Freeze-thaw sensitive composite material optimized printing method based on artificial intelligence

Abstract

The invention provides a freeze-thaw sensitive composite material optimized printing method based on artificial intelligence. The method comprises the steps that rock-soil body performance parameters of an alpine region are obtained; designing freeze-thaw sensitive composite material samples with various formulas and process parameters; performing system mechanical test and freeze-thaw cycle experiment on the sample; establishing an intelligent database containing material components, printing process parameters and material performance data; establishing a material-process-performance mapping relation model, and performing training optimization on the model; the model predicts the performance of the freeze-thaw sensitive composite material under different formulas and process parameters, and recommends an optimal printing parameter combination and a composite material formula; the prediction precision of the recommendation result is verified, and the model is reversely optimized; a real-time monitoring technology is introduced, and an adaptive control strategy is developed; a comprehensive evaluation system is constructed, and an optimal printing scheme is recommended; the method can accurately reproduce the characteristics of the special rock-soil body in the alpine region, improves the printing quality and the material performance stability, and provides an efficient and accurate solution for related fields.

Description

Technical Field

[0001] The present invention relates to the field of special rock and soil materials and 3D printing technology in alpine areas, and in particular to an optimized printing method for freeze-thaw sensitive composite materials based on artificial intelligence. Background Art

[0002] The rock and soil in alpine areas, with its unique physical and mechanical properties, such as significantly low compressive strength, high permeability, and high sensitivity to freeze-thaw cycles, have brought unprecedented challenges to traditional construction and repair projects. Traditionally, the engineering treatment of this type of special rock and soil relies on field tests and empirical judgments, which is not only time-consuming and labor-intensive, but also difficult to accurately simulate and predict the material behavior under actual working conditions. In recent years, with the rapid development of 3D printing technology, its application in civil engineering and materials science has shown great potential, providing unprecedented possibilities for customized construction of complex structures and high-performance materials. However, the direct application of existing 3D printing technology to the simulation and repair of rock and soil in alpine areas still faces many difficulties: the existing printing materials are difficult to reproduce the complex mechanical properties of special rock and soil bodies such as moraine and frozen-thaw clay; the correlation mechanism between printing parameters and material properties is unclear; and there is a lack of dynamic parameter adjustment mechanism under freeze-thaw cycle conditions. In addition, the existing technology mostly uses manual trial and error to adjust the formulation and process parameters of printing materials, which is not only inefficient, but also difficult to achieve precise control of performance. Therefore, developing a 3D printing material and method that can accurately match the characteristics of rock and soil in high-altitude cold regions and has the ability to efficiently and accurately control performance has become an important direction of current research. Summary of the invention

[0003] The purpose of the present invention is to provide a method for preparing 3D printing materials that can accurately match the characteristics of rock and soil in high-cold areas and has efficient and precise control capabilities.

[0004] To achieve the above object, the present invention proposes an optimized printing method for freeze-thaw sensitive composite materials based on artificial intelligence, comprising the following steps: S1: Obtain rock and soil performance data under different conditions in high-altitude cold regions; S2: Based on the properties of the rock mass, freeze-thaw sensitive composite material specimens with various formulations and process parameters are designed, covering different proportions of base material, reinforcement phase and additives. The specimens are prepared using advanced 3D printing technology to ensure the accuracy and repeatability of the preparation process; S3: Obtain performance data of each composite material sample through systematic mechanical testing and freeze-thaw cycle experiments, and analyze the experimental results through image recognition and machine learning technology; S4: Establish an intelligent database containing material composition, printing process parameters and material performance data; S5: Establish a mapping relationship model between materials, processes and performance through the database, and train and optimize the model; S6: Use the trained model to predict the performance of freeze-thaw sensitive composite materials under different formulations and process parameters, and use the optimization algorithm to recommend the optimal printing parameter combination and composite material formulation based on the prediction results; S7: 3D print standardized samples according to the recommended results and verify the prediction accuracy of the recommended results. According to the verification results, reverse optimize the model and iteratively adjust the recommended parameters to improve the prediction accuracy; S8: Introduce real-time monitoring technology and develop adaptive control strategies; S9: Build a comprehensive evaluation system and use multi-objective optimization algorithms to recommend the best printing solution; S10: Through multiple experiments and model adjustments, the prediction accuracy and recommendation ability of the model are continuously optimized; and the uncertainty factors in the experimental process, such as material batch differences and equipment accuracy, are considered, and the model is optimized and improved through robustness testing; S11: The model is connected to the 3D printing device to enable the system to automatically adjust the material formula and process parameters during the 3D printing process to achieve optimal performance, and the system performance and accuracy are regularly evaluated, and necessary iterations and upgrades are performed based on the evaluation results.

[0005] Furthermore, step S1 is specifically as follows: collecting the physical and mechanical parameters of various typical rock and soil bodies in high-altitude cold areas, the physical and mechanical parameters of rock and soil bodies include but are not limited to compressive strength, tensile strength, shear strength, permeability and freeze-thaw cycle durability; based on the influence of environmental factors on the performance of rock and soil bodies, recording performance data under different conditions.

[0006] Furthermore, in step S2, freeze-thaw sensitive composite material samples with various formulations and process parameters are designed using a 3D printing device, wherein the formulations include different proportions of a base material, a reinforcing phase, and an additive.

[0007] Furthermore, in step S3, the mechanical tests include compressive strength tests, tensile strength tests, and shear strength tests, and the failure morphology and stress-strain curves are obtained and recorded to analyze the mechanical properties and failure mechanisms of the samples. By simulating the climatic conditions in high-altitude cold areas, multiple freeze-thaw cycle experiments are performed on the samples to obtain and record the performance changes of the samples during the freeze-thaw cycles, including strength loss and volume changes. Image recognition and machine learning technologies are used to automatically analyze the experimental results to improve the efficiency and accuracy of data processing.

[0008] Furthermore, in steps S4 and S5, big data and cloud computing technologies are used to establish an intelligent database containing material composition, printing process parameters and performance data. Through data mining and analysis, the similarities and differences between materials are identified to provide rich data support for intelligent algorithms. Cluster analysis and association rule mining methods are used to discover the potential relationship between material composition, printing process parameters and performance. Through random forest or neural network algorithms, a mapping relationship model between material-process-performance is learned from the database and established. The model is trained using cross-validation or grid search methods. The model is optimized by adjusting algorithm parameters and increasing training data to improve the prediction accuracy and generalization ability of the model.

[0009] Furthermore, in step S6, the predicted performance results include compressive strength, permeability coefficient, and elastic modulus; based on the predicted results, the genetic algorithm and particle swarm optimization algorithm are used to recommend the optimal printing parameter combination and composite material formula.

[0010] Furthermore, step S7 is specifically as follows: printing standardized samples according to the recommended formula and process parameters, and conducting mechanical tests and freeze-thaw cycle experiments; comparing the experimental results with the predicted results to verify the prediction accuracy and reliability of the recommendation system. According to the experimental results, the model is reversely optimized by adjusting the model parameters and the recommendation strategy; step S7 is iterative, and the model is reversely optimized by continuously verifying and adjusting the recommended parameters until the optimal highest prediction accuracy and recommendation effect are achieved.

[0011] Furthermore, in step S8, a real-time monitoring device is introduced during the 3D printing process to monitor key parameters of the printing material in real time, develop an adaptive control strategy, and automatically adjust printing process parameters according to real-time monitoring data, such as key parameters such as temperature and pressure of the printing material, to ensure the stability and consistency of the printing material; the real-time monitoring device includes an infrared thermal imager and a pressure sensor to monitor key parameters such as temperature and pressure of the printing material in real time.

[0012] Furthermore, in step S9, the performance indicators in the comprehensive evaluation system include compressive strength, permeability coefficient, elastic modulus and number of freeze-thaw cycles; the model uses a multi-objective optimization algorithm to comprehensively consider different performance indicators, and finds the optimal solution that balances multiple objectives through the multi-objective optimization algorithm, thereby recommending the optimal composite material formula and process parameters.

[0013] Furthermore, step S11 is specifically as follows: establishing an integrated framework and interface of the system to achieve seamless connection and data interaction with 3D printing equipment; regularly evaluating the performance and accuracy of the system; performing necessary iterations and upgrades on the system based on the evaluation results and user needs; and at the same time, establishing a continuous technical support and maintenance mechanism to ensure the stable operation and sustainable development of the system.

[0014] Compared with the prior art, the advantages of the present invention are: The present invention can accurately reproduce the complex mechanical properties of special rock and soil bodies in alpine areas. Through multiple experiments and model optimization and adjustment, the correlation mechanism between printing parameters and material properties and the dynamic parameter adjustment mechanism under freeze-thaw cycle conditions are clarified, thereby improving the printing quality and performance stability of composite materials. At the same time, artificial intelligence technology is used to adjust the formula and process parameters of printing materials, thereby improving printing efficiency and accuracy. This provides an efficient and accurate solution for the simulation, repair and engineering application of rock and soil bodies in alpine areas, effectively filling the gap in current technology in this field.

[0015] The present invention establishes a more comprehensive and accurate performance database by experimentally mining the mapping relationship between material composition, printing process parameters and material performance data. At the same time, it combines image recognition and machine learning technology to automatically analyze the experimental results, significantly improving the efficiency and accuracy of data processing.

[0016] The present invention can accurately predict the performance of composite materials under different formulations and process parameters by constructing a database and a model, and also uses an optimization algorithm to recommend the optimal printing parameter combination and composite material formulation, thereby further improving the performance stability and consistency of the composite material.

[0017] The present invention introduces real-time monitoring technology in the 3D printing process, which can monitor key parameters such as temperature and pressure of the printing material in real time, and automatically adjust process parameters such as printing speed, layer thickness, and temperature according to the real-time monitoring data. This adaptive control strategy ensures the stability and consistency of the printing material and improves the printing quality.

[0018] The present invention constructs a comprehensive evaluation system including multiple performance indicators, uses a multi-objective optimization algorithm to comprehensively consider different performance indicators, and recommends the optimal composite material formula and process parameters. This comprehensive evaluation and optimization method makes the performance of the composite material more comprehensive and balanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a schematic diagram of a process flow of an optimized printing method for freeze-thaw sensitive composite materials based on artificial intelligence according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the process framework of the method for optimizing printing of freeze-thaw sensitive composite materials based on artificial intelligence in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be further described below.

[0021] This embodiment proposes an optimized printing method for freeze-thaw sensitive composite materials based on artificial intelligence, such as Figure 1 As shown, the following steps are included: Step 1: Obtain rock and soil performance data under different conditions in alpine areas, specifically: 1.1: In the alpine areas, representative rock and soil samples are collected, covering different types of geological structures and climatic conditions. The samples include sandstone, mudstone, frozen soil, moraine and other types to ensure the comprehensiveness and diversity of the data.

[0022] 1.2: Conduct systematic performance tests on the collected rock and soil samples, including but not limited to compressive strength, tensile strength, shear strength, permeability, elastic modulus, freeze-thaw cycle durability, etc. At the same time, considering the impact of environmental factors such as temperature and humidity on the performance of rock and soil, design and implement a series of experiments to record performance data under different conditions.

[0023] 1.3: Clean, organize and standardize the collected data, remove outliers and duplicate data, and ensure the accuracy and consistency of the data. Store the processed data in a dedicated database to provide a basis for subsequent analysis.

[0024] Step 2: Based on the rock and soil properties, design multiple formulas and process parameters of freeze-thaw sensitive composite material samples, and use 3D printing technology to prepare the samples, specifically: 2.1: Based on existing research and understanding of the composition of rock and soil, design freeze-thaw sensitive composite materials with various formulations; the formulations should cover different proportions of base materials (such as polymers, cement-based materials), reinforcing phases (such as fibers, particles) and additives (such as antifreeze, plasticizers). At the same time, consider the impact of different formulations on printing process parameters and design a reasonable range of printing parameters.

[0025] 2.2: Use a high-precision 3D printer to prepare composite material samples according to the preset process parameters. During the preparation process, key parameters such as printing speed, layer thickness, and temperature should be strictly controlled to ensure the accuracy and repeatability of the samples. At the same time, the prepared samples should be uniquely identified for subsequent experiments and data analysis.

[0026] Step 3: Obtain the performance data of each composite material sample through system mechanical testing and freeze-thaw cycle experiments, and analyze the experimental results through image recognition and machine learning technology; specifically: 3.1: Carry out systematic mechanical tests on the prepared specimens, including compressive strength test, tensile strength test, shear strength test, etc., record the failure morphology and stress-strain curve, and analyze the mechanical properties and failure mechanism of the specimens.

[0027] 3.2: Simulate the climate conditions in high-cold areas and conduct multiple freeze-thaw cycle experiments on the samples. Record the performance changes of the samples during the freeze-thaw cycle, including strength loss, volume change, etc.

[0028] 3.3: Introduce image recognition and machine learning technology to automatically analyze experimental results and improve the efficiency and accuracy of data processing.

[0029] Step 4: Use big data and cloud computing technology to establish an intelligent database containing material composition, printing process parameters and material performance data; the database should support efficient data query, analysis and mining functions, provide rich data support for subsequent intelligent algorithms, and facilitate the identification of similarities and differences between different materials through data mining and analysis techniques. In this embodiment, cluster analysis, association rule mining and other methods can be used to discover the potential relationship between material composition, printing process parameters and performance, providing important reference and basis for subsequent intelligent algorithms.

[0030] Step 5: Establish a mapping relationship model between materials, processes and performance through the database, and train and optimize the model, specifically: 5.1: Select intelligent algorithms such as random forests and neural networks to learn and establish a mapping relationship model between materials, processes and performance from the database; select appropriate algorithms and parameter configurations based on the complexity of the problem and the characteristics of the data; 5.2: Use cross-validation, grid search and other methods to train and optimize the model. Improve the prediction accuracy and generalization ability of the model by adjusting algorithm parameters and increasing training data. At the same time, evaluate and verify the performance of the model to ensure the reliability and stability of the model.

[0031] Step 6: Use the trained model to predict the performance of freeze-thaw sensitive composite materials under different formulations and process parameters, and use the optimization algorithm to recommend the optimal printing parameter combination and composite material formulation based on the prediction results; the prediction results include multiple performance indicators, such as compressive strength, permeability, elastic modulus, etc.; based on the prediction results, use genetic algorithms and particle swarm optimization algorithms to recommend the optimal printing parameter combination and composite material formulation. The recommendation system should comprehensively consider multiple performance indicators and actual application needs to provide reasonable recommendation solutions.

[0032] Step 7: 3D print standardized specimens according to the recommended results, and verify the prediction accuracy of the recommended results through mechanical testing and freeze-thaw cycle experiments. According to the verification results, the reverse optimization model adjusts the parameters. This step is iterative, specifically: 7.1: Print standardized samples according to the formula and process parameters recommended in step 6, and perform mechanical tests and freeze-thaw cycle experiments on the standardized samples, and record the experimental results; 7.2: Compare the experimental results with the prediction results to verify the prediction accuracy and reliability of the recommendation system. According to the verification results, reverse optimize the model and improve the prediction accuracy and recommendation effectiveness by adjusting the model parameters and recommendation strategies.

[0033] 7.3: Repeat the above steps and perform continuous iterative optimization until satisfactory prediction accuracy and recommendation effect are achieved.

[0034] Step 8: Introduce real-time monitoring technology and develop adaptive control strategies; specifically: during the 3D printing process, by introducing real-time monitoring devices such as infrared thermal imagers and pressure sensors, real-time monitoring of key parameters such as temperature and pressure of the printing material can be carried out to ensure the stability and consistency of the printing material; develop adaptive control strategies to automatically adjust process parameters such as printing speed, layer thickness, and temperature according to real-time monitoring data, and realize dynamic optimization and adaptive adjustment of the printing process through feedback control mechanisms.

[0035] Step 9: Construct a comprehensive evaluation system and use a multi-objective optimization algorithm to recommend the optimal printing solution; the evaluation indicators in the comprehensive evaluation system include performance indicators such as compressive strength, permeability coefficient, elastic modulus and freeze-thaw cycles to comprehensively reflect the performance characteristics of composite materials; the model uses a multi-objective optimization algorithm to comprehensively consider the trade-off relationship between different performance indicators, and solves the optimal composite material formula and process parameter combination through the optimization algorithm, so as to recommend the optimal composite material formula and process parameters to meet the needs of practical applications.

[0036] In this embodiment, Figure 2 As shown in the figure, an intelligent database is constructed by integrating experimental data, literature and simulation results. The database covers material formula (such as matrix / reinforcement ratio, additive type), process parameters (printing nozzle temperature, layer thickness, printing speed) and performance indicators (compressive strength, permeability, freeze-thaw cycle durability or thermal stability), and has undergone data cleaning and standardization. Based on this database, a mapping model between printing parameters and material properties is established. Figure 2 As shown in the model diagram, x represents the data set, y is the output result, and the intermediate branch decision tree together constitutes a random forest model. The target mechanical parameters are input, combined with the anytime forest multi-objective optimization algorithm, with the goal of maximizing performance and minimizing cost, and the optimal parameter combination is searched under process constraints. A closed-loop optimization system is formed through experimental verification and feedback iteration, ultimately achieving efficient design and intelligent manufacturing of composite materials.

[0037] Step 10: Continuously optimize the model’s prediction accuracy and recommendation capabilities through multiple experiments and model adjustments. At the same time, consider the uncertainty factors in the experimental process, such as material batch differences, equipment accuracy, etc., analyze the impact of these factors on the model’s prediction accuracy and recommendation effects, and evaluate the model’s stability and reliability under different conditions through robustness testing. Based on the test results, optimize and improve the model to improve its robustness and adaptability.

[0038] Step 11: Connect the model to the 3D printing device to achieve the system's automatic adjustment of material formula and process parameters during the 3D printing process to achieve optimal performance, and regularly evaluate the system's performance and accuracy, and perform necessary iterations and upgrades based on the evaluation results. Specifically: Establish a system integration framework and interface to achieve seamless connection and data interaction with 3D printing equipment; regularly evaluate the system's performance and accuracy; perform necessary iterations and upgrades based on the evaluation results and user needs; introduce new technologies and methods to improve the system's performance and competitiveness, and at the same time, establish a continuous technical support and maintenance mechanism to ensure the system's stable operation and sustainable development.

[0039] The above is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any technician in the relevant technical field, without departing from the scope of the technical solution of the present invention, makes any form of equivalent replacement or modification to the technical solution and technical content disclosed in the present invention, which does not depart from the content of the technical solution of the present invention and still falls within the protection scope of the present invention.

Claims

1. An optimized printing method for freeze-thaw sensitive composite materials based on artificial intelligence, characterized in that: The steps include: S1: Obtain rock and soil performance data under different conditions in high-altitude cold regions; S2: Design freeze-thaw sensitive composite material specimens with various formulations and process parameters based on the properties of the rock mass; S3: Obtain performance data of each composite material sample through systematic mechanical testing and freeze-thaw cycle experiments, and analyze the experimental results through image recognition and machine learning technology; S4: Establish an intelligent database containing material composition, printing process parameters and material performance data; S5: Establish a mapping relationship model between materials, processes and performance through the database, and train and optimize the model; S6: Use the trained model to predict the performance of freeze-thaw sensitive composite materials under different formulations and process parameters, and use the optimization algorithm to recommend the optimal printing parameter combination and composite material formulation based on the prediction results; S7: 3D print standardized samples according to the recommended results and verify the prediction accuracy of the recommended results. According to the verification results, reverse optimize the model and iteratively adjust the recommended parameters; S8: Introduce real-time monitoring technology and develop adaptive control strategies; S9: Build a comprehensive evaluation system and use multi-objective optimization algorithms to recommend the best printing solution; S10: Continuously optimize the prediction accuracy and recommendation ability of the model through multiple experiments and model adjustments; and optimize and improve the model through robustness testing; S11: Connect the model to the 3D printing equipment to enable the system to automatically adjust the material formula and process parameters, and regularly evaluate the system performance and accuracy.

2. The method for optimizing printing of freeze-thaw sensitive composite materials based on artificial intelligence according to claim 1, characterized in that: In step S8, during the 3D printing process, a real-time monitoring device is introduced to monitor the key parameters of the printing material in real time, develop an adaptive control strategy, and automatically adjust the printing process parameters; the real-time monitoring device includes an infrared thermal imager and a pressure sensor.

3. The method for optimizing printing of freeze-thaw sensitive composite materials based on artificial intelligence according to claim 1, characterized in that: In step S9, the performance indicators in the comprehensive evaluation system include compressive strength, permeability coefficient, elastic modulus and number of freeze-thaw cycles; the model uses a multi-objective optimization algorithm to comprehensively consider different performance indicators, thereby recommending the optimal composite material formula and process parameters.

4. The method for optimizing printing of freeze-thaw sensitive composite materials based on artificial intelligence according to claim 1, characterized in that: Step S1 is specifically as follows: collecting the physical and mechanical parameters of various typical rock and soil bodies in high-altitude cold areas, the physical and mechanical parameters of rock and soil bodies include but are not limited to compressive strength, tensile strength, shear strength, permeability and freeze-thaw cycle durability; based on the influence of environmental factors on the performance of rock and soil bodies, recording performance data under different conditions.

5. The method for optimizing printing of freeze-thaw sensitive composite materials based on artificial intelligence according to claim 1, characterized in that: In step S2, freeze-thaw sensitive composite material samples with various formulations and process parameters are designed using a 3D printing device, wherein the formulations include different proportions of a base material, a reinforcing phase, and an additive.

6. The method for optimizing printing of freeze-thaw sensitive composite materials based on artificial intelligence according to claim 1, characterized in that: In step S3, the mechanical tests include compressive strength test, tensile strength test, and shear strength test, and the failure morphology and stress-strain curve are obtained and recorded to analyze the mechanical properties and failure mechanism of the sample; multiple freeze-thaw cycle experiments are carried out on the sample by simulating the climatic conditions in high-altitude cold areas to obtain and record the performance changes of the sample during the freeze-thaw cycle, including strength loss and volume change; and the experimental results are automatically analyzed using image recognition and machine learning technology.

7. The method for optimizing printing of freeze-thaw sensitive composite materials based on artificial intelligence according to claim 1, characterized in that: In steps S4 and S5, cluster analysis and association rule mining methods are used to discover the potential relationship between material composition, printing process parameters and performance. A random forest or neural network algorithm is used to learn and establish a mapping relationship model between material, process and performance from the database. The model is trained using cross-validation or grid search methods, and the model is optimized by adjusting algorithm parameters and increasing training data.

8. The method for optimizing printing of freeze-thaw sensitive composite materials based on artificial intelligence according to claim 1, characterized in that: In step S6, the predicted performance results include compressive strength, permeability coefficient, and elastic modulus; based on the predicted results, the genetic algorithm and particle swarm optimization algorithm are used to recommend the optimal printing parameter combination and composite material formula.

9. The method for optimizing printing of freeze-thaw sensitive composite materials based on artificial intelligence according to claim 1, characterized in that: Step S7 is specifically as follows: printing standardized samples according to the recommended formula and process parameters, and conducting mechanical tests and freeze-thaw cycle experiments; comparing the experimental results with the predicted results to verify the prediction accuracy and reliability of the recommendation system; according to the experimental results, reversely optimizing the model by adjusting the model parameters and the recommendation strategy; step S7 is iteratively performed, and reversely optimizing the model by continuously verifying and adjusting the recommended parameters until the optimal prediction accuracy and recommendation effect are achieved.

10. The method for optimizing printing of freeze-thaw sensitive composite materials based on artificial intelligence according to claim 1, characterized in that: Step S11 is specifically as follows: establishing an integrated framework and interface for the system to achieve seamless connection and data interaction with 3D printing equipment; regularly evaluating the performance and accuracy of the system; iterating and upgrading the system based on the evaluation results and user needs; and at the same time, establishing a continuous technical support and maintenance mechanism to ensure the stable operation and sustainable development of the system.

Images