Big data-based infrastructure engineering project management system

Abstract

The present application relates to the field of construction project management, in particular to a big data-based infrastructure construction project management system. By acquiring multi-modal engineering project data in the system, the multi-modal engineering project data is spatio-temporally aligned, the outliers in the aligned data are processed to obtain complete engineering project data, the complete engineering project data is multi-modal fused, a feature library of fused engineering project data is constructed, a ResNet-Transformer risk prediction model is established, the hyperparameters of the model are optimized by using an improved whale optimization algorithm of IWOA, the feature engineering project data is input into the target risk prediction model for prediction, and construction planning is carried out based on the construction engineering project state. The data island problem is solved, a complete data set covering all engineering elements is formed, the system can automatically trigger a hierarchical response strategy, and closed-loop management from risk identification to planning adjustment is realized.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of engineering construction, in particular to a basic construction project management system based on big data. BACKGROUND

[0002] In the field of engineering construction, the construction process involves multidimensional data interaction and complex risk control, and the traditional management mode faces significant challenges. In the prior art, engineering project data exists in independent modalities such as BIM models, sensor monitoring, supply chain records, meteorological environment data and engineering logs, and the data formats are heterogeneous and the space-time benchmarks are not unified, resulting in prominent data island problems and difficulty in forming a global project state cognition. In addition, traditional risk prediction models are difficult to consider spatial feature extraction and time series dependence, and the model generalization ability is limited, resulting in lagging construction planning adjustment and inability to adapt to the dynamic changing engineering environment. With the increasing complexity of engineering, how to integrate multi-modal data, build high-precision prediction models and realize intelligent construction planning has become a technical problem that needs to be solved in the industry. SUMMARY

[0003] The purpose of the application is to solve the above problems, and a basic construction project management system based on big data is designed.

[0004] To achieve the above purpose, the technical scheme of the application is that, further, in the basic construction project management system based on big data, the basic construction project management system comprises the following modules:

[0005] An engineering data acquisition module is used to acquire multi-modal engineering project data in the system, including at least BIM model data, IoT sensor data, supply chain data, geographic and meteorological data and engineering log text;

[0006] A data preprocessing module is used to perform space-time alignment on the multi-modal engineering project data, process abnormal values in the aligned data to obtain complete engineering project data, and perform multi-modal fusion on the complete engineering project data to obtain fused engineering project data;

[0007] A data feature fusion module is used to construct a feature library of the fused engineering project data, including at least physical features, behavior features and derived features, to obtain feature engineering project data;

[0008] A risk model establishment module is used to establish a ResNet-Transformer risk prediction model, and use an IWOA improved whale optimization algorithm to optimize the hyperparameters of the model to obtain a target IWOA-ResNet-Transformer risk prediction model;

[0009] A project construction planning module is configured to input the feature engineering project data into the target IWOA-ResNet-Transformer risk prediction model to obtain a construction project state, and perform construction planning based on the construction project state.

[0010] Further, in the above-mentioned big data-based infrastructure engineering project management system, the engineering data collection module comprises the following sub-modules:

[0011] A BIM model data extraction sub-module is configured to extract geometric attribute data, material parameters, and construction process logical relationship data of building components.

[0012] An IoT sensor data collection sub-module is configured to collect environmental data, structural data, and equipment data, wherein the environmental data includes wind speed, temperature and humidity, and rainfall, the structural data includes concrete strain, tower crane inclination, and foundation settlement, and the equipment data includes excavator oil pressure and pump truck flow.

[0013] A supply chain data collection sub-module is configured to obtain material inventory data, transportation vehicle GPS trajectory, and supplier credit rating data.

[0014] A geographic and meteorological data acquisition sub-module is configured to obtain radar detection result data, future 72-hour wind speed probability distribution, and tide table.

[0015] Further, in the above-mentioned big data-based infrastructure engineering project management system, the data preprocessing module comprises the following sub-modules:

[0016] A space-time alignment sub-module is configured to synchronize the equipment clock in the multi-modal engineering project data by using a DTW dynamic time warping algorithm, convert the BIM model coordinate system into a WGS84 geographic coordinate system, match the sensor data space, and obtain aligned engineering project data.

[0017] An outlier sub-module is configured to detect sensor abnormal data of the aligned engineering project data by using a 3σ principle, identify faults in mechanical record text data in the data by using an LSTM neural network, delete the abnormal values and fault data, and obtain complete engineering project data.

[0018] A data fusion sub-module is configured to associate BIM components, sensor readings, and construction logs by using timestamps and projects as key values to establish a unified space-time index, embed unstructured text into a 128-dimensional vector by using a GraphSAGE algorithm, and input the sensor numerical data and the 128-dimensional vector into a graph neural network to obtain fused engineering project data.

[0019] Further, in the above-mentioned big data-based infrastructure engineering project management system, the data feature fusion module comprises the following sub-modules:

[0020] A construction sub-module is configured to construct a feature library of the fusion engineering project data, extract physical features in the fusion engineering project data through an improved Arrhenius equation, and the calculation formula is as follows:

[0021] ;

[0022] wherein, represents a material property constant in the engineering project, represents a hydration reaction activation energy, represents an ideal gas constant, represents time a real-time temperature, represents a correction term, represents the influence value of curing temperature and time on strength;

[0023] An index sub-module is configured to obtain dynamic indexes reflecting the interactive behavior of people, machines and materials in the construction process in the fusion engineering project data based on process network topology and real-time progress calculation, and obtain behavior features.

[0024] An acquisition sub-module is configured to obtain supply chain resilience indexes and space-time correlation features by calculating the fusion engineering project data, and obtain derived features.

[0025] A calculation sub-module is configured to use a sliding window method to perform stream calculation on the physical features, behavior features and derived features, and obtain feature engineering project data.

[0026] Further, in the above-mentioned big data-based infrastructure engineering project management system, the risk model establishment module comprises the following sub-modules:

[0027] An establishment sub-module is configured to establish a ResNet-Transformer risk prediction model, obtain historical engineering project data in the feature library, and map physical features, behavior features and derived features in the historical engineering project data to high-dimensional vectors through an input layer of the model ;

[0028] ;

[0029] wherein, represents a feature splicing operation, represents a learnable embedding matrix for mapping the spliced features to a high-dimensional space; , represents physical features, behavior features and derived features in the historical engineering project data; Indicates the bias term;

[0030] The residual submodule is used to extract local spatiotemporal patterns using ResNet residual blocks in the ResNet-Transformer risk prediction model.

[0031] ;

[0032] in, Residual functions containing Conv1D convolutional layers and activation functions, Indicates the th ResNet residual block Layer output; Representing the residual function The weight parameters included;

[0033] The capture submodule is used to capture long-range dependencies between features using Multi-Head Attention in the Transformer encoding layer of the ResNet-Transformer risk prediction model.

[0034] ;

[0035] in, Indicates a causal mask. Represents the query vector. Represents the key vector. Represents a value vector; Represents the key vector The dimension used to scale the dot product. ;

[0036] The enhancement submodule is used to enhance the nonlinearity during data training based on the FFN feedforward network in the model:

[0037] ;

[0038] in, This represents the input to the FFN feedforward network. This represents the weight matrix, which participates in two linear transformations. and This represents the bias term, which adds an offset to the model in each of the two linear transformations; This represents the activation function, which introduces nonlinear characteristics into the model.

[0039] Furthermore, in the aforementioned infrastructure project management system based on big data, the risk model establishment module includes the following units:

[0040] The population generation unit is used to optimize the hyperparameters of the model using the improved whale optimization algorithm of IWOA. It randomly generates a whale population, where each individual in the whale population represents a set of model hyperparameter combinations and a pre-trained ResNet-Transformer model skeleton.

[0041] The loss function computation unit is used to compute the loss function of each hyperparameter combination, including at least the number of Transformer heads, the number of residual block layers, the learning rate, and the batch size, on the validation set. ;

[0042] ;

[0043] in, Represents the cross-entropy loss in binary classification. Indicates task weight, Represents the L2 regularization coefficient. This represents the combination of model hyperparameters. Indicates the calculation of the first Real labels in each task With predictive labels The differences between them represents the squared L2 norm of the model hyperparameter combination;

[0044] The model fine-tuning unit is used to update the whale's position according to the IWOA rules, retain the historical best solution, and trigger Cauchy mutation if the best fitness does not improve for 10 consecutive generations. The model is fine-tuned by selecting the hyperparameter combination with the highest fitness to obtain the target IWOA-ResNet-Transformer risk prediction model.

[0045] Furthermore, in the aforementioned infrastructure project management system based on big data, the project construction planning module includes the following units:

[0046] The indicator prediction unit is used to input the characteristic engineering project data into the target IWOA-ResNet-Transformer risk prediction model for prediction, and obtain multi-dimensional status indicators of the construction project, including at least risk level, status parameters and trend prediction.

[0047] The status judgment unit is used to integrate the risk level, status parameters and trend predictions output by the model to obtain a project status report. According to the engineering management standards, the project status is divided into three levels: normal status, early warning status and emergency status.

[0048] The construction planning unit is used to plan construction based on the project status. If it is in an early warning state, it assesses available resources and adjusts the priority of local processes. If it is in an emergency state, it suspends regional construction and recalculates the BIM model.

[0049] Further, the method for implementing the above-mentioned infrastructure construction project management system based on big data comprises the following steps:

[0050] Obtaining multi-modal engineering project data in the system, including at least BIM model data, IoT sensor data, supply chain data, geographic and meteorological data, and engineering log text;

[0051] Performing spatio-temporal alignment on the multi-modal engineering project data, processing abnormal values in the aligned data to obtain complete engineering project data, and performing multi-modal fusion on the complete engineering project data to obtain fused engineering project data;

[0052] Constructing a feature library of the fused engineering project data, including at least physical features, behavior features, and derived features, to obtain feature engineering project data;

[0053] Establishing a ResNet-Transformer risk prediction model, optimizing the hyperparameters of the model using an improved whale optimization algorithm (IWOA), and obtaining a target IWOA-ResNet-Transformer risk prediction model;

[0054] Inputting the feature engineering project data into the target IWOA-ResNet-Transformer risk prediction model for prediction to obtain the state of the construction project, and performing construction planning based on the state of the construction project.

[0055] Further, in the above-mentioned infrastructure construction project management method based on big data, the method comprises the following steps:

[0056] Extracting geometric property data, material parameters, and construction process logical relationship data of building components;

[0057] Collecting environmental data, structural data, and equipment data, the environmental data including wind speed, temperature and humidity, and rainfall, the structural data including concrete strain, tower crane inclination, and foundation settlement, and the equipment data including excavator oil pressure and pump truck flow;

[0058] Obtaining material inventory data, transportation vehicle GPS trajectory, and supplier credit rating data;

[0059] Obtaining radar detection result data, 72-hour future wind speed probability distribution, and tide table.

[0060] Further, in the above-mentioned infrastructure construction project management method based on big data, the voice data in the real-time environment is obtained through a microphone array, comprising:

[0061] Synchronize the equipment clock in the multi-modal engineering project data by the DTW dynamic time warping algorithm, convert the BIM model coordinate system to the WGS84 geographic coordinate system, match the sensor data space, and obtain aligned engineering project data;

[0062] Detect the sensor abnormal data of the aligned engineering project data by the 3σ principle, identify the mechanical record text data in the data by the LSTM neural network, delete the abnormal values and fault data, and obtain complete engineering project data;

[0063] Establish a unified space-time index by associating the BIM components, sensor readings, and construction logs with timestamps and project keys, embed the unstructured text into a 128-dimensional vector by the GraphSAGE algorithm, and input the sensor numerical data into the graph neural network together, to obtain fusion engineering project data.

[0064] The beneficial effects are that through space-time alignment and abnormal value processing, the heterogeneous BIM model, sensor, supply chain, and other data are unified into a standardized framework, solving the data island problem and providing a high-quality data foundation. A comprehensive feature library containing physical, behavioral, and derived features is constructed, and the ResNet-Transformer model can extract spatial dimension structure features through ResNet and capture time dimension process connection rules through Transformer, realizing multi-scale characterization of engineering status. The IWOA improved whale optimization algorithm is introduced to further improve the model hyperparameter search efficiency, and compared with traditional optimization methods, the prediction accuracy is improved. The hierarchical response strategy can be automatically triggered to realize closed-loop management from risk identification to planning adjustment. The dependence on artificial experience is reduced, and the management efficiency and refinement level are improved. Real-time access of engineering logs and sensor data and model iterative optimization enable the system to have self-learning ability and adapt to different project complex scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0065] Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments with reference made to the accompanying drawings. The drawings are for purposes of illustration only and are not considered a limitation of the present application.

[0066] Figure 1 The first embodiment of the infrastructure engineering project management system based on big data in the embodiments of the present application is shown in the schematic diagram.

[0067] Figure 2 The second embodiment of the infrastructure engineering project management system based on big data in the embodiments of the present application is shown in the schematic diagram.

[0068] Figure 3The third embodiment of the infrastructure engineering project management system based on big data in the embodiments of the present application is shown. DETAILED DESCRIPTION

[0069] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0070] It can be understood by those skilled in the art that the singular form "a", "an" and "the" used herein can include the plural form, unless specifically stated otherwise. It should be further understood that the use of the word "comprise" in the specification of the present application means that the features, integers, steps, operations, elements and / or components exist, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0071] The present application will be described in detail below in combination with the drawings, as shown in Figure 1 The infrastructure engineering project management system based on big data includes the following modules:

[0072] 101, an engineering data acquisition module for acquiring multi-modal engineering project data in the system, including at least BIM model data, IoT sensor data, supply chain data, geographic and meteorological data, and engineering log text;

[0073] Specifically, the present embodiment further includes a BIM model data extraction submodule for extracting geometric property data, material parameters and construction process logical relationship data of building components;

[0074] An IoT sensor data acquisition submodule for collecting environmental data, structural data and equipment data, the environmental data including wind speed, temperature and humidity and rainfall, the structural data including concrete strain, tower crane inclination and foundation settlement, and the equipment data including excavator oil pressure and pump truck flow;

[0075] A supply chain data acquisition submodule for acquiring material inventory data, transportation vehicle GPS trajectory and supplier credit rating data;

[0076] A geographic and meteorological data acquisition submodule for acquiring radar detection result data, future 72-hour wind speed probability distribution and tide table.

[0077] 102, a data preprocessing module for spatio-temporal alignment of multi-modal engineering project data, processing outliers in the aligned data to obtain complete engineering project data, and multi-modal fusion of the complete engineering project data to obtain fused engineering project data;

[0078] Specifically, the embodiment further includes a space-time alignment submodule for synchronizing the equipment clock in the multi-modal engineering project data through the DTW dynamic time warping algorithm, converting the BIM model coordinate system to the WGS84 geographic coordinate system, matching the sensor data space, and obtaining aligned engineering project data.

[0079] An outlier submodule is configured to detect sensor abnormal data of the aligned engineering project data using the 3σ principle, and identify faults in mechanical record text data in the data using an LSTM neural network, delete the outliers and fault data, and obtain complete engineering project data.

[0080] A data fusion submodule is configured to associate BIM components, sensor readings, and construction logs by time stamp and project as key values, establish a unified space-time index, embed unstructured text into a 128-dimensional vector using a GraphSAGE algorithm, and input the sensor numerical data into a graph neural network together, to obtain fused engineering project data.

[0081] 103. A data feature fusion module is configured to construct a feature library of the fused engineering project data, including at least physical features, behavior features, and derived features, to obtain feature engineering project data.

[0082] Specifically, the embodiment further includes a construction submodule configured to construct a feature library of the fused engineering project data, extract physical features in the fused engineering project data through an improved Arrhenius equation, and the calculation formula is as follows:

[0083] ;

[0084] wherein, represents a material property constant in the engineering project, represents a hydration reaction activation energy, represents an ideal gas constant, represents time real-time temperature, represents a correction term, represents the influence value of curing temperature and time on strength;

[0085] An index submodule is configured to calculate based on the process network topology and real-time progress, obtain dynamic indexes reflecting the interaction behavior of people, machines, and materials in the construction process in the fused engineering project data, and obtain behavior features.

[0086] An acquisition submodule is configured to calculate the supply chain resilience index and space-time correlation features by calculating the fused engineering project data, and obtain derived features.

[0087] The computation submodule is used to perform streaming computation on physical features, behavioral features, and derived features using the sliding window method to obtain feature engineering project data.

[0088] 104. Risk Model Building Module: This module is used to build a ResNet-Transformer risk prediction model. It optimizes the hyperparameters of the model using the improved whale optimization algorithm of IWOA to obtain the target IWOA-ResNet-Transformer risk prediction model.

[0089] Specifically, this implementation also includes establishing a submodule for building a ResNet-Transformer risk prediction model, acquiring historical engineering project data from the feature library, and using the model's input layer to map the physical features, behavioral features, and derived features from the historical engineering project data into high-dimensional vectors. ;

[0090] ;

[0091] in, This indicates a feature concatenation operation. This represents a learnable embedding matrix, used to map the concatenated features to a high-dimensional space; , This represents the physical, behavioral, and derived characteristics of historical engineering project data. Indicates the bias term;

[0092] The residual submodule is used to extract local spatiotemporal patterns using ResNet residual blocks in the ResNet-Transformer risk prediction model.

[0093] ;

[0094] in, Residual functions containing Conv1D convolutional layers and activation functions, Indicates the th ResNet residual block Layer output; Representing the residual function The weight parameters included;

[0095] The capture submodule is used to capture long-range dependencies between features using Multi-Head Attention in the Transformer encoding layer of the ResNet-Transformer risk prediction model.

[0096] ;

[0097] in, Indicates a causal mask. denotes a query vector, denotes a key vector, denotes a value vector; denotes a key vector dimension, used to scale dot product ;

[0098] enhancement module, for enhancing the nonlinearity in the data training process based on the FFN feedforward network in the model:

[0099] ;

[0100] wherein, denotes the input of the FFN feedforward network, denotes the weight matrix participating in the two linear transformations; and denote the bias terms, which respectively increase the offset of the model in the two linear transformations; denotes the activation function, which introduces the nonlinearity of the model.

[0101] population generation unit, for optimizing the hyperparameters of the model by using the improved whale optimization algorithm of IWOA, randomly generating a whale population, wherein each individual of the whale population represents a combination of model hyperparameters, and pre-training the ResNet-Transformer model skeleton;

[0102] loss function calculation unit, for calculating the loss function of each hyperparameter combination, including at least the number of Transformer heads, the number of residual blocks, the learning rate and the batch size, on the validation set ;

[0103] ;

[0104] wherein, denotes the binary cross-entropy loss, denotes the task weight, denotes the L2 regularization coefficient, denotes the model hyperparameter combination, denotes the difference between the true label and the predicted label in the first task, denotes the square of the L2 norm of the model hyperparameter combination;

[0105] The model fine-tuning unit is used to update the whale's position according to the IWOA rules, retain the historical best solution, and trigger Cauchy mutation if the best fitness does not improve for 10 consecutive generations. The model is fine-tuned by selecting the hyperparameter combination with the highest fitness to obtain the target IWOA-ResNet-Transformer risk prediction model.

[0106] Improving the whale optimization algorithm involves enhancing hyperparameter search efficiency and avoiding getting trapped in local optima. The improved strategies include: 1. Dynamically adjusting the search step size and using an adaptive inertia weight adjustment strategy to balance global exploration and local development; 2. Applying Cauchy perturbation to the optimal solution and using a Cauchy mutation strategy to enhance the ability to escape local optima; 3. Introducing a dynamic spiral encirclement mechanism with inertia weights and mutation factors when updating the whale position.

[0107] The improved strategy also includes optimizing the objective function with hyperparameters to minimize multi-task prediction error and model complexity.

[0108] 105. Project construction planning module, used to input characteristic engineering project data into the target IWOA-ResNet-Transformer risk prediction model for prediction, obtain the construction project status, and carry out construction planning based on the construction project status.

[0109] Specifically, this implementation also includes,

[0110] The indicator prediction unit is used to input the characteristic engineering project data into the target IWOA-ResNet-Transformer risk prediction model for prediction, and obtain multi-dimensional status indicators of the construction project, including at least risk level, status parameters and trend prediction.

[0111] The status judgment unit is used to integrate the risk level, status parameters and trend predictions output by the model to obtain a project status report. According to the engineering management standards, the project status is divided into three levels: normal status, early warning status and emergency status.

[0112] The construction planning unit is used to plan construction based on the project status. If it is in an early warning state, it assesses the available resources and adjusts the priority of local processes. If it is in an emergency state, it suspends construction in the area and recalculates the BIM model.

[0113] I. Status Analysis and Classification of Construction Projects

[0114] Multi-dimensional status integration: The risk level, key parameters, trend predictions and other information output by the model are integrated into an intuitive status report. For example, the risk heat map, progress Gantt chart deviation, resource supply and demand balance table of each construction area can be displayed through the dashboard.

[0115] State Classification and Early Warning: Based on engineering management standards, project status is classified into three levels:

[0116] Normal State: All key indicators are within the preset threshold (e.g., progress deviation ≤ 5%, safety risk score < 60 points), no significant abnormal trend;

[0117] Early Warning State: Some indicators are close to or exceed the threshold (e.g., progress deviation 5%-15%, equipment failure rate ≥ 10%), which needs to be focused on;

[0118] Emergency State: Key indicators are severely over-standard (e.g., progress deviation > 15%, safety risk score ≥ 80 points), or the trend shows that the risk may deteriorate rapidly.

[0119] Abnormal State Localization: For early warning or emergency state, through the feature library, the specific abnormal source is traced back (e.g., the BIM model of a certain area shows that the structure design conflicts with the on-site IoT sensor data, the supply chain data shows that a certain material supplier delays delivery), and the link where the problem occurs (design, construction, supply, environment, etc.) is determined.

[0120] II. State-based Construction Planning Adjustment

[0121] Developing Preliminary Adjustment Plan: According to the project state classification, the engineering management team develops targeted measures:

[0122] Normal State: Maintain the existing construction plan and strengthen daily monitoring (e.g., increase the frequency of engineering log recording, regularly calibrate sensor data).

[0123] Early Warning State:

[0124] For progress lag: Evaluate deployable resources (e.g., increase construction teams, extend work time), adjust local process priorities (e.g., prioritize tasks on the critical path);

[0125] For safety risks: Increase on-site inspection frequency, and add temporary protective measures in high-risk areas (e.g., deep foundation pits, high-altitude work areas);

[0126] For resource shortage: Start the alternative supplier procurement process, and stockpile easily short materials in advance (e.g., based on geographic and meteorological data, predict that heavy rain may affect transportation, and stockpile cement in advance).

[0127] Emergency State:

[0128] Suspend high-risk operations: Immediately stop work and investigate the problem (e.g., find structural stress anomalies, suspend construction in the area and recalculate the BIM model);

[0129] Reorganize resource allocation: Call on emergency plan reserve resources (e.g., activate standby equipment, coordinate with idle manpower from other projects);

[0130] Adjust the overall plan: Communicate with the owner and supervision unit to revise the construction schedule (if the progress is seriously delayed due to extreme weather, apply for an extension of the construction period or shorten the time for non-critical tasks).

[0131] Feasibility assessment: A multidisciplinary team, including design, construction, materials, and safety professionals, will review the proposed adjustments, focusing on verifying the following:

[0132] Technical feasibility (e.g., whether the adjusted procedures comply with specifications, whether the BIM model supports the new design);

[0133] Resource matching (whether existing inventory / supply chain can meet new demand, and whether there are conflicts in personnel and equipment scheduling);

[0134] Impact on cost and schedule (whether the additional costs of implementing the solution are within budget, and whether the schedule adjustment meets the contract requirements).

[0135] Approval and Release of the Plan: The approved plan will be submitted to the project leader for approval. After approval, it will be issued to each construction team in the form of an official document (such as a construction liaison form or a schedule adjustment plan), which will specify the adjustment content, responsible persons and time nodes (such as "Section 3 needs to complete the procurement of spare materials within 48 hours and add 20 construction workers within 5 days").

[0136] III. Construction Planning Implementation and Dynamic Monitoring

[0137] Implementation of the adjustment plan: Each responsible party shall implement the adjustment measures according to the plan (such as the materials department purchasing materials, the safety department adding protective facilities, and the construction team adjusting the work sequence), and record the actual implementation status (such as the material arrival time and the number of personnel on site) in the project log.

[0138] Real-time data feedback and model iteration:

[0139] Regularly (e.g., daily / weekly), input newly generated engineering logs, IoT sensor data, and supply chain update data into the model to verify whether the current status is improving in the expected direction (e.g., whether the schedule deviation has narrowed or the risk level has decreased).

[0140] If the adjusted status does not meet expectations (e.g., the warning status is not lifted for 3 consecutive days), re-analyze the model prediction results, investigate loopholes in the implementation of the plan (e.g., inadequate resource allocation, incomplete handling of abnormal data), and restart the planning adjustment process if necessary.

[0141] Document archiving and experience accumulation: The results of this status analysis, adjustment plan and execution effect will be entered into the project management system to form a historical case library, which will provide a reference for risk prediction and planning of similar projects in the future (such as supply chain risk response strategies under a certain type of geographical and meteorological data).

[0142] Its beneficial effects lie in unifying heterogeneous BIM models, sensor data, and supply chain data into a standardized framework through spatiotemporal alignment and outlier handling, thus solving the data silo problem and providing a high-quality data foundation. A comprehensive feature library encompassing physical, behavioral, and derived features is constructed. Combined with the ResNet-Transformer model, it can extract spatial structural features through ResNet and capture temporal process connection patterns using Transformer, achieving multi-scale characterization of engineering status. The introduction of an improved IWOA whale optimization algorithm further enhances the model's hyperparameter search efficiency, improving prediction accuracy compared to traditional optimization methods. It can automatically trigger hierarchical response strategies, achieving closed-loop management from risk identification to planning adjustments. It reduces reliance on human experience, improving management efficiency and precision. Real-time access to engineering logs and sensor data, along with iterative model optimization, enables the system to learn independently and adapt to complex scenarios in different projects.

[0143] In this embodiment, please refer to Figure 2 The second embodiment of the infrastructure project management system based on big data in this invention includes a data feature fusion module comprising the following sub-modules:

[0144] The construction submodule is used to build a feature library of integrated engineering project data. The physical features in the integrated engineering project data are extracted through the improved Arrhenius equation. The calculation formula is as follows;

[0145]

[0146] in, Represents the material property constants in an engineering project. Indicates the activation energy of the hydration reaction. Represents the ideal gas constant. Indicates time Real-time temperature, Indicates a correction term. This indicates the effect of curing temperature and time on strength.

[0147] The indicator submodule is used to obtain dynamic indicators reflecting the interaction behavior of people, machines and materials during the construction process from the integrated engineering project data based on the process network topology and real-time progress calculation, and to obtain behavioral characteristics.

[0148] The acquisition submodule is used to calculate supply chain resilience indicators and spatiotemporal correlation characteristics by integrating engineering project data, and obtain derived features.

[0149] The computation submodule is used to perform streaming computation on physical features, behavioral features, and derived features using the sliding window method to obtain feature engineering project data.

[0150] The beneficial effect is that, by spatiotemporal alignment and outlier processing, the heterogeneous BIM model, sensor, supply chain, etc. Data is unified to a standardized framework, solving the data island problem, forming a complete data set covering all elements of the project, and providing a high-quality data foundation for accurate analysis

[0151] In the embodiment, please refer to Figure 3 The third embodiment of the infrastructure construction project management system based on big data in the embodiment comprises the following sub-units:

[0152] The index prediction unit is configured to input the feature engineering project data into the target IWOA-ResNet-Transformer risk prediction model for prediction, and obtain multi-dimensional state indexes of the construction project, including at least risk level, state parameter and trend prediction.

[0153] The state judgment unit is configured to integrate the risk level, state parameter and trend prediction output by the model to obtain a project state report, and divide the project state into three levels according to the engineering management standard, to obtain a normal state, a warning state and an emergency state.

[0154] The construction planning unit is configured to plan construction based on the project state, if the state is a warning state, the system can adjust the resource allocation and adjust the local process priority, if the state is an emergency state, the system can suspend the regional construction and recalculate the BIM model.

[0155] The beneficial effect is that, based on the real-time predicted project state (such as progress deviation, resource shortage risk level), the system can automatically trigger a hierarchical response strategy (such as adjusting the process priority, starting the standby supply chain), realizing the closed-loop management from risk identification to planning adjustment. When the model predicts that the rainstorm may cause material transportation delay, the inventory resources can be allocated in advance and the construction sequence can be optimized.

[0156] The basic principles, main features and advantages of the present application are shown and described above. Those skilled in the art should understand that the present application is not limited to the above embodiments, and the above embodiments and descriptions in the specification are only preferred examples of the present application and are not intended to limit the present application. Without departing from the spirit and scope of the present application, various modifications and improvements can be made to the present application, and these modifications and improvements all fall within the scope of the present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A big data based infrastructure project management system characterized in that, The infrastructure engineering project management system comprises the following modules: An engineering data acquisition module for acquiring multi-modal engineering project data in the system, at least comprising BIM model data, IoT sensor data, supply chain data, geographic meteorological data and engineering log text; A data preprocessing module for spatiotemporal alignment of the multi-modal engineering project data, processing abnormal values in the aligned data to obtain complete engineering project data, and performing multi-modal fusion on the complete engineering project data to obtain fused engineering project data; A data feature fusion module for constructing a feature library of the fused engineering project data, at least comprising physical features, behavior features and derived features, to obtain feature engineering project data; The data feature fusion module comprises the following sub-modules: A construction sub-module for constructing the feature library of the fused engineering project data, and extracting physical features in the fused engineering project data by an improved Arrhenius equation; An index sub-module for calculating dynamic indexes reflecting the interaction behavior of people, machines and materials in the construction process based on process network topology and real-time progress, to obtain behavior features; An acquisition sub-module for acquiring supply chain resilience indexes and spatiotemporal correlation features by calculating the fused engineering project data, to obtain derived features; A calculation sub-module for performing stream computing on the physical features, behavior features and derived features by a sliding window method, to obtain feature engineering project data; A risk model establishment module for establishing a ResNet-Transformer risk prediction model, optimizing the hyperparameters of the model by an IWOA improved whale optimization algorithm, and obtaining a target IWOA-ResNet-Transformer risk prediction model; The risk model establishment module comprises the following units: A population generation unit for optimizing the hyperparameters of the model by the IWOA improved whale optimization algorithm, randomly generating a whale population, wherein each individual of the whale population represents a combination of model hyperparameters, and a pre-trained ResNet-Transformer model skeleton; A loss function calculation unit for calculating the loss function of each hyperparameter combination on a validation set; A model fine-tuning unit for updating the whale position according to the IWOA rules, retaining the historical optimal solution, triggering Cauchy mutation if the optimal fitness is not improved for 10 consecutive generations, fine-tuning the model with the hyperparameter combination having the highest fitness, and obtaining the target IWOA-ResNet-Transformer risk prediction model; A project construction planning module for inputting the feature engineering project data into the target IWOA-ResNet-Transformer risk prediction model for prediction, obtaining a construction engineering project state, and planning construction based on the construction engineering project state.

2. The big data based infrastructure project management system as claimed in claim 1 wherein, The engineering data acquisition module comprises the following sub-modules: A BIM model data extraction sub-module for extracting geometric attribute data, material parameters and construction process logic relationship data of building components; IoT sensor data collection sub-module, used for collecting environmental data, structural data and equipment data; Supply chain data collection sub-module, used for obtaining material inventory data, transportation vehicle GPS trajectory and supplier credit rating data; Geographical and meteorological data acquisition sub-module, used for acquiring radar detection result data, future 72-hour wind speed probability distribution and tide table.

3. The big data based infrastructure project management system as claimed in claim 1 wherein, The data preprocessing module comprises the following sub-modules: Space-time alignment sub-module, used for synchronizing the equipment clock in the multi-modal engineering project data by a DTW dynamic time warping algorithm, converting the BIM model coordinate system into a WGS84 geographical coordinate system, matching the sensor data space, and obtaining aligned engineering project data; Outlier sub-module, used for detecting sensor abnormal data of the aligned engineering project data by a 3σ principle, and identifying faults in mechanical record text data in the data by an LSTM neural network, deleting the outliers and fault data, and obtaining complete engineering project data; Data fusion sub-module, used for associating BIM components, sensor readings and construction logs by time stamp and project as key values to establish a unified space-time index, embedding unstructured text into a 128-dimensional vector by a GraphSAGE algorithm, and inputting the sensor numerical data into a graph neural network together, to obtain fused engineering project data.

4. The big data based infrastructure project management system as claimed in claim 1 wherein, The risk model establishment module comprises the following sub-modules: Establishment sub-module, used for establishing a ResNet-Transformer risk prediction model, obtaining historical engineering project data in a feature library, and mapping physical features, behavioral features and derived features in the historical engineering project data into high-dimensional vectors by an input layer of the model; Residual sub-module, used for extracting local space-time patterns by a ResNet residual block in the ResNet-Transformer risk prediction model; Capture sub-module, used for capturing long-range dependencies between features by Multi-HeadAttention multi-head self-attention in the Transformer encoding layer in the ResNet-Transformer risk prediction model; Enhancement sub-module, used for enhancing nonlinearity in the data training process based on an FFN feedforward network in the model.

5. The big data based infrastructure project management system as claimed in claim 1 wherein, The project construction planning module comprises the following units: Index prediction unit, used for inputting the feature engineering project data into the target IWOA-ResNet-Transformer risk prediction model for prediction, to obtain multi-dimensional state indexes of the construction project, including at least risk level, state parameter and trend prediction; State judgment unit, used for integrating the risk level, state parameter and trend prediction output by the model to obtain a project state report, dividing the project state into three levels according to engineering management standards to obtain a normal state, a warning state and an emergency state; Construction planning unit, used for planning construction based on the project state, evaluating allocatable resources and adjusting local process priorities if the state is a warning state, or suspending regional construction and recalculating the BIM model if the state is an emergency state.

6. The method of implementing the big data based infrastructure project management system as claimed in claim 1, wherein, The method comprises the following steps: Obtaining multi-modal engineering project data in a system, including at least BIM model data, IoT sensor data, supply chain data, geographic and meteorological data, and engineering log text; Temporal and spatial alignment of the multi-modal engineering project data, processing of abnormal values in the aligned data to obtain complete engineering project data, multi-modal fusion of the complete engineering project data to obtain fused engineering project data; Building a feature library of the fused engineering project data, including at least physical features, behavior features, and derived features, to obtain feature engineering project data; Establishing a ResNet-Transformer risk prediction model, optimizing the hyperparameters of the model using an IWOA improved whale optimization algorithm to obtain a target IWOA-ResNet-Transformer risk prediction model; Inputting the feature engineering project data into the target IWOA-ResNet-Transformer risk prediction model for prediction to obtain construction engineering project status, and conducting construction planning based on the construction engineering project status.

7. The method of implementing the big data based infrastructure project management system as claimed in claim 6, wherein, The method comprises the following steps: Extracting geometric attribute data, material parameters, and construction process logical relationship data of building components; Collecting environmental data, structural data, and equipment data, the environmental data including wind speed, temperature and humidity, and rainfall, the structural data including concrete strain, tower crane inclination, and foundation settlement, and the equipment data including excavator oil pressure and pump truck flow; Obtaining material inventory data, transportation vehicle GPS trajectory, and supplier credit rating data; Obtaining radar detection result data, 72-hour future wind speed probability distribution, and tide table.

8. The method of implementing the big data based infrastructure project management system as claimed in claim 7, wherein, The method comprises the following steps: Synchronizing equipment clocks in the multi-modal engineering project data by a DTW dynamic time warping algorithm, converting BIM model coordinate systems to WGS84 geographic coordinate systems, and matching sensor data in space to obtain aligned engineering project data; Detecting sensor abnormal data of the aligned engineering project data using a 3σ principle, and identifying mechanical record text data faults using an LSTM neural network, deleting abnormal values and fault data to obtain complete engineering project data; Associating BIM components, sensor readings, and construction logs by timestamps and projects as key values to establish a unified spatio-temporal index, embedding unstructured text into 128-dimensional vectors using a GraphSAGE algorithm, and inputting the sensor numerical data into a graph neural network to obtain fused engineering project data.

Images