Engineering supervision project evaluation management method and system based on Internet of Things

Abstract

The invention discloses an engineering supervision project assessment management method and system based on the Internet of Things, and relates to the technical field of engineering project assessment, and the method comprises the steps: collecting and processing the field environment data and equipment data of an engineering project, and constructing an engineering field digital twinborn model; carrying out engineering equipment risk resonance analysis according to the digital twin model to construct a risk resonance matrix, and carrying out simulation risk early warning according to the risk resonance matrix; and recording the engineering field digital twin model in the block chain, updating through real-time field environment data and equipment data, and synchronously recording and storing the data by the block chain. According to the method, the accuracy of the digital twinborn model is improved, the risk resonance matrix is constructed according to the digital twinborn model and the equipment data for simulation risk analysis, the efficiency and accuracy of risk analysis are improved, and monitoring of engineering projects is effectively facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering project evaluation, and particularly to an engineering supervision project evaluation management method and system based on the Internet of Things. Background Art

[0002] In recent years, with the booming development of Internet of Things technology, the management mode of engineering supervision projects is transforming towards intelligence and digitization. The wide application of Internet of Things sensor devices enables the real-time collection of environmental data and equipment data at the engineering site, and through digital systems for comprehensive processing and analysis, so as to achieve efficient monitoring of construction progress, equipment status and environmental safety. Especially the introduction of digital twin technology, by creating a digital model highly consistent with the engineering site, can more intuitively and comprehensively simulate various dynamic changes during the construction process. However, in the existing technology, the construction of digital twin models often lacks sufficient physical accuracy and fails to fully consider the multi-physical field coupling effect between devices, resulting in insufficient accuracy of the model and the precision of risk assessment. Moreover, when dealing with complex linkage risks, it is unable to accurately predict the resonance effect between devices, leading to inaccuracies in risk assessment and early warning. Summary of the Invention

[0003] In view of the problems existing in the above-mentioned existing engineering supervision project evaluation management method and system based on the Internet of Things, the present invention is proposed.

[0004] Therefore, the problems to be solved by the present invention are that the construction of digital twin models often lacks sufficient physical accuracy and fails to fully consider the multi-physical field coupling effect between devices, resulting in insufficient accuracy of the model and the precision of risk assessment. Moreover, when dealing with complex linkage risks, it is unable to accurately predict the resonance effect between devices, leading to inaccuracies in risk assessment and early warning.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: An engineering supervision project evaluation management method based on the Internet of Things, which includes collecting and processing environmental data and equipment data at the engineering project site, and constructing a digital twin model of the engineering site; performing engineering equipment risk resonance analysis based on the digital twin model to construct a risk resonance matrix, and performing simulation risk early warning based on the risk resonance matrix; recording the digital twin model of the engineering site on the blockchain and updating it through real-time on-site environmental data and equipment data, and the blockchain synchronously performs data recording and storage.

[0006] As a preferred solution of the engineering supervision project evaluation and management method based on the Internet of Things according to the present invention, wherein: the collection and processing of the on-site environmental data and equipment data of the engineering project refers to deploying sensors to collect the on-site environmental data and equipment data of the engineering project, connecting the sensors through a wireless network to form a sensor network and connecting it to a console, the sensors sending the collected data to the console through the wireless network, and the console using a Kalman filter to perform noise filtering processing on the collected data and synchronizing the timestamps of the data collected by all sensors.

[0007] As a preferred solution of the engineering supervision project evaluation and management method based on the Internet of Things according to the present invention, wherein: the construction of the digital twin model of the engineering site refers to constructing the basic model of the engineering site, establishing the static equipment model according to the collected equipment data, and deploying the static equipment model to the corresponding position of the basic model of the engineering site according to the equipment positions on the engineering site;

[0008] Based on the equipment data, the equipment is decomposed into nodes through finite element analysis, the equipment stiffness matrix K is obtained according to the nodes, and the mass matrix M is constructed according to the equipment mass distribution. The damping matrix C is established based on the equipment stiffness matrix K and the mass matrix M using the damping coefficient;

[0009] The real-time external load f(t) of the equipment is obtained by integrating the environmental data and the equipment data, and a multi-physical coupling equation is constructed:

[0010]

[0011] where is the equipment speed, is the equipment acceleration, and u(t) is the equipment displacement;

[0012] The optimization objective function J is defined as:

[0013]

[0014] The value of the optimization objective function is calculated by collecting the equipment displacement data through the sensors, and the genetic algorithm is used to iteratively adjust the equipment speed and the equipment acceleration. The equipment speed and the equipment acceleration that minimize the value of the optimization objective function are output as equipment parameters;

[0015] The equipment displacement, the equipment speed, and the equipment acceleration are mapped to the static equipment model in real time and adjusted to construct the equipment dynamic model, thereby forming the digital twin model of the engineering site.

[0016] As a preferred solution of the engineering supervision project evaluation and management method based on the Internet of Things according to the present invention, wherein: the construction of the risk resonance matrix for the engineering equipment risk resonance analysis according to the digital twin model includes performing standardization processing on the collected equipment data, and obtaining the danger threshold F of each type of data in the equipment data according to the equipment parametersd ;

[0017] Define the time window as Δt, and calculate the risk value F of each type of data respectively i :

[0018]

[0019] where f i (t) is the value of the i-th type of data at time t, and t is the integration variable;

[0020] Calculate the change rate v according to trend fitting i , and calculate the tolerance time T i :

[0021]

[0022] Calculate the risk resonance value R of the device according to the risk value and tolerance time of each type of data:

[0023]

[0024] where w i is the weight of each type of data, and n is the number of data types;

[0025] Perform multiple linear regression analysis on all data of each device to establish a regression model, and calculate the state variable x of the device j , and calculate the Pearson correlation coefficient ρ between devices using the device state variable jk ;

[0026] Obtain the data sampling frequency and the number of sampling points, and calculate the cross-correlation function C between devices jk (τ):

[0027]

[0028] where x j (q) is the state variable of device j at time q, and x k (q + τ) is the state variable of device k at time q + τ, S is the number of sampling points within the time window Δt, q is the time of each sampling, and τ is the time delay;

[0029] Traverse all τ within the time window Δt, calculate the cross-correlation function values for each time delay respectively, and select the τ that maximizes the cross-correlation function value as the final time delay τ z ;

[0030] Calculate the linkage coefficient B between devices according to the final time delay jk :

[0031]

[0032] where β i is the influence coefficient of the regression model, and τ t is the maximum allowable time delay;

[0033] Based on the risk resonance value R of the device and the linkage coefficient B between devices jk calculate the linkage risk value A between devices jk :

[0034] A jk = R j * R k * B jk ;

[0035] Define the total number of devices as p, and construct a risk resonance matrix A based on the linkage risk value between devices.

[0036] As a preferred solution of the method for evaluating and managing engineering supervision projects based on the Internet of Things according to the present invention, wherein: the simulation risk early warning based on the risk resonance matrix refers to collecting environmental data and device data, and predicting future environmental data and device data based on the LSTM model;

[0037] Use feature engineering to extract the data features of future environmental data and device data, and construct a convolutional neural network for training. Set the input of the convolutional neural network as the risk resonance matrix and the data features of environmental data and device data, and the output as the device risk state, including device risk and device linkage risk. Define a cross-entropy loss function and an Adam optimizer to iteratively optimize the parameters of the convolutional neural network;

[0038] Input the risk resonance matrix and the data features of future environmental data and device data into the trained convolutional neural network to obtain the device risk state, and perform risk early warning according to the device risk state and notify the staff to eliminate the risks.

[0039] As a preferred solution of the method for evaluating and managing engineering supervision projects based on the Internet of Things according to the present invention, wherein: recording the digital twin model of the engineering site on the blockchain and updating it through real-time on-site environmental data and device data means uploading the constructed digital twin model to the blockchain, and performing real-time updates on the device dynamic model in the digital twin model through the real-time collected engineering site environmental data and device data, and performing simulation risk early warning according to the real-time updated digital twin model.

[0040] As a preferred solution of the method for evaluating and managing engineering supervision projects based on the Internet of Things according to the present invention, wherein: the blockchain synchronously records and stores data, which means that the blockchain stores the digital twin model in the cloud database and regularly synchronizes the real-time updated digital twin model to the stored digital twin model, and the blockchain generates a synchronization record and stores it in the database.

[0041] Another object of the present invention is to provide an engineering supervision project evaluation and management system based on the Internet of Things, which includes a data collection module for deploying sensors to collect engineering site environment data and equipment data and perform preprocessing;

[0042] A model construction module for constructing a static device model and calculating model parameters through equipment data to map to the static device model for model adjustment to form a digital twin model;

[0043] A resonance analysis module for analyzing the equipment risk resonance value according to the digital twin model and equipment data, calculating the linkage coefficient between devices and integrating it into the linkage risk value, and constructing a risk resonance matrix according to the linkage risk value;

[0044] A risk warning module for performing simulation risk warning according to the risk resonance matrix and equipment data;

[0045] A storage and update module for using the blockchain to record the digital twin model and updating and synchronously storing the digital twin model according to the real-time collected environment data and equipment data.

[0046] A computer device includes: a memory and a processor; the memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method for evaluating and managing engineering supervision projects based on the Internet of Things are implemented.

[0047] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for evaluating and managing engineering supervision projects based on the Internet of Things are implemented.

[0048] The beneficial effects of the present invention are as follows: by collecting engineering site environment data and equipment data, the present invention adopts finite element analysis and multi-physical coupling to solve model parameters, constructs a digital twin model according to the model parameters, improves the accuracy of the digital twin model, and constructs a risk resonance matrix according to the digital twin model and equipment data for simulation risk analysis, improving the efficiency and accuracy of risk analysis and effectively helping to monitor engineering projects. Description of the Drawings

[0049] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0050] Figure 1 It is a schematic flowchart of a method for evaluating and managing engineering supervision projects based on the Internet of Things.

[0051] Figure 2 It is a schematic structural diagram of a system for evaluating and managing engineering supervision projects based on the Internet of Things. Specific Embodiments

[0052] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the specific embodiments of the present invention in detail with reference to the accompanying drawings of the specification.

[0053] In the following description, many specific details are set forth to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0054] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that can be included in at least one implementation manner of the present invention. The "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is separate or selectively mutually exclusive with other embodiments.

[0055] Embodiment 1

[0056] Referring to Figure 1 , which is the first embodiment of the present invention. This embodiment provides a method for evaluating and managing engineering supervision projects based on the Internet of Things. The method for evaluating and managing engineering supervision projects based on the Internet of Things includes

[0057] S1. Collect the on-site environmental data and equipment data of the engineering project for processing, and construct a digital twin model of the engineering site;

[0058] Specifically, collecting and processing on-site environmental data and equipment data of the engineering project means deploying sensors to collect on-site environmental data and equipment data of the engineering project. Environmental sensors are used to monitor the on-site environment of the project, such as temperature sensors, humidity sensors, wind speed sensors, and air quality sensors, etc. Equipment sensors are used to monitor on-site equipment, such as vibration sensors, structure sensors, stress sensors, and displacement sensors, etc. At the same time, the equipment data also includes equipment basic information and equipment parameters. Connect the sensors through a wireless network to form a sensor network and connect it to the console. The sensors send the collected data to the console through the wireless network. The console uses the Kalman filter to perform noise filtering processing on the collected data and synchronize the timestamps of the data collected by all sensors.

[0059] By monitoring the environment and equipment status in real time, potential environmental threats and equipment failures can be detected in a timely manner, reducing construction delays and safety accidents caused by external factors or equipment damage, providing comprehensive data support, which helps project managers formulate more scientific engineering scheduling and equipment maintenance plans. Through the Kalman filter, the system can filter out the noise in the data, improve the quality of the data, and ensure more accurate subsequent analysis. The processing of timestamp synchronization avoids the problem of data inconsistency between multiple sensors, ensuring accurate monitoring and real-time analysis of the project status. The wireless sensor network can flexibly and quickly adapt to on-site requirements, reducing the complexity of wiring and increasing the possibility of system expansion. Since the sensor network does not need to rely on a complex hardware structure, it can work efficiently in a complex and changeable engineering on-site environment, ensuring the continuity and real-time nature of the data. The risk assessment based on high-quality data can significantly improve the response speed of the engineering supervision system, avoid potential safety problems, the system can issue warning signals in a timely manner to remind managers to take countermeasures, reduce construction risks, and improve engineering efficiency and safety.

[0060] Furthermore, constructing a digital twin model of the engineering site means constructing a basic model of the engineering site, establishing an equipment static model based on the collected equipment data, and deploying the equipment static model to the corresponding position of the basic model of the engineering site according to the equipment positions on the engineering site;

[0061] Based on the equipment data, decompose the equipment into nodes through finite element analysis, obtain the equipment stiffness matrix K according to the nodes, and construct the mass matrix M according to the equipment mass distribution:

[0062] K = ∫ V B T DBdV;

[0063] where B is the displacement-strain matrix, which is obtained by decomposing the engineering equipment into nodes through finite element analysis for analysis, B Tis the transpose of the displacement strain matrix, D is the material stiffness matrix obtained from the elastic modulus and Poisson's ratio of the device material, and V is the volume of the device;

[0064] Based on the damping coefficient, the damping matrix C is established using the device stiffness matrix K and the mass matrix M:

[0065] C = αK + βM;

[0066] where α and β are damping coefficients obtained through experimental measurements;

[0067] The real-time external load f(t) of the device is obtained by synthesizing environmental data and device data, such as the combined vector of forces such as wind force, gravity, device power, and construction collision, and a multi-physical coupling equation is constructed:

[0068]

[0069] where is the device velocity, is the device acceleration, and u(t) is the device displacement;

[0070] The optimization objective function J is defined as:

[0071]

[0072] The optimization objective function value is calculated by collecting device displacement data through sensors, and the genetic algorithm is used to iteratively adjust the device velocity and device acceleration. The device velocity and device acceleration that minimize the optimization objective function value are output as device parameters;

[0073] The device displacement, device velocity, and device acceleration are mapped to the device static model in real time and adjusted to construct a device dynamic model, and then a digital twin model of the engineering site is formed.

[0074] In actual engineering projects, equipment may be moved or adjusted during different construction stages. By deploying and adjusting the static model of equipment in real time, project managers can more accurately grasp the real-time position and working status of each piece of equipment, reducing errors in manual recording and monitoring. The establishment and deployment of the static model of equipment enable the visualization and digitalization of the equipment layout at the construction site, facilitating construction planning and resource scheduling. For example, through the layout of the static model, managers can optimize the arrangement and distribution of equipment, improve construction efficiency, and reduce interference between equipment. Through the decomposition and analysis of nodes, the system can accurately evaluate the structural strength and material properties of equipment, especially for key equipment during construction. By analyzing the stress and displacement of equipment, potential design defects can be detected at the early stage of the project and corrected before the project starts, reducing the risk of equipment failures during construction. Finite element analysis is not only used for real-time construction monitoring but also provides important data support for the long-term management of equipment. Through long-term monitoring after node decomposition, managers can regularly evaluate the fatigue life and material degradation of equipment, providing a scientific basis for the regular maintenance and replacement of equipment. By setting reasonable damping coefficients, the system can significantly reduce the mechanical stress caused by frequent vibrations during equipment operation, thereby enhancing the overall stability and working life of the equipment. This is particularly important for key equipment (such as cranes, excavators, etc.) that are in a high-stress environment for a long time. The optimization of the damping system can also reduce the vibration transmission of equipment operation to the surrounding environment, reducing noise pollution and vibration impact. Especially for construction projects in densely populated urban areas, damping optimization is particularly important. By real-time monitoring of various external forces (such as wind loads, equipment dynamic loads, earthquakes, etc.), the system can issue early warnings when external conditions become abnormal and avoid equipment failures or construction accidents by adjusting the working parameters of the equipment. This greatly improves the safety of the construction site and reduces potential accident hazards. Multi-physical coupling analysis can help construction managers accurately control the operating state of equipment. By adjusting the acceleration and displacement of the equipment, the system can optimize the dynamic performance of the equipment to ensure that the equipment operates efficiently and stably under different working conditions. The system can continuously adjust the operating parameters of the equipment through genetic algorithms to keep it in the best state in a dynamic environment. Such an automatic optimization process reduces the need for human intervention and improves the operating efficiency and intelligent level of the equipment. The construction site is often in an uncertain and dynamically changing environment. The application of genetic algorithms enables the system to quickly adapt to these changes and find the optimal equipment operating strategy under complex multi-variable coupling conditions to ensure the efficient operation of the equipment in different scenarios. The dynamic model combined with digital twin technology can achieve real-time monitoring and status prediction of equipment. Managers can intuitively observe the operating state of the equipment through the virtual model and take necessary measures before the equipment is about to fail. The digital twin model covers the entire construction site and can real-time monitor the working status of each piece of equipment and changes in the external environment. This all-round management mode improves construction efficiency.Reduces unnecessary downtime and economic losses caused by equipment failures.

[0075] S2. Conduct engineering equipment risk resonance analysis based on the digital twin model to construct a risk resonance matrix, and conduct simulation risk warning based on the risk resonance matrix;

[0076] Specifically, conducting engineering equipment risk resonance analysis based on the digital twin model to construct a risk resonance matrix includes standardizing the collected equipment data, and obtaining the hazard threshold F of each type of data in the equipment data according to the equipment parameters d ;

[0077] Define the time window as Δt, and calculate the risk value F of each type of data respectively i :

[0078]

[0079] where f i (t) is the value of the i-th type of data at time t, and t is the integration variable;

[0080] Calculate the change rate v according to trend fitting i , and calculate the tolerance time T i :

[0081]

[0082] Calculate the risk resonance value R of the equipment according to the risk value and tolerance time of each type of data:

[0083]

[0084] where w i is the weight of each type of data, and n is the number of data types;

[0085] Conduct multiple linear regression analysis on all the data of each device to establish a regression model, and calculate the state variable x of the device j :

[0086] x j (t) = β 0 + β 1 f 1 (t)+……+ β n f n (t)+∈;

[0087] where β i is the influence coefficient, and ∈ is the error term;

[0088] Calculate the Pearson correlation coefficient ρ between devices using the device state variable jk ;

[0089] Obtain the data sampling frequency and the number of sampling points, and calculate the cross-correlation function C jk (τ):

[0090]

[0091] where x j (q) is the state variable of device j at time q, and x k (q + τ) is the state variable of device k at time q + τ, S is the number of sampling points within the time window Δt, q is the time of each sampling, and τ is the time delay;

[0092] Traverse all τ within the time window Δt, calculate the cross-correlation function values for each time delay respectively, and select the τ that maximizes the cross-correlation function value as the final time delay τ z ;

[0093] Calculate the linkage coefficient B between devices according to the final time delay jk :

[0094]

[0095] where β i is the influence coefficient of the regression model, and τ t is the maximum allowable time delay;

[0096] Calculate the linkage risk value A between devices according to the risk resonance value R of the devices and the linkage coefficient B jk : jk :

[0097] A jk = R j * R k * B jk ;

[0098] Define the total number of devices as p, and construct the risk resonance matrix A according to the linkage risk values between devices:

[0099]

[0100] where A ij is the linkage risk value of device i to device j.

[0101] The standardized data enables different types of data to have the same scale, so that they can be compared and analyzed within the same framework, avoiding errors caused by different data dimensions, improving the accuracy of the model. By combining the specific physical attributes of the device and the operation historical data, the present invention can customize exclusive danger thresholds for each device, avoiding the generalization problem brought about by uniformly setting thresholds in traditional methods, thereby enhancing the accuracy of risk warning. The risk value calculation does not solely rely on the data at a single time point, but dynamically monitors the data over a period of time to capture the trend changes of the device. This method improves the sensitivity of risk assessment, enabling the system to identify abnormal conditions in the device operation earlier. By trend fitting and calculating the tolerance time based on the change rate, the system can accurately predict the time for the device to continue operating in a dangerous state. This accuracy allows the manager to take flexible countermeasures according to the tolerance time, avoiding premature shutdown or delaying the intervention time, and enhancing the maintenance efficiency. Multiple linear regression can not only identify the influence of a single variable on the device state, but also reveal the interaction between multiple variables. Through this model, the health state of the device can be more comprehensively evaluated by the combined action of multiple factors. Compared with traditional single-variable analysis methods, the present invention more accurately describes the complex relationship between the device state and the external environment through multiple linear regression, reducing the evaluation error caused by ignoring related factors, thereby enhancing the reliability of device state monitoring. When highly correlated devices fail, they may produce a chain effect, causing other devices to be affected. Through the analysis of the Pearson correlation coefficient, the present invention can quickly identify these high-risk devices, helping the manager to take preventive measures in advance. Through the device correlation analysis, the manager can better allocate maintenance resources, concentrating more maintenance and monitoring resources on devices with high correlation, thereby improving the efficiency and effectiveness of device maintenance. The interaction between devices often does not occur synchronously, but there is a certain time delay. Through the cross-correlation function analysis, the present invention can identify the optimal delay time between devices, thereby more accurately predicting the chain risk between devices. By identifying the time delay between devices, the system can accurately predict the propagation path and time of device failures, providing a more timely basis for risk warning. By accurately calculating the coupling coefficient, the present invention can conduct a refined analysis of the chain risk between devices, not only identifying which devices have chain risks, but also evaluating the intensity and propagation speed of this risk. The coupling coefficient and the risk resonance value provide a reliable decision-making basis for the manager, helping them to adopt corresponding strategies according to the risk level of the device and the chain risk, such as priority maintenance, adjusting device operation parameters or installing protection measures. The risk resonance matrix provides an intuitive tool for the manager, enabling them to grasp the chain risk between devices globally, ensuring that risks are not overlooked when managing large-scale complex engineering projects. The risk resonance matrix can be dynamically adjusted with the update of real-time data.This enables the system to reflect the latest risk status of the device at any time, ensuring that managers can take timely countermeasures and improving the safety and stability of the project.

[0102] Furthermore, simulating risk early warning according to the risk resonance matrix means collecting environmental data and device data, and predicting future environmental data and device data based on the LSTM model;

[0103] Using feature engineering to extract the data features of future environmental data and device data, and constructing a convolutional neural network for training. Set the input of the convolutional neural network as the risk resonance matrix and the data features of environmental data and device data, and the output as the device risk status, including device risk and device linkage risk. Define the cross-entropy loss function and the Adam optimizer to iteratively optimize the parameters of the convolutional neural network;

[0104] Input the risk resonance matrix and the data features of future environmental data and device data into the trained convolutional neural network to obtain the device risk status. Conduct risk early warning according to the device risk status and notify the staff to eliminate the risks.

[0105] Through the time series prediction of the LSTM model, the system can grasp the future environment and equipment change trends in advance, helping engineering managers to formulate risk response strategies in advance. Since LSTM can effectively capture the long-term dependencies in time series data, the prediction results are highly stable, providing a reliable data basis for subsequent risk warnings. Feature engineering can extract the most valuable information from a large amount of raw data, avoiding the interference of irrelevant or redundant information on model performance, thereby improving the training effect of CNN. Through high-quality feature extraction, the model can better capture the patterns behind the data, so that when facing new environment and equipment data, CNN can maintain good risk assessment performance. CNN is good at processing multi-dimensional data and can analyze complex equipment data and environmental data in a short time to identify potential risk areas. By inputting the risk resonance matrix, CNN can not only analyze the risks of a single device, but also capture the risks between devices. The Adam optimizer can reduce the training time while maintaining a high model accuracy, and is particularly suitable for complex convolutional neural network training scenarios. The cross entropy loss function can effectively measure the classification error of the equipment risk status, ensuring the risk identification accuracy of the model in actual engineering applications. Based on simulation risk analysis, the system can warn of the risk status of the equipment in advance, ensuring that managers can take measures before risks occur to reduce the probability of accidents. Through real-time monitoring and early warning, the system can effectively reduce construction delays and safety accidents caused by equipment failures, and improve the safety and efficiency of the overall project. The combination of risk resonance matrix and predicted data provides the system with a more global risk perspective, which can fully identify the complex linkage relationship between equipment and reduce the occurrence of hidden risks. By combining the prediction of future environment and equipment data, the system can achieve more accurate risk assessment and ensure the timeliness and accuracy of early warning.

[0106] S3. Record the digital twin model of the project site in the blockchain and update it with real-time on-site environmental data and equipment data. The blockchain will simultaneously record and store data.

[0107] Specifically, recording the digital twin model of the engineering site on the blockchain and updating it through real-time on-site environmental data and equipment data means uploading the constructed digital twin model to the blockchain, updating the equipment dynamic model in the digital twin model in real time through the real-time collected engineering site environmental data and equipment data, and issuing simulation risk warnings based on the real-time updated digital twin model.

[0108] Through blockchain technology, the data of the digital twin model can be securely stored, preventing data from being tampered with or lost, ensuring data transparency and credibility during the engineering supervision process. The distributed nature of the blockchain enables multiple parties involved in the engineering project to access the same digital twin model in real time, promoting collaborative management among multiple parties and enhancing the overall operational efficiency of the project. Through the continuous input of real-time data, the digital twin model can reflect the latest operating status of the equipment at any time, thus ensuring the timeliness and accuracy of the model and providing a more reliable basis for risk analysis. Real-time data collection and dynamic update enable the system to accurately monitor the operating conditions of the equipment, identify potential failure risks in advance, and provide data support for subsequent simulation warnings. Each data block of the blockchain records the timestamp and historical update information, so users can trace the evolution history of the digital twin model at any time and verify the authenticity of the data. The blockchain provides a reliable sharing platform for all parties involved in the project. The participants can make decisions and manage based on consistent data, reducing communication barriers and management mistakes caused by inconsistent data. The simulation risk warning system can predict potential risks during equipment operation in advance based on real-time updated equipment status and environmental data, helping managers make intervention decisions before the risks occur and reducing the occurrence of sudden accidents. Through real-time monitoring and simulation warnings, the present invention can promptly identify equipment failures and issue early warning signals in advance, helping to reduce delays and safety accidents caused by equipment problems during the construction process.

[0109] Furthermore, the blockchain synchronously records and stores data, which means that the blockchain stores the digital twin model in the cloud database and regularly synchronizes the real-time updated digital twin model to the stored digital twin model. The blockchain generates a synchronization record and stores it in the database.

[0110] The cloud database provides a flexible storage solution, which can automatically expand or reduce the storage space according to the scale of the engineering project, thus improving the efficiency and cost-effectiveness of data storage. By storing the digital twin model in the cloud, all stakeholders of the project can access the updated model data at any time, realizing remote collaborative management and monitoring, and enhancing the transparency and collaborative efficiency of the engineering project. The distributed ledger feature of the blockchain ensures that the data after the digital twin model is updated cannot be tampered with or deleted. This mechanism makes the data management of the entire system more transparent, preventing data leakage or loss caused by human operation or system failure. Since each model synchronization operation is recorded and a unique synchronization record is generated, the blockchain can provide a reliable audit path for the project, ensuring that each change is legal and traceable. This not only helps to improve the standardization of data management but also provides a strong guarantee for risk control in engineering projects.

[0111] Embodiment 2

[0112] Refer to Figure 2, which is the second embodiment of the present invention. This embodiment is different from the previous one and provides an engineering supervision project evaluation management system based on the Internet of Things, including

[0113] A data collection module for deploying sensors to collect engineering site environment data and equipment data and performing preprocessing;

[0114] A model construction module for constructing a device static model and calculating model parameters through device data, mapping them to the device static model for model adjustment to form a digital twin model;

[0115] A resonance analysis module for analyzing the device risk resonance value based on the digital twin model and device data, calculating the linkage coefficient between devices and integrating it into the linkage risk value, and constructing a risk resonance matrix based on the linkage risk value;

[0116] A risk warning module for performing simulation risk warning based on the risk resonance matrix and device data;

[0117] A storage and update module for using blockchain to record the digital twin model and updating and synchronously storing the digital twin model according to the real-time collected environment data and equipment data.

[0118] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0119] The logic and / or steps represented in the flowchart or otherwise described herein can, for example, be considered as a definitional sequence list of executable instructions for implementing logical functions, and can be embodied specifically in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0120] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection portion having one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or, if necessary, other suitable processing, and then storing it in a computer memory.

[0121] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), and the like.

[0122] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A project evaluation management method for engineering supervision based on the Internet of Things, characterized by: include, Collect and process the on-site environmental data and equipment data of the project, and build a digital twin model of the project site; Conduct risk resonance analysis of engineering equipment based on the digital twin model to build a risk resonance matrix, and conduct simulation risk warning based on the risk resonance matrix; The digital twin model of the engineering site is recorded in the blockchain and updated with real-time on-site environmental data and equipment data. The blockchain also records and stores the data synchronously.

2. The engineering supervision project evaluation management method based on the Internet of Things as claimed in claim 1, characterized in that: The collecting of environmental data and equipment data at the project site for processing refers to deploying sensors to collect environmental data and equipment data at the project site, connecting the sensors to form a sensor network through a wireless network and connecting them to a console, the sensors sending the collected data to the console through the wireless network, the console using a Kalman filter to perform noise filtering on the collected data, and synchronizing the timestamps of all sensor data collection.

3. The engineering supervision project evaluation management method based on the Internet of Things as claimed in claim 2 is characterized by: The construction of the digital twin model of the engineering site refers to constructing a basic model of the engineering site, establishing a static model of the equipment according to the collected equipment data, and deploying the static model of the equipment to the corresponding position of the basic model of the engineering site according to the equipment position of the engineering site; Based on the equipment data, the equipment is decomposed into nodes through finite element analysis, and the equipment stiffness matrix K is obtained according to the nodes, and the mass matrix M is constructed according to the equipment mass distribution. The damping matrix C is established based on the damping coefficient using the equipment stiffness matrix K and the mass matrix M; The real-time device external load f(t) is obtained by integrating environmental data and device data, and a multi-physics coupling equation is constructed: in is the device velocity, üu(t) is the device acceleration, and u(t) is the device displacement; The optimization objective function J is defined as: The device displacement data is collected by sensors to calculate the optimization objective function value, and the device speed and device acceleration are iteratively adjusted using a genetic algorithm, and the device speed and device acceleration that minimize the optimization objective function value are output as device parameters; The equipment displacement, equipment speed and equipment acceleration are mapped to the equipment static model in real time and adjusted to build the equipment dynamic model, thereby forming a digital twin model of the engineering site.

4. The engineering supervision project evaluation management method based on the Internet of Things as claimed in claim 3 is characterized by: The risk resonance analysis of engineering equipment based on the digital twin model to construct a risk resonance matrix includes standardizing the collected equipment data and obtaining the danger threshold F of each type of equipment data according to the equipment parameters. d ; Define the time window as Δt and calculate the risk value F for each type of data i : where f i (t) is the value of the i-th data at time t, and t is the integral variable; Calculate the rate of change v based on trend fitting i , and calculate the tolerance time T i : Calculate the risk resonance value R of the equipment based on each data risk value and tolerance time: where w i is the weight of each data, n is the data type; Perform multiple linear regression analysis on all data of each device to establish a regression model and calculate the state variable x of the device. j , and use the device state variables to calculate the Pearson correlation coefficient ρ between devices jk ; Get the data sampling frequency and number of sampling points, and calculate the cross-correlation function C between devices jk (τ): where x j (q) is the state variable of device j at time q, x k (q+τ) is the state variable of device k at time q+τ, S is the number of sampling points in the time window Δt, q is the time of each sampling, and τ is the time delay; Traverse all τ in the time window Δt, calculate the cross-correlation function value of each time delay respectively, and select the τ that makes the cross-correlation function value the largest as the final time delay τ z ; Calculate the linkage coefficient B between devices based on the final time delay jk : where β i is the influence coefficient of the regression model, τ t is the maximum allowed time delay; According to the risk resonance value R of the equipment and the linkage coefficient B between the equipment jk Calculate the linkage risk value A between devices jk : A jk =R j *R k *B jk ; Define the total number of devices as p, and construct the risk resonance matrix A based on the linkage risk values ​​between devices.

5. The engineering supervision project evaluation management method based on the Internet of Things as claimed in claim 4 is characterized by: The simulation risk warning according to the risk resonance matrix refers to collecting environmental data and equipment data, and predicting future environmental data and equipment data based on the LSTM model; Use feature engineering to extract data features of future environmental data and equipment data, and build a convolutional neural network for training. Set the convolutional neural network input as the risk resonance matrix and data features of environmental data and equipment data, and output as the equipment risk status, including equipment risk and equipment linkage risk. Define the cross entropy loss function and Adam optimizer to iteratively optimize the convolutional neural network parameters. The data features of the risk resonance matrix and future time environmental data and equipment data are input into the trained convolutional neural network to obtain the equipment risk status. Risk warnings are issued based on the equipment risk status and staff are notified to eliminate the risks.

6. The engineering supervision project evaluation management method based on the Internet of Things as claimed in claim 5 is characterized by: The recording of the engineering site digital twin model on the blockchain and updating it through real-time site environment data and equipment data refers to uploading the constructed digital twin model to the blockchain, updating the equipment dynamic model in the digital twin model in real time through the real-time collected engineering site environment data and equipment data, and issuing simulation risk warnings based on the real-time updated digital twin model.

7. The engineering supervision project evaluation management method based on the Internet of Things as claimed in claim 6 is characterized by: The blockchain synchronizes data records and stores data, which means that the blockchain stores the digital twin model in a cloud database, and regularly synchronizes the real-time updated digital twin model to the stored digital twin model. The blockchain generates synchronization records and stores them in the database.

8. An engineering supervision project evaluation management system based on the Internet of Things according to any one of claims 1 to 7, characterized in that: include, Data collection module, used to deploy sensors to collect engineering site environmental data and equipment data and perform pre-processing; A model building module is used to build a static model of the equipment and calculate the model parameters through equipment data and map them to the static model of the equipment to adjust the model and form a digital twin model; The resonance analysis module is used to analyze the equipment risk resonance value based on the digital twin model and equipment data, calculate the linkage coefficient between the equipment and integrate it into the linkage risk value, and build a risk resonance matrix based on the linkage risk value; Risk warning module, used to conduct simulation risk warning based on risk resonance matrix and equipment data; The storage update module is used to use blockchain to record the digital twin model and update and synchronize the digital twin model based on the environmental data and equipment data collected in real time.

9. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the engineering supervision project evaluation management method based on the Internet of Things described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the engineering supervision project evaluation management method based on the Internet of Things described in any one of claims 1 to 7 are implemented.

Images