Variable-temperature curing method for curing high-ground-temperature tunnel sprayed concrete test piece

Abstract

The invention discloses a variable-temperature curing method for curing a high-ground-temperature tunnel sprayed concrete test piece, and relates to the technical field of concrete construction. Comprising the following steps: acquiring concrete test piece samples with different water-binder ratios, aggregate types and additive contents, recording hydration heat data of the concrete test piece samples, and performing normalization processing to generate a training sample data set; and establishing a neural network prediction model based on the data set, inputting concrete characteristics, and outputting a hydration heat prediction value. Thirdly, calculating a hydration heat influence index in combination with the thickness and the surface roughness, and meanwhile obtaining environmental parameters in the tunnel, including temperature, humidity and wind speed to calculate an environmental influence index; and finally, dynamically correcting the curing temperature of the to-be-detected concrete test piece by utilizing the heat conductivity of the tunnel surface structure and the comprehensive environment and hydration heat influence index, so that the accuracy and effectiveness of temperature control are ensured, and the overall efficiency and quality of construction are remarkably improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of concrete construction, in particular to a variable temperature curing method for curing high-temperature tunnel sprayed concrete test pieces. BACKGROUND

[0002] High-temperature tunnel construction is an important technology in modern infrastructure construction, and its complex environmental conditions and high-temperature characteristics make concrete curing a key issue. In high-temperature environments, the hydration reaction rate of concrete accelerates, and if not effectively controlled, it will lead to a decrease in the strength and durability of concrete. Traditional curing methods usually rely on manual experience and are difficult to adapt to environmental changes, leading to unevenness in concrete quality and structural safety hazards. In high-temperature tunnels, environmental parameters such as temperature, humidity, and wind speed change frequently, bringing great challenges to the hydration process of concrete. Due to the lack of effective monitoring and control means, construction personnel often have difficulty in achieving precise control of the curing temperature of concrete.

[0003] In early hydration reactions, hydration heat can accelerate the development of concrete strength and improve early strength. However, excessive hydration heat can lead to a decrease in later strength, and in mass concrete construction, hydration heat can cause internal temperature rise in concrete, easily causing temperature cracks. Reasonable temperature control measures such as cooling water pipes, admixtures, etc. can slow down the release speed of hydration heat, and the influence of hydration heat will also delay the curing time of concrete, affecting its impermeability and durability. Reasonable control of hydration heat can ensure that concrete is cured under optimal humidity and temperature, thereby improving its durability, so hydration heat reaction affects the performance of concrete from many aspects and is an important factor that cannot be ignored.

[0004] Currently, many studies have explored the characteristics of concrete hydration heat and its influence on concrete performance, but in the application of high-temperature tunnels, how to scientifically and real-time monitor and control the curing temperature of concrete through hydration heat is still a technical problem to be solved. In addition, existing technologies often rely on static data analysis, lack dynamic prediction and adjustment capabilities, and cannot respond to environmental changes in real time, limiting the efficiency and effectiveness of concrete curing. Therefore, a new temperature control method needs to be developed, which uses advanced data processing technology and artificial intelligence models to achieve precise prediction of concrete hydration heat and dynamic regulation of curing temperature.

[0005] In the prior art, a large volume concrete construction temperature control method based on temperature rise regulation is disclosed in CN116680782A, which specifically includes: establishing a cement hydration and concrete heat transfer model based on experiments; establishing a fine temperature field numerical calculation model based on hydration degree according to structural geometric parameters, boundary heat exchange conditions, construction and maintenance measures; extracting the internal maximum temperature and the maximum temperature difference between the surface and the table temperature control indicators, and comparing them with the design requirements under the premise of meeting the specification requirements; and the requirements can be packaged and output as temperature control technology. However, the "maximum temperature" and "maximum temperature difference between the surface and the table" mentioned in this scheme as temperature control indicators, although they can reflect the temperature rise of the concrete, may not fully reflect the actual performance and state of the concrete. Lack of comprehensive evaluation of other influencing factors (such as environmental impact, roughness risk, etc.), which may lead to insufficient comprehensive temperature control of the concrete. At the same time, this scheme only relies on model calculation, and lacks the ability to monitor the real-time changes of the concrete temperature field. In actual construction, environmental conditions may change at any time, and if the temperature control measures cannot be adjusted in real time, it may lead to concrete temperature exceeding the standard or unevenness. Therefore, the accuracy and effectiveness of the temperature control method are reduced.

[0006] The above information disclosed in the background section is only intended to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute the prior art known to those of ordinary skill in the art. SUMMARY

[0007] The purpose of the present application is to provide a variable temperature curing method for curing high-temperature tunnel sprayed concrete test pieces, in order to solve the problems raised in the background art.

[0008] To achieve the above-mentioned purpose, the present application provides the following technical solutions: A variable temperature curing method for curing high-temperature tunnel sprayed concrete test pieces, comprising the following specific steps: Obtain a plurality of concrete test piece samples with different water-binder ratios, aggregate types and additive contents, obtain hydration heat data of different concrete test piece samples under the same quality through experiments, normalize and preprocess the obtained hydration heat data, and map the preprocessed hydration heat data to the water-binder ratio, aggregate type and additive content data of the corresponding concrete test piece sample one by one to generate a training sample data set; Based on the data in the training sample data set, a neural network prediction model is established, the water-binder ratio, aggregate type and additive content data of the concrete test piece samples in the training sample data set are taken as the input of the neural network prediction model, and the corresponding hydration heat data is taken as the label, the neural network prediction model is trained, and a hydration heat prediction model is obtained; The water-cement ratio, aggregate type and additive content data of the concrete test piece to be detected are obtained and input into the trained hydration heat prediction model to obtain the hydration heat prediction value of the concrete test piece to be detected. According to the obtained hydration heat prediction value of the concrete test piece to be detected, the hydration heat influence index is calculated in combination with the surface roughness and thickness of the concrete test piece to be detected. The environmental parameters in the high-temperature tunnel are obtained, and the environmental influence index is calculated according to the obtained environmental parameters in the high-temperature tunnel, wherein the environmental parameters in the high-temperature tunnel include the real-time temperature of the tunnel surface, the real-time humidity in the tunnel and the real-time wind speed in the tunnel. The thermal conductivity of the tunnel surface structure in the high-temperature tunnel is collected, and the curing temperature of the concrete test piece to be detected is dynamically corrected according to the obtained thermal conductivity of the tunnel surface structure, the environmental influence index and the hydration heat influence index to obtain the real-time curing temperature accurate value. The curing temperature of the concrete test piece to be detected is regulated according to the obtained real-time curing temperature accurate value to complete the temperature control of the concrete test piece curing.

[0009] Further, the obtained hydration heat data is normalized and preprocessed, and the formula for performing the normalization preprocessing is: ; In the formula, is the normalized data of the hydration heat of the i th concrete test piece sample, is the hydration heat data of the i th concrete test piece sample, is the minimum hydration heat data in the concrete test piece sample, is the maximum hydration heat data in the concrete test piece sample, wherein i is the index of the concrete test piece sample, , wherein is the total number of concrete test piece samples; The generation method of the training sample data set is that the preprocessed hydration heat data and the water-cement ratio, aggregate type and additive content data of the corresponding concrete test piece sample are one-to-one mapped to form a corresponding grid, and the formed grid is recorded as the training sample data set.

[0010] Further, based on the data in the training sample data set, a neural network prediction model is established, wherein the hydration heat prediction model is established based on a long short-term memory network model (LSTM model). The long short-term memory network model (LSTM model) selects an activation function and an optimization algorithm, wherein a Tanh function is selected as the activation function, and Adam is selected as the optimization algorithm of the LSTM model. The formula of the Tanh function is: ; In the formula, represents the Tanh function, and the independent variable represents the input weight sum of the neuron, i.e., the result of the weighted sum of the inputs received by the neuron from the previous layer; Meanwhile, the hyperparameters of the LSTM model are set, including the number of network layers, the number of iterations, the learning rate, the batch size, the number of training times, the batch quantity, and the number of hidden layer neurons. The number of network layers is set to a 4-layer network structure, the number of iterations is set to 100, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the batch quantity is set to 128, and the number of hidden layer neurons is set to 32. The trained hydration heat prediction model takes the water-binder ratio, aggregate type, and additive content data of the concrete specimen as input and outputs the corresponding hydration heat prediction value.

[0011] Further, according to the obtained hydration heat prediction value of the to-be-detected concrete specimen, the surface roughness and thickness of the to-be-detected concrete specimen are combined to calculate a hydration heat influence index, wherein the formula for calculating the hydration heat influence index is: ; In the formula, is the hydration heat influence index, is the surface roughness of the to-be-detected concrete specimen, is the hydration heat prediction value, is the thickness of the to-be-detected concrete specimen, is the volume of the to-be-detected concrete specimen.

[0012] Further, the surface roughness of the to-be-detected concrete specimen is The specific acquisition method is as follows: The surface roughness of the to-be-detected concrete specimen is measured by a stylus profilometer. A plurality of sampling regions are randomly selected from the surface region of the to-be-detected concrete specimen, and the stylus profilometer is used to measure and analyze the sampling regions to obtain the surface roughness of each sampling region and calculate the average surface roughness of all sampling regions. This average value is taken as the surface roughness of the to-be-detected concrete specimen, and the calculation formula is as follows: ; ; In the formula, represents the sampling length of the stylus profilometer in the kth sampling region, k is the index of the sampling region, and K is the number of sampling regions, is the height of the sampling point at the qth position in the sampling length of the kth sampling region, q is the coordinate of the sampling point in the sampling length, is the surface roughness of the kth sampling region, For the surface roughness of the concrete test piece to be detected, the center line and Data processing is carried out through the built-in software of the stylus profilometer.

[0013] Further, the environmental parameters in the high-temperature tunnel are acquired, and the environmental influence index is calculated according to the acquired environmental parameters in the high-temperature tunnel. ; In the formula, is the environmental influence index, is the real-time temperature of the tunnel surface, is the real-time humidity in the tunnel, is the real-time wind speed in the tunnel, is the set reference humidity, is the set reference temperature.

[0014] Further, the curing temperature of the concrete test piece to be detected is dynamically corrected according to the obtained thermal conductivity of the tunnel surface structure, in combination with the environmental influence index and the hydration heat influence index, to obtain the accurate value of the real-time curing temperature, and the specific formula for calculating the accurate value of the real-time curing temperature is: ; In the formula, is the accurate value of the real-time curing temperature, is the initial value of the curing temperature of the concrete test piece to be detected, is the thermal conductivity of the tunnel surface structure, is the weight coefficient of the environmental influence index, is the weight coefficient of the hydration heat influence index, is the weight coefficient of the thermal conductivity of the tunnel surface structure, wherein and , and are greater than 0.

[0015] Compared with the prior art, the beneficial effects of the present application are: Firstly, by establishing a hydration heat prediction model and dynamically adjusting the curing temperature based on environmental parameters, the system can respond to real-time changes in temperature and humidity within the tunnel, thereby precisely controlling the curing process of the concrete. This real-time and dynamic control mechanism avoids the problem of improper temperature control due to insufficient experience in traditional curing methods, ensuring that the concrete is always in the best hydration state, significantly improving the strength and durability of the concrete. Secondly, machine learning technology is used to predict the hydration heat of the concrete, which not only improves the accuracy of the prediction but also helps to quickly adapt and optimize the concrete mix ratio under different conditions. In addition, combined with real-time monitoring of environmental parameters and dynamic adjustment strategies, the construction process of high-temperature tunnels is more flexible. Not only does it improve the safety of construction and reduce potential risks caused by temperature changes, but it also improves the work efficiency of construction personnel. Construction personnel can more intuitively understand the hydration state of the concrete, thereby better organizing the construction schedule and avoiding subsequent problems caused by improper curing. The application of this method in high-temperature tunnel construction can significantly improve the overall efficiency and quality of construction, promoting the progress of tunnel construction technology. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 is a schematic diagram of the overall method of the present application; Figure 2 is a fitting curve graph of surface roughness-hydration heat influence index; Figure 3 is a fitting curve graph of hydration heat prediction value-hydration heat influence index; Figure 4 is a statistical graph of environmental parameters and environmental influence index; Figure 5 is a fitting curve graph of surface temperature-environmental influence index; Figure 6 is a fitting curve graph of real-time wind speed-environmental influence index; Figure 7 is a comparison graph of curing temperature precise value calculation representation; Figure 8 is a comparison graph of concrete performance parameters under different curing temperatures. DETAILED DESCRIPTION

[0017] To make the purpose, technical solutions and advantages of the present application clearer and more apparent, the present application is further described in detail below in combination with specific embodiments.

[0018] It should be noted that the technical terms or scientific terms used in the present application should be understood as the general meaning understood by those skilled in the art of the present application unless otherwise defined. The "first", "second" and similar words used in the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Include" or "contain" and similar words mean that the elements or objects before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connected" or "connected" and similar words are not limited to physical or mechanical connection, but can include electrical connection, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to represent the relative positional relationship, when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0019] Embodiments: Please refer to Figures 1-8 The present application provides a technical solution: A variable temperature curing method for curing high-geothermal-tunnel sprayed concrete test pieces, comprising the following specific steps: Step 1: Obtain a plurality of concrete test piece samples with different water-binder ratios, aggregate types and additive contents, obtain hydration heat data of different concrete test piece samples under the same quality through tests, normalize and pretreat the obtained hydration heat data, and map the pretreated hydration heat data to the water-binder ratio, aggregate type and additive content data of the corresponding concrete test piece samples one by one to generate a training sample data set.

[0020] The water-binder ratio is the ratio of the mass of water to the mass of cement (binder) in the concrete mix, and it is one of the important components of concrete, directly affecting the strength, durability and workability of concrete. Different water-binder ratios specifically refer to: high water-binder ratio: generally refers to a water-binder ratio greater than 0.5, such concrete has good fluidity, but lower strength and durability, and is prone to cracking; medium water-binder ratio: generally between 0.4 and 0.5, it can strike a balance between the workability and strength of concrete; low water-binder ratio: water-binder ratio less than 0.4, usually used for concrete that requires high strength and low permeability, but may reduce its fluidity.

[0021] Aggregates are the main components of concrete, including coarse aggregates and fine aggregates. Different types of aggregates can affect the workability, strength, durability, and other properties of concrete. Aggregate types specifically refer to: Coarse aggregates: usually stone with a particle size greater than 5mm, such as gravel, pebbles, etc. Different types of coarse aggregates (such as granite, limestone, basalt, etc.) can affect the strength and density of concrete; Fine aggregates: usually sand with a particle size less than 5mm, the type of fine aggregate (such as natural sand, machine-made sand) can affect the fluidity and workability of concrete; Special aggregates: such as lightweight aggregates (used to reduce the weight of concrete) and heavy aggregates (used to increase the density of concrete), the selection of which will affect the specific performance of concrete.

[0022] Additives refer to materials added to improve the performance of concrete. Different types of additives and their contents can significantly change the properties of concrete. The types and contents of additives specifically refer to: the addition ratio of water-reducing agents, retarders, early strength agents, and antifreeze agents.

[0023] Obtain the hydration heat data of different concrete test samples under the same quality through experiments, and the specific method is: prepare the concrete sample, use the DSC equipment, set it according to the manufacturer's instructions, including temperature range, heating rate, etc., pour the mixed concrete into the measuring cavity of the calorimeter, cover the thermal insulation material to reduce the interference of environmental heat, start the calorimeter, record the temperature change during hydration, and calculate the hydration heat through the temperature change during hydration. Higher hydration heat will cause temperature differences in concrete, leading to dry shrinkage and temperature stress, thereby increasing the risk of cracking. The influence of hydration heat will also delay the curing time of concrete, affecting its impermeability and durability. Reasonable control of hydration heat can ensure that the concrete is cured at the best humidity and temperature, thereby improving its durability. In the early hydration reaction, hydration heat can accelerate the development of concrete strength and improve early strength. However, excessive hydration heat may lead to a decrease in later strength.

[0024] In summary, the characteristics of concrete hydration heat have important influences on the strength, crack resistance, durability, and construction control of concrete. By analyzing different hydration heat factors and taking effective curing temperature control measures accordingly, the advantages of hydration heat can be fully utilized, and its negative effects on the performance of concrete can be reduced.

[0025] The obtained hydration heat data is normalized and preprocessed, and the formula for normalizing and preprocessing is: ; In the formula, is the normalized data of the hydration heat of the i-th concrete test sample, is the hydration heat data of the i-th concrete test sample, is the minimum hydration heat data in the concrete test sample, is the maximum hydration heat data in the concrete specimen sample, wherein i is the index of the concrete specimen sample, wherein is the total number of concrete specimen samples; The method for generating the training sample data set is: mapping the preprocessed hydration heat data one by one with the water-binder ratio, aggregate type and additive content data of the corresponding concrete specimen sample to form a corresponding grid, and recording the formed grid as the training sample data set.

[0026] Step 2: Based on the data in the training sample data set, a neural network prediction model is established, taking the water-binder ratio, aggregate type and additive content data of the concrete specimen samples in the training sample data set as the input of the neural network prediction model, and taking the corresponding hydration heat data as the label, the neural network prediction model is trained to obtain a hydration heat prediction model.

[0027] Based on the data in the training sample data set, a neural network prediction model is established, wherein a hydration heat prediction model is established based on a long short-term memory network model (LSTM model). The LSTM model selects an activation function and an optimization algorithm, wherein a Tanh function is selected as the activation function, and Adam is selected as the optimization algorithm of the LSTM model. The formula of the Tanh function is: ; In the formula, represents the Tanh function, and the independent variable represents the input weight sum of the neuron, i.e. the result of the weighted sum of the input received by the neuron from the previous layer; At the same time, the hyperparameters of the LSTM model are set, including: the number of network layers, the number of iterations, the learning rate, the batch size, the number of training times, the batch processing quantity and the number of hidden layer neurons. The number of network layers is set to 4-layer network structure, the number of iterations is set to 100, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the batch processing quantity is set to 128, and the number of hidden layer neurons is set to 32. The trained hydration heat prediction model takes the water-binder ratio, aggregate type and additive content data of the concrete specimen as input, and outputs the corresponding hydration heat prediction value.

[0028] The LSTM network can capture long-term dependencies in time series data, which is particularly important for cement hydration process prediction, because hydration heat is a time-varying process, and the early hydration state will affect the subsequent hydration reaction.

[0029] LSTM can dynamically adjust its internal state based on the input sequence to adapt to the time-varying heat of hydration. This adaptability allows the model to maintain high prediction accuracy under different construction conditions and environmental factors. The generation of heat of hydration is not only related to factors such as water-cement ratio, temperature, and humidity, but also affected by cement type and other materials. LSTM can effectively capture these complex nonlinear relationships, and compared with traditional linear models, LSTM networks have a greater advantage in handling nonlinear features.

[0030] Step 3: Obtain the water-cement ratio, aggregate type, and additive content data of the concrete specimen to be tested, and input them into the trained hydration heat prediction model to obtain the hydration heat prediction value of the concrete specimen to be tested. Based on the obtained hydration heat prediction value of the concrete specimen to be tested, combined with the surface roughness and thickness of the concrete specimen to be tested, calculate the hydration heat influence index.

[0031] Based on the predicted heat of hydration of the concrete specimen to be tested, and combined with the surface roughness and thickness of the concrete specimen, the heat of hydration influence index is calculated. The specific formula used to calculate the heat of hydration influence index is as follows: ; In the formula, The heat of hydration influence index, The surface roughness of the concrete specimen to be tested. This is the predicted value for heat of hydration. The thickness of the concrete specimen to be tested. The volume of the concrete specimen to be tested; It should be noted that the hydration heat impact index The heat of hydration effect index is used to represent the influence of heat released during the hydration reaction of concrete specimens. The higher the value, the more heat is released during the hydration reaction of the concrete specimen, and the more necessary it is to lower the curing temperature of the concrete specimen.

[0032] The heat of hydration is the heat generated during the hardening process of concrete. Excessive heat of hydration can lead to an increase in the internal temperature of the concrete, increasing the risk of cracking. This can be predicted using the heat of hydration value. Quantifying the potential risks of heat of hydration to concrete performance, therefore, the predicted value of heat of hydration. With hydration heat influence index Proportional, through This indicates that the higher the heat of hydration, the faster the heat may accumulate in the concrete, which may lead to significant effects of the heat of hydration, such as the formation of cracks.

[0033] The surface roughness of concrete specimens under test is typically used to assess the unevenness of the concrete surface. Variations in curing temperature affect the capillary structure in concrete; excessively high temperatures may lead to the formation of capillaries, increasing surface roughness and consequently increasing the probability of surface drying and cracking, ultimately affecting the molding quality of the concrete. Therefore, the surface roughness of concrete specimens under test is crucial. With hydration heat influence index Proportional, through an exponential function The denominator indicates the roughness. The effect is logarithmic. The effect of surface roughness on concrete structures can be nonlinear, especially when... When the value is small, the properties of the logarithm can better reflect the impact of its growth.

[0034] Under the same water-cement ratio, aggregate type, and additive content, the heat of hydration released by concrete is directly proportional to its volume. That is, the larger the specimen volume, the higher the total heat of hydration. This is because more cement and other components participate in the hydration reaction, naturally increasing the released heat; therefore, the volume of the concrete specimen to be tested... With hydration heat influence index Proportional.

[0035] The thickness of the concrete specimen being tested affects heat conduction and dissipation, thus influencing the accumulation and release of hydration heat. Concrete thickness affects its heat storage and dissipation capacity. Thicker concrete typically has a higher capacity for hydration heat accumulation, but may also experience slower heat dissipation, leading to temperature concentration and potentially affecting the quality of concrete molding. Therefore, the thickness of the concrete specimen being tested is crucial. With hydration heat influence index Proportional, in the form of square root This indicates that increasing the thickness leads to a greater impact, but the increase is not linear. At the same time, it avoids excessively large diameter values ​​from having a disproportionate impact on the calculation results, ensuring that the calculation results are smooth and reasonable.

[0036] The parameters for calculating the heat of hydration influence index are shown in Table 1.

[0037] Table 1

[0038] Through the analysis of the data, it is observed that there is a certain correlation between different characteristic parameters. For example, from the data, it can be seen that there is a certain negative correlation between the surface roughness and the hydration heat influence index. With the increase of the sample number, the surface roughness gradually decreases (from 2.00 to 1.55), and the hydration heat influence index also decreases (from 6.120 to 5.085). This shows that under the condition of rougher surface, the hydration heat of concrete has more influence, which may lead to higher heat release.

[0039] In the analysis of the relationship between the predicted value of hydration heat and the thickness of the concrete specimen, it is found that with the increase of the thickness, the predicted value of hydration heat presents a gradually decreasing trend. This may be due to the fact that in the hydration process of thicker concrete specimens, heat is more difficult to conduct to the external environment, thereby affecting the release efficiency of hydration heat. For example, the thickness of sample No. 5 is 36 mm, and the corresponding predicted value of hydration heat is 460, while the thickness of sample No. 1 is 40 mm, and the predicted value is 500. The comprehensive influence of thickness and hydration heat should be considered to optimize the proportioning and construction technology of concrete.

[0040] In addition, the volume of the concrete specimen to be detected also shows a certain correlation with the hydration heat influence index. Larger concrete volume usually accompanies higher hydration heat influence index. The volume of sample No. 1 is 1.50 m³, and the hydration heat influence index is 6.120, while the volume of sample No. 6 is 1.25 m³, and the hydration heat influence index is 5.475. This shows that in larger volume of concrete specimen, the accumulation effect of hydration heat may lead to higher temperature change, which has an impact on the strength and durability of concrete.

[0041] Therefore, the surface roughness, the predicted value of hydration heat, the thickness of concrete and its volume are important factors affecting the hydration heat influence index.

[0042] On the surface of the concrete specimen, appropriate coupling agent such as oil or water is applied, the ultrasonic probe is attached to the surface of the specimen, the instrument emits ultrasonic waves, measures the time of wave propagation in concrete, calculates the thickness, and also can measure at multiple positions and take the average value as the thickness of the concrete specimen to be detected.

[0043] The concrete specimen is completely immersed in a water tank with a known volume, the initial water level is recorded, after the specimen is put into the water tank, the water level is measured again, the water volume corresponding to the water level rise is calculated, which is the volume of the concrete specimen.

[0044] The surface roughness of the concrete specimen to be detected is The specific method for obtaining the surface roughness of the concrete specimen to be detected is as follows: The surface roughness measuring device for the concrete specimen to be detected selects a touch stylus profilometer, randomly selects a plurality of sampling regions from the surface region of the concrete specimen to be detected, measures and analyzes the sampling regions by using the touch stylus profilometer, obtains the surface roughness of each sampling region, and calculates the average surface roughness of all the sampling regions, which is taken as the surface roughness of the concrete specimen to be detected. The calculation formula is as follows: ; ; In the formula, represents the sampling length of the touch stylus profilometer in the kth sampling region, k is the index of the sampling region, and K is the number of sampling regions, is the height of the sampling point deviating from the center line at the qth position in the sampling length of the kth sampling region, q is the coordinate of the sampling point in the sampling length, is the surface roughness of the kth sampling region, is the surface roughness of the concrete specimen to be detected, the center line and is obtained by data processing by the built-in software of the touch stylus profilometer.

[0045] Step 4: Obtain the environmental parameters in the high-temperature tunnel, and calculate the environmental influence index according to the obtained environmental parameters in the high-temperature tunnel, wherein the environmental parameters in the high-temperature tunnel include real-time temperature of the tunnel surface, real-time humidity in the tunnel, and real-time wind speed in the tunnel.

[0046] Obtain the environmental parameters in the high-temperature tunnel, and calculate the environmental influence index according to the obtained environmental parameters in the high-temperature tunnel, wherein the formula for calculating the environmental influence index is as follows: ; In the formula, is the environmental influence index, is the real-time temperature of the tunnel surface, is the real-time humidity in the tunnel, is the real-time wind speed in the tunnel, is the set reference humidity, is the set reference temperature.

[0047] It should be noted that the environmental influence index is used to represent the influence of the environment in the tunnel on the curing temperature of the concrete specimen to be detected, wherein the environmental influence index The larger the value is, the higher the temperature in the tunnel is, and the curing temperature of the concrete specimen to be detected should be reduced.

[0048] wherein, high humidity can cause the concrete surface water evaporation slow, delay solidification, while the heat capacity of air in high humidity conditions will increase, because the specific heat capacity of wet air is higher than that of dry air. This means that in high humidity environment, air can store more heat, resulting in reduced heat dissipation efficiency, when the humidity is high, the water vapor content in the air increases, which will affect the transfer of heat. The thermal conductivity of wet air is low, and the heat dissipation capacity is limited, which may cause the temperature of the concrete specimen to be too high, affecting the quality of the concrete; while low humidity can accelerate water evaporation, causing dry shrinkage cracks. Therefore, whether the humidity is too high or too low, it will not be conducive to the performance and construction quality of concrete, so the difference between the real-time humidity in the tunnel and the reference humidity is proportional to the environmental impact index , calculated in square form , which means the greater the deviation of humidity from the reference humidity, the greater the contribution to the environmental impact index. When the humidity is higher or lower than the reference value, the impact is positive, especially when the deviation is large, the environmental impact index will increase significantly.

[0049] High temperature environment can accelerate the hydration reaction of concrete, but it can also cause water evaporation too fast, affecting the strength development and increasing the risk of cracks, especially in high ground temperature tunnels, so the real-time temperature on the surface of the tunnel is proportional to the environmental impact index , through the exponential function , which shows that its impact on the environmental impact index is nonlinear. As the temperature deviates from the reference temperature, the impact index will rise rapidly.

[0050] Increased wind speed will enhance the water evaporation rate on the surface of the concrete, resulting in lower humidity, accelerating the solidification process, and improving heat dissipation. Higher wind speed will take away the heat generated, avoiding high curing temperature, so the real-time wind speed in the tunnel is inversely proportional to the environmental impact index , standardized by squaring and by the logarithmic function , which shows that the impact of wind speed on the environmental impact index is relatively small, and will not produce dramatic changes like humidity and temperature.

[0051] wherein the reference humidity set can be set according to expert experience combined with the environment in high ground temperature tunnels, generally taking values of to , the setting method of the reference temperature is the same. Part of the sample parameters and environmental impact index specific data are shown in Table 2.

[0052] Table 2

[0053] The influence of environmental changes on curing temperature is more significant in high-temperature tunnels, and therefore, adjusting the curing temperature according to the unique environmental parameters in high-temperature tunnels can improve the durability and crack resistance.

[0054] Step 5: Collect the thermal conductivity of the tunnel surface structure in the high-temperature tunnel, and based on the obtained thermal conductivity of the tunnel surface structure, combine the environmental influence index and the hydration heat influence index to dynamically correct the curing temperature of the concrete test piece, obtain the real-time curing temperature accurate value, and adjust the curing temperature of the concrete test piece according to the obtained real-time curing temperature accurate value, and complete the temperature control of the concrete test piece curing.

[0055] Based on the obtained thermal conductivity of the tunnel surface structure, combine the environmental influence index and the hydration heat influence index to dynamically correct the curing temperature of the concrete test piece, obtain the real-time curing temperature accurate value, wherein the specific formula for calculating the real-time curing temperature accurate value is: ; In the formula, is the real-time curing temperature accurate value, is the initial value of the curing temperature of the concrete test piece to be detected, is the thermal conductivity of the tunnel surface structure, is the weight coefficient of the environmental influence index, is the weight coefficient of the hydration heat influence index, is the weight coefficient of the thermal conductivity of the tunnel surface structure, wherein and , and are all greater than 0.

[0056] Since the above describes the relative relationship between the environmental influence index and the hydration heat influence index on the curing temperature, it is not repeated here, and it is necessary to note that the square form indicates the nonlinear characteristics of environmental influence, which means that when the environmental influence is large, the correction effect will increase significantly, emphasizing the greater adjustment demand for curing temperature under adverse environmental conditions; the logarithmic function indicates the importance of hydration heat in influencing the curing temperature, and the logarithmic function indicates has a greater influence on the real-time curing temperature accurate value in a small range, but the influence tends to be slow at a larger value.

[0057] The thermal conductivity of the tunnel surface structure reflects the heat absorption and dissipation capacity of the concrete test piece. The higher the thermal conductivity, the stronger the heat dissipation capacity of the concrete test piece, which may result in the need for higher curing temperature to prevent insufficient concrete strength caused by low temperature, and therefore the thermal conductivity of the tunnel surface structure is combined with the real-time curing temperature accurate value Proportional, by the square root of the form Reduce its impact, avoid excessive thermal conductivity on the results of disproportionate influence, to ensure the smoothness and reasonableness of the calculation results.

[0058] Among them, usually in the process of concrete construction, environmental conditions (such as temperature, humidity, wind speed, etc.) have the most significant impact on the hydration process and strength development of concrete, especially for high-temperature tunnels. Poor environmental conditions can directly lead to reduced concrete strength, increased cracks, and other problems. Hydration heat is the heat generated during the hydration process of concrete, which has an important influence on the hydration rate and strength development. However, compared to the influence of external environment, the influence of hydration heat, although important, is usually secondary. The thermal conductivity of the tunnel surface structure affects the heat conduction capacity of the concrete, and although it affects heat dissipation to some extent, its influence is usually smaller compared to the environment and hydration heat, so the thermal conductivity of the tunnel surface structure is set And , And are greater than 0. Some of the real-time curing temperature accurate value data is shown in Table 3.

[0059] Table 3

[0060] The performance parameters of the concrete test pieces under the real-time curing temperature accurate value are shown in Table 4.

[0061] Table 4

[0062] Through the analysis of the data, we observed that the change between the initial value and the accurate value of the curing temperature has a certain influence on the strength and crack number of the concrete. For example, the curing temperature initial value of sample No. 1 is 30°C, and the strength is 31 MPa, while under the corrected temperature, the strength is increased to 31 MPa, and the crack number remains 1. Such results show that the temperature stability during the curing process is crucial for the maintenance of concrete performance.

[0063] Most of the samples have their concrete strength generally improved under the corrected curing temperature. For example, the strength of sample No. 5 is increased from 32 MPa to 35 MPa, showing that the corrected curing temperature can promote the hydration reaction of concrete, thereby enhancing its overall strength.

[0064] The modified curing temperature also significantly affects the number of cracks. In multiple samples, the number of cracks decreases after modification, indicating that appropriate temperature adjustment can effectively reduce the shrinkage stress of concrete during the hydration process, thereby reducing the generation of cracks. For example, sample No. 5 reduces the number of cracks from 4 to 2 while improving the strength, showing that the optimization of curing temperature can improve the overall durability of concrete.

[0065] The above formulas are dimensionless values calculated, and the formula is obtained by software simulation of a large number of data to obtain the most real situation. The preset parameters in the formula are set by a person skilled in the art according to the actual situation.

[0066] The above embodiments can be realized wholly or partially by software, hardware, firmware, or any other combination. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of the examples described in connection with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0067] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, which can be located in one place or distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0068] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A variable temperature curing method for curing a high ground temperature tunnel shotcrete test piece, characterized by, The specific steps include: Obtain a plurality of concrete specimen samples with different water-binder ratios, aggregate types, and additive contents, obtain hydration heat data of different concrete specimen samples under the same quality through experiments, normalize and preprocess the obtained hydration heat data, and map the preprocessed hydration heat data to the water-binder ratio, aggregate type, and additive content data of the corresponding concrete specimen sample one by one to generate a training sample data set; Based on the data in the training sample data set, a neural network prediction model is established, the water-binder ratio, aggregate type, and additive content data of the concrete specimen samples in the training sample data set are taken as the input of the neural network prediction model, and the corresponding hydration heat data is taken as the label, the neural network prediction model is trained, and a hydration heat prediction model is obtained; Obtain the water-binder ratio, aggregate type, and additive content data of the concrete specimen to be detected, and input them into the trained hydration heat prediction model to obtain the hydration heat prediction value of the concrete specimen to be detected, and calculate the hydration heat influence index based on the obtained hydration heat prediction value of the concrete specimen to be detected, combined with the surface roughness and thickness of the concrete specimen to be detected; Obtain the environmental parameters in the high-temperature tunnel, and calculate the environmental influence index based on the obtained environmental parameters in the high-temperature tunnel, wherein the environmental parameters in the high-temperature tunnel include the real-time temperature of the tunnel surface, the real-time humidity in the tunnel, and the real-time wind speed in the tunnel; Collect the thermal conductivity of the tunnel surface structure in the high-temperature tunnel, dynamically correct the curing temperature of the concrete specimen to be detected based on the obtained thermal conductivity of the tunnel surface structure, combined with the environmental influence index and the hydration heat influence index, obtain the real-time curing temperature accurate value, and regulate the curing temperature of the concrete specimen to be detected based on the obtained real-time curing temperature accurate value, complete the temperature control of the concrete specimen curing.

2. The method according to claim 1, wherein the method is characterized by: The obtained hydration heat data is normalized and preprocessed, and the formula for normalization and preprocessing is: ； wherein is the normalized data of the hydration heat of the i-th concrete specimen, is the hydration heat data of the i-th concrete specimen, is the minimum hydration heat data in the concrete specimen, is the maximum hydration heat data in the concrete specimen, wherein i is the index of the concrete specimen, wherein is the total number of the concrete specimens; The generation method of the training sample data set is to map the preprocessed hydration heat data to the water-binder ratio, aggregate type, and additive content data of the corresponding concrete specimen sample one by one to form a corresponding grid, and the formed grid is recorded as the training sample data set.

3. The method of claim 2, wherein the method is characterized by: Based on the data in the training sample data set, a neural network prediction model is established, wherein the hydration heat prediction model is established based on a long short-term memory network model (LSTM model), the LSTM model selects an activation function and an optimization algorithm, wherein a Tanh function is selected as the activation function, and Adam is selected as the optimization algorithm of the LSTM model; the formula of the Tanh function is: ； wherein denotes the Tanh function, the argument denotes the input weighted sum of a neuron, i.e. the result of the weighted sum of the inputs received by the neuron from the previous layer; Meanwhile, the hyperparameters of the LSTM model are set, including the number of network layers, the number of iterations, the learning rate, the batch size, the number of training times, the batch processing quantity, and the number of hidden layer neurons; The number of network layers is set to 4 layers, the number of iterations is set to 100, the learning rate is set to 0.001, the batch size is set to 32, the number of training times is set to 100, the batch processing quantity is set to 128, and the number of hidden layer neurons is 32. The hydration heat prediction model after training inputs water-binder ratio, aggregate type and additive content data of the concrete test piece, and outputs corresponding hydration heat prediction value.

4. The method of claim 1, wherein the method is characterized by: According to the obtained hydration heat prediction value of the to-be-detected concrete test piece, combined with the surface roughness and thickness of the to-be-detected concrete test piece, a hydration heat influence index is calculated, wherein the specific formula for calculating the hydration heat influence index is: ； wherein, is a hydration heat influence index, is a surface roughness of the concrete specimen to be detected, is a hydration heat prediction value, is a thickness of the concrete specimen to be detected, is a volume of the concrete specimen to be detected.

5. The method of claim 4, wherein the method is characterized by: The surface roughness of the concrete test piece to be detected The specific acquisition method is that: The surface roughness of the to-be-detected concrete test piece is measured by a stylus profilometer. Multiple sampling areas are randomly selected from the surface area of the to-be-detected concrete test piece. The stylus profilometer is used to measure and analyze the sampling areas to obtain the surface roughness of each sampling area. The average surface roughness of all sampling areas is calculated, which is taken as the surface roughness of the to-be-detected concrete test piece. The calculation formula is as follows: ； ； In the formula, represents the sampling length of the stylus profilometer in the kth sampling area, k is the index of the sampling area, and , K is the number of sampling areas, is the height of the qth sampling point in the kth sampling area deviating from the center line within the sampling length, q is the coordinate of the sampling point within the sampling length, is the surface roughness of the kth sampling area, is the surface roughness of the concrete test piece to be detected, the center line and is obtained by data processing through the built-in software of the stylus profilometer.

6. The method of claim 4, wherein the method is characterized by: The environmental parameters in the high-temperature tunnel are obtained. According to the obtained environmental parameters in the high-temperature tunnel, an environmental influence index is calculated, wherein the specific formula for calculating the environmental influence index is: ； wherein, is an environmental impact index, is a real-time temperature of the tunnel surface, is a real-time humidity inside the tunnel, is a real-time wind speed inside the tunnel, is a set reference humidity, is a set reference temperature.

7. The method of claim 6, wherein the method is characterized by: According to the obtained tunnel surface structure thermal conductivity, combined with the environmental influence index and the hydration heat influence index, the curing temperature of the to-be-detected concrete test piece is dynamically corrected to obtain an accurate real-time curing temperature value, wherein the specific formula for calculating the accurate real-time curing temperature value is: ； wherein is the real-time curing temperature accurate value, is the curing temperature initial value of the concrete test piece to be detected, is the thermal conductivity of the tunnel surface structure, is the weight coefficient of the environmental influence index, is the weight coefficient of the hydration heat influence index, is the weight coefficient of the thermal conductivity of the tunnel surface structure, wherein and , and are all greater than 0.

Images