Vertical transportation efficient scheduling method in super high-rise building construction

Abstract

The invention relates to the technical field of building construction, and discloses a vertical transportation efficient scheduling method in super high-rise building construction. The method comprises the following steps: S1, defining a system state space, and combining states of real-time data acquisition equipment into the state space of the system; s2, establishing a Markov decision process (MDP) model, and selecting an optimal equipment task allocation scheme by collecting the working state and task requirements of equipment in real time; and S3, setting a plurality of objective functions by using a nonlinear optimization algorithm. The Markov decision process model is adopted to optimize equipment scheduling, and the technical effect of intelligently selecting the optimal task allocation scheme according to the real-time state of the equipment and task requirements is achieved. Compared with a traditional fixed scheduling method in the prior art, the MDP model can flexibly cope with the complex and changeable working environment on site, the equipment utilization rate is remarkably improved, and the effect of low efficiency caused by task conflicts or resource idleness is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of building construction, and in particular to a method for efficiently dispatching vertical transportation in super high-rise building construction. Background Art

[0002] Vertical transportation is a critical component of today's super-high-rise construction. As building floors increase, equipment scheduling and material transportation become increasingly complex. Traditional scheduling methods often rely on manual experience or fixed schedules, which lack flexibility and adaptability in the face of real-time changes on the construction site.

[0003] Traditional scheduling methods don't fully utilize real-time equipment status information. While some systems record equipment status and task progress, this information is often not effectively integrated and utilized for decision-making, resulting in excessive equipment idle time and even inability to optimize task wait times. Previous scheduling systems simply allocated tasks based on chronological order, making it difficult to dynamically adjust based on actual equipment status, task priority, and urgency, which undoubtedly increased construction time.

[0004] Existing vertical transportation scheduling technologies are mostly static and lack real-time adjustment and adaptability. Equipment failures, task changes, and changes in the construction environment are common during the construction process. Traditional systems are unable to effectively adapt to these changes, resulting in a significant decrease in equipment resource scheduling efficiency in the event of an emergency. For example, when a piece of equipment fails, the system fails to promptly reallocate tasks, causing delays in the overall construction schedule.

[0005] Most existing technologies focus on a single optimization objective, such as minimizing transportation time or equipment idle time, but often ignore the balancing of multiple objectives. On the construction site, it is often necessary to balance multiple objectives, including equipment load, task priority, equipment idle time, etc. The lack of consideration for multi-objective optimization leads to the neglect of certain important factors in the optimization process, which affects the overall scheduling effect and construction efficiency. Existing technologies generally use a single optimization algorithm or rule for equipment scheduling, which is difficult to cope with the dynamic changes of complex construction sites. Traditional algorithms are relatively simple and lack flexibility. They cannot be adjusted in the face of real-time feedback and environmental changes. Especially in the construction of super-high-rise buildings with diverse equipment and complex task types, traditional methods seem to be unable to cope with the situation. Summary of the Invention

[0006] In response to the shortcomings of the existing technology, the present invention provides an efficient scheduling method for vertical transportation in super high-rise building construction, which solves the problems of low scheduling efficiency of vertical transportation equipment, long task waiting time, high equipment idle time and inability to adapt to changes in the construction site in real time in super high-rise building construction.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for efficiently scheduling vertical transportation in super high-rise building construction, comprising the following steps:

[0008] S1. Define the system state space, and combine the state of the real-time data acquisition device into the system state space;

[0009] S2. Establish a Markov decision process (MDP) model to select the optimal equipment task allocation plan by collecting the working status and task requirements of the equipment in real time;

[0010] S3. Use nonlinear optimization algorithms to perform multi-objective optimization by setting multiple objective functions to minimize total transportation time, equipment idle time, and task waiting time;

[0011] S4. Apply the adaptive genetic algorithm (AGA) to dynamically adjust the scheduling strategy based on real-time feedback of environmental changes during the construction process;

[0012] S5. Adjust equipment scheduling in real time based on the optimization plan and make dynamic adjustments according to changes in the construction site.

[0013] Preferably, the MDP model in step S2 solves the optimal equipment scheduling strategy by maximizing the cumulative reward of the equipment scheduling decision, and the reward function is determined by calculating the idle time, total transportation time and task waiting time of the equipment.

[0014] Preferably, in step S1, the working status, load condition and task completion status of the equipment are obtained through sensors and positioning systems, and transmitted to the scheduling platform for processing through Internet of Things technology.

[0015] Preferably, the objective function of the optimization algorithm in step S3 includes:

[0016] Minimize total shipping time;

[0017] Minimize device idle time;

[0018] Minimize task waiting time; the objective function is formed by weighted summation, and the weight coefficient is dynamically set according to the priority requirements of the construction site.

[0019] Preferably, the multi-objective optimization in step S3 includes constraints, and the constraints include:

[0020] The load on the equipment does not exceed its maximum working load;

[0021] The task must be completed within the scheduled time;

[0022] The task allocation of equipment must meet the construction progress and task priority requirements.

[0023] Preferably, the adaptive genetic algorithm in step S4 adjusts the selection of genetic operators, crossover probability and mutation rate according to real-time feedback data to adapt to dynamic changes in the construction site, such as equipment failure or changes in task requirements.

[0024] Preferably, the scheduling platform can execute the Markov decision process and optimization algorithm in real time, generate the optimal scheduling plan and feed it back to the equipment control system or operator to ensure coordinated operation of equipment during the construction process.

[0025] Preferably, the equipment task allocation ensures that high-priority tasks are allocated to equipment first and reduces task waiting time by matching task priorities with construction progress.

[0026] Preferably, the weighted sum of the objective function optimization in step S3 is calculated by the following formula:

[0027] minf(x)=α1·T total (x)+α2·T idle (x)+α3·T waiting (x)

[0028] in;

[0029] T total (x) is the total transportation time;

[0030] T idle (x) is the device idle time;

[0031] T waiting (x) is the task waiting time, and α1, α2, α3 are predetermined weighting coefficients.

[0032] Preferably, the scheduling optimization is ensured to operate efficiently in actual construction through real-time simulation and verification, and the optimization algorithm is further adjusted according to the simulation data to improve the response speed and robustness of the system.

[0033] The present invention provides an efficient scheduling method for vertical transportation during super high-rise building construction. It has the following beneficial effects:

[0034] 1. This invention optimizes equipment scheduling by employing a Markov decision process model, intelligently selecting the optimal task allocation scheme based on the real-time status of equipment and task requirements. Compared to traditional fixed scheduling methods in the prior art, the MDP model can flexibly adapt to complex and changing on-site working environments, significantly improving equipment utilization and avoiding inefficiencies caused by task conflicts or idle resources.

[0035] 2. By introducing a nonlinear optimization algorithm, this invention achieves multi-objective optimization, simultaneously minimizing total transport time, equipment idle time, and task waiting time. Compared to traditional single-objective optimization, this optimization approach overcomes the problem of neglecting the balance of multiple factors in actual construction, effectively reducing construction time and costs, and improving the accuracy of scheduling decisions.

[0036] 3. This invention uses an adaptive genetic algorithm (AGA) to dynamically adjust scheduling strategies. This allows scheduling plans to promptly adapt to unexpected situations, such as equipment failures or changes in task requirements, particularly with real-time feedback during construction. Compared to existing technologies, traditional methods are unable to adapt to environmental changes, making the system inflexible. The AGA algorithm significantly improves the system's responsiveness and adaptability, ensuring coordinated equipment operation.

[0037] 4. Through real-time data collection and an optimized feedback mechanism, this invention continuously adjusts equipment scheduling plans to ensure that each task is completed within the scheduled time. Compared to the static scheduling strategies used in existing technologies, this invention's dynamic adjustment capability significantly improves scheduling flexibility and accuracy, avoiding task delays and equipment idleness caused by untimely plan adjustments. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 Flow chart of the method of the present invention. DETAILED DESCRIPTION

[0039] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the present specification. 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 making creative efforts are within the scope of protection of the present invention.

[0040] Please see the attached Figure 1 , an embodiment of the present invention provides an efficient scheduling method for vertical transportation in super high-rise building construction, comprising the following steps;

[0041] S1. Define the system state space, and combine the state of the real-time data acquisition device into the system state space;

[0042] Specifically, this embodiment establishes this state space through real-time data collection of equipment status. In vertical transportation scheduling, equipment status is a key factor influencing scheduling decisions. Equipment operating status, load, and task completion are all directly related to equipment availability. Therefore, establishing an accurate system state space is fundamental to achieving efficient scheduling.

[0043] Used to describe the operating status of equipment at different points in time. By collecting real-time data, combining equipment status with task requirements, this information is combined into the system's state space, which serves as the basis for subsequent decision-making. Equipment status includes "idle" or "busy," as well as specific task progress, task priority, and load information.

[0044] The system state space is a dynamic space, constantly updated with construction progress and equipment performance. Equipment status is adjusted to "idle" or "busy" based on real-time feedback. This dynamic change helps the scheduling system make accurate decisions based on the actual equipment conditions.

[0045] The state space includes the state of each device and the assigned state of each task. The state of a device is determined by whether it is idle or busy. The state of a task is represented by the progress of the task. The system state space can be expressed as follows:

[0046] S t ={(s1,s2,…,s n )}

[0047] in;

[0048] S t represents the system state space at time t;

[0049] s i Indicates the status of device i;

[0050] s i ∈{idle, busy} represents the state of device i at time t. The device state changes over time and is updated through real-time data.

[0051] Specifically, this embodiment takes into account the specific type of device task, its priority, and other external environmental factors. For example, a high-priority task may force an idle device to occupy it, even if that device has other tasks to execute. This information needs to be updated in real time in the system state space to ensure the accuracy of scheduling decisions.

[0052] S2. Establish a Markov decision process (MDP) model to select the optimal equipment task allocation plan by collecting the working status and task requirements of the equipment in real time;

[0053] Specifically, in this embodiment, after defining the system state space and collecting real-time data, step S2 utilizes a Markov decision process (MDP) model to make equipment scheduling decisions, selecting the optimal scheduling strategy based on the equipment's current operating status and task requirements. This model maximizes equipment efficiency, reduces task wait times, and optimizes the overall performance of the vertical transportation process.

[0054] In this example, the MDP model is used to determine the optimal task allocation plan at each moment based on the equipment status and task requirements. By evaluating equipment idle time, task urgency, and transportation progress factors during the decision cycle, the MDP effectively guides equipment scheduling, thereby maximizing overall system efficiency. By defining a reasonable reward function, the system can evaluate the benefits of each scheduling action and select the optimal decision.

[0055] A Markov decision process (MDP) is an optimization method based on a state-action decision process. An MDP consists of the following elements.

[0056] State space S t ; represents the state of the system at time t. Specifically, the state space includes the working states of all devices and the combination of task requirements

[0057] Action space A t : At time t, the set of actions that the system can choose, that is, the task allocation decision.

[0058] Transition probability P(s t ,a t ,s t+1 ); in the current state S t Next, select action a t After that, the system transfers to the next state s t+1 The transition probability reflects the changes in equipment status and task allocation.

[0059] Reward function R(s t ,a t ) measures the immediate reward obtained after executing a scheduling action. In this embodiment, the reward function is primarily defined based on factors such as device idle time, total transport time, and task waiting time, with the goal of maximizing overall system efficiency.

[0060] Value function V(s t ); indicates that from state s t The expected cumulative reward after executing the optimal strategy is the value function. The value function is usually solved by dynamic programming.

[0061] In this embodiment, the goal of the MDP model is to achieve optimal scheduling of devices based on the working status and task requirements of the devices. Specifically, in step S2, the system implements the following process:

[0062] First, the system is based on the state s at the current time t t , i.e. the working status of the equipment and the task requirements, evaluate each possible action a t Action a tThis corresponds to a task allocation plan for a certain device, for example, assigning Task 1 to Device A and Task 2 to Device B. By evaluating the immediate reward brought by each action, the system selects the action that brings the greatest reward to execute.

[0063] Reward function R(s t ,a t ) design includes the following factors;

[0064] Equipment Idle Time: If the equipment is idle, the system will reduce the reward value. Equipment idle time is an important factor affecting equipment utilization. Excessive idle time will lead to low system efficiency.

[0065] Total transport time: The longer the total transport time, the less efficient the system. When tasks are dispatched promptly and completed quickly, the total transport time decreases, leading to higher rewards.

[0066] Task waiting time: Task waiting time refers to the time from the time a task arrives to the time the device begins executing it. The shorter the task waiting time, the better the system's scheduling performance and the higher the reward.

[0067] Therefore, the reward function can be expressed as;

[0068] R(s t ,a t )=-α1·T idle -α2·T total -α3·T waiting

[0069] in:

[0070] T idle The device idle time;

[0071] T total is the total transport time;

[0072] T waiting Waiting time for the task;

[0073] α1, α2, and α3 are weighting coefficients used to balance the importance of different objectives.

[0074] The weight coefficients α1, α2, and α3 can be adjusted dynamically according to the needs of the construction site. For example, when materials are urgently transported, the system can increase T total The weight of the reward is used to give priority to task allocation plans that can speed up transportation.

[0075] Solving the optimal strategy of the MDP model;

[0076] The system solves the MDP model and obtains the current state s tInitially, the optimal device task allocation strategy. Specifically, the system uses the numerical function V(s t ) to evaluate possible scheduling actions. The value function represents the value of the state s. t At the beginning, the expected cumulative reward after executing according to the optimal strategy. The goal of the system is to maximize the value function;

[0077] To achieve this goal, the following algorithms are usually used;

[0078] Value iteration method: This method recursively calculates the optimal value function for each state until convergence.

[0079] The specific formula is;

[0080]

[0081] V(s t ) represents the state s at time t t The value function measures the value of the state s. t Initially, the expected cumulative reward after executing the optimal strategy;

[0082] a t Represents the action at time t, which determines the system's transition from the current state s t Transition to the next state s t +1;

[0083] R(s t ,a t ) in state s t Next, take action a t Immediate rewards after

[0084] P(s t ,a t ,s t+1 ) is the transition probability, indicating that from state s t Through action a t Transfer to state s t+1 probability;

[0085] γ is a discount factor that controls the weight of current rewards and future rewards and is usually used to balance short-term and long-term goals;

[0086] s t+1 The state at the next moment t+1;

[0087] Policy iteration first calculates a value function based on the current policy, and then updates the policy based on the value function. Policy iteration can usually converge to the optimal policy quickly.

[0088] Specifically, in this embodiment, step S2 utilizes a Markov Decision Process (MDP) model to make equipment scheduling decisions. The system collects real-time data on equipment status and task requirements and utilizes the reward function within the MDP model to maximize overall system efficiency. By selecting the optimal task allocation plan, the system can effectively reduce equipment idle time, shorten total transport time, and shorten task wait times, thereby improving vertical transport efficiency.

[0089] S3. Use nonlinear optimization algorithms to perform multi-objective optimization by setting multiple objective functions to minimize total transportation time, equipment idle time, and task waiting time;

[0090] Specifically, in this embodiment, the basic framework design of equipment scheduling is completed through real-time data collection and Markov decision process (MDP) model, and the task allocation plan under the current state of the equipment is obtained. Step S3 further optimizes these task allocation plans through a nonlinear optimization algorithm. By considering multiple optimization objectives, the overall construction efficiency is improved, the equipment utilization rate is maximized, the task waiting time is reduced, and the transportation time and equipment idle time are controlled.

[0091] In this embodiment, the optimization objective function includes the following key factors:

[0092] Total transport time: This refers to the time required from the start of a task to its completion. Optimization of this objective aims to shorten the transport time of equipment as much as possible, avoiding unnecessary delays and thus improving the construction schedule.

[0093] Equipment Idle Time: When equipment is idle, even though it is not involved in any task, it still consumes maintenance and energy costs. Therefore, reducing equipment idle time helps improve the overall efficiency of equipment use.

[0094] Task waiting time: refers to the time a task waits for equipment execution. Longer task waiting time will lead to delays in construction progress. Therefore, reducing task waiting time is an important goal in scheduling optimization.

[0095] To balance the relationships between different objectives, the system prioritizes them by setting weight coefficients α1, α2, and α3. Specifically, the system dynamically adjusts these weight coefficients based on the actual needs of the construction site. For example, if urgent tasks are prioritized, the system might increase the weight of total transport time and decrease the weight of task waiting time, thereby prioritizing urgent tasks.

[0096] The weighted sum of the optimization objective function can be expressed as the following formula;

[0097] f(x)=α1·T total (x)+α2·T idle (x)+α3·T waiting(x)

[0098] in;

[0099] f(x) is the comprehensive optimization objective function;

[0100] T total (x) is the total transportation time;

[0101] T idle (x) is the device idle time;

[0102] T waiting (x) is the task waiting time;

[0103] α1, α2, α3 are the weighting coefficients of each target.

[0104] During the optimization process, this embodiment uses a nonlinear optimization algorithm to solve the problem. The goal of the optimization algorithm is to minimize the above-mentioned comprehensive objective function f(x) and optimize the equipment scheduling by adjusting the equipment task allocation plan.

[0105] Use nonlinear optimization methods to minimize the objective function by calculating the gradient information of the objective function near the current solution, gradually adjust the task allocation plan, and finally obtain the optimal solution.

[0106] The gradient descent method is optimized through the following iterative formula;

[0107]

[0108] in;

[0109] x k is the current solution (i.e., task allocation plan);

[0110] α is the step size, which controls the update amplitude of each iteration;

[0111] is the objective function f(x) at the current solution x k The gradient at .

[0112] By gradually updating the allocation plan of equipment tasks and finding the minimum value of the objective function, the optimal equipment scheduling plan is obtained.

[0113] In addition to optimizing the objective function, the system also needs to consider some constraints. These constraints ensure the feasibility of the scheduling plan and prevent the system from generating unrealistic scheduling plans.

[0114] In this embodiment, the constraints of the optimization algorithm include:

[0115] Equipment load limit: The load of each device cannot exceed its maximum workload L max ,Right now:

[0116]

[0117] Among them, L i (x) is the load of device i under task allocation scheme x, L max is the maximum load of device i.

[0118] Equipment task allocation sequence: Equipment task allocation must meet the construction progress and task priority requirements, give priority to urgent tasks, and ensure that high-priority tasks are processed immediately when the equipment is idle.

[0119] Specifically, in this embodiment, step S3 performs multi-objective optimization on equipment scheduling by applying a nonlinear optimization algorithm. The system combines multiple optimization objectives, such as total transportation time, equipment idle time, and task waiting time, through weighted summation to obtain an optimization objective function. The optimization algorithm solves the optimal equipment task allocation plan by minimizing this objective function. During this process, the system also considers constraints such as equipment load limit and task completion time limit to ensure the feasibility of the scheduling plan. Through the nonlinear optimization algorithm, the system can provide efficient and feasible equipment scheduling plans in a dynamic construction environment, significantly improving construction efficiency.

[0120] S4. Apply the adaptive genetic algorithm (AGA) to dynamically adjust the scheduling strategy based on real-time feedback of environmental changes during the construction process;

[0121] Specifically, in this embodiment, the module of the system pre-processing is organically connected with the specific implementation of this step, and it is ensured that the details in the technical implementation can be clearly reflected.

[0122] First, during the processing of the aforementioned modules, the system preprocesses the input data and selects functions. According to the requirements of step S4, the system will further optimize the processing results and adjust key parameters to ensure that the following operation steps can proceed smoothly. For step S4, first, the transmission and processing flow of the data flow; second, the application of the optimization algorithm; and finally, the precise control of parameter adjustment.

[0123] In this embodiment, step S4 further improves the system's computational accuracy by performing multi-level processing on the input signal. Specifically, the system employs an optimization algorithm-based adjustment method. By introducing this optimization algorithm, the system's response speed and processing capabilities to input signals can be significantly improved. The system dynamically adjusts key parameters by performing gradient descent optimization on the objective function to ensure that the system can complete task processing in a relatively short period of time.

[0124] The key algorithm involved in step S4 is based on a convolutional neural network (CNN), which optimizes the processing effect by gradually extracting feature information. In particular, in terms of parameter definition, each parameter in the formula has a clear definition. Let the input signal be X, and the objective function of the system optimization be F(X,θ), where θ represents the adjustable parameter in the optimization process. The optimization process is achieved by minimizing the objective function F(X,θ), as shown below:

[0125]

[0126] in;

[0127] θ opt Represents the optimal parameter value after optimization;

[0128] F(X,θ) is the objective function;

[0129] By adjusting θ, the system can achieve the optimal processing result. In this optimization process, gradient descent is widely used to minimize the error and improve the response speed of the system.

[0130] During implementation, after the input signal undergoes multiple transmissions and processing, the system dynamically adjusts its parameters based on the optimization results, ensuring that each operation achieves the desired effect. Parameter adjustment involves not only processing the input data but also real-time adjustments to the algorithm during operation. Through this multi-level optimization process, the system continuously improves its processing capabilities and adapts to changes in input data.

[0131] Specifically, the implementation of step S4 in this embodiment, through optimization algorithms and dynamic parameter adjustment, not only ensures a close connection between the front and back modules, but also further improves the stability and reliability of the system. The detailed definition of each parameter and the disclosure of the technical solution ensure the operability and technical integrity of the present invention.

[0132] S5. Adjust equipment scheduling in real time based on the optimization plan and make dynamic adjustments according to changes in the construction site.

[0133] Specifically, in this embodiment, through the aforementioned steps, the system has completed data optimization processing and parameter adjustment, ensuring the stability and accuracy of each module during operation. In step S5, the system's main goal is to further process the data output and make appropriate adjustments based on the feedback from the previous steps to ensure the accurate execution of subsequent tasks.

[0134] In this embodiment, the data output and feedback adjustment process involved in step S5 is primarily executed through a specific decision-making mechanism. Specifically, the system evaluates and further adjusts the data processed in the previous steps. The system uses discriminant logic to analyze the data output and revise the results. This process is crucial to ensuring the efficiency of the final processing results.

[0135] Specifically, in step S5, the system first evaluates the adjusted parameters and data to determine whether they meet the preset standards. If the data meets the standards, execution can continue; if the data does not meet the standards, it needs to be corrected through the adjustment mechanism and the optimization algorithm is re-executed until the system output meets the requirements. The system can incorporate a multi-stage feedback mechanism so that the output of each step is checked and adjusted in real time to ensure data accuracy and availability.

[0136] In this embodiment, the system adjusts the output result by introducing an adaptive algorithm. The basic idea of the adaptive algorithm is to obtain feedback signals in real time during the operation of the system, and then dynamically adjust the various parameters in the processing process according to the feedback signals. Let the processing result be Y and the judgment standard be θ target , then when Y and θ target When the deviation is large, the system will adjust according to the adaptive rules. The adjustment formula is as follows:

[0137] θ new =θ old +α·(Y-θ target )

[0138] in;

[0139] θ new is the adjusted parameter value;

[0140] θ old is the previous parameter value;

[0141] α is the adjustment step size;

[0142] Y is the current processing result;

[0143] θ target As the target standard.

[0144] When the output result Y and the target standard θ target When there is a large gap between the two, the system will adjust the parameters according to a certain ratio α. Through this adjustment, the system can gradually approach the optimal result after each feedback.

[0145] Specifically, the implementation of step S5 further optimizes the system's decision-making behavior through feedback control and adaptive mechanisms. By introducing optimization algorithms and reinforcement learning techniques, the system can continuously improve its performance and adapt to various input signals.

[0146] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An efficient scheduling method for vertical transportation in super high-rise building construction, characterized by: The following steps are included: S1. Define the system state space, and combine the state of the real-time data acquisition device into the system state space; S2. Establish a Markov decision process (MDP) model to select the optimal equipment task allocation plan by collecting the working status and task requirements of the equipment in real time; S3. Use nonlinear optimization algorithms to perform multi-objective optimization by setting multiple objective functions to minimize total transportation time, equipment idle time, and task waiting time; S4. Apply the adaptive genetic algorithm (AGA) to dynamically adjust the scheduling strategy based on real-time feedback of environmental changes during the construction process; S5. Adjust equipment scheduling in real time based on the optimization plan and make dynamic adjustments according to changes in the construction site.

2. The method for efficient scheduling of vertical transportation in super high-rise building construction according to claim 1 is characterized in that: In step S2, the MDP model solves the optimal equipment scheduling strategy by maximizing the cumulative reward of the equipment scheduling decision, and the reward function is determined by calculating the equipment's idle time, total transportation time, and task waiting time.

3. The efficient scheduling method for vertical transportation in super high-rise building construction according to claim 1 is characterized in that: In step S1, the working status, load condition and task completion status of the equipment are obtained through sensors and positioning systems, and transmitted to the scheduling platform for processing through the Internet of Things technology.

4. The method for efficient scheduling of vertical transportation in super high-rise building construction according to claim 1 is characterized in that: The objective function of the optimization algorithm in step S3 includes: Minimize total shipping time; Minimize device idle time; Minimize task waiting time; The objective function is formed by weighted summation, and the weight coefficient is dynamically set according to the priority requirements of the construction site.

5. The efficient scheduling method for vertical transportation in super high-rise building construction according to claim 1 is characterized in that: The multi-objective optimization in step S3 includes constraints, which include: The load on the equipment does not exceed its maximum working load; The task must be completed within the scheduled time; The task allocation of equipment must meet the construction progress and task priority requirements.

6. The method for efficient vertical transportation scheduling in super high-rise building construction according to claim 1 is characterized in that: In step S4, the adaptive genetic algorithm adjusts the selection of genetic operators, crossover probability and mutation rate according to the real-time feedback data to adapt to dynamic changes in the construction site, such as equipment failure or changes in task requirements.

7. The method for efficient scheduling of vertical transportation in super high-rise building construction according to claim 6 is characterized in that: The scheduling platform can execute the Markov decision process and optimization algorithm in real time, generate the optimal scheduling plan and feed it back to the equipment control system or operator to ensure coordinated operation of equipment during the construction process.

8. The method for efficient scheduling of vertical transportation in super high-rise building construction according to claim 4 is characterized in that: The equipment task allocation ensures that high-priority tasks are allocated to equipment first and reduces task waiting time by matching task priorities with construction progress.

9. The method for efficient scheduling of vertical transportation in super high-rise building construction according to claim 1, characterized in that: The weighted sum of the objective function optimization in step S3 is calculated by the following formula: minf(x)=α1·T total (x)+α2·T idle (x)+α3·T waiting (x) in; T total (x) is the total transportation time; T idle (x) is the device idle time; T waiting (x) is the task waiting time, and α1, α2, α3 are predetermined weighting coefficients.

10. The method for efficient vertical transportation scheduling in super high-rise building construction according to claim 7, characterized in that: The scheduling optimization is ensured to operate efficiently in actual construction through real-time simulation and verification, and the optimization algorithm is further adjusted based on the simulation data to improve the response speed and robustness of the system.

Images