Preparation method and system of spiral auxetic fiber concrete with high anti-knock performance

By optimizing the diameter ratio and wrapping angle of helical tensile fibers through deep learning and genetic algorithms, and combining the design to maximize the negative Poisson's ratio effect, the problems of low tensile strength and easy cracking of concrete are solved, realizing efficient and safe fiber concrete preparation, which is suitable for multiple applications.

CN121132900AActive Publication Date: 2025-12-16HEFEI UNIV OF TECH
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202511676855.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-17
Publication Date
2025-12-16
Estimated Expiration
2045-11-17

AI Technical Summary

Technical Problem

Existing concrete has low tensile strength, is prone to cracking, and is susceptible to bursting under impact loads. Traditional fiber incorporation methods are not ideal for strengthening concrete and are difficult to adapt to complex and personalized application needs.

Method used

Deep learning was used to predict the diameter ratio and wrapping angle of helical tensile fibers, and genetic algorithms were combined to optimize the matrix mix ratio to prepare helical tensile fiber concrete. The optimal matching scheme between the fiber and the concrete was maximized by the negative Poisson's ratio effect.

Benefits of technology

It significantly improves the anti-blast performance of concrete, enhances its toughness, effectively inhibits crack development, ensures structural safety, reduces resource waste, and is suitable for civilian, industrial, and military applications.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121132900A_ABST
    Figure CN121132900A_ABST
Patent Text Reader

Abstract

The invention provides a preparation method of spiral auxetic fiber concrete with high anti-knock performance, and belongs to the field of fiber reinforced concrete.The preparation method comprises the steps that according to fiber types and mechanical property parameters, the diameter ratio and the wrapping angle of spiral auxetic fibers are predicted based on deep learning, and the spiral auxetic fibers are prepared; the spiral auxetic fibers are embedded into concrete with different matrix strengths, negative Poisson's ratio values of the spiral auxetic fibers are measured after maintenance, and the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio value is recorded; under the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio value, generating multiple groups of mix proportions, obtaining a mechanical property predicted value based on deep learning according to the spiral auxetic fiber characteristic parameters and the mix proportions, calculating the fitness of the mechanical property predicted value and a target value, searching a matrix mix proportion based on a genetic algorithm, and verifying the matrix mix proportion; concrete is prepared according to the matrix mix proportion and the spiral auxetic fibers; the invention further provides a preparation system. The anti-explosion performance of the concrete is improved.
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fiber reinforced concrete, in particular to a spiral tensile fiber concrete preparation method and system with high blast resistance. BACKGROUND

[0002] Concrete is an artificial stone made of cement as a cementitious material, mixed with water, aggregate (sand, gravel) and admixture in proportion, and hardened after stirring, molding and curing. Concrete is widely used in construction engineering (house beam column, floor), infrastructure (bridge, road, tunnel), water conservancy engineering (dam, dike) and other fields due to its high compressive strength, good durability (service life up to 100 years), strong plasticity, economy and practicality. As a core material of modern engineering, concrete supports the structural safety and long-term service of various civil engineering with high cost performance and multi-functionality.

[0003] However, concrete also has the disadvantages of low tensile strength (only 1 / 10 of the compressive strength), internal microcrack defects and poor fracture toughness. In addition, when encountering impact load, concrete is prone to produce blast pits on the blast surface and splashes on the back blast surface, causing harm to the internal structure personnel. Incorporating fibers is an effective means to enhance the blast resistance of concrete. At present, the incorporation of fibers into concrete is mainly single fiber incorporation, and the incorporated fibers are generally steel fibers, polyvinyl alcohol fibers, polypropylene fibers and glass fibers. Single fiber incorporation can enhance the toughness of concrete, but the enhancement effect is still not ideal. In addition, the traditional fiber concrete mix design method often focuses on empirical formulas and test data, which is difficult to meet the complex and individualized application requirements. In recent years, the development of deep learning technology provides a new way to solve this problem. For example, the Chinese invention patent application with publication number CN117912594A "High-performance concrete mix design and performance prediction method based on deep learning" applies deep learning algorithm to the research and development of ultra-high performance concrete. However, this method still has the problem of not ideal enhancement effect by incorporating single fiber into concrete. SUMMARY

[0004] The technical problem to be solved by the present application is how to improve the blast resistance of concrete.

[0005] The present application solves the above technical problems by the following technical scheme: a spiral tensile fiber concrete preparation method with high blast resistance, the method comprising: According to the type and mechanical property parameters of the fibers, the diameter ratio and wrapping angle of the spiral tensile fibers are predicted based on deep learning, and the spiral tensile fibers are prepared; The spiral tensile fibers are embedded in concrete with different matrix strengths, and the negative Poisson's ratio of the spiral tensile fibers is measured after curing. The concrete matrix strength grade corresponding to the maximum negative Poisson's ratio is recorded; Under the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio value, a plurality of groups of mix proportions are generated, the mechanical property prediction value is obtained based on deep learning according to the spiral dilatation fiber characteristic parameters and the mix proportions, the fitness of the mechanical property prediction value and the target value is calculated, the matrix mix proportion is searched based on the genetic algorithm, and the matrix mix proportion is verified; The concrete is prepared according to the matrix mix proportion and the spiral dilatation fiber.

[0006] The spiral dilatation fiber negative Poisson's ratio effect maximization optimization is performed based on deep learning, the optimal diameter ratio and wrapping angle are predicted from the fiber type and mechanical property parameters, the predicted fiber has a negative Poisson's ratio, the spiral dilatation fiber of the optimal fiber type, diameter ratio and wrapping angle is designed, the maximum negative Poisson's ratio of the spiral dilatation fiber with different geometric parameters in different concrete strength grades is statistically obtained based on the principle that the spiral dilatation fiber negative Poisson's ratio effect is maximized in the concrete, the optimal matching scheme of the spiral dilatation fiber and the different strength concrete matrix is designed, a plurality of groups of mix proportions are generated under the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio value, the mechanical property is predicted based on deep learning from the spiral dilatation fiber characteristic parameters and the mix proportions, the fitness of the mechanical property prediction value and the target value is calculated, the optimal matrix mix proportion is searched, and the matrix mix proportion is verified to ensure the rationality of the predicted mix proportion. Compared with single fiber incorporation, the concrete prepared according to the matrix mix proportion and the spiral dilatation fiber has high toughness, the spiral dilatation fiber has good energy absorption characteristics, can effectively inhibit the generation and development of concrete cracks by absorbing explosion load energy, and can improve the anti-explosion performance of the concrete, and can ensure the safety of the personnel in the concrete structure under the impact load, and has a wide application prospect in civil, industrial and military fields.

[0007] Preferably, the process of predicting the diameter ratio and wrapping angle of the fiber based on deep learning from the fiber type and mechanical property parameters comprises: The multi-layer fully connected neural network is trained to obtain the deep learning model by taking the fiber type and fiber mechanical property parameters of the spiral yarn as input and taking the structure parameters of the spiral yarn as output label, wherein the fiber mechanical property parameters include Poisson's ratio, elastic modulus and breaking elongation, and the structure parameters of the spiral yarn include diameter ratio, wrapping angle and negative Poisson's ratio effect value; Two fibers with large difference in elastic modulus are selected, the fiber type and mechanical property parameters are input into the deep learning model, and the diameter ratio and wrapping angle of the spiral dilatation fiber are output.

[0008] Preferably, the process of preparing the spiral dilatation fiber comprises: Two types of fibers with different elastic modulus are selected, one type of fiber is core fiber, and the other type of fiber is wrapping fiber, and the fiber types include polypropylene fiber, polyvinyl alcohol fiber, flax fiber, glass fiber, and steel fiber; The core fiber is wound on the fiber conveying device, and the core fiber is in a straightened state, and the fiber conveying device uniformly conveys the core fiber; The wrapping fiber is fixed on the winding device, and the conveying speed of the fiber conveying device and the rotating speed of the winding device are adjusted, so that the wrapping fiber is wound on the core fiber at a predicted wrapping angle, and a spiral auxetic fiber is obtained. The prepared spiral auxetic fiber is collected by using the take-up device, and the spiral auxetic fiber is cut, and universal glue is added at both ends of the cut spiral auxetic fiber.

[0009] Preferably, the different base strength concretes have different raw material proportions in the preparation process and the same preparation method, the spiral auxetic fiber is embedded in the different base strength concretes, and the process of measuring the negative Poisson's ratio of the spiral auxetic fiber after curing includes: The spiral auxetic fiber is immersed in a 3% silane coupling agent ethanol solution for 15 min, and is dried at 60°C for standby; The coarse aggregate and fine aggregate are added to the mixer mixing container and stirred for 1 min; The cement, slag powder, fly ash and silica fume are mixed and stirred for 2 min, then poured into the mixer mixing container and stirred for another 2 min; The water and polycarboxylic acid water reducing agent are mixed and stirred for 30 s, then poured into the mixer mixing container and stirred for 3 min to obtain the target base strength concrete; The target base strength concrete is poured into the mold, and the spiral auxetic fiber with a length of 30 mm is vertically embedded in the concrete base with an embedding depth of 20 mm, and is cured for 28 days; The spiral auxetic fiber is subjected to a pull-out load, and the spiral auxetic fiber inside the concrete is scanned using in-situ CT, and the negative Poisson's ratio of the spiral auxetic fiber inside the concrete during the load action is recorded.

[0010] Preferably, the cement is PII·52.5 grade ordinary portland cement, the fine aggregate is quartz sand with a particle size of 0.15-0.6 mm, the fly ash is I grade fly ash, the SiO2 content in the silica fume is ≥90%, the chloride ion in the silica fume is ≤0.1%, the sulfide in the silica fume is ≤2%, the fineness of the silica fume satisfies the specific surface area ≥15.000 m² / kg, the water content in the silica fume is ≤3%, and the polycarboxylic acid water reducing agent satisfies: water reducing rate ≥35%, air content ≤6%, and alkali content ≤10%.

[0011] Preferably, based on the spiral auxetic fiber characteristic parameters and the mix proportion, the process of obtaining the mechanical property prediction value based on deep learning includes: The performance prediction network is trained by taking the helical auxetic fiber characteristic parameters and the mixing ratio as inputs and taking the mechanical properties of the fiber concrete as output labels, wherein the helical auxetic fiber characteristic parameters include fiber type, diameter, length, elastic modulus and Poisson's ratio, and the mixing ratio includes water-cement ratio, sand ratio, water reducing agent content and helical auxetic fiber volume content; The helical auxetic fiber characteristic parameters and the mixing ratio are input into the performance prediction network, wherein the water-cement ratio in the mixing ratio is less than or equal to 0.3, the sand ratio ranges from 30% to 40%, and the mechanical property prediction value is output, and the mechanical properties include splitting tensile strength, toughness index and strain energy.

[0012] Preferably, the fitness of the mechanical property prediction value and the target value is

[0013] , , , The target splitting tensile strength, the target toughness index and the target strain energy are respectively, , , The predicted splitting tensile strength, the predicted toughness index and the predicted strain energy are respectively, The cost coefficient is.

[0014] Preferably, the process of searching for the matrix mixing ratio based on the genetic algorithm comprises: Under the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio value, a plurality of mixing ratios are randomly generated to form an initial population, and each mixing ratio is taken as an individual; The fitness of each individual is calculated, the individuals are selected according to the fitness, the selected individuals are subjected to a crossover operation to generate new individuals, and the individuals after the crossover operation are subjected to a mutation operation to generate the next generation population, and the cycle is executed until the iteration is set number of times or the fitness change is less than 1e -5 , and the matrix mixing ratio is obtained.

[0015] Preferably, the matrix mixing ratio includes water-cement ratio , sand ratio , helical auxetic fiber volume content , helical auxetic fiber negative Poisson's ratio , and water reducing agent content The constraint condition of the matrix mixing ratio is verified as: , , , , .

[0016] ​The application also provides a spiral tensile fiber concrete preparation system with high anti-explosion performance, which comprises: A spiral tensile fiber design module is used to predict the diameter ratio and wrapping angle of the spiral tensile fiber based on deep learning according to the fiber type and mechanical property parameters, and prepare the spiral tensile fiber. A matrix strength determination module based on negative Poisson's ratio effect maximization is used to bury the spiral tensile fiber in concrete with different matrix strengths, measure the negative Poisson's ratio of the spiral tensile fiber after curing, and record the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio. A matrix mix proportion design module is used to generate multiple groups of mix proportions under the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio, obtain the mechanical property prediction value based on deep learning according to the spiral tensile fiber characteristic parameters and the mix proportions, calculate the fitness of the mechanical property prediction value and the target value, search for the matrix mix proportion based on the genetic algorithm, and verify the matrix mix proportion. A concrete preparation module is used to prepare concrete according to the matrix mix proportion and the spiral tensile fiber.

[0017] The spiral tensile fiber for concrete designed based on deep learning can meet the diversification and complication requirements of concrete, the concrete mix proportion design based on deep learning can reduce the waste of raw materials caused by concrete trial mixing, greatly improve the fiber concrete mix proportion design efficiency, reduce the resource waste caused by trial mixing, help low-carbon emission reduction, realize reasonable use of resources and sustainable development. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 A flowchart of the spiral tensile fiber concrete preparation method with high anti-explosion performance provided for the embodiment 1 of the application is provided. Figure 2 A principle diagram of the spiral tensile fiber design based on deep learning in the spiral tensile fiber concrete preparation method with high anti-explosion performance provided for the embodiment 1 of the application is provided. Figure 3 A spiral tensile fiber synthesized by polypropylene fiber (d=0.9mm) and steel fiber (d=0.3mm) with a wrapping angle of 15° in the spiral tensile fiber concrete preparation method with high anti-explosion performance provided for the embodiment 1 of the application, a photo in a natural state, and the negative Poisson's ratio can reach-3.23. Figure 4 A spiral tensile fiber synthesized by polypropylene fiber (d=0.9mm) and steel fiber (d=0.3mm) with a wrapping angle of 20° in the spiral tensile fiber concrete preparation method with high anti-explosion performance provided for the embodiment 1 of the application, a photo in a natural state, and the negative Poisson's ratio can reach-5.2. Figure 5 The spiral tensile fiber in the spiral tensile fiber concrete preparation method with high anti-blast performance provided in Embodiment 1 of the present application is a spiral tensile fiber composed of polypropylene fiber (d=1.2 mm) and steel fiber (d=0.3 mm) with a wrapping angle of 10°, and the negative Poisson's ratio can reach -3.61 in a natural state; Figure 6 The schematic diagram of the principle of constructing the double prediction model in the spiral tensile fiber concrete preparation method with high anti-blast performance provided in Embodiment 1 of the present application; Figure 7 The reverse performance prediction network code in the spiral tensile fiber concrete preparation method with high anti-blast performance provided in Embodiment 1 of the present application; Figure 8 The genetic algorithm optimization mixing proportion implementation code in the spiral tensile fiber concrete preparation method with high anti-blast performance provided in Embodiment 1 of the present application; Figure 9 The constraint verification module code in the spiral tensile fiber concrete preparation method with high anti-blast performance provided in Embodiment 1 of the present application; Figure 10 The schematic diagram of the spiral tensile fiber concrete preparation system with high anti-blast performance provided in Embodiment 2 of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical scheme and advantages of the present application clearer and more apparent, the technical scheme of the present application is described clearly and completely below in combination with specific embodiments and with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0020] Embodiment 1 As shown in Figure 1 , the present embodiment provides a spiral tensile fiber concrete preparation method with high anti-blast performance, including the following steps: Step 1, according to the fiber type and mechanical property parameters, the diameter ratio and wrapping angle of the spiral tensile fiber are predicted based on deep learning, and the spiral tensile fiber is prepared.

[0021] Referring to Figure 2 , the process of predicting the diameter ratio and wrapping angle of the fiber based on deep learning according to the fiber type and mechanical property parameters includes: Step 1.1.1, collect the existing negative Poisson's ratio helical yarn related parameters and the basic mechanical properties of common fibers incorporated into concrete, including polyvinyl alcohol fiber (PVA), polypropylene fiber (PP), flax fiber, glass fiber, and steel fiber. The basic mechanical properties of the fibers include Poisson's ratio, Young's modulus, and elongation at break. The existing negative Poisson's ratio helical yarn structure parameters include inner / outer diameter ratio, wrap angle, and negative Poisson's ratio effect value (label and numerical value judgment).

[0022] The fiber type and fiber mechanical property parameters of the helical yarn are input, and the structure parameters of the helical yarn are output as labels to train a multi-layer fully connected neural network (MLP Regression). The multi-layer fully connected neural network includes linear layers, ReLU activation functions, linear layers, ReLU activation functions, and linear layers connected in turn. When the loss function is minimized, the deep learning model is obtained, where the fiber mechanical property parameters include Poisson's ratio, Young's modulus, and elongation at break, and the structure parameters of the helical yarn include diameter ratio, wrap angle, and negative Poisson's ratio effect value. The loss function uses mean squared error for regression of diameter ratio and wrap angle, and a classification loss can be added if it is necessary to distinguish whether it is a negative Poisson's ratio, where the mean squared error is calculated as follows:

[0023] where is the true value of the th sample, is the predicted value of the th sample, is the total number of samples.

[0024] Step 1.1.2, select two fibers with different elastic moduli, input the fiber type and mechanical property parameters into the deep learning model, and output the diameter ratio and wrap angle of the helical auxetic fiber.

[0025] The present application is based on deep learning to design spiral tensile fibers suitable for concrete. By constructing a deep learning model, five types of fibers are subjected to Embedding or One-Hot, combined with the Poisson's ratio, elastic modulus, elongation at break and target negative Poisson's ratio range of each type of fiber, the input features are constructed, and the diameter ratio and wrapping angle are taken as output labels. The diameter ratio is a non-continuous value, and the specific value is 2, 3, 4. The wrapping angle is also a non-continuous value, and the range is 10°, 15°, 20°, 25°. Based on the existing negative Poisson's ratio spiral yarn related parameters and the basic mechanical performance parameters of the commonly used fibers mixed into concrete, the deep learning model is trained to obtain the trained deep learning model, which is used to predict the optimal diameter ratio and wrapping angle according to the fiber type and its performance parameters, so that the predicted yarn has a negative Poisson's ratio. The spiral tensile fiber with negative Poisson's ratio effect is a spiral structure composed of two kinds of fiber filaments with large difference in elastic modulus, for example, the two kinds of fiber filaments are polypropylene fiber and steel fiber.

[0026] In order to verify the rationality of the spiral tensile fiber suitable for concrete designed based on deep learning, the present application compares the prediction results with the test results: Select two types of fibers, polypropylene fiber and steel fiber, and obtain the mechanical performance parameters of polypropylene fiber and steel fiber, including Poisson's ratio, elastic modulus and elongation at break. The fiber type and mechanical performance parameters are input into the trained deep learning model, and the diameter ratio and wrapping angle of the spiral tensile fiber are output, and the maximum negative Poisson's ratio value is predicted. Referring to Table 1, the predicted value of the maximum negative Poisson's ratio corresponding to the diameter ratio 1:3 and wrapping angle 15° of polypropylene fiber and steel fiber is-2.59. According to the diameter ratio 1:3 and wrapping angle 15°, polypropylene fiber is used as core fiber, and steel fiber is used as wrapping fiber to prepare spiral tensile fiber, Figure 3 The actual preparation effect diagram of the spiral tensile fiber is shown in the figure. The measured maximum negative Poisson's ratio of the prepared spiral tensile fiber is-2.68. The predicted value of the maximum negative Poisson's ratio corresponding to the diameter ratio 1:3 and wrapping angle 20° of polypropylene fiber and steel fiber is-3.10. According to the diameter ratio 1:3 and wrapping angle 20°, polypropylene fiber is used as core fiber, and steel fiber is used as wrapping fiber to prepare spiral tensile fiber, Figure 4 The actual preparation effect diagram of the spiral tensile fiber is shown in the figure. The measured maximum negative Poisson's ratio of the prepared spiral tensile fiber is-3.08. The predicted value of the maximum negative Poisson's ratio corresponding to the diameter ratio 1:3 and wrapping angle 20° of polypropylene fiber and steel fiber is-3.10. According to the diameter ratio 1:3 and wrapping angle 20°, polypropylene fiber is used as core fiber, and steel fiber is used as wrapping fiber to prepare spiral tensile fiber, Figure 5The actual preparation effect diagram of the spiral auxetic fiber is shown in FIG. 6. The maximum negative Poisson's ratio of the prepared spiral auxetic fiber is -1.99. It can be seen that the prediction result is in good coincidence with the test, and therefore, the deep learning model can well design the spiral auxetic fiber suitable for concrete.

[0027] Table 1 Comparison of prediction results and test results of spiral auxetic fiber suitable for concrete based on deep learning

[0028] The process of preparing the spiral auxetic fiber includes: Step 1.2.1, selecting two types of fibers with large difference in elastic modulus, one type of fiber as core fiber and the other type of fiber as wrapping fiber, and the fiber types include polypropylene fiber, polyvinyl alcohol fiber, flax fiber, glass fiber and steel fiber; Step 1.2.2, winding the core fiber on the fiber conveying device so that the core fiber is in a straightened state, and the fiber conveying device uniformly conveys the core fiber; Step 1.2.3, fixing the wrapping fiber on the winding device, and adjusting the conveying speed of the fiber conveying device and the rotation speed of the winding device so that the wrapping fiber is wound on the core fiber at the predicted wrapping angle to obtain the spiral auxetic fiber; Step 1.2.4, collecting the prepared spiral auxetic fiber using the take-up device, cutting the spiral auxetic fiber, and dropping universal glue at both ends of the cut spiral auxetic fiber.

[0029] Step 2, embedding the spiral auxetic fiber in concrete with different matrix strengths, measuring the negative Poisson's ratio of the spiral auxetic fiber after curing, and recording the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio.

[0030] In the process of preparing the concrete with different matrix strengths, the proportions of raw materials are different, and the preparation methods are the same. The raw materials include cement, coarse aggregate, fine aggregate, cement, slag powder, fly ash, silica fume, water and polycarboxylic acid water reducing agent. The cement is PII·52.5 grade ordinary portland cement, the fine aggregate is quartz sand with a particle size of 0.15-0.6 mm, the fly ash is I grade fly ash, the silica fume contains SiO2≥90%, the chloride ion in the silica fume is ≤0.1%, the sulfide in the silica fume is ≤2%, the fineness of the silica fume satisfies the specific surface area≥15.000 m² / kg, the water content in the silica fume is ≤3%, the polycarboxylic acid water reducing agent satisfies: water reducing rate≥35%, air content≤6%, and alkali content≤10%. The water is tap water or drinking water, which meets the requirements of “Standard for Water Used in Concrete” (JGJ63-2006).

[0031] The process of embedding the spiral auxetic fiber in concrete with different matrix strengths and measuring the negative Poisson's ratio of the spiral auxetic fiber after curing includes: Step 2.1, immerse the helical auxetic fiber in a 3% silane coupling agent ethanol solution for 15 min, and dry at 60 DEG C for standby; Step 2.2, add coarse aggregate and fine aggregate into the mixer mixing container and stir for 1 min; Step 2.3, mix and stir the cement, slag powder, fly ash and silica fume for 2 min, then pour into the mixer mixing container and stir for another 2 min; Step 2.4, mix and stir the water and polycarboxylic acid water reducing agent for 30 s, then pour into the mixer mixing container and stir for 3 min to obtain the target matrix strength concrete; Step 2.5, pour the target matrix strength concrete into the mold, and vertically bury the helical auxetic fiber with a length of 30 mm in the concrete matrix, with a burial depth of 20 mm, and cure for 28 days; Step 2.6, apply a pull-out load to the helical auxetic fiber, use in-situ CT to scan the helical auxetic fiber inside the concrete, and record the negative Poisson's ratio value of the helical auxetic fiber inside the concrete during the load action.

[0032] The present application applies a load to the prepared helical auxetic fiber concrete specimen, uses in-situ CT to scan the internal fiber, counts the change of the fiber Poisson's ratio during the load application, and based on the maximum principle of the negative Poisson's ratio effect of the fiber, counts the concrete of different matrix strength corresponding to the optimal fiber geometric parameters.

[0033] Step 3, under the matrix strength grade corresponding to the maximum value of the negative Poisson's ratio, generate multiple groups of mix proportions, according to the helical auxetic fiber characteristic parameters and mix proportions, based on deep learning to obtain the mechanical performance prediction value, calculate the fitness of the mechanical performance prediction value and the target value, search for the matrix mix proportion based on the genetic algorithm, and verify the matrix mix proportion.

[0034] The process of obtaining the mechanical performance prediction value based on deep learning according to the helical auxetic fiber characteristic parameters and mix proportions comprises: Step 3.1.1, based on literature research and test data, obtain 300 groups of original data of fiber concrete parameters and performance, the data should include fiber characteristics: fiber type, diameter and length (mm), elastic modulus (MPa) and Poisson's ratio, mix proportion parameters: water-binder ratio, sand ratio, water reducing agent dosage, fiber volume fraction, in order to quantify the toughening effect of helical auxetic fiber on concrete, set the helical auxetic fiber group and the control group of steel fiber for comparison, except that the fiber type is different, the rest of the variables are the same, and the fiber concrete toughening effect index is: splitting tensile strength (MPa), toughness index, strain energy (N·m). Clean the original data, normalize the data set, scale all numerical features to [0, 1], convert the fiber type to One-hot vector, and apply ±5% random disturbance to the sample to realize data enhancement.

[0035] A dual prediction network model is constructed, see Figure 6 , which includes a performance prediction network and a mix ratio generation network. The performance prediction network is a forward network, including a bidirectional LSTM network and a full connection layer connected in sequence, for predicting mechanical properties according to input fiber characteristics and mix ratio. The mix ratio generation network is a reverse network, including a convolutional layer and a full connection layer connected in sequence, for outputting fiber parameters and matrix mix ratio according to input target mechanical properties, including split tensile strength, toughness index, and strain energy. The loss function of the reverse network is: fitness = performance prediction error (sum of split tensile strength, toughness index, and strain energy error) + fiber cost penalty term (to control economy). The reverse network code is shown in Figure 7 .

[0036] The bidirectional LSTM network is trained with spiral tensile fiber characteristic parameters and mix ratio as input and mechanical properties of fiber concrete as output label. When the loss function is minimized, the performance prediction network is obtained, wherein the spiral tensile fiber characteristic parameters include fiber type, diameter, length, elastic modulus, and Poisson's ratio, and the mix ratio includes water-cement ratio, sand ratio, water reducing agent dosage, and spiral tensile fiber volume fraction; the loss function is the weighted average of split tensile strength, toughness index, and strain energy loss, and the calculation method is: + +

[0037] wherein , , are the real values of split tensile strength, toughness index, and strain energy of the i-th sample, , , , are the predicted values of split tensile strength, toughness index, and strain energy of the i-th sample. Step 3.1.2, input the spiral tensile fiber characteristic parameters and mix ratio into the performance prediction network, wherein the water-cement ratio in the mix ratio is less than or equal to 0.3, the sand ratio ranges from 30% to 40%, and output the mechanical property prediction value, including split tensile strength, toughness index, and strain energy.

[0038] The fitness of the mechanical property prediction value and the target value is:

[0039]

[0040] wherein,​​ , , respectively are the target tensile splitting strength, target toughness index, target strain energy, i.e. the target values of each mechanical property, , , respectively are the predicted tensile splitting strength, predicted toughness index, predicted strain energy, i.e. the predicted values of each mechanical property, is the cost coefficient.

[0041] The process of searching for the matrix mix proportion based on the genetic algorithm includes: Step 3.2.1, randomly generate multiple groups of mix proportions under the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio value, 100 groups of mix proportions are randomly generated in this embodiment (satisfying the constraints: water-cement ratio ≤ 0.3, sand ratio 30-40%), constituting the initial population, each group of mix proportions as an individual; Step 3.2.2, calculate the fitness of each individual, select the individual according to the fitness, perform crossover operation on the selected individual, two-point crossover, probability 0.8, generate new individuals, perform mutation operation on the individual after the crossover operation, add Gaussian disturbance, probability 0.2, standard deviation 0.05, produce the next generation population, loop execution until it meets 50 generations (also can be set to 100 generations according to the need) or the fitness changes less than 1e -5 , get the matrix mix proportion. The code for optimizing the mix proportion by genetic algorithm is shown in Figure 8 .

[0042] Based on the provisions of “Technical Specification for Application of Fiber Reinforced Concrete” (JGJ / T221-2010) and “Mix Proportion Design Specification for Ordinary Concrete” (JGJ55-2019), as well as the basic requirements of concrete mix proportion and the research results of related literature. In order to avoid extreme unreasonable results, ensure that the water-cement ratio, sand ratio, spiral tensile fiber volume fraction, and water reducing agent dosage must be within the reasonable range determined by the specification or experiment, and ensure that the spiral tensile fiber can play the maximum negative Poisson's ratio effect inside the concrete matrix, the range of factors is shown in Table 2.

[0043] Table 2 Constraint conditions for multi-objective optimization design of spiral tensile fiber reinforced concrete

[0044] As can be seen from Table 2, the matrix mix proportion includes water-cement ratio , sand ratio , spiral tensile fiber volume fraction , spiral tensile fiber negative Poisson's ratio , and water reducing agent dosage , the constraint conditions for verifying the matrix mix proportion are: , , , , The constraint verification module implementation code is as shown in the accompanying Figure 9 .

[0045] Verification and application effect: through the test set verification, the performance prediction network R 2 reaches 0.92 (split tensile strength), 0.89 (toughness index), 0.95 (strain energy). The input spiral dilatancy fiber mechanical performance parameters and the mechanical performance in different strength matrices are based on the principle of maximizing the negative Poisson's ratio effect of the spiral dilatancy fiber, and the optimal solution set is obtained. This optimal solution balances multiple performance goals and is considered to be the solution closest to the ideal solution among all considered factors.

[0046] Table 3 shows the optimal solution set given by the deep learning model, all of which successfully meet the performance requirements and are considered to have the best matching performance of the geometric parameters of the spiral dilatancy fiber and the concrete matrix, and can maximize the fiber toughening effect.

[0047] Table 3 Optimal solution set given by the deep learning model

[0048] Step 4, preparing concrete according to the matrix mix proportion and spiral dilatancy fiber.

[0049] The present application optimizes the spiral dilatancy fiber negative Poisson's ratio effect based on deep learning, predicts the optimal diameter ratio and wrapping angle from the fiber type and mechanical performance parameters, so that the predicted fiber has a negative Poisson's ratio, designs the best spiral dilatancy fiber type, diameter ratio and wrapping angle, and based on the principle of maximizing the negative Poisson's ratio effect of the spiral dilatancy fiber in the concrete, the maximum negative Poisson's ratio of the spiral dilatancy fiber with different geometric parameters in different concrete strength grades is calculated, the best matching scheme of the spiral dilatancy fiber and the different strength concrete matrix is designed, and multiple groups of mix proportions are generated at the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio, the mechanical performance is predicted from the spiral dilatancy fiber characteristics parameters and the mix proportion based on deep learning, the fitness of the mechanical performance prediction value and the target value is calculated, the best matrix mix proportion is searched, and the rationality of the predicted mix proportion is ensured through the verification of the matrix mix proportion.

[0050] Compared with single fiber incorporation, the concrete prepared according to the matrix mix proportion and the spiral dilatancy fiber has high toughness, the spiral dilatancy fiber has good energy absorption characteristics, and can effectively inhibit the generation and development of concrete cracks by absorbing explosion load energy, thereby improving the anti-explosion performance of concrete and ensuring the safety of personnel inside the concrete structure under impact load, which has a wide application prospect in civil, industrial and military fields.

[0051] To show that the spiral dilatancy fiber has a significant toughening effect on concrete, and based on the effectiveness of the optimal mix proportion solution set of spiral dilatancy fiber concrete obtained by deep learning, the spiral dilatancy fiber concrete of the above scheme is prepared according to the Technical Application Regulation of Fiber Concrete (JGJ / T 221-2010), and the splitting tensile strength, toughness index and strain energy of the spiral dilatancy fiber concrete of each scheme are measured. In addition, the spiral dilatancy fiber of the above scheme is replaced by steel fiber with the same length-diameter ratio and the same volume fraction, and the steel fiber control group is prepared according to the Technical Application Regulation of Fiber Concrete (JGJ / T 221-2010), and the splitting tensile strength, toughness index and strain energy of each control group are measured. The splitting tensile strength, toughness index and strain energy of the spiral dilatancy fiber concrete prepared in each scheme, and the splitting tensile strength, toughness index and strain energy of the control group are shown in Table 4.

[0052] Table 4 Mechanical property test results of each group

[0053] As shown in Table 4, No. 1 group, compared with the control group of steel fiber, the same mix proportion of spiral dilatancy fiber makes the splitting tensile strength, toughness index and strain energy of the concrete increase by 28.4%, 24.2% and 27.0% respectively; No. 2 group, compared with the control group of steel fiber, the same mix proportion of spiral dilatancy fiber makes the splitting tensile strength, toughness index and strain energy of the concrete increase by 28.7%, 25.7% and 23.0% respectively; No. 3 group, compared with the control group of steel fiber, the same mix proportion of spiral dilatancy fiber makes the splitting tensile strength, toughness index and strain energy of the concrete increase by 19.5%, 38.2% and 21.3% respectively, and in addition, compared with the orthogonal experiment method, the time cost is reduced by 90%, and the fiber utilization rate is increased by 15-30%.

[0054] In summary, based on the principle of maximizing the negative Poisson's ratio effect of spiral dilatancy fiber in concrete and the spiral dilatancy fiber concrete prepared by deep learning design, the spiral dilatancy fiber concrete has high toughness, which can greatly improve the impact load performance of concrete. Compared with the existing single fiber mixed into concrete, the present application can enhance the toughening effect of the fiber by changing the geometric structure of the two fibers mixed into the concrete. The present application combines deep learning method with spiral dilatancy fiber concrete material design, greatly improves the efficiency of fiber concrete mix proportion design, reduces the resource waste caused by trial preparation, helps low-carbon emission reduction, and realizes the rational use of resources. Compared with the traditional method, the preparation method of the high blast-resistant performance concrete of the present application not only has higher precision and higher efficiency, but also has stronger generalization ability.

[0055] Example 2 Reference Figure 10The embodiment provides a spiral tensile fiber concrete preparation system with high anti-blast performance, and comprises the following modules: A spiral tensile fiber design module is used for predicting the diameter ratio and wrapping angle of the spiral tensile fiber based on deep learning according to the fiber type and mechanical property parameters, and preparing the spiral tensile fiber.

[0056] The process of predicting the diameter ratio and wrapping angle of the fiber based on deep learning according to the fiber type and mechanical property parameters comprises the following steps: A multi-layer fully connected neural network is trained by taking the fiber type and fiber mechanical property parameters of the spiral yarn as input and the structural parameters of the spiral yarn as output labels, to obtain a deep learning model, wherein the fiber mechanical property parameters comprise Poisson's ratio, elastic modulus and breaking elongation, and the structural parameters of the spiral yarn comprise the diameter ratio, the wrapping angle and the negative Poisson's ratio effect value; Two fibers with large difference in elastic modulus are selected, and the fiber type and mechanical property parameters are input into the deep learning model to output the diameter ratio and wrapping angle of the spiral tensile fiber.

[0057] The process of preparing the spiral tensile fiber comprises the following steps: Two fibers with large difference in elastic modulus are selected, one type of fiber is a core fiber, and the other type of fiber is a wrapping fiber, and the fiber type comprises polypropylene fiber, polyvinyl alcohol fiber, flax fiber, glass fiber and steel fiber; The core fiber is wound on a fiber conveying device so that the core fiber is in a straightened state, and the fiber conveying device uniformly conveys the core fiber; The wrapping fiber is fixed on a winding device, the fiber conveying speed of the fiber conveying device is adjusted to be the same as the rotation speed of the winding device, so that the wrapping fiber is wound on the core fiber at the predicted wrapping angle, and the spiral tensile fiber is obtained; The prepared spiral tensile fiber is collected by using a take-up device, the spiral tensile fiber is cut, and universal glue is added at both ends of the cut spiral tensile fiber.

[0058] A matrix strength determination module based on maximum negative Poisson's ratio effect is used for embedding the spiral tensile fiber in concrete with different matrix strengths, measuring the negative Poisson's ratio of the spiral tensile fiber after curing, and recording the matrix strength grade corresponding to the maximum negative Poisson's ratio value.

[0059] The concrete with different matrix strengths has different proportions of raw materials in the preparation process and the same preparation method, the spiral tensile fiber is embedded in the concrete with different matrix strengths, and the process of measuring the negative Poisson's ratio of the spiral tensile fiber after curing comprises the following steps: The spiral tensile fiber is immersed in a 3% silane coupling agent ethanol solution for 15 min, and is dried at 60 DEG C for standby; The coarse aggregate and fine aggregate are added to the mixer mixing container and stirred for 1 min; The cement, slag powder, fly ash and silica fume are mixed and stirred for 2 minutes, then poured into the mixer mixing container and stirred for 2 minutes again; The water and polycarboxylic acid water reducing agent are mixed and stirred for 30 seconds, then poured into the mixer mixing container, stirred for 3 minutes, and the target matrix strength concrete is obtained; The target matrix strength concrete is poured into the mold, and the spiral dilatational fiber with a length of 30 mm is vertically embedded in the concrete matrix with an embedding depth of 20 mm, and cured for 28 days; The spiral dilatational fiber is subjected to a pull-out load, and the spiral dilatational fiber inside the concrete is scanned in situ using CT, and the negative Poisson's ratio value of the spiral dilatational fiber inside the concrete during the load action is recorded.

[0060] The cement is PII·52.5 grade ordinary portland cement, the fine aggregate is quartz sand with a particle size of 0.15-0.6 mm, the fly ash is I grade fly ash, the SiO2 content in the silica fume is ≥90%, the chloride ion in the silica fume is ≤0.1%, the sulfide in the silica fume is ≤2%, the fineness of the silica fume meets the specific surface area ≥15.000 m² / kg, the water content in the silica fume is ≤3%, the polycarboxylic acid water reducing agent meets: water reducing rate ≥35%, air content ≤6%, alkali content ≤10%.

[0061] The matrix mix proportion design module is used to generate multiple groups of mix proportions under the concrete matrix strength grade corresponding to the maximum value of the negative Poisson's ratio, calculate the fitness of the mechanical property prediction value and the target value based on the spiral dilatational fiber characteristic parameters and the mix proportions, search for the matrix mix proportion based on the genetic algorithm, and verify the matrix mix proportion.

[0062] The process of obtaining the mechanical property prediction value based on deep learning according to the spiral dilatational fiber characteristic parameters and the mix proportions includes: The bidirectional LSTM network is trained with the spiral dilatational fiber characteristic parameters and the mix proportions as input and the mechanical properties of the fiber concrete as output label to obtain the performance prediction network, wherein the spiral dilatational fiber characteristic parameters include fiber type, diameter, length, elastic modulus and Poisson's ratio, and the mix proportions include water-cement ratio, sand ratio, water reducing agent dosage and spiral dilatational fiber volume dosage; The spiral dilatational fiber characteristic parameters and the mix proportions are input into the performance prediction network, wherein the water-cement ratio in the mix proportion is less than or equal to 0.3, and the sand ratio ranges from 30% to 40%, and the mechanical property prediction value is output, and the mechanical properties include splitting tensile strength, toughness index and strain energy.

[0063] The fitness of the mechanical property prediction value and the target value is:

[0064] wherein,​ , , respectively as the target splitting tensile strength, the target toughness index, the target strain energy, , , respectively as the predicted splitting tensile strength, the predicted toughness index, the predicted strain energy, is a cost coefficient.

[0065] The process of searching for the matrix mixing ratio based on the genetic algorithm includes: Under the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio value, a plurality of mixing ratios are randomly generated to form an initial population, and each mixing ratio is taken as an individual; Calculate the fitness of each individual, select the individual according to the fitness, perform a crossover operation on the selected individual to generate a new individual, and perform a mutation operation on the individual after the crossover operation to generate the next generation population, and the cycle is executed until the iteration is set number or the fitness change is less than 1e -5 , the matrix mixing ratio is obtained.

[0066] The matrix mixing ratio includes the water-cement ratio , the sand ratio , the volume fraction of the spiral dilatational fiber , the negative Poisson's ratio of the spiral dilatational fiber , and the water reducing agent content , and the constraint condition of the matrix mixing ratio is verified as: , , , , .

[0067] The concrete preparation module is used to prepare concrete according to the matrix mixing ratio and the spiral dilatational fiber.

[0068] In order to ensure the normal operation of the model and sufficient data storage space, the software and hardware configuration used by the present application is as follows: Windows 11 operating system equipped with Python 3.7.2 and Matlab R2021b, which can provide powerful programming and scientific calculation support; internally equipped with AMD Ryzen 7 5800H with Radeon Graphics processor, matched with NVIDIA GeForce RTX 3050-6G graphics processor, to ensure the calculation ability and graphics processing ability; in addition, equipped with 16GB of memory and 520GB of solid state disk, to ensure the multitasking processing ability and efficient data access.

[0069] The maximum negative Poisson's ratio test results of the spiral dilatational fiber in different strength concrete matrix in Example 1 are introduced as follows through a plurality of comparative examples: Comparative Example 1 The preparation process of the helical auxetic fiber with negative Poisson's ratio effect is as follows: 1. The core fiber polypropylene fiber (diameter 0.9 mm) is wound on the fiber conveying device, ensuring that the core fiber is in a straightened state, and ensuring that the fiber conveying device can uniformly convey the polypropylene fiber; 2. The steel fiber (diameter 0.3 mm) is fixed on the winding device (i.e. hollow spindle), and the fiber conveying device conveying speed and the hollow spindle rotating speed are adjusted, so that the steel fiber is wound on the polypropylene fiber at a wrapping angle of 15°; 3. The prepared helical auxetic fiber is collected using the take-up device, and then the fiber is cut into 30 mm long, and universal glue is added at both ends of the cut fiber to ensure the stability of the fiber.

[0070] The method for measuring the Poisson's ratio of the helical auxetic fiber in different matrix strength concrete is as follows: (1) Surface modification: immerse the helical auxetic fiber in a 3% silane coupling agent (KH-550) ethanol solution for 15 min, and dry at 60°C before use.

[0071] (2) Add 1100 parts of coarse aggregate and 700 parts of fine aggregate to the mixer mixing container and stir for 1 min.

[0072] (3) Mix 300 parts of cement, 120 parts of slag powder, 50 parts of fly ash and 30 parts of silica fume for 2 min, then pour into the above aggregate mixture and stir for another 2 min.

[0073] (4) Mix 150 parts of water and 7.5 parts of polycarboxylic acid water reducer for 30 s, then pour into the mixer mixing container and stir for 3 min.

[0074] (5) Pour the concrete into the mold, and vertically bury the helical auxetic fiber with a length of 30 mm in the concrete matrix, with a burial depth of 20 mm, then cure for 28 d according to the national standard requirements, and the concrete matrix strength grade is C60.

[0075] (6) Apply the pull-out load to the helical auxetic fiber, use in-situ CT to scan the helical auxetic fiber inside the concrete, and record the Poisson's ratio of the helical auxetic fiber inside the concrete during the load action.

[0076] Comparative Example 2 The preparation process of the helical auxetic fiber with negative Poisson's ratio effect is as follows: 1. The core fiber polypropylene fiber (diameter 0.9 mm) is wound on the fiber conveying device, ensuring that the core fiber is in a straightened state, and ensuring that the fiber conveying device can uniformly convey the polypropylene fiber; 2. The steel fiber (diameter 0.3 mm) is fixed on the winding device (i.e. hollow spindle), and the fiber conveying device conveying speed and the hollow spindle rotating speed are adjusted, so that the steel fiber is wound on the polypropylene fiber at a wrapping angle of 15°; 3. The prepared helical auxetic fiber is collected using the take-up device, and then the fiber is cut to a length of 30 mm, and universal glue is added at both ends of the cut fiber to ensure the stability of the fiber.

[0077] The method for measuring the Poisson's ratio of the helical auxetic fiber in the different matrix strength concrete is as follows: (1) Surface modification: immerse the helical auxetic fiber in a 3% silane coupling agent (KH-550) ethanol solution for 15 min, and dry at 60°C for standby.

[0078] (2) Add 1100 parts of coarse aggregate and 650 parts of fine aggregate to the mixer mixing container and stir for 1 min.

[0079] (3) Mix 300 parts of cement, 150 parts of slag powder, 30 parts of fly ash and 50 parts of silica fume for 2 min, then pour into the above aggregate mixture and stir for another 2 min.

[0080] (4) Mix 140 parts of water and 14 parts of polycarboxylic acid water reducer for 30 s, then pour into the mixer mixing container and stir for 3 min.

[0081] (5) Pour the concrete into the mold, and vertically bury the helical auxetic fiber with a length of 30 mm in the concrete matrix, with a burial depth of 20 mm, and then cure for 28 d according to the national standard requirements, and the concrete matrix strength grade is C80.

[0082] (6) Apply the pull-out load to the helical auxetic fiber, use in-situ CT to scan the helical auxetic fiber inside the concrete, and record the Poisson's ratio of the helical auxetic fiber inside the concrete during the load action.

[0083] Comparative Example 3 The preparation process of the helical auxetic fiber with negative Poisson's ratio effect is as follows: 1. The core fiber polypropylene fiber (diameter 0.9 mm) is wound on the fiber conveying device, ensuring that the core fiber is in a straightened state, and ensuring that the fiber conveying device can uniformly convey the polypropylene fiber; 2. The steel fiber (diameter 0.3 mm) is fixed on the winding device (i.e. hollow spindle), and the fiber conveying device conveying speed and the hollow spindle rotating speed are adjusted, so that the steel fiber is wound on the polypropylene fiber at a wrapping angle of 15°; 3. The prepared helical auxetic fiber is collected using the take-up device, and then the fiber is cut to a length of 30 mm, and universal glue is added at both ends of the cut fiber to ensure the stability of the fiber.

[0084] The method for measuring the Poisson's ratio of the helical auxetic fiber in the different matrix strength concrete is as follows: (1) Surface modification: immerse the helical auxetic fiber in a 3% silane coupling agent (KH-550) ethanol solution for 15 min, and dry at 60°C for standby.

[0085] (2) Add 1050 parts of coarse aggregate and 650 parts of fine aggregate to the mixer mixing container and stir for 1 min.

[0086] (3) Mix and stir 280 parts of cement, 220 parts of slag powder, 60 parts of fly ash and 80 parts of silica fume for 2 min, then pour into the above aggregate mixture and stir for another 2 min.

[0087] (4) Mix and stir 140 parts of water and 20 parts of polycarboxylic acid water reducer for 30 s, then pour into the mixer mixing container and stir for 3 min.

[0088] (5) Pour the concrete into the mold, and vertically embed the helical auxetic fiber with a length of 30 mm into the concrete matrix, with an embedding depth of 20 mm, and then cure for 28 d according to the national standard requirements, and the concrete matrix strength grade is C100.

[0089] (6) Apply the pull-out load to the helical auxetic fiber, use in-situ CT to scan the helical auxetic fiber inside the concrete, and record the Poisson's ratio of the helical auxetic fiber inside the concrete during the load action.

[0090] Comparative Example 4 The preparation process of the helical auxetic fiber with negative Poisson's ratio effect is as follows: 1. The core fiber polypropylene fiber (diameter 0.9 mm) is wound on the fiber conveying device, ensuring that the core fiber is in a straightened state, and ensuring that the fiber conveying device can uniformly convey the polypropylene fiber; 2. The steel fiber (diameter 0.3 mm) is fixed on the winding device (i.e. hollow spindle), and the fiber conveying device conveying speed and the hollow spindle rotating speed are adjusted, so that the steel fiber is wound on the polypropylene fiber at a wrapping angle of 20°; 3. The prepared helical auxetic fiber is collected using the take-up device, and then the fiber is cut to a length of 30 mm, and universal glue is added at both ends of the cut fiber to ensure the stability of the fiber.

[0091] The method for measuring the Poisson's ratio of the helical auxetic fiber in the different matrix strength concrete is as follows: (1) Surface modification: immerse the helical auxetic fiber in a 3% silane coupling agent (KH-550) ethanol solution for 15 min, and dry at 60°C for standby.

[0092] (2) Add 1100 parts of coarse aggregate and 700 parts of fine aggregate to the mixer mixing container and stir for 1 min.

[0093] (3) Mix and stir 300 parts of cement, 120 parts of slag powder, 50 parts of fly ash and 30 parts of silica fume for 2 min, then pour into the above aggregate mixture and stir for another 2 min.

[0094] (4) Mix and stir 150 parts of water and 7.5 parts of polycarboxylic acid water reducer for 30 s, then pour into the mixer mixing container and stir for 3 min.

[0095] (5) Pour the concrete into the mold, and vertically embed the helical auxetic fiber with a length of 30 mm into the concrete matrix, with an embedding depth of 20 mm, and then cure for 28 d according to the national standard requirements, and the concrete matrix strength grade is C60.

[0096] (6) Apply the pull-out load to the helical auxetic fiber, use in-situ CT to scan the helical auxetic fiber inside the concrete, and record the Poisson's ratio of the helical auxetic fiber inside the concrete during the load action.

[0097] Comparative Example 5 The preparation process of the helical auxetic fiber with negative Poisson's ratio effect is as follows: 1. The core fiber polypropylene fiber (diameter 0.9 mm) is wound on the fiber conveying device, ensuring that the core fiber is in a straightened state, and ensuring that the fiber conveying device can uniformly convey the polypropylene fiber; 2. The steel fiber (diameter 0.3 mm) is fixed on the winding device (i.e. hollow spindle), and the fiber conveying device conveying speed and the hollow spindle rotating speed are adjusted, so that the steel fiber is wound on the polypropylene fiber at a wrapping angle of 20°; 3. The prepared helical auxetic fiber is collected using the take-up device, and then the fiber is cut to a length of 30 mm, and universal glue is added at both ends of the cut fiber to ensure the stability of the fiber.

[0098] The method for measuring the Poisson's ratio of the helical auxetic fiber in the different matrix strength concrete is as follows: (1) Surface modification: immerse the helical auxetic fiber in a 3% silane coupling agent (KH-550) ethanol solution for 15 min, and dry at 60°C for standby.

[0099] (2) Add 1100 parts of coarse aggregate and 650 parts of fine aggregate to the mixer mixing container and stir for 1 min.

[0100] (3) Mix 300 parts of cement, 150 parts of slag powder, 30 parts of fly ash and 50 parts of silica fume for 2 min, then pour into the above aggregate mixture and stir for another 2 min.

[0101] (4) Mix 140 parts of water and 14 parts of polycarboxylic acid water reducing agent for 30 s, then pour into the mixer mixing container and stir for 3 min.

[0102] (5) Pour the concrete into the mold, and vertically bury the helical auxetic fiber with a length of 30 mm in the concrete matrix, with a burial depth of 20 mm, and then cure for 28 d according to the national standard requirements, and the concrete matrix strength grade is C80.

[0103] (6) Apply the pull-out load to the helical auxetic fiber, use in-situ CT to scan the helical auxetic fiber inside the concrete, and record the Poisson's ratio of the helical auxetic fiber inside the concrete during the load action.

[0104] Comparative Example 6 The preparation process of the helical auxetic fiber with negative Poisson's ratio effect is as follows: 1. The core fiber polypropylene fiber (diameter 0.9 mm) is wound on the fiber conveying device, ensuring that the core fiber is in a straightened state, and ensuring that the fiber conveying device can uniformly convey the polypropylene fiber; 2. The steel fiber (diameter 0.3 mm) is fixed on the winding device (i.e. hollow spindle), and the fiber conveying device conveying speed and the hollow spindle rotating speed are adjusted, so that the steel fiber is wound on the polypropylene fiber at a wrapping angle of 20°; 3. The prepared helical auxetic fiber is collected using the take-up device, and then the fiber is cut to a length of 30 mm, and universal glue is added at both ends of the cut fiber to ensure the stability of the fiber.

[0105] The method for measuring the Poisson's ratio of the helical auxetic fiber in the different matrix strength concrete is as follows: (1) Surface modification: immerse the helical auxetic fiber in a 3% silane coupling agent (KH-550) ethanol solution for 15 min, and dry at 60°C for standby.

[0106] (2) Add 1050 parts of coarse aggregate and 650 parts of fine aggregate to the mixer mixing container and stir for 1 min.

[0107] (3) Mix and stir 280 parts of cement, 220 parts of slag powder, 60 parts of fly ash and 80 parts of silica fume for 2 min, then pour into the above aggregate mixture and stir for another 2 min.

[0108] (4) Mix and stir 140 parts of water and 20 parts of polycarboxylic acid water reducer for 30 s, then pour into the mixer mixing container and stir for 3 min.

[0109] (5) Pour the concrete into the mold, and vertically bury the helical auxetic fiber with a length of 30 mm in the concrete matrix, with a burial depth of 20 mm, and then cure for 28 d according to the national standard requirements, and the concrete matrix strength grade is C100.

[0110] (6) Apply the pull-out load to the helical auxetic fiber, use in-situ CT to scan the helical auxetic fiber inside the concrete, and record the Poisson's ratio of the helical auxetic fiber inside the concrete during the load action.

[0111] Comparative Example 7 The preparation process of the helical auxetic fiber with negative Poisson's ratio effect is as follows: 1. The core fiber polypropylene fiber (diameter 1.2 mm) is wound on the fiber conveying device, ensuring that the core fiber is in a straightened state, and ensuring that the fiber conveying device can uniformly convey the polypropylene fiber; 2. The steel fiber (diameter 0.3 mm) is fixed on the winding device (i.e. hollow spindle), and the fiber conveying device conveying speed and the hollow spindle rotating speed are adjusted, so that the steel fiber is wound on the polypropylene fiber at a wrapping angle of 10°; 3. The prepared helical auxetic fiber is collected using the take-up device, and then the fiber is cut to a length of 30 mm, and universal glue is added at both ends of the cut fiber to ensure the stability of the fiber.

[0112] The method for measuring the Poisson's ratio of the helical auxetic fiber in the different matrix strength concrete is as follows: (1) Surface modification: immerse the helical auxetic fiber in a 3% silane coupling agent (KH-550) ethanol solution for 15 min, and dry at 60°C for standby.

[0113] (2) Add 1100 parts of coarse aggregate and 700 parts of fine aggregate to the mixer mixing container and stir for 1 min.

[0114] (3) Mix 300 parts of cement, 120 parts of slag powder, 50 parts of fly ash and 30 parts of silica fume for 2 min, then pour into the above aggregate mixture and stir for another 2 min.

[0115] (4) Mix 150 parts of water and 7.5 parts of polycarboxylic acid water reducer for 30 s, then pour into the mixer mixing container and stir for 3 min.

[0116] (5) Pour the concrete into the mold, and vertically bury the helical auxetic fiber with a length of 30 mm in the concrete matrix, with a burial depth of 20 mm, and then cure for 28 d according to the national standard requirements. The concrete matrix strength grade is C60.

[0117] (6) Apply the pull-out load to the helical auxetic fiber, use in-situ CT to scan the helical auxetic fiber inside the concrete, and record the Poisson's ratio of the helical auxetic fiber inside the concrete during the load action.

[0118] Comparative Example 8 The preparation process of the helical auxetic fiber with negative Poisson's ratio effect is as follows: 1. The core fiber polypropylene fiber (diameter 1.2 mm) is wound on the fiber conveying device, ensuring that the core fiber is in a straightened state, and ensuring that the fiber conveying device can uniformly convey the polypropylene fiber; 2. The steel fiber (diameter 0.3 mm) is fixed on the winding device (i.e. hollow spindle), and the fiber conveying device conveying speed and the hollow spindle rotating speed are adjusted, so that the steel fiber is wound on the polypropylene fiber at a wrapping angle of 10°; 3. The prepared helical auxetic fiber is collected using the take-up device, and then the fiber is cut to a length of 30 mm, and universal glue is added at both ends of the cut fiber to ensure the stability of the fiber.

[0119] The method for measuring the Poisson's ratio of the helical auxetic fiber in the different matrix strength concrete is as follows: (1) Surface modification: immerse the helical auxetic fiber in a 3% silane coupling agent (KH-550) ethanol solution for 15 min, and dry at 60°C for standby.

[0120] (2) Add 1100 parts of coarse aggregate and 650 parts of fine aggregate to the mixer mixing container and stir for 1 min.

[0121] (3) Mix 300 parts of cement, 150 parts of slag powder, 30 parts of fly ash and 50 parts of silica fume for 2 min, then pour into the above aggregate mixture and stir for another 2 min.

[0122] (4) Mix 140 parts of water and 14 parts of polycarboxylic acid water reducer for 30 s, then pour into the mixer mixing container and stir for 3 min.

[0123] (5) Pour the concrete into the mold, and vertically bury the helical auxetic fiber with a length of 30 mm in the concrete matrix, with a burial depth of 20 mm, and then cure for 28 d according to the national standard requirements. The concrete matrix strength grade is C80.

[0124] (6) Apply the pull-out load to the helical auxetic fiber, use in-situ CT to scan the helical auxetic fiber inside the concrete, and record the Poisson's ratio of the helical auxetic fiber inside the concrete during the load action.

[0125] Comparative Example 9 The preparation process of the helical auxetic fiber with negative Poisson's ratio effect is as follows: 1, winding the core fiber polypropylene fiber (diameter 1.2 mm) on the fiber conveying device, ensuring that the core fiber is in a straight state, and ensuring that the fiber conveying device can uniformly convey the polypropylene fiber; 2, fixing the steel fiber (diameter 0.3 mm) on the winding device (i.e. hollow spindle), adjusting the fiber conveying speed of the fiber conveying device and the rotation speed of the hollow spindle, so that the steel fiber is wound on the polypropylene fiber at a wrapping angle of 10°; 3, collecting the prepared helical auxetic fiber using the take-up device, then cutting the fiber into a length of 30 mm, and dropping universal glue at both ends of the cut fiber to ensure the stability of the fiber.

[0126] The method for measuring the Poisson's ratio of the helical auxetic fiber in different matrix strength concrete is as follows: (1) Surface modification: immerse the helical auxetic fiber in a 3% silane coupling agent (KH-550) ethanol solution for 15 min, and dry at 60°C before use.

[0127] (2) Add 1050 parts of coarse aggregate and 650 parts of fine aggregate into the mixer mixing container and stir for 1 min.

[0128] (3) Mix 280 parts of cement, 220 parts of slag powder, 60 parts of fly ash and 80 parts of silica ash for 2 min, then pour into the above aggregate mixture and stir for another 2 min.

[0129] (4) Mix 140 parts of water and 20 parts of polycarboxylic acid water reducing agent for 30 s, then pour into the mixer mixing container and stir for 3 min.

[0130] (5) Pour the concrete into the mold, and vertically embed the helical auxetic fiber with a length of 30 mm into the concrete matrix with a burial depth of 20 mm, then cure for 28 d according to the national standard requirements, and the concrete matrix strength grade is C100.

[0131] (6) Apply the pull-out load to the helical auxetic fiber, use in-situ CT to scan the helical auxetic fiber inside the concrete, and record the Poisson's ratio of the helical auxetic fiber inside the concrete during the load action.

[0132] The test results of the maximum negative Poisson's ratio of the helical auxetic fiber in different matrix strength concrete are shown in Table 5: from Table 5, based on the principle of maximizing the negative Poisson's ratio effect of the helical auxetic fiber, the helical auxetic fiber with a diameter ratio of 1-3 and a wrapping angle of 15° has the best matching performance with C60 concrete; the helical auxetic fiber with a diameter ratio of 1-3 and a wrapping angle of 20° has the best matching performance with C80 concrete; the helical auxetic fiber with a diameter ratio of 1-4 and a wrapping angle of 10° has the best matching performance with C100 concrete.

[0133] Table 5. Statistics of the maximum negative Poisson's ratio detection results of the helical auxetic fibers in different matrix strength concretes

[0134] The above examples are only used to illustrate the technical solutions of the present application, but not limit the present application; although the present application has been described in detail with reference to the foregoing examples, those ordinarily skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacement for some technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for preparing spiral tensile fiber reinforced concrete with high explosion resistance, characterized in that: The methods include: Based on fiber type and mechanical property parameters, the diameter ratio and wrapping angle of helical turgor fibers are predicted using deep learning, and helical turgor fibers are then prepared. Spiral tensile fibers were embedded in concrete with different matrix strengths. After curing, the negative Poisson's ratio of the spiral tensile fibers was measured, and the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio was recorded. Under the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio, multiple mix proportions are generated. Based on the characteristic parameters of the helical tensile fiber and the mix proportion, the mechanical property prediction value is obtained based on deep learning. The fitness of the mechanical property prediction value and the target value is calculated. The matrix mix proportion is searched based on the genetic algorithm and verified. Concrete is prepared based on the matrix mix proportions and helical expansion fibers.

2. The method for preparing spiral tensile fiber reinforced concrete with high explosion resistance according to claim 1, characterized in that: The process of predicting the fiber diameter ratio and wrapping angle based on fiber type and mechanical property parameters using deep learning includes: Using the fiber type and fiber mechanical property parameters of the spiral yarn as input, and the structural parameters of the spiral yarn as output labels, a multi-layer fully connected neural network is trained to obtain a deep learning model. The fiber mechanical property parameters include Poisson's ratio, elastic modulus and elongation at break, and the structural parameters of the spiral yarn include diameter ratio, wrapping angle and negative Poisson's ratio effect value. Two fibers with significantly different elastic moduli are selected, and the fiber type and mechanical property parameters are input into a deep learning model to output the diameter ratio and wrapping angle of the helical swollen fiber.

3. The method for preparing spiral tensile fiber reinforced concrete with high explosion resistance according to claim 1, characterized in that: The process of preparing helical stretched fibers includes: Choose two types of fibers with a large difference in elastic modulus. One type of fiber is the core fiber, and the other type is the wrapped fiber. The fiber types include polypropylene fiber, polyvinyl alcohol fiber, flax fiber, glass fiber, and steel fiber. The core fiber is wound around the fiber conveying device, so that the core fiber is in a straight state, and the fiber conveying device conveys the core fiber at a uniform speed. The wrapping fiber is fixed on the winding device, and the fiber conveying speed of the fiber conveying device and the rotation speed of the winding device are adjusted so that the wrapping fiber is wrapped around the core fiber at the predicted wrapping angle to obtain a spiral stretched fiber. The prepared spiral-stretched fibers are collected using a take-up device, the spiral-stretched fibers are cut, and all-purpose adhesive is dripped onto both ends of the cut spiral-stretched fibers.

4. The method for preparing spiral tensile fiber reinforced concrete with high explosion resistance according to claim 1, characterized in that: Concrete with different matrix strengths uses the same preparation method but different raw material proportions. The process of embedding helical tensile fibers into concrete with different matrix strengths and then measuring the negative Poisson's ratio of the helical tensile fibers after curing includes: The spiral-stretched fiber was immersed in a 3% silane coupling agent ethanol solution for 15 minutes and then dried at 60°C for later use. Add the coarse and fine aggregates to the mixing container of the mixer and mix for 1 minute; Mix cement, slag powder, fly ash and silica fume for 2 minutes, then pour the mixture into the mixing container of the mixer and mix for another 2 minutes. After mixing water and polycarboxylate superplasticizer for 30 seconds, pour the mixture into the mixing container of the mixer and stir for 3 minutes to obtain concrete with the target matrix strength. Pour concrete of the target matrix strength into the mold, and vertically embed 30mm long spiral expansion fibers into the concrete matrix to a depth of 20mm, and cure for 28 days; Pull-out loads were applied to the helical expansion fibers, and in-situ CT scans were used to examine the helical expansion fibers inside the concrete. The negative Poisson's ratio of the helical expansion fibers inside the concrete was recorded during the loading process.

5. The method for preparing spiral tensile fiber reinforced concrete with high explosion resistance according to claim 4, characterized in that: The cement is PII·52.5 grade ordinary Portland cement, the fine aggregate is quartz sand with a particle size of 0.15-0.6 mm, the fly ash is Class I fly ash, the silica fume has SiO2 content ≥90%, chloride ion content ≤0.1%, sulfide content ≤2%, the fineness of the silica fume meets the requirement of specific surface area ≥15.000 m² / kg, the moisture content of the silica fume is ≤3%, and the polycarboxylate superplasticizer meets the requirements of: water reduction rate ≥35%, air content ≤6%, and alkali content ≤10%.

6. The method for preparing spiral tensile fiber reinforced concrete with high explosion resistance according to claim 1, characterized in that: The process of obtaining predicted mechanical properties based on deep learning, according to the characteristic parameters and blending ratio of helical stretched fibers, includes: Using the characteristic parameters of helical tensile fibers and the mix proportion as input, and the mechanical properties of fiber-reinforced concrete as output labels, a bidirectional LSTM network is trained to obtain a performance prediction network. The characteristic parameters of helical tensile fibers include fiber type, diameter, length, elastic modulus and Poisson's ratio, and the mix proportion includes water-cement ratio, sand ratio, water-reducing agent dosage and helical tensile fiber volume content. Input the characteristic parameters of the spiral tensile fiber and the mix proportion into the performance prediction network. In the mix proportion, the water-cement ratio is less than or equal to 0.3 and the sand ratio is in the range of 30%-40%. Output the predicted values ​​of mechanical properties, including splitting tensile strength, toughness index and strain energy.

7. The method for preparing spiral tensile fiber reinforced concrete with high explosion resistance according to claim 1, characterized in that: Fit between predicted and target mechanical properties for: in, , , These are the target splitting tensile strength, the target toughness index, and the target strain energy, respectively. , , These are respectively used to predict splitting tensile strength, predict toughness index, and predict strain energy. This is the cost coefficient.

8. The method for preparing spiral tensile fiber reinforced concrete with high explosion resistance according to claim 1, characterized in that: The process of finding the matrix mixing ratio based on the genetic algorithm includes: Under the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio, multiple mix proportions are randomly generated to form an initial population, with each mix proportion serving as an individual. Calculate the fitness of each individual, select individuals based on fitness, perform crossover on the selected individuals to generate new individuals, perform mutation on the crossover individuals to generate the next generation population, and repeat this process until the set number of iterations is met or the fitness change is less than 1e. -5 The matrix mix ratio is obtained.

9. The method for preparing spiral tensile fiber reinforced concrete with high explosion resistance according to claim 1, characterized in that: The matrix mix proportions include the water-cement ratio. Sand ratio Spiral expanded fiber volume content Negative Poisson's ratio of spiral-stretched fibers Water-reducing agent dosage The constraints for verifying the matrix mix proportions are: , , , , .

10. A spiral tensile fiber reinforced concrete preparation system with high explosion resistance, characterized in that: The system includes: The spiral tensile fiber design module is used to predict the diameter ratio and wrapping angle of the spiral tensile fiber based on the fiber type and mechanical property parameters using deep learning, and to prepare the spiral tensile fiber. The matrix strength determination module based on maximizing the negative Poisson's ratio effect is used to embed helical tensile fibers into concrete with different matrix strengths, measure the negative Poisson's ratio value of the helical tensile fibers after curing, and record the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio value. The matrix mix design module is used to generate multiple mix proportions under the concrete matrix strength grade corresponding to the maximum negative Poisson's ratio. Based on the characteristic parameters of the helical tensile fiber and the mix proportion, the module obtains the predicted mechanical properties based on deep learning, calculates the fitness of the predicted mechanical properties with the target values, searches for the matrix mix proportion based on the genetic algorithm, and verifies the matrix mix proportion. A concrete preparation module for preparing concrete based on matrix mix proportions and helical expansion fibers.

Citation Information

Patent Citations

  • Concrete prepared by utilizing synthetic double-helix fibers and preparation method of concrete

    CN108558312A

  • Spiral steel fiber ultra-high-performance concrete and preparation method thereof

    CN108585689A

  • Anti-explosion and anti-impact multistage heterogeneous fiber prefabricated body composite concrete and preparation method thereof

    CN111003959A

  • High-performance concrete mix proportion design and performance prediction method based on deep learning

    CN117912594A

  • Fiber hybrid composite material anti-explosion structure optimization method and system

    CN119312647A