An intelligent green construction system and method for bridge decks based on UHPC materials

Abstract

This invention relates to the field of intelligent engineering construction technology, specifically to an intelligent green construction system and method for bridge decks based on UHPC materials. First, sensors collect data on bridge deck status, material properties, environmental data, and energy consumption, which are transmitted via a 5G network. Then, wavelet transform denoising and Z-score normalization techniques are used to process the data, generating a combined authentication code to ensure data usability. Next, energy consumption and environmental impact scores are calculated to identify high-energy-consuming components. Based on the analysis results, energy optimization schemes are formulated, and improvement measures are proposed for pollution emissions and noise levels. Furthermore, mechanical operations are automatically adjusted according to the optimization scheme to ensure precise construction. Finally, the system enters the intelligent maintenance phase, using long-term monitoring data to predict faults and formulate maintenance plans to extend the service life of the bridge decks. This invention achieves energy conservation, emission reduction, and environmental protection goals during the bridge deck construction process.

Description

Technical Field

[0001] This invention relates to the field of intelligent engineering construction technology, specifically to an intelligent green construction system and method for bridge decks based on UHPC material. Background Technology

[0002] With the development of information technology, intelligent technology has gradually been integrated into the construction industry, providing strong support for achieving refined management and efficient construction. Through the application of the Internet of Things, big data analysis and artificial intelligence algorithms, various parameters at the construction site can be monitored in real time, including temperature, humidity, noise, dust concentration, etc., so as to promptly identify and correct potential environmental risks. At the same time, the data analysis system based on the cloud computing platform can deeply mine massive amounts of data, optimize design schemes and construction processes, and reduce unnecessary waste of resources.

[0003] Chinese invention patent CN114896882A discloses a data-driven green digital twin construction system and method, which includes a model platform encapsulated with a model-based systems engineering approach: a model platform with several visualization models and computational analysis models; a data platform that connects to several data sources through a gateway to obtain big data from production, construction, operation and maintenance, sensor networks, the Internet, and APP; a digital twin space for model fusion; and a physical application space; and exchanges data with each part through digital threads, realizing green and intelligent construction driven by digital twins, which significantly improves the work efficiency, energy saving rate, and risk control capabilities throughout the entire life cycle of the project.

[0004] The bridge deck construction process suffers from inefficiency, high energy consumption, and insufficient environmental performance: reliance on manual operation leads to low construction precision and susceptibility to environmental influences; frequent use of high-energy-consuming equipment increases the environmental burden; furthermore, data security and availability are difficult to guarantee, posing a risk of loss or forgery. Summary of the Invention

[0005] The purpose of this invention is to address the problems existing in the background technology by proposing an intelligent green construction system and method for bridge decks based on UHPC materials.

[0006] The technical solution of this invention: an intelligent green construction method for bridge decks based on UHPC material, comprising the following specific implementation steps:

[0007] S1. Collect bridge deck status data, material performance data, environmental data, and energy consumption data, and perform data denoising and standardization on the collected bridge deck status data, material performance data, environmental data, and energy consumption data;

[0008] S2. Generate a combined authentication code for the processed bridge deck status data, material performance data, environmental data, and energy consumption data, and check the availability of the bridge deck status data, material performance data, environmental data, and energy consumption data;

[0009] S3. Call the energy consumption optimization model to calculate the energy consumption of each stage, identify the total energy consumption and high energy consumption stages in the construction process, and call the environmental analysis model to assess and monitor the environmental impact of pollution and noise generated during construction, and output a comprehensive environmental impact score.

[0010] S4. If the energy consumption of a certain construction stage exceeds the set threshold I or the total energy consumption exceeds the set threshold II, then an energy optimization plan shall be formulated to reduce energy consumption during construction. If the comprehensive environmental impact score exceeds the set score threshold III, then an environmental optimization plan shall be formulated.

[0011] S5. Based on energy optimization and environmental optimization plans, the mechanical operation is automatically adjusted to automatically complete the batching, casting and molding of UHPC;

[0012] S6. After construction is completed, a comprehensive quality assessment will be conducted using bridge deck condition data and material performance data, and predictive maintenance will be carried out on the bridge deck.

[0013] The preferred predictive maintenance process is as follows:

[0014] S21. Call the fault prediction model and input the time series data X = {x'1, x'2, ..., x'...} i , ..., x' n},include:

[0015] Stress I t : Reflects the stress state of the bridge deck under load;

[0016] strain ε t : Represents the deformation of a material under different load conditions;

[0017] Temperature T t : Reflects the effect of ambient temperature on material properties;

[0018] Humidity H t : Reflects the influence of ambient humidity on material properties;

[0019] Where, x' i For the i-th data;

[0020] S22. By inputting the hidden states of multiple time steps into a fully connected layer, the failure probability p at the next time step can be obtained. t+1 :

[0021] P t+1 =fLSTM (X);

[0022] In the formula, p t+1 This represents the probability of failure at a future time point t+1, i.e., the likelihood that the bridge deck will fail at the next time point; f LSTM () represents the LSTM model function, which, after training, can map time series data to fault probabilities and capture the state changes of the bridge deck.

[0023] S23. Develop a maintenance plan: The maintenance cycle is determined based on the principle of cost minimization, comprehensively considering maintenance costs and failure costs. The maintenance cycle T is adjusted to minimize the total cost C. maintenance (T)+C failure Minimize (T) to obtain the optimal maintenance cycle T. opt To achieve a balance between costs and minimize risks:

[0024]

[0025] C failure (T)=P f (T)·C f ;

[0026] P f (T)=1-e -λT ;

[0027] In the formula, T opt Indicates the optimal maintenance cycle; C maintenance (T) represents the maintenance cost, which is the total cost of performing maintenance every T days; C failure (T) represents the failure cost, which is the potential cost of failure that may result from maintenance every T days; C m This represents the unit maintenance cost, which includes the cost of labor, equipment, and materials; P f (T) represents the failure probability function, that is, the probability of a failure occurring within period T, which is p. t+1 C f λ represents the unit failure cost, including equipment repair, material replacement, and downtime impact; λ represents the failure rate parameter, which reflects the rate of increase in the probability of failure over time; T represents the maintenance cycle length.

[0028] S24. Continuously adjust T based on the actual monitored failure probability and bridge deck condition. opt If the actual failure rate of the bridge deck is lower than expected, the maintenance cycle will be extended; if the failure rate is higher, the maintenance cycle will be shortened, and the maintenance cost model C will be optimized based on historical maintenance data. maintenance (T) and fault prediction model P f (T).

[0029] Preferably, the data denoising process is as follows:

[0030] S31. Decompose the received signal X(t) into multi-scale components. The decomposition formula is as follows:

[0031]

[0032] In the formula, W X (a,b) represent the decomposition coefficients of the signal; X(t) represents the bridge deck condition data, material performance data, environmental data, or energy consumption data; a represents the scale factor, which determines the resolution of the wavelet; b represents the translation factor, which determines the position of the wavelet; ψ a,b (t) represents a wavelet function with scale factor a and shift factor b;

[0033] S32. Set a threshold λ for the high-frequency coefficients obtained from the decomposition, set the coefficients smaller than the threshold to zero, and retain the useful signal:

[0034] If |W X (a,b)|≥λ, then

[0035] If |W X (a,b)|<λ, then

[0036] in, The decomposition coefficients of the denoised signal are represented by λ; λ represents the threshold.

[0037] S33. Based on the decomposition coefficients of the denoised signal Perform inverse wavelet transform to obtain the denoised signal. This yields the bridge deck status data, material performance data, environmental data, or energy consumption data after noise reduction.

[0038] The preferred method for comprehensive environmental impact assessment is as follows:

[0039] S41. Obtain the total CO2 content, total sound decibel data, and solid waste emissions from environmental data;

[0040] S42. Calculate the comprehensive environmental impact score:

[0041]

[0042]

[0043] In the formula, Indicates total carbon dioxide emissions; L total W represents the total sound volume in decibels. waste Indicates solid waste emissions; P i t represents the power of the i-th construction stage; iα represents the duration of the i-th construction stage; i L represents the amount of carbon dioxide emitted per unit of energy consumed in the i-th stage; i This represents the noise level generated during the i-th construction phase.

[0044] The preferred implementation process for comprehensive quality assessment is as follows:

[0045] S51. Real-time acquisition and long-term monitoring of bridge deck condition data and material performance data, from which temperature data, humidity data, load data, stress data and vibration data are obtained;

[0046] S52. Performance Changes Due to the Impact of the Computing Environment

[0047]

[0048] I = E·ε;

[0049] In the formula, This indicates the performance change caused by environmental factors; P0 represents the original performance value. The coefficient of variation represents the temperature effect, reflecting the material's sensitivity to temperature changes; T represents the amount of temperature change. The coefficient represents the humidity effect, reflecting the material's sensitivity to humidity changes; H represents the amount of humidity change; I represents stress; E represents the material's elastic modulus; ε represents strain.

[0050] S53. Based on this, conduct a comprehensive quality assessment, and if performance changes are caused by monitored environmental impacts. If the set threshold IV is exceeded, or the stress value exceeds the safety threshold V, an early warning signal will be automatically issued.

[0051] Preferably, the process for generating the combined authentication code is as follows:

[0052] S61. Encode the bridge deck status data, material performance data, environmental data, and energy consumption data respectively to obtain binary strings data1, data2, data3, and data4;

[0053] S62, From the finite field F q Select a random number κ and calculate the first-level coding generation parameter PⅠ. g =κ×P2;

[0054] Where P2 is a generator of the additive cyclic group G2 of order q;

[0055] S63. Generate an authentication code for the bridge deck status data. The generation process is as follows:

[0056] S6301, Calculate the secondary encoding generation parameter PⅡ g1=κ×H1(ID1, G1);

[0057] Here, ID1 is the type identifier of the bridge panel status data, defined as 0x00; H1 is any hash mapping with a value range of G1; G1 is an additive cyclic group of order q, from which a bilinear mapping e is defined: G1 × G2 = G T G T It is a multiplicative cyclic group of order q;

[0058] S6302, from the finite field F q Select a random number r1 and calculate the authentication code for the following bridge deck status data:

[0059] Level 1 authentication code CⅠ1=PⅡ g1 +r1×P1;

[0060] Level 2 authentication code CⅡ1 = r1 × H2(data1||ID1, q) × P2;

[0061] Where P1 is the generator of group G1; H2 is any hash map with a range of q; || is the string concatenation symbol;

[0062] S6303, Generate the authentication code C1 = (CⅠ1, CⅡ1) for bridge deck status data;

[0063] S64. Generate an authentication code for the material property data. The generation process is as follows:

[0064] S6401, Calculate the secondary encoding generation parameter PⅡ g2 =κ×H1(ID2, G1);

[0065] Among them, ID2 is the type identifier of material property data, which is defined as 0x01;

[0066] S6402, from the finite field F q Select a random number r2 and calculate the authentication code for the following material property data:

[0067] Level 1 authentication code CⅠ2=PⅡ g2 +r2×P1;

[0068] Level 2 authentication code CⅡ2 = r2 × H2(data2||ID2,q) × P2;

[0069] S6403, Generate the authentication code C2 = (CⅠ2, CⅡ2) for bridge deck status data;

[0070] S65. Generate an authentication code for the environmental data. The generation process is as follows:

[0071] S6501, Calculate the secondary encoding generation parameter PⅡ g3=κ×H1(ID3, G1);

[0072] Among them, ID3 is the type identifier of environmental data, defined as 0x10;

[0073] S6502, from the finite field F q Select a random number r3 and calculate the authentication code for the following environmental data:

[0074] Level 1 authentication code CⅡ3=PⅠ g3 +r3×P1;

[0075] Level 2 authentication code CⅡ3 = r3 × H2(data3||ID3,q) × P2;

[0076] S6503, Authentication code for generating environmental data C3 = (CⅠ3, CⅡ3);

[0077] S66. Generate an authentication code for the energy consumption data. The generation process is as follows:

[0078] S6601, Calculate the secondary encoding generation parameter PⅡ g4 =κ×H1(ID4, G1);

[0079] Among them, ID4 is the type identifier of energy consumption data, defined as 0x11;

[0080] S6602, from the finite field F q Select a random number r4 and calculate the authentication code for the following energy consumption data:

[0081] Level 1 authentication code CⅠ4=PⅡ g4 +r4×P1;

[0082] Level 2 authentication code CⅡ4 = r4 × H2(data4||ID4,q) × P2;

[0083] S6603, Authentication code for generating energy consumption data C4 = (CⅠ4, CⅡ4);

[0084] S67. Generate the combined authentication code JC = (JCⅠ, JCⅡ);

[0085] Among them, JCⅠ is the first-level combined authentication code: JCI is a two-level combined authentication code: JCI = CI1 + CI2 + CI3 + CI4.

[0086] Preferably, the process for checking the availability of bridge deck condition data, material performance data, environmental data, and energy consumption data is as follows:

[0087] S71. Calculate the certification factor Fa:

[0088] S72. If Fa = 1, then the availability test of bridge deck condition data, material performance data, environmental data, and energy consumption data is passed.

[0089] The technical solution of this invention: an intelligent green construction system for bridge decks based on UHPC material, which is used in the aforementioned intelligent green construction method for bridge decks based on UHPC material, comprising:

[0090] The data acquisition and transmission module is used to collect bridge deck status data, material performance data, environmental data and energy consumption data using sensors arranged on the bridge deck, and transmit the data in real time through the 5G communication network.

[0091] The data processing module is used to preprocess the received data;

[0092] The data analysis module is equipped with an algorithm library that supports concurrent processing of multiple data streams and integrates energy consumption optimization models, fault prediction models, and environmental analysis models.

[0093] The energy consumption optimization model is used to model and optimize based on energy consumption data during the bridge deck construction process using big data analytics, and to identify high-energy-consuming processes.

[0094] Environmental analysis models are used to analyze pollution emissions, material consumption, and noise during the construction process based on sensor data and environmental analysis models, and to conduct green assessments and scores for the entire construction process;

[0095] Fault prediction models are used to predict potential bridge deck failures based on historical data and machine learning algorithms;

[0096] The construction process control module is used to execute the construction of the bridge deck through intelligent equipment and automated machinery, including automated batching, casting and molding steps;

[0097] The environmental impact optimization module is used to develop environmental optimization plans for construction projects.

[0098] The energy optimization module is used to develop energy optimization plans;

[0099] The fault prediction and maintenance module provides maintenance recommendations to extend the service life of the bridge deck.

[0100] Compared with the prior art, the above-mentioned technical solution of the present invention has the following beneficial technical effects:

[0101] This invention proposes an intelligent green construction system and method for bridge decks based on UHPC materials. By integrating advanced sensing technology, data processing algorithms, automated control, and predictive maintenance strategies, it achieves intelligent, green, and efficient bridge deck construction, providing an innovative solution for modern bridge engineering.

[0102] (1) Improve construction efficiency and quality: The data acquisition and transmission module monitors the bridge deck status, material properties, environmental data and energy consumption data in real time, and combines them with the data analysis module for comprehensive evaluation, so as to achieve precise control of the construction process, improve construction efficiency and ensure the quality of the bridge deck.

[0103] (2) Reduce energy consumption and carbon emissions: The energy optimization module formulates energy optimization plans based on data analysis results, and takes measures such as prioritizing high-efficiency equipment, intelligent operation control, reasonable allocation of power load, and optimization of construction procedures, which effectively reduces energy consumption and carbon emissions during construction.

[0104] (3) Reduce environmental pollution: The environmental impact optimization module reduces pollutant emissions during construction and protects the ecological environment by reducing the frequency of use of high-emission equipment, real-time monitoring of carbon dioxide concentration, treatment of waste gas and solid waste, and water pollution control.

[0105] (4) Enhance system security: The combined authentication code generation process ensures the availability of data and prevents data from being tampered with or leaked. At the same time, the fault prediction and maintenance module discovers potential problems in advance and takes measures through long-term monitoring and predictive maintenance, thereby improving the security and reliability of the system.

[0106] (5) Supporting decision-making: The data analysis module provides detailed energy consumption analysis and environmental impact assessment reports, providing scientific basis for the construction team and management to make more reasonable decisions;

[0107] (6) Enhanced user experience: The intelligent maintenance function reduces unexpected downtime and improves the reliability and stability of the equipment through real-time monitoring and predictive maintenance, thereby enhancing user satisfaction and user experience. Attached Figure Description

[0108] Figure 1 This is a system architecture diagram of an intelligent green construction system for bridge decks based on UHPC material proposed in this invention. Detailed Implementation

[0109] Example 1, as Figure 1 As shown, the present invention proposes an intelligent green construction system for bridge decks based on UHPC materials, which includes a data acquisition and transmission module, a data processing module, a data analysis module, a construction process control module, an environmental impact optimization module, an energy consumption optimization module, and a fault prediction and maintenance module.

[0110] The data acquisition and transmission module is used to collect bridge deck status data (including but not limited to humidity and vibration data), material performance data (including but not limited to strength, durability and crack performance), environmental data and energy consumption data using sensors arranged on the bridge deck, and to achieve efficient real-time data transmission through the 5G communication network.

[0111] The data processing module is used to preprocess the received data, including but not limited to noise reduction and standardization;

[0112] The data analysis module is equipped with an algorithm library that supports concurrent processing of multiple data streams and integrates energy consumption optimization models, fault prediction models, and environmental analysis models.

[0113] It should be noted that the energy consumption optimization model uses big data analysis technology to model and optimize based on energy consumption data during the bridge deck construction process, and to identify high-energy-consuming links;

[0114] The environmental analysis model, based on sensor data and the environmental analysis model, analyzes pollution emissions, material consumption and noise during the construction process, and conducts green assessment and scoring of the entire construction process;

[0115] The fault prediction model, based on historical data and machine learning algorithms, predicts potential faults in bridge decks.

[0116] The construction process control module is used to execute the construction of the bridge deck through intelligent equipment and automated machinery, including automated batching, casting and molding steps;

[0117] The Environmental Impact Optimization module is used to develop environmental optimization plans for construction projects.

[0118] The energy optimization module is used to develop energy optimization solutions;

[0119] The fault prediction and maintenance module provides maintenance recommendations to extend the service life of the bridge deck.

[0120] Example 2: The present invention proposes an intelligent green construction method for bridge decks based on UHPC materials, which is applied to the intelligent green construction system for bridge decks based on UHPC materials proposed in Example 1. The specific implementation steps are as follows:

[0121] S1. The data acquisition and transmission module collects bridge deck status data (including but not limited to temperature, humidity and vibration data), material performance data (including but not limited to strength, durability and crack performance), environmental data (including but not limited to CO2 content, sound decibel data, solid waste emissions) and energy consumption data (including but not limited to power consumption of each device and construction time), and transmits the collected bridge deck status data, material performance data, environmental data and energy consumption data to the data processing module through the 5G communication network deployed at the construction site.

[0122] S2. The data processing module performs noise reduction and standardization on the received bridge deck status data, material performance data, environmental data, and energy consumption data. The specific implementation process is as follows:

[0123] S21. Wavelet transform is used to denoise the received bridge deck state data, material performance data, environmental data, and energy consumption data. The specific implementation process is as follows:

[0124] S2101. Decompose the received signal X(t) into multi-scale components. The decomposition formula is as follows:

[0125]

[0126] In the formula, W X (a,b) represent the decomposition coefficients of the signal; X(t) represents the signal, which in this embodiment represents bridge deck state data, material performance data, environmental data, or energy consumption data; a represents the scale factor, which determines the resolution of the wavelet; b represents the translation factor, which determines the position of the wavelet; ψ a,b (t) represents a wavelet function with scale factor a and shift factor b;

[0127] S2102. Set a threshold λ for the high-frequency coefficients obtained from the decomposition, set the coefficients smaller than the threshold to zero, and retain the useful signal:

[0128] If |W X (a,b)|≥λ, then

[0129] If |W X (a,b)|<λ, then

[0130] in, The decomposition coefficients of the denoised signal are represented by λ; λ represents the threshold.

[0131] S2103, Based on the decomposition coefficients of the denoised signal Perform inverse wavelet transform to obtain the denoised signal. This yields the bridge deck status data, material performance data, environmental data, or energy consumption data after noise reduction.

[0132] S22. Use Z-score standardization to standardize the denoised bridge deck condition data, material performance data, environmental data, or energy consumption data, converting data of different dimensions and ranges into a unified scale. The specific implementation process is as follows:

[0133] S2201, For the denoised signal Standardized data Z = {z1, z2, ..., z}i , ..., z n The calculation method is as follows:

[0134]

[0135] In the formula, x i z represents the i-th original data; i Represents the i-th standardized data point; μ represents the mean of the data; σ represents the standard deviation of the data;

[0136] S23. Generate a combined authentication code based on the preprocessed bridge deck condition data, material performance data, environmental data, and energy consumption data. The process for generating the combined authentication code is as follows:

[0137] S2301. Encode the bridge deck status data, material performance data, environmental data, and energy consumption data respectively to obtain binary strings data1, data2, data3, and data4.

[0138] S2302, from the finite field F q Select a random number κ and calculate the first-level coding generation parameter PⅠ. g =κ×P2, and publicly disclose the encoded generation parameter PⅠ to the data analysis module. g ;

[0139] Where P2 is a generator of the additive cyclic group G2 of order q;

[0140] S2303. Generate an authentication code for the bridge deck status data. The generation process is as follows:

[0141] (1) Calculate the secondary encoding generation parameter PⅡ g1 =κ×H1(ID1, G1);

[0142] Here, ID1 is the type identifier of the bridge panel status data, defined as 0x00; H1 is any hash mapping with a value range of G1; G1 is an additive cyclic group of order q, from which a bilinear mapping e is defined: G1 × G2 = G T G T It is a multiplicative cyclic group of order q;

[0143] (2) From the finite field F q Select a random number r1 and calculate the authentication code for the following bridge deck status data:

[0144] Level 1 authentication code CⅠ1=PⅡ g1 +r1×P1;

[0145] Level 2 authentication code CⅡ1 = r1 × H2(data1||ID1, q) × P2;

[0146] Where P1 is the generator of group G1; H2 is any hash map with a range of q; || is the string concatenation symbol;

[0147] (3) Generate the authentication code C1 = (CⅠ1, CⅡ1) for the bridge panel status data;

[0148] S2304. Generate an authentication code for material performance data. The generation process is as follows:

[0149] (1) Calculate the secondary encoding generation parameter PⅡ g2 =κ×H1(ID2, G1);

[0150] Among them, ID2 is the type identifier of material property data, which is defined as 0x01;

[0151] (2) From the finite field F q Select a random number r2 and calculate the authentication code for the following material property data:

[0152] Level 1 authentication code CⅠ2=PⅡ g2 +r2×P1;

[0153] Level 2 authentication code CⅡ2 = r2 × H2(data2||ID2,q) × P2;

[0154] (3) Generate the authentication code C2 = (CⅠ2, CⅡ2) for the bridge deck status data;

[0155] S2305. Generate an authentication code for environmental data. The generation process is as follows:

[0156] (1) Calculate the secondary encoding generation parameter PⅡ g3 =κ×H1(ID3, G1);

[0157] Among them, ID3 is the type identifier of environmental data, defined as 0x10;

[0158] (2) From the finite field F q Select a random number r3 and calculate the authentication code for the following environmental data:

[0159] Level 1 authentication code CⅡ3=PⅠ g3 +r3×P1;

[0160] Level 2 authentication code CⅡ3 = r3 × H2(data3||ID3,q) × P2;

[0161] (3) Generate the authentication code for environmental data C3 = (CⅠ3, CⅡ3);

[0162] S2306. Generate an authentication code for energy consumption data. The generation process is as follows:

[0163] (1) Calculate the secondary encoding generation parameter PⅡ g4 =κ×H1(ID4, G1);

[0164] Among them, ID4 is the type identifier of energy consumption data, defined as 0x11;

[0165] (2) From the finite field F q Select a random number r4 and calculate the authentication code for the following energy consumption data:

[0166] Level 1 authentication code CⅠ4=PⅡ g4 +r4×P1;

[0167] Level 2 authentication code CⅡ4 = r4 × H2(data4||ID4,q) × P2;

[0168] (3) Generate the authentication code C4 = (CⅠ4, CⅡ4) for energy consumption data;

[0169] S2307. Generate the combined authentication code JC = (JCⅠ, JCⅡ);

[0170] Among them, JCⅠ is the first-level combined authentication code: JCI is a two-level combined authentication code: JCI = CI1 + CI2 + CI3 + CI4;

[0171] S24. Transfer {(JCⅠ, JCⅡ), data1, data2, data3, data4} to the data analysis module.

[0172] S3. The data analysis module receives {(JCⅠ, JCⅡ), data1, data2, data3, data4} and performs the following operations:

[0173] S31. The data analysis module checks the availability of the received data. The checking process is as follows:

[0174] S3101, Calculate the certification factor Fa:

[0175] S3102. If Fa = 1, then the data analysis module receives {(JCⅠ, JCⅡ), data1, data2, data3, data4} and passes the authentication, meaning that the bridge deck status data, material performance data, environmental data, and energy consumption data are available.

[0176] S32. Call the energy consumption optimization model in the algorithm library, calculate the energy consumption of each stage based on the received energy consumption data, and output the high energy consumption stages in the construction process. The energy consumption formula is as follows:

[0177]

[0178] E i =P i ×t i ;

[0179] In the formula, E total E represents total energy consumption. i P represents the energy consumption of the i-th construction stage; i t represents the power consumption of the i-th construction stage, i.e., the energy consumed per unit time. This is determined by the type of equipment and the workload. For example, the power consumption of a batching machine and a pouring machine differs; a batching machine may require a longer time, while a pouring machine may require more power. i This represents the duration of the i-th construction stage; N represents the total number of stages involved in the construction process.

[0180] S33. The data analysis module calls the environmental analysis model in the algorithm library to obtain the total CO2 content, total sound decibel data, and solid waste emission from the environmental data. It then assesses and monitors the pollution and noise environmental impact generated during construction. The comprehensive environmental impact scoring formula is as follows:

[0181]

[0182] In the formula, Indicates total carbon dioxide emissions; L total Indicates the total noise pollution level; W waste Indicates solid waste emissions; P i t represents the power of the i-th construction stage; i α represents the duration of the i-th construction stage; i L represents the amount of carbon dioxide emitted per unit of energy consumed in the i-th stage; i This represents the noise level generated during the i-th construction phase.

[0183] S4. The energy consumption optimization module acquires the high-energy-consuming construction stages and total energy consumption identified by the data analysis module. If the energy consumption of a certain stage exceeds the set threshold I or the total energy consumption exceeds the set threshold II, then the energy consumption during the construction process is reduced, and an energy optimization plan is formulated.

[0184] (1) Selection of high-efficiency equipment: Prioritize the selection of construction equipment with high energy efficiency ratio, such as energy-saving concrete mixers and pouring equipment, and reduce energy consumption through optimized motors and transmission devices;

[0185] (2) Intelligent operation control: Combined with construction tasks and actual needs, the equipment operation mode is adjusted by using automation and intelligent control technology. For example, through sensors and data analysis, the equipment is controlled to enter a low-energy standby mode when the load is low and to restore normal power operation in real time when needed.

[0186] (3) Power load distribution: According to the actual construction needs, the power load of the equipment is reasonably distributed to avoid some equipment from operating under overload or underload. The equipment load is automatically adjusted according to real-time data to maintain the power within the optimal range and reduce unnecessary energy consumption.

[0187] (4) Construction sequence optimization: Arrange the construction sequence reasonably to avoid frequent start-ups and shutdowns or waiting time between equipment. For example, seamlessly connect the material preparation, pouring and molding process of bridge deck to reduce the idle time of equipment.

[0188] (5) Real-time feedback of energy consumption data: During the construction process, the energy consumption data of the equipment is collected in real time to form a feedback mechanism. If the energy consumption of a certain link exceeds the expectation, the construction personnel will be automatically prompted to adjust the equipment or process.

[0189] (6) Time-of-use electricity pricing: When construction time can be flexibly arranged, high-energy-consuming equipment can be automatically selected to run during periods of low electricity price, thereby reducing overall energy consumption costs.

[0190] S5. The environmental impact optimization module acquires the comprehensive environmental impact score output by the data analysis module and compares it with the set scoring threshold III. If the comprehensive environmental impact score exceeds the set scoring threshold III, an environmental optimization plan is formulated to reduce pollution emissions and ecological impacts during construction, ensuring that the project meets environmental protection standards.

[0191] (1) Reduce the frequency of use of high-emission equipment, and arrange continuous construction as much as possible when it is necessary to run the equipment to avoid unnecessary emissions caused by frequent start-up and shutdown of the equipment;

[0192] (2) Monitor the carbon dioxide concentration in the construction area in real time. Once the set standard is exceeded, the system will automatically adjust the working mode of the equipment or remind the staff to take measures.

[0193] (3) The exhaust gas generated during equipment operation is treated by setting up a filtration device. For volatile materials (such as concrete curing agents), sealed storage and on-demand preparation are adopted to reduce volatilization emissions.

[0194] (4) Solid waste treatment: If concrete waste or construction waste is generated, develop automatic sorting, recycling and resource utilization strategies.

[0195] (5) Water pollution control: Use a closed system to treat wastewater during construction, or use a recyclable water resource management system to reduce water pollution.

[0196] (6) Real-time monitoring of noise levels in the construction area will automatically alert users to exceed noise standards and take corresponding control measures.

[0197] S6. The construction process control module obtains the energy optimization plan formulated by the energy consumption optimization module and the environmental optimization plan formulated by the environmental impact optimization module, and adjusts the mechanical operation automatically accordingly. It uses automated equipment to complete the batching, pouring and molding of UHPC to ensure precise construction.

[0198] S7. After construction is completed, the system switches to intelligent maintenance function, using the data acquisition and transmission module to collect bridge deck status data and material performance data, conduct comprehensive quality assessment, and perform predictive maintenance on the bridge deck. The specific implementation steps are as follows:

[0199] S71. The performance of the bridge deck may change due to environmental and load effects during use. Sensors are used to collect and monitor the bridge deck's condition and material properties in real time, obtaining data on temperature, humidity, load, stress, and vibration. This data is then used for comprehensive quality assessment to promptly understand performance changes in the bridge deck. If the monitored environmental influences cause performance changes... If the set threshold IV is exceeded, or the stress value exceeds the safety threshold V, the fault prediction and maintenance module will automatically issue a warning signal;

[0200]

[0201] I = E·ε;

[0202] In the formula, This indicates performance changes caused by environmental influences; P0 represents the original performance value (such as compressive strength or crack resistance). The coefficient of variation represents the temperature effect, reflecting the material's sensitivity to temperature changes; T represents the amount of temperature change. The coefficient represents the humidity effect, reflecting the material's sensitivity to humidity changes; H represents the amount of humidity change; I represents stress; E represents the material's elastic modulus; ε represents strain.

[0203] S72. To extend the service life of the bridge deck, the data analysis module uses long-term monitoring data and a fault prediction model to predict faults. The fault prediction and maintenance module then generates a maintenance plan based on this plan. The specific implementation steps are as follows:

[0204] S7201, The data analysis module calls the fault prediction model and inputs time series data X = {x'1, x'2, ..., x'...} i , ..., x' n},include:

[0205] Stress I t : Reflects the stress state of the bridge deck under load;

[0206] strain ε t : Represents the deformation of a material under different load conditions;

[0207] Temperature T t : Reflects the effect of ambient temperature on material properties;

[0208] Humidity H t : Reflects the influence of ambient humidity on material properties;

[0209] Where, x' i For the i-th data;

[0210] It should be noted that the fault prediction model adopts the LSTM (Long Short-Term Memory) architecture. LSTM is an improved recurrent neural network (RNN) that performs well when processing long sequence data because it can effectively capture long-term and short-term dependencies in time series data. LSTM solves the gradient vanishing or gradient exploding problems that are prone to occur in long time series by introducing "memory units" and "gate structures".

[0211] S7202. By inputting the hidden states of multiple time steps into a fully connected layer, the failure probability p at the next time step can be obtained. t+1 :

[0212] P t+1 =f LSTM (X);

[0213] In the formula, p t+1 f represents the probability of failure at a future time point t+1, ranging from [0, 1], that is, the likelihood that the bridge deck will fail at the next time point; LSTM () represents the LSTM model function, which, after training, can map time series data to fault probabilities and capture the state changes of the bridge deck.

[0214] S7203, after obtaining the future failure probability p t+1 Then, the fault prediction and maintenance module formulates the optimal maintenance plan to ensure the reliability of the bridge deck;

[0215] The maintenance cycle is determined based on the principle of cost minimization, taking into account both maintenance costs and failure costs. The maintenance cycle T is adjusted to minimize the total cost C. maintenance (T)+C failure Minimize (T) to obtain the optimal maintenance cycle T. opt To achieve a balance between costs and minimize risks:

[0216]

[0217] C failure (T)=P f (T)·C f ;

[0218] P f (T)=1-e -λT ;

[0219] In the formula, T opt Indicates the optimal maintenance cycle; C maintenance (T) represents the maintenance cost, which is the total cost of performing maintenance every T days; C failure (T) represents the failure cost, which is the potential cost of failure that may result from maintenance every T days; C m This represents the unit maintenance cost, which includes the cost of labor, equipment, and materials; P f (T) represents the failure probability function, that is, the probability of a failure occurring within period T, which is p. t+1 C f λ represents the unit failure cost, including equipment repair, material replacement, and downtime impact; λ represents the failure rate parameter, which reflects the rate of increase in the probability of failure over time; T represents the maintenance cycle length.

[0220] The S7204 fault prediction and maintenance module continuously adjusts T based on the actual monitored fault probability and bridge deck condition. opt If the actual failure rate of the bridge deck is lower than expected, the fault prediction and maintenance module extends the maintenance cycle; if the failure rate increases, the maintenance cycle is shortened, and the maintenance cost model C is optimized based on historical maintenance data. maintenance (T), and transmits historical maintenance data to the data analysis module;

[0221] The data analysis module then continuously optimizes the fault prediction model P based on historical maintenance data. f (T).

[0222] The embodiments of the present invention have been described in detail above with reference to the accompanying drawings. However, the present invention is not limited thereto. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention.

Claims

1. A method for intelligent and green construction of bridge decks based on UHPC material, characterized in that, The specific implementation steps include the following: S1. Collect bridge deck status data, material performance data, environmental data, and energy consumption data, and perform data denoising and standardization on the collected bridge deck status data, material performance data, environmental data, and energy consumption data; S2. Generate a combined authentication code for the processed bridge deck status data, material performance data, environmental data, and energy consumption data, and check the availability of the bridge deck status data, material performance data, environmental data, and energy consumption data; The process of generating the combined authentication code is as follows: A1. Encode the bridge deck status data, material performance data, environmental data, and energy consumption data respectively to obtain binary strings data1, data2, data3, and data4; A2, from the finite field F q Select a random number κ and calculate the first-level coding generation parameter PⅠ. g =κ×P2; Where P2 is a generator of the additive cyclic group G2 of order q; A3. Generate an authentication code for the bridge deck status data. The generation process is as follows: Calculate the second-level encoding generation parameter PⅡ g1 =κ×H1(ID1, G1); Here, ID1 is the type identifier of the bridge panel status data, defined as 0x00; H1 is any hash mapping with a value range of G1; G1 is an additive cyclic group of order q, from which a bilinear mapping e is defined: G1 × G2 = G T G T It is a multiplicative cyclic group of order q; From the finite field F q Select a random number r1 and calculate the authentication code for the following bridge deck status data: Level 1 authentication code CⅠ1=PⅡ g1 +r1×P1; Level 2 authentication code CⅡ1 = r1 × H2(data1||ID1,q) × P2; Where P1 is the generator of group G1; H2 is any hash map with a range of q; || is the string concatenation symbol; The authentication code for generating bridge deck status data is C1 = (CⅠ1, CⅡ1); A4. Generate an authentication code for the material performance data. The generation process is as follows: Calculate the second-level encoding generation parameter PⅡ g2 =κ×H1(ID2, G1); Among them, ID2 is the type identifier of material property data, which is defined as 0x01; From the finite field F q Select a random number r2 and calculate the authentication code for the following material property data: Level 1 authentication code CⅠ2=PⅡ g2 +r2×P1; Level 2 authentication code CⅡ2 = r2 × H2(data2||ID2,q) × P2; The authentication code for generating bridge deck status data is C2 = (CⅠ2, CⅡ2); A5. Generate authentication codes for environmental data. The generation process is as follows: Calculate the second-level encoding generation parameter PⅡ g3 =κ×H1(ID3,G1); Among them, ID3 is the type identifier of environmental data, defined as 0x10; From the finite field F q Select a random number r3 and calculate the authentication code for the following environmental data: Level 1 authentication code CⅡ3=PⅠ g3 +r3×P1; Level 2 authentication code CⅡ3 = r3 × H2(data3||ID3,q) × P2; The authentication code for generating environmental data is C3 = (CⅠ3, CⅡ3); A6. Generate an authentication code for energy consumption data. The generation process is as follows: Calculate the second-level encoding generation parameter PⅡ g4 =κ×H1(ID4, G1); Among them, ID4 is the type identifier of energy consumption data, defined as 0x11; From the finite field F q Select a random number r4 and calculate the authentication code for the following energy consumption data: Level 1 authentication code CⅠ4=PⅡ g4 +r4×P1; Level 2 authentication code CⅡ4 = r4 × H2(data4||ID4,q) × P2; The authentication code for generating energy consumption data is C4 = (CⅠ4, CⅡ4); A7. Generate the combined authentication code JC=(JCⅠ, JCⅡ); Among them, JCⅠ is the first-level combined authentication code: JCI is a two-level combined authentication code: JCI = CI1 + CI2 + CI3 + CI4; The process for checking the availability of bridge deck condition data, material performance data, environmental data, and energy consumption data is as follows: Calculate the certification factor Fa: ; If Fa=1, then the availability test of bridge deck condition data, material performance data, environmental data, and energy consumption data is passed; S3. Call the energy consumption optimization model to calculate the energy consumption of each construction stage, identify the total energy consumption and high energy consumption stages in the construction process, and call the environmental analysis model to assess and monitor the environmental impact of pollution and noise generated during the construction process, and output a comprehensive environmental impact score. S4. If the energy consumption of a certain link is greater than the set threshold I or the total energy consumption is greater than the set threshold II, then an energy optimization plan shall be formulated to reduce energy consumption during construction. If the comprehensive environmental impact score exceeds the set score threshold III, then an environmental optimization plan shall be formulated. S5. Based on energy optimization and environmental optimization plans, the mechanical operation is automatically adjusted to automatically complete the batching, casting and molding of UHPC; S6. After construction is completed, a comprehensive quality assessment will be conducted using bridge deck condition data and material performance data, and predictive maintenance will be carried out on the bridge deck.

2. The intelligent green construction method for bridge decks based on UHPC material according to claim 1, characterized in that, The predictive maintenance process is as follows: S21. Call the fault prediction model and input the time series data X={x'1, x'2, ..., x'...} i , ..., x' n },include: Stress I t : Reflects the stress state of the bridge deck under load; strain ε t : Represents the deformation of a material under different load conditions; Temperature T t : Reflects the effect of ambient temperature on material properties; Humidity H t : Reflects the influence of ambient humidity on material properties; Where, x' i For the i-th data; S22. By inputting the hidden states of multiple time steps into a fully connected layer, the failure probability p at the next time step can be obtained. t+1 : ； In the formula, p t+1 This represents the probability of failure at a future time point t+1, that is, the likelihood that the bridge deck will fail at the next time point; This represents the LSTM model function, which, after training, can map time series data to fault probabilities and capture changes in the state of the bridge deck. S23. Develop a maintenance plan: The maintenance cycle is determined based on the principle of cost minimization, comprehensively considering maintenance costs and failure costs, and adjusting the maintenance cycle T to minimize the total cost. Minimize to obtain the optimal maintenance cycle T opt : ； ； ； ； In the formula, T opt Indicates the optimal maintenance cycle; This represents the maintenance cost, which is the total cost of performing maintenance every T days. This represents the failure cost, which is the potential cost of failure that may result from maintenance every T days. This indicates the unit maintenance cost, which includes the cost of labor, equipment, and materials. The failure probability function represents the probability of a failure occurring within a period T, which is p. t+1 ; This represents the unit cost of failure, which includes equipment repair, replacement materials, and the impact of downtime. This represents the failure rate parameter, which reflects the rate at which the probability of a failure increases over time; T represents the maintenance cycle length. S24. Continuously adjust T based on the actual monitored failure probability and bridge deck condition. opt If the actual failure rate of the bridge deck is lower than expected, the maintenance cycle will be extended; if the failure rate is higher, the maintenance cycle will be shortened, and the maintenance cost model will be optimized based on historical maintenance data. and fault prediction model .

3. The intelligent green construction method for bridge decks based on UHPC material according to claim 1, characterized in that, The data denoising process is as follows: S31. Decompose the received signal X(t) into multi-scale components. The decomposition formula is as follows: ； In the formula, Represents the decomposition coefficients of the signal; This represents bridge deck condition data, material performance data, environmental data, or energy consumption data; 'a' represents the scale factor, which determines the wavelet's resolution; 'b' represents the translation factor, which determines the wavelet's position. Describes a wavelet function with a scaling factor a and a shift factor b; S32. Set a threshold λ for the high-frequency coefficients obtained from the decomposition, set the coefficients smaller than the threshold to zero, and retain the useful signal: If | If |≥λ, then = ; If | If |<λ, then =0; in, The decomposition coefficients of the denoised signal are represented by λ; λ represents the threshold. S33. Based on the decomposition coefficients of the denoised signal Perform inverse wavelet transform to obtain the denoised signal. This means obtaining the bridge deck status data, material performance data, environmental data, or energy consumption data after noise reduction.

4. The intelligent green construction method for bridge decks based on UHPC material according to claim 1, characterized in that, The comprehensive environmental impact assessment method is as follows: S41. Obtain the total CO2 content, total sound decibel data, and solid waste emissions from environmental data; S42. Calculate the comprehensive environmental impact score: ； ； ； In the formula, This represents total carbon dioxide emissions; This represents the total sound volume in decibels; Indicates solid waste emissions; P i t represents the power of the i-th construction stage; i This represents the duration of the i-th construction stage; L represents the amount of carbon dioxide emitted per unit of energy consumed in the i-th stage; i This represents the noise level generated during the i-th construction phase.

5. The intelligent green construction method for bridge decks based on UHPC material according to claim 1, characterized in that, The implementation process of the comprehensive quality assessment is as follows: S51. Real-time acquisition and long-term monitoring of bridge deck condition data and material performance data, from which temperature data, humidity data, load data, stress data and vibration data are obtained; S52. Performance Changes Due to the Computing Environment : ； ； In the formula, This indicates performance changes caused by environmental factors; Represents the original performance value; The coefficient of variation represents the temperature effect, reflecting the material's sensitivity to temperature changes; T represents the amount of temperature change. H represents the humidity effect coefficient, reflecting the material's sensitivity to humidity changes; I represents the amount of humidity change; and E represents the material's elastic modulus. Indicates strain; S53. Based on this, conduct a comprehensive quality assessment, and if performance changes are caused by monitored environmental impacts. If the set threshold IV is exceeded, or the stress value exceeds the safety threshold V, an early warning signal will be automatically issued.

6. A smart green construction system for bridge decks based on UHPC material, used to execute the smart green construction method for bridge decks based on UHPC material as described in any one of claims 1 to 5, characterized in that, include: The data acquisition and transmission module is used to collect bridge deck status data, material performance data, environmental data and energy consumption data using sensors arranged on the bridge deck, and transmit the data in real time through the 5G communication network. The data processing module is used to preprocess the received data; The data analysis module is equipped with an algorithm library that supports concurrent processing of multiple data streams and integrates energy consumption optimization models, fault prediction models, and environmental analysis models. The energy consumption optimization model is used to model and optimize based on energy consumption data during the bridge deck construction process using big data analytics, and to identify high-energy-consuming processes. Environmental analysis models are used to analyze pollution emissions, material consumption, and noise during the construction process based on sensor data and environmental analysis models, and to conduct green assessments and scores for the entire construction process; Fault prediction models are used to predict potential bridge deck failures based on historical data and machine learning algorithms; The construction process control module is used to execute the construction of the bridge deck through intelligent equipment and automated machinery, including automated batching, casting and molding steps; The environmental impact optimization module is used to develop environmental optimization plans for construction projects. The energy optimization module is used to develop energy optimization plans; The fault prediction and maintenance module provides maintenance recommendations to extend the service life of the bridge deck.

Images