BIM-based transportation engineering construction progress and resource management optimization system

Abstract

This invention discloses a BIM-based transportation engineering construction progress and resource management optimization system. The system includes a three-dimensional cognitive interactive body that adjusts construction progress and resource allocation in real time, eliminating physical differences between the virtual model and the actual environment; an adaptive computing engine that uses real-time perception data and a cognitive correction mechanism to connect the virtual model with the actual construction site; a progress prediction simulation module that uses deep learning and an adaptive feedback mechanism to dynamically predict and optimize the construction progress; a virtual-reality synchronized perception grid that is constructed based on the obtained dynamic progress prediction and optimization results, and synchronizes and dynamically corrects the virtual model and the construction site; and a self-optimization module that uses self-optimization and ecological optimization mechanisms, genetic algorithms, and multi-objective optimization to achieve adaptive optimization and long-term evolution. This invention solves the problem of virtual reality distortion, allowing for precise correction of differences between virtual and real life during construction.

Description

Technical Field

[0001] The present invention relates to the technical field of BIM optimization, and in particular to a BIM-based transportation engineering construction progress and resource management optimization system. Background Art

[0002] With the rapid development of information technology, Building Information Modeling (BIM) has become a key technology in building and infrastructure project management. BIM not only provides 3D visualizations of project phases but also integrates a wide range of project data, including timelines, costs, and resource allocation, helping project teams make more efficient and accurate decisions across design, construction, and operations. In the transportation engineering sector, the application of BIM technology is gradually transforming traditional construction management models, demonstrating significant potential in optimizing construction schedules and resource management.

[0003] However, transportation engineering construction has complex task characteristics and a dynamic external environment. Traditional BIM technology faces many challenges when dealing with construction progress and resource management. For example, transportation engineering involves numerous construction tasks with long construction cycles, a complex and changing construction environment, and a wide variety of resources with close dependencies. In addition, the construction process may be disrupted by factors such as weather changes and emergencies, which can lead to deviations in construction progress and resources, bringing additional difficulties to project management. To meet these challenges, more and more research has begun to focus on how to improve construction accuracy and efficiency and reduce delays and cost overruns through BIM-based construction progress prediction and resource optimization management.

[0004] In this process, the integration of BIM with other advanced technologies, such as the Internet of Things (IoT), big data analytics, artificial intelligence (AI), and virtual reality (VR), provides more intelligent, data-driven solutions. For example, BIM models based on real-time data can help managers accurately understand the real-time status of the construction site and automatically adjust resource allocation and schedules. With the support of VR technology, construction teams can rehearse the construction process in a virtual environment, conduct risk assessments, and make optimization adjustments, thereby reducing errors and uncontrollable factors in actual construction.

[0005] However, the integration of virtual reality technology and BIM, particularly in the construction of large-scale transportation projects, presents a prominent problem: virtual reality distortion. Specifically, as BIM models become more sophisticated, more and more physical behaviors (such as mechanics, fluid dynamics, and thermodynamics) are incorporated into the simulation system to more accurately simulate the real-world conditions of the construction site. However, during this process, significant differences can exist between the physical behaviors in the virtual model and the physical conditions in actual construction. For example, the construction process can be affected by a variety of factors, such as ambient temperature and humidity, soil properties, and the performance of construction equipment. These factors have complex effects on construction progress and resource allocation, and simple geometric models cannot effectively simulate these factors.

[0006] Current simulation engines primarily rely on geometric data and engineering design parameters for calculations, often neglecting the deep integration of physical states and dynamic environmental changes. This leads to discrepancies between simulation results and the actual construction environment. This discrepancy is particularly pronounced in large-scale, multi-layered, and multi-factorial construction environments. This issue not only hinders accurate predictions of construction progress but also makes it difficult to fully validate and optimize resource management solutions in real-world applications. Therefore, how to accurately simulate and correct these discrepancies without sacrificing computing performance has become a core issue that needs to be addressed in the current deep integration of BIM and VR technologies.

[0007] This challenge challenges the limits of existing simulation engines. In complex construction environments, virtual models must not only accurately represent building geometry but also simulate the changes in physical behavior during construction, ensuring a high degree of consistency between these changes and the actual conditions on the construction site. This places extremely high demands on the system's computing performance, data processing capabilities, and real-time update mechanisms. Therefore, exploring new optimization methods to address the physical discrepancies between virtual and real life has become a major technical challenge in the application of BIM in transportation engineering. Summary of the Invention

[0008] In order to solve the problem of virtual reality distortion, the present invention provides a BIM-based transportation engineering construction progress and resource management optimization system.

[0009] To achieve the above object, the technical solutions adopted by the present invention are as follows:

[0010] A three-dimensional cognitive interactive body adjusts construction progress and resource allocation in real time through adaptive feedback from the perception layer, cognitive decision-making layer, collaborative decision-making mechanism, and resource scheduling, eliminating the physical differences between the virtual model and the actual environment;

[0011] Adaptive computing engine, using real-time perception data and cognitive correction mechanism to achieve the connection between virtual model and actual construction site;

[0012] The progress prediction simulation module uses deep learning and adaptive feedback mechanisms to achieve dynamic prediction and optimization of construction progress, providing decision support for progress management;

[0013] A virtual-reality synchronous perception grid is constructed based on the obtained progress dynamic prediction and optimization results, and the virtual model of the internship is synchronized and dynamically corrected with the construction site;

[0014] Self-optimization module: Utilizes self-optimization and ecological optimization mechanisms, through genetic algorithms and multi-objective optimization, to achieve adaptive optimization and long-term evolution.

[0015] Further: the three-dimensional cognitive interactive body includes:

[0016] The perception layer combines environmental data collected by multiple sensors to build an instant 3D state model of the construction site. Through sensor input, the actual situation of the construction site is fed back to the 3D cognitive interaction body in real time, forming a real-time perception data stream.

[0017] The cognitive decision-making layer introduces nonlinear optimization and feedback control to dynamically adjust the execution path of construction tasks. When the construction progress deviates from expectations, a nonlinear least squares algorithm is used to make corrections and calculate the optimal path adjustment. The optimization goal is to minimize the time and resource consumption of the construction task:

[0018]

[0019] in, represents the optimization path, is the task execution function on the path, is the desired target state;

[0020] Through multiple rounds of cognitive feedback on the construction process, the three-dimensional cognitive interactive body can self-adjust. Each execution of a construction task returns a feedback signal to the cognitive decision-making layer. Reinforcement learning is then introduced. Reinforcement learning enables each correction to further optimize its decision-making ability based on historical feedback. Finally, the probability of each decision is updated through the Bayesian update rule, and the optimal action plan is derived in real time.

[0021] A collaborative decision-making mechanism introduces a game theory model to simulate the strategic choices of multiple three-dimensional cognitive interactors in resource competition and coordinate the behaviors of each three-dimensional cognitive interactor.

[0022] Adaptive feedback for resource scheduling is formulated as a multi-objective optimization problem, where the optimization goal is to minimize resource consumption and construction time:

[0023]

[0024] in, For resource allocation plan, It is The time consumption of a task, It is The consumption of resources, and is the weighting factor.

[0025] Further: the adaptive computing engine includes:

[0026] Real-time perception data processing module: extracts meaningful environmental features and change patterns from the data obtained from the perception layer, providing input for subsequent cognitive correction;

[0027] Cognitive Correction Decision Module: Based on perception data and historical behavior patterns, it uses an adaptive model correction method to correct the physical behavior in the virtual model to ensure a better match with the actual environment of the construction site;

[0028] Correction feedback and optimization module: Provides real-time feedback on the effects of model corrections and uses optimization algorithms to update correction strategies to gradually improve the consistency between virtual and reality.

[0029] Further: the progress prediction simulation module includes:

[0030] The brain-inspired neural network model has an input layer that includes real-time construction data and historical construction progress data, an output layer that predicts future construction progress, and an intermediate layer that processes and calculates progress decisions using a multi-layer neural network.

[0031] Input layer: real-time data ,in, Indicates at time The collected Item data;

[0032] Middle layer: Calculates dependencies between tasks through synaptic connections between neurons and adjusts progress predictions based on historical progress data and real-time feedback;

[0033] Output layer: Calculate the future construction progress forecast value through the activation function of the neural network;

[0034]

[0035] in, It's time Forecasted construction progress, is the weight of the input data, is the activation function;

[0036] By strengthening the correlation signal, the connection weights between neurons are updated. Assuming that the neurons and There is a certain synergistic relationship between the input and output of the neuron. The output activates the neuron , then the synaptic connection weight should increase, and the weight update formula is as follows:

[0037]

[0038] in, From neurons to neurons The synaptic connection weights, is the learning rate, It is Input data, It is The activation value of each output;

[0039] To further improve the accuracy of progress prediction, we combine Q-learning to make dynamic adjustments to maximize the expected future rewards:

[0040]

[0041] in, It is at the moment For an action and status The value function of is the learning rate, It’s an instant reward. is the discount factor;

[0042] Based on the progress forecast error and construction site feedback for each time period, the specific correction process is as follows:

[0043] Forecast error calculation:

[0044]

[0045] in, The actual construction progress. is the predicted construction progress, is the prediction error;

[0046] Based on the prediction error ,The weight parameters in the neural network are updated through the gradient descent method, and then the progress prediction model is adjusted;

[0047]

[0048] in, It is at the moment Adjusted weights, is the learning rate, is the gradient of the prediction error with respect to the weight;

[0049] Through the multi-task learning mechanism, the network can simultaneously predict the progress of multiple construction tasks and learn the interdependence between tasks.

[0050] Furthermore: the virtual-reality synchronization perception grid includes:

[0051] Virtual-to-reality data mapping module: This module is responsible for mapping and synchronously updating the physical parameters of the virtual model with the sensory data from the actual construction site. It dynamically adjusts the state of the virtual model based on on-site sensor data and historical construction progress data.

[0052] Real-time data acquisition and processing module: Based on the sensor network at the construction site, it collects multi-modal data in real time and converts the sensor network data into digital signals that can be connected to the virtual model through data fusion algorithms;

[0053] Synchronous control and feedback module: controls the update of the virtual model according to the differences between the virtual model and the real environment, and provides dynamic feedback on the behavior of the construction site based on the corrected virtual state.

[0054] Further: the self-optimization module includes:

[0055] The self-optimization mechanism introduced simulates the principles of natural selection and gene mutation in biological evolution, and combines the real-time feedback and learning mechanisms that occur during system operation to achieve continuous optimization of models and algorithms. The self-optimization mechanism includes:

[0056] Genetic Algorithm: Simulates the natural selection, crossover, and mutation processes in biological evolution to automatically optimize resource allocation, schedule prediction, and risk management during the construction process;

[0057] Reinforcement learning and adaptive optimization: Through interactive learning with the environment, we can optimize progress prediction and resource scheduling decisions to achieve long-term performance optimization;

[0058] A self-optimization cycle based on evolutionary selection, mutation, and adaptive feedback mechanisms. After each cycle, the optimization direction is adjusted based on real-time data and historical feedback.

[0059] Each evolutionary step includes:

[0060] Initialize a population: Initialize a population based on the existing progress forecast and resource scheduling strategy , the population contains different evolutionary bodies;

[0061] Fitness evaluation: By comparing the construction goals with the actual results, the fitness of each individual is evaluated. The fitness evaluation function is:

[0062]

[0063] in, is an individual At the moment The fitness of The actual construction progress. is the predicted construction progress, is the prediction error;

[0064] Select individuals with high fitness to perform crossover operations to form the next generation plan. The crossover operation is implemented by the following formula:

[0065]

[0066] in, It is a new individual produced by crossover. and are the two selected parent individuals, is the cross coefficient;

[0067] Perform mutation operations on some individuals, randomly changing their resource allocation or progress prediction strategies to introduce new variations and find potential optimization space. The mutation process is as follows:

[0068]

[0069] in, is the mutation amplitude, It is Gaussian noise, and the generated mutation term causes random changes in individuals;

[0070] Adjust the parameters of the genetic algorithm based on real-time construction environment feedback and historical data to ensure that individuals in each generation are more adaptable to the complex construction environment;

[0071] Ecological optimization draws on the ecological coordination and mutual assistance mechanisms in nature, and achieves overall performance optimization in large-scale and complex construction environments through multi-task collaborative optimization and resource sharing mechanisms; through ecological optimization algorithms, the best collaborative solution is found among multi-dimensional optimization goals.

[0072] Further: the ecological optimization algorithm is implemented by the following steps:

[0073] Assume there are m optimization goals, progress ,cost ,quality , each goal corresponds to a cost function, the overall ecological fitness for:

[0074]

[0075] in, , , is the weight coefficient of each target;

[0076] In the process of ecological optimization, the optimal compromise solution between different objectives is found through the Pareto optimal solution principle. Assume that an individual's performance on multiple objectives is , this example finds the Pareto frontier solution through non-dominated sorting:

[0077]

[0078] In construction tasks, resource dependencies and time constraints between tasks are considered to enable collaborative optimization between tasks. The resource allocation mechanism is modeled by the following formula:

[0079]

[0080] in, It's a task At the moment The amount of resource allocation, It is the biggest limitation of resources;

[0081] Through multiple rounds of optimization iterations, resource allocation and schedule scheduling between tasks are continuously updated to achieve the overall optimal state:

[0082]

[0083] in, is the adjustment in resource allocation, is the ecological fitness of the previous iteration, is the adjustment factor.

[0084] Compared with the prior art, the present invention has the following technical advances:

[0085] First, through the deep integration of a three-dimensional cognitive interactive body and an adaptive computing engine for perception and cognitive correction, this invention ensures real-time updates and accurate feedback of multi-dimensional data from the construction site, thereby minimizing the physical differences between the virtual model and the actual construction environment. Unlike traditional BIM models that rely solely on geometric data, this invention introduces real-time physical environment perception, enabling dynamic adjustments to factors such as ambient temperature and humidity, mechanics, and equipment load, ensuring precise synchronization between the simulation and the mechanical, fluid, and thermodynamic behaviors of real-world construction.

[0086] Secondly, during the optimization of schedule and resource management, this method utilizes a brain-inspired simulation schedule prediction algorithm and a synchronized virtual-reality intelligent perception grid to model the complex physical behavior of the construction process within a simulation environment, enabling real-time schedule adjustments and resource allocation. Through multiple adaptive mechanisms, deviations between the virtual model's physical behavior and the actual construction state can be quickly detected and corrected, avoiding physical distortions between virtual and reality and ensuring efficient computing performance, preventing system slowdowns or data processing bottlenecks caused by overly sophisticated simulations.

[0087] Finally, by combining ecological optimization and self-evolutionary mechanisms, this invention can automatically optimize progress forecasting and resource allocation during the construction process. It uses genetic algorithms and multi-objective optimization to find the optimal solution for construction management and continuously corrects the virtual model based on real-time feedback. This not only optimizes geometric errors in traditional BIM models but also effectively addresses the virtual reality distortion caused by the dynamic changes in the construction environment, thereby achieving more accurate construction progress forecasting and resource management, reducing project costs, shortening construction periods, and improving construction quality.

[0088] In summary, the present invention not only solves the problem of virtual reality distortion, but also accurately corrects the difference between virtual and reality during the construction process through an adaptive correction mechanism and innovative optimization algorithm, thereby greatly improving the intelligence and accuracy of construction management, ensuring efficient coordination and rational allocation of resources throughout the entire construction process. BRIEF DESCRIPTION OF THE DRAWINGS

[0089] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0090] In the attached figure:

[0091] Figure 1 This is a system structure diagram of the present invention. DETAILED DESCRIPTION

[0092] The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. The embodiments of the present invention will be described below with reference to the accompanying drawings.

[0093] like Figure 1 As shown, the present invention discloses a BIM-based transportation engineering construction progress and resource management optimization system, including: a three-dimensional cognitive interactive body, which adjusts the construction progress and resource allocation in real time through the perception layer, cognitive decision layer, collaborative decision-making mechanism and adaptive feedback of resource scheduling, eliminating the physical differences between the virtual model and the actual environment;

[0094] Adaptive computing engine, using real-time perception data and cognitive correction mechanism to achieve the connection between virtual model and actual construction site;

[0095] The progress prediction simulation module uses deep learning and adaptive feedback mechanisms to achieve dynamic prediction and optimization of construction progress, providing decision support for progress management;

[0096] A virtual-reality synchronous perception grid is constructed based on the obtained progress dynamic prediction and optimization results, and the virtual model of the internship is synchronized and dynamically corrected with the construction site;

[0097] Self-optimization module: Utilizes self-optimization and ecological optimization mechanisms, through genetic algorithms and multi-objective optimization, to achieve adaptive optimization and long-term evolution.

[0098] Specifically, by constructing a three-dimensional cognitive interactive body, the multi-dimensional information of the transportation engineering construction site (such as the environment, resources, personnel behavior, etc.) is integrated into an intelligent perception and adaptive decision-making system. The three-dimensional cognitive interactive body no longer relies on traditional hard-coded control, but dynamically adjusts the construction progress and resource allocation through real-time environmental perception, autonomous learning and collaborative decision-making, thereby solving the distortion problem between the virtual model and the actual physical state.

[0099] 1.1. Perception Layer

[0100] The 3D cognitive interactive body combines environmental data collected by multiple sensors (such as temperature, pressure, displacement, and vision sensors) to construct a real-time 3D state model of the construction site. These sensors do not operate independently, but rather work together within the perception layer through multimodal data fusion to ensure the accuracy and comprehensiveness of perceived information. Sensor inputs provide real-time feedback to the 3D cognitive interactive body on the actual construction site, forming a real-time perception data stream.

[0101] 1.2. Conversion and Preprocessing of Perception Data

[0102] The raw data stream received by the perception layer needs to be processed through adaptive filtering algorithms and data fusion algorithms. The key task of this layer is to eliminate noise and extract effective information to ensure that environmental data can be accurately converted into a three-dimensional cognitive model with minimal delay.

[0103] Specifically, it includes data filtering and fusion: the Kalman filter algorithm is used to suppress sensor noise, and the weighted average method is used to combine data from multiple sensors to obtain a more accurate three-dimensional state model.

[0104] 1.3. Cognitive Decision-Making Layer

[0105] Once the perception layer provides sufficient data flow, the 3D cognitive interactive body uses an adaptive physical correction algorithm to correct the virtual model based on nonlinear changes in the real-time construction environment. Specifically, this part introduces nonlinear optimization and feedback control to dynamically adjust the execution path of the construction task. When the construction progress deviates from the expected, a nonlinear least squares algorithm is used to correct it and calculate the optimal path adjustment. The optimization goal is to minimize the time and resource consumption of the construction task:

[0106]

[0107] in, represents the optimization path, is the task execution function on the path, is the desired target state.

[0108] Through multiple rounds of cognitive feedback on the construction process, the three-dimensional cognitive interactive body can self-adjust. Each time a construction task is executed, a feedback signal will be returned to the cognitive decision-making layer. Then, reinforcement learning is introduced. Reinforcement learning enables each correction to further optimize its decision-making ability based on historical feedback. Finally, the probability of each decision is updated through the Bayesian update rule, and the optimal action plan is derived in real time.

[0109] 1.4. Collaborative decision-making mechanism

[0110] The three-dimensional cognitive interactive body is not only responsible for the decision-making of a single task, but also needs to collaborate with other three-dimensional cognitive interactive bodies to achieve the overall construction goal. In this embodiment, a game theory model is introduced to simulate the strategy selection of multiple three-dimensional cognitive interactive bodies in resource competition and coordinate the behavior between each three-dimensional cognitive interactive body.

[0111] At each point in time, each three-dimensional cognitive interactive entity needs to choose its optimal strategy to ensure efficient use of resources while avoiding conflicts with other three-dimensional cognitive interactive entities. The game theory model determines the optimal strategy through the following Nash equilibrium.

[0112] 1.5. Adaptive Feedback for Resource Scheduling

[0113] How to effectively schedule limited resources among multiple 3D cognitive interactive entities is a key issue. Through multi-objective optimization algorithms, 3D cognitive interactive entities can maximize resource utilization while ensuring construction quality. Adaptive feedback on resource scheduling can be expressed as a multi-objective optimization problem, with the optimization goal of minimizing resource consumption and construction time:

[0114]

[0115] in, For resource allocation plan, It is The time consumption of a task, It is The consumption of resources, and is the weighting factor.

[0116] Through adaptive feedback from its perception layer, cognitive decision-making layer, collaborative decision-making mechanism, and resource scheduling, the 3D cognitive interactive body can adjust construction progress and resource allocation in real time, eliminating physical discrepancies between the virtual model and the actual environment. Through reinforcement learning, nonlinear optimization, and multimodal data fusion, the 3D cognitive interactive body not only addresses the virtual distortion issues common in traditional solutions but also provides highly flexible and adaptive solutions in dynamic environments, enhancing the level of intelligent management during the construction process.

[0117] The three-dimensional cognitive interactive body has completed the perception and real-time feedback processing of on-site data. The next step is to build an adaptive computing engine for perception and cognitive correction based on this perception data, so that the three-dimensional cognitive interactive body can optimize the differences between the virtual model and the physical environment in real time according to the dynamic changes of the construction site, avoiding the distortion between virtual and real physical behaviors that occurs in traditional simulations.

[0118] The adaptive computing engine is based on the following key modules:

[0119] Real-time perception data processing module: The data obtained from the perception layer (the perception results from sensors and three-dimensional cognitive interaction bodies) are filtered and pre-processed to extract meaningful environmental features and change patterns, providing input for subsequent cognitive corrections.

[0120] Cognitive correction decision module: Based on perception data and historical behavior patterns, an adaptive model correction method is used to correct the physical behavior in the virtual model to ensure a better match with the actual environment of the construction site.

[0121] Correction feedback and optimization module: Provides real-time feedback on the effects of model corrections and uses optimization algorithms to update correction strategies to gradually improve the consistency between virtual and reality.

[0122] The implementation of the cognitive correction decision module includes:

[0123] 2.1. Dynamic physical correction algorithm. The core idea of ​​this algorithm is to use nonlinear optimization methods to automatically adjust the physical parameters (such as mechanics, fluid mechanics, etc.) in the virtual model under the dynamic environmental changes of the construction site, thereby eliminating the differences between the virtual model and the actual environment.

[0124] 2.2. Adaptive Correction Model

[0125] Based on the field data provided by the perception layer, the correction algorithm adjusts the parameters in the above physical field model through adaptive optimization. To this end, this embodiment designs an adaptive correction model, which generates correction factors based on historical data and real-time feedback to minimize the error between the virtual model and the actual construction environment. The error definition refers to the error between the virtual and actual physical behavior. :

[0126]

[0127] in, is the physical force in the virtual model, is the physical force measured by the field sensor, the error Represents the difference between the model and the field data.

[0128] Then define the correction factor. To reduce the error, the gradient descent method is used to calculate the correction factor:

[0129]

[0130] in, At the moment Physical field model parameters The correction amount, is the learning rate, It is an error The gradient of the model parameters. During the optimization process, the algorithm continuously adjusts (i.e., the physical parameters of the model) to minimize the error , thereby achieving physical correction of the virtual model.

[0131] 2.3. Feedback and Correction Loop

[0132] To achieve real-time correction, the physical correction algorithm needs to run continuously during the construction process to update the physical parameters at each time point. The corrected virtual model will be fed back to the cognitive correction decision module as input for the next decision cycle. This process can be represented as a feedback optimization loop, that is, the state after each correction will enter the correction model again and be further optimized in the next round of calculations.

[0133] 2.4. Dynamic Feedback Optimization Algorithm

[0134] To ensure the adaptability and accuracy of the system, the optimization algorithm for correction feedback not only relies on the physical correction error but also needs to consider construction resource constraints and schedule goals. Therefore, this embodiment designs a multi-objective optimization algorithm so that the correction process not only optimizes the matching of physical behavior but also optimizes schedule delays and resource waste.

[0135] Multi-objective optimization: Set the optimization goal to minimize the physical correction error Deviation from construction progress and resource consumption The weighted sum of , we get the following optimization function:

[0136]

[0137] in, , , is the weighting factor, is the physical correction error, is the progress deviation, It is resource consumption.

[0138] 2.5. Joint Optimization of Resource and Schedule Scheduling

[0139] While making physical corrections, the balance between resource scheduling and progress management must be considered. To this end, this embodiment introduces a resource constraint optimization algorithm to dynamically schedule resources and adjust the progress based on the corrected construction status (such as adjusted physical behavior, progress deviation, etc.).

[0140] Assuming construction resources Subject to some constraints (such as the number of equipment, personnel availability, etc.), the resource scheduling optimization objective can be expressed as:

[0141]

[0142] in, It is Resources at the time The scheduling amount, It is the ideal resource scheduling amount.

[0143] The implementation of the schedule forecast simulation module includes:

[0144] In the cognitive correction decision-making module, by building an adaptive computing engine for perception and cognitive correction, it is possible to correct physical behavior based on real-time data and optimize construction resources and progress allocation. The goal of the progress prediction simulation module is to further enhance the construction progress prediction capability by introducing a brain-inspired simulation progress prediction algorithm, enabling accurate progress simulation and optimization in a highly dynamic construction environment.

[0145] This algorithm draws on neuroscience and brain-inspired mechanisms, and simulates the workings of the construction brain based on real-time feedback data from the construction site and historical construction progress data, thereby efficiently and accurately predicting construction progress in nonlinear and complex construction environments. It can not only handle various uncertainties in construction, but also dynamically adjust the progress prediction model to ensure its high adaptability and high precision.

[0146] First, a model framework of brain-inspired mechanisms is introduced.

[0147] 3.1. Core Concepts of Brain-Inspired Mechanisms

[0148] This brain-inspired mechanism is based on how neural networks and the brain process information, specifically the synaptic connections between neurons and the updating of synaptic weights. It simulates the information flow and optimized decision-making process in construction progress forecasting. This mechanism simulates the relationships between various factors on the construction site (such as resource scheduling, weather changes, and construction worker efficiency) and adjusts the progress forecast model through synaptic weight updates. The core concept is that construction progress forecasting can be represented by a brain-inspired neural network. Each construction task and each construction phase can be viewed as a neuron, while the construction progress and resource allocation are the synaptic connections between neurons, represented by their activation values.

[0149] 3.2. Neural network structure for simulation progress prediction

[0150] This embodiment designs a brain-inspired neural network model for the construction progress prediction problem. Its input layer consists of real-time construction data and historical construction progress data, the output layer is the future construction progress forecast, and the middle layer processes and calculates progress decisions through a multi-layer neural network.

[0151] Input layer: real-time data These data include construction resource status, site environment, weather conditions, etc.:

[0152]

[0153] in, Indicates at time The collected Items of data, such as equipment status, personnel efficiency, etc.

[0154] Middle layer (hidden layer): Calculates the dependencies between tasks through the synaptic connections of neurons and adjusts the progress prediction based on historical progress data and real-time feedback.

[0155] Output layer: Calculate the predicted value of future construction progress through the activation function of the neural network.

[0156]

[0157] in, It's time Forecasted construction progress, is the weight of the input data, is the activation function (such as Sigmoid or ReLU).

[0158] 3.4. Synaptic Weight Update Rules

[0159] The core of the brain-inspired model lies in simulating the update of synaptic weights between neurons, that is, how to update the various weights in the model based on the input real-time data and historical data. To apply this mechanism in construction progress forecasting, this embodiment adopts a combination of learning rules and reinforcement learning algorithms, so that the progress forecast at each time point can be adaptively adjusted.

[0160] Learning rule: Update the connection weights between neurons by strengthening the correlation signal. Specifically, assume that the neurons and There is a certain synergistic relationship between the input and output of the neuron. The output activates the neuron , then the synaptic connection weight should increase, and the weight update formula is as follows:

[0161]

[0162] in, From neurons to neurons The synaptic connection weights, is the learning rate, It is Input data It is The activation value of the output.

[0163] Reinforcement Learning Update: To further improve the accuracy of progress prediction, this embodiment combines Q-learning with dynamic adjustment. Q-learning can automatically update the model based on prediction errors and reward mechanisms, thereby maximizing future expected rewards (i.e., improving prediction accuracy):

[0164]

[0165] in, It is at the moment For an action and status The value function of is the learning rate, It’s an instant reward. is the discount factor.

[0166] 3.5. Model Adaptation

[0167] The synaptic weights in the brain-inspired model adjust to the dynamic changes at the construction site. Using the progress prediction errors and feedback from the construction site during each time period, the model can perform real-time self-correction. The specific correction process is as follows:

[0168] Forecast error calculation:

[0169]

[0170] in, The actual construction progress. is the predicted construction progress, is the prediction error.

[0171] Adaptive adjustment: based on prediction error ,The weight parameters in the neural network are updated by the gradient descent method, and then the progress prediction model is adjusted.

[0172]

[0173] in, It is at the moment Adjusted weights, is the learning rate, is the gradient of the prediction error with respect to the weights.

[0174] 3.6. Multi-task progress prediction

[0175] Since there are often multiple tasks going on simultaneously at a construction site, the optimization of progress prediction is not only about predicting a single task, but also includes the mutual influence between tasks. This embodiment uses a multi-task learning mechanism to enable the network to simultaneously predict the progress of multiple construction tasks and learn the interdependence between tasks.

[0176] Multi-task loss function: Set the total loss function as the weighted sum of all task losses:

[0177]

[0178] in, It is Tasks at time The loss function is is the weight coefficient of the task.

[0179] After each prediction, the progress error will adjust the network parameters through the feedback mechanism and be applied to subsequent progress predictions. Through this feedback mechanism, the accuracy of progress prediction can be gradually improved as the construction progress changes.

[0180] By introducing a brain-inspired simulation progress prediction algorithm, this embodiment not only addresses the nonlinearity and complexity of construction schedules, but also dynamically adjusts the prediction model, correcting errors between the virtual model and the actual progress in real time. This brain-inspired mechanism enables the system to self-learn and self-correct like the human brain, achieving efficient decision-making in construction progress prediction. This approach provides a new, highly intelligent solution for BIM and transportation engineering construction progress management.

[0181] The implementation of the virtual-reality synchronized perception grid includes:

[0182] In the progress prediction simulation module, this embodiment implements dynamic construction progress prediction and adapts to changes in the on-site environment by introducing a brain-inspired simulation progress prediction algorithm. The goal is to construct a virtual-reality synchronized perception grid based on the aforementioned progress prediction and correction results. This grid seamlessly connects the virtual model with the real-world construction site in real time, enabling simultaneous updates, corrections, and dynamic feedback. Specifically, various parameters in the virtual model (such as progress, resource allocation, and equipment status) must be synchronized with the actual construction site conditions (collected through sensory data) to ensure accurate and real-time construction management.

[0183] This grid not only needs to synchronize virtual and real-world data, but also ensure low latency, high accuracy, and efficient computation in large-scale construction environments. Therefore, the core challenge of this approach is to process and optimize the data mapping and synchronization between virtual and real-world data through efficient computing frameworks and intelligent perception algorithms.

[0184] First, the basic framework of the virtual-reality synchronized intelligent perception grid is constructed.

[0185] 4.1. Architecture Design of Virtual-Reality Synchronization

[0186] The virtual-reality synchronized perception grid consists of the following key modules:

[0187] Virtual-reality data mapping module: This module is responsible for mapping and synchronously updating the physical parameters of the virtual model (such as construction progress, resource consumption, equipment status, etc.) with the perception data of the actual construction site. This module needs to dynamically adjust the status of the virtual model based on on-site sensor data and historical construction progress data.

[0188] Real-time data acquisition and processing module: Based on the sensor network at the construction site, including GPS, cameras, temperature and humidity sensors, equipment sensors, etc., it collects multimodal data from the site in real time and converts this data into digital signals that can be connected to the virtual model through data fusion algorithms.

[0189] Synchronous control and feedback module: controls the update of the virtual model according to the differences between the virtual model and the real environment, and provides dynamic feedback on the behavior of the construction site based on the corrected virtual state.

[0190] 4.2. Key Technologies for Data Synchronization and Mapping

[0191] The core of synchronization and mapping technology is to precisely map the virtual model to the perceived data of the construction site, ensuring consistency between the virtual and real-world progress. The following describes how this process is implemented.

[0192] Then multi-scale data mapping and synchronization are performed.

[0193] Multi-scale mapping between the construction site and the virtual model

[0194] To ensure data synchronization between the construction site and the virtual model, various parameters in the virtual model must be hierarchically mapped to multi-scale on-site data (such as building area, equipment operating status, and environmental parameters). Specifically, the physical space of the virtual-reality synchronization grid is divided into multiple virtual-reality unit grids, each corresponding to a physical unit in the actual construction (such as a section of road, bridge, or equipment area). Each data item within these physical units is synchronized using data interpolation and mapping functions.

[0195] Assume that in this embodiment there is a building area in the virtual model , the area is divided into n sub-unit grids . In the actual area of ​​​​the construction site In the example, the real-time data set obtained through the sensor network is , the dataset is connected to each virtual subunit grid via a multi-scale data map.

[0196] The mapping relationship can be expressed in the following ways:

[0197]

[0198] in, is the mapping function between virtual and real data, For the moment Updated virtual model data, For the moment Sensor data collected from real-world sites.

[0199] 4.5. Spatial Interpolation and Dynamic Correction

[0200] In order to improve the accuracy of mapping, spatial interpolation technology is used to align the sensor data on site with the node data in the virtual model point by point. Assuming that each grid cell Corresponding to a virtual coordinate space and a real coordinate space, this embodiment uses three-dimensional linear interpolation or Gaussian process regression to perform spatial correction, so that the virtual model and the real scene are highly consistent in multi-dimensional data such as position and status.

[0201] The spatial interpolation formula is as follows:

[0202]

[0203] in, For sensor nodes At the moment data, For nodes The corresponding weight coefficient is is the spatial coordinate.

[0204] Finally, dynamic synchronization and feedback mechanism are implemented.

[0205] 4.6. Virtual-Reality Progress Feedback Mechanism

[0206] There may be differences between the actual progress of the construction site and the virtual progress, so a feedback mechanism is needed to achieve dynamic correction of the progress. and actual progress When deviations occur, the system automatically adjusts the relevant parameters in the virtual model.

[0207] The progress feedback formula is:

[0208]

[0209] in, time The correction amount of the virtual model progress, is the correction factor.

[0210] 4.7. Intelligent Perception Correction and Synchronous Control

[0211] In the sensor network at the construction site, the real-time environmental data collected (such as temperature, humidity, personnel status, etc.) may affect the physical behavior of the virtual model. Therefore, through the intelligent perception and correction mechanism, the system will use deep learning algorithms to model the environmental impact during each synchronization, thereby performing dynamic corrections.

[0212] By establishing a synchronized virtual-reality intelligent perception grid, this embodiment enables efficient, multi-dimensional, and all-time synchronization and dynamic correction between the virtual model and the construction site. This grid, based on multi-scale data mapping, spatial interpolation, dynamic progress feedback, and intelligent perception and correction technologies, effectively eliminates discrepancies between virtual and real life, ensuring real-time monitoring and intelligent optimization during the construction process.

[0213] The specific implementation of the self-optimization module includes:

[0214] By establishing a virtual-reality synchronized perception grid within the virtual-reality synchronized perception grid, this embodiment achieves precise synchronization between the virtual model and the real-world construction environment, and allows for real-time adjustments to virtual progress and resource status. The self-optimization module aims to further promote system self-optimization and ecological optimization. Through adaptive learning mechanisms and ecological network optimization algorithms, the system is able to continuously self-optimize in long-term, multi-task, and complex construction environments, and intelligently evolve in dynamic environments. The core challenge at this stage is how to enable the system to not only adapt to environmental changes in large-scale and complex construction environments, but also automatically improve its own performance, such as optimizing resource allocation, schedule scheduling, and risk management.

[0215] 5.1. Self-optimization

[0216] At this stage, the self-optimization mechanism introduced in this embodiment simulates the principles of natural selection and gene mutation in biological evolution, and combines the real-time feedback and learning mechanisms that occur during system operation to achieve continuous optimization of models and algorithms. The system's self-optimization mechanism consists of the following two parts:

[0217] Genetic algorithm: simulates the processes of natural selection, crossover, mutation, etc. in biological evolution, and automatically optimizes resource allocation, progress prediction, risk management, etc. during the construction process.

[0218] Reinforcement learning and adaptive optimization: The system learns through environmental interaction, thereby optimizing decisions such as progress prediction and resource scheduling to achieve long-term performance optimization.

[0219] 5.2. Self-optimization cycle

[0220] The self-optimization process is based on mechanisms such as evolutionary selection, mutation, and adaptive feedback. After each cycle, the system adjusts the optimization direction based on real-time data and historical feedback.

[0221] Each evolutionary step includes:

[0222] 5.2.1. Initialize a population: Based on existing progress prediction, resource scheduling and other strategies, initialize a population ,The population contains different evolutionary bodies (i.e., different construction progress, resource allocation plans).

[0223] 5.2.2. Fitness evaluation: By comparing the construction goals (such as time, cost, quality, etc.) with the actual results, the fitness of each individual is evaluated. The fitness evaluation function is:

[0224]

[0225] in, is an individual At the moment The fitness of The actual construction progress. is the predicted construction progress, is the prediction error.

[0226] 5.23. Selection and Crossover: Individuals with higher fitness are selected for crossover to form the next generation of solutions. The crossover operation is implemented using the following formula:

[0227]

[0228] in, It is a new individual produced by crossover. and are the two selected parent individuals, is the cross coefficient.

[0229] 5.2.4. Mutation and Adjustment: Mutate some individuals, randomly changing their resource allocation or progress prediction strategy to introduce new variations and find potential optimization space. The mutation process is as follows:

[0230]

[0231] in, is the mutation amplitude, is Gaussian noise, and the generated mutation term causes random changes in individuals.

[0232] 5.2.5. Adaptive feedback: Based on real-time construction environment feedback and historical data, adjust the parameters in the genetic algorithm to ensure that individuals in each generation are more adaptable to the complex construction environment.

[0233] 5.3. Ecosystem Optimization

[0234] Ecological optimization draws on the collaborative and mutually supportive mechanisms of natural ecosystems. Through multi-task collaborative optimization and resource sharing, this approach optimizes overall system performance in large-scale, complex construction environments. Using this ecological optimization algorithm, this embodiment can find the optimal collaborative solution across multiple optimization objectives (such as schedule, cost, quality, and safety).

[0235] At the construction site, there is a complex relationship of resource competition and sharing between multiple tasks (such as roadbed construction, bridge construction, equipment installation, etc.). How to optimize the resource allocation between different tasks so that the entire construction process can evolve synergistically is the key to ecological optimization.

[0236] 5.4. Design of ecological optimization algorithm

[0237] This embodiment designs a multi-objective ecological optimization algorithm for this purpose, which is implemented through the following steps:

[0238] 5.4.1. Objective function definition: Assume there are m optimization objectives, such as progress ,cost ,quality , each goal corresponds to a cost function, and the ecological fitness of the entire system for:

[0239]

[0240] in, , , is the weight coefficient of each target.

[0241] 5.4.2. Multi-objective optimization: In the process of ecological optimization, the optimal compromise solution between different objectives is found through the Pareto optimal solution principle. Suppose an individual performs well on multiple objectives. , this example finds the Pareto frontier solution through non-dominated sorting:

[0242]

[0243] 5.4.3. Task coordination mechanism: In construction tasks, resource dependencies and time constraints between tasks are considered to enable coordinated optimization between tasks. The resource allocation mechanism is modeled using the following formula:

[0244]

[0245] in, It's a task At the moment The amount of resource allocation, It is the biggest limitation of resources.

[0246] 5.4.4. Ecosystem Feedback and Optimization: Through multiple rounds of optimization iterations, resource allocation and progress scheduling between tasks are continuously updated to achieve the overall optimal state:

[0247]

[0248] in, is the adjustment in resource allocation, is the ecological fitness of the previous iteration, is the adjustment factor.

[0249] Through self-optimization and ecological optimization mechanisms, the system continuously optimizes decisions on construction schedules, resource allocation, cost control, and other aspects based on dynamic changes at the construction site, driving its intelligent evolution within complex construction environments. By combining genetic algorithms with multi-objective ecological optimization, the system not only optimizes single objectives but also finds the globally optimal construction management solution within the context of multi-task collaboration and resource sharing.

[0250] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the claims of the present invention.

Claims

1. The BIM-based transportation engineering construction progress and resource management optimization system is characterized by: include: The 3D cognitive interactive body adjusts construction progress and resource allocation in real time through adaptive feedback from the perception layer, cognitive decision-making layer, collaborative decision-making mechanism, and resource scheduling, eliminating the physical differences between the virtual model and the actual environment. The 3D cognitive interactive body includes: The perception layer combines environmental data collected by multiple sensors to build an instant 3D state model of the construction site. Through sensor input, the actual situation of the construction site is fed back to the 3D cognitive interaction body in real time, forming a real-time perception data stream. The cognitive decision-making layer introduces nonlinear optimization and feedback control to dynamically adjust the execution path of construction tasks. When the construction progress deviates from expectations, a nonlinear least squares algorithm is used to make corrections and calculate the optimal path adjustment. The optimization goal is to minimize the time and resource consumption of the construction task: in, represents the optimization path, is the task execution function on the path, is the desired target state; Through multiple rounds of cognitive feedback on the construction process, the three-dimensional cognitive interactive body can self-adjust. Each execution of a construction task returns a feedback signal to the cognitive decision-making layer. Reinforcement learning is then introduced. Reinforcement learning enables each correction to further optimize its decision-making ability based on historical feedback. Finally, the probability of each decision is updated through the Bayesian update rule, and the optimal action plan is derived in real time. A collaborative decision-making mechanism introduces a game theory model to simulate the strategic choices of multiple three-dimensional cognitive interactors in resource competition and coordinate the behaviors of each three-dimensional cognitive interactor. Adaptive feedback for resource scheduling is formulated as a multi-objective optimization problem, where the optimization goal is to minimize resource consumption and construction time: in, For resource allocation plan, It is The time consumption of a task, It is The consumption of resources, and is the weighting factor; Adaptive computing engine, using real-time perception data and cognitive correction mechanism to achieve the connection between virtual model and actual construction site; The progress prediction simulation module uses deep learning and adaptive feedback mechanisms to achieve dynamic prediction and optimization of construction progress, providing decision support for progress management; A virtual-reality synchronous perception grid is constructed based on the obtained progress dynamic prediction and optimization results, and the virtual model of the internship is synchronized and dynamically corrected with the construction site; Self-optimization module: Utilizes self-optimization and ecological optimization mechanisms, through genetic algorithms and multi-objective optimization, to achieve adaptive optimization and long-term evolution.

2. The BIM-based transportation engineering construction progress and resource management optimization system according to claim 1 is characterized in that: The adaptive computing engine includes: Real-time perception data processing module: extracts meaningful environmental features and change patterns from the data obtained from the perception layer, providing input for subsequent cognitive correction; Cognitive Correction Decision Module: Based on perception data and historical behavior patterns, it uses an adaptive model correction method to correct the physical behavior in the virtual model to ensure a better match with the actual environment of the construction site; Correction feedback and optimization module: Provides real-time feedback on the effects of model corrections and uses optimization algorithms to update correction strategies to gradually improve the consistency between virtual and reality.

3. The BIM-based transportation engineering construction progress and resource management optimization system according to claim 2 is characterized in that: The progress prediction simulation module includes: The brain-inspired neural network model has an input layer that includes real-time construction data and historical construction progress data, an output layer that predicts future construction progress, and an intermediate layer that processes and calculates progress decisions using a multi-layer neural network. Input layer: real-time data ,in, Indicates at time The collected Item data; Middle layer: Calculates dependencies between tasks through synaptic connections between neurons and adjusts progress predictions based on historical progress data and real-time feedback; Output layer: Calculate the future construction progress forecast value through the activation function of the neural network; in, It's time Forecasted construction progress, is the weight of the input data, is the activation function; By strengthening the correlation signal, the connection weights between neurons are updated. Assuming that the neurons and There is a certain synergistic relationship between the input and output of the neuron. The output activates the neuron , then the synaptic connection weight should increase, and the weight update formula is as follows: in, From neurons to neurons The synaptic connection weights, is the learning rate, It is Input data, It is The activation value of each output; To further improve the accuracy of progress prediction, we combine Q-learning to make dynamic adjustments to maximize the expected future rewards: in, It is at the moment For an action and status The value function of is the learning rate, It’s an instant reward. is the discount factor; Based on the progress forecast error and construction site feedback for each time period, the specific correction process is as follows: Forecast error calculation: in, The actual construction progress. is the predicted construction progress, is the prediction error; Based on the prediction error ,The weight parameters in the neural network are updated through the gradient descent method, and then the progress prediction model is adjusted; in, It is at the moment Adjusted weights, is the learning rate, is the gradient of the prediction error with respect to the weight; Through the multi-task learning mechanism, the network can simultaneously predict the progress of multiple construction tasks and learn the interdependence between tasks.

4. The BIM-based transportation engineering construction progress and resource management optimization system according to claim 3 is characterized in that: The virtual-reality synchronization perception grid includes: Virtual-to-reality data mapping module: This module is responsible for mapping and synchronously updating the physical parameters of the virtual model with the sensory data from the actual construction site. It dynamically adjusts the state of the virtual model based on on-site sensor data and historical construction progress data. Real-time data acquisition and processing module: Based on the sensor network at the construction site, it collects multi-modal data in real time and converts the sensor network data into digital signals that can be connected to the virtual model through data fusion algorithms; Synchronous control and feedback module: controls the update of the virtual model according to the differences between the virtual model and the real environment, and provides dynamic feedback on the behavior of the construction site based on the corrected virtual state.

5. The BIM-based transportation engineering construction progress and resource management optimization system according to claim 4 is characterized in that: The self-optimization module includes: The self-optimization mechanism introduced simulates the principles of natural selection and gene mutation in biological evolution, and combines the real-time feedback and learning mechanisms that occur during system operation to achieve continuous optimization of models and algorithms. The self-optimization mechanism includes: Genetic Algorithm: Simulates the natural selection, crossover, and mutation processes in biological evolution to automatically optimize resource allocation, schedule prediction, and risk management during the construction process; Reinforcement learning and adaptive optimization: Through interactive learning with the environment, we can optimize progress prediction and resource scheduling decisions to achieve long-term performance optimization; A self-optimization cycle based on evolutionary selection, mutation, and adaptive feedback mechanisms. After each cycle, the optimization direction is adjusted based on real-time data and historical feedback. Each evolutionary step includes: Initialize a population: Initialize a population based on the existing progress forecast and resource scheduling strategy , the population contains different evolutionary bodies; Fitness evaluation: By comparing the construction goals with the actual results, the fitness of each individual is evaluated. The fitness evaluation function is: in, is an individual At the moment The fitness of The actual construction progress. is the predicted construction progress, is the prediction error; Select individuals with high fitness to perform crossover operations to form the next generation plan. The crossover operation is implemented by the following formula: in, It is a new individual produced by crossover. and are the two selected parent individuals, is the cross coefficient; Perform mutation operations on some individuals, randomly changing their resource allocation or progress prediction strategies to introduce new variations and find potential optimization space. The mutation process is as follows: in, is the mutation amplitude, It is Gaussian noise, and the generated mutation term causes random changes in individuals; Adjust the parameters of the genetic algorithm based on real-time construction environment feedback and historical data to ensure that individuals in each generation are more adaptable to the complex construction environment; Ecological optimization draws on the ecological coordination and mutual assistance mechanisms in nature, and achieves overall performance optimization in large-scale and complex construction environments through multi-task collaborative optimization and resource sharing mechanisms; through ecological optimization algorithms, the best collaborative solution is found among multi-dimensional optimization goals.

6. The BIM-based transportation engineering construction progress and resource management optimization system according to claim 5 is characterized in that: The ecological optimization algorithm is implemented by the following steps: Assume there are m optimization goals, progress ,cost ,quality , each goal corresponds to a cost function, the overall ecological fitness for: in, , , is the weight coefficient of each target; In the process of ecological optimization, the optimal compromise solution between different objectives is found through the Pareto optimal solution principle. Assume that an individual's performance on multiple objectives is , find the Pareto front solution by non-dominated sorting: In construction tasks, resource dependencies and time constraints between tasks are considered to enable collaborative optimization between tasks. The resource allocation mechanism is modeled by the following formula: in, It's a task At the moment The amount of resource allocation, It is the biggest limitation of resources; Through multiple rounds of optimization iterations, resource allocation and schedule scheduling between tasks are continuously updated to achieve the overall optimal state: in, is the adjustment in resource allocation, is the ecological fitness of the previous iteration, is the adjustment factor.

Images