Intelligent control method for improving quality of cement concrete
By introducing self-healing internal curing gel and photosensitive temperature-controlled materials into cement concrete, and combining them with a neural network model, intelligent temperature and humidity control and self-healing are achieved, which solves the shortcomings of traditional curing methods and improves the durability and stability of concrete.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WUHAN METALLURGY ARCHITECTURE RES YUAN CO LTD
- Filing Date
- 2023-12-13
- Publication Date
- 2026-06-26
AI Technical Summary
Existing cement concrete curing methods are inflexible, have limited self-healing capabilities, are difficult to control in terms of temperature, and have inaccurate strength prediction, resulting in insufficient structural durability and stability.
By blending self-healing internal maintenance gel with high-strength foamed iron-nickel alloy, combined with photosensitive temperature control materials and neural network genetic algorithms, an intelligent temperature and humidity control, self-healing, and environmentally adaptable maintenance system is achieved.
It improves the service life and durability of concrete structures, reduces maintenance costs, and enhances the stability and self-healing ability of the structures.
Smart Images
Figure BDA0004608026370000051 
Figure BDA0004608026370000052 
Figure BDA0004608026370000061
Abstract
Description
Technical Field
[0001] This invention belongs to the field of building materials, and in particular relates to an intelligent control method for improving the quality of cement concrete. Background Technology
[0002] Cement concrete is one of the most commonly used materials in construction and infrastructure. However, cement concrete structures have long faced numerous problems during use, such as cracking, damage, and aging. These problems not only affect the strength and durability of the structure but also lead to high maintenance costs and resource waste. The curing period of concrete is a key stage of strength development, and to address these issues, many researchers have dedicated themselves to improving the curing methods and materials for cement concrete. Traditional curing methods typically rely on the control of external environmental conditions, which often fails to meet the specific needs of concrete structures. Furthermore, due to the complexity of cement concrete structures, older self-healing crack technologies often have limited effectiveness and are complex to implement.
[0003] Current problems in concrete curing include: 1. Inflexible curing strategies: Traditional curing methods rely on external environmental conditions and cannot be intelligently adjusted according to the actual needs of the concrete structure. 2. Limited self-healing ability: Existing self-healing materials suffer from complex application and unstable repair effects, making it difficult to achieve lasting repair of cracks and damage. 3. Difficulty in temperature control: Changes in ambient temperature have a significant impact on the curing effect of concrete, but there is currently a lack of effective methods to achieve precise temperature regulation. 4. Lack of control over strength during curing: Traditional strength prediction methods are often based on experience and inference, lacking accuracy and reliability. Summary of the Invention
[0004] This invention discloses an intelligent control method for improving the quality of cement concrete. This method realizes an intelligent, self-healing, and environmentally adaptable cement concrete curing system, possessing self-healing capabilities, humidity control, and temperature regulation functions. It can extend the service life of concrete structures, reduce maintenance costs, and improve their durability and stability.
[0005] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:
[0006] A method for comprehensively improving the quality of cement concrete during the curing period is provided, including the following steps:
[0007] 1) Concrete mixing and molding stage: The self-healing internal curing gel and high-strength foamed iron-nickel alloy are mixed using negative pressure and ultrasonic method. The resulting mixture is used as aggregate and mixed with raw materials cement, sand and aggregate to obtain concrete, which is then molded and demolded.
[0008] 2) Spraying application of photosensitive temperature control material: Photosensitive polyimide and photosensitive heat-absorbing material are mixed to obtain photosensitive temperature control material. The photosensitive temperature control material is evenly sprayed on the concrete surface to ensure that the coating evenly covers the entire surface. The light source is used to irradiate it to cure it into a film.
[0009] 3) Intensity prediction and automated control stage:
[0010] ①Based on neural network genetic algorithm technology, a concrete strength prediction model is established through data preprocessing, neural network construction, network training and optimization, and genetic algorithm optimization. Then, the model is verified and its accuracy is evaluated. Using the verified strength prediction model, the optimal temperature and humidity for concrete strength development are calculated and generated.
[0011] ② Monitor the temperature change of the concrete surface. When the temperature is lower than the optimal temperature obtained in step ①, increase the thickness of the photosensitive temperature control material and / or increase the light frequency to raise the concrete surface temperature and achieve precise temperature control.
[0012] ③ Monitor the changes in humidity on the concrete surface. When the humidity is lower than the optimal humidity obtained in step ②, increase the humidity by spraying water onto the surface after removing the photosensitive temperature control film.
[0013] According to the above scheme, in step 1), the preparation step of the self-healing-internal maintenance gel is as follows: dissolve the self-healing material in water to form a saturated solution of the self-healing material, and then add an internal maintenance agent to fully absorb the saturated solution of the self-healing material to form a self-healing-internal maintenance gel.
[0014] Preferably, the self-healing material, by weight, comprises: 20-40 parts of cationic complexing agent, 80-120 parts of calcium ion additive, 30-60 parts of reaction promoter, and 10-50 parts of solvent.
[0015] More preferably, the cationic complexing agent is one or more of sodium oxalate, sodium polyacrylate, sodium citrate, sodium nitrite, and sodium phosphate; the calcium ion auxiliary agent is one or two of calcium nitrate and calcium oxalate; the reaction promoter is one or two of choline and choline chloride; and the solvent is water.
[0016] Preferably, the internal curing agent is a superabsorbent resin.
[0017] More preferably, the superabsorbent resin is a sodium polyacrylate-polyacrylamide copolymer.
[0018] More preferably, the superabsorbent resin is a white powder with a water absorption ratio of 500-1000, while the water absorption ratio of physiological saline is 50-120.
[0019] Preferably, the mass ratio of the self-healing material to water is 1:100 to 17:100.
[0020] According to the above scheme, in step 1), the high-strength foamed iron-nickel alloy has a porosity of 56-75% and a density of 0.2-1.9 g / cm³. 3 Pore size 10-20μm, compressive strength 35-50MPa, particle size 3-5mm.
[0021] According to the above scheme, in step 1), the specific parameters for blending by negative pressure and ultrasound are: negative pressure -45kPa to 60kPa, and ultrasound is usually selected at 15 to 23kHz.
[0022] According to the above scheme, in step 1), concrete is prepared by feeding the mixture within 12 hours after preparation to avoid the evaporation of moisture in the mixture, and it should be stored in a dark place at room temperature.
[0023] According to the above scheme, in step 2), the photosensitive heat-absorbing material is selected from one or more of the following: metal nanoparticles (silver, copper), carbon nanotubes, graphene, malachite green, and rhodamine B.
[0024] According to the above scheme, in step 2), the mixing ratio of photosensitive polyimide and photosensitive heat-absorbing material is determined according to the photothermal conversion ratio of the heat-absorbing material, and the mass ratio is usually 100:20-25.
[0025] According to the above scheme, in step 3)③, the photosensitive temperature control film is removed by solvent reaction by spraying a mixture of ethanol and dimethyl sulfoxide with a volume ratio of 2.5-3.5:1.
[0026] According to the above scheme, in step 3), data preprocessing includes:
[0027] ① Collect concrete sample data, including concrete internal temperature, humidity, curing time and corresponding concrete strength;
[0028] ② The collected data is preprocessed, including normalization or standardization, to ensure that the input features have similar scale and range.
[0029] According to the above scheme, step 3) of constructing the neural network model includes:
[0030] ① Design a multi-layer feedforward neural network, including an input layer, hidden layers, and an output layer; ② Define the connection weights and bias terms between each layer and initialize them to random values; ③ Select an appropriate activation function, such as the Sigmoid function or the ReLU function, to introduce non-linear characteristics.
[0031] According to the above scheme, in step 3), network training and optimization include:
[0032] ① Use the training set data as input and calculate the network's output value through forward propagation;
[0033] ② Calculate the loss between the output value and the actual intensity. Commonly used loss functions include mean squared error or cross-entropy.
[0034] ③ Use the backpropagation algorithm to update the weights and biases to optimize the loss function and reduce the gap between the predicted and actual values;
[0035] ④ Repeat the above steps until the model converges, that is, the loss function reaches a satisfactory minimum value.
[0036] According to the above scheme, in step 3), the genetic algorithm optimization includes:
[0037] ① Further optimize the neural network model by using a genetic algorithm to search and adjust the network parameters in order to find a better solution;
[0038] ② Define a fitness function to evaluate the fitness of each individual based on the difference between the predicted results and the actual values;
[0039] ③ By applying genetic operations such as selection, crossover, and mutation, new individuals are generated through continuous iteration, and individuals with low fitness are eliminated, so that the population gradually tends towards the optimal solution;
[0040] ④ The genetic algorithm is terminated when the number of iterations or fitness reaches a set threshold, resulting in an optimized neural network model.
[0041] According to the above scheme, in step 3), model verification and accuracy evaluation: the established strength prediction model is verified, and the accuracy and reliability of the model are evaluated by comparing it with the actual test results to ensure that it can accurately predict the development trend of concrete strength.
[0042] This invention provides an intelligent control method for improving the quality of cement concrete. On one hand, a self-healing internal curing gel is infiltrated into a high-strength, high-porosity foamed iron-nickel alloy via negative pressure ultrasonication. This prevents rapid moisture loss from the self-healing internal curing gel and ensures a stable, long-term internal water supply for concrete curing. Simultaneously, the self-healing internal curing gel does not form cavities within the concrete after moisture loss, and the high-strength foamed iron-nickel alloy provides reliable support, guaranteeing the concrete's strength. On the other hand, after concrete molding, a photosensitive temperature-controlling material is sprayed onto the surface. Upon light exposure, a curing film forms, sealing the internal environment of the concrete and preventing moisture loss. Furthermore, based on changes in ambient temperature, the photosensitive temperature-controlling material converts light energy into heat energy by adjusting the light exposure frequency, automatically adjusting the surface temperature of the concrete structure, providing a foundation for subsequent intelligent curing control. Finally, this invention applies neural network genetic algorithm technology to the processing model of the intelligent regulation system. By substituting previous experimental data for calculations, and based on a strength prediction model and optimal temperature and humidity, the control strategy and parameters of the automated control system are designed to ensure that temperature and humidity are regulated according to the optimal curve. Based on real-time monitoring data and feedback mechanisms, the control strategy and parameters are dynamically adjusted to achieve stable and precise control results.
[0043] Compared with the prior art, the beneficial effects of the present invention are as follows:
[0044] This invention provides an intelligent control method for improving the quality of cement concrete. It involves infiltrating a self-healing, internal curing gel into a high-strength, high-porosity foamed iron-nickel alloy using negative pressure ultrasound, and adding it during concrete mixing to reduce porosity and strength loss. Simultaneously, a photosensitive temperature-controlled material is sprayed after concrete molding to achieve temperature regulation and moisture retention. Finally, based on a neural network prediction model and temperature and humidity sensor monitoring, the amount of moisture replenishment is precisely adjusted to improve the strength and stability of the concrete structure. This invention realizes an intelligent, self-healing, and environmentally adaptable cement concrete curing system with self-healing capabilities, humidity control, and temperature regulation functions. It can extend the service life of concrete structures, reduce maintenance costs, and improve their durability and stability. Attached Figure Description
[0045] Figure 1 This is a comparison of the true and predicted values in MATLAB for the training set (top figure) and the test set (bottom figure) in an embodiment of the present invention.
[0046] Figure 2 These are the scatter plots of the actual and predicted values fitted to the MATLAB test set in this embodiment of the invention.
[0047] Figure 3 This is an example of the effect of repairing concrete cracks after curing in an embodiment of the present invention. Detailed Implementation
[0048] The invention of this application is further illustrated below with examples, but the embodiments should not be regarded as limiting the invention.
[0049] Example
[0050] A smart control method for improving the quality of cement concrete is provided, comprising the following steps:
[0051] 1) Concrete mixing and molding steps:
[0052] Specifically, a self-healing material is prepared, comprising 25 parts of a cationic complexing agent, 97 parts of a calcium ion accelerator, 43 parts of a reaction promoter, and 40 parts of a solvent; the cationic complexing agent is sodium polyacrylate; the calcium ion accelerator is calcium oxalate; the reaction promoter is choline; and the solvent is deionized water.
[0053] Specifically, prepare an internal protective agent, which is composed of superabsorbent resin with a water absorption ratio of 850, while physiological saline has a water absorption ratio of 77. The main chemical component is sodium polyacrylate-polyacrylamide copolymer.
[0054] First, dissolve the self-healing material in water at a mass ratio of 13:100 to form a saturated solution of the self-healing material. Then, the internal maintenance agent fully absorbs the saturated solution of the self-healing material to form a self-healing-internal maintenance gel.
[0055] Self-healing internal maintenance gel blended with high-strength foamed iron-nickel alloy: the high-strength foamed iron-nickel alloy has a selected porosity of 56% and a density of 1.4 g / cm³. 3 The self-healing-internal maintenance gel with a pore size of 12μm, a compressive strength of 45MPa, and a particle size of 3-5mm was blended with a high-strength foamed iron-nickel alloy. The blending method was negative pressure and ultrasonic blending, with a negative pressure of -55kPa and an ultrasonic frequency of 15kHz. The blending was stirred for 1.5h to ensure that the resulting mixture was uniformly distributed.
[0056] Adding the mixture to the concrete mixing equipment: Add the above-obtained mixture as aggregate to the concrete mixing equipment, mix it with raw materials such as cement, sand, and aggregate, and then form it to ensure that the mixture is uniformly mixed. See Table 1 for the specific mix proportions.
[0057] Table 1. Design mix proportions (g) for different grades of concrete
[0058]
[0059] 2) Spray application of photosensitive temperature control materials:
[0060] Prepare the photosensitive temperature control material. Select photosensitive polyimide and carbon nanotubes and mix them at a mass ratio of 100:23.
[0061] Photosensitive temperature control material spraying: After the concrete is molded and demolded, the photosensitive temperature control material is evenly sprayed onto the concrete surface using a high-pressure spraying device (12 MPa pressure) to ensure that the coating evenly covers the entire surface. Based on the current ambient temperature of -8℃, the spray thickness is 3mm, and the spraying time is 15s.
[0062] The light source irradiates it, causing it to solidify into a film.
[0063] 3) Establish an intensity prediction model and an automated control system:
[0064] Strength prediction and automated control stage: A concrete strength prediction model is established through data preprocessing, neural network construction, network training and optimization, and genetic algorithm optimization.
[0065] I. Collect concrete sample data, including concrete internal temperature, humidity, curing time, and corresponding concrete strength; concrete mix design is shown in Table 1 above, and test data is shown in Table 2 below.
[0066] Table 2: Specific experimental data are as follows
[0067]
[0068]
[0069]
[0070]
[0071] The embodiments described above preprocess the collected data, including normalization or standardization, to ensure that the input features have similar scale and range. Neural Network Model Construction: 1. Design a multi-layer feedforward neural network, including an input layer, hidden layers, and an output layer; 2. Define the connection weights and biases between each layer and initialize them to random values; 3. Choose the Sigmoid function as the activation function to introduce non-linear characteristics. Network Training and Optimization: 1. Use the training set data as input and calculate the network's output value through forward propagation; 2. Calculate the loss between the output value and the actual strength. Commonly used loss functions include mean squared error or cross-entropy; 3. Update the weights and biases using the backpropagation algorithm to optimize the loss function and reduce the gap between the predicted and actual values; 4. Repeat the above steps until the model converges, i.e., the loss function reaches a satisfactory minimum value. Genetic Algorithm Optimization: 1. Further optimize the neural network model by using a genetic algorithm to search and adjust network parameters to find a better solution; 2. Define a fitness function to evaluate the fitness of each individual based on the difference between the predicted result and the true value; 3. Apply genetic operations such as selection, crossover, and mutation to generate new individuals through continuous iteration and eliminate individuals with low fitness, gradually bringing the population towards the optimal solution; 4. Terminate the genetic algorithm when the number of iterations or the fitness reaches a set threshold, obtaining the optimized neural network model. The settings include: 5 hidden layer nodes, a maximum number of iterations of 1000, an error threshold of 1e-6, a learning rate of 0.01, 50 generations, a population size of 5, a selection function parameter of 0.09, a crossover function parameter of 2, and a mutation function parameter of 3.
[0072] Model validation and accuracy evaluation: The established intensity prediction model was validated. By comparing it with actual test results, the model's prediction accuracy was found to be 96.8%, proving the model's feasibility.
[0073] Calculate the optimal internal temperature and humidity: Using a validated strength prediction model, calculate and generate the optimal temperature and humidity for concrete strength development, which will serve as a basis for curing and a reference for automated control systems.
[0074] The humidity control method is to adjust the humidity by spraying water off the surface of the photosensitive temperature control film. The photosensitive temperature control film is removed by spraying a mixture of ethanol and dimethyl sulfoxide (volume ratio 3:1) to remove it through a solvent reaction.
[0075] The temperature control method involves increasing the light frequency to control the temperature rise and decreasing the light frequency to control the temperature fall.
[0076] The curing process is automated, equipped with temperature and humidity sensors, and combined with a device to adjust the thickness of the photosensitive temperature-controlled material and the light frequency. Based on real-time monitoring data and a feedback mechanism, the automated control system precisely adjusts and controls the temperature and humidity to achieve optimal conditions. Table 3 below shows the results of comparing no curing and curing chamber curing schemes, demonstrating that the curing scheme in this embodiment has a positive impact on the development of concrete compressive strength. Meanwhile, as... Figure 3 As shown, cracks on the concrete surface can self-heal, which greatly improves the recovery of strength and waterproof performance.
[0077] Table 3: Compressive Strength of Concrete under Different Curing Conditions and Curing Times
[0078]
[0079] The embodiments described above provide a detailed explanation of the technical solutions and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the present invention. Any modifications, additions, and equivalent substitutions made within the scope of the principles of the present invention should be included within the protection scope of the present invention.
Claims
1. An intelligent control method for improving the quality of cement concrete, characterized in that, Includes the following steps: 1) Concrete mixing and molding stage: The self-healing internal curing gel and high-strength foamed iron-nickel alloy are mixed using negative pressure and ultrasonic method. The resulting mixture is used as aggregate and mixed with concrete raw materials to obtain concrete, which is then molded and demolded. 2) Spraying application of photosensitive temperature control material: Photosensitive polyimide and photosensitive heat-absorbing material are mixed to obtain photosensitive temperature control material. The photosensitive temperature control material is evenly sprayed on the concrete surface to ensure that the coating evenly covers the entire surface. The light source is used to irradiate it to cure it into a film. 3) Intensity prediction and automated control stage: ①Based on neural network genetic algorithm technology, a concrete strength prediction model is established through data preprocessing, neural network construction, network training and optimization, and genetic algorithm optimization. Then, the model is verified and its accuracy is evaluated. Using the verified strength prediction model, the optimal temperature and humidity for concrete strength development are calculated and generated. ② Monitor the temperature change of the concrete surface. When the temperature is lower than the optimal temperature obtained in step ①, increase the thickness of the photosensitive temperature control material and / or increase the light frequency to raise the concrete surface temperature and achieve precise temperature control. ③ Monitor changes in concrete surface humidity. When the humidity is lower than the optimal humidity obtained in step ①, increase the humidity by spraying water onto the surface after removing the photosensitive temperature control film; where: Data preprocessing includes: ① Collect concrete sample data, including concrete internal temperature, humidity, curing time and corresponding concrete strength; ② The collected data is preprocessed, including normalization or standardization, to ensure that the input features have similar scale and range; Neural network construction includes: ① Design a multi-layer feedforward neural network, including an input layer, hidden layers, and an output layer; ② Define the connection weights and bias terms between each layer and initialize them to random values; ③ Choose either the Sigmoid function or the ReLU function to introduce nonlinear characteristics; Network training and optimization include: ① Use the training set data as input and calculate the network's output value through forward propagation; ② Calculate the loss between the output value and the actual intensity. Commonly used loss functions include mean squared error or cross-entropy. ③ Use the backpropagation algorithm to update the weights and biases to optimize the loss function and reduce the gap between the predicted and actual values; ④ Repeat the above steps until the model converges, that is, the loss function reaches a satisfactory minimum value; Genetic algorithm optimization includes: ① Further optimize the neural network model by using a genetic algorithm to search and adjust the network parameters in order to find a better solution; ② Define a fitness function to evaluate the fitness of each individual based on the difference between the predicted results and the actual values; ③ By applying selection, crossover, and mutation genetic operations, new individuals are generated through continuous iteration, and individuals with low fitness are eliminated, so that the population gradually tends towards the optimal solution; ④ The genetic algorithm is terminated when the number of iterations or fitness reaches a set threshold, resulting in an optimized neural network model.
2. The intelligent control method according to claim 1, characterized in that, In step 1), the preparation step of the self-healing-internal maintenance gel is as follows: dissolve the self-healing material in water to form a saturated solution of the self-healing material, and then add an internal maintenance agent to fully absorb the saturated solution of the self-healing material to form a self-healing-internal maintenance gel.
3. The intelligent control method according to claim 2, characterized in that, By weight, the self-healing material consists of: 20 parts cationic complexing agent. 40 portions, calcium ion additive 80 120 parts, reaction accelerator 30 60 parts, solvent 10 50 parts; the inner curing agent is a superabsorbent resin.
4. The intelligent control method according to claim 3, characterized in that, The cationic complexing agent is one or more of sodium oxalate, sodium polyacrylate, sodium citrate, sodium nitrite, and sodium phosphate; the calcium ion auxiliary agent is one or two of calcium nitrate and calcium oxalate; the reaction promoter is one or two of choline and choline chloride; and the solvent is water.
5. The intelligent control method according to claim 1, characterized in that, In step 1), the high-strength foamed iron-nickel alloy has a porosity of 56-75%, a density of 0.2-1.9 g / cm³, a pore size of 10-20 μm, a compressive strength of 35-50 MPa, and a particle size of 3-5 mm.
6. The intelligent control method according to claim 1, characterized in that, In step 1), the specific parameters for blending using negative pressure and ultrasound are: negative pressure -45kPa~60kPa, and ultrasound selected at 15~23 kHz.
7. The intelligent control method according to claim 1, characterized in that, In step 2), the photosensitive heat-absorbing material is selected from one or more of the following: metal nanoparticles, carbon nanotubes, graphene, malachite green, and rhodamine B.
8. The intelligent control method according to claim 1, characterized in that, In step 2), the mass ratio of photosensitive polyimide to photosensitive heat-absorbing material is 100:20-25.
9. The intelligent control method according to claim 1, characterized in that, In step 3)③, the photosensitive temperature control film is removed by spraying a mixture of ethanol and dimethyl sulfoxide with a volume ratio of 2.5-3.5:1 to remove it through solvent reaction.