IoT-based Smart Construction Site EPC Full-Process Management Method and System

Abstract

This application discloses a smart construction site EPC full-process management method and system based on the Internet of Things (IoT), relating to the IoT field. The method includes: using an edge construction monitoring array to monitor construction operations at a school building construction site, obtaining a sequence of operation data within a historical time zone; predicting and obtaining a set of predicted material consumption ratios and predicted construction delay ratios within a preset time zone; constructing a tower crane operation scheduling evaluation function with the optimization objectives of maximizing operational collaboration efficiency and tower crane utilization, and minimizing the overall construction delay ratio and tower crane operation energy consumption; optimizing the scheduling of hoisting tasks within the preset time zone to obtain the optimal tower crane scheduling scheme; and controlling multiple tower cranes to perform collaborative hoisting operations according to the optimal tower crane scheduling scheme within the preset time zone. This solves the problems of insufficient control over construction progress in existing construction site management methods, leading to low tower crane utilization, low operational collaboration efficiency, and inaccurate and untimely construction progress analysis.

Description

Technical Field

[0001] This application relates to the field of Internet of Things (IoT) technology, specifically to a smart construction site EPC full-process management method and system based on IoT. Background Technology

[0002] With the continuous development of the construction industry, school construction sites typically involve complex personnel flows, a large number of workers with diverse jobs, and their activities at different construction stages and in different areas increase the difficulty of site management. Furthermore, the daily activities of students, teachers, and other non-construction personnel overlap with the construction area, requiring special attention to construction safety and the impact on normal teaching order. Simultaneously, school construction sites have a relatively compact spatial layout, often requiring rational planning within limited space to meet the placement and operation needs of construction equipment without excessively interfering with surrounding teaching and living facilities. As school construction projects increase in number and scale, traditional site management methods often rely on manual experience and irregular on-site inspections to control construction progress. This leads to low tower crane utilization, low operational coordination efficiency, and inaccurate and untimely construction progress analysis. It also fails to predict material consumption and construction delay rates in advance, thus affecting the overall construction plan and increasing overall construction delays and tower crane energy consumption. Summary of the Invention

[0003] This application provides a smart construction site EPC full-process management method and system based on the Internet of Things, which solves the technical problems of insufficient control over construction progress in existing construction site management methods, resulting in low tower crane utilization, low work coordination efficiency, and inaccurate and untimely construction progress analysis.

[0004] The technical solution to the above-mentioned technical problems in this application is as follows:

[0005] Firstly, this application provides a smart construction site EPC full-process management method based on the Internet of Things, the method comprising:

[0006] The edge construction monitoring array was used to monitor the construction operations at the school building construction site and obtain several sets of operation data sequences for several construction areas within historical time zones.

[0007] Based on the aforementioned sets of work data sequences, the construction progress is analyzed to predict and obtain a set of predicted material consumption ratios and a set of predicted construction delay ratios within a preset time zone.

[0008] A tower crane operation scheduling evaluation function is constructed with the optimization objectives of maximizing operational coordination efficiency, tower crane utilization rate, minimizing overall construction delay rate, and tower crane operation energy consumption.

[0009] Based on the distribution of tower crane locations and tower crane operation attributes within the school construction site, as well as the aforementioned sets of predicted material consumption ratios and the aforementioned sets of predicted construction delay ratios, the optimal tower crane scheduling scheme is obtained by optimizing the scheduling of hoisting tasks within a preset time zone based on the tower crane operation scheduling evaluation function.

[0010] Within the preset time zone, multiple tower cranes are controlled to carry out coordinated lifting operations according to the optimal tower crane scheduling scheme.

[0011] Secondly, this application provides an IoT-based smart construction site EPC full-process management system, including:

[0012] The data acquisition module is used to monitor construction operations at the school building construction site using the edge construction monitoring array, and to acquire several sets of operation data sequences for several construction areas within a historical time zone.

[0013] The proportion prediction module is used to analyze the construction progress based on the several sets of work data sequences, and to predict and obtain several sets of predicted material consumption proportions and several sets of predicted construction delay proportions within a preset time zone.

[0014] The function building module is used to construct a tower crane operation scheduling evaluation function with the optimization objectives of maximizing operation coordination efficiency, tower crane utilization rate and minimizing the overall construction delay ratio and tower crane operation energy consumption.

[0015] The scheme acquisition module is used to optimize the scheduling of hoisting tasks within a preset time zone based on the tower crane location distribution and tower crane operation attributes within the school building construction site, as well as the several predicted material consumption ratio sets and several predicted construction delay ratios, and obtain the optimal tower crane scheduling scheme based on the tower crane operation scheduling evaluation function.

[0016] The operation execution module is used to control multiple tower cranes to carry out coordinated lifting operations within the preset time zone according to the optimal tower crane scheduling scheme.

[0017] This application provides one or more technical solutions, which have at least the following technical effects or advantages:

[0018] This application provides a smart construction site EPC full-process management method and system based on the Internet of Things. First, it utilizes an edge construction monitoring array to acquire historical operation data, comprehensively understanding the construction status. Then, by analyzing the construction progress, it predicts the material consumption ratio and construction delay ratio in advance, helping to rationally arrange material supply and construction plans, avoiding delays and increased costs due to material shortages or construction delays. Second, it constructs a tower crane operation scheduling evaluation function and performs scheduling optimization to improve tower crane utilization and operational coordination efficiency. Simultaneously, with the goal of maximizing operational coordination efficiency and tower crane utilization while minimizing the overall construction delay ratio and tower crane operation energy consumption, it makes the allocation of tower crane lifting tasks more scientific and reasonable, reducing tower crane idle time and operation waiting time, lowering tower crane operation energy consumption, thereby improving overall construction efficiency and economic benefits.

[0019] Through the above technical solutions, the lifting tasks of tower cranes in future time zones can be optimized and scheduled in the school construction site by combining construction progress data. The optimal tower crane scheduling scheme is implemented to make full use of tower crane resources. By rationally allocating lifting tasks, the operations in each construction area can be carried out in an orderly manner, improving the efficiency of work coordination, reducing the overall construction delay rate and tower crane operation energy consumption, and reducing construction costs. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the IoT-based smart construction site EPC full-process management method provided in this application embodiment;

[0022] Figure 2 This is a schematic diagram of the structure of the IoT-based smart construction site EPC full-process management system provided in the embodiments of this application.

[0023] The components represented by each number in the attached diagram are explained below:

[0024] Data acquisition module 11, proportion prediction module 12, function construction module 13, scheme acquisition module 14, and job execution module 15. Detailed Implementation

[0025] This application provides a smart construction site EPC full-process management method and system based on the Internet of Things, which is used to address the technical problems of insufficient control over construction progress in existing construction site management methods, resulting in low tower crane utilization, low work coordination efficiency, and inaccurate and untimely construction progress analysis.

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0028] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid unnecessarily obscuring the description of this application. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0029] Example 1, as Figure 1 As shown in the embodiments of this application, a smart construction site EPC full-process management method based on the Internet of Things is provided, including:

[0030] S10: Use the edge construction monitoring array to monitor construction operations at the school building construction site and obtain several sets of operation data sequences for several construction areas within historical time zones;

[0031] In this embodiment of the application, the construction scenario is a school building construction site, including buildings such as teaching buildings and canteens, and does not target tall and large buildings, such as residential buildings or commercial buildings.

[0032] School construction sites are typically characterized by complex and regular personnel movement. During the teaching period, students and faculty are frequently active, and construction activities must fully consider their impact on normal teaching order. For example, noisy and dangerous construction work should be avoided during breaks and peak hours to prevent disruption to teaching activities and safety hazards.

[0033] Meanwhile, the school buildings are clearly divided into functional zones, and the construction requirements and schedules vary considerably between different areas. Teaching areas, such as teaching buildings and laboratories, have high requirements for construction quality and precision, and relevant standards and specifications must be strictly followed during construction. On the other hand, logistics and activity areas, such as canteens and gymnasiums, have relatively flexible construction schedules, but they must still be coordinated with the overall construction schedule.

[0034] IoT sensors are deployed in several construction areas at the school building construction site to build an edge construction monitoring array. These IoT sensors can collect various types of construction data in real time. For example, angle and displacement sensors installed in the tower crane operation area monitor the tower crane's working status and hoisting trajectory. Through the collaborative work of multiple sensors, a series of operation data sequences for the construction area within historical time zones are obtained.

[0035] Specifically, step S10 in the method includes:

[0036] Deploy IoT sensors in several construction areas at the school building construction site to build an edge construction monitoring array;

[0037] According to the preset time interval, the construction operation monitoring array is used to monitor the construction site of the school building and obtain several sets of operation data sequences in several construction areas within the historical time zone. Among them, the operation data types include at least the construction progress ratio set, equipment operation status, personnel operation status and material remaining ratio set.

[0038] In this embodiment, firstly, IoT sensors are deployed in several construction areas at the school building construction site to build an edge construction monitoring array, acquiring several sets of operation data sequences for these construction areas within historical time zones. Monitoring at preset time intervals ensures the continuity and timeliness of the data. For example, acquiring operation data once per hour allows for timely capture of dynamic changes during the construction process.

[0039] Furthermore, the data types for operational tasks include construction progress percentage sets, equipment operating status, personnel operating status, and material remaining percentage sets. Construction progress percentage sets include the completion percentage for each floor and each work process, reflecting the construction completion status of each construction area within a historical time zone. Analyzing these percentage sets helps determine whether the construction progress in different areas is balanced. Equipment operating status data helps determine whether construction equipment is operating normally and whether there are potential malfunctions. For example, if the operating parameters of a tower crane fluctuate abnormally, it may indicate that the equipment is about to malfunction and requires timely maintenance.

[0040] Personnel work status data can reflect the work efficiency and intensity of construction workers, which helps to rationally allocate personnel; the material surplus ratio set includes several types of building materials, providing a basis for material supply and management, and avoiding construction delays or resource waste caused by material shortages or stockpiles.

[0041] The operation data sequence obtained through the edge construction monitoring array provides comprehensive and accurate data support for subsequent construction progress analysis and tower crane scheduling plan formulation.

[0042] S20: Analyze the construction progress based on the aforementioned sets of work data sequences, and predict and obtain a set of predicted material consumption ratios and a set of predicted construction delay ratios within a preset time zone.

[0043] In this embodiment, data such as construction progress ratio sets and material surplus ratio sets from several sets of work data sequences are mined and analyzed. Using time series analysis, machine learning, and other methods, and considering various influencing factors such as construction technology, weather conditions, and staffing, a construction progress prediction model is established. This model predicts several sets of predicted material consumption ratios and several sets of predicted construction delay ratios for each construction area within a preset time zone.

[0044] For example, for a concrete pouring construction area, based on historical data such as concrete usage, construction progress, and weather conditions, and combined with future weather forecasts, the proportion of concrete consumption in that area within a preset time zone is predicted. Simultaneously, considering potential factors such as personnel shortages and equipment malfunctions, the proportion of construction delays in that area is predicted.

[0045] Specifically, step S20 in the method includes:

[0046] Upload the aforementioned multiple sets of work data sequences to the cloud management platform, and randomly select the first set of work data sequences for the first construction area;

[0047] Within the cloud management platform, the first construction progress analysis plugin for the first construction area is invoked to perform construction progress analysis within a preset time zone based on the first work data sequence group, outputting a first predicted material consumption ratio set and a first predicted construction delay ratio, and sequentially analyzing to obtain several predicted material consumption ratio sets and several predicted construction delay ratios.

[0048] The construction method of the first construction progress analysis plugin includes:

[0049] Based on the historical construction logs of the first construction area, multiple sample operation data sequence groups are collected, and historical material consumption ratio sets and historical construction delay ratios of different sample operation data sequence groups are collected to obtain multiple sample material consumption ratio sets and multiple sample construction delay ratios.

[0050] The multiple sample operation data sequence groups, multiple sample material consumption ratio sets, and multiple sample construction delay ratios are used as training data, and data with replacement are randomly selected to construct a K sample training set, where K is greater than or equal to 10.

[0051] The Long Short-Term Memory Network is trained to convergence using the K sample training sets to obtain K first construction progress analyzers, which are then integrated and constructed into a first construction progress analysis plugin according to the mean fusion strategy.

[0052] In this embodiment, firstly, several sets of acquired work data sequences are uploaded to the cloud management platform. Then, the first set of work data sequences for the first construction area is randomly selected to facilitate subsequent targeted analysis of the construction progress. Within the cloud management platform, the first construction progress analysis plugin for the first construction area is invoked.

[0053] Secondly, based on the historical construction logs of the first construction area, multiple sample operation data sequence sets were collected. At the same time, the historical material consumption ratio set and historical construction delay ratio corresponding to different sample operation data sequence sets were collected to obtain multiple sample material consumption ratio sets and multiple sample construction delay ratios, which provide a foundation for subsequent model training.

[0054] Next, the data from the first assignment's data sequence group is used as the training data, and data is randomly selected with replacement to construct a training set of K samples, where K is greater than or equal to 10. Randomly selecting data with replacement increases the diversity of the data, making the training set more representative.

[0055] Next, the Long Short-Term Memory (LSTM) network was trained to convergence using K sample training sets, resulting in K first-level construction progress analyzers. The LSM network possesses powerful sequence data processing capabilities, enabling it to learn the relationship between construction progress and time. Finally, a first-level construction progress analysis plugin was constructed by integrating these plugins using a mean fusion strategy, combining the advantages of multiple analyzers to improve the accuracy and reliability of the analysis.

[0056] By constructing a first construction progress analysis plugin, the construction progress within a preset time zone is analyzed based on a first set of work data sequences, outputting a first predicted material consumption ratio set and a first predicted construction delay ratio. The same analysis is then performed on other construction areas sequentially, ultimately yielding several predicted material consumption ratio sets and several predicted construction delay ratios.

[0057] For example, the first construction progress analysis plugin is built and trained based on a Long Short-Term Memory network, and the specific steps are as follows:

[0058] First, data preparation involves collecting historical construction logs from the first construction area, extracting multiple sample operation data sequence sets, and simultaneously recording the historical material consumption ratios and historical construction delay ratios corresponding to different sample operation data sequence sets, forming multiple sample material consumption ratio sets and multiple sample construction delay ratio sets. The data is then cleaned and preprocessed to remove outliers and missing values, ensuring data quality and consistency. Finally, the prepared data is randomly selected with replacement to construct a K-sample training set, where K ≥ 10.

[0059] Secondly, for model building, a Long Short-Term Memory (LST) network model is constructed using Python and deep learning frameworks such as TensorFlow. The input layer receives sets of sample job data sequences, and the output layer outputs the predicted material consumption ratios and construction delay ratios.

[0060] The number of nodes in the input layer is equal to the dimension of the input features. For example, if the first task data sequence has 4 features, then the input layer contains 4 nodes. Set 1-3 hidden layers, and adjust the number of nodes in each layer through experiments, such as 64, 32, etc. The activation function is ReLU. The number of nodes in the output layer is equal to the predicted construction delay ratio. For example, if the predicted time is 1 node, the output layer generally does not use an activation function and directly outputs continuous values.

[0061] Then, the model is trained using K training samples to train the Long Short-Term Memory (LSTM) network until convergence. The training framework is constructed using the Adam optimizer and the Mean Squared Error (MSE) loss function, with a batch size of 32 and a total of 50 training epochs. An early stopping mechanism (patience=5) is introduced: if the validation set loss does not decrease for 5 consecutive epochs, the training process is automatically terminated, resulting in K completed first construction progress analyzers. The LSM network processes sequential data to capture the patterns of construction progress changes over time, thereby accurately predicting the proportion of material consumption and construction delays.

[0062] Finally, the model is integrated by combining the K first construction progress analyzers obtained from training according to the mean fusion strategy to build the first construction progress analysis plugin.

[0063] Furthermore, the mean fusion strategy refers to averaging the outputs of K analyzers, which can combine the advantages of multiple analyzers, reduce the error of a single analyzer, and improve the accuracy and reliability of the analysis.

[0064] The first construction progress analysis plugin, built and trained based on a long short-term memory network, can make full use of historical construction data to provide a more accurate tool for construction progress analysis and prediction.

[0065] Specifically, the first construction progress analysis plugin is invoked to perform construction progress analysis within a preset time zone based on the first work data sequence group, and outputs a first predicted material consumption ratio set and a first predicted construction delay ratio, including:

[0066] Perform state fluctuation analysis on the first construction progress ratio set sequence and the first material remaining ratio set sequence in the first operation data sequence group, and output the first construction progress fluctuation coefficient and the first material consumption fluctuation coefficient.

[0067] The first construction status fluctuation degree is determined based on the first construction progress fluctuation coefficient and the first material consumption fluctuation coefficient.

[0068] The ratio of the first construction state fluctuation to the maximum historical construction state fluctuation within the historical time range is multiplied by K and rounded to obtain the optimal number of analyzers J, where J is not less than 2.

[0069] J analyzers are randomly selected from the K first construction progress analyzers in the first construction progress analysis plugin. Based on the first work data sequence group, the construction progress analysis is performed within a preset time zone, and the first predicted material consumption ratio set and the first predicted construction delay ratio are output.

[0070] In this embodiment of the application, firstly, the first construction progress ratio set sequence and the first material remaining ratio set sequence in the first operation data sequence group are subjected to state fluctuation analysis, the fluctuation of each indicator is calculated respectively, and then weighted according to the influence degree of the indicator to obtain the first construction progress fluctuation coefficient and the first material consumption fluctuation coefficient.

[0071] Secondly, after analyzing and obtaining the first construction progress fluctuation coefficient and the first material consumption fluctuation coefficient, the first construction state fluctuation degree is assessed and determined. The first construction state fluctuation degree reflects the overall fluctuation of construction progress and material consumption, and is an indicator for measuring construction stability. The lower the construction state fluctuation degree, the more stable the construction process.

[0072] For example, if the weight of the construction progress fluctuation coefficient is 0.6 and the weight of the material consumption fluctuation coefficient is 0.4, it can be calculated by the formula "first construction state fluctuation = first construction progress fluctuation coefficient × 0.6 + first material consumption fluctuation coefficient × 0.4".

[0073] Then, the first construction state fluctuation is compared with the maximum historical construction state fluctuation within the historical time range. The ratio is calculated and multiplied by K, then rounded to obtain the optimal number of analyzers J. The maximum historical construction state fluctuation represents the maximum fluctuation that occurred in the construction area during past construction. Selecting J analyzers is to improve analysis efficiency while ensuring analysis accuracy. J is not less than 2 to avoid potential errors from a single analyzer.

[0074] Finally, J analyzers are randomly selected from the K first construction progress analyzers in the first construction progress analysis plugin. These analyzers perform construction progress analysis within a preset time zone based on the first set of work data sequences, outputting a first predicted material consumption ratio set and a first predicted construction delay ratio. These randomly selected J analyzers combine the advantages of different analyzers to analyze the first set of work data sequences, thereby more accurately predicting the material consumption ratio and construction delay ratio within the preset time zone.

[0075] For example, if the first construction state fluctuation is 0.3, the maximum historical construction state fluctuation within the historical time range is 0.5, and K is 15, then the ratio is 0.3 ÷ 0.5 = 0.6, multiplied by K is 0.6 × 15 = 9, that is, J is 9.

[0076] After randomly selecting J analyzers from the K first construction progress analyzers in the first construction progress analysis plugin, a construction progress analysis is performed within a preset time zone based on the first operation data sequence group. The J analyzers combine their own training results with the information in the first operation data sequence group, and use their respective algorithms and models to perform calculations and predictions, ultimately outputting the first predicted material consumption ratio set and the first predicted construction delay ratio.

[0077] S30: Construct a tower crane operation scheduling evaluation function with the optimization objectives of maximizing operation coordination efficiency, tower crane utilization rate, minimizing overall construction delay ratio, and tower crane operation energy consumption;

[0078] In this embodiment, to achieve scientific scheduling of tower crane operations, improve construction efficiency, and reduce costs, a tower crane operation scheduling evaluation function is constructed with the optimization objective in mind. The tower crane operation scheduling evaluation function aims to maximize operational coordination efficiency, tower crane utilization rate, minimize overall construction delay ratio, and tower crane operation energy consumption.

[0079] Improving operational coordination efficiency ensures close cooperation between various construction stages, reducing time wastage caused by poor workflow. For example, during concrete pouring, tower cranes can promptly and accurately transport concrete to designated locations, operating in sync with construction workers and preventing situations where personnel are waiting or tower cranes are idle. By enhancing operational coordination efficiency, the overall construction progress can be accelerated.

[0080] Maximizing tower crane utilization means fully utilizing their working capacity and minimizing their idle time. Based on the distribution of construction areas and operational needs, tower crane lifting tasks should be rationally scheduled to enable them to complete more lifting work per unit of time. For example, lifting tasks in adjacent construction areas can be concentrated on the same tower crane, reducing the time the crane spends moving between different areas.

[0081] Furthermore, minimizing the overall construction delay ratio during the construction process can be affected by various factors, such as weather changes and equipment failures, leading to construction delays. By constructing an evaluation function, these factors can be comprehensively considered, and countermeasures can be formulated in advance to reduce the possibility of construction delays. Minimizing tower crane operation energy consumption not only helps reduce construction costs but also meets the requirements of energy conservation and emission reduction. Energy consumption can be reduced by optimizing the tower crane's operating path and reducing unnecessary lifting and lowering operations. For example, an intelligent control system can be used to automatically adjust the tower crane's operating speed and power based on the weight and distance of the goods being lifted.

[0082] The determination of weighting coefficients needs to be dynamically adjusted according to the specific characteristics and requirements of the construction project to ensure that the evaluation function can accurately reflect the actual needs in the construction process.

[0083] By optimizing the evaluation function, the optimal tower crane operation scheduling scheme is obtained, thereby achieving high efficiency, energy saving, and timely completion of the construction process.

[0084] Specifically, step S30 in the method includes:

[0085] According to the preset project construction schedule, construction delay analysis is conducted based on several construction schedule ratio sets to obtain the construction delay ratio of several regions.

[0086] Weights are assigned to the criticality of several processes in several construction areas, and the construction delay ratios of the aforementioned areas are weighted and summed to obtain the current overall construction delay ratio.

[0087] The product of 1 and the current overall construction delay ratio and the constant P is used as the construction delay weight adjustment coefficient to compensate for the initial construction delay weight and obtain the adapted construction delay weight. The initial construction delay weight is 0.5, P is greater than 2 and less than or equal to 5, and the adapted construction delay weight is not less than 0.2 and not greater than 0.8.

[0088] Based on the adapted construction delay weight, the weight ratios of operation coordination efficiency, tower crane utilization rate, and tower crane operation energy consumption are configured according to a preset ratio to construct an adapted weight distribution;

[0089] Based on the aforementioned adaptive weight distribution, a tower crane operation scheduling evaluation function is constructed with the optimization objectives of maximizing operation coordination efficiency, tower crane utilization rate, minimizing overall construction delay ratio, and tower crane operation energy consumption.

[0090] In this embodiment, firstly, a construction delay analysis is performed on several sets of construction progress ratios according to a preset project construction schedule. These sets of construction progress ratios reflect the actual progress of each construction area at different stages. By comparing the preset schedule with the actual progress, the construction delay ratios for several areas can be accurately obtained.

[0091] Next, weights are assigned based on the criticality of several construction processes across several construction areas. Critical processes that significantly impact the overall construction progress should be assigned higher weights. Then, the weighted summation of the construction delay percentages across several areas yields a more accurate overall construction delay percentage that reflects the overall project's construction delay status. For example, in a project encompassing multiple construction areas such as foundation construction, main structure construction, and interior decoration, the foundation construction process has a high criticality; any delays in this area will have a magnified impact during the weighted summation.

[0092] For example, assume the criticality weight of the foundation construction area is 0.4, the criticality weight of the main structure construction area is 0.3, and the criticality weight of the decoration and finishing area is 0.3. The construction delay ratio of the foundation construction area is 0.1, the construction delay ratio of the main structure construction area is 0.05, and the construction delay ratio of the decoration and finishing area is 0.03. Then the current overall construction delay ratio is 0.1×0.4+0.05×0.3+0.03×0.3=0.064.

[0093] Subsequently, the product of 1 and the current overall construction delay ratio with a constant P is used as the construction delay weight adjustment coefficient. The constant P ranges from greater than 2 to less than or equal to 5, allowing for flexible adjustments based on the characteristics of different projects and the severity of construction delays. The initial construction delay weight is compensated; the initial construction delay weight is 0.5, and after adjustment, an appropriate construction delay weight is obtained, which is neither less than 0.2 nor greater than 0.8. This makes the evaluation function more reasonably reflect the impact of construction delays on the overall construction. For example, when construction delays are more severe, the appropriate construction delay weight will increase accordingly, thus giving more attention to construction delays in the evaluation function.

[0094] For example, the initial construction delay weight is 0.5, and P is greater than 2 and less than or equal to 5. Assuming P is 3, and the current overall construction delay ratio is 0.064, then the construction delay weight adjustment coefficient is 1 + 0.064 × 3 = 1.192. Therefore, the adapted construction delay weight is 0.5 × 1.192 = 0.596, and the adapted construction delay weight is not less than 0.2 and not greater than 0.8. This result meets the requirements.

[0095] Secondly, based on the weight of the adapted construction delay, the weight ratios of operation coordination efficiency, tower crane utilization rate, and tower crane operation energy consumption are configured according to preset proportions to construct an adapted weight distribution. For example, if the sum of the preset weight ratios of operation coordination efficiency, tower crane utilization rate, and tower crane operation energy consumption is 1 minus the weight of the adapted construction delay, i.e., 1-0.596=0.404, then 0.404 can be allocated to operation coordination efficiency, tower crane utilization rate, and tower crane operation energy consumption in a ratio of 2:3:1. Then, the weight of operation coordination efficiency is 0.404×(2 / 6)≈0.135, the weight of tower crane utilization rate is 0.404×(3 / 6)≈0.202, and the weight of tower crane operation energy consumption is 0.404×(1 / 6)≈0.067.

[0096] Finally, based on the adapted weight distribution, a tower crane operation scheduling evaluation function is constructed with the optimization objectives of maximizing operational collaboration efficiency, tower crane utilization rate, minimizing the overall construction delay ratio, and tower crane operation energy consumption. This evaluation function can be expressed as: Evaluation function value = Operational collaboration efficiency × 0.135 + Tower crane utilization rate × 0.202 - Overall construction delay ratio × 0.596 - Tower crane operation energy consumption × 0.067. This evaluation function comprehensively considers multiple key factors in the construction process. By optimizing and solving this function, the optimal tower crane operation scheduling scheme can be obtained, thereby achieving high efficiency, energy saving, and on-time completion of the construction process.

[0097] S40: Based on the distribution of tower crane locations and tower crane operation attributes within the school building construction site, as well as the aforementioned sets of predicted material consumption ratios and the aforementioned sets of predicted construction delay ratios, the optimal tower crane scheduling scheme is obtained by optimizing the scheduling of hoisting tasks within the preset time zone based on the tower crane operation scheduling evaluation function.

[0098] In this embodiment, the location distribution and operational attributes of tower cranes within the school construction site are first considered to optimize the scheduling of hoisting tasks within a preset time zone. The location distribution of tower cranes determines their coverage area and hoisting capacity; tower cranes in different locations have varying accessibility to different construction areas. For example, the goal is to maximize tower crane utilization, minimize overall construction delays, maximize operational coordination efficiency, and minimize tower crane energy consumption. Tower crane operational attributes include tower crane type, maximum hoisting load capacity, and operational coverage area.

[0099] Meanwhile, several sets of predicted material consumption ratios and several sets of predicted construction delay ratios also serve as the basis for scheduling optimization. The set of predicted material consumption ratios can reflect in advance the amount of materials required by different construction areas within a preset time zone, thereby ensuring timely material supply. The predicted construction delay ratios help dispatchers to anticipate potential construction delays.

[0100] Based on the above information, and combined with the tower crane operation scheduling evaluation function, the scheduling optimization of hoisting tasks within the preset time zone is performed.

[0101] During the optimization process, the scheduling plan needs to be continuously evaluated and adjusted. Based on changes in actual construction conditions, such as earlier or later construction progress, or changes in material supply, the scheduling plan should be modified promptly to ensure its optimality and feasibility.

[0102] Specifically, step S40 in the method includes:

[0103] A tower crane operation simulation space is constructed based on the distribution of tower crane locations and tower crane operation attributes within the school building construction site.

[0104] Obtain several hoisting task sets for several construction areas within a preset time zone, and randomly allocate the several hoisting task sets based on the tower crane operation attributes to obtain several tower crane scheduling schemes;

[0105] The predicted material consumption ratio set and the predicted construction delay ratio are input into the tower crane operation simulation space for conditional rendering to generate the current crane operation simulation space;

[0106] Within the current crane operation simulation space, the crane operation simulation is performed in a preset time zone according to the several tower crane scheduling schemes, and several crane operation simulation results are output at the end of the preset time zone.

[0107] Based on the tower crane operation scheduling evaluation function, the scheduling quality of the several hoisting simulation results is evaluated, and the tower crane scheduling scheme corresponding to the maximum scheduling quality coefficient is output as the optimal tower crane scheduling scheme.

[0108] In this embodiment, firstly, a tower crane operation simulation space is constructed based on the distribution of tower crane locations and their operational attributes within the school construction site. The simulation space includes the tower crane's location, coverage area, and lifting capacity.

[0109] Next, several hoisting task sets are obtained from several construction areas within a preset time zone. These task sets contain material hoisting needs for different construction areas within the preset time zone, such as the type and quantity of materials to be hoisted, and the starting and ending points of the hoisting. Then, based on tower crane operation attributes, the hoisting task sets are randomly assigned to obtain several tower crane scheduling schemes. During the assignment process, attributes such as tower crane type, maximum hoisting capacity, and work coverage area are considered to ensure that the assigned tasks are within the tower crane's capacity.

[0110] Next, several sets of predicted material consumption ratios and several sets of predicted construction delay ratios are input into the tower crane operation simulation space for conditional rendering to generate the current crane operation simulation space. The predicted material consumption ratio sets allow the simulation space to more accurately reflect the material demand of different construction areas within a preset time zone, while the predicted construction delay ratios can simulate the impact of possible construction delays on the lifting task. Through conditional rendering, the simulation space is made to better reflect the actual construction situation.

[0111] Furthermore, within the current crane operation simulation space, lifting tasks are simulated within preset time zones according to several tower crane scheduling schemes. During the simulation, factors such as tower crane running time, lifting path, and number of lifting operations are considered, and several lifting simulation results are output at the end of the preset time zone.

[0112] Finally, the scheduling quality of several hoisting simulation results is evaluated based on the tower crane operation scheduling evaluation function. The scheduling quality coefficient for each scheduling scheme is calculated to measure the merits of each scheme. A higher scheduling quality coefficient indicates better performance in maximizing operational coordination efficiency, tower crane utilization, minimizing overall construction delays, and reducing tower crane operation energy consumption. The optimal tower crane scheduling scheme is the one with the highest value among all scheduling quality coefficients.

[0113] The hoisting simulation results include the overall tower crane idle time, the overall construction delay ratio, the overall tower crane operation waiting time, and the overall tower crane operation energy consumption.

[0114] In this embodiment, a tower crane operation scheduling evaluation function is used to evaluate the scheduling quality of several hoisting simulation results. This evaluation function aims to maximize operational coordination efficiency, tower crane utilization, and minimize the overall construction delay ratio and tower crane operation energy consumption. By comprehensively evaluating various indicators of the hoisting simulation results, it outputs the tower crane scheduling scheme corresponding to the maximum scheduling quality coefficient as the optimal tower crane scheduling scheme. The optimal scheme can maximize tower crane utilization and reduce energy consumption while ensuring construction progress, achieving high efficiency, energy saving, and on-time completion of the construction process.

[0115] S50: Within the preset time zone, control multiple tower cranes to perform coordinated lifting operations according to the optimal tower crane scheduling scheme.

[0116] In this embodiment, within a preset time zone, multiple tower cranes are controlled to perform coordinated lifting operations according to the optimal tower crane scheduling scheme, ensuring efficient, energy-saving, and timely completion of construction. During the operation, a real-time monitoring system is established to comprehensively monitor the tower crane's operating status and lifting task execution. Various sensors installed on the tower cranes acquire real-time information such as the tower crane's position, speed, and lifting weight.

[0117] In summary, compared with existing technologies, this application, through refined management of tower crane operation scheduling, fully considers factors such as operation coordination efficiency, tower crane utilization rate, overall construction delay ratio, and tower crane operation energy consumption, constructs a scientific and reasonable evaluation function, and obtains the optimal tower crane scheduling scheme through optimization algorithm.

[0118] In summary, the embodiments of this application have at least the following technical effects:

[0119] This application provides an IoT-based smart construction site EPC full-process management method. First, it utilizes an edge construction monitoring array to acquire historical operation data, comprehensively understanding the construction status. Then, by analyzing the construction progress, it predicts the material consumption ratio and construction delay ratio in advance, helping to rationally arrange material supply and construction plans, avoiding delays and increased costs due to material shortages or construction delays. Second, it constructs a tower crane operation scheduling evaluation function and performs scheduling optimization to improve tower crane utilization and operational coordination efficiency. Simultaneously, with the goal of maximizing operational coordination efficiency and tower crane utilization while minimizing the overall construction delay ratio and tower crane operation energy consumption, it makes the allocation of tower crane lifting tasks more scientific and reasonable, reducing tower crane idle time and operation waiting time, lowering tower crane operation energy consumption, thereby improving overall construction efficiency and economic benefits. Through the above technical solutions, the lifting tasks of tower cranes in future time zones can be optimized and scheduled in the school construction site by combining construction progress data. The optimal tower crane scheduling scheme is implemented to make full use of tower crane resources. By rationally allocating lifting tasks, the operations in each construction area can be carried out in an orderly manner, improving the efficiency of work coordination, reducing the overall construction delay rate and tower crane operation energy consumption, and reducing construction costs.

[0120] Example 2, as Figure 2 As shown, based on the same inventive concept as the IoT-based smart construction site EPC full-process management method provided in Embodiment 1, this application also provides an IoT-based smart construction site EPC full-process management system, including:

[0121] Data acquisition module 11 is used to monitor construction operations at the school building construction site using the edge construction monitoring array, and to acquire several sets of operation data sequences for several construction areas within a historical time zone.

[0122] The ratio prediction module 12 is used to perform construction progress analysis based on the several sets of work data sequences, and to predict and obtain several sets of predicted material consumption ratios and several sets of predicted construction delay ratios within a preset time zone.

[0123] Function construction module 13 is used to construct a tower crane operation scheduling evaluation function with the optimization objectives of maximizing operation coordination efficiency, tower crane utilization rate and minimizing overall construction delay ratio and tower crane operation energy consumption;

[0124] The scheme acquisition module 14 is used to optimize the scheduling of hoisting tasks within a preset time zone based on the tower crane location distribution and tower crane operation attributes within the school building construction site, as well as the several predicted material consumption ratio sets and several predicted construction delay ratios, and obtain the optimal tower crane scheduling scheme based on the tower crane operation scheduling evaluation function.

[0125] The operation execution module 15 is used to control multiple tower cranes to carry out coordinated lifting operations in accordance with the optimal tower crane scheduling scheme within the preset time zone.

[0126] In one embodiment, the data acquisition module 11 is specifically used for:

[0127] Deploy IoT sensors in several construction areas at the school building construction site to build an edge construction monitoring array;

[0128] According to the preset time interval, the construction operation monitoring array is used to monitor the construction site of the school building and obtain several sets of operation data sequences in several construction areas within the historical time zone. Among them, the operation data types include at least the construction progress ratio set, equipment operation status, personnel operation status and material remaining ratio set.

[0129] In one embodiment, the ratio prediction module 12 is specifically used for:

[0130] Upload the aforementioned multiple sets of work data sequences to the cloud management platform, and randomly select the first set of work data sequences for the first construction area;

[0131] Within the cloud management platform, the first construction progress analysis plugin for the first construction area is invoked to perform construction progress analysis within a preset time zone based on the first work data sequence group, outputting a first predicted material consumption ratio set and a first predicted construction delay ratio, and sequentially analyzing to obtain several predicted material consumption ratio sets and several predicted construction delay ratios.

[0132] The construction method of the first construction progress analysis plugin includes:

[0133] Based on the historical construction logs of the first construction area, multiple sample operation data sequence groups are collected, and historical material consumption ratio sets and historical construction delay ratios of different sample operation data sequence groups are collected to obtain multiple sample material consumption ratio sets and multiple sample construction delay ratios.

[0134] The multiple sample operation data sequence groups, multiple sample material consumption ratio sets, and multiple sample construction delay ratios are used as training data, and data with replacement are randomly selected to construct a K sample training set, where K is greater than or equal to 10.

[0135] The Long Short-Term Memory Network is trained to convergence using the K sample training sets to obtain K first construction progress analyzers, which are then integrated and constructed into a first construction progress analysis plugin according to the mean fusion strategy.

[0136] Furthermore, in one embodiment, a first construction progress analysis plugin is invoked to perform construction progress analysis within a preset time zone based on the first work data sequence group, outputting a first predicted material consumption ratio set and a first predicted construction delay ratio, including:

[0137] Perform state fluctuation analysis on the first construction progress ratio set sequence and the first material remaining ratio set sequence in the first operation data sequence group, and output the first construction progress fluctuation coefficient and the first material consumption fluctuation coefficient.

[0138] The first construction status fluctuation degree is determined based on the first construction progress fluctuation coefficient and the first material consumption fluctuation coefficient.

[0139] The ratio of the first construction state fluctuation to the maximum historical construction state fluctuation within the historical time range is multiplied by K and rounded to obtain the optimal number of analyzers J, where J is not less than 2.

[0140] J analyzers are randomly selected from the K first construction progress analyzers in the first construction progress analysis plugin. Based on the first work data sequence group, the construction progress analysis is performed within a preset time zone, and the first predicted material consumption ratio set and the first predicted construction delay ratio are output.

[0141] In one embodiment, function construction module 13 is specifically used for:

[0142] According to the preset project construction schedule, construction delay analysis is conducted based on several construction schedule ratio sets to obtain the construction delay ratio of several regions.

[0143] Weights are assigned to the criticality of several processes in several construction areas, and the construction delay ratios of the aforementioned areas are weighted and summed to obtain the current overall construction delay ratio.

[0144] The product of 1 and the current overall construction delay ratio and the constant P is used as the construction delay weight adjustment coefficient to compensate for the initial construction delay weight and obtain the adapted construction delay weight. The initial construction delay weight is 0.5, P is greater than 2 and less than or equal to 5, and the adapted construction delay weight is not less than 0.2 and not greater than 0.8.

[0145] Based on the adapted construction delay weight, the weight ratios of operation coordination efficiency, tower crane utilization rate, and tower crane operation energy consumption are configured according to a preset ratio to construct an adapted weight distribution;

[0146] Based on the aforementioned adaptive weight distribution, a tower crane operation scheduling evaluation function is constructed with the optimization objectives of maximizing operation coordination efficiency, tower crane utilization rate, minimizing overall construction delay ratio, and tower crane operation energy consumption.

[0147] In one embodiment, the solution acquisition module 14 is specifically used for:

[0148] A tower crane operation simulation space is constructed based on the distribution of tower crane locations and tower crane operation attributes within the school building construction site.

[0149] Obtain several hoisting task sets for several construction areas within a preset time zone, and randomly allocate the several hoisting task sets based on the tower crane operation attributes to obtain several tower crane scheduling schemes;

[0150] The predicted material consumption ratio set and the predicted construction delay ratio are input into the tower crane operation simulation space for conditional rendering to generate the current crane operation simulation space;

[0151] Within the current crane operation simulation space, the crane operation simulation is performed in a preset time zone according to the several tower crane scheduling schemes, and several crane operation simulation results are output at the end of the preset time zone.

[0152] Based on the tower crane operation scheduling evaluation function, the scheduling quality of the several hoisting simulation results is evaluated, and the tower crane scheduling scheme corresponding to the maximum scheduling quality coefficient is output as the optimal tower crane scheduling scheme.

[0153] Furthermore, the hoisting simulation results include the overall tower crane idle time, the overall construction delay ratio, the overall tower crane operation waiting time, and the overall tower crane operation energy consumption.

[0154] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0155] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0156] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and modifications fall within the scope of this application and its equivalents, this application intends to include such modifications and modifications.

Claims

1. A smart construction site EPC full-process management method based on the Internet of Things, characterized in that the method The method comprises the following steps: monitoring the construction operation of a school building construction site by using an edge construction monitoring array, obtaining a plurality of operation data sequence groups of a plurality of construction areas in a historical time zone; analyzing the construction progress according to the plurality of operation data sequence groups, and obtaining a plurality of predicted material consumption ratios and a plurality of predicted construction delay ratios in a preset time zone; constructing a tower crane operation scheduling evaluation function with the optimization objectives of maximizing operation synergy efficiency and tower crane utilization rate and minimizing overall construction delay ratio and tower crane operation energy consumption; scheduling and optimizing the hoisting tasks in the preset time zone based on the tower crane operation scheduling evaluation function according to the tower crane position distribution and tower crane operation attribute in the school building construction site and the plurality of predicted material consumption ratios and the plurality of predicted construction delay ratios, and obtaining an optimal tower crane scheduling scheme; controlling a plurality of tower cranes to perform collaborative hoisting operation in the preset time zone according to the optimal tower crane scheduling scheme; analyzing the construction progress according to the plurality of operation data sequence groups, and obtaining a plurality of predicted material consumption ratios and a plurality of predicted construction delay ratios in a preset time zone, which comprises the following steps: uploading the plurality of operation data sequence groups to a cloud management platform, and randomly selecting a first operation data sequence group of a first construction area; in the cloud management platform, calling a first construction progress analysis plug-in of the first construction area, analyzing the construction progress in the preset time zone according to the first operation data sequence group, outputting a first predicted material consumption ratio set and a first predicted construction delay ratio, and sequentially analyzing a plurality of predicted material consumption ratio sets and a plurality of predicted construction delay ratios; wherein the construction method of the first construction progress analysis plug-in comprises the following steps: based on the historical construction log of the first construction area, collecting a plurality of sample operation data sequence groups, and collecting a plurality of sample material consumption ratio sets and a plurality of sample construction delay ratios of different sample operation data sequence groups, obtaining a plurality of sample material consumption ratio sets and a plurality of sample construction delay ratios; using the plurality of sample operation data sequence groups, the plurality of sample material consumption ratio sets and the plurality of sample construction delay ratios as training data, and performing random data selection with replacement, constructing K sample training sets, wherein K is greater than or equal to 10; training the long short-term memory network to convergence respectively by using the K sample training sets, obtaining K first construction progress analyzers, and integrating and constructing a first construction progress analysis plug-in according to the mean fusion strategy; calling the first construction progress analysis plug-in, analyzing the construction progress in the preset time zone according to the first operation data sequence group, and outputting the first predicted material consumption ratio set and the first predicted construction delay ratio, which comprises the following steps: performing state fluctuation analysis on the first construction progress ratio set sequence and the first material remaining ratio set sequence in the first operation data sequence group respectively, and outputting a first construction progress fluctuation coefficient and a first material consumption fluctuation coefficient; determining the first construction state fluctuation degree based on the first construction progress fluctuation coefficient and the first material consumption fluctuation coefficient; The ratio of the first construction state fluctuation degree to the maximum historical construction state fluctuation degree in a historical time range is multiplied by K to obtain an optimal analyzer selection number J, wherein J is not less than 2; J analyzers are randomly selected from the K first construction progress analyzers of the first construction progress analysis plug-in, construction progress analysis is performed in a preset time zone according to the first job data sequence group, and a first predicted material consumption proportion set and a first predicted construction delay proportion are output; An evaluation function of tower crane operation scheduling is constructed by taking the maximum job coordination efficiency, tower crane utilization rate and the minimum overall construction delay proportion, tower crane operation energy consumption as the optimization target, including: According to the preset project construction progress, construction delay analysis is performed according to a plurality of construction progress proportion sets to obtain a plurality of regional construction delay proportions; The weights of a plurality of process criticalities of a plurality of construction regions are set, and the plurality of regional construction delay proportions are weighted and summed to obtain a current overall construction delay proportion; A construction delay weight adjustment coefficient is obtained by taking 1 plus the product of the current overall construction delay proportion and a constant P as the construction delay weight adjustment coefficient, and the initial construction delay weight is compensated to obtain an adaptive construction delay weight, wherein the initial construction delay weight is 0.5, P is greater than 2 and less than or equal to 5, and the adaptive construction delay weight is not less than 0.2 and not greater than 0.8; Based on the adaptive construction delay weight, the weight proportions of the job coordination efficiency, the tower crane utilization rate and the tower crane operation energy consumption are configured according to a preset proportion to construct an adaptive weight distribution; Based on the adaptive weight distribution, an evaluation function of tower crane operation scheduling is constructed by taking the maximum job coordination efficiency, tower crane utilization rate and the minimum overall construction delay proportion, tower crane operation energy consumption as the optimization target. 2.The IoT-based intelligent construction site EPC whole-process management method according to claim 1, characterized in that, The school building construction site is monitored by using the edge construction monitoring array to obtain a plurality of job data sequence groups of a plurality of construction regions in a historical time zone, including: The Internet of Things sensors are deployed in the plurality of construction regions of the school building construction site to build the edge construction monitoring array; The school building construction site is monitored by using the edge construction monitoring array according to a preset time interval to obtain a plurality of job data sequence groups of a plurality of construction regions in a historical time zone, wherein the job data types at least include a construction progress proportion set, a device running state, a personnel operation state and a material remaining proportion set. 3.The IoT-based intelligent construction site EPC whole-process management method according to claim 1, characterized in that, Based on the tower crane operation scheduling evaluation function, the hoisting tasks in the preset time zone are scheduled and optimized to obtain an optimal tower crane scheduling scheme according to the tower crane position distribution and the tower crane operation attribute in the school building construction site, and the plurality of predicted material consumption proportion sets and the plurality of predicted construction delay proportions, including: A tower crane operation simulation space is simulated and constructed based on the tower crane position distribution and the tower crane operation attribute in the school building construction site; A plurality of hoisting task sets of a plurality of construction regions in the preset time zone are obtained, and the plurality of hoisting task sets are randomly allocated with the tower crane operation attribute as a constraint to obtain a plurality of tower crane scheduling schemes; The several sets of predicted material consumption ratios and several predicted construction delay ratios are input into the tower crane operation simulation space for conditional rendering to generate a current crane operation simulation space; In the current crane operation simulation space, the several tower crane scheduling schemes are used to simulate the lifting tasks in a preset time zone, and several lifting simulation results at the end of the preset time zone are output; Based on the tower crane operation scheduling evaluation function, the several lifting simulation results are evaluated in terms of scheduling quality, and the tower crane scheduling scheme corresponding to the maximum scheduling quality coefficient is output as the optimal tower crane scheduling scheme. 4.The IoT-based intelligent construction site EPC whole-process management method according to claim 3, characterized in that, The lifting simulation results include overall tower crane idle time, overall construction delay ratio, overall tower crane operation waiting time, and overall tower crane operation energy consumption.

5. The intelligent construction site EPC whole-process management system based on the Internet of Things, characterized in that, A method for performing any one of claims 1-4, comprising: a data acquisition module for monitoring construction operations at a school building construction site using an edge construction monitoring array to obtain several sets of operation data sequences for several construction areas in historical time zones; a ratio prediction module for analyzing construction progress based on the several sets of operation data sequences to predict several sets of predicted material consumption ratios and several predicted construction delay ratios in a preset time zone; a function construction module for constructing a tower crane operation scheduling evaluation function with the optimization objectives of maximizing operation synergy efficiency and tower crane utilization rate and minimizing overall construction delay ratio and tower crane operation energy consumption; a scheme acquisition module for scheduling and optimizing lifting tasks in the preset time zone based on the tower crane operation scheduling evaluation function according to the tower crane position distribution and operation attributes in the school building construction site, as well as the several sets of predicted material consumption ratios and the several predicted construction delay ratios, to obtain an optimal tower crane scheduling scheme; an operation execution module for controlling multiple tower cranes to perform collaborative lifting operations in the preset time zone according to the optimal tower crane scheduling scheme.

Images