and quality respectively; pc1 and bc1 are the penalty-reward factors for construction period delay and construction period advance respectively; T cdis the contract duration; pc2 and bc2 are the penalty-reward factors for quality compliance and non-compliance respectively; E cd is the contract quality;

[0030] Construct constraint conditions; the constraint conditions include: resource constraints, quality constraints, and environmental constraints;

[0031] Based on the two-stage objective function and the constraint conditions, optimize the construction tasks and resource allocation based on deterministic conditions to generate an initial construction plan, consider environmental uncertainty, and adjust the construction plan to optimize the total cost to obtain an optimized construction schedule plan.

[0032] Preferably, the optimization algorithm is the Grey Wolf Optimization Algorithm.

[0033] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0034] The present invention provides a method for adaptive scheduling of the construction progress of power infrastructure based on digital twin, including: constructing a digital twin model of construction progress according to preset historical data and construction data real-time feedback from the construction site; predicting the construction progress trend based on the digital twin model of construction progress to obtain construction progress prediction data; combining the uncertainty of human factors, construction process, and environmental conditions, and conducting construction safety assessment according to the construction progress prediction data to obtain construction safety assessment results; designing an adaptive scheduling method according to the construction safety assessment results and the construction progress prediction data to optimize the construction schedule plan; using an optimization algorithm to iteratively optimize the optimized construction schedule plan to obtain an optimal scheduling plan; applying the optimal scheduling plan to actual construction management. The present invention combines the adaptive scheduling algorithm with the digital twin model, and can achieve intelligent progress management in the construction of power infrastructure. Description of the Drawings

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings without creative efforts based on these drawings.

[0036] Figure 1 is the flowchart of the method provided by the embodiment of the present invention;

[0037] Figure 2 is the schematic diagram of the digital twin model of the construction progress provided by the embodiment of the present invention. Detailed Embodiments

[0038] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0039] The object of the present invention is to provide an adaptive scheduling method for the construction progress of power infrastructure based on digital twin, which combines an adaptive scheduling algorithm with a digital twin model and can achieve intelligent progress management in the construction of power infrastructure.

[0040] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0041] Figure 1 For the method flowchart provided in the embodiments of the present invention, as Figure 1 shown, the present invention provides an adaptive scheduling method for the construction progress of power infrastructure based on digital twin, including:

[0042] Step 100: Construct a construction progress digital twin model according to the preset historical data and the construction data real-time feedback from the construction site;

[0043] Step 200: Predict the construction progress trend based on the construction progress digital twin model to obtain construction progress prediction data;

[0044] Step 300: Combine the uncertainty of human factors, construction process, and environmental conditions, and conduct construction safety assessment according to the construction progress prediction data to obtain a construction safety assessment result;

[0045] Step 400: Design an adaptive scheduling method according to the construction safety assessment result and the construction progress prediction data to optimize the construction progress scheduling plan;

[0046] Step 500: Use an optimization algorithm to iteratively optimize the optimized construction progress scheduling plan to obtain an optimal scheduling plan;

[0047] Step 600: Apply the optimal scheduling plan to actual construction management.

[0048] The specific steps of this embodiment are as follows

[0049] I. Construct a construction progress digital twin model

[0050] The digital twin model consists of a digital model, a physical model, and a "data transmission chain" between the two. Low-latency and high-bandwidth information interaction can achieve real-time synchronization of operation data in the virtual and real spaces, thus realizing information prediction and perception and optimization of future trends. As Figure 2 shown, various types of massive data feedback in real time from the construction site are transmitted to the cloud data platform. The cloud data platform transmits it together with relevant historical data to the digital space to establish a twin model. The twin model performs real-time calculation and analysis based on its own algorithm, returns the obtained results to the cloud data platform to complete the update of the historical database, and acts on the project progress through the project person in charge.

[0051] The digital model in the virtual space is the most important part of the digital twin model. It is a true, objective, and complete mapping of the physical entity in the digital space and is the carrier of twin data. The digital model includes a 3D model, a behavior model, and a rule model, which describe and depict the physical entity in terms of time and space.

[0052] 3D model: To build the physical model of the virtual construction progress model on-site, it is necessary to first establish a 3D model of the construction site building through 3D modeling software. The constructed model should accurately reflect the construction site and include basic data of the construction object, such as area, height, structure, etc. Secondly, it is necessary to collect construction progress information, including planned start and end times, actual progress, progress deviation, and contract duration. In addition, it is also necessary to collect on-site resource information, including data on human resources and material resources, such as the number of workers, skill levels, types of materials, quantities, and usage progress.

[0053] Behavior model: Describes the real-time responses and behaviors generated by the physical entity under the combined action of different external environmental interferences and internal operating mechanisms. In the behavior model of the digital twin virtual entity of the virtual construction progress model on-site, the spatio-temporal evolution of the construction site progress is mainly obtained by analyzing the mutual influences among people, machinery, materials, methods, and the environment.

[0054] Rule model: The rule model includes regular rules based on historical associated data, experiences summarized from tacit knowledge, and relevant field standards and guidelines, etc. The rule model of the digital twin virtual entity for dynamic scheduling on the construction site refers to the rule base and knowledge base, including national standards and specifications, basic construction activity logic, construction quotas, etc.

[0055] II. Propose a safety evaluation method for the digital twin model considering uncertain risk factors

[0056] 1. Identify uncertain risk factors

[0057] The uncertain risk factors in the construction of power infrastructure are mainly divided into three categories: human factors, construction process factors, and environmental factors. Human factors include all personnel involved in construction management and actual operation, and their safety awareness and behaviors directly affect construction safety. Construction process factors include the standardization degree of construction operations and the completeness of safety systems. Environmental factors mainly involve the impacts of natural disasters, such as heavy rain and floods. To comprehensively identify the uncertain safety risks in the construction of power infrastructure, this study uses job hazard analysis and safety checklist analysis. Job hazard analysis assesses the potential risks in work activities, qualitatively identifies risks, and determines the possibility R of safety risks. Its calculation formula is:

[0058] R = f(L, S) (1)

[0059] Among them, L is the probability of an accident occurring, S is the severity of the accident consequences, and R is divided into five levels, from minor to severe. At the same time, safety checklist analysis assesses whether construction operations and the environment meet safety requirements by listing a series of inspection items and identifies existing risks.

[0060] 2. Construct an evaluation model based on grey relational analysis

[0061] To evaluate the safety risks in the construction of power infrastructure, we adopt a model based on grey relational analysis. This model can effectively quantify and compare the development and changes of construction projects, especially analyze the relationship between events and safety levels. First, establish the sequence of grey relational analysis, identify and standardize the quantitative and qualitative factors in the construction of power infrastructure. Extract the optimal factors from multiple independent variables, set them as the dependent variable, and use them as the reference factors for the safety risk assessment model. Then, the reference data of the sequence is expressed as:

[0062]

[0063] Among them, (X1, X2, …, X n ) is a sequence composed of multiple independent variables, x ij is the data point of the independent variable X i , and m is the number of factors related to safety risks. After obtaining the calculation results, the sequence is standardized. In this paper, the interval transformation method is used to calculate the absolute difference matrix between the reference sequence and each comparison sequence, in the form of:

[0064]

[0065] Among them, λ = |x0 - x i |, i = 1, 2, …, m. By comparing the correlation degrees between the comparison sequences and the reference sequence, the correlation coefficient β is obtained. The smaller the correlation coefficient, the greater the difference between the two. The correlation coefficient is used to rank the correlation degrees of each sequence.

[0066] 3. Determine evaluation indicators and adjust weights

[0067] After establishing the initial model, the key lies in defining specific evaluation indicators and adjusting weights. The evaluation indicators and weight adjustment of environmental factors in power infrastructure construction are based on past experience and relevant standards to ensure the smooth and safe execution of the project under various weather conditions. The selection of evaluation indicators for human factors and construction process factors varies according to the specific nature of daily operations. The safety evaluation method includes two types of evaluation indicators: positive indicator Q and negative indicator U. The specific formulas are as follows:

[0068]

[0069]

[0070] After calculating the positive and negative indicators, the weights of the model are adjusted. In this paper, the entropy weight method is used to assign weights. The definition of entropy weight is as follows:

[0071]

[0072] where E i is the information entropy of x i . The importance of construction operations is evaluated and weights are assigned through the entropy weight method. The smaller the entropy value of a certain indicator, the greater its coefficient of variation, which means the higher the weight of this evaluation indicator. The formula for the comprehensive score F is:

[0073]

[0074] where Q i is the positive indicator of x i , and B i is the entropy weight of x i .

[0075] 4. Shutdown mechanism

[0076] In the safety evaluation model of power infrastructure construction based on grey relational analysis, a shutdown mechanism is introduced to deal with the situation where the comprehensive score F exceeds a specific range. The shutdown mechanism means that when the score exceeds the predetermined threshold, the construction party immediately stops construction activities and takes corresponding safety measures until the safety risk is effectively controlled and the score returns to the acceptable range. The specific model is as follows:

[0077]

[0078] where z i is the construction variable. When z i = 0, it means shutdown; when z i = 1, it means normal construction. F is the lower limit value of the comprehensive score.

[0079] Due to the changes of various risk factors, the uncertainty of the construction plan is further increased. To formulate the best dynamic construction schedule and dispatching strategy, this paper constructs a distributionally robust fuzzy set based on moment information and Wasserstein information.

[0080]

[0081] where \(P\) and \(\hat{P}\) E are the true distribution and the empirical distribution of the construction variables. is the upper bound of the probability of work stoppage. \(\Gamma\) is the set of probability distributions of the true probability distribution. \(\rho\) is the Wasserstein radius, representing the distance between \(P\) and \(\hat{P}\). E For the convenience of solving, the Wasserstein metric is re-expressed as:

[0082]

[0083] III. Adaptive Scheduling Model Considering Uncertain Risks and Its Solving Method

[0084] 1. Mathematical Model for Dynamic Control of Construction Progress

[0085] ① Objective Function

[0086] The dynamic control of construction progress is an accurate reflection of the construction period, cost, quality and environment. And the environmental factors in construction projects have a significant impact on the progress, cost and quality, which is an important part that cannot be ignored in uncertainty management. Harsh environments such as heavy rain, heavy snow and extreme temperatures can not only directly interrupt construction activities, but also may lead to equipment damage, material loss and construction quality decline. To consider the uncertainty of environmental factors in the dynamic control of construction progress, this paper proposes a construction plan adjustment method based on two-stage robust optimization of fuzzy sets. In the first stage, with the shortest construction period as the objective function, the initial construction plan variables including construction task allocation and resource allocation are determined. In the second stage, considering the uncertainty of environmental factors, with the minimum total construction cost as the objective, the plan adjustment variables including the amount of construction task adjustment and resource adjustment are determined. The two-stage objective functions are as follows:

[0087]

[0088] where \(\Phi / \Theta\) are the decision variable sets in the first stage / second stage respectively; \(T\) is the construction period; \(K\) is the set of types of resources required for construction, including material resources and human resources; is the unit cost of resource \(k\); is the usage amount of resource \(k\) on the \(t\)-th day of the construction plan; \(z\) t is the construction indication variable. When \(z\) t = 1, the construction proceeds normally. When \(z\) tWhen it is equal to 0, stop the construction. It is the unit adjustment cost of resource k; It represents the amount of usage adjustment for resource k on the t-th day due to environmental impacts. Environmental factors may lead to unreasonable resource allocation in the first stage. For example, bad weather may interrupt construction activities, resulting in the idleness of originally planned resources. To complete the construction period on time, it is necessary to speed up the progress in the subsequent stages, and additional resource adjustments and temporary allocations may be required to make up for the deficiencies in the original plan; f(T) / f(E) is the penalty-reward function of the construction period / quality. pc1 / bc1 is the penalty / reward factor for construction period delay / advance; T cd is the contract construction period. pc2 / bc2 is the penalty / reward factor for quality compliance / failure; E cd is the contract quality.

[0089] ② Constraint conditions

[0090] 1) Resource constraints

[0091] During the construction period, the actual amount of resources used on the current day is composed of the planned resource amount determined in the first stage plus the resource adjustment amount. Assuming there is no resource waste during the construction period, that is, the actual total usage of resources should be the same as the rated total usage. The specific expression is:

[0092]

[0093] Among them, is the planned resource amount; R cd is the rated total usage of resources.

[0094] During the construction cycle, the actual daily usage of resources, the planned resource usage, and the resource adjustment usage should all be within a reasonable range. The specific expression is:

[0095]

[0096] Among them, are the lower limit values of the actual daily usage of resources / planned resource usage / resource adjustment usage respectively. are the upper limit values of the actual daily usage of resources / planned resource usage / resource adjustment usage respectively.

[0097] 2) Quality constraints

[0098] It is difficult to quantitatively describe the quality in construction. This article believes that neither too short nor too long construction period can optimize the quality. When the actual construction period is the same as the contract construction period, the construction quality is optimal. The relationship between the construction period and the construction quality satisfies the bell-shaped function. The specific constraints are as follows:

[0099] A i = 2a·ri -a, C i = 2·r i ' (16)

[0100] Among them, / T is the upper / lower limit of the construction period; b (b > 0) reflects the width and flatness of the bell-shaped function.

[0101] 3) Environmental constraints

[0102] When the risk score exceeds the threshold, the construction party should immediately stop construction activities. The uncertainty risk constraint is given by formula (8 - 10).

[0103] 2. Apply the Grey Wolf Optimization Algorithm for Construction Schedule Optimization

[0104] ① Initialize the population

[0105] Set the population size, the maximum number of iterations, and the upper and lower bounds of the search space.

[0106]

[0107] Randomly initialize the position of each grey wolf, representing a potential construction schedule plan.

[0108]

[0109] ② Calculate the fitness value

[0110] Calculate the fitness value for the position of each grey wolf (construction schedule plan). The fitness value can be determined based on indicators such as construction cost, construction period, and resource utilization efficiency. Select the three grey wolves with the highest fitness values as Alpha, Beta, and Delta wolves, representing the current optimal, sub-optimal, and third-optimal construction schedule plans.

[0111]

[0112] ③ Update the position

[0113] According to the position information of Alpha, Beta, and Delta wolves, and the current positions of other grey wolves, update the position of each grey wolf. Use the position update formula in the GWO algorithm to simulate the hunting behavior of grey wolves and guide the grey wolves to gradually approach the optimal solution.

[0114]

[0115] ④ Parameter update

[0116] As the number of iterations increases, gradually reduce the control parameter The value is used to simulate the behavior of grey wolves gradually approaching their prey during hunting. Update the search coefficients A and C to control the balance between global search and local search during the search process.

[0117]

[0118] Among them, is the convergence parameter that controls the search behavior of grey wolves, t is the current iteration number, and T is the maximum iteration number.

[0119] ⑤ Iterative optimization

[0120] Repeat the steps of calculating the fitness value and updating the position until the maximum iteration number or other termination conditions are reached.

[0121] ⑥ Output the optimal solution

[0122] Output the position of the Alpha wolf as the optimal construction schedule.

[0123] X * = X α (26)

[0124] Among them, X * is the found optimal solution, that is, the current position of the Alpha wolf.

[0125] ]>By introducing the GWO algorithm, the intelligence and adaptability of construction schedule can be further improved, enabling the schedule to better cope with the uncertain factors during the construction process. This method can optimize resource allocation, reduce construction delays, improve construction efficiency, and ensure construction quality.

[0126] This embodiment proposes an adaptive scheduling method for the construction progress of power infrastructure based on digital twin, which combines the adaptive scheduling algorithm with the digital twin model to achieve intelligent progress management in power infrastructure construction. First, considering the progress information of power infrastructure construction, a digital twin model reflecting the construction progress is established. Subsequently, a safety assessment method for power infrastructure is developed by combining the uncertainties of human factors, construction processes, and environmental conditions. Then, an adaptive scheduling method that can incorporate the uncertainty of suspension risks is designed. This embodiment provides a virtual model that is highly consistent with the actual construction progress, making monitoring and prediction more accurate; ensuring the synchronization of the digital twin model with the actual situation on site, improving the real-time performance and response speed of construction management; the resource optimization in the first stage and the environmental adaptability adjustment in the second stage improve the flexibility and reliability of the construction plan.

[0127] The beneficial effects of the present invention are as follows:

[0128] (1) The present invention improves the accuracy of construction management. Through real-time data synchronization and the precise construction of a digital twin model, the monitoring and prediction of the construction progress are more accurate.

[0129] (1) The present invention enhances the adaptability of the construction plan. The two-stage robust optimization method enables the construction plan to adapt to environmental changes and uncertainties, reducing the risks of construction delays and cost overruns.

[0130] (3) The present invention improves the resource utilization efficiency. The optimization algorithm effectively allocates resources, reduces resource waste, and improves the construction efficiency.

[0131] In this specification, the various embodiments are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the various embodiments, reference can be made to each other.

[0132] Specific examples are used in this article to elaborate on the principles and implementation methods of the present invention. The descriptions of the above embodiments are only used to help understand the method and its core idea of the present invention. At the same time, for those of ordinary skill in the art, based on the idea of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be construed as a limitation on the present invention.

Claims

1. An adaptive scheduling method for the construction progress of power infrastructure based on digital twin, characterized in that, Including: Construct a construction progress digital twin model based on preset historical data and construction data real-time feedback from the construction site; Predict the construction progress trend based on the construction progress digital twin model to obtain construction progress prediction data; Combining the uncertainties of human factors, construction processes, and environmental conditions, conduct construction safety assessment based on the construction progress prediction data to obtain construction safety assessment results; Design an adaptive scheduling method based on the construction safety assessment results and the construction progress prediction data to optimize the construction progress scheduling plan; Use an optimization algorithm to iteratively optimize the optimized construction progress scheduling plan to obtain the optimal scheduling plan; Apply the optimal scheduling plan to actual construction management.

2. The method for adaptively scheduling the construction progress of power infrastructure based on digital twin according to claim 1, wherein, The construction progress digital twin model includes: a 3D model, a behavior model, and a rule model.

3. The method for adaptively scheduling the construction progress of power infrastructure based on digital twin according to claim 1, characterized in that, Predict the construction progress trend based on the construction progress digital twin model to obtain construction progress prediction data, including: Based on the construction progress digital twin model, achieve real-time synchronization of the construction data with the virtual space through low-latency and high-bandwidth information interaction; Conduct real-time calculation and analysis through the construction progress digital twin model, and feedback the calculation and analysis results to the cloud data platform and update the historical data.

4. The adaptive scheduling method for the construction progress of power infrastructure based on digital twin according to claim 1, wherein, Combining the uncertainties of human factors, construction processes, and environmental conditions, conduct construction safety assessment based on the construction progress prediction data to obtain construction safety assessment results, including: Based on the actual situation of the construction site, collect data related to human factors, construction process factors, and environmental factors; Based on the job hazard analysis method and safety checklist analysis method, identify the uncertainty risk factors in the construction process according to the data related to human factors, construction process factors, and environmental factors to obtain a list of uncertainty risk factors; According to the list of uncertainty risk factors, use the grey relational analysis method to quantify the impact of each risk factor on the safety level in the construction project to construct an initial safety assessment model; Define evaluation indicators according to the evaluation results of the initial safety assessment model, and use the entropy weight method to adjust the weights of each evaluation indicator to form a comprehensive safety assessment model; Introduce a shutdown mechanism into the comprehensive safety assessment model, and conduct construction safety assessment on the construction progress prediction data according to the comprehensive safety assessment model to obtain the construction safety assessment results.

5. The method for adaptively scheduling the construction progress of power infrastructure based on digital twin according to claim 4, wherein The calculation formula of the job hazard analysis method is: R = f(L,S); where R is the possibility of safety risk, L is the probability of an accident occurring, S is the severity of the accident consequences, and R is divided into multiple levels.

6. The method for self-adaptive scheduling of the construction progress of power infrastructure based on digital twin according to claim 4, wherein The evaluation indicators include a positive indicator Q and a negative indicator U; the calculation formula for the positive indicator Q is: The calculation formula for the negative indicator U is: where x i is the sequence of indicator observation values, and x m is the measured value of the evaluation indicator.

7. The method for adaptively scheduling the construction progress of power infrastructure based on digital twin according to claim 6, characterized in that, The calculation formula of the entropy weight method is as follows: where B is the entropy weight and E i is the information entropy of x i .

8. The method for adaptively scheduling the construction progress of power infrastructure based on digital twin according to claim 7, characterized in that The expression of the shutdown mechanism is as follows: where z i is a construction variable. When z i = 0, it indicates shutdown; when z i = 1, it indicates normal construction; F is the lower limit value of the comprehensive score F, and the calculation formula of the comprehensive score F is: where Q i is a positive index of x i , B i is the entropy weight of x i , and n is the sum of the number of indicators.

9. The method for adaptively scheduling the construction progress of power infrastructure based on digital twin according to claim 1, wherein Design an adaptive scheduling method based on the construction safety assessment results and the construction progress prediction data to optimize the construction progress scheduling plan, including: Taking the shortest construction period as the goal, make decisions on the initial construction plan variables, and considering the uncertainty of environmental factors, take the minimum total construction cost as the goal to make decisions on the plan adjustment variables to obtain the objective functions of the two stages; the initial construction plan variables include construction task allocation and resource allocation; the plan adjustment variables include construction task adjustment amount and resource adjustment amount; the expression of the objective function is: Among them, Φ / Θ are the decision variable sets of the first stage / second stage respectively; T is the construction period; K is the set of types of resources required for construction, including material resources and human resources; is the unit cost of resource k; r t o,k is the usage amount of resource k on the t-th day of the construction plan; z t is a construction indication variable. When z t =1, the construction proceeds normally; when z t =0, the construction stops; is the unit adjustment cost of resource k; represents the usage adjustment amount of resource k on the t-th day due to environmental impact; f(T) and f(E) are the penalty-reward functions of the construction period and quality respectively; pc1 and bc1 are the penalty-reward factors for construction period delay and construction period advance respectively; T cd is the contract construction period; pc2 and bc2 are the penalty-reward factors for quality compliance and non-compliance respectively; E cd is the contract quality; Construct constraint conditions; the constraint conditions include: resource constraints, quality constraints, and environmental constraints; Based on the two-stage objective function and the constraint conditions, optimize the construction tasks and resource allocation based on deterministic conditions to generate an initial construction plan, consider environmental uncertainties, and adjust the construction plan to optimize the total cost to obtain an optimized construction progress scheduling plan.

10. The method for adaptively scheduling the construction progress of power infrastructure based on digital twin according to claim 1, wherein, The optimization algorithm is the grey wolf optimization algorithm.

Images