Fiber reinforced composite material defect repairing equipment and batch repairing method

Abstract

The invention provides repairing equipment for defects of a fiber reinforced composite material and a batch repairing method. The repairing equipment comprises an atmospheric pressure plasma processing module, a to-be-repaired part detection and analysis module of the to-be-repaired fiber reinforced composite material, a repairing data monitoring and information flow module, a post-repairing detection module and a repairing operation process planning module. The invention also discloses a batch repair method based on the repair equipment, which comprises the following steps: constructing a repair sample data set, and constructing and training a composite material repair machine learning model by using a machine learning method; on the basis of a machine learning model and repair data, personalized repair processes and parameters are generated, batch repair is carried out, and model updating iteration is continuously carried out. By establishing batch repairing equipment and combining automatic transmission and precise process control, a plurality of samples can be repaired at the same time, and the repairing efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the field of fiber - reinforced composite materials, and particularly relates to a repair device for defects of fiber - reinforced composite materials and a batch repair method. Background Art

[0002] Fiber - reinforced composite materials are widely used in fields such as aerospace, energy and power, electronics and electrical appliances, biomedicine, etc. due to their excellent performance, and have become key basic materials for lightweight and functional components. However, surface defects will inevitably occur during the production, manufacturing or use of fiber - reinforced composite materials. Therefore, the surface repair of fiber - reinforced composite materials is a key technology to ensure the stable performance of composite materials.

[0003] Currently, the main surface repairs rely on manual grinding, sandblasting, and chemical treatment. There are also some existing technologies that use auxiliary technologies for repair. For example, Chinese invention patent CN116749561A discloses a method for repairing carbon fiber composite materials under microwave plasma surface treatment. The technical solution of this patent washes and dries the carbon fiber composite material to be repaired, places it on the workbench of the microwave plasma device, uses air as the plasma gas in an atmospheric pressure environment, makes the workbench move reciprocally to clean the area to be repaired, pastes T800 prepreg on the area to be repaired, and cures it by microwave to complete the repair. Although this method restores the mechanical properties of carbon fiber composite materials to a certain extent, there is still a certain degree of non - uniformity in the repair materials when using the method of impregnating and curing. At the same time, due to the diversity of composite material components, processes, structures, and defects, targeted repair cannot be carried out. In addition, the repair efficiency of this method is low. With the development of repair technology towards low - cost, green, and rapid directions, the existing technology has been difficult to meet the actual needs. Summary of the Invention

[0004] The purpose of the present invention is to overcome the defects of the above - mentioned existing technologies and provide an intelligent repair device for fiber - reinforced composite materials and a high - throughput repair method.

[0005] One aspect of the present invention provides a repair device for defects of fiber - reinforced composite materials. The device includes a main body module: an atmospheric pressure plasma treatment module, a detection and analysis module for the part to be repaired of the fiber - reinforced composite material to be repaired, a repair data monitoring and information flow module, a post - repair detection module, and a repair operation process planning module.

[0006] The atmospheric pressure plasma treatment module is used for cleaning, activation treatment, and depositing polymers for repair; The detection and analysis module for the part to be repaired can scan and analyze the surface of the fiber - reinforced composite material to be repaired and obtain defect morphology data for initial defect morphology classification; The post - repair detection module can scan and analyze the surface of the repaired fiber - reinforced composite material, and obtain inspection and test data for classifying the defect repair status. The repair data monitoring and information flow module is used to monitor the repair process of the fiber - reinforced composite material to be repaired, record and transmit the spatio - temporal data during the repair process, and confirm and adjust the parameters adopted by the atmospheric pressure plasma treatment module. The repair operation process planning module is used to call the information in other modules, plan and regulate the specific operation steps of the atmospheric pressure plasma treatment module during the repair process, and output the repair parameters.

[0007] Further, the atmospheric pressure plasma treatment module in the repair equipment for fiber - reinforced composite material defects includes a discharge gas release unit, an organosilicon monomer supply unit, a flow control unit, a heating unit, and a power supply system; the flow control unit can control the volume ratio of the discharge gas released by the discharge gas release unit to the organosilicon provided by the organosilicon supply unit to be 1:0.01 - 1:0.1.

[0008] Further, the heating unit can provide a heating temperature of 60°C - 150°C for the fiber - reinforced composite material.

[0009] Further, the discharge gas release unit can release one of argon, nitrogen, and air.

[0010] Further, the organosilicon monomer supply unit can provide organosilane monomers, which are selected from one of alkoxysilanes, chlorosilanes, aminosilanes, epoxy - silanes, and vinylsilanes.

[0011] Further, the power supply system is used to provide stable and compliant electrical energy for the discharge gas release unit so that it can ionize the gas to generate plasma.

[0012] Further, the above - mentioned repair equipment for fiber - reinforced composite material defects further includes a post - treatment module, and the post - treatment module is used to perform heating and polishing treatments on the repaired fiber - reinforced composite material.

[0013] Another aspect of the present invention provides a batch repair method for fiber - reinforced composite material defects, which includes the following steps: S1) Set up the above - mentioned repair equipment for fiber - reinforced composite material defects; S2) Conduct repair tests through the above - mentioned repair equipment for fiber - reinforced composite material defects, and collect the test data in the repair tests; construct a repair sample data set through the test data; S3) Based on the repair sample data set, use machine learning methods to construct and train a machine learning model for composite material repair. S4) Based on the repaired machine learning model obtained in step S3), as well as the data obtained in real time by the detection and analysis module for the part to be repaired, the repair data monitoring and information flow module, and the repair operation process planning module, generate a personalized repair process and parameters for repairing the defects of fiber-reinforced composites. Through the repair data monitoring and information flow module, call the atmospheric pressure plasma treatment module to batch repair fiber-reinforced composites; S5) Collect the data in the detection and analysis module for the part to be repaired, the repair data monitoring and information flow module, the post-repair detection module, and the repair operation process planning module during the repair process, and add this data to the repair database for updating and iterating the repaired machine learning model.

[0014] The repair test in step S2) includes the following steps: Place the fiber-reinforced composite to be repaired under the atmospheric pressure plasma jet for treatment, where the atmospheric pressure plasma is generated by a discharge gas and an organosilicon monomer, and the volume ratio of the discharge gas to the organosilicon monomer is 1:0.01 - 1:0.1; After treatment under the atmospheric pressure plasma jet, perform a post-treatment step, and the post-treatment is heating.

[0015] The organosilicon monomer is one of alkoxysilane, chlorosilane, aminosilane, epoxy silane, vinyl silane; The organosilicon monomer is selected from one of alkoxysilane, chlorosilane, aminosilane, epoxy silane, vinyl silane; The discharge gas is selected from one of argon, nitrogen, and air.

[0016] Before placing the fiber-reinforced composite to be repaired under the atmospheric pressure plasma jet for treatment, a pretreatment step is also included, and the pretreatment is to clean and activate the fiber-reinforced composite to be repaired; After repair, a polishing treatment is also included.

[0017] Further, the type of fiber in the fiber-reinforced composite is one of glass fiber, basalt fiber, carbon fiber, aramid fiber, polyimide fiber, and polyarylate fiber.

[0018] Further, the type of resin in the fiber-reinforced composite is one of unsaturated polyester resin, epoxy resin, phenolic resin, and silicone resin.

[0019] Beneficial effects The present invention uses atmospheric pressure plasma generated by discharge gas and organosilicon monomers to deposit polymers. By chemically bonding the organosilicon polymer with the resin matrix at a certain temperature, the composite of the organosilicon polymer and the resin is achieved, significantly shortening the repair time and improving the efficiency. There is no need for vacuum equipment and a large amount of reagents, and the reaction is carried out in an open environment, reducing energy consumption, pollution and equipment maintenance costs. It is suitable for a variety of composite materials, and effective repair can be achieved by adjusting parameters, thus broadening the application fields.

[0020] By constructing batch repair equipment and combining automated transmission with precise process control, the present invention can repair multiple samples simultaneously, increasing the repair output.

[0021] In addition, the methods and equipment of the present invention are based on learning from a large amount of sample data. According to the composite materials and defect conditions, personalized repair plans are accurately generated to improve the success rate. The repair process is monitored in real time, the quality is predicted by comparing historical data, and the process is adjusted in a timely manner to ensure product quality and reduce the scrap rate. It is continuously optimized with the accumulation of data to explore new repair rules and methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a schematic flow chart of the method for batch repairing defects of fiber-reinforced composite materials according to the present invention.

[0023] Figure 2 It is a microscope photo of a fiber-reinforced composite material with surface defects.

[0024] Figure 3 It is a microscope photo of a fiber-reinforced composite material after high-throughput repair. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] Now, various exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be noted that: unless otherwise specifically stated, the relative arrangements, numerical expressions and numerical values of the components and steps set forth in these embodiments do not limit the scope of the present invention. The description of at least one exemplary embodiment below is actually only illustrative and in no way limits the present invention and its application or use.

[0026] Technologies, methods and equipment known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the said technologies, methods and equipment should be regarded as part of the specification. In all the examples shown and discussed here, any specific value should be construed as merely exemplary and not as a limitation. Therefore, other examples of the exemplary embodiments may have different values.

[0027] The object of the present invention is to provide an intelligent repair device for fiber - reinforced composites and a high - throughput repair method, which combines atmospheric pressure plasma technology and machine learning to provide a low - cost, automated, green, fast, and personalized repair method for fiber - reinforced composites. It can batch and specifically repair different types of defects in fiber - reinforced composites, with a fast repair rate and being green and pollution - free. It solves the problems in the prior art that the repair equipment for fiber - reinforced composites is complex, requires vacuum pressurization, and cannot be batch - processed and personalized.

[0028] Specifically, as combined with Figure 1 shown, the method for batch - repairing defects in fiber - reinforced composites provided by the present invention includes the following steps: Step S1) Set up the repair equipment; The repair equipment is based on atmospheric pressure plasma technology, and uses the reaction of silane monomer materials and discharge gases to generate organosilicon polymers to achieve the repair of defects in fiber - reinforced composites.

[0029] The repair equipment includes: an atmospheric pressure plasma treatment module, a detection and analysis module for the part to be repaired of the fiber - reinforced composite to be repaired, a repair data monitoring and information flow module, a post - repair detection module, and a repair operation process planning module.

[0030] Among them, the atmospheric pressure plasma treatment module repairs by cleaning, activating, and depositing polymers; it includes a discharge gas release unit, an organosilicon monomer supply unit, a flow control unit, a heating module, and a power system. This device generates atmospheric pressure plasma by mixing discharge gases and organosilicon monomers in a specific ratio, where the gas ratio is controlled at 1:0.01 - 1:0.1. The discharge gas can be selected from argon, nitrogen, and air, and the organosilane monomer is selected from one of alkoxysilane, chlorosilane, aminosilane, epoxy - silane, and vinylsilane.

[0031] The heating unit can provide a temperature for heating the fiber - reinforced composite to 60°C - 150°C.

[0032] All operating parameters of the atmospheric pressure plasma treatment module are regulated by the repair operation process planning module. At the same time, the operating parameters involved in the atmospheric pressure plasma treatment module are recorded and transmitted through the repair data monitoring and information flow module.

[0033] In a specific embodiment, the repair equipment further includes a post - treatment module.

[0034] In a specific embodiment, the operating parameters include the regulation of the working voltage of the atmospheric pressure plasma treatment module, the flow rate of the discharge gas, the flow rate of the organosilicon monomer, as well as the control of the distance between the atmospheric pressure plasma and the surface of the material to be repaired, and the heating temperature of the heating unit.

[0035] The module for detecting and analyzing the part to be repaired is used for scanning and analyzing the surface of the fiber-reinforced composite material to be repaired; the module for detecting and analyzing the part to be repaired includes a detection module and an analysis module. The detection module is used for collecting data on the surface defects of the fiber-reinforced composite material to be repaired, and the detection module is selected from visual imaging elements. The analysis module is used for analyzing the data obtained by the detection module to obtain the types, sizes, shapes, and depths of the surface defects of the fiber-reinforced composite material to be repaired, and at the same time, the data obtained by detection and analysis is transmitted to the repair operation process planning module through the repair data monitoring and information flow module.

[0036] In a specific embodiment, the imaging element can be a high-resolution optical imaging unit, which can accurately image the surface of the material, obtain visual data such as the macroscopic morphology information of the material surface, and identify obvious damage areas, crack directions, etc.

[0037] In a specific embodiment, the imaging element uses the OPT - SC series cameras produced by Guangdong Opto Technology Co., Ltd. This camera is equipped with an image sensor for converting optical signals into digital image signals. At the same time, with the SciVision vision development package, image processing and analysis can be realized. To improve the imaging effect, a supplementary light source can also be equipped to provide uniform and sufficient light for the shooting scene. The intelligent optical component also plays a key role in the imaging process. It is mainly composed of a laser sensor and an optical lens. Among them, the laser sensor is used to assist in measuring information such as the distance and shape of the target object, providing additional data support for image analysis; the optical lens is responsible for focusing light to ensure that the image is clearly and accurately projected onto the image sensor of the camera.

[0038] The post-repair detection module is used for scanning and analyzing the surface of the fiber-reinforced composite material after repair to obtain inspection and detection data; the post-repair detection module includes a detection module and an analysis module. The detection module is used for collecting data on the fiber-reinforced composite material after repair, and the detection module is selected from imaging elements. The analysis module is used for analyzing the data obtained by the detection module to obtain the repair situation of the surface defects of the fiber-reinforced composite material after repair, and at the same time, the data obtained by detection and analysis is transmitted to the repair operation process planning module through the repair data monitoring and information flow module.

[0039] In a specific embodiment, the repair device includes a post-treatment module, and the post-repair detection module is used to detect the repaired fiber-reinforced composite material that has been post-treated by the post-treatment module.

[0040] In a specific embodiment, the repair device does not include a post-treatment module, and the post-repair detection module is used to detect the repaired fiber-reinforced composite material that has been treated by the atmospheric pressure plasma treatment module.

[0041] The repair data monitoring and information flow module monitors the process of the fiber-reinforced composite material to be repaired, and confirms and adjusts the operating parameters applied by the atmospheric pressure plasma treatment module; In a specific embodiment, monitoring the repair process of the fiber-reinforced composite material to be repaired is to monitor the operating parameters adopted by the atmospheric pressure plasma treatment module during the repair process. The operating parameters include the regulation of the working voltage, discharge gas flow rate, and organosilicon monomer flow rate of the atmospheric pressure plasma treatment module, as well as the control of the distance between the atmospheric pressure plasma and the surface of the material to be repaired, etc.

[0042] For example, flow meters for monitoring the flow rates of discharge gas and organosilicon monomer, voltage sensors for measuring the working voltage, and distance sensors for obtaining the distance between the atmospheric pressure plasma and the surface of the material to be repaired can be used to continuously collect corresponding data information.

[0043] In a specific embodiment, the method for confirming and adjusting the operating parameters adopted by the atmospheric pressure plasma treatment module is manual setting.

[0044] In a specific embodiment, the method for confirming and adjusting the operating parameters adopted by the atmospheric pressure plasma treatment module is real-time regulation through a model obtained by machine learning.

[0045] Specifically, based on the real-time data obtained by the repair data monitoring and information flow module and the detection and analysis module for the part to be repaired, such as the real-time data of the defect type, size, etc. obtained by analysis, is transmitted into the machine learning model. When receiving the real-time data, the model uses the trained algorithm to analyze and calculate the optimal operating parameters of the atmospheric pressure plasma treatment module under the current working conditions, such as the working voltage, discharge gas flow rate, organosilicon monomer flow rate, and the distance between the nozzle and the material to be repaired, etc., and then automatically issues instructions to precisely regulate the relevant regulating components to ensure that the device is always in the best operating state and achieve efficient repair of the fiber-reinforced composite material.

[0046] The repair operation process planning module is used to call the information in other modules to plan and regulate the specific operation steps of the atmospheric pressure plasma treatment module during the repair process.

[0047] Specifically, the repair operation process planning module calls the data monitored and obtained in the repair data monitoring and information flow module to plan and regulate the specific operation steps of the atmospheric pressure plasma processing module during the repair process. For example, it regulates the opening and closing times of the discharge gas release unit and the organosilicon monomer supply unit in the atmospheric pressure plasma processing module, as well as the opening and closing times of the atmospheric pressure plasma processing module.

[0048] To further optimize the repair effect, a post-processing module can be added. In a specific embodiment, the post-processing module is a polishing device, which includes a connecting rod, a polishing pad, and a moving component. The moving component drives the connecting rod to move to the repair area, and the polishing pad fixed on the connecting rod polishes the surface of the fiber-reinforced composite material.

[0049] S2) Conduct repair tests using the above-mentioned repair equipment for fiber-reinforced composite material defects, and collect the test data in the repair tests; construct a repair sample data set with the test data; the repair sample data set supports multiple data types and multi-source data access; The multiple data types include structured data, unstructured data, multi-dimensional spatio-temporal data, and real-time stream data; In some specific embodiments, the structured data includes the parameter setting records recorded by the repair equipment for fiber-reinforced composite material defects during the experiment, such as the repair duration, repair parameters, and the data obtained after analog-to-digital conversion and data collation of the data collected by the detection and analysis module for the part to be repaired.

[0050] The unstructured data includes visual information such as images collected before, during, and after the repair, and can also include text information such as the records and descriptions made by the test personnel during the test process.

[0051] The multi-dimensional spatio-temporal data includes the state change data of the fiber-reinforced composite material to be repaired at different stages of the repair.

[0052] The real-time stream data includes the data continuously generated during the operation of the equipment. The sensors of the repair equipment continuously collect physical quantities such as temperature and flow rate, and transmit them in the form of a continuous data stream to continuously reflect the current state of the equipment.

[0053] The multi-source data access is achieved through different interfaces. The multi-source data can include the data set by and collected from the repair equipment itself, and the test data is transmitted through the data connection of different components. The simulation software outputs the simulation data in a preset format through a specific data export function. After various data sources are accessed, they are integrated into the repair sample data set after preprocessing steps such as data cleaning and format conversion.

[0054] The repair test includes the following steps: Preprocess the fiber-reinforced composite material to be repaired by cleaning and activation treatment; Place the fiber-reinforced composite material to be repaired under an atmospheric pressure plasma jet for treatment, where the atmospheric pressure plasma is generated by a discharge gas and a silicone monomer, and the volume ratio of the discharge gas to the silicone monomer is 1:0.01 - 1:0.1; The silicone monomer is selected from one of alkoxysilane, chlorosilane, aminosilane, epoxy silane, vinyl silane; The discharge gas is selected from one of argon, nitrogen, air.

[0055] After treatment under the atmospheric pressure plasma jet, a post-treatment step is carried out. The post-treatment is heating, and the heating temperature is 60 - 150 °C, with the specific temperature being the heating temperature at which the color of the repaired fiber-reinforced composite material begins to change. Heating is an indispensable step for repair, which can make the repair materials combine tightly and achieve the consistency of the appearance after repair. In addition, polishing treatment can be carried out as needed.

[0056] S3) Based on the repair sample dataset, use machine learning methods to construct and train a machine learning model for composite material repair; The specific process of constructing and training the machine learning model is to use the defect morphology data, repair process data, and inspection and detection data after repair in the repair sample dataset to construct and train the machine learning model.

[0057] It includes the following steps: S301) Data preprocessing: Perform separate preprocessing on different types of data. For defect morphology data, which is visual data, use image recognition technology to extract features.

[0058] For repair process data, use normalization to process different types of data. At the same time, differential processing can also be carried out on the time series repair process data to capture the dynamic features during the repair process.

[0059] In some specific solutions, the sliding window technique can also be used to divide the continuous time series data into windows of a fixed length as the input of the model, so that the model can learn local time series patterns.

[0060] S302) Model training Use the repaired sample data set as the training data set to train the repair model, construct a correspondence model between the operating parameters of the plasma generating device and the spatio-temporal data of the defect morphology, that is, the input is the operating parameters, and the output is the spatio-temporal data of the defect repair morphology, so as to reveal the correspondence between the operating parameters and the defect morphology data, inspection and detection data, and repair process data of the repaired sample data set. According to the characteristics of the data and the requirements of the repair task, select appropriate machine learning algorithms, such as neural networks, random forests, support vector machines, etc., and design the corresponding model structure.

[0061] In some specific embodiments, the operating parameters include the regulation of the working voltage of the atmospheric pressure plasma treatment module, the discharge gas flow rate, the flow rate of the organosilicon monomer, and the control of the distance between the atmospheric pressure plasma and the surface of the material to be repaired. The spatio-temporal data of the defect repair morphology includes the size, shape, and integrity of the defect repair at a certain moment.

[0062] S4) Based on the repaired machine learning model obtained in step S3), as well as the data obtained by the module for detecting and analyzing the part to be repaired and the expected repair target, generate a personalized defect repair process and parameters for the fiber-reinforced composite material, and batch repair the fiber-reinforced composite material by calling the atmospheric pressure plasma treatment module through the repair data monitoring and information flow module; S401) Analyze the fiber-reinforced composite material to be repaired by using the module for detecting and analyzing the part to be repaired to obtain defect morphology data; S402) Obtain the repair process data according to the obtained defect morphology data and the expected repair data, and at the same time batch repair the fiber-reinforced composite material by calling the atmospheric pressure plasma treatment module through the repair data monitoring and information flow module; S5) Collect the data in the module for detecting and analyzing the part to be repaired, the repair data monitoring and information flow module, the post-repair detection module, and the repair operation process planning module during the repair process, and add this data to the repair database for updating and iterating the repaired machine learning model.

[0063] It includes S501) Real-time multi-module data collection. At different stages of the repair process, use a variety of sensors and data collection interfaces to complete the collection of multi-module data.

[0064] For example, the repair data monitoring and information flow module can monitor environmental parameters, repair equipment parameters, dynamic data of material status, etc., and can also include data of manual intervention events, such as manually adjusting parameters, pausing repair, etc. The environmental parameters can include the temperature and humidity during the repair process, and the repair equipment parameters can include the power of discharge, the flow rate of discharge gas, the flow rate of organosilicon monomer, and the nozzle spacing. The dynamic data of material status can include imaging data, such as regularly taking pictures of the repair area (e.g., once every 5 seconds) using a high-resolution camera to record the defect filling process.

[0065] S502) Preprocessing of data Preprocess the data obtained in S501) through data cleaning, format conversion, spatio-temporal alignment, and feature extraction.

[0066] Data cleaning includes identifying and removing outliers and noise points in the data. For example, for the data collected by a flow sensor, if its value exceeds 20% of the preset threshold range, it is determined as an outlier and corrected or deleted.

[0067] Format conversion is to convert heterogeneous data collected by different modules into a unified format for subsequent storage and analysis.

[0068] Spatio-temporal alignment includes aligning multi-source data according to timestamps and associating them with the spatial coordinates of the repair area.

[0069] Feature extraction includes extracting parameter features related to the input and output of the model from the collected data.

[0070] S503) Model iteration Store the preprocessed data in the repair sample dataset, triggering the update and iteration process of the repair machine learning model: Data loading: Load the latest repair data from the repair sample dataset and merge it with the original repair sample dataset to form a new training dataset.

[0071] Model fine-tuning: Based on the new training dataset, use transfer learning technology to fine-tune the existing repair machine learning model; during the fine-tuning process, fix most of the parameters of the model and only optimize a few parameters related to the repair task to improve the training efficiency of the model, avoid overfitting, and obtain the iteration of the model.

[0072] In some specific embodiments, it further includes a model evaluation step: using the updated and trained model to predict part of the data in the repair database and comparing it with the actual repair results to evaluate the performance of the model. By calculating indicators such as accuracy and mean square error, the prediction accuracy of the model is quantified. If the model evaluation result meets the preset performance requirements, the updated and trained model is deployed to the repair system to replace the original model; if not, the model parameters are further adjusted or the model structure is optimized, and the above training and evaluation processes are repeated until the model performance reaches the standard, completing the model iteration.

[0073] Attached Figure 2 shows the image data collected before the repair of the fiber-reinforced composite material, Figure 3 shows the image data collected only after the repair of the fiber-reinforced composite material. It can be seen by comparison that the method of the present invention can repair the surface defects of the fiber-reinforced composite material.

[0074] The method of the present invention can be used for the surface defect repair of different fiber-reinforced composite materials such as carbon fiber-reinforced composite materials, polyarylate fiber-reinforced composite materials, polyimide fiber-reinforced composite materials, and natural fiber-reinforced composite materials in addition to glass fiber-reinforced composite materials. Fiber-reinforced composite materials are a class of high-performance materials composed of fibers and matrix materials through a specific process. Among them, the reinforcing fibers bear the main load-bearing role, endowing the material with high strength, high modulus and other properties; the matrix material binds the reinforcing fibers together, making the composite material have a certain shape, protecting the fibers from the external environment, and transmitting stress when the material is stressed. The fibers include different fibers such as carbon fibers, glass fibers, natural fibers, and ceramic fibers. And the matrix materials include thermoplastic resin and thermosetting resin matrices, etc.

[0075] In summary, the present invention uses atmospheric pressure plasma technology to repair the surface defects of fiber-reinforced composite materials. Through the chemical bonding of organosilicon polymers and resin matrices, the composite of organosilicon polymers and resins is realized, greatly shortening the repair time and improving the efficiency. And it abandons vacuum equipment and a large number of chemical reagents, reacts in an open environment, reducing energy consumption, pollution and equipment maintenance costs. In terms of application value, machine learning uses deep learning of big data sample data to accurately formulate personalized repair plans according to the characteristics and defect conditions of composite materials, improving the success rate. During the repair process, the data is monitored in real time, compared with historical data to predict the quality, and the process is adjusted in time to ensure the repair quality.

Claims

1. A repair device for defects of fiber-reinforced composite materials, characterized in that, The repair device includes a main body module: an atmospheric pressure plasma processing module, a detection and analysis module for the part to be repaired of the fiber-reinforced composite material to be repaired, a repair data monitoring and information flow module, a post-repair detection module, and a repair operation process planning module; The atmospheric pressure plasma processing module is used for cleaning, activation treatment, and depositing polymers for repair; The detection and analysis module for the part to be repaired can scan and analyze the surface of the fiber-reinforced composite material to be repaired, and obtain defect morphology data for classifying the initial defect morphology; The post-repair detection module can scan and analyze the surface of the fiber-reinforced composite material after repair, and obtain inspection and test data for classifying the defect repair status; The repair data monitoring and information flow module is used for monitoring the repair process of the fiber-reinforced composite material to be repaired, recording and transmitting the spatio-temporal data of the repair process, and confirming and adjusting the parameters adopted by the atmospheric pressure plasma processing module; The repair operation process planning module is used for calling the information in other modules, planning and regulating the specific operation steps of the atmospheric pressure plasma processing module during the repair process, and outputting repair parameters.

2. The repair device according to claim 1, characterized in that, The atmospheric pressure plasma processing module in the repair device includes a discharge gas release unit, an organosilicon monomer supply unit, a flow control unit, a heating unit, and a power supply system; the flow control unit can control the volume ratio of the discharge gas released by the discharge gas release unit to the organosilicon provided by the organosilicon supply unit to be 1:0.01 - 1:0.1; The discharge gas release unit can release one of argon, nitrogen, and air; The organosilicon monomer supply unit can provide organosilane monomers, which are selected from one of alkoxysilanes, chlorosilanes, aminosilanes, epoxy silanes, and vinyl silanes.

3. The repair device according to claim 1, characterized in that, The repair device further includes a pretreatment module, which is used for cleaning and activating the fiber-reinforced composite material to be repaired; The repair device further includes a post-treatment module, which is used for polishing the fiber-reinforced composite material after repair.

4. A batch repair method for defects in fiber-reinforced composite materials, characterized in that, It includes the following steps: S1) Set up the repair device according to any one of claims 1 - 3; S2) Conduct a repair test through the repair device according to any one of claims 1 - 3, and collect the test data in the repair test; Construct a repair sample data set through the test data; S3) Based on the repair sample data set, use machine learning methods to construct and train a machine learning model for composite material repair; S4) Based on the repair machine learning model obtained in step S3), and the data obtained in real time by the detection and analysis module for the part to be repaired, the repair data monitoring and information flow module, and the repair operation process planning module, generate a personalized defect repair process and parameters for repairing the fiber-reinforced composite material, and batch repair the fiber-reinforced composite material by calling the atmospheric pressure plasma processing module through the repair data monitoring and information flow module; S5) Collect the data in the detection and analysis module for the part to be repaired, the repair data monitoring and information flow module, the post-repair detection module, and the repair operation process planning module during the repair process, and add this data to the repair database for updating and iterating the repair machine learning model.

5. The batch repair method according to claim 4, wherein The repair test in step S2) includes the following steps: The fiber-reinforced composite material to be repaired is placed under an atmospheric pressure plasma jet for treatment, where the atmospheric pressure plasma is generated by a discharge gas and a silicone monomer, and the volume ratio of the discharge gas to the silicone monomer is 1:0.01 to 1:0.1; After treatment under the atmospheric pressure plasma jet, a post-treatment step is carried out, and the post-treatment is heating.

6. The batch repair method according to claim 5, wherein The silicone monomer is selected from one of alkoxysilanes, chlorosilanes, aminosilanes, epoxy silanes, vinyl silanes; The discharge gas is selected from one of argon, nitrogen, and air.

7. The batch repair method according to claim 5, characterized in that Before placing the fiber-reinforced composite material to be repaired under the atmospheric pressure plasma jet for treatment, a pre-treatment step is also included, and the pre-treatment is to clean and activate the fiber-reinforced composite material to be repaired; Polishing treatment is also included after repair.

8. The batch repair method according to claim 4, characterized in that, Step S3) includes the following steps: S301) Data preprocessing; S302) Model training The repair model is trained using a repair sample data set as the training data set to construct a correspondence model between the operating parameters of the plasma generating device and the repair spatio-temporal data of the defect morphology; where the input is the operating parameters and the output is the spatio-temporal data of the defect repair morphology.

9. The batch repair method according to claim 4, wherein Step S5) includes the following steps: S501) Multi-module data real-time collection. At different stages of the repair process, with the help of a variety of sensors and data acquisition interfaces, the collection of multi-module data is completed; S502) Preprocessing of data; S503) Model iteration The preprocessed data is stored in the repair sample data set, triggering the update and iteration process of the repair machine learning model; Data loading: Load the latest repair data from the repair sample data set and merge it with the original repair sample data set to form an iterative training data set; Model fine-tuning: Based on the iterative training data set, use transfer learning technology to fine-tune the existing repair machine learning model; during the fine-tuning process, most of the parameters of the model are fixed, and only a few parameters related to the repair task are optimized to improve the training efficiency of the model, avoid overfitting, and obtain the iteration of the model.

10. The batch repair method according to claim 4, wherein The repair sample data set in step S2) supports multiple data types and multi-source data access; the multiple data types include structured data, unstructured data, multi-dimensional spatio-temporal data, and real-time stream data.

Images