Flame retardation-early warning-damage identification integrated intelligent coating system and construction method thereof

Abstract

The invention provides a flame retardation-early warning-damage identification integrated intelligent coating system and a construction method thereof, and belongs to the technical field of high-end equipment intelligent protection and structure health monitoring. Through collaborative design, functional components such as HEA and VS copolymer matrixes, thermoelectric filler and piezoelectric filler are integrated, an intelligent recognition system is constructed in combination with a K-means clustering algorithm and a convolutional neural network model, and the integrated function of flame retardance, fire early warning and damage recognition is achieved. According to the principle, the thermoelectric filler in the functional layer senses temperature change to generate a voltage signal, the piezoelectric filler captures a stress signal caused by structural deformation, early fire warning and accurate damage judgment are achieved through intelligent model analysis, and meanwhile flame-retardant components restrain flame spreading through a carbon layer blocking and free radical capturing mechanism. According to the invention, collaborative optimization of safety protection and state monitoring of the high-end equipment structural member is realized, the safety and reliability under complex working conditions are remarkably improved, and a brand new technical scheme is provided for high-end equipment protection.

Description

Technical Field

[0001] This invention belongs to the field of intelligent protection and structural health monitoring technology for high-end equipment, specifically relating to an integrated intelligent coating system for flame retardancy, early warning, and damage identification, and its construction method. Background Technology

[0002] With the rapid development of modern aviation, aerospace, shipbuilding, rail transportation and other industries, various high-end equipment are constantly upgrading towards high speed, large size and intelligence, and their structural safety and reliability have become core elements.

[0003] For example, in the aviation industry, aircraft structural components constantly face extremely complex and harsh environmental challenges during long-term service. On the one hand, critical components such as engine compartments, fuel systems, hydraulic pipelines, and electrical equipment pose a very high risk of fire. Once a fire occurs, it will quickly escalate into a catastrophic accident in the confined environment of a high-altitude cabin. On the other hand, under the complex loads of takeoff and landing cycles, airflow impact, temperature fluctuations, and foreign object impacts, structural materials inevitably develop latent defects such as fatigue cracks, delamination, and impact damage. If these defects are not detected and assessed in time, they will directly threaten structural integrity and lead to catastrophic failure. Statistics show that in recent years, aviation accidents caused by cabin fires and structural damage have accounted for more than 35% of all aviation accidents worldwide, resulting in extremely serious economic losses and social impacts. Therefore, building a structural safety system with active protection, early warning, and real-time monitoring capabilities has become a key technological bottleneck that urgently needs to be overcome in the aviation field.

[0004] Traditional aviation protection technologies have long adopted a "functional separation and independent deployment" model, which involves passive fire protection through flame-retardant coatings, fire detection through independent sensor networks, and damage assessment through periodic non-destructive testing. This fragmented solution has revealed numerous systemic flaws in practical applications. Regarding flame-retardant protection, existing aviation flame-retardant coatings mostly use halogen-based, phosphorus-based, or intumescent flame retardants. While these can slow flame spread to some extent, they are essentially still a "passive response" mechanism, only functioning after a fire has occurred, lacking early detection and proactive warning capabilities. More seriously, traditional flame-retardant coatings may release toxic fumes when decomposing at high temperatures, endangering not only the lives of occupants but also causing secondary damage to sensitive electronic equipment. Furthermore, these coatings have limited functionality and cannot address structural health monitoring needs, resulting in high redundancy in the protection system and high maintenance costs.

[0005] In terms of fire early warning technology, aircraft currently rely primarily on smoke detectors, infrared sensors, and independent temperature sensing units. Smoke detectors suffer from response lag, typically requiring visible smoke from combustion to trigger an alarm, by which time the fire is often difficult to control. While infrared sensors enable non-contact temperature measurement, they are susceptible to interference from other heat sources within the cabin, resulting in a high false alarm rate. Distributed temperature sensing systems require complex wiring networks, which are challenging in compact and weight-sensitive aircraft applications, leading to poor electromagnetic compatibility and interface mismatch between the sensors and the structural body, significantly reducing reliability under long-term vibration. Crucially, these early warning devices are independent of the structural protective coating, not only occupying additional space and load but also failing to achieve functional synergy and data fusion, making it difficult to meet the lightweight and integrated development requirements of modern aviation equipment.

[0006] Structural damage identification technology also faces severe challenges. Currently, the aviation field commonly employs periodic nondestructive testing (NDI) methods, such as ultrasonic C-scanning, X-ray inspection, and eddy current testing. While these methods offer high accuracy, they have inherent limitations: First, the testing cycle is strong, making real-time online monitoring impossible, and damage initiating between tests may continue to expand. Second, the equipment is expensive and the operation complex, requiring the aircraft to be disassembled and stored, resulting in high maintenance costs and low availability. Third, accessibility to complex curved surfaces and concealed areas is poor, making it difficult to achieve full structural coverage inspection. In recent years, structural health monitoring (SHM) technology has emerged, using piezoelectric ceramic (PZT) sensors and fiber Bragg grating (FBG) sensor networks to achieve real-time acquisition of damage signals. However, PZT sensors are brittle and dense, resulting in poor compatibility with lightweight composite material structures; while FBG sensors offer advantages such as resistance to electromagnetic interference and high sensitivity, their demodulation equipment is expensive, and they suffer from strain-temperature cross-sensitivity, with measurement errors exceeding 40% without precise calibration. More importantly, these sensing systems are all "add-on" deployments, requiring bonding to the surface of the structure or pre-embedding inside. This not only alters the original mechanical properties of the structure but also presents the challenge of interface compatibility with the protective coating. The mismatch in modulus and thermal expansion coefficients between the sensor and the coating material can easily lead to interface peeling and signal attenuation, severely restricting their stability and durability during long-term service.

[0007] Faced with the aforementioned technical challenges, the concept of intelligent protection, integrating flame retardant protection, fire early warning, and damage identification functions into a single coating system, has emerged and become a hot topic in international research. However, multifunctional integration is not simply a matter of physically blending different functional materials; its technical implementation faces three core challenges. First, the inherent contradictions between functional materials. Highly efficient flame retardancy typically relies on dense char layer barrier and free radical capture mechanisms, requiring materials to rapidly decompose and cross-link at high temperatures; while sensitive early warning requires functional fillers to respond stably and reversibly output signals under thermal / mechanical stimulation, creating an inherent conflict at the material design level. Second, the complexity of signal recognition and decoupling. Coatings simultaneously endure thermal and mechanical loads in service environments, and thermoelectric and piezoelectric signals are highly susceptible to mutual interference. Extracting effective features from mixed signals and accurately distinguishing between fire heat sources and structural damage sources places extremely high demands on intelligent algorithms. Third, the interface matching and process compatibility issues of multi-layer structures. To achieve functional decoupling, smart coatings often require a multi-layer architecture consisting of a base layer, functional layers, and a surface layer. Differences in curing temperature, solvent compatibility, and shrinkage rate of each layer can lead to interface defects and stress concentration, severely affecting the adhesion and service life of the coating.

[0008] In recent years, the development of nanotechnology has provided new design freedom for multifunctional coatings. Two-dimensional transition metal carbides / nitrides (MXenes) are considered ideal thermistor materials due to their excellent conductivity, thermoelectric conversion efficiency, and mechanical properties; carbon nanotubes (CNTs), with their unique piezoelectric effect and high aspect ratio structure, have shown great potential in stress sensing; and expanded graphite (EG), through rapid expansion at high temperatures to form a "worm-like" carbon layer, has become an important candidate for halogen-free, environmentally friendly flame retardants. However, how to accurately construct these nanofunctional fillers in the same system, achieve spatially ordered distribution, avoid agglomeration and sedimentation, and build stable and efficient cross-scale interfaces remains a key challenge restricting their engineering applications. In addition, existing research mostly focuses on single-function verification and lacks systematic integration solutions. Especially at the level of intelligent algorithms, simple threshold judgments or linear models cannot cope with the strong interference and nonlinear characteristics of the aerospace service environment. There is an urgent need to develop adaptive recognition algorithms based on machine learning to achieve accurate classification and quantitative assessment of fire risks and damage modes.

[0009] In summary, the high-end equipment sector (especially the aerospace field) urgently demands structural safety protection technologies that feature "functional integration, rapid response, intelligent identification, and lightweight systems." However, existing technologies suffer from significant shortcomings in areas such as functional fragmentation, delayed response, poor compatibility, and low levels of intelligence. Developing an intelligent coating that integrates flame retardancy, early warning, and damage identification, and achieving a shift from passive protection to proactive early warning and from periodic inspection to real-time monitoring through collaborative material-structure-algorithm design, is not only a strategic requirement for improving the inherent structural safety of high-end equipment but also a crucial breakthrough for driving the leapfrog development of materials technology in this field. Summary of the Invention

[0010] This invention is made to solve the above problems. Its purpose is to build an integrated intelligent protection solution for next-generation aerospace equipment by integrating innovative component design, multi-layer gradient architecture and intelligent algorithm, and to provide an integrated intelligent coating system for flame retardancy, early warning and damage recognition and its construction method.

[0011] This invention provides a method for constructing an integrated intelligent coating system for flame retardancy, early warning, and damage recognition, characterized by the following steps: S10, mixing, dissolving, and randomly copolymerizing hydroxyethyl acrylate, sodium vinyl sulfonate, and an initiator to obtain a flame retardant coating solution; S20, adding thermoelectric fillers and piezoelectric fillers to the flame retardant coating solution and mixing to obtain a functional coating slurry; S30, coating the functional coating slurry onto a substrate and drying to obtain a functional integrated coating; S40, setting electrodes on the functional integrated coating and electrically connecting them to a signal acquisition module, the signal acquisition module being used to acquire the original electrical signals generated by the functional integrated coating, the original electrical signals including at least the thermoelectric signals generated by the thermoelectric fillers due to temperature changes and the piezoelectric signals generated by the piezoelectric fillers due to the functional integrated coating. S50, construct an intelligent identification module and connect it to the signal acquisition module. The intelligent identification module is configured to: first, receive the raw electrical signal acquired by the signal acquisition module; then, analyze the raw electrical signal through an unsupervised clustering algorithm to establish a baseline of the signal distribution under normal operating conditions and identify signals of abnormal events that deviate from the baseline; finally, perform deep feature extraction and pattern recognition on the signals of abnormal events through a pre-trained deep learning model to distinguish the categories of abnormal events and output the judgment results of fire risk level and / or structural damage type and its corresponding degree; S60, integrate the substrate, functional integrated coating, signal acquisition module and intelligent identification module together as a flame-retardant-early warning-damage identification integrated intelligent coating system.

[0012] The construction method of the flame-retardant-early warning-damage recognition integrated intelligent coating system provided by the present invention may also have the following feature: wherein, in step S10, the molar ratio of hydroxyethyl acrylate to sodium vinyl sulfonate is 1:1.

[0013] The construction method of the flame-retardant-early warning-damage recognition integrated intelligent coating system provided by the present invention may also have the following features: wherein, in step S10, the initiator includes potassium persulfate, and the mixing method is: ultrasonic dispersion at 200W~400W power for 30min~60min, stirring at 600rpm~1500rpm for 60min~120min, and random copolymerization is carried out by water bath heating and reflux at 60℃~70℃ for 4h~6h to carry out free radical copolymerization.

[0014] Preferably, in step S10, the random copolymerization temperature is 65°C and the reaction time is 5 hours. This setting ensures that hydroxyethyl acrylate and sodium vinyl sulfonate monomers are fully polymerized, thereby improving the film-forming properties and flame-retardant properties of the copolymer.

[0015] Preferably, in step S10, the mass of potassium persulfate initiator is 1% to 3% of the mass of hydroxyethyl acrylate and sodium vinyl sulfonate.

[0016] Preferably, in step S10, after random copolymerization, the mixture is further concentrated by vacuum distillation to obtain a flame-retardant coating solution with a mass fraction of 25 wt% of the copolymer of hydroxyethyl acrylate and sodium vinyl sulfonate.

[0017] The construction method of the flame-retardant-early warning-damage recognition integrated intelligent coating system provided by the present invention may also have the following features: wherein, in step S20, the thermoelectric filler includes any one or more of bismuth telluride, MXene nanosheets or modified carbon nanotubes, and the piezoelectric filler includes lead zirconate titanate.

[0018] Preferably, in step S20, the thermoelectric filler is bismuth telluride.

[0019] The construction method of the flame-retardant-early warning-damage recognition integrated intelligent coating system provided by the present invention may also have the following feature: wherein, in step S20, the mass ratio of the copolymer of hydroxyethyl acrylate and sodium vinyl sulfonate, thermoelectric filler and piezoelectric filler is (10~60):(5~15):(8~20).

[0020] The construction method of the flame-retardant-early warning-damage recognition integrated intelligent coating system provided by the present invention may also have the following features: wherein, in step S20, the mixing method is: stirring at 600 rpm to 1500 rpm for 60 min, followed by ultrasonic dispersion for 30 min.

[0021] Preferably, in step S20, the stirring speed during homogenization is 700 rpm, and the ultrasonic power is 250W~300W. This setting ensures that the various functional fillers are evenly distributed in the slurry, avoiding agglomeration.

[0022] The construction method of the flame-retardant-early warning-damage recognition integrated intelligent coating system provided by the present invention may also have the following features: In step S30, the functional integrated coating has a random copolymer generated by copolymerization of hydroxyethyl acrylate and sodium vinyl sulfonate. The random copolymer plays a role in fire conditions through a gas-phase-solid phase synergistic flame-retardant mechanism: In the gas phase, the decomposition products of sodium vinyl sulfonate are used to capture the free radicals required for the combustion chain reaction, thereby providing intrinsic flame retardancy. In the solid phase, hydroxyethyl acrylate is dehydrated at high temperature, absorbs heat and cools down, forming a firmly attached and densely structured carbonized layer. The carbonized layer is used to isolate heat and oxygen, thereby achieving fire protection for the functional integrated coating.

[0023] The construction method of the flame-retardant-early warning-damage recognition integrated intelligent coating system provided by the present invention may also have the following features: wherein, in step S30: the substrate includes any one or more of fabric, foam and fiber-reinforced composite materials, the thickness of the functional integrated coating is controlled to be 0.5μm~100μm, and the drying method is: vacuum drying at 60℃~90℃ for 0.5h~12h.

[0024] Preferably, in step S30, the thickness of the functionally integrated coating is controlled to be 1 μm to 20 μm. This setting ensures the compatibility between the coating and the substrate.

[0025] The construction method of the flame-retardant-early warning-damage recognition integrated intelligent coating system provided by the present invention may also have the following features: wherein, in step S50, the unsupervised clustering algorithm includes the K-means clustering algorithm, and the deep learning model includes a convolutional neural network.

[0026] Preferably, in step S50, the convolutional neural network has 2 convolutional layers, uses 2×2 max pooling, and has 32 fully connected units. This configuration is used to improve the accuracy and response speed of signal recognition.

[0027] This invention also provides an integrated intelligent coating system for flame retardancy, early warning, and damage recognition, characterized by being constructed using the construction method of any of the preceding claims, comprising: a substrate; a functional integrated coating disposed on the substrate, including a flame retardant coating and functional fillers dispersed therein, wherein the flame retardant coating is a random copolymer of hydroxyethyl acrylate and sodium vinyl sulfonate, and the functional fillers include thermoelectric fillers and piezoelectric fillers; a signal acquisition module electrically connected to the functional integrated coating for acquiring raw electrical signals generated by the functional integrated coating; and an intelligent recognition module connected to the signal acquisition module for processing the raw electrical signals to output a determination result of fire risk level and / or structural damage type and its corresponding degree.

[0028] The flame-retardant, early warning, and damage recognition integrated intelligent coating system of this invention achieves integrated functions of flame retardancy, early warning, and damage recognition through the synergistic effect of its various functional components.

[0029] (1) Fire early warning mechanism: When the ambient temperature rises to the threshold (≥250℃), the thermoelectric filler in the functional integrated coating generates carrier migration due to thermal excitation, forming an obvious voltage signal; at the same time, the random copolymer generated by the copolymerization of hydroxyethyl acrylate and sodium vinyl sulfonate begins to decompose, releasing flame retardant components. The signal acquisition module transmits the piezoelectric signal to the intelligent recognition module, which quickly determines the fire risk through K-means clustering algorithm and convolutional neural network, triggering early warning.

[0030] (2) Flame retardant protection mechanism: When a fire occurs, the carbon layer formed by the decomposition of each unit of the copolymer works together to build a dense heat-insulating and flame-retardant barrier, preventing the spread of flames and heat transfer; the sulfonate groups in sodium vinyl sulfonate can capture free radicals, inhibit the combustion chain reaction, and achieve high-efficiency flame retardancy.

[0031] (3) Damage identification mechanism: When the matrix is ​​deformed or cracked, the stress generated acts on the piezoelectric functional filler, causing it to generate a piezoelectric effect and output an electrical signal; the intelligent identification module analyzes the amplitude and frequency changes of the signal through a convolutional neural network model, accurately determines the location and extent of damage, and provides a basis for maintenance decisions.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] (1) Functional integration: It realizes the deep integration of flame retardant, fire early warning and damage identification functions, solves the problem of functional separation of traditional technology, and can complete multiple protection and monitoring without additional equipment, significantly improving the safety guarantee level of aviation structural components.

[0034] (2) Rapid and accurate response: Fire warning response time ≤3s, temperature detection accuracy ±2℃, damage identification accuracy ≥95%, can provide timely warning and quickly determine the damage status in the early stage of fire, and buy valuable time for emergency response.

[0035] (3) Excellent compatibility and durability: The coating is firmly bonded to the substrate of the structural components of high-end equipment, has good resistance to high and low temperatures and damp heat, can adapt to the complex service environment in the aviation field, and has a long service life.

[0036] (4) Simple preparation process: It adopts conventional spraying and dipping processes, requires no special equipment, has low production cost, and the coating thickness is controllable. It is suitable for complex structural parts of different types of high-end equipment and is easy to scale up.

[0037] (5) Wide range of applications: In addition to the aviation field, the technical solution of this invention can also be extended to aerospace, shipbuilding, rail transportation and other fields with high safety protection requirements, which is of great significance to promoting the development of high-end equipment protection technology. Attached Figure Description

[0038] Figure 1 This is an architecture diagram of an integrated intelligent coating system for flame retardancy, early warning, and damage recognition, according to an embodiment of the present invention.

[0039] Figure 2 This is a flowchart illustrating the construction method of the flame-retardant-early warning-damage recognition integrated intelligent coating system according to an embodiment of the present invention.

[0040] Figure 3 These are the infrared test results of the flame-retardant coating solution and functional coating slurry of embodiments of the present invention.

[0041] Figure 4 These are SEM images of sample 1 before and after flame retardant testing in an embodiment of the present invention.

[0042] Figure 5 The heat release rate of the flame retardant test obtained by using a cone calorimeter before and after sample 1 treatment in the embodiments of the present invention is shown.

[0043] Figure 6 These are digital photographs of the residual charcoal in sample 1 and the pure fabric after flame retardant testing in an embodiment of the present invention. Detailed Implementation

[0044] To make the technical means, creative features, objectives and effects of the present invention easy to understand, the following embodiments, in conjunction with the accompanying drawings, specifically illustrate an integrated intelligent coating system for flame retardancy, early warning and damage identification and its construction method.

[0045] Example

[0046] Figure 1 This is an architecture diagram of an integrated intelligent coating system for flame retardancy, early warning, and damage recognition, according to an embodiment of the present invention.

[0047] like Figure 1 As shown, this embodiment provides a flame-retardant-early warning-damage recognition integrated intelligent coating system 100, including a substrate 10, a functional integrated coating 20, a signal acquisition module 30, and an intelligent recognition module 40.

[0048] The matrix 10 is made of any one or more of the following materials commonly used in high-end equipment fields (aviation, aerospace, shipbuilding, rail transportation, etc.): fabrics, foams, and fiber-reinforced composite materials. Among them, fiber-reinforced composite materials include carbon fiber composites, glass fiber composites, and plant fiber composites.

[0049] A functional integrated coating 20 is applied to the substrate 10, with a thickness of 1 μm to 20 μm. The material composition of the functional integrated coating 20 includes a flame-retardant coating and functional fillers dispersed therein. Specifically, the flame-retardant coating is a random copolymer (HEA50-co-VS50) of hydroxyethyl acrylate (HEA) and sodium vinyl sulfonate (VS); the functional fillers include thermoelectric fillers made of bismuth telluride and piezoelectric fillers made of lead zirconate titanate.

[0050] In this embodiment, the random copolymer functions under fire conditions through a gas-solid synergistic flame-retardant mechanism:

[0051] (1) In the gas phase, the decomposition products of sodium vinyl sulfonate (VS) are used to capture free radicals required for the combustion chain reaction, thereby providing intrinsic flame retardancy.

[0052] (2) In the solid phase, hydroxyethyl acrylate (HEA) undergoes high-temperature dehydration and heat absorption to cool down, forming a firmly attached and dense carbonized layer. The carbonized layer is used to isolate heat and oxygen, thereby achieving fire protection for the functional integrated coating.

[0053] The signal acquisition module 30 is electrically connected to the functional integrated coating 20 via electrode 31 and is used to acquire the raw electrical signals generated by the functional integrated coating 20.

[0054] The original electrical signal includes:

[0055] (1) Thermoelectric signals generated by temperature changes in thermoelectric fillers.

[0056] (2) Piezoelectric signals generated by the structural deformation of the functional integrated coating 20 due to the piezoelectric filler.

[0057] The intelligent recognition module 40 is connected to the signal acquisition module 30 and includes an unsupervised clustering unit 41 and a deep learning model 42.

[0058] The unsupervised clustering unit 41 is based on the K-means clustering algorithm and is used to perform real-time unsupervised clustering analysis on the original electrical signal to establish and dynamically update the baseline of the signal distribution under normal operating conditions, and to initially identify signals of abnormal events that deviate from the aforementioned baseline.

[0059] The deep learning model 42 is based on a pre-trained deep learning model (specifically a convolutional neural network in this embodiment) and is used to perform deep feature extraction and pattern recognition on the signals of abnormal events after the background signals have been identified and filtered out by the unsupervised clustering unit 41, thereby distinguishing the categories of abnormal events and outputting the judgment results of fire risk level and / or structural damage type and their corresponding degree.

[0060] Figure 2This is a flowchart illustrating the construction method of the flame-retardant-early warning-damage recognition integrated intelligent coating system according to an embodiment of the present invention.

[0061] like Figure 2 As shown, the construction method of the flame-retardant-early warning-damage recognition integrated intelligent coating system 100 in this embodiment includes the following steps:

[0062] S10, Prepare the flame-retardant coating solution, including the following sub-steps S11~S13:

[0063] S11, weigh 0.1 mol of hydroxyethyl acrylate (HEA) and 0.1 mol of sodium vinyl sulfonate (VS), add 100 mL of deionized water, and ultrasonically disperse at 200 W to 400 W for 30 min to 60 min, and stir at 600 rpm to 1500 rpm for 60 min to 120 min until completely dissolved.

[0064] S12, add 2g of potassium persulfate initiator, heat to 65℃ and reflux in a water bath for 5h to carry out free radical copolymerization.

[0065] S13, concentrated by vacuum distillation to a mass concentration of 25 wt%, yielded an aqueous solution of a copolymer of hydroxyethyl acrylate and sodium vinyl sulfonate (HEA50-co-VS50). This solution was used as a flame-retardant coating solution, and its infrared test results are as follows: Figure 3 As shown.

[0066] S20, preparing the functional coating slurry, including the following sub-steps S21~S23:

[0067] S21, 19g of lead zirconate titanate was dried in a vacuum drying oven at 80℃ for 12h, and 12g of bismuth telluride was dried in a vacuum drying oven at 80℃ for 12h.

[0068] S22, take 50g of flame retardant coating solution, add 3g of film-forming aid (specifically dodecyl alcohol ester in this embodiment), and stir at 400r / min for 30min.

[0069] S23, Take 30g of the flame-retardant coating solution treated in step S22, add 6g of lead zirconate titanate (as a piezoelectric filler) and 4g of bismuth telluride (as a thermoelectric filler) treated in step S21, stir at 700rpm for 60min, and ultrasonically disperse at 280W for 30min to obtain the functional coating slurry. Its infrared test results are as follows: Figure 3 As shown.

[0070] S30, a functional coating slurry is coated on the substrate 10 to obtain a functional integrated coating 20 with a thickness of 0.5μm~100μm, specifically in this embodiment:

[0071] (1) When the substrate 10 is a fabric (in this embodiment, linen fabric is specifically selected), the processing method is as follows:

[0072] The substrate 10 is cut to the required size and immersed in the functional coating slurry for 5 min to 100 min. It is then removed and placed in a vacuum oven at 60℃ to 90℃ for 1 h to 12 h to obtain the functional integrated coating 20, which is designated as sample 1.

[0073] A flame retardancy test was conducted on the entire substrate 10 with the functional integrated coating 20 applied under this condition. The morphological distribution before and after the flame retardant treatment is as follows: Figure 4 As shown, the prepared coating has been successfully adhered to the fabric surface.

[0074] Heat release situation as follows Figure 5 As shown, the peak heat release rate of the treated fabric is 15% lower than that of the pure sample, indicating a significant reduction in heat release rate.

[0075] Figure 6 These are digital photographs of the residual charcoal in sample 1 and the pure fabric after flame retardant testing in an embodiment of the present invention.

[0076] like Figure 6 As shown, the flame-retardant treated fabric still retains a relatively intact structure and mass after the combustion test, while the untreated fabric is completely burned.

[0077] (2) When the substrate 10 is foam (polyurethane foam is specifically selected in this embodiment), the treatment method is as follows:

[0078] The substrate 10 is cut to the required size and immersed in the functional coating slurry for 5 min to 100 min. It is then removed and placed in an empty oven at 60℃ to 90℃ for 1 h to 12 h to obtain the functional integrated coating 20, which is designated as sample 2.

[0079] (3) When the matrix 10 is an aerospace structural component (fiber-reinforced composite material), the specific operation is as follows:

[0080] A functional coating slurry was applied to the substrate 10 using a spraying process at a pressure of 0.3 MPa to 0.5 MPa. The substrate was then placed in a vacuum oven and dried at 80°C for 4 hours to obtain a functional integrated coating 20, which was designated as sample 3.

[0081] S40, Set electrode 31, the specific operation is as follows:

[0082] Electrodes 31 with a spacing of 2mm to 10mm are adhered to the surface of the functionally integrated coating 20 and electrically connected to the signal acquisition module 30. The signal acquisition module 30 is used to acquire the raw electrical signals generated by the functionally integrated coating 20.

[0083] Specifically in this embodiment: the spacing between the electrodes 31 on the surface of sample 1 is 6 mm, and the spacing between the electrodes 31 on the surface of sample 2 is 3 mm.

[0084] S50, construct the intelligent recognition module 40 and connect it to the signal acquisition module 30. The intelligent recognition module 40 is configured to perform the following steps S51~S53:

[0085] S51 receives the raw electrical signal acquired by the signal acquisition module 30.

[0086] S52 uses the K-means clustering algorithm to analyze the original electrical signal, thereby establishing a baseline for the signal distribution under normal operating conditions and identifying signals of abnormal events that deviate from the baseline.

[0087] S53 uses a pre-trained convolutional neural network model to perform deep feature extraction and pattern recognition on signals from abnormal events, thereby distinguishing the categories of abnormal events and outputting the judgment results of fire risk level and / or structural damage type and its corresponding degree. The convolutional neural network model has 2 convolutional layers, uses 2×2 max pooling in the pooling layers, and has 32 fully connected units.

[0088] S60, the substrate 10, the functional integrated coating 20, the signal acquisition module 30 and the intelligent recognition module 40 are combined as a flame-retardant-early warning-damage recognition integrated intelligent coating system 100, thereby completing its construction.

[0089] Those skilled in the art should understand that this invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to this invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for constructing an integrated intelligent coating system for flame retardancy, early warning, and damage recognition, characterized in that, Includes the following steps: S10, hydroxyethyl acrylate, sodium vinyl sulfonate and initiator are mixed, dissolved and randomly copolymerized to obtain flame retardant coating solution; S20, thermoelectric filler and piezoelectric filler are added to the flame-retardant coating solution and mixed to obtain a functional coating slurry; S30, the functional coating slurry is coated onto the substrate and dried to obtain a functional integrated coating; S40, electrodes are disposed on the functional integrated coating and electrically connected to a signal acquisition module, the signal acquisition module being used to acquire the raw electrical signals generated by the functional integrated coating. The original electrical signal includes at least the thermoelectric signal generated by the thermoelectric filler due to temperature changes and the piezoelectric signal generated by the piezoelectric filler due to structural deformation of the functional integrated coating; S50, construct an intelligent recognition module and connect it to the signal acquisition module. The intelligent recognition module is configured as follows: First, the original electrical signal acquired by the signal acquisition module is received. Subsequently, an unsupervised clustering algorithm is used to analyze the original electrical signal to establish a baseline for the signal distribution under normal operating conditions and to identify signals of abnormal events that deviate from the baseline. Finally, a pre-trained deep learning model is used to perform deep feature extraction and pattern recognition on the signals of the abnormal events, thereby distinguishing the categories of the abnormal events and outputting the judgment results of fire risk level and / or structural damage type and their corresponding degree. S60, the substrate, the functional integrated coating, the signal acquisition module, and the intelligent recognition module are collectively used as the flame-retardant-early warning-damage recognition integrated intelligent coating system.

2. The method for constructing the integrated intelligent coating system for flame retardancy, early warning, and damage recognition according to claim 1, characterized in that: in, In step S10, the molar ratio of hydroxyethyl acrylate to sodium vinyl sulfonate is 1:

1.

3. The method for constructing the integrated intelligent coating system for flame retardancy, early warning, and damage recognition according to claim 1, characterized in that: in, In step S10, the initiator includes potassium persulfate. The mixing method is as follows: ultrasonic dispersion at 200W~400W power for 30min~60min, followed by stirring at 600rpm~1500rpm for 60min~120min. Random copolymerization is achieved by water bath heating and reflux.

4. The method for constructing the integrated intelligent coating system for flame retardancy, early warning, and damage recognition according to claim 1, characterized in that: in, In step S20, the thermoelectric filler includes any one or more of bismuth telluride, MXene nanosheets, or modified carbon nanotubes. The piezoelectric filler includes lead zirconate titanate.

5. The method for constructing the integrated intelligent coating system for flame retardancy, early warning, and damage recognition according to claim 4, characterized in that: in, In step S20, the mass ratio of the copolymer of hydroxyethyl acrylate and sodium vinyl sulfonate, the thermoelectric filler, and the piezoelectric filler is (10~60):(5~15):(8~20).

6. The method for constructing the integrated intelligent coating system for flame retardancy, early warning, and damage recognition according to claim 1, characterized in that: in, In step S20, the mixing method is as follows: stirring at 600 rpm to 1500 rpm for 60 min, followed by ultrasonic dispersion for 30 min.

7. The method for constructing the integrated intelligent coating system for flame retardancy, early warning, and damage recognition according to claim 1, characterized in that: in, In step S30, the functional integrated coating contains a random copolymer formed by the copolymerization of hydroxyethyl acrylate and sodium vinyl sulfonate. This random copolymer functions under fire conditions through a gas-solid synergistic flame-retardant mechanism. In the gas phase, the decomposition products of sodium vinyl sulfonate capture the free radicals required for the combustion chain reaction, thus providing intrinsic flame retardancy. In the solid phase, hydroxyethyl acrylate undergoes high-temperature dehydration and heat absorption to cool down, forming a firmly adhered and densely structured carbonized layer. This carbonized layer serves to insulate against heat and oxygen, thereby achieving fire protection for the functional integrated coating.

8. The method for constructing the integrated intelligent coating system for flame retardancy, early warning, and damage recognition according to claim 1, characterized in that: in, In step S30: The matrix includes any one or more of fabrics, foams, and fiber-reinforced composite materials. The thickness of the functional integrated coating is controlled to be 0.5μm~100μm. The drying method is: vacuum drying at 60℃~90℃ for 0.5h~12h.

9. The method for constructing the integrated intelligent coating system for flame retardancy, early warning, and damage recognition according to claim 1, characterized in that: in, In step S50, the unsupervised clustering algorithm includes the K-means clustering algorithm. The deep learning model includes a convolutional neural network.

10. An integrated intelligent coating system for flame retardancy, early warning, and damage recognition, characterized in that, The system is constructed using the method for constructing the integrated intelligent coating system for flame retardancy, early warning, and damage recognition as described in any one of claims 1 to 9, comprising: Matrix; A functional integrated coating is disposed on the substrate, comprising a flame-retardant coating and functional fillers dispersed therein, wherein the flame-retardant coating is a random copolymer of hydroxyethyl acrylate and sodium vinyl sulfonate, and the functional fillers include the thermoelectric filler and the piezoelectric filler; A signal acquisition module is electrically connected to the functional integrated coating and is used to acquire the raw electrical signals generated by the functional integrated coating. The intelligent identification module, connected to the signal acquisition module, is used to process the original electrical signal to output the determination results of fire risk level and / or structural damage type and its corresponding degree.

Images