Preparation method of fireproof, high-temperature-resistant, waterproof, moisture-proof and strong-sound-absorption composite material of micro-perforated UHPC (Ultra High Performance Concrete) board

Abstract

The invention provides a preparation method of a fireproof, high-temperature-resistant, waterproof, moisture-proof and strong-sound-absorption composite material of a micro-perforated UHPC board, and belongs to the technical field of electrical digital data processing.The preparation method comprises the steps that firstly, the key parameter range is determined through orthogonal test design, a sample is prepared, and the acoustic performance is tested and analyzed through an impedance tube; then, optimal micropore structure parameters (the aperture is 0.5 mm, the pitch is 15.6 mm and the perforation rate is 8%) are determined by applying a parameter optimization function, the optimal backing material and thickness are selected and verified, and the sound absorption performance is optimized by utilizing a pre-trained graph neural network prediction model. And then the surface of the UHPC board substrate is subjected to nanoscale hydrophobic coating treatment, and the UHPC board substrate and a backing material are compounded to form an integrated structure. Finally, the product performance is verified through a high-temperature experiment test and full-performance evaluation, perfect combination of fire resistance, high temperature resistance, water resistance, moisture resistance and efficient sound absorption performance is achieved, and traditional glass wool and rock wool are omitted; the ceiling can be used for ceilings of movie theaters, ceilings and side walls of stadiums, ceilings and side walls of terminal buildings and inner walls of highway tunnels.

Description

Technical Field

[0001] The present invention belongs to the technical field of electrical digital data processing. Specifically, it relates to a preparation method of a strongly sound-absorbing composite material for a micro-perforated UHPC board with fire resistance, high temperature resistance, waterproofness, and moisture resistance. Background Art

[0002] In the fields of architectural acoustics, industrial noise reduction, and environmental protection, high-efficiency sound-absorbing materials are of great significance for controlling noise pollution and improving the acoustic environment. Traditional micro-perforated sound-absorbing materials have received extensive attention because they can achieve effective sound absorption without fiber filling. Typical applications include various scenarios such as transportation hubs, theaters, and stadiums. Traditional micro-perforated sound-absorbing materials are mainly made of materials such as metal, wood, or plastic, and the attenuation of sound wave energy is achieved by precisely controlling parameters such as the micropore diameter, spacing, and perforation rate.

[0003] However, traditional micro-perforated sound-absorbing materials have obvious defects when applied in harsh environments. Metal micro-perforated plates are prone to corrosion in humid environments, plastic micro-perforated plates have poor fire resistance, and most traditional sound-absorbing materials can only achieve good sound absorption effects within a specific frequency range. In addition, when such materials need to have fire resistance, high temperature resistance, and waterproof performance simultaneously, additional protective layers or treatment processes are often required, which easily leads to a significant reduction in sound absorption performance.

[0004] Currently, in engineering practice, methods such as multi-layer composite or special coating treatment are often used to solve the above problems. However, these methods have disadvantages such as complex processes, high costs, and mutual constraints among various performances. It is difficult to achieve excellent fire resistance, high temperature resistance, waterproofness, and moisture resistance while ensuring the sound absorption efficiency of the micro-perforated structure, especially in application scenarios that need to withstand high temperature and high humidity environments for a long time. That is to say, there is a technical problem in the prior art that it is difficult to simultaneously achieve the high-efficiency sound absorption performance and the fire resistance, high temperature resistance, waterproofness, and moisture resistance of micro-perforated sound-absorbing materials. Summary of the Invention

[0005] In view of this, the present invention provides a preparation method of a strongly sound-absorbing composite material for a micro-perforated UHPC board with fire resistance, high temperature resistance, waterproofness, and moisture resistance, which can solve the technical problem in the prior art that it is difficult to simultaneously achieve the high-efficiency sound absorption performance and the fire resistance, high temperature resistance, waterproofness, and moisture resistance of micro-perforated sound-absorbing materials.

[0006] The present invention is implemented as follows: The present invention provides a preparation method of a strongly sound-absorbing composite material for a micro-perforated UHPC board with fire resistance, high temperature resistance, waterproofness, and moisture resistance, including: conducting an orthogonal experimental design for the micro-perforated UHPC board to determine the range of key parameters; preparing multiple groups of micro-perforated UHPC specimens and measuring the acoustic absorption coefficient; applying a parameter optimization function to optimize and analyze the results of the orthogonal experimental design to determine the optimal micro-hole structure parameters and prepare a standard micro-perforated UHPC board substrate; selecting a backing material and conducting a performance comparison experiment; using a pre-trained prediction model for the performance of micro-perforated sound-absorbing materials to predict the sound-absorbing performance of different structural combinations to determine the optimal thickness of the backing material and the composite structure scheme; performing waterproof treatment on the surface of the substrate using a nano-scale hydrophobic coating technology to ensure waterproof and moisture-proof effects while maintaining the micro-hole permeability of the substrate surface; combining the substrate with the backing material with the optimal thickness of the backing material through an adhesive to form an integrated composite structure; and conducting a full-performance test on the integrated composite structure to obtain the final product. Optionally, the adhesive can be a commonly used adhesive for UHPC in the art.

[0007] Among them, in the orthogonal experimental design, the factor levels of the micro-hole diameter are set to 0.3 mm, 0.5 mm, and 0.7 mm, the factor levels of the micro-hole spacing are set to 12.5 mm, 15.6 mm, and 18.7 mm, and the factor levels of the micro-hole perforation rate are set to 5%, 8%, and 11%.

[0008] Among them, in the step of preparing multiple groups of micro-perforated UHPC specimens, the impedance tube test method is used to measure the acoustic absorption coefficients of multiple groups of micro-perforated UHPC specimens at different frequencies, and the parameter combination with the optimal acoustic performance is obtained through analysis.

[0009] Among them, the parameter optimization function inputs the factor levels of the micro-hole diameter, the factor levels of the micro-hole spacing, the factor levels of the micro-hole perforation rate, the target frequency range parameters, and the application environment type parameters, and the parameter optimization function outputs the optimal micro-hole structure parameters.

[0010] Among them, according to the optimal micro-hole structure parameters, the factor level of the micro-hole diameter is preferably 0.5 mm, the factor level of the micro-hole spacing is preferably 15.6 mm, and the factor level of the micro-hole perforation rate is preferably 8%, and a standard micro-perforated UHPC board substrate is prepared.

[0011] Among them, in the step of selecting the backing material, basalt cloth or soluble fiber felt is selected as the backing material, and a performance comparison experiment with different backing material thicknesses is conducted to measure the frequency characteristic curve of the acoustic absorption coefficient after compounding.

[0012] Among them, the performance prediction model of the micro-perforated sound-absorbing material inputs the micro-hole diameter factor level, the micro-hole spacing factor level, the micro-hole perforation rate factor level, the type of the backing material, and the thickness of the backing material, and the performance prediction model of the micro-perforated sound-absorbing material outputs the predicted frequency characteristic curve of the acoustic absorption coefficient.

[0013] Among them, the specific structure of the performance prediction model of the micro-perforated sound-absorbing material is a performance prediction network for micro-perforated sound-absorbing materials based on the combination of a graph neural network and a convolutional neural network, which includes three main modules: a material structure feature encoding module, an acoustic property prediction module, and an application environment adaptation module.

[0014] Among them, the steps for establishing the training data set in the pre-training process of the performance prediction model of the micro-perforated sound-absorbing material include collecting the published research data of the micro-perforated sound-absorbing material, simulating and generating more data points through finite element analysis software to expand the data set, performing standardized processing on all the data and dividing it into a training set, a validation set, and a test set, and classifying and labeling the data according to different parameter types of the application environment.

[0015] Among them, the full performance test includes an acoustic absorption coefficient test, a fire resistance rating test, a water resistance test, a flexural strength test, and a weight density test.

[0016] Compared with the prior art, the present invention provides a preparation method of a micro-perforated UHPC board with strong sound absorption and composite properties of fire resistance, high temperature resistance, water resistance, and moisture resistance. The present invention proposes a preparation method of a micro-perforated sound-absorbing composite material based on UHPC, determines the optimal micro-hole structure parameters through orthogonal experimental design and parameter optimization, combines basalt cloth or soluble fiber felt as the backing material, and simultaneously adopts a nano-scale hydrophobic coating technology to achieve surface waterproof treatment.

[0017] This method solves the defect problems of traditional micro-perforated sound-absorbing materials in applications under harsh environments. The UHPC substrate has natural fire resistance and high strength, solving the problems of flammability or insufficient strength of traditional materials; through the optimization of micro-perforation parameters and the compounding of the backing material, the problem of narrow sound absorption frequency range of a single structure is solved; the nano-hydrophobic coating treatment realizes the waterproof and moisture-proof functions without affecting the air permeability of the micro-holes, solving the contradiction that traditional waterproof treatment will block the micro-holes and affect the sound absorption performance.

[0018] The present invention successfully solves the technical problem that it is difficult for micro-perforated sound-absorbing materials to simultaneously have high-efficiency sound absorption performance and fire resistance, high temperature resistance, water resistance, and moisture resistance by integrating advanced materials science and acoustic principles, providing a new technical path for acoustic governance in harsh environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flowchart of the method of the present invention. Specific Embodiments

[0020] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0021] As Figure 1 shown, it is a flowchart of a preparation method of a strongly sound-absorbing composite material with fire resistance, high temperature resistance, waterproofness, and moisture resistance for a micro-perforated UHPC board provided by the present invention. The method includes the following steps:

[0022] S01. Conduct an orthogonal experimental design for the micro-perforated UHPC board to determine the key parameter range. Set the factor levels of the micro-hole diameter to 0.3 mm, 0.5 mm, and 0.7 mm, the factor levels of the micro-hole spacing to 12.5 mm, 15.6 mm, and 18.7 mm, and the factor levels of the micro-hole perforation rate to 5%, 8%, and 11%.

[0023] S02. Prepare multiple groups of micro-perforated UHPC specimens according to the orthogonal experimental design, measure the acoustic absorption coefficients of the multiple groups of micro-perforated UHPC specimens at different frequencies by using the impedance tube test method, and analyze to obtain the parameter combination with the optimal acoustic performance.

[0024] S03. Apply a parameter optimization function to optimize and analyze the results of the orthogonal experimental design. The parameter optimization function inputs the factor levels of the micro-hole diameter, the factor levels of the micro-hole spacing, the factor levels of the micro-hole perforation rate, the target frequency range parameter, and the application environment type parameter. The parameter optimization function outputs the optimal micro-hole structure parameters. According to the optimal micro-hole structure parameters, determine that the factor level of the micro-hole diameter is preferably 0.5 mm, the factor level of the micro-hole spacing is preferably 15.6 mm, and the factor level of the micro-hole perforation rate is preferably 8%, and prepare a standard micro-perforated UHPC board substrate.

[0025] S04. Select basalt cloth or soluble fiber felt as the backing material, conduct a performance comparison experiment with different backing material thicknesses, and measure the frequency characteristic curve of the acoustic absorption coefficient after compounding.

[0026] S05. Use a pre-trained micro-perforated sound-absorbing material performance prediction model to predict the sound-absorbing performance under different structural combinations. The micro-perforated sound-absorbing material performance prediction model inputs the factor levels of the micro-hole diameter, the factor levels of the micro-hole spacing, the factor levels of the micro-hole perforation rate, the type of the backing material, and the thickness of the backing material. The micro-perforated sound-absorbing material performance prediction model outputs the predicted frequency characteristic curve of the acoustic absorption coefficient. According to the predicted frequency characteristic curve of the acoustic absorption coefficient, determine the optimal thickness of the backing material and the compound structure scheme to maximize the sound-absorbing performance in the full frequency band.

[0027] S06. Waterproof the surface of the micro-perforated UHPC board substrate using nano-scale hydrophobic coating technology to ensure waterproof and moisture-proof effects while maintaining the micropore permeability of the surface of the micro-perforated UHPC board substrate;

[0028] S07. Compose the micro-perforated UHPC board substrate with basalt cloth or soluble fiber felt of the optimal backing material thickness through an adhesive to form an integrated composite structure;

[0029] S08. Conduct a high-temperature experimental test on the integrated composite structure, maintain it for 4 hours in an environment of 850 degrees Celsius, and determine the structural integrity and mechanical property retention rate of the integrated composite structure;

[0030] S09. Conduct a full-performance test on the integrated composite structure, including acoustic absorption coefficient test, fire rating test, water resistance test, flexural strength test, and weight density test. Optionally, also include feedback of the full-performance test data to the micro-perforated sound-absorbing material performance prediction model for continuous optimization.

[0031] Among them, the impedance tube test method refers to measuring the acoustic absorption coefficient of a material using an impedance tube device in an acoustic laboratory according to the international standard ISO 10534-2, and calculating the absorption ability of the material for sound waves of different frequencies through the ratio of the incident sound wave to the reflected sound wave.

[0032] Among them, the micro-perforated UHPC board substrate refers to a board made of UHPC material and precisely processed with micropores of a specific diameter on the surface. UHPC has the characteristics of ultra-high strength, high density, and low porosity.

[0033] Among them, basalt cloth refers to an inorganic fiber cloth woven from basalt fibers, which has excellent fire resistance, maintains stability in a high-temperature environment, and has a melting point as high as 1450 degrees Celsius.

[0034] Among them, soluble fiber felt refers to a heat-insulating material mainly processed from soluble inorganic fibers, which has good heat-insulating performance in a high-temperature environment and does not produce harmful gases.

[0035] Among them, nano-scale hydrophobic coating technology refers to forming a nano-structured hydrophobic layer on the surface of a material, making water droplets not easily penetrate into the micropores but not affecting air circulation, thereby achieving waterproofing without affecting the sound-absorbing performance.

[0036] Among them, the target frequency range parameter refers to the range of sound wave frequencies that need to be mainly absorbed determined according to the application scenario requirements, generally including the low-frequency band of 125 - 500 Hz, the middle-frequency band of 500 - 2000 Hz, and the high-frequency band of 2000 - 4000 Hz.

[0037] Among them, the application environment type parameter refers to the environmental classification of material usage, including indoor environment, semi-outdoor environment or full outdoor environment. Different environments have different requirements for the waterproof and moisture-proof performance of materials.

[0038] Among them, the backing material type refers to two kinds of backing materials, basalt cloth or soluble fiber felt.

[0039] Among them, the backing material thickness refers to the thickness of basalt cloth or soluble fiber felt, usually in the range of 10 millimeters to 50 millimeters.

[0040] Among them, the optimal backing material thickness refers to the thickness of the backing material that can achieve the best sound absorption effect obtained through experiments or model predictions.

[0041] The parameter optimization function is used to analyze the influence law of micro-perforation structure parameters on acoustic performance based on multiple groups of experimental data and predict the optimal parameter combination. The inputs of the parameter optimization function include the micro-hole diameter factor level array, the micro-hole spacing factor level array, the micro-hole perforation rate factor level array, the target frequency range parameter and the application environment type parameter. The output of the parameter optimization function is the optimal micro-perforation structure parameter combination for a specific application scenario and the predicted acoustic performance curve.

[0042] The specific structure of the micro-perforated sound absorption material performance prediction model is a micro-perforated sound absorption material performance prediction network based on the combination of a graph neural network and a convolutional neural network, including three main modules: a material structure feature encoding module, an acoustic characteristic prediction module and an application environment adaptation module. Among them, the material structure feature encoding module uses a multi-layer graph convolutional network to transform the micro-hole diameter factor level, the micro-hole spacing factor level, the micro-hole perforation rate factor level and the physical properties of the backing material type into high-dimensional feature vectors. The acoustic characteristic prediction module uses a deep transformer network based on the multi-head attention mechanism to predict the acoustic absorption coefficient at different frequencies. The number of attention heads is dynamically adjusted according to the combination number of the micro-hole diameter factor level and the backing material type. The application environment adaptation module adjusts the prediction result based on the acoustic characteristics of the application environment type parameter and generates a final performance evaluation report.

[0043] The steps for establishing the training dataset during the pre-training process of the performance prediction model for the micro-perforated sound-absorbing material specifically include collecting a large amount of published research data on micro-perforated sound-absorbing materials, including the measured acoustic absorption coefficient frequency characteristic curves under different levels of the micro-hole diameter factor, the micro-hole spacing factor, the micro-hole perforation rate factor, the type of the backing material, and the combination of the thickness of the backing material. At the same time, more data points are simulated and generated through finite element analysis software to expand the dataset. All the data is standardized and divided into a training set, a validation set, and a test set. Finally, the data is classified and labeled according to different types of application environment parameters to form a complete multi-dimensional training dataset.

[0044] The steps for pre-training the performance prediction model for the micro-perforated sound-absorbing material specifically include first initializing the parameters of the performance prediction model for the micro-perforated sound-absorbing material using a traditional acoustic theory model, training the material structure feature encoding module and the acoustic characteristic prediction module in sequence using a hierarchical pre-training strategy, then performing full-network joint fine-tuning. During the training process, real environmental noise data is introduced to enhance the diversity of training samples. The mean square error loss function based on frequency weighting is used to evaluate the performance of the performance prediction model for the micro-perforated sound-absorbing material and guide parameter update. Finally, the prediction accuracy of the performance prediction model for the micro-perforated sound-absorbing material under different types of application environment parameters is verified by comparing with the measured data, and targeted optimization is carried out to form a pre-training model that can meet the design requirements of various micro-perforated UHPC composite materials.

[0045] The specific implementation manners of the above steps are described in detail below. The specific implementation manner of step S01 is to conduct an orthogonal experiment design for the micro-perforated UHPC plate. First, based on the acoustic micro-perforation theory, the range of key structure parameters is determined, and the experimental scheme is designed using the L9(33) orthogonal table. This step includes calculating the number of experiments required for the orthogonal experiment, determining the parameter levels according to the micro-perforated sound-absorbing principle, and setting the micro-hole diameter factor levels as 0.3 mm, 0.5 mm, and 0.7 mm, the micro-hole spacing factor levels as 12.5 mm, 15.6 mm, and 18.7 mm, and the micro-hole perforation rate factor levels as 5%, 8%, and 11%. During the parameter setting process, considering the material properties of UHPC, the micro-hole diameter should not be too small, otherwise the processing difficulty will increase; nor should it be too large, otherwise the acoustic wave damping effect will weaken. This step ensures the reliability and representativeness of the subsequent experimental results through a scientific experimental design method, laying a foundation for optimizing the micro-perforated structure parameters.

[0046] The specific implementation of step S02 is to prepare micro-perforated UHPC specimens and test their acoustic properties. First, according to the orthogonal test design of S01, prepare UHPC raw materials, including cement, silica fume, quartz sand, water reducer, steel fiber, etc., with weight ratios of 1:0.25:1.1:0.02:0.02 respectively. Use precision drilling equipment to process micro-holes that meet the test design on the hardened UHPC board, and prepare 9 groups of specimens with different parameters. Then, use an impedance tube device configured according to ISO 10534-2 standard to measure the acoustic absorption coefficient of each specimen at intervals of 100 Hz in the frequency range of 100 - 5000 Hz. This step uses standard test methods to obtain accurate and reliable acoustic performance data. By analyzing and comparing the sound absorption performance under different parameter combinations, the key factors affecting the sound absorption performance and their interaction relationships are initially determined, providing a data basis for subsequent parameter optimization. During the test, the environmental temperature is controlled at 20 ± 2 °C, and the relative humidity is controlled at 50 ± 5%, to ensure the repeatability of the test results.

[0047] The specific implementation of step S03 is to apply a parameter optimization function to analyze the orthogonal test results and determine the optimal micro-hole structure parameters. This function is based on an optimization strategy that combines the response surface method and the genetic algorithm. First, perform variance analysis on the test data to determine the significance of the influence of each factor on the sound absorption performance, calculate the average sound absorption coefficient of each factor level, and draw a factor-response diagram. Then, construct a second-order polynomial regression model to characterize the relationship between the parameters and the sound absorption coefficient. Input the target frequency range parameters (such as the mid-frequency range of 500 - 2000 Hz) and the application environment type parameters (such as a semi-outdoor environment) into the model, and use an improved genetic algorithm to search for the optimal solution. Set the population size to 50, the crossover probability to 0.8, the mutation probability to 0.1, and the number of iterations to 100. Encode the micro-hole diameter, micro-hole spacing, and micro-hole perforation rate as chromosomes, and evaluate the performance of each group of parameters through a fitness function. According to the optimization results, the preferred factor level of the micro-hole diameter is 0.5 mm, the preferred factor level of the micro-hole spacing is 15.6 mm, and the preferred factor level of the micro-hole perforation rate is 8%. Based on this, prepare a standard micro-perforated UHPC board substrate. This step determines the optimal parameter combination through mathematical optimization methods, achieving the precision and scientific nature of the micro-perforated structure design.

[0048] The specific implementation of step S04 is to select and test the combined performance of different backing materials and thicknesses. First, the basic physical properties of basalt cloth and soluble fiber felt are evaluated, including parameters such as density, porosity, flow resistance, and thermal stability. Then, samples of backing materials with different thicknesses are prepared, with the thickness ranging from 10 mm to 50 mm, at intervals of 10 mm, for a total of 5 thickness specifications. These backing materials are respectively compounded with the standard micro-perforated UHPC plate matrix prepared in step S03 to form a temporary test structure. The impedance tube test method is used to measure the acoustic absorption coefficient of the composite specimen in the frequency range of 100 - 5000 Hz. At the same time, physical parameters such as the total thickness and total weight of the composite structure are recorded. This step systematically compares the sound absorption performance of different backing materials and different thickness combinations, obtains the relationship data between the backing material thickness and the sound absorption frequency characteristics, and provides an experimental basis for subsequent optimization of the backing structure. During the test, it was found that increasing the thickness of the backing material would improve the low-frequency sound absorption performance, but when the thickness exceeded a specific threshold (about 40 mm), the performance improvement was not obvious.

[0049] The specific implementation of step S05 is to use a pre-trained prediction model for the performance of micro-perforated sound-absorbing materials to predict and determine the optimal backing material and thickness. This model is based on a graph neural network and a convolutional neural network architecture, and inputs the micropore diameter (0.5 mm), micropore spacing (15.6 mm), micropore perforation rate (8%) parameters determined in step S03, as well as the candidate backing material types (basalt cloth or soluble fiber felt) and thicknesses (in the range of 10 - 50 mm, at intervals of 5 mm). The prediction model calculates the frequency characteristic curves of the acoustic absorption coefficient in the frequency range of 100 - 5000 Hz for different combinations through the previously trained weight matrix. Then, according to the preset evaluation indicators (such as the average sound absorption coefficient in 6 frequency bands, curve flatness, etc.), a comprehensive score is given to each combination scheme. The evaluation results show that when using basalt cloth with a thickness of 30 mm as the backing material, the average sound absorption coefficient can reach above 0.85 in the frequency band of 250 - 4000 Hz, and the frequency characteristic curve is relatively flat, belonging to the combination with the best full-frequency sound absorption performance. This step uses deep learning technology to accelerate the material optimization process, avoids a large number of trial-and-error experiments, and improves the design efficiency.

[0050] The specific implementation of step S06 is to perform a nano-scale hydrophobic coating treatment on the surface of the micro-perforated UHPC board substrate. First, use sandpaper to polish and alcohol to clean the surface of the micro-perforated UHPC board substrate to remove impurities and dust. Then, mix the silane-based hydrophobic agent, organic solvent, and nano-silica in a ratio of 1:20:0.5 to form a coating formulation. Use a low-pressure spraying device to uniformly apply the nano-hydrophobic coating on the surface of the micro-perforated UHPC board substrate, and control the coating thickness below 0.1 micrometers to ensure that the micropores are not blocked. After the coating is applied, let it stand at room temperature for 24 hours to complete curing. Confirm the surface hydrophobicity through a contact angle test. The contact angle of water droplets on the surface after the hydrophobic coating treatment should reach more than 140 degrees. At the same time, conduct an air flow resistance test to ensure that the change in air flow resistance before and after the coating treatment does not exceed 5%, ensuring that the micropore permeability is not affected. This step uses nanotechnology to achieve super-hydrophobicity on the surface of the micro-perforated board, while not affecting its acoustic performance, effectively solving the contradiction between the waterproofness and permeability of the sound-absorbing material.

[0051] The specific implementation of step S07 is to composite the micro-perforated UHPC board substrate with the backing material into an integrated structure. First, cut the basalt cloth backing material with a thickness of 30 millimeters according to the best solution determined in step S05. Then, select a general adhesive or prepare a special binder, the main components of which are modified epoxy resin and high-temperature curing agent, with a ratio of 100:25. Uniformly coat the binder on the back of the micro-perforated UHPC board substrate, and control the coverage rate above 80%, avoiding some micropore outlet areas to maintain the air flow channel. Closely attach the cut backing material to the board substrate coated with the binder, and use a flat press to apply a uniform pressure of 20 kPa for 2 hours. Then, cure it in an environment with a temperature of 60 °C for 24 hours to ensure that the binder is completely cured. After the composite is completed, use edge sealant to seal the periphery of the material to prevent moisture from seeping in from the side. This step realizes the firm bonding of the micro-perforated board and the backing material through a special bonding technology, forming an integrated composite material with stable structure and excellent performance.

[0052] The specific implementation of step S08 is to conduct high-temperature experimental tests on the integrated composite structure. First, prepare a standard test sample with dimensions of 300×300×thickness in millimeters, and set temperature monitoring points on the sample, located on the surface, in the middle, and on the back respectively. Place the test sample in a resistance high-temperature test furnace, control the heating process according to the ISO 834 standard fire curve, gradually heat from room temperature to 850°C, and maintain the temperature for 4 hours. During the test, continuously monitor the temperature changes at each monitoring point of the sample, the changes in the surface state, and possible phenomena such as cracking and spalling. After the high-temperature test, cool it naturally to room temperature, measure the dimensional changes and mass loss rate of the specimen, and evaluate the remaining flexural strength through a three-point bending test. The results show that after the prepared integrated composite structure is maintained at 850°C for 4 hours, the structural integrity is good, there are no obvious cracking and spalling phenomena, the flexural strength retention rate reaches more than 75% of the original strength, and the mass loss rate is less than 3%. This step verifies the fire resistance of the material through strict high-temperature tests, ensuring that it can still maintain its basic functions and structural safety under extreme conditions.

[0053] The specific implementation of step S09 is to conduct full-performance tests on the integrated composite structure and optimize the prediction model. First, test the acoustic absorption coefficient according to the ISO 10534-2 standard, with a frequency range of 100 - 5000 Hz. Then conduct a fire rating test according to the GB8624 standard to evaluate its combustion performance and smoke toxicity. Conduct a water resistance test according to the GB / T 23447 standard, including measuring the water absorption rate and strength change rate after soaking for 24 hours. Test the flexural strength according to the GB / T 17671 standard, and record the fracture load and fracture mode. Finally, measure the weight density of the composite material and calculate the mass per unit area. After collecting complete test data, input it into the performance prediction model of the micro-perforated sound-absorbing material for comparative analysis, and evaluate the error between the predicted result and the measured result. According to the error analysis results, use the Bayesian optimization algorithm to adjust the model parameters, improve the feature extraction ability of the graph convolutional network and the frequency response prediction accuracy of the multi-head attention mechanism. The prediction accuracy of the updated model has increased by more than 15%, especially in the mid-high frequency band (1000 - 4000 Hz), the prediction error has been reduced to within ±5%. This step verifies the comprehensive performance of the final product through comprehensive performance tests and data feedback, and also realizes the continuous optimization of the prediction model, forming a virtuous cycle of product development and model improvement.

[0054] The specific implementation of the performance prediction model structure of the micro-perforated sound-absorbing material is based on a hybrid architecture of a graph neural network and a convolutional neural network. The model consists of three core modules: a material structure feature encoding module, an acoustic property prediction module, and an application environment adaptation module. The material structure feature encoding module adopts a three-layer graph convolutional network structure. The input layer receives parameters such as the micropore diameter, micropore spacing, micropore perforation rate, and the type of backing material. Each parameter is regarded as the feature of a graph node, and the edges are constructed through physical relationships between the nodes. The first layer of graph convolution uses 32 filters, the second layer uses 64 filters, and the third layer uses 128 filters. After each layer, batch normalization and the ReLU activation function are connected. Finally, a 256-dimensional material structure feature vector is output. The acoustic property prediction module is based on a transformer network with a multi-head attention mechanism, which contains 4 encoder layers, each with 8 attention heads, and the hidden layer dimension is 512. This module receives the material structure feature vector and introduces frequency encoding information to generate predicted values of the acoustic absorption coefficient at different frequency points (100 - 5000 Hz, with an interval of 100 Hz). The application environment adaptation module uses a fully connected neural network, which consists of three layers with the number of neurons being 256, 128, and 50 respectively. It inputs the application environment type parameters (encoded as one-hot vectors) and the output of the acoustic property prediction module, adjusts the prediction results according to the acoustic characteristics of a specific environment, and finally outputs the corrected absorption coefficient values at 50 frequency points and the comprehensive performance score. The model adopts a multi-task learning framework to simultaneously optimize the prediction error of the absorption coefficient and the classification accuracy of the performance. The loss function is a combination of weighted mean squared error and cross-entropy loss. Through multi-level feature extraction and the attention mechanism, this model structure effectively captures the complex non-linear relationship between the micro-perforated structure and the acoustic performance, achieving high-precision performance prediction.

[0055] The specific implementation of establishing the training dataset during the pre-training process of the performance prediction model for micro-perforated sound-absorbing materials mainly includes four links: data collection, data generation, data processing, and data classification. In the data collection link, the experimental data in the research literature on micro-perforated sound-absorbing materials published in the past decade was systematically sorted out, and parameter information such as the micropore diameter (in the range of 0.2 - 1.5 mm), micropore spacing (in the range of 5 - 30 mm), micropore perforation rate (in the range of 1% - 15%), type of backing material (a total of 5 typical materials), and thickness of the backing material (in the range of 5 - 100 mm) was extracted, as well as the corresponding measured frequency characteristic curve data of the acoustic absorption coefficient. A total of 350 groups of effective data points were collected. In the data generation link, a simulation model of the acoustic characteristics of the micro-perforated sound-absorbing structure was established using the finite element analysis software COMSOL Multiphysics. Based on the Delany-Bazley-Miki equation as the theoretical basis, within the parameter space of the collected experimental data, 2000 new parameter combinations were generated according to the Latin hypercube sampling strategy, and the corresponding frequency characteristic curves of the acoustic absorption coefficient were calculated to expand the dataset scale and fill the sparse regions of the parameter space. In the data processing link, all data was standardized. The micropore parameters were scaled to the range of 0 - 1 using the min-max normalization method, and the acoustic absorption coefficient curve was denoised and feature-extracted using wavelet transform, and then randomly divided into a training set, a validation set, and a test set according to the ratio of 8:1:1. In the data classification link, according to the collected application case information, the data was labeled into three categories: indoor environment, semi-outdoor environment, and outdoor environment, and a characteristic sound spectrum and a performance weight matrix were defined for each environment to complete the construction of the multi-dimensional training dataset. This dataset contains the parameter-performance correspondence relationship, characteristics of different application environments, and material physical property data, providing a solid data foundation for the comprehensive training of the model.

[0056] The following details the mathematical models or calculation processes involved in the present invention.

[0057] In step S02, the impedance tube test method is used to measure the acoustic absorption coefficient of the micro-perforated UHPC specimen. According to the ISO10534-2 standard, the calculation process of the acoustic absorption coefficient is specifically expressed as follows:

[0058] α = 1 - |R| 2 ;

[0059] In the formula, α is the acoustic absorption coefficient, and its value range is 0 - 1; R is the complex reflection coefficient, which is calculated from the ratio of the incident sound wave to the reflected sound wave.

[0060] The calculation formula for the complex reflection coefficient R is:

[0061]

[0062] In the formula, H 12is the transfer function between two measurement points; H i is the transfer function of the incident wave; H r is the transfer function of the reflected wave; k is the wave number, k = 2πf / c; f is the acoustic wave frequency, in hertz; c is the speed of sound, approximately 343 m / s under standard conditions; x 1 is the distance from the first microphone to the specimen surface, in meters; j is the imaginary unit.

[0063] The transfer function H 12 is calculated from the sound pressure signals measured by two microphones:

[0064]

[0065] where p 1 and p 2 are the sound pressures measured at the positions of the two microphones, in pascals respectively.

[0066] Ideally, the transfer functions of the incident wave and the reflected wave can be expressed as:

[0067] H i = e -jks ;

[0068] H r = e jks ;

[0069] where s is the distance between the two microphones, in meters.

[0070] This set of equations is based on the basic principle of sound wave propagation in a duct. By measuring the ratio of sound pressures at two points, the incident wave and the reflected wave are separated, and thus the acoustic absorption characteristics of the material surface are calculated. The advantage of the impedance tube method is that high-precision sound absorption coefficient data can be obtained under laboratory conditions, providing a reliable basis for material design.

[0071] In step S03, the parameter optimization function adopts an optimization strategy combining the response surface method and the genetic algorithm. First, a second-order polynomial regression model is constructed:

[0072]

[0073] where α f is the acoustic absorption coefficient at a specific frequency f; x 1 is the normalized micropore diameter factor level; x 2 is the normalized micropore spacing factor level; x 3 is the normalized micropore perforation rate factor level; β 0 is the constant term coefficient; β i is the first-order term coefficient; β ii is the second-order term coefficient; β ijis the interaction term coefficient; ε is the random error term, which is usually assumed to follow a normal distribution with a mean of 0 and a variance of σ 2 .

[0074] The parameter normalization process uses the following formula:

[0075]

[0076] where X i is the original parameter value; X i，min is the minimum value of the parameter; X i，max is the maximum value of the parameter. For the micropore diameter, X 1，min = 0.3 mm, X 1，max = 0.7 mm; for the micropore spacing, X 2，min = 12.5 mm, X 2，max = 18.7 mm; for the micropore perforation rate, X 3，min = 5%, X 3，max = 11%.

[0077] During the optimization process using the genetic algorithm, the fitness function is defined as:

[0078]

[0079] where F is the comprehensive fitness value; is the acoustic absorption coefficient at the frequency f i ; w i is the weight coefficient at the frequency f i , which is determined according to the target frequency range parameter; n is the number of evaluation frequency points, usually taken as 10 - 20 points. The value of the weight coefficient w i is related to the application environment type parameter. For the indoor environment, the weight of the medium and high frequency bands (1000 - 4000 Hz) is higher; for the industrial environment, the weight of the low frequency band (125 - 500 Hz) is higher.

[0080] This optimization equation combines the accurate fitting ability of the response surface method and the global search ability of the genetic algorithm, and can effectively handle the optimization problem of the multi - parameter, non - linear, multi - objective sound - absorbing structure to find the parameter combination with the optimal overall sound - absorbing performance. The selection of the second - order polynomial model is based on the understanding that there is a second - order non - linear relationship between the parameters and performance of the micro - perforated sound - absorbing structure in acoustic theory, and the interaction term reflects the mutual influence between the parameters.

[0081] In step S05, the prediction of the acoustic absorption coefficient in the micro - perforated sound - absorbing material performance prediction model uses an improved combined model of Delany - Bazley theory and Maa theory:

[0082]

[0083] Wherein, α(ω) is the acoustic absorption coefficient at angular frequency ω; Z(ω) is the complex acoustic impedance of the material surface; ρ 0 is the air density, approximately 1.21 kg / m³; c 0 is the speed of sound in air, approximately 343 m / s.

[0084] The complex acoustic impedance Z(ω) is jointly contributed by the micro-perforated panel and the backing material:

[0085] Z(ω) = z mp (ω) + Z b (ω);

[0086] Wherein, Z mp (ω) is the acoustic impedance of the micro-perforated panel; Z b (ω) is the acoustic impedance of the backing material.

[0087] The acoustic impedance Z mp (ω) of the micro-perforated panel is calculated based on the Ma theory:

[0088]

[0089] Wherein, p is the micropore perforation rate; η is the air dynamic viscosity, approximately 1.84×10 -5 Pa·s; t is the plate thickness in meters; d is the micropore diameter in meters; x is a parameter, j is the imaginary unit.

[0090] The acoustic impedance Z b (ω) of the backing material is based on the combination of the Delany-Bazley equation and the air layer model:

[0091] Z b (ω) = -jρ 0 c 0 cot(k b D);

[0092] Wherein, k b is the complex wave number in the backing material; D is the thickness of the backing material in meters.

[0093] The formula for calculating the complex wave number k b is:

[0094] k b = k 0 (1 + δ 1 -jδ 2 );

[0095] Wherein, k 0 is the wave number in air, k 0 = ω / c 0 ; δ1 and δ 2 is a correction coefficient related to the properties of the backing material.

[0096] For the basalt cloth backing material, the correction coefficient is obtained by experimental fitting:

[0097]

[0098] In the formula, f is the frequency, with the unit of hertz; σ is the flow resistance of the backing material, with the unit of N·s / m 4 ; C 1 、C 2 、C 3 、C 4 are fitting coefficients. For the basalt cloth material, the typical values are 0.0571, 0.754, 0.087, and 0.732 respectively.

[0099] This set of equation systems comprehensively considers the acoustic wave dissipation mechanism of the micro-perforated structure and the acoustic characteristics of the backing material, and can accurately predict the sound absorption performance of the composite structure at different frequencies. The power-law relationship and complex number calculation in the model are based on the physical laws of sound wave propagation in porous materials, reflecting the viscous dissipation and heat dissipation processes of sound energy converted into heat energy. The interaction term reflects the synergistic effect between the micro-perforated plate and the backing material, and this synergistic effect is the key mechanism for achieving broadband sound absorption.

[0100] In step S06, the evaluation of the micropore permeability after nano-coating treatment adopts a modified form of Darcy's Law:

[0101]

[0102] In the formula, ΔP is the pressure difference across the micropores, with the unit of pascal; μ is the fluid viscosity, approximately 1.81×10 -5 Pa·s for air; K p is the material permeability, with the unit of square meter; v is the apparent velocity of the fluid, with the unit of m / s; t is the material thickness, with the unit of meter.

[0103] The change rate of the permeability before and after coating treatment is calculated as:

[0104]

[0105] In the formula, is the permeability before treatment; is the permeability after treatment. To ensure that the micropore permeability is not affected, ΔK p % should be controlled within the range of -5% to 0%.

[0106] The permeability is measured by an air flow test device. The sample is fixed in the test chamber, a constant pressure difference is applied, and the air flow rate Q through the sample is measured. Then, the formula:

[0107]

[0108] where Q is the volume flow rate in cubic meters per second; A is the test area in square meters.

[0109] This set of equations is based on the principles of fluid mechanics and is used to evaluate the effect of the nano - coating on the permeability of microporous air flow. The modified form of Darcy's law is applicable to fluid flow in porous media under low Reynolds number conditions and can accurately characterize the permeation characteristics of the microporous structure. By controlling the change in permeability before and after coating treatment, it is ensured that the waterproof effect is achieved without affecting the acoustic performance of the material.

[0110] In step S08, the calculation formula for the retention rate of the material mechanical properties under high - temperature conditions is:

[0111]

[0112] where R s is the strength retention rate, representing the percentage of the material strength after high - temperature treatment to the strength at room temperature; is the flexural strength at room temperature in megapascals; is the flexural strength after heat treatment at 850 °C for 4 hours in megapascals.

[0113] The flexural strength is obtained through a three - point bending test, and the calculation formula is:

[0114]

[0115] where F is the fracture load in newtons; L is the support span in millimeters; b is the specimen width in millimeters; h is the specimen thickness in millimeters.

[0116] The calculation formula for the mass loss rate of the material is:

[0117]

[0118] where M L is the mass loss rate; m before is the mass of the sample before high - temperature test in grams; m after is the mass of the sample after high - temperature test in grams.

[0119] This set of equations is used to quantitatively evaluate the degree of performance degradation of materials under high-temperature conditions. The strength retention rate reflects the maintenance of the structural integrity and load-bearing capacity of the material, while the mass loss rate reflects the degree of decomposition or gasification of the material components. The three-point bending test is selected based on its simplicity and reliability, and is suitable for the strength test of plate-shaped materials. These indicators together characterize the fire resistance of materials under extreme high-temperature conditions, which is crucial for evaluating the safety of materials in high-temperature environments such as fires.

[0120] In step S09, the model optimization adopts the Bayesian optimization algorithm, and its objective function is defined as:

[0121]

[0122] Where J(θ) is the loss function; θ is the set of model parameters; N is the number of test samples; w i is the frequency weight coefficient; y i is the measured sound absorption coefficient of the i-th sample; is the sound absorption coefficient predicted by the model; λ is the regularization coefficient, usually taking a value of 0.001 - 0.01; is the L2 norm of the model parameters, which is used to prevent overfitting.

[0123] The frequency weight coefficient w i is calculated by the formula:

[0124]

[0125] Where f i is the i-th frequency point, with the unit of Hertz; β is the frequency bias coefficient. For the case of strengthening low-frequency performance, β < 0; for the case of strengthening high-frequency performance, β > 0; for the case of balancing the performance of the entire frequency band, β ≈ 0.

[0126] The model prediction accuracy is evaluated using the mean relative error:

[0127]

[0128] This set of equations is used for performance evaluation and parameter adjustment in the model optimization process. The Bayesian optimization algorithm is selected based on its efficiency in dealing with complex non-linear problems, and can find a solution close to the global optimum within fewer iterations. The addition of the frequency weight term in the loss function is to adjust the prediction focus of the model for different application scenarios, while the regularization term is used to control the model complexity and prevent overfitting. The mean relative error as an evaluation index intuitively reflects the accuracy of the model prediction, providing an objective basis for the iterative optimization of the model.

[0129] Specifically, the principle of the present invention is as follows: The technical principle of the present invention is based on the organic combination of the micro-perforated sound absorption theory and the characteristics of UHPC materials. The micro-perforated sound absorption theory shows that when sound waves pass through micro-holes with a diameter of sub-millimeter level, viscous effects and heat exchange effects will occur in the pore channels, converting sound energy into heat energy and being absorbed. The pore diameter, pore spacing, and perforation rate are the key parameters affecting the micro-perforated sound absorption effect. Through orthogonal experimental design and parameter optimization functions, the present invention determines the optimal parameter combination (pore diameter 0.5 mm, pore spacing 15.6 mm, perforation rate 8%), achieving the optimal sound absorption effect within the target frequency range.

[0130] As the matrix material, UHPC's ultra-high strength (usually greater than 150 MPa), high density, and low porosity characteristics endow the material with excellent mechanical properties and durability, while its inorganic composition ensures the non-combustibility and high-temperature stability of the material. Basalt cloth or soluble fiber felt as the backing material forms a Helmholtz resonance cavity structure, and the sound absorption effect within a wider frequency range can be achieved by adjusting the backing thickness, especially enhancing the low-frequency sound absorption ability.

[0131] The innovative application of nano-scale hydrophobic coating technology solves the problem that traditional waterproof treatment may block the micro-holes. This technology forms a nano-scale hydrophobic layer on the surface of the micro-holes, using the surface tension effect to make it difficult for water droplets to enter the micro-holes, but does not affect the free passage of air molecules, ensuring the coordinated performance of waterproof and sound absorption properties. In addition, the present invention innovatively applies a performance prediction model based on graph neural networks. Through the encoding of material structure characteristics and the prediction of acoustic characteristics, the accurate prediction and optimization of the performance of composite materials are achieved, greatly improving the efficiency and accuracy of material design.

[0132] A specific embodiment 1 of the present invention is provided below. The specific implementation of each step in this embodiment 1 is described in detail as follows.

[0133] The specific implementation of step S01 is to conduct an orthogonal experimental design of micro-perforated UHPC plates. First, based on the acoustic micro-perforation theory, the range of key structural parameters is determined, and the L9(3 3)Orthogonal array design of the experimental scheme. This step includes calculating the number of experiments required for the orthogonal experiment, determining the parameter levels according to the principle of micro-perforated sound absorption, setting the factor levels of the micro-hole diameter as 0.3 mm, 0.5 mm, and 0.7 mm, the factor levels of the micro-hole spacing as 12.5 mm, 15.6 mm, and 18.7 mm, and the factor levels of the micro-hole perforation rate as 5%, 8%, and 11%. During the parameter setting process, considering the material properties of UHPC, the micro-hole diameter should not be too small, otherwise the processing difficulty will increase; nor should it be too large, otherwise the acoustic damping effect will weaken. This step ensures the reliability and representativeness of the subsequent experimental results through scientific experimental design methods, laying a foundation for optimizing the micro-perforated structure parameters. In the orthogonal experimental design, the number of experiments N is calculated according to the number of factors k and the number of levels s: N = s k , for the design of three factors and three levels, it can be reduced to 9 experiments through the L9 orthogonal array, greatly reducing the experimental workload.

[0134] The specific implementation of step S02 is to prepare micro-perforated UHPC specimens and test their acoustic properties. First, according to the orthogonal experimental design of S01, prepare the UHPC raw materials, including cement, silica fume, quartz sand, water reducer, steel fiber, etc., with weight ratios of 1:0.25:1.1:0.02:0.02 respectively. Use precision drilling equipment to process micro-holes that meet the experimental design on the hardened UHPC board to prepare 9 groups of specimens with different parameters. Then, use an impedance tube device configured according to the ISO 10534-2 standard to measure the acoustic absorption coefficient of each specimen at intervals of 100 Hz in the frequency range of 100 - 5000 Hz. This step uses standard test methods to obtain accurate and reliable acoustic performance data. By analyzing and comparing the sound absorption performance under different parameter combinations, the key factors affecting the sound absorption performance and their interaction relationships are initially determined, providing a data basis for subsequent parameter optimization. The acoustic absorption coefficient is calculated using the following formula:

[0135] α = 1 - |R| 2 ;

[0136] In the formula, α is the acoustic absorption coefficient, and its value range is 0 - 1; R is the complex reflection coefficient, which is calculated from the ratio of the incident sound wave to the reflected sound wave.

[0137] The calculation formula for the complex reflection coefficient R is:

[0138]

[0139] In the formula, H 12 is the transfer function between two measurement points; H i is the transfer function of the incident wave; H ris the transfer function of the reflected wave; k is the wave number, k = 2πf / c; f is the acoustic wave frequency, with the unit of Hertz; c is the speed of sound, which is approximately 343 m / s under standard conditions; x 1 is the distance from the first microphone to the surface of the specimen, with the unit of meter; j is the imaginary unit.

[0140] The specific implementation of step S03 is to analyze the orthogonal test results using a parameter optimization function and determine the optimal microporous structure parameters. This function is based on an optimization strategy that combines the response surface method and the genetic algorithm. First, an analysis of variance is performed on the test data to determine the significance of the influence of each factor on the sound absorption performance, calculate the average sound absorption coefficient of each factor level, and plot the factor-response graph. Then, a second-order polynomial regression model is constructed to characterize the relationship between the parameters and the sound absorption coefficient:

[0141]

[0142] In the formula, α f is the acoustic absorption coefficient at a specific frequency f; x 1 is the normalized micropore diameter factor level; x 2 is the normalized micropore spacing factor level; x 3 is the normalized micropore perforation rate factor level; β 0 is the constant term coefficient; β i is the first-order term coefficient; β ii is the second-order term coefficient; β ij is the interaction term coefficient; ε is the random error term.

[0143] The parameter normalization process uses the following formula:

[0144]

[0145] In the formula, X i is the original parameter value; X i，min is the minimum value of the parameter; X i，max is the maximum value of the parameter. Input the target frequency range parameters (such as the mid-frequency range of 500 - 2000 Hertz) and the application environment type parameters (such as a semi-outdoor environment) into the model, and use an improved genetic algorithm to search for the optimal solution. Set the population size to 50, the crossover probability to 0.8, the mutation probability to 0.1, and the number of iterations to 100. During the optimization process using the genetic algorithm, the fitness function is defined as:

[0146]

[0147] In the formula, F is the comprehensive fitness value; is the acoustic absorption coefficient at frequency f i ; w i is the acoustic absorption coefficient at frequency f iThe weight coefficient at; n is the number of evaluation frequency points. According to the optimization results, it is determined that the preferred factor level of the micropore diameter is 0.5 mm, the preferred factor level of the micropore spacing is 15.6 mm, and the preferred factor level of the micropore perforation rate is 8%. Based on this, a standard microperforated UHPC board substrate is prepared.

[0148] The specific implementation manner of step S04 is the same as the foregoing, and will not be elaborated here.

[0149] The specific implementation manner of step S05 is to use a pre-trained prediction model for the performance of microperforated sound-absorbing materials to predict and determine the optimal backing material and thickness. This model is based on a graph neural network and a convolutional neural network architecture, and inputs the micropore diameter (0.5 mm), micropore spacing (15.6 mm), and micropore perforation rate (8%) parameters determined in step S03, as well as the candidate backing material types (basalt cloth or soluble fiber felt) and thicknesses (in the range of 10 - 50 mm, with an interval of 5 mm). The prediction calculation of the acoustic absorption coefficient is based on an improved combined model of Delany's theory and Maa's theory:

[0150]

[0151] In the formula, α(ω) is the acoustic absorption coefficient at angular frequency ω; Z(ω) is the complex acoustic impedance of the material surface; ρ 0 is the air density; c 0 is the speed of sound in air.

[0152] The complex acoustic impedance Z(ω) is contributed by the microperforated plate and the backing material together:

[0153] Z(ω) = Z mp (ω) + Z b (ω);

[0154] In the formula, Z mp (ω) is the acoustic impedance of the microperforated plate; Z b (ω) is the acoustic impedance of the backing material.

[0155] The acoustic impedance Z mp (ω) of the microperforated plate is calculated based on Maa's theory:

[0156]

[0157] In the formula, p is the micropore perforation rate; η is the air dynamic viscosity; t is the plate thickness; d is the micropore diameter; x is a parameter,

[0158] The evaluation results show that when using basalt cloth with a thickness of 30 mm as the backing material, the average sound absorption coefficient can reach above 0.85 in the frequency range of 250 - 4000 Hz, and the frequency characteristic curve is relatively flat, belonging to the combination with the optimal sound absorption performance in the full frequency band. This step uses deep learning technology to accelerate the material optimization process, avoiding a large number of trial-and-error experiments and improving the design efficiency.

[0159] The specific implementation of step S06 is to perform a nano-scale hydrophobic coating treatment on the surface of the micro-perforated UHPC board substrate. First, sandpaper is used to polish and alcohol is used to clean the surface of the micro-perforated UHPC board substrate to remove impurities and dust. Then, a silane-based hydrophobizing agent, an organic solvent, and nano-silica are mixed in a ratio of 1:20:0.5 to form a coating formulation. Using a low-pressure spraying device, a nano-hydrophobic coating is uniformly applied on the surface of the micro-perforated UHPC board substrate, and the coating thickness is controlled below 0.1 μm to ensure that the micropores are not blocked. After the coating is applied, it is left to stand at room temperature for 24 hours to complete curing. The surface hydrophobicity is confirmed through a contact angle test, and the contact angle of water droplets on the surface after the hydrophobic coating treatment should reach above 140 degrees. At the same time, an air flow resistance test is carried out. The calculation formula for the change rate of permeability before and after the nano-coating treatment is as follows:

[0160]

[0161] In the formula, is the permeability before treatment; is the permeability after treatment. To ensure that the micropore permeability is not affected, ΔK p % should be controlled within the range of -5% to 0%. The permeability is measured through an air flow test device:

[0162]

[0163] In the formula, Q is the volume flow rate; μ is the fluid viscosity; t is the material thickness; A is the test area; ΔP is the pressure difference. This step uses nanotechnology to achieve super-hydrophobicity on the surface of the micro-perforated plate without affecting its acoustic performance, effectively solving the contradiction between the waterproofness and permeability of the sound absorption material.

[0164] The specific implementation of step S07 is the same as the foregoing and will not be elaborated here.

[0165] The specific implementation of step S08 is to conduct high-temperature experimental tests on the integrated composite structure. First, prepare a standard test sample with dimensions of 300×300×thickness in millimeters. Set temperature monitoring points on the sample, located on the surface, in the middle, and on the back respectively. Place the test sample in a resistance high-temperature test furnace, and control the heating process according to the ISO 834 standard fire curve, gradually heating from room temperature to 850°C and maintaining the temperature for 4 hours. During the test, continuously monitor the temperature changes at each monitoring point of the sample, the changes in the surface state, and possible phenomena such as cracking and spalling. After the high-temperature test, cool it naturally to room temperature, and calculate the strength retention rate:

[0166]

[0167] In the formula, R s is the strength retention rate; is the flexural strength at room temperature; is the flexural strength after being treated at 850°C for 4 hours.

[0168] The flexural strength is obtained through a three-point bending test, and the calculation formula is:

[0169]

[0170] In the formula, F is the fracture load; L is the fulcrum span; b is the sample width; h is the sample thickness.

[0171] At the same time, calculate the mass loss rate of the material:

[0172]

[0173] In the formula, M L is the mass loss rate; m before is the mass of the sample before the high-temperature test; m after is the mass of the sample after the high-temperature test. The results show that after the prepared integrated composite structure is maintained at 850°C for 4 hours, the structural integrity is good, there are no obvious cracking and spalling phenomena, the strength retention rate of the flexural strength reaches more than 75% of the original strength, and the mass loss rate is less than 3%. This step verifies the fire resistance of the material through strict high-temperature tests, ensuring that it can still maintain its basic functions and structural safety under extreme conditions.

[0174] The specific implementation of step S09 is to conduct full-performance testing on the integrated composite structure and optimize the prediction model. First, the acoustic absorption coefficient is tested according to ISO 10534-2 standard, with the frequency range of 100 - 5000 Hz. Then, the fire rating test is carried out according to GB8624 standard to evaluate its combustion performance and smoke toxicity. The water resistance test is conducted according to GB / T 23447 standard, including the determination of water absorption rate and strength change rate after 24 hours of immersion. The flexural strength is tested according to GB / T 17671 standard, and the fracture load and fracture mode are recorded. Finally, the weight density of the composite material is measured, and the mass per unit area is calculated. After collecting the complete test data, it is input into the performance prediction model of the micro-perforated sound-absorbing material for comparative analysis, and the error between the predicted result and the measured result is evaluated. The model optimization adopts the Bayesian optimization algorithm, and its objective function is defined as:

[0175]

[0176] In the formula, J(θ) is the loss function; θ is the set of model parameters; N is the number of test samples; w i is the frequency weight coefficient; y i is the measured sound absorption coefficient of the i-th sample; is the sound absorption coefficient predicted by the model; λ is the regularization coefficient; is the L2 norm of the model parameters.

[0177] The calculation formula of the frequency weight coefficient w i is:

[0178]

[0179] In the formula, f i is the i-th frequency point; β is the frequency deviation coefficient. The average relative error is used to evaluate the prediction accuracy of the model:

[0180]

[0181] The prediction accuracy of the updated model has increased by more than 15%, especially in the medium and high frequency bands (1000 - 4000 Hz), and the prediction error has been reduced to within ±5%. This step verifies the comprehensive performance of the final product through comprehensive performance testing and data feedback, and realizes the continuous optimization of the prediction model, forming a virtuous cycle of product development and model improvement.

[0182] The specific implementation of establishing the training dataset during the pre-training process of the performance prediction model for micro-perforated sound-absorbing materials mainly includes four links: data collection, data generation, data processing, and data classification. In the data collection link, the experimental data in the research literature on micro-perforated sound-absorbing materials published in the past decade was systematically sorted out, and parameter information such as the micropore diameter (in the range of 0.2 - 1.5 mm), micropore spacing (in the range of 5 - 30 mm), micropore perforation rate (in the range of 1% - 15%), the type of backing material (a total of 5 typical materials), and the thickness of the backing material (in the range of 5 - 100 mm) was extracted, as well as the measured acoustic absorption coefficient frequency characteristic curve data. A total of 350 effective data points were collected. In the data generation link, a simulation model of the acoustic characteristics of the micro-perforated sound-absorbing structure was established using the finite element analysis software COMSOL Multiphysics. Based on the Delany-Bazley equation as the theoretical basis, within the parameter space of the collected experimental data, 2000 new parameter combinations were generated according to the Latin hypercube sampling strategy. The distribution density function of the sampling points is:

[0183]

[0184] where ρ(x) is the probability density function of the sampling points; V is the hypervolume of the parameter space; d is the dimension of the parameter space; x i，min and x i，max are the minimum and maximum values of the i-th parameter respectively. Then the corresponding acoustic absorption coefficient frequency characteristic curve was calculated to expand the dataset scale and fill the sparse areas of the parameter space. In the data processing link, all data was standardized. The micropore parameters were scaled to the range of 0 - 1 using the min-max normalization method, and the acoustic absorption coefficient curve was denoised and feature-extracted using wavelet transform. The denoising process used the soft threshold function:

[0185]

[0186] where W j，k is the wavelet coefficient; is the wavelet coefficient after threshold processing; λ j is the threshold of the j-th scale, usually taken as where σ is the noise standard deviation and N is the number of data points. Then it was randomly divided into a training set, a validation set, and a test set according to the ratio of 8:1:1. In the data classification link, according to the collected application case information, the data was labeled into three categories: indoor environment, semi-outdoor environment, and full-outdoor environment, and a characteristic sound spectrum and a performance weight matrix were defined for each environment to complete the construction of the multi-dimensional training dataset. This dataset contains the parameter-performance correspondence relationship, the characteristics of different application environments, and the material physical property data, providing a solid data foundation for the comprehensive training of the model.

[0187] In summary, through the fine implementation and scientific calculation of each step, the efficient preparation of the micro-perforated UHPC board fire-resistant, high-temperature-resistant, waterproof, moisture-proof and strong sound-absorbing composite material has been achieved. The organic connection between each step forms a complete technological process and performance optimization system. The combination of orthogonal experimental design and parameter optimization ensures the optimization of the microporous structure; the combination of acoustic theory and deep learning model realizes the accurate prediction of sound absorption performance; the nano-coating technology solves the contradiction between waterproofness and permeability; the high-temperature experiment verifies the excellent fire resistance of the material. The method of Example 1 not only prepares a new composite material with excellent comprehensive performance, but also establishes a systematic design optimization methodology, providing a scientific reference for the development of similar functional materials.

[0188] To better understand and implement the present invention, Example 2 of a specific application scenario of the present invention is provided below: In the design of the new T3 terminal building of a large international airport, the micro-perforated UHPC sound-absorbing composite board of the present invention is used to solve the problem of high-noise environment in the terminal building. The designed daily passenger flow of this terminal building reaches 150,000 person-times, the main hall area is about 85,000 square meters, the floor height is 18 meters, and there are many noisy sound sources inside, including the voices of passengers talking, the sounds of the public address system, the noise of luggage wheels, etc., forming a complex reverberant environment. At the same time, as a public building, there are extremely high requirements for the fire resistance, durability, aesthetics and maintenance cost of the materials.

[0189] According to the acoustic analysis, the design team of the terminal building determines that the target noise control areas are mainly distributed in the ceiling and side wall areas of the main hall, with a total area of about 32,000 square meters. The target acoustic index is that the reverberation time is controlled within 1.8 seconds, the noise level is reduced by 8 - 10 decibels, especially the noisy sounds in the frequency band of 250 - 2000 Hz should be controlled, and the clarity of the public address system should be guaranteed to reach more than 0.65. At the same time, the material must meet the Class A fire protection standard, have a service life of not less than 25 years, and maintain the modern aesthetic style of the terminal building.

[0190] The research team designed and prepared the micro-perforated UHPC sound-absorbing composite board for the terminal building according to the method of the present invention. First, according to the noise spectrum characteristics, orthogonal experiments were carried out to determine the micro-perforation structure parameters, and then the optimal parameter combination was determined through the analysis of the parameter optimization function. As shown in Table 1:

[0191] Table 1 Noise Spectrum Characteristics and Parameter Optimization Results of the Terminal Building

[0192] Frequency band (Hz) Noise sound pressure level (dB) Target sound absorption coefficient Optimized parameters 125-250 82.5 >0.60 Micropore diameter = 0.5 mm 250-500 86.3 >0.75 Micropore spacing = 15.6 mm 500-1000 88.7 >0.85 Perforation rate = 8% 1000-2000 85.4 >0.90 Plate thickness = 12 mm 2000-4000 79.2 >0.80 Backing thickness = 30 mm

[0193] Based on the above parameters, a standard micro-perforated UHPC board substrate was prepared. The concrete mix ratio was cement: silica fume: quartz sand: water reducer: steel fiber = 1: 0.25: 1.1: 0.02: 0.02 (by weight), and the water-cement ratio was controlled at 0.18. The steam curing process was adopted to ensure that the 28-day compressive strength of the concrete reached over 120 MPa. On the hardened concrete board, micro-holes were processed using precision CNC drilling technology, and the diameter accuracy was controlled within ±0.02 mm.

[0194] For the special application environment of the terminal building, the research team conducted a performance comparison experiment on two kinds of backing materials, and the results are shown in Table 2:

[0195] Table 2 Performance Comparison of Backing Materials

[0196] Performance indicators Basalt cloth (30 mm) Soluble fiber felt (30 mm) Mid-frequency sound absorption coefficient (500 - 1000 Hz) 0.89 0.81 High-frequency sound absorption coefficient (1000 - 4000 Hz) 0.92 0.87 Low-frequency sound absorption coefficient (125 - 500 Hz) 0.65 0.73 <![CDATA[Density (kg / m 3 )]]> 120 96 Fire resistance limit (min) >240 >180 Service temperature range (°C) -40～1200 -40～950 Water absorption rate (%) <1.5 <2.2 Cost index 1.0 0.85

[0197] Through comprehensive evaluation, it was determined to use basalt cloth as the backing material, and its excellent high-frequency sound absorption performance and extremely long fire resistance time better meet the requirements of the terminal building. Subsequently, the research team used the micro-perforated sound absorption material performance prediction model to simulate the sound absorption effect of basalt cloth with different thicknesses, and the results are shown in Table 3:

[0198] Table 3 Predicted Sound Absorption Performance of Basalt Cloth with Different Thicknesses

[0199]

[0200] Taking into account the sound absorption performance, material thickness and cost factors, it was determined to use 30-mm-thick basalt cloth as the optimal backing material. Subsequently, nano-hydrophobic treatment was carried out on the surface of the micro-perforated UHPC board. A silane-based nano-hydrophobic agent was used and evenly applied by low-pressure spraying. The coating thickness was controlled at 0.08 microns to ensure that the micro-holes were not blocked. The contact angle of the treated board surface reached 145°, meeting the waterproof requirements, and the increase in air flow resistance was only 2.8%, ensuring the acoustic performance.

[0201] The treated micro-perforated UHPC board and 30-mm-thick basalt cloth were compounded through a high-temperature-resistant epoxy-based binder to form an integral sound absorption board. The size specification of the composite board was 600 mm × 600 mm × 45 mm (including the thickness of the installation clips), and the weight of a single board was about 12.8 kg. It could be installed on the ceiling keel or wall bracket through a special clip system.

[0202] After the composite board was completed, a comprehensive performance test was carried out, and the results are shown in Table 4:

[0203] Table 4 Comprehensive Performance Test Results of Micro-Perforated UHPC Sound Absorption Composite Board

[0204]

[0205] After the installation of the terminal building was completed, an actual acoustic environment test was conducted. The test results showed that the reverberation time in the installation area decreased from the originally designed estimate of 3.2 seconds to 1.68 seconds, the average noise level decreased by 9.5 dB, and the clarity of the public address system reached 0.72. Especially during the peak passenger flow period, the acoustic environment in the terminal building was significantly improved. The passenger satisfaction survey showed that the satisfaction with the acoustic environment increased from 62% before installation to 91%.

[0206] This sound-absorbing composite panel system also exhibits excellent comprehensive performance: The surface adopts a micro-perforated design, eliminating the need for traditional fibrous or porous sound-absorbing materials to be exposed, thus avoiding problems such as fiber shedding and dust accumulation; The UHPC surface can be treated with a variety of colors and textures, perfectly integrating with the overall design style of the terminal building; The nano waterproof treatment on the surface enables the panel to maintain stable performance in high-humidity environments; The panel has almost no risk of damage when accidentally collided, greatly reducing the maintenance cost; It uses a combination of all-inorganic materials, does not contain organic fibers, and completely avoids the risk of toxic gas release during a fire.

[0207] Traditional acoustic treatment solutions for terminal buildings usually adopt a perforated metal plate + glass wool or mineral wool sound-absorbing system. Although it has a certain sound-absorbing effect, it has multiple defects: Fibrous materials are prone to shedding and dust accumulation, becoming potential indoor air pollution sources; Metal plates are prone to deformation, and the surface treatment is prone to oxidation and fading; Organic fibers will produce toxic gases during a fire; Metal plates and sound-absorbing filling materials need to be frequently maintained and replaced, resulting in high operating costs; And in high-humidity environments, materials such as glass wool are prone to moisture absorption and deformation, leading to a decline in sound-absorbing performance.

[0208] In contrast, the micro-perforated UHPC sound-absorbing composite panel system in this Embodiment 2 has achieved multiple technological breakthroughs: It uses the micro-perforation principle to replace traditional porous sound-absorbing materials, eliminating the problem of fiber shedding pollution; The combination of the UHPC matrix and basalt cloth realizes an extremely long service life and extremely high fire resistance; The nano waterproof technology solves the moisture-proof problem of traditional sound-absorbing materials without affecting the sound wave conduction; The overall inorganic material system completely eliminates the risk of toxic gas release; The integrated composite structure design is easy to install and has extremely low maintenance costs. This solution not only meets the stringent acoustic requirements of the terminal building, but also comprehensively improves in terms of safety, durability, and aesthetics, providing a new technical path for acoustic treatment of public buildings.

[0209] It should be noted that the detailed explanations of the variables involved in the present invention are shown in Tables 5 and 6 below.

[0210] Table 5 Variable Explanation Table (First Part)

[0211]

[0212] Table 6 Variable Explanation Table (Second Part)

[0213]

[0214]

[0215] As described above, it is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention.

Claims

1. A method for preparing a fireproof, high temperature, waterproof, moisture-proof and highly sound-absorbing composite material of a micro-perforated UHPC board, characterized in that: include: Conduct orthogonal experimental design of micro-perforated UHPC panels to determine the range of key parameters; Prepare multiple groups of micro-perforated UHPC specimens and measure the acoustic absorption coefficient; The parameter optimization function is used to optimize and analyze the orthogonal experimental design results, determine the optimal microporous structure parameters and prepare the standard microperforated UHPC board matrix; select the backing material and conduct performance comparison experiments; use the pre-trained microperforated sound absorption material performance prediction model to predict the sound absorption performance of different structural combinations, and determine the optimal backing material thickness and composite structure scheme; The substrate surface is waterproofed by using nano-scale hydrophobic coating technology to ensure waterproof and moisture-proof effects while maintaining the microporous permeability of the substrate surface; the substrate and the backing material with the optimal backing material thickness are compounded with an adhesive to form an integrated composite structure; the integrated composite structure is fully tested for performance to obtain the final product.

2. The method for preparing the fireproof, high temperature, waterproof, moisture-proof and highly sound-absorbing composite material of the micro-perforated UHPC board according to claim 1 is characterized in that: In the orthogonal experimental design, the micropore diameter factor levels are set to 0.3 mm, 0.5 mm, and 0.7 mm, the micropore spacing factor levels are set to 12.5 mm, 15.6 mm, and 18.7 mm, and the micropore perforation factor levels are set to 5%, 8%, and 11%.

3. The method for preparing a fireproof, high temperature, waterproof, moisture-proof and highly sound-absorbing composite material of a micro-perforated UHPC board according to claim 2, characterized in that: In the step of preparing multiple groups of micro-perforated UHPC specimens, the impedance tube test method is used to measure the acoustic absorption coefficients of the multiple groups of micro-perforated UHPC specimens at different frequencies, and the parameter combination with the best acoustic performance is analyzed.

4. The method for preparing a fireproof, high temperature, waterproof, moisture-proof and highly sound-absorbing composite material of a micro-perforated UHPC board according to claim 3, characterized in that: The parameter optimization function inputs the micropore diameter factor level, the micropore spacing factor level, the micropore perforation rate factor level, the target frequency range parameter and the application environment type parameter, and the parameter optimization function outputs the optimal micropore structure parameters.

5. The method for preparing a fireproof, high temperature, waterproof, moisture-proof and highly sound-absorbing composite material of a micro-perforated UHPC board according to claim 4, characterized in that: According to the optimal microporous structure parameters, it is determined that the microporous diameter factor level is preferably 0.5 mm, the microporous spacing factor level is preferably 15.6 mm, and the microporous perforation factor level is preferably 8%, and a standard microperforated UHPC board matrix is ​​prepared.

6. The method for preparing a fireproof, high temperature, waterproof, moisture-proof and highly sound-absorbing composite material of a micro-perforated UHPC board according to claim 5, characterized in that: In the step of selecting the backing material, basalt cloth or soluble fiber felt is selected as the backing material, a performance comparison experiment of different backing material thicknesses is carried out, and the frequency characteristic curve of the acoustic absorption coefficient after compounding is measured.

7. The method for preparing a fireproof, high temperature, waterproof, moisture-proof and highly sound-absorbing composite material of a micro-perforated UHPC board according to claim 6, characterized in that: The micro-perforated sound absorbing material performance prediction model inputs the micro-pore diameter factor level, the micro-pore spacing factor level, the micro-pore perforation factor level, the backing material type and the backing material thickness, and the micro-perforated sound absorbing material performance prediction model outputs a predicted acoustic absorption coefficient frequency characteristic curve.

8. The method for preparing a fireproof, high temperature, waterproof, moisture-proof and highly sound-absorbing composite material of a micro-perforated UHPC board according to claim 7, characterized in that: The specific structure of the micro-perforated sound-absorbing material performance prediction model is a micro-perforated sound-absorbing material performance prediction network based on the combination of graph neural network and convolutional neural network, which includes three main modules: material structure feature encoding module, acoustic property prediction module and application environment adaptation module.

9. The method for preparing a fireproof, high temperature, waterproof, moisture-proof and highly sound-absorbing composite material of a micro-perforated UHPC board according to claim 8, characterized in that: The steps of establishing the training data set in the pre-training process of the micro-perforated sound-absorbing material performance prediction model include collecting published research data on micro-perforated sound-absorbing materials, simulating and generating more data points through finite element analysis software to expand the data set, standardizing all data and dividing them into training sets, validation sets and test sets, and classifying and labeling the data according to different application environment type parameters.

10. The method for preparing a fireproof, high temperature resistant, waterproof, moisture resistant and highly sound absorbing composite material of a micro-perforated UHPC board according to claim 9, characterized in that: The full performance test includes an acoustic absorption coefficient test, a fire rating test, a water resistance test, a bending strength test and a weight density test.

Images