Infrastructure construction whole process data management method and system based on digital twinning and block chain

Abstract

The invention discloses an infrastructure whole process data management method and system based on digital twin and block chains, and relates to the technical field of infrastructure project management, and the method comprises the steps: collecting original data of an infrastructure project, carrying out the preprocessing, obtaining normalized data, carrying out the encryption and hashing, and forming a binding data package for storage; extracting the stored binding data packet for decryption and verification to obtain normalized data, setting a mapping relation table to map the normalized data, constructing a digital twin model to simulate the mapped normalized data, and outputting simulation results for weighted summation to obtain a predicted risk score; based on the predicted risk score, constructing an objective function, using a hybrid optimization algorithm to iteratively update the objective function, generating an optimal weight set, and feeding back the optimal weight set to weighted summation to obtain a final risk score; the data management efficiency and the safety operation and maintenance level of the capital construction project are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of infrastructure project management technology, and in particular to a method and system for managing data throughout the entire infrastructure process based on digital twins and blockchain. Background Technology

[0002] In recent years, with the acceleration of modern urbanization, the scale and complexity of infrastructure construction have been increasing. To ensure the safety, efficiency, and sustainability of infrastructure projects, more and more intelligent technologies are being applied to the infrastructure field, especially digital twins and blockchain technology. Digital twin technology enables real-time monitoring and analysis of infrastructure projects by constructing virtual models that correspond one-to-one with actual projects. This technology utilizes sensors and big data technology to not only collect and transmit on-site data in real time but also predict project performance under different operating conditions through simulation analysis. On the other hand, blockchain technology, with its immutable, transparent, and decentralized characteristics, provides strong guarantees for the storage, transmission, and verification of infrastructure project data. In recent years, increasing research and practice have shown that combining digital twins with blockchain can further improve the data management level of infrastructure projects, ensuring that information is transparent, traceable, and verifiable throughout the entire process from design and construction to maintenance.

[0003] In the existing technology, most systems rely on simple parameter injection for data-driven operations, lacking boundary condition mapping mechanisms. As a result, they cannot truly reflect the instantaneous state evolution of the structure. Furthermore, they often depend on simple threshold judgments or expert experience, failing to reflect the risk status of the project in real time and effectively. This leads to low accuracy and timeliness in risk prediction, as well as a lack of real-time response capabilities. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a method and system for managing data throughout the entire infrastructure construction process based on digital twins and blockchain, which solves the problems that existing technologies cannot truly reflect the instantaneous state evolution of structures and cannot effectively reflect the risk status of projects in real time.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for managing data throughout the entire infrastructure construction process based on digital twins and blockchain, comprising: The raw data from infrastructure projects is collected, preprocessed, and then normalized, encrypted, and hashed to form bound data packets for storage. Extract the stored bound data packets, decrypt and verify them to obtain normalized data, set up a mapping table to map the normalized data, construct a digital twin model to simulate the mapped normalized data, output the simulation results, perform weighted summation, and obtain the predicted risk score. Based on the predicted risk score, an objective function is constructed, and a hybrid optimization algorithm is used to iteratively update the objective function to generate the optimal weight set, which is then fed back to the weighted summation to obtain the final risk score. The hybrid optimization algorithm refers to a combination of the Harris Hawks algorithm and arithmetic optimization algorithms; Risk warnings are issued based on the final risk score, and emergency response measures are implemented according to the warning results.

[0007] As a preferred embodiment of the infrastructure full-process data management method based on digital twins and blockchain described in this invention, the following steps are included: After setting a mapping relationship table to map the normalized data, a digital twin model is constructed to simulate the mapped normalized data, and the simulation results are weighted and summed to obtain a predicted risk score: A mapping table is set up based on the principles of physical consistency and causality. The BIM model file is obtained through the API interface and parsed to obtain key information, including three-dimensional geometry, spatial location, dimensional parameters, material type and design loads. Based on key information, a simulation model is constructed as a digital twin model. After normalized data is mapped to boundary conditions through a mapping relationship table, it is input into the digital twin model for simulation. The finite element solver is called to solve the simulated digital twin model and output the simulation results, including the stress distribution, vibration response, temperature distribution, displacement and deformation of the structure, and the change of internal pressure of the object over time in various parts of the infrastructure. Set the initial weight and generation interval for each data point in the simulation results, and use a weighted summation formula to calculate the sum based on the initial weights and each data point in the simulation results. This sum is defined as the predicted risk score. The generated range includes an upper limit value and a lower limit value.

[0008] As a preferred embodiment of the infrastructure full-process data management method based on digital twins and blockchain described in this invention, the following steps are included: Constructing an objective function, iteratively updating the objective function using a hybrid optimization algorithm, generating an optimal weight set and feeding it back to a weighted summation to obtain the final risk score: The initial weights are integrated into a weight set, and multiple weight sets are randomly generated within the generation interval using a pseudo-number random generator. Each weight set is then used as an individual in the hybrid optimization algorithm to generate the population initialization. Define the objective function for each individual, and minimize the value of the objective function. The objective function values ​​are calculated and sorted in descending order. The individual with the smallest objective function value is selected as the prey. The Harris Hawks algorithm is used to simulate the hunting behavior of eagles, and all individuals surround the prey. During the surround, the position of each individual is randomly selected and the position of each individual is updated. Based on the updated position, the fitness value of each individual is recalculated and sorted in ascending order to form a sorted list. A refinement value is set, and the sorted list is traversed to count the number of times each fitness value is repeated. When the number of repetitions is greater than or equal to the refinement value, the arithmetic optimization algorithm is used to update the individual position again. Otherwise, the Harris Hawks algorithm is used to update the individual position. After iterating to the maximum number of times, the optimal weight set is output. Each weight in the optimal weight set is fed back into the weighted summation formula of the true risk score, the risk score is recalculated, and the final risk score is generated. The optimal weight set includes weights for stress distribution, vibration response, temperature distribution, structural displacement and deformation, and the rate of change of internal pressure distribution.

[0009] As a preferred embodiment of the infrastructure full-process data management method based on digital twins and blockchain described in this invention, the step of conducting risk warning based on the final risk score and implementing emergency response measures according to the warning result refers to setting a risk threshold by statistically analyzing historical data. When the final risk score is greater than the risk threshold, it indicates that the infrastructure project is currently in a dangerous state and triggers a warning; otherwise, it indicates that the infrastructure project is currently in a normal state and continues to be monitored. When an alert is triggered, an alert record is generated in the blockchain through a smart contract. After forming a block containing the alert information, emergency response measures are then executed through the smart contract. The emergency response measures executed via smart contracts refer to sending notifications to management personnel.

[0010] As a preferred embodiment of the infrastructure full-process data management method based on digital twins and blockchain described in this invention, the step of collecting and preprocessing the raw data of the infrastructure project refers to deploying multiple types of sensors at various locations of the infrastructure project to collect raw data and perform filtering, noise reduction, calibration, and normalization. The various types of sensors include temperature, vibration, stress, acceleration, and pressure sensors; The raw data includes construction site temperature, construction site vibration, structural stress, object acceleration, and internal pressure data.

[0011] As a preferred embodiment of the infrastructure-wide data management method based on digital twins and blockchain described in this invention, the step of encrypting and hashing the obtained normalized data to form a bound data packet for storage includes the following steps: Based on the normalized data, the AES encryption algorithm is used to encrypt the data to generate an encrypted data packet. Then, the SHA-256 hash algorithm is used to hash the encrypted data packet to obtain an initial hash value, which is then bound to the encrypted data packet to obtain a bound data packet. Based on the bound data packets, each bound data packet is treated as an independent blockchain data block, and then the data block is transmitted to the central data platform for storage via wireless communication technology.

[0012] As a preferred embodiment of the infrastructure full-process data management method based on digital twins and blockchain described in this invention, the step of extracting and decrypting the stored bound data packets to obtain normalized data refers to extracting data blocks from the central data platform, re-hashing the encrypted data packets in the data blocks using the SHA-256 hash algorithm to obtain a secondary hash value. When the secondary hash value matches the initial hash value, the corresponding key is used to decrypt the data block using AES to obtain normalized data; otherwise, the extraction and decryption of the data blocks are repeated.

[0013] Secondly, this invention provides a data management system for the entire infrastructure construction process based on digital twins and blockchain, including: The data acquisition and encryption module is used to collect raw data from infrastructure projects, preprocess it, obtain normalized data, encrypt and hash it, and then form bound data packets for storage. The simulation summation module is used to extract the stored bound data packets for decryption and verification to obtain normalized data. After setting a mapping table to map the normalized data, a digital twin model is constructed to simulate the mapped normalized data. The simulation results are then weighted and summed to obtain the predicted risk score. The hybrid optimization module is used to construct an objective function based on the predicted risk score, use a hybrid optimization algorithm to iteratively update the objective function, generate the optimal weight set and feed it back to the weighted summation to obtain the final risk score; The early warning and response module is used to issue risk warnings based on the final risk score and to implement emergency response measures according to the warning results.

[0014] Thirdly, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, it implements any step of the infrastructure end-to-end data management method based on digital twins and blockchain as described in the first aspect of the present invention.

[0015] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the infrastructure end-to-end data management method based on digital twins and blockchain as described in the first aspect of the present invention.

[0016] The beneficial effects of this invention are as follows: By inputting normalized sensor data into a digital twin model for simulation and using a hybrid optimization algorithm for risk assessment, this invention not only enables real-time risk prediction and intelligent early warning, but also significantly improves the data management efficiency and safe operation and maintenance level of infrastructure projects. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of the infrastructure data management method based on digital twins and blockchain in Example 1.

[0019] Figure 2 This is a structural diagram of the infrastructure full-process data management system based on digital twins and blockchain in Example 1.

[0020] Figure 3 This is a flowchart of the risk warning in Example 1. Detailed Implementation

[0021] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0022] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0023] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0024] Example 1, referring to Figures 1-3This is the first embodiment of the present invention, which provides a method for managing data throughout the entire infrastructure construction process based on digital twins and blockchain, including the following steps: S1. Collect raw data from infrastructure projects, preprocess it, obtain normalized data, encrypt and hash it, and then form bound data packets for storage; Specifically, collecting raw data from infrastructure projects and preprocessing it refers to deploying multiple types of sensors at various locations within the infrastructure project to collect raw data and then filtering, denoising, calibrating, and normalizing it. The various types of sensors include temperature, vibration, stress, acceleration, and pressure sensors; The raw data includes construction site temperature, construction site vibration, structural stress, object acceleration, and internal pressure data.

[0025] By deploying temperature, vibration, stress, acceleration, and pressure sensors at various locations within infrastructure projects, comprehensive perception of the structural environment and operating conditions can be achieved. The collaborative acquisition of multidimensional data not only reflects static physical states (such as temperature distribution and internal pressure) but also captures dynamic responses (such as seismic vibration and traffic loads). Filtering and denoising effectively eliminate non-structural components such as construction noise and equipment interference, improving the signal-to-noise ratio of the data. Calibration ensures the comparability of data collected by different sensors, eliminating analytical biases caused by systematic errors. Normalization provides a unified input standard for multidimensional data, facilitating direct use by subsequent machine learning algorithms or simulation calculations. Preprocessed data possesses higher reliability, significantly improving the accuracy of risk identification and trend prediction.

[0026] Furthermore, after the normalized data is encrypted and hashed, it is used to form a bound data packet for storage, including the following steps: Based on the normalized data, the AES encryption algorithm is used to encrypt the data to generate an encrypted data packet. Then, the SHA-256 hash algorithm is used to hash the encrypted data packet to obtain an initial hash value, which is then bound to the encrypted data packet to obtain a bound data packet. Based on the bound data packets, each bound data packet is treated as an independent blockchain data block, and then the data block is transmitted to the central data platform for storage via wireless communication technology.

[0027] Encrypting normalized data using AES is the first step in building a secure data transmission link. Compared to traditional plaintext storage or transmission methods, this step significantly reduces the risk of data interception during wireless transmission and remote storage. Binding SHA-256 hash values ​​to encrypted data packets not only increases the system's anti-tampering capabilities but also enables data integrity verification. Traditional encryption only ensures data is "unreadable" but cannot prevent data from being replaced during transmission. Hash verification, on the other hand, provides a "data fingerprint." If any slight change occurs in the data packet content, the recalculated hash value will not match the initial hash value, thus promptly detecting tampering. By combining encrypted data and hash values ​​into bound data packets, this invention achieves an integrated design for data confidentiality and integrity verification. This design is more efficient than the traditional two-step process of "encryption first, verification later," and also facilitates rapid verification and indexing in subsequent blockchain storage and retrieval stages. Storing the bound data packets as independent data blocks in the blockchain fully leverages the blockchain's immutability, traceability, and distributed consensus characteristics. Utilizing wireless communication technology to transmit blockchain data blocks to the central data platform in real time significantly improves the data flow and real-time performance of infrastructure projects.

[0028] S2. Extract the stored bound data packets, decrypt and verify them to obtain normalized data. Set up a mapping table to map the normalized data, construct a digital twin model to simulate the mapped normalized data, output the simulation results, perform weighted summation, and obtain the predicted risk score. Specifically, the process involves extracting and decrypting the stored bound data packets to obtain normalized data. This means extracting data blocks from the central data platform, re-hashing the encrypted data packets in the data blocks using the SHA-256 hash algorithm to obtain a secondary hash value. If the secondary hash value matches the initial hash value, the corresponding key is used to decrypt the data block using AES to obtain normalized data; otherwise, the extraction and decryption of the data blocks are repeated.

[0029] After retrieving the bound data packet from the central data platform, the encrypted data is first subjected to a second SHA-256 hash operation to generate a secondary hash value, which is then compared with the initial hash value. This step ensures that any minor modification to the data during transmission or storage will cause a drastic change in the hash value, which will be immediately detected by the system. Furthermore, through secondary hash verification, the system ensures that the extracted data is completely consistent with the original data, providing a reliable data foundation for subsequent decryption and simulation. If the secondary hash value is inconsistent with the initial hash value, the system will automatically trigger a re-extraction and decryption process. This "fault-tolerant data verification mechanism" can effectively cope with abnormal scenarios such as network jitter, data packet loss, and malicious attacks, thereby ensuring data reliability and availability. This mechanism avoids the risks of manual intervention or system crashes in traditional systems, improving the automation and robustness of the data processing flow. Once the hash value verification is successful, the system uses the corresponding key to perform AES decryption on the encrypted data packet, obtaining normalized data. This step ensures that even if an attacker obtains the data packet, they cannot decrypt the data due to the lack of the key, thus effectively preventing information leakage. Furthermore, only authorized users with valid keys can access the data, meeting the security and compliance requirements of industrial applications.

[0030] Furthermore, after mapping the normalized data using a mapping table, a digital twin model is constructed to simulate the mapped normalized data. The simulation results are then weighted and summed to obtain the predicted risk score, including the following steps: A mapping table is set up based on the principles of physical consistency and causality. A specific example of a mapping relationship table is as follows: Normalized temperature data is mapped to transient thermal load boundary conditions for the corresponding spatial region in the model, which is used to drive thermo-mechanical coupling analysis, update the temperature field distribution of the material, and affect thermal expansion strain and material property degradation parameters. Normalized vibration data → mapped to displacement or velocity time history boundary conditions of the finite element nodes where the monitoring point is located, or applied as external excitation to relevant components to correct the dynamic response characteristics and damping parameters of the structure. Normalized stress data → used as inversion input, through model parameter identification algorithms (such as least squares method or Kalman filtering), dynamically adjusts the elastic modulus or constitutive relation parameters of the corresponding component material to achieve online calibration of the material state; Normalized acceleration data is mapped to dynamic acceleration excitation loads at specific nodes, used to update the transient response simulation of the structure under dynamic loads (such as traffic, wind vibration, earthquake), and to calculate inertial force and dynamic displacement. Normalized pressure data → mapped to the boundary conditions of hydrostatic or dynamic pressure distribution of fluid inside a closed or semi-closed structure, used to simulate the forces exerted by the internal medium (such as water or gas) on the structural walls, and to evaluate the compressive stability and sealing performance of the structure. The BIM model file is obtained through the API interface and parsed to obtain key information, including three-dimensional geometry, spatial location, dimensional parameters, material type and design loads. Based on key information, a simulation model is constructed as a digital twin model. After normalized data is mapped to boundary conditions through a mapping relationship table, it is input into the digital twin model for simulation. The finite element solver is called to solve the simulated digital twin model and output the simulation results, including the stress distribution, vibration response, temperature distribution, displacement and deformation of the structure, and the change of internal pressure of the object over time in various parts of the infrastructure. By setting the initial weight and generation interval for each data point in the simulation results through experiments and domain knowledge, and using a weighted summation formula to combine the initial weights and each data point in the simulation results, the sum is calculated and defined as the predicted risk score. The generated range includes an upper limit value and a lower limit value.

[0031] Traditional digital twin systems often rely on empirical formulas or static parameter configurations, leading to discrepancies between the simulation model and the actual engineering conditions. This invention introduces dual constraints of "physical consistency" and "causal relationship" to ensure the physical interpretability and predictive accuracy of the correspondence between sensor data and simulation boundary conditions. This mechanism effectively avoids common misjudgment problems in "data-driven models," improving the credibility and stability of simulation calculations. By mapping normalized data to inputs such as boundary conditions, material parameters, or external excitations, the finite element solver can directly utilize field data for real-time simulation. This deep integration not only enables dynamic updates to the digital twin model but also avoids the problem of "separation between sensor data and simulation model" in traditional methods. Secondly, the introduction of weighted summation and risk scoring mechanisms enables quantitative evaluation of simulation results. By setting initial weights and generation intervals, this invention uses experimental experience and domain knowledge to calculate and predict risk scores, thereby achieving a closed loop from simulation results to risk decision-making. This method overcomes the shortcomings of traditional monitoring systems that rely on single-indicator early warnings, improving the robustness and interpretability of predictions.

[0032] S3. Based on the predicted risk score, construct an objective function, use a hybrid optimization algorithm to iteratively update the objective function, generate the optimal weight set and feed it back to the weighted summation to obtain the final risk score; Specifically, the objective function is constructed, and a hybrid optimization algorithm is used to iteratively update the objective function to generate the optimal weight set, which is then fed back into a weighted summation to obtain the final risk score. This includes the following steps: The initial weights are integrated into a weight set, and multiple weight sets are randomly generated within the generation interval using a pseudo-number random generator. Each weight set is then used as an individual in the hybrid optimization algorithm to generate the population initialization. Define the objective function for an individual, and minimize the value of the objective function. The formula is: ; In the formula, Represents the objective function value. Represents the total number of samples. Indicates the first Predicted risk score for each sample Indicates the first The true risk score for each sample (which can be set through experiments and expert experience). The objective function values ​​are calculated and sorted in descending order. The individual with the smallest objective function value is selected as prey. The Harris Hawks algorithm is used to simulate the hunting behavior of eagles, causing all individuals to surround and capture the prey. During the capture process, the position of each individual is updated by randomly selecting one individual's position, using the following formula: ; In the formula, Indicates that the individual is in Position at the next iteration Indicates the prey is Position at the next iteration and This represents a random number generated under the condition that the value is less than a certain value (this number can be generated using a pseudo-random number generator). This represents the lower limit of the generated interval. This represents the upper limit of the generated interval. The judgment value can be set through experiments and knowledge from books in related fields. Indicates that randomly selected individuals are in Position at the next iteration and This represents a random number that is greater than or equal to a given value. Indicates that the individual is in The position at the next iteration; Based on the updated positions, the fitness values ​​of each individual are recalculated and sorted in ascending order to form a sorted list. A refinement value is set according to the required precision and experimental settings. The sorted list is traversed, and the frequency of each fitness value is counted. When the frequency of occurrence is greater than or equal to the refinement value, the individual's position is updated again using an arithmetic optimization algorithm. The formula is: ; In the formula, Indicates in The individual position is updated using an arithmetic optimization algorithm in the next iteration. Indicates in The position of the individual with the minimum fitness value at the next iteration (which can be obtained from the sorted list). This represents a mathematical optimization probability function. Random numbers representing arithmetic optimization algorithms (which can be generated using a pseudo-random number generator); The specific form of the mathematical optimization probability function is as follows: ; In the formula, This represents the fitness value of the current individual. This represents the total number of fitness values. Represents an individual fitness value; Otherwise, the Harris Hawks algorithm is used to update the individual position. After iterating to the maximum number of times, the optimal weight set is output. Each weight in the optimal weight set is fed back into the weighted summation formula of the true risk score, the risk score is recalculated, and the final risk score is generated. The optimal weight set includes weights for stress distribution, vibration response, temperature distribution, structural displacement and deformation, and the rate of change of internal pressure distribution.

[0033] By generating multiple weight sets within a preset interval using a pseudo-random number generator to form an initial population, the coverage of the search space can be significantly increased, avoiding local optima caused by concentrated initial values. This mechanism is particularly crucial in infrastructure risk prediction scenarios, addressing the data variability and complexity across different engineering environments. The objective function adopts the mean squared error form, which not only quantifies the prediction error but also exhibits good convexity, facilitating iterative optimization. By continuously minimizing... The algorithm can adaptively adjust the weights of various physical quantities (such as stress, vibration, and temperature) to ultimately generate a high-precision risk score that reflects the true risks of the project, providing a scientific basis for early warning decisions. The HHO algorithm simulates the hunting strategy of a flock of eagles, enabling each individual to dynamically adjust its position in a high-dimensional space. And through... The individual update formula enables adaptive switching between "jump-style global search" and "local tracking," allowing the search for weights to be unrestricted by initial values, thus improving the algorithm's global convergence capability and solution diversity. Furthermore, when the algorithm detects that the number of times the fitness value is repeated exceeds a set threshold, it triggers the Arithmetic Optimization Algorithm (AOA) to perform a local update, and through... The mathematical optimization probability function in the update formula allows for adjustment of the step size and direction of individual updates. Furthermore, AOA can achieve high-precision local fine-tuning based on the global search of HHO, effectively preventing overfitting or oscillatory convergence and improving optimization stability. Secondly, the specific form of the mathematical optimization probability function is to adaptively adjust the selection probability of each individual based on the fitness value, achieving a dynamic balance between global and local searches. This mechanism ensures that during the training of the risk prediction model, it maintains exploratory capabilities while focusing on optimizing high-value individuals, avoiding getting trapped in local minima. The final output optimal weight set represents the optimal combination of various physical characteristics (stress, vibration, temperature, displacement, pressure). Feeding this set back to the weighted summation formula to recalculate the risk score enables self-learning closed-loop optimization of infrastructure risk assessment. This process not only gives the weighted summation dynamic adaptive capabilities but also allows for continuous iteration to optimize risk prediction accuracy, thus enabling generalized applications for different projects.

[0034] S4. Conduct risk warnings based on the final risk score and implement emergency response measures according to the warning results; Specifically, risk warnings are issued based on the final risk score, and emergency response measures are implemented according to the warning results. This involves setting risk thresholds through statistical analysis of historical data. When the final risk score is greater than the risk threshold, it indicates that the infrastructure project is currently in a dangerous state and an warning is triggered. Otherwise, it indicates that the infrastructure project is currently in a normal state and monitoring continues. When an alert is triggered, an alert record is generated in the blockchain through a smart contract. After forming a block containing the alert information, emergency response measures are then executed through the smart contract. The emergency response measures executed via smart contracts refer to sending notifications to management personnel.

[0035] The final risk score is obtained through statistical modeling and dynamic optimization algorithms, exhibiting significant self-learning capabilities and situational adaptability compared to traditional static early warning systems based on single-parameter thresholds. This mechanism can reflect the safety status of infrastructure structures under multi-dimensional stress coupling and environmental loads in real time, reducing misjudgments caused by external disturbances. Its beneficial effects lie in improving the accuracy, timeliness, and sensitivity of the early warning system. Risk assessment results and emergency events generated during the early warning process are encrypted and recorded via blockchain, with each block containing a hash pointer and timestamp. This operation effectively prevents data from being tampered with afterward, ensuring the objectivity of accident analysis and engineering audits. When the risk score exceeds the threshold, the system automatically calls a smart contract to generate an early warning block and simultaneously executes emergency response logic, such as immediately notifying management personnel. Compared to traditional manual approval-based response mechanisms, this solution significantly shortens response latency and achieves automation of the "perception-judgment-execution" closed loop.

[0036] This embodiment also provides a data management system for the entire infrastructure construction process based on digital twins and blockchain, including: The data acquisition and encryption module is used to collect raw data from infrastructure projects, preprocess it, obtain normalized data, encrypt and hash it, and then form bound data packets for storage. The simulation summation module is used to extract the stored bound data packets for decryption and verification to obtain normalized data. After setting a mapping table to map the normalized data, a digital twin model is constructed to simulate the mapped normalized data. The simulation results are then weighted and summed to obtain the predicted risk score. The hybrid optimization module is used to construct an objective function based on the predicted risk score, use a hybrid optimization algorithm to iteratively update the objective function, generate the optimal weight set and feed it back to the weighted summation to obtain the final risk score; The early warning and response module is used to issue risk warnings based on the final risk score and to implement emergency response measures according to the warning results.

[0037] This embodiment also provides a computer device applicable to the infrastructure full-process data management method based on digital twins and blockchain, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the infrastructure full-process data management method based on digital twins and blockchain proposed in the above embodiment.

[0038] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0039] This embodiment also provides a storage medium storing a computer program. When executed by a processor, the program implements the data management method for the entire infrastructure process based on digital twins and blockchain, as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0040] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for managing data throughout the entire infrastructure construction process based on digital twins and blockchain, characterized in that: include, The raw data from infrastructure projects is collected, preprocessed, and then normalized, encrypted, and hashed to form bound data packets for storage. Extract the stored bound data packets, decrypt and verify them to obtain normalized data, set up a mapping table to map the normalized data, construct a digital twin model to simulate the mapped normalized data, output the simulation results, perform weighted summation, and obtain the predicted risk score. Based on the predicted risk score, an objective function is constructed, and a hybrid optimization algorithm is used to iteratively update the objective function to generate the optimal weight set, which is then fed back to the weighted summation to obtain the final risk score. The hybrid optimization algorithm refers to a combination of the Harris Hawks algorithm and arithmetic optimization algorithms; Risk warnings are issued based on the final risk score, and emergency response measures are implemented according to the warning results.

2. The infrastructure data management method based on digital twins and blockchain as described in claim 1, characterized in that: After mapping the normalized data using the mapping relationship table, a digital twin model is constructed to simulate the mapped normalized data. The simulation results are then weighted and summed to obtain the predicted risk score. This process includes the following steps: A mapping table is set up based on the principles of physical consistency and causality. The BIM model file is obtained through the API interface and parsed to obtain key information, including three-dimensional geometry, spatial location, dimensional parameters, material type and design loads. Based on key information, a simulation model is constructed as a digital twin model. After normalized data is mapped to boundary conditions through a mapping relationship table, it is input into the digital twin model for simulation. The finite element solver is called to solve the simulated digital twin model and output the simulation results, including the stress distribution, vibration response, temperature distribution, displacement and deformation of the structure, and the change of internal pressure of the object over time in various parts of the infrastructure. Set the initial weight and generation interval for each data point in the simulation results, and use a weighted summation formula to calculate the sum based on the initial weights and each data point in the simulation results. This sum is defined as the predicted risk score. The generated range includes an upper limit value and a lower limit value.

3. The infrastructure data management method based on digital twins and blockchain as described in claim 2, characterized in that: The construction of the objective function, using a hybrid optimization algorithm to iteratively update the objective function, generating an optimal weight set that is fed back into the weighted summation to obtain the final risk score, includes the following steps: The initial weights are integrated into a weight set, and multiple weight sets are randomly generated within the generation interval using a pseudo-number random generator. Each weight set is then used as an individual in the hybrid optimization algorithm to generate the population initialization. Define the objective function for each individual, and minimize the value of the objective function. The objective function values ​​are calculated and sorted in descending order. The individual with the smallest objective function value is selected as the prey. The Harris Hawks algorithm is used to simulate the hunting behavior of eagles, and all individuals surround the prey. During the surround, the position of each individual is randomly selected and the position of each individual is updated. Based on the updated position, the fitness value of each individual is recalculated and sorted in ascending order to form a sorted list. A refinement value is set, and the sorted list is traversed to count the number of times each fitness value is repeated. When the number of repetitions is greater than or equal to the refinement value, the arithmetic optimization algorithm is used to update the individual position again. Otherwise, the Harris Hawks algorithm is used to update the individual position. After iterating to the maximum number of times, the optimal weight set is output. Each weight in the optimal weight set is fed back into the weighted summation formula of the true risk score, the risk score is recalculated, and the final risk score is generated. The optimal weight set includes weights for stress distribution, vibration response, temperature distribution, structural displacement and deformation, and the rate of change of internal pressure distribution.

4. The infrastructure full-process data management method based on digital twins and blockchain as described in claim 3, characterized in that: The aforementioned risk warning based on the final risk score and the execution of emergency response measures based on the warning results refer to setting a risk threshold by statistically analyzing historical data. When the final risk score is greater than the risk threshold, it indicates that the infrastructure project is currently in a dangerous state and an warning is triggered; otherwise, it indicates that the infrastructure project is currently in a normal state and monitoring continues. When an alert is triggered, an alert record is generated in the blockchain through a smart contract. After forming a block containing the alert information, emergency response measures are then executed through the smart contract. The emergency response measures executed via smart contracts refer to sending notifications to management personnel.

5. The infrastructure full-process data management method based on digital twins and blockchain as described in claim 4, characterized in that: The preprocessing of raw data collected from infrastructure projects refers to deploying multiple types of sensors at various locations within the infrastructure project to collect raw data and then performing filtering, noise reduction, calibration, and normalization. The various types of sensors include temperature, vibration, stress, acceleration, and pressure sensors; The raw data includes construction site temperature, construction site vibration, structural stress, object acceleration, and internal pressure data.

6. The infrastructure full-process data management method based on digital twins and blockchain as described in claim 5, characterized in that: The process of encrypting and hashing the obtained normalized data to form a bound data packet for storage includes the following steps: Based on the normalized data, the AES encryption algorithm is used to encrypt the data to generate an encrypted data packet. Then, the SHA-256 hash algorithm is used to hash the encrypted data packet to obtain an initial hash value, which is then bound to the encrypted data packet to obtain a bound data packet. Based on the bound data packets, each bound data packet is treated as an independent blockchain data block, and then the data block is transmitted to the central data platform for storage via wireless communication technology.

7. The infrastructure full-process data management method based on digital twins and blockchain as described in claim 6, characterized in that: The process of extracting and decrypting the bound data packets stored in the database to obtain normalized data involves extracting data blocks from the central data platform, re-hashing the encrypted data packets in the data blocks using the SHA-256 hash algorithm to obtain a secondary hash value. If the secondary hash value matches the initial hash value, the corresponding key is used to decrypt the data block using AES to obtain normalized data; otherwise, the extraction and decryption of the data blocks are repeated.

8. A data management system for the entire infrastructure construction process based on digital twins and blockchain, based on the data management method for the entire infrastructure construction process based on digital twins and blockchain as described in any one of claims 1 to 7, characterized in that: include, The data acquisition and encryption module is used to collect raw data from infrastructure projects, preprocess it, obtain normalized data, encrypt and hash it, and then form bound data packets for storage. The simulation summation module is used to extract the stored bound data packets for decryption and verification to obtain normalized data. After setting a mapping table to map the normalized data, a digital twin model is constructed to simulate the mapped normalized data. The simulation results are then weighted and summed to obtain the predicted risk score. The hybrid optimization module is used to construct an objective function based on the predicted risk score, use a hybrid optimization algorithm to iteratively update the objective function, generate the optimal weight set and feed it back to the weighted summation to obtain the final risk score; The early warning and response module is used to issue risk warnings based on the final risk score and to implement emergency response measures according to the warning results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the infrastructure full-process data management method based on digital twins and blockchain as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the infrastructure full-process data management method based on digital twins and blockchain as described in any one of claims 1 to 7.

Images