Analysis system for intelligent construction of nuclear power construction

Abstract

The invention relates to the technical field of building construction, and particularly discloses a nuclear power construction intelligent building construction analysis system, which comprises a data acquisition module, a big data analysis module, a digital twin module, an emergency response module, a logistics management module and an information sharing module, the sensor network and the data processing platform are arranged to collect and analyze various data of the construction site in real time, so that managers can master the construction progress in time, make decisions quickly, reduce delay and shutdown time in construction, predict and optimize the construction data through a machine learning algorithm, help to optimize the construction scheme, and improve the construction efficiency. The sensor network monitors the stress and deformation conditions of key structure parts in real time, the construction quality is ensured, potential structure problems are found and prevented in time, the digital twinning technology can achieve virtual and real linkage, it is ensured that construction is conducted according to design specifications, and the construction quality is improved.

Description

Technical Field

[0001] The present invention relates to the field of nuclear power engineering construction, and in particular to an analysis system for intelligent construction of nuclear power construction. Background Art

[0002] There are a series of problems in traditional engineering construction, such as construction management methods often rely on manual monitoring, paper records and regular progress reports. These methods are not only inefficient, but also difficult to accurately reflect the real-time dynamics of the construction site. The construction progress is difficult to track in real time, the construction quality is difficult to effectively ensure, the equipment utilization rate is low, and the material management is chaotic.

[0003] With the rapid development of information technology, especially the continuous maturity of technologies such as the Internet of Things, big data, artificial intelligence and machine learning, the construction management of nuclear power construction is ushering in a revolutionary change. By real-time monitoring and analysis of various data at the construction site, managers can be provided with accurate and timely construction information to help them make more scientific and reasonable decisions, optimize construction plans and improve construction efficiency. However, in actual construction, there are still certain difficulties in implementing the above technologies. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide an analysis system for the intelligent construction of nuclear power construction, which provides accurate and timely construction information, is conducive to optimizing the construction plan and improving construction efficiency.

[0005] The present invention provides an analysis system for intelligent construction of nuclear power construction, comprising:

[0006] The data acquisition module uses a sensor network to obtain environmental condition data of the nuclear power construction site, obtain real-time status data of key structural parts, and locate and track location information data of construction equipment and personnel to obtain sensor data;

[0007] The big data analysis module cleans, stores and manages the sensor data, and then uses machine learning algorithms to analyze it, predict progress, identify risks, optimize construction plans, obtain analysis results, and provide scientific decision-making suggestions based on the analysis results;

[0008] The digital twin module integrates design, construction, and operation and maintenance information to form a unified 3D model, supports collaborative management, uses digital twin technology to build a virtual construction site, realizes the linkage between virtual and reality, and optimizes the construction process;

[0009] The emergency response module quickly responds to emergencies based on analysis results, implements all-weather safety monitoring and risk warning, and ensures the safety of construction personnel and equipment;

[0010] The logistics management module optimizes the supply chain management of materials and equipment through data analysis to ensure timely delivery and reasonable inventory, monitor the use of construction resources in real time, optimize scheduling plans, and improve resource utilization efficiency;

[0011] The information sharing module displays the construction progress through 3D visualization technology, which helps managers understand the construction status in real time and builds a unified information sharing platform to ensure that all participants can obtain the latest construction information in a timely manner and promote collaborative work.

[0012] In a specific embodiment of the present invention, it is characterized in that the sensor network includes environmental monitoring sensors, structural health monitoring sensors and location tracking sensors.

[0013] In a specific embodiment of the present invention, the environment monitoring sensor monitors the temperature of the environment, which is expressed as:

[0014]

[0015] Where T represents temperature;

[0016] Vout represents the sensor output voltage;

[0017] V0 represents the reference voltage;

[0018] k represents the sensor sensitivity,

[0019] By displaying the data collected by the sensor, the temperature of the construction site is calculated to ensure a suitable construction environment;

[0020] Structural health monitoring sensors monitor stress, expressed as:

[0021]

[0022] Where σ represents stress; F represents applied force; A represents the area under force;

[0023] Monitor the stress of structural components in real time to prevent structural damage.

[0024] 4. The analysis system for intelligent construction of nuclear power construction according to claim 1 is characterized in that the machine learning algorithm adopts a linear regression model and uses historical construction data to predict construction progress and risks, and the predicted progress is expressed as:

[0025] y=β0+β1x1+...+βnxn

[0026] Where y represents the prediction result;

[0027] β0 represents the intercept;

[0028] β1,β2,…,βn represent regression coefficients;

[0029] x1, x2,…, xn represent input variables;

[0030] Identify risks as:

[0031]

[0032] Where P(y=1|x) represents the probability of an event occurring;

[0033] β0,β1,β2,…,βn represent regression coefficients;

[0034] x1, x2,…, xn represent input variables;

[0035] Identify risks that arise during the construction process by analyzing field data.

[0036] In a specific embodiment of the present invention, the digital twin technology synchronizes real-time data into the digital twin model to keep the virtual model consistent with the actual construction status. The status update formula is expressed as:

[0037] X(t+1)=f(X(t),U(t))

[0038] Where X(t) represents the current state;

[0039] X(t+1) represents the state at the next moment;

[0040] U(t) represents the control input;

[0041] f represents the state transfer function.

[0042] In a specific embodiment of the present invention, the risk warning is performed by calculating the probability of various risks in the construction process through historical data and real-time monitoring, and the warning is expressed as:

[0043]

[0044] Where P(A|B) represents the probability of event A occurring after event B occurs;

[0045] P(B|A) represents the probability of event B occurring after event A occurs;

[0046] P(A)P represents the prior probability of event A occurring;

[0047] P(B) represents the prior probability of event B occurring.

[0048] In a specific embodiment of the present invention, the supply chain management uses linear programming, which is expressed as:

[0049] MinC H d

[0050] Subject to Md≤b

[0051] Where C represents the cost coefficient matrix;

[0052] d represents the decision variable;

[0053] M represents the constraint coefficient matrix;

[0054] b represents the constraint vector;

[0055] H represents the transpose of the matrix.

[0056] In a specific implementation of the present invention, the visualization technology uses a Gantt chart progress equation to represent progress visualization, which is expressed as:

[0057]

[0058] P i(t) represents the progress of task i at time t;

[0059] aij represents the workload ratio of task i and resource j;

[0060] uj(t) represents the usage of resource j at time t.

[0061] Compared with the prior art, the analysis system for intelligent construction of nuclear power construction of the present invention improves work efficiency, accurately reflects the real-time dynamics of the construction site, and effectively guarantees the construction quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 This is a block diagram of the analysis system for intelligent construction of nuclear power plants of the present invention;

[0063] Figure 2 The sensor network composition block diagram of the present invention. DETAILED DESCRIPTION

[0064] In order to further understand the present invention, the embodiments of the present invention are described below in conjunction with examples, but it should be understood that these descriptions are only for further illustrating the features and advantages of the present invention, rather than limiting the present invention.

[0065] See also Figure 1 to Figure 2 As shown, an analysis system for intelligent construction of nuclear power construction includes:

[0066] The data acquisition module uses a sensor network to obtain environmental condition data of the nuclear power construction site, obtain real-time status data of key structural parts, and locate and track location information data of construction equipment and personnel to obtain sensor data;

[0067] The big data analysis module cleans, stores and manages the sensor data, and then uses machine learning algorithms to analyze it, predict progress, identify risks, optimize construction plans, obtain analysis results, and provide scientific decision-making suggestions based on the analysis results;

[0068] The digital twin module integrates design, construction, and operation and maintenance information to form a unified 3D model, supports collaborative management, uses digital twin technology to build a virtual construction site, realizes the linkage between virtual and reality, and optimizes the construction process;

[0069] The emergency response module quickly responds to emergencies based on analysis results, implements all-weather safety monitoring and risk warning, and ensures the safety of construction personnel and equipment;

[0070] The logistics management module optimizes the supply chain management of materials and equipment through data analysis to ensure timely delivery and reasonable inventory, monitor the use of construction resources in real time, optimize scheduling plans, and improve resource utilization efficiency;

[0071] The information sharing module displays the construction progress through 3D visualization technology, which helps managers understand the construction status in real time and builds a unified information sharing platform to ensure that all participants can obtain the latest construction information in a timely manner and promote collaborative work.

[0072] The sensor network includes an environmental monitoring sensor, a structural health monitoring sensor and a position tracking sensor. The environmental monitoring sensor monitors the temperature of the environment, which is expressed as:

[0073]

[0074] Where T represents temperature;

[0075] Vout represents the sensor output voltage;

[0076] V0 represents the reference voltage;

[0077] k represents the sensor sensitivity,

[0078] By displaying the data collected by the sensor, the temperature of the construction site is calculated to ensure a suitable construction environment;

[0079] Similarly, the environmental monitoring sensor can also monitor the humidity of the environment.

[0080] Structural health monitoring sensors monitor stress, expressed as:

[0081]

[0082] Where σ represents stress; F represents applied force; A represents the area under force;

[0083] Monitor the stress of structural components in real time to prevent structural damage.

[0084] The machine learning algorithm adopts a linear regression model and uses historical construction data to predict construction progress and risks. The predicted progress is expressed as:

[0085] y=β0+β1x1+...+βnxn

[0086] Where y represents the prediction result;

[0087] β0 represents the intercept;

[0088] β1,β2,…,βn represent regression coefficients;

[0089] x1, x2,…, xn represent input variables;

[0090] Identify risks as:

[0091]

[0092] Where P(y=1|x) represents the probability of an event occurring;

[0093] β0,β1,β2,…,βn represent regression coefficients;

[0094] x1, x2,…, xn represent input variables;

[0095] Identify risks that arise during the construction process by analyzing field data.

[0096] The digital twin technology synchronizes real-time data to the digital twin model to keep the virtual model consistent with the actual construction status. The status update formula is expressed as:

[0097] X(t+1)=f(X(t),U(t))

[0098] Where X(t) represents the current state;

[0099] X(t+1) represents the state at the next moment;

[0100] U(t) represents the control input;

[0101] f represents the state transfer function.

[0102] The risk warning is based on historical data and real-time monitoring to calculate the probability of various risks in the construction process and issue warnings, which are expressed as:

[0103]

[0104] Where P(A|B) represents the probability of event A occurring after event B occurs;

[0105] P(B|A) represents the probability of event B occurring after event A occurs;

[0106] P(A)P represents the prior probability of event A occurring;

[0107] P(B) represents the prior probability of event B occurring.

[0108] The supply chain management uses linear programming to optimize the supply chain of materials and equipment, reduce costs and improve efficiency, which can be expressed as:

[0109] MinC H d

[0110] Subject to Md≤b

[0111] Where C represents the cost coefficient matrix;

[0112] d represents the decision variable;

[0113] M represents the constraint coefficient matrix;

[0114] b represents the constraint vector;

[0115] H represents the transpose of the matrix.

[0116] The visualization technique uses the Gantt chart progress equation to represent the progress visualization, which is expressed as:

[0117]

[0118] P i(t) represents the progress of task i at time t;

[0119] aij represents the workload ratio of task i and resource j;

[0120] uj(t) represents the usage of resource j at time t;

[0121] The progress equation shows the completion status of each task, making it easier for managers to track progress.

[0122] Embodiment 1:

[0123] The progress forecast of infrastructure construction of a nuclear power plant is as follows:

[0124] 1) Data collection

[0125] Environmental monitoring sensor data:

[0126] Temperature sensor output voltage Vout: 610;

[0127] Reference voltage V0: 500;

[0128] Sensor sensitivity k (mV / ℃): 10;

[0129] Structural Health Monitoring Sensor Data:

[0130] Force F (N): 2000;

[0131] Force area A(mm 2 ):100;

[0132] Ambient temperature calculation:

[0133] T=(Vout-V0) / k=(610-500) / 10=11℃;

[0134] Structural stress calculation:

[0135] σ=F / A=2000 / 100=20 MPa;

[0136] 2) Big Data Analysis

[0137] Historical construction data:

[0138] Construction days X (days): [10, 20, 30, 40, 50];

[0139] Completion progress Y (%): [15, 30, 45, 60, 75];

[0140] Linear regression model training:

[0141] y = β0 + β1x;

[0142] Training results:

[0143] Intercept β0: 0.5%;

[0144] Regression coefficient β1: 1.5%;

[0145] Construction progress forecast: forecast the construction progress on a certain day, for example, the 60th day: y = β0 + β1x = 0.5% + 1.5% × 60 = 90.5%;

[0146] 3) Logistics Management

[0147] Materials and equipment supply chain optimization:

[0148] Cost coefficient matrix C: [10, 20, 30];

[0149] Decision variable x: [5, 10, 15];

[0150] Constraint coefficient matrix A: [[1,2,3],[2,1,2]];

[0151] Constraint vector b: [30,20];

[0152] Linear programming solution: Objective: Minimize CTx = 10 × 5 + 20 × 10 + 30 × 15 = 850;

[0153] Constraints: Ax≤b;

[0154] 4) Emergency Response

[0155] Risk warning: Assume that historical risk data of a construction operation is identified:

[0156] Event A: Equipment failure;

[0157] Event B: The ambient temperature is higher than 25°C;

[0158] P(B|A): 0.8;

[0159] P(A): 0.1;

[0160] P(B): 0.2;

[0161] Bayesian risk calculation:

[0162] P(A∣B)=P(B∣A)·P(A)P(B)=0.8×0.1 / 0.2=0.4;

[0163] 5) Information Sharing

[0164] Visualization of construction progress: Display the progress of construction tasks through Gantt chart: Task 1: Infrastructure construction, planned time: 30 days, actual completion: 25 days Task 2: Equipment installation, planned time: 20 days, actual completion: 22 days;

[0165] The test data is shown in Table 1 below:

[0166] Table 1

[0167]

[0168]

[0169] Through the above steps and data, each component of the nuclear power construction intelligent construction analysis system can be fully tested to ensure its effectiveness and reliability.

[0170] From the above, we can see that by setting up a sensor network and a data processing platform to collect and analyze various data at the construction site in real time, managers can keep abreast of the construction progress, make decisions quickly, reduce delays and downtime in construction, and predict and optimize construction data through machine learning algorithms to help optimize construction plans and improve construction efficiency.

[0171] The sensor network monitors the stress and deformation of key structural parts in real time to ensure construction quality and promptly discover and prevent potential structural problems. Digital twin technology can realize the linkage between virtual and reality, ensure that construction is carried out in accordance with design specifications, improve construction quality, and respond quickly to emergencies based on analysis results and emergency response modules to ensure the safety of construction personnel and equipment.

[0172] Through the Internet of Things technology, construction equipment can be uniformly managed and scheduled, equipment status can be monitored in real time, equipment utilization can be improved, and equipment failure rate can be reduced. The intelligent logistics management system optimizes the supply chain management of materials and equipment, ensures timely delivery and reasonable inventory, and reduces waste and costs.

[0173] The unified information sharing platform ensures that all participants can obtain the latest construction information in a timely manner, promotes collaborative work, and improves overall construction efficiency. The construction progress is displayed through 3D visualization technology, which makes it easier for managers to understand the construction status in real time and coordinate resources from all parties.

[0174] The above embodiments are only used to help understand the method and core idea of ​​the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made to the present invention without departing from the principles of the present invention, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

[0175] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An analysis system for intelligent construction of nuclear power plants. It is characterized in that include: The data acquisition module uses a sensor network to obtain environmental condition data of the nuclear power construction site, obtain real-time status data of key structural parts, and locate and track location information data of construction equipment and personnel to obtain sensor data; The big data analysis module cleans, stores and manages the sensor data, and then uses machine learning algorithms to analyze it, predict progress, identify risks, optimize construction plans, obtain analysis results, and provide scientific decision-making suggestions based on the analysis results; The digital twin module integrates design, construction, and operation and maintenance information to form a unified 3D model, supports collaborative management, uses digital twin technology to build a virtual construction site, realizes the linkage between virtual and reality, and optimizes the construction process; The emergency response module quickly responds to emergencies based on analysis results, implements all-weather safety monitoring and risk warning, and ensures the safety of construction personnel and equipment; The logistics management module optimizes the supply chain management of materials and equipment through data analysis to ensure timely delivery and reasonable inventory, monitor the use of construction resources in real time, optimize scheduling plans, and improve resource utilization efficiency; The information sharing module displays the construction progress through 3D visualization technology, which helps managers understand the construction status in real time and builds a unified information sharing platform to ensure that all participants can obtain the latest construction information in a timely manner and promote collaborative work.

2. According to claim 1, the analysis system for intelligent construction of nuclear power construction, It is characterized in that The sensor network includes environmental monitoring sensors, structural health monitoring sensors, and location tracking sensors.

3. According to claim 2, the analysis system for intelligent construction of nuclear power construction, It is characterized in that The environment monitoring sensor monitors the temperature of the environment, which is expressed as: Where T represents temperature; Vout represents the sensor output voltage; V0 represents the reference voltage; k represents the sensor sensitivity, By displaying the data collected by the sensor, the temperature of the construction site is calculated to ensure a suitable construction environment; Structural health monitoring sensors monitor stress, expressed as: Where σ represents stress; F represents applied force; A represents the area under force; Monitor the stress of structural components in real time to prevent structural damage.

4. The analysis system for intelligent construction of nuclear power construction according to claim 1, It is characterized in that The machine learning algorithm adopts a linear regression model and uses historical construction data to predict construction progress and risks. The predicted progress is expressed as: y=β0+β1x1+...+βnxn Where y represents the prediction result; β0 represents the intercept; β1,β2,…,βn represent regression coefficients; x1, x2,…, xn represent input variables; Identify risks as: Where P(y=1|x) represents the probability of an event occurring; β0,β1,β2,…,βn represent regression coefficients; x1, x2,…, xn represent input variables; Identify risks that arise during the construction process by analyzing field data.

5. According to claim 1, the analysis system for intelligent construction of nuclear power construction, It is characterized in that The digital twin technology synchronizes real-time data to the digital twin model to keep the virtual model consistent with the actual construction status. The status update formula is expressed as: X(t+1)=f(X(t),U(t)) Where X(t) represents the current state; X(t+1) represents the state at the next moment; U(t) represents the control input; f represents the state transfer function.

6. The analysis system for intelligent construction of nuclear power construction according to claim 1, It is characterized in that The risk warning is based on historical data and real-time monitoring to calculate the probability of various risks in the construction process and issue warnings, which are expressed as: Where P(A|B) represents the probability of event A occurring after event B occurs; P(B|A) represents the probability of event B occurring after event A occurs; P(A)P represents the prior probability of event A occurring; P(B) represents the prior probability of event B occurring.

7. The analysis system for intelligent construction of nuclear power construction according to claim 1, It is characterized in that The supply chain management uses linear programming, which is expressed as: MinC H d Subject to Md≤b Where C represents the cost coefficient matrix; d represents the decision variable; M represents the constraint coefficient matrix; b represents the constraint vector; H represents the transpose of the matrix.

8. The analysis system for intelligent construction of nuclear power construction according to claim 1, It is characterized in that The visualization technique uses the Gantt chart progress equation to represent the progress visualization, which is expressed as: Pi(t) represents the progress of task i at time t; aij represents the workload ratio of task i and resource j; uj(t) represents the usage of resource j at time t.

Images