Method and device for detecting wear resistance of formed carbon nanofibers

Abstract

The invention provides a method and a device for detecting wear resistance of carbon nanofiber molding, and relates to the field of carbon fiber wear resistance detection. Deviation analysis is conducted on time sequence information of the spraying posture, the nozzle moving position, the nozzle flow and the spraying cavity temperature, and a spraying control deviation vector matrix is obtained; and when the spraying control deviation threshold matrix is not met, carrying out wear resistance detection identification on the first nano carbon fiber forming body, and conveying the first nano carbon fiber forming body to a wear resistance detection area for wear resistance detection. The technical problem that in the prior art, due to the fact that spraying uniformity of a wear-resistant coating of an irregular-shaped carbon nanofiber forming body is insufficient, comprehensive detection is needed, and the detection efficiency is low is solved, the purposes that products possibly having the wear-resistant performance problem are recognized by analyzing spraying process parameters, selective wear-resistant performance detection is achieved, and the detection efficiency is improved are achieved. And the detection efficiency is improved.

Description

Technical Field

[0001] The invention relates to the field of carbon fiber wear resistance detection, and in particular to a wear resistance detection method and device for nano carbon fiber molding. Background Art

[0002] Nano carbon fiber moldings have broad application prospects in many fields due to their unique physical and chemical properties. However, the wear resistance of the nano carbon fiber molding itself is poor. In order to improve its service life and practicality, it is usually necessary to spray a wear-resistant coating on its surface. In the prior art, the spraying process of the wear-resistant coating is usually carried out in a unified flipping mode. This method works well for moldings of regular shapes, but it is obviously insufficient for moldings of irregular shapes formed due to actual needs. Due to the shape differences of irregular bodies, the flow trajectory of the wear-resistant coating on its surface is uncertain, and it is difficult to ensure the uniformity of the coating, which in turn affects the overall wear resistance of the nano carbon fiber molding. In order to ensure product quality, a comprehensive detection method is currently generally used to detect the wear resistance of each nano carbon fiber molding. Although this method can effectively avoid the omission of products with poor wear resistance, the detection efficiency is low, which increases production costs and time. Therefore, how to improve the detection efficiency of the wear resistance of nano carbon fiber moldings while ensuring that no problematic products are missed has become a problem that needs to be solved urgently. Summary of the invention

[0003] The present invention aims to solve the technical problem in the prior art that the wear-resistant coating of irregular-shaped nano-carbon fiber moldings is not sprayed uniformly, resulting in the need for comprehensive testing and low testing efficiency. A method and device for testing the wear resistance of nano-carbon fiber moldings are provided to solve the problem.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: In the first aspect, the present invention provides a method for detecting the wear resistance of nano-carbon fiber molding, including: an interactive nano-carbon fiber molding sprayer, receiving the spraying posture timing information, nozzle movement position timing information, nozzle flow timing information and spray chamber temperature timing information of a first nano-carbon fiber molding body; matching the spraying posture reference timing information, nozzle movement position reference timing information, nozzle flow reference timing information and spray chamber temperature reference timing information according to the model of the first nano-carbon fiber molding body and the model of the wear-resistant coating; based on the spraying posture reference timing information, the nozzle movement position reference timing information, the nozzle flow reference timing information and the spray chamber temperature reference timing information. The spraying posture timing information, the nozzle movement position timing information, the nozzle flow rate timing information and the spray chamber temperature reference timing information are analyzed for deviation to obtain a spray control deviation vector matrix; when the spray control deviation vector matrix does not satisfy the spray control deviation threshold matrix, the first nano-carbon fiber molding is marked for wear resistance detection and transported to a wear resistance detection area for wear resistance detection, and multiple attributes of the spray control deviation threshold matrix are logically ANDed.

[0005] In the second aspect, the present invention provides a wear resistance detection device for nano-carbon fiber molding, including: a spraying information receiving unit, used to interact with the nano-carbon fiber molding spraying machine, to receive the spraying posture timing information, nozzle movement position timing information, nozzle flow timing information and spray chamber temperature timing information of the first nano-carbon fiber molding body; a reference information matching unit, used to match the spraying posture reference timing information, nozzle movement position reference timing information, nozzle flow reference timing information, spray chamber temperature reference timing information according to the first nano-carbon fiber molding body model and the wear-resistant coating model; a deviation analysis unit, used to analyze the spraying posture reference timing information based on the spraying posture reference timing information , the nozzle movement position reference timing information, the nozzle flow reference timing information, the spray chamber temperature reference timing information, the spray posture timing information, the nozzle movement position timing information, the nozzle flow timing information and the spray chamber temperature timing information are subjected to deviation analysis to obtain a spray control deviation vector matrix; a detection decision unit is used for, when the spray control deviation vector matrix does not satisfy the spray control deviation threshold matrix, to mark the first nano-carbon fiber molded body for wear resistance detection and transport it to a wear resistance detection area for wear resistance detection, wherein the multiple attributes of the spray control deviation threshold matrix are logically ANDed.

[0006] In a third aspect, the present application provides an electronic device, comprising: a processor; a memory for storing instructions executable by the processor; wherein the processor is used to execute a method for detecting wear resistance of nano-carbon fiber molding provided in the present application.

[0007] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, and the computer program is used to execute a method for detecting wear resistance of nano-carbon fiber molding provided in the present application.

[0008] The beneficial effects of the present invention are: The interactive nano-carbon fiber forming spraying machine receives the spraying posture timing information, nozzle movement position timing information, nozzle flow timing information and spray chamber temperature timing information of the first nano-carbon fiber forming body, collects the key parameters in the spraying process, and provides basic data for subsequent analysis; according to the model of the first nano-carbon fiber forming body and the model of the wear-resistant coating, the spraying posture reference timing information, nozzle movement position reference timing information, nozzle flow reference timing information, and spray chamber temperature reference timing information are matched to determine the ideal spraying parameters for a specific forming body and coating combination, and establish an evaluation standard; based on the above-mentioned reference timing information The information is used to perform deviation analysis on the timing information of various parameters in the actual spraying process, and the spraying control deviation vector matrix is ​​obtained. The deviation degree of the spraying process is quantified by comparing the actual parameters with the benchmark parameters. When the spraying control deviation vector matrix does not satisfy the spraying control deviation threshold matrix, the first nano-carbon fiber molding is marked for wear resistance detection and transported to the wear resistance detection area for wear resistance detection, wherein multiple attributes of the spraying control deviation threshold matrix are logical and relationships. According to the deviation analysis results, the wear resistance detection is selectively performed on the moldings that may have problems, so as to achieve targeted detection.

[0009] This method enables accurate monitoring and analysis of the spraying process, and selective testing based on the analysis results. This not only ensures the comprehensiveness of the test and avoids the omission of problematic products, but also improves overall efficiency by reducing unnecessary testing. The setting of logical and relationships ensures that the wear resistance test can be skipped only when all parameters meet the requirements, further ensuring product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic flow chart of a method for testing the wear resistance of carbon nanofiber molding provided by the present invention; Figure 2 A schematic structural diagram of a wear resistance testing device for nano-carbon fiber molding provided by the present invention; Figure 3 A schematic diagram of the structure of an electronic device provided by the present invention; Figure 4 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0011] In the accompanying drawings, the components represented by the reference numerals are listed as follows: Spraying information receiving unit 11, reference information matching unit 12, deviation analysis unit 13, detection decision unit 14, electronic device 200, memory 210, processor 220, computer program 211, computer readable storage medium 300, computer program 311. DETAILED DESCRIPTION

[0012] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0013] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0014] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0015] Embodiment 1: like Figure 1 As shown, an embodiment of the present invention provides a method for detecting the wear resistance of nano-carbon fiber molding, comprising: Step S100: the interactive nano-carbon fiber forming spraying machine receives the spraying posture timing information, the nozzle movement position timing information, the nozzle flow timing information and the spraying chamber temperature timing information of the first nano-carbon fiber forming body.

[0016] Specifically, data is exchanged with the nano-carbon fiber forming spraying machine to obtain the key parameter timing information of the spraying process of the first nano-carbon fiber forming body, including the spraying posture timing information, the nozzle movement position timing information, the nozzle flow timing information and the spraying chamber temperature timing information, which fully reflects the dynamic characteristics of the spraying process. Among them, the spraying posture timing information reflects the spatial positioning and direction changes of the first nano-carbon fiber forming body during the spraying process, which is collected by installing a posture sensor on the first nano-carbon fiber forming body or using a computer vision system for real-time tracking; the nozzle movement position timing information records the movement trajectory of the spray nozzle throughout the process, which is directly obtained through the motion control system of the sprayer; the nozzle flow timing information represents the flow change of the wear-resistant coating released by the nozzle during the spraying process, which is measured by installing a flow sensor on the nozzle; the spraying chamber temperature timing information reflects the dynamic changes in the spraying environment temperature, which is collected by deploying a temperature sensor network in the spraying chamber.

[0017] By acquiring the spraying posture timing information, nozzle movement position timing information, nozzle flow timing information and spray chamber temperature timing information of the first nano-carbon fiber molded body, the dynamic changes of various parameters in the entire spraying process can be captured, providing a rich data basis for subsequent precise analysis. Due to the irregular shape of the nano-carbon fiber molded body, the traditional uniform flipping mode is difficult to ensure the uniformity of spraying. By collecting detailed information, support is provided for the subsequent analysis of the impact of irregular shapes on the spraying effect.

[0018] Step S200: Match the spraying posture reference timing information, the nozzle movement position reference timing information, the nozzle flow reference timing information, and the spraying chamber temperature reference timing information according to the first nano-carbon fiber molded body model and the wear-resistant coating model.

[0019] Specifically, the model of the first nano-carbon fiber molded body and the model of the wear-resistant coating used are first identified. Because molded bodies of different shapes and different types of coatings require different spraying strategies, based on this information, the corresponding reference timing information is matched, including spraying posture reference timing information, nozzle movement position reference timing information, nozzle flow reference timing information, and spray chamber temperature reference timing information. Among them, the spraying posture reference timing information provides the posture change sequence that the first nano-carbon fiber molded body should take during the ideal spraying process; the nozzle movement position reference timing information gives the optimal motion trajectory of the spray nozzle; the nozzle flow reference timing information determines the ideal flow change of the wear-resistant coating that the nozzle should release during the spraying process; the spray chamber temperature reference timing information specifies the optimal change curve of the spraying environment temperature. For example, using machine learning technology, based on a large amount of historical data, the optimal parameter model for a specific model of molded body and coating is trained, or an expert system is used to encode the knowledge of experienced technicians into the system for generating reference timing information.

[0020] By matching the benchmark timing information, the foundation is laid for the subsequent deviation analysis. These benchmark information represent the spraying parameter state that should be achieved under ideal conditions, providing a standard for evaluating the quality of the actual spraying process. At the same time, the matching method based on specific models fully considers the characteristics of different nano carbon fiber moldings and the requirements of different wear-resistant coatings, improving the pertinence and accuracy of the spraying process.

[0021] Step S300: Based on the spraying posture reference timing information, the nozzle movement position reference timing information, the nozzle flow reference timing information, and the spraying chamber temperature reference timing information, deviation analysis is performed on the spraying posture timing information, the nozzle movement position timing information, the nozzle flow timing information, and the spraying chamber temperature timing information to obtain a spraying control deviation vector matrix.

[0022] Specifically, the deviation analysis between the actual spraying process and the ideal state is performed to evaluate the spraying quality. First, the spraying posture timing information is compared with the spraying posture reference timing information, the nozzle movement position timing information is compared with the nozzle movement position reference timing information, the nozzle flow timing information is compared with the nozzle flow reference timing information, and the spray chamber temperature timing information is compared with the spray chamber temperature reference timing information. Deviation analysis is performed to obtain the spraying control deviation vector matrix. For the spraying posture, the degree of deviation between the actual posture change sequence and the ideal sequence is analyzed, and the angle difference or position offset is calculated; for the nozzle movement position, the matching degree between the actual trajectory and the optimal trajectory is evaluated, and the trajectory deviation is calculated; for the nozzle flow, the difference between the actual flow change and the ideal flow change is analyzed, and the cumulative flow error is calculated; for the spray chamber temperature, the degree of deviation between the actual temperature curve and the optimal temperature curve is evaluated, and the temperature fluctuation range is calculated. Afterwards, the deviation analysis results are summarized into the spraying control deviation vector matrix. The spray control deviation vector matrix is ​​a multidimensional data structure. Each dimension corresponds to a parameter (such as spraying posture, nozzle position, nozzle flow, spray chamber temperature). The elements of the matrix represent the deviation values ​​at different time points, thereby comprehensively reflecting the dynamic deviation of each parameter in the entire spraying process.

[0023] By constructing a spray control deviation vector matrix, a quantitative basis is provided for subsequent wear resistance performance evaluation. This multi-parameter, full-process deviation analysis method can fully consider the comprehensive impact of various factors on spray quality and improve the accuracy and reliability of spray evaluation.

[0024] Step S400: When the spray control deviation vector matrix does not satisfy the spray control deviation threshold matrix, the first nano-carbon fiber molded body is marked for wear resistance detection and transported to the wear resistance detection area for wear resistance detection, and the multiple attributes of the spray control deviation threshold matrix are logically ANDed.

[0025] Specifically, after obtaining the spray control deviation vector matrix, it is determined whether to perform a wear resistance test on the first nano-carbon fiber molded body according to the spray control deviation vector matrix. First, the spray control deviation vector matrix is ​​compared with a preset spray control deviation threshold matrix. The spray control deviation threshold matrix is ​​a preset multidimensional threshold structure, and its dimension corresponds to the spray control deviation vector matrix, and each dimension represents the maximum acceptable deviation range of each parameter (such as spraying posture, nozzle position, nozzle flow, spray chamber temperature). During the comparison process, check whether each element in the spray control deviation vector matrix is ​​less than or equal to the corresponding threshold. Among them, the multiple attributes of the spray control deviation threshold matrix are logically and related, that is, only when all elements of the spray control deviation vector matrix meet the corresponding threshold requirements, the entire spraying process is considered acceptable, thereby ensuring the comprehensiveness and reliability of the spraying.

[0026] When the spray control deviation vector matrix does not meet the requirements of the spray control deviation threshold matrix, the first nano-carbon fiber molded body is marked for wear resistance detection. The mark can be a physical mark, such as a label or a printed barcode, or an electronic mark in a database. The purpose of the mark is to ensure that the molded body can be correctly identified and sent to the wear resistance detection area. Afterwards, the marked first nano-carbon fiber molded body is transported to a special wear resistance detection area. In this area, a series of standardized wear resistance tests, such as friction and wear tests, hardness tests, etc., are performed on the marked first nano-carbon fiber molded body to determine the actual wear resistance of the molded body.

[0027] The selective wear resistance testing method significantly improves the testing efficiency. Compared with the traditional full inspection method, only the molded parts with possible problems are tested in detail, which not only ensures product quality, but also saves time and resources. At the same time, it also provides valuable feedback information for the continuous improvement of the production process, which helps to continuously optimize the spraying parameters and process flow.

[0028] Furthermore, the embodiment of the present application also includes: Step S210: constructing a three-dimensional model of the first carbon nanofiber molded body according to the model of the first carbon nanofiber molded body; Step S220: constructing a spray chamber space coordinate system, and configuring an active area of ​​the first carbon nanofiber molded body three-dimensional model and an active area of ​​the spray head; Step S230: Optimize the spraying control according to the active area of ​​the first nano-carbon fiber molded body three-dimensional model, the active area of ​​the nozzle and the wear-resistant coating model, and obtain the spraying posture reference timing information, the nozzle movement position reference timing information, the nozzle flow reference timing information, and the spray chamber temperature reference timing information.

[0029] In a feasible implementation, through three-dimensional modeling and numerical simulation, the influence of different molded body shapes and coating properties on the spraying process is fully considered, thereby obtaining customized spraying control benchmark information.

[0030] First, obtain the model of the first nano-carbon fiber molded body. The model identifies the specific shape, size, structure and other characteristic parameters of the molded body. Then, use computer-aided design software, such as AutoCAD, SolidWorks, etc., to construct a three-dimensional model of the first nano-carbon fiber molded body in the computer according to the characteristic parameters in the model of the first nano-carbon fiber molded body. The model accurately depicts the three-dimensional shape of the first nano-carbon fiber molded body model, and provides a digital geometric basis for the subsequent acquisition of benchmark timing information. After completing the construction of the three-dimensional model of the first nano-carbon fiber molded body, further construct the spray chamber space coordinate system. By establishing a rectangular coordinate system in three-dimensional space, a unified spatial reference frame is formed as the spray chamber space coordinate system, which provides a basis for describing the spatial position and motion trajectory of the molded body and the spray nozzle. Among them, the origin of the spray chamber space coordinate system is flexibly set according to the actual situation, such as selecting the center of the spray chamber or a certain characteristic point. In the spray chamber space coordinate system, the activity area of ​​the first nano-carbon fiber molded body three-dimensional model is configured. The activity area defines the possible position range of the molded body during the spraying process. By analyzing the geometric shape of the 3D model and the characteristics of the spraying process, a reasonable activity area boundary is delineated. At the same time, by fully considering factors such as spraying distance, angle, and collision avoidance, the activity area of ​​the spray nozzle is configured. The nozzle activity area determines the movement range of the nozzle in space.

[0031] After completing the construction of the spatial coordinate system and the configuration of the active area, the active area of ​​the first nano-carbon fiber molded body three-dimensional model, the active area of ​​the nozzle and the wear-resistant coating model are comprehensively considered, and the spray control parameters are optimized by using computer simulation and numerical optimization technology. Among them, the active area of ​​the first nano-carbon fiber molded body three-dimensional model provides the precise geometric information of the spray object; the active area of ​​the nozzle determines the spatial constraints of the spray execution; and the wear-resistant coating model provides the rheological properties and process requirements of the coating material. On this basis, through numerical simulation and computational analysis, different combinations of spray control parameters are comprehensively evaluated, such as spraying posture, nozzle speed, spray flow rate, spray chamber temperature, etc., and the best spray posture reference timing information, nozzle movement position reference timing information, nozzle flow rate reference timing information, and spray chamber temperature reference timing information are selected to achieve the best coating quality and the highest efficiency.

[0032] By quickly generating corresponding benchmark timing information for different nanocarbon fiber moldings and coating types, the accuracy and efficiency of the benchmark timing information are improved, providing the best control benchmark for subsequent actual spraying execution, helping to improve coating quality and reduce trial and error costs.

[0033] Furthermore, the embodiment of the present application also includes: Step S231: the first carbon nanofiber molded body three-dimensional model has a first posture positioning point, a second posture positioning point and a third posture positioning point, and the first posture positioning point, the second posture positioning point and the third posture positioning point are not in the same straight line; Step S232: Randomly position the first positioning point of the posture, the second positioning point of the posture, and the third positioning point of the posture in the active area of ​​the first three-dimensional model of the nano-carbon fiber molded body based on the preset spraying time, and obtain the first time zone assigned spraying posture, the second time zone assigned spraying posture, and the Nth time zone assigned spraying posture; Step S233: performing random positioning based on the preset spraying duration according to the active area of ​​the nozzle, obtaining the first time zone assigned nozzle movement position timing information, the second time zone assigned nozzle movement position timing information until the Nth time zone assigned nozzle movement position timing information; Step S234: performing random positioning based on the preset spraying duration according to the nozzle flow interval, obtaining the nozzle flow timing information assigned in the first time zone, the nozzle flow timing information assigned in the second time zone, and finally the nozzle flow timing information assigned in the Nth time zone; Step S235: According to the spray chamber temperature range, random positioning is performed based on the preset spraying time, and the spray chamber temperature timing information assigned to the first time zone, the spray chamber temperature timing information assigned to the second time zone, and so on until the spray chamber temperature timing information assigned to the Nth time zone is obtained; Step S236: Based on the first time zone assigned spraying posture and the wear-resistant paint model, paint flow simulation is performed according to the first time zone assigned nozzle movement position timing information, the first time zone assigned nozzle flow timing information and the first time zone assigned spraying chamber temperature timing information to obtain the first time zone spraying simulation result; Step S237: Based on the first time zone spraying simulation result, the second time zone assigned spraying posture and the wear-resistant coating model, paint flow simulation is performed according to the second time zone assigned nozzle movement position timing information, the second time zone assigned nozzle flow timing information and the second time zone assigned spraying chamber temperature timing information to obtain the second time zone spraying simulation result; Step S238: until based on the N-1th time zone spraying simulation result, the Nth time zone assigned spraying posture and the wear-resistant coating model, the coating flow simulation is performed according to the Nth time zone assigned nozzle movement position timing information, the second time zone assigned nozzle flow timing information and the second time zone assigned spraying chamber temperature timing information, to obtain the Nth time zone spraying simulation result; Step S239: When the coating coverage of the Nth time zone spraying simulation result is greater than or equal to the coating coverage threshold, and the coating thickness mean is greater than or equal to the coating thickness threshold, and the coating thickness variance is less than or equal to the coating thickness variance threshold, the first time zone assigned spraying posture, the second time zone assigned spraying posture, and the Nth time zone assigned spraying posture are set as the spraying posture reference timing information, the first time zone assigned nozzle movement position timing information, the second time zone assigned nozzle movement position timing information, and the Nth time zone assigned nozzle movement position timing information are set as the nozzle movement position reference timing information, the first time zone assigned nozzle flow timing information, the second time zone assigned nozzle flow timing information, and the Nth time zone assigned nozzle flow timing information are set as the nozzle flow reference timing information, and the first time zone assigned spray chamber temperature timing information, the second time zone assigned spray chamber temperature timing information, and the Nth time zone assigned spray chamber temperature timing information are set as the spray chamber temperature reference timing information.

[0034] In a preferred embodiment, first, there are three posture positioning points on the three-dimensional model of the first nano-carbon fiber molded body, namely, the first posture positioning point, the second posture positioning point and the third posture positioning point, and they are not collinear in space, which are used to determine the posture of the first nano-carbon fiber molded body three-dimensional model in space. Then, according to the preset duration of spraying, the time axis is divided into N time zones, such as 1 second or 0.1 second for each time zone. Subsequently, in each time zone, the position of each posture positioning point is randomly sampled. During sampling, a random moment is first determined, and the coordinates of the three posture positioning points are randomly disturbed at this moment, and the disturbance range is limited to the activity area of ​​the three-dimensional model of the first nano-carbon fiber molded body. Through random disturbance, the random posture of the three-dimensional model of the first nano-carbon fiber molded body in each time zone is obtained, and the spraying posture is assigned to the first time zone, the spraying posture is assigned to the second time zone, and the spraying posture is assigned to the Nth time zone. These randomly generated posture sequences cover various posture combinations that may appear in the molding during the spraying process, and provide a rich candidate solution for subsequent optimization. Similar to random sampling of postures, the spatial position of the spray nozzle is randomly sampled in each time zone. During sampling, a position coordinate is randomly generated in the nozzle activity area as the position of the nozzle in the time zone. Through N random samplings, a complete sequence of nozzle movement positions is obtained, which is successively referred to as the first time zone assigned nozzle movement position timing information, the second time zone assigned nozzle movement position timing information until the Nth time zone assigned nozzle movement position timing information. At the same time, in each time zone, the output flow of the spray nozzle is randomly sampled. During sampling, a flow value is randomly generated within the preset nozzle flow range as the output flow of the nozzle in the time zone. Through N random samplings, a complete nozzle flow control sequence is obtained, which is successively referred to as the first time zone assigned nozzle flow timing information, the second time zone assigned nozzle flow timing information until the Nth time zone assigned nozzle flow timing information. Similarly, for each time zone, a temperature value is randomly generated within the spray chamber temperature range as the ambient temperature of the spray chamber in the time zone. Through N random samplings, a complete temperature control sequence is obtained, which is successively called the first time zone assignment spray chamber temperature timing information, the second time zone assignment spray chamber temperature timing information until the Nth time zone assignment spray chamber temperature timing information.

[0035] Subsequently, computational fluid dynamics technology is used to numerically simulate the spraying process of the first time zone. The input parameters include the spraying posture assigned in the first time zone, the timing information of the nozzle movement position assigned in the first time zone, the timing information of the nozzle flow assigned in the first time zone, the timing information of the spraying chamber temperature assigned in the first time zone, and the type of wear-resistant coating used. On this basis, by solving the fluid control equation, the flow, spreading, and curing processes of the coating on the surface of the molded body are simulated to predict the three-dimensional morphological characteristics of the coating. The simulation results are called the spraying simulation results of the first time zone, which include key quality indicators such as the thickness distribution, surface roughness, and defect probability of the coating. After completing the spraying simulation of the first time zone, the coating morphology formed in the first time zone is used as the initial condition to carry out the spraying simulation of the second time zone. In addition to the updated initial conditions, the input parameters also include various spraying control parameters and the wear-resistant coating model of the second time zone. The simulation process is similar to that of the first time zone, and the spraying simulation results of the second time zone are finally obtained. Repeat the spraying simulation of each time zone until the simulation of the Nth time zone is completed, until the spraying simulation results of the Nth time zone are obtained. The simulation of each time zone takes the simulation results of the previous time zone as the initial condition, and uses the control parameters of this time zone as input to predict the dynamic evolution of the coating morphology. When the simulation of all N time zones is completed, the complete coating formation process and the final three-dimensional structure of the coating are obtained.

[0036] Afterwards, based on the spraying simulation results of the last time zone, that is, the spraying simulation results of the Nth time zone, evaluate whether the coating quality meets the predetermined quality requirements. By analyzing the spraying simulation results of the Nth time zone, the coating coverage, coating thickness mean, and coating thickness variance indicators are extracted and compared with the preset coating coverage threshold, coating thickness threshold, and coating thickness variance threshold, respectively. Among them, the coating coverage indicates the coating's coverage integrity on the substrate surface, which is required to be greater than or equal to the coating coverage threshold; the coating thickness mean indicates the average level of the coating thickness, which is required to be greater than or equal to the coating thickness threshold; the coating thickness variance reflects the uniformity of the coating thickness, which is required to be less than or equal to the coating thickness variance threshold. When the coating coverage, coating thickness mean, and coating thickness variance in the spraying simulation results of the Nth time zone meet the coating coverage threshold, coating thickness threshold, and coating thickness variance threshold, respectively, it is considered that the control parameter combination corresponding to the current simulation can generate a high-quality coating. At this time, a series of posture information used in the simulation process (the spraying posture assigned in the first time zone, the spraying posture assigned in the second time zone, and the spraying posture assigned in the Nth time zone) is recorded as the spraying posture reference timing information, and the nozzle position information used in the simulation process (the nozzle movement position timing information assigned in the first time zone, the nozzle movement position timing information assigned in the second time zone, and the nozzle movement position timing information assigned in the Nth time zone) is recorded as the nozzle movement position reference timing information; the nozzle flow information used in the simulation process (the nozzle flow timing information assigned in the first time zone, the nozzle flow timing information assigned in the second time zone, and the nozzle flow timing information assigned in the Nth time zone) is recorded as the nozzle flow reference timing information; the spray chamber temperature information used in the simulation process (the spray chamber temperature timing information assigned in the first time zone, the spray chamber temperature timing information assigned in the second time zone, and the spray chamber temperature timing information assigned in the Nth time zone) is recorded as the spray chamber temperature reference timing information.

[0037] By predicting the coating formation process through numerical simulation, the time and cost of physical experiments are saved, while the risk of trial and error is avoided. For different nano-carbon fiber moldings and wear-resistant coatings, customized spray control timing can be automatically generated, which has strong adaptability and flexibility.

[0038] Furthermore, the embodiment of the present application also includes: Step S2361: matching the coating viscosity prediction network and coating density information according to the wear-resistant coating model; Step S2362: Analyze the first time zone assigned spray chamber temperature time series information through the paint viscosity prediction network to obtain the first paint viscosity time series information; Step S2363: According to the spraying posture assigned in the first time zone, fluid motion simulation is performed based on the nozzle movement position timing information assigned in the first time zone, the nozzle flow timing information assigned in the first time zone, the first paint viscosity timing information and the paint density information to obtain the spraying simulation result in the first time zone.

[0039] In a preferred embodiment, when performing spray simulation on the first time zone, a coating viscosity prediction network is introduced, and the influence of factors such as temperature, flow rate, and posture on the rheological properties and flow behavior of the coating is comprehensively considered, thereby improving the simulation accuracy. First, according to the wear-resistant coating model to be sprayed, the corresponding coating viscosity prediction network and coating density information are retrieved from the material database. Among them, the coating viscosity prediction network is obtained by training based on a large amount of experimental data using a machine learning method, and can predict the change law of coating viscosity according to temperature changes; the coating density information is a material property parameter determined according to the coating formula and production process conditions, and is regarded as a constant during the simulation process. Subsequently, the temperature timing information of the spray chamber assigned in the first time zone is input into the coating viscosity prediction network to obtain the change curve of the coating viscosity over time in the time zone, that is, the first coating viscosity timing information. Temperature is an important factor affecting the viscosity of the coating. Through the viscosity prediction network, the relationship between temperature and viscosity is quantitatively described to provide dynamic material parameters for flow simulation. Then, according to the posture information of the molded body in the first time zone, the coordinate system orientation and the calculation domain boundary conditions are determined. Next, the first time zone assigned nozzle movement position timing information, the first time zone assigned nozzle flow timing information, the first coating viscosity timing information and coating density information are set as input parameters to the fluid simulation solver. By numerically solving the fluid control equation, the flow, spreading and aggregation process of the coating on the surface of the molded body in the time zone is simulated to obtain the three-dimensional morphology of the coating distribution, that is, the first time zone spraying simulation result.

[0040] By introducing the coating viscosity prediction network and fluid simulation, the dynamic process of spray coating formation in a single time zone can be simulated with high precision, providing support for obtaining benchmark timing information.

[0041] Furthermore, the embodiment of the present application also includes: Step S2371: matching the coating viscosity prediction network and coating density information according to the wear-resistant coating model; Step S2372: Connect the first time zone assigned spray chamber temperature timing information and the second time zone assigned spray chamber temperature timing information to obtain the first time zone and the second time zone fused spray chamber temperature timing information; Step S2373: Analyze the time series information of the temperature of the spray chamber fused in the first time zone and the second time zone through the paint viscosity prediction network to obtain the time series information of the viscosity of the second paint; Step S2374: Analyze the second time zone assigned spray chamber temperature time series information through the paint viscosity prediction network to obtain third paint viscosity time series information; Step S2375: According to the spraying simulation result of the first time zone, fluid motion simulation is performed based on the nozzle movement position timing information assigned in the second time zone, the nozzle flow timing information assigned in the second time zone, the second paint viscosity timing information, the third paint viscosity timing information and the paint density information to obtain the spraying simulation result of the second time zone.

[0042] In a preferred embodiment, when performing spraying simulation in the second time zone, compared with the simulation in the first time zone, the simulation in the second time zone needs to additionally consider the influence of the coating applied in the previous time zone, so it is necessary to introduce temperature fusion of the first time zone and the second time zone and dual viscosity prediction.

[0043] First, according to the wear-resistant coating model to be sprayed, the corresponding coating viscosity prediction network and coating density information are read from the material database. Since the physical properties of the same coating in different time zones are generally unchanged, the data of the first time zone can be directly used. However, if the coating formula needs to be dynamically adjusted in actual production, it is necessary to re-acquire the coating viscosity prediction network and coating density information. Then, the spray chamber temperature timing information assigned to the first time zone and the spray chamber temperature timing information assigned to the second time zone are connected to obtain a complete temperature change curve, that is, the first time zone and the second time zone fusion spray chamber temperature timing information. This fusion process takes into account both the temperature field left over from the previous time zone and the new temperature conditions in the current time zone, and can more accurately describe the continuous change of coating viscosity. Subsequently, using the obtained first time zone and the second time zone fusion spray chamber temperature timing information, the viscosity change curve of the coating applied in the previous time zone in the second time zone is obtained through the coating viscosity prediction network, that is, the second coating viscosity timing information, which reflects the flow characteristics of the existing coating in the current time zone. Since the temperature history of the applied coating is different from that of the newly applied coating, its viscosity change needs to be calculated separately, and the coating viscosity data of the current time zone cannot be simply used. Then, using the real-time spray chamber temperature information of the second time zone, the viscosity change curve of the newly applied coating in the second time zone is obtained through the coating viscosity prediction network, that is, the third coating viscosity time series information, which reflects the flow characteristics of the new coating in the current time zone. Since the initial temperature value of the new coating is different from that of the existing coating, its viscosity change law will also be different. After that, the fluid motion simulation is used to numerically simulate the flow and forming process of the coating. The difference is that in addition to the parameters such as the nozzle movement position, nozzle flow rate, and coating density in the second time zone, the second coating viscosity time series information and the third coating viscosity time series information need to be input at the same time to describe the rheological properties of the applied coating and the newly applied coating, respectively. In addition, the spray simulation results of the first time zone are used as the initial conditions, and they work together with the boundary conditions of the second time zone to obtain the spatiotemporal evolution process of the entire coating. Through numerical solution, key physical quantities such as the thickness distribution and flow velocity field of the new coating in the second time zone are obtained, and superimposed with the morphology of the existing coating to obtain the spraying simulation results in the second time zone.

[0044] By considering the temperature field and viscosity field of the previous and next time zones in a coordinated manner, the continuous simulation of the spraying process in multiple time zones is realized, which can more realistically reflect the rheological behavior and evolution law of the complex coating system. The time zone fusion and dual viscosity prediction method adopted effectively solves the problem of differences in coating temperature history and rheological properties, and can obtain more accurate and reliable coating performance prediction results.

[0045] Furthermore, the embodiment of the present application also includes: Step S2364: collecting the spray chamber temperature record timing information and the coating viscosity record timing information of the preset wear-resistant coating model; Step S2365: disassembling the spray chamber temperature recording timing information and the paint viscosity recording timing information, obtaining the spray chamber temperature recording information at the first moment and the paint viscosity recording information at the first moment, until the spray chamber temperature recording information at the Mth moment and the paint viscosity recording information at the Mth moment; Step S2366: Use the spray chamber temperature record information at the kth moment and the paint viscosity record information at the kth moment as the input of the BP neural network, use the paint viscosity record information at the k+1th moment as the supervision of the BP neural network, retrieve the spray chamber temperature record information at the first moment and the paint viscosity record information at the first moment, until the spray chamber temperature record information at the Mth moment and the paint viscosity record information at the Mth moment are used to train the paint viscosity prediction network.

[0046] In a feasible implementation, in order to construct a coating viscosity prediction network, first, for a preset wear-resistant coating model, in actual spraying tests or industrial production, the spray chamber temperature and coating viscosity data within a period of time are synchronously collected using sensor equipment to obtain corresponding time series information, namely, the spray chamber temperature recording time series information and the coating viscosity recording time series information. These two time series information should have the same sampling time interval and sequence length to ensure data alignment. During the collection process, try to cover different stages and states of the spraying process to improve the diversity and richness of the samples. Then, the collected spray chamber temperature recording time series information and coating viscosity recording time series information are disassembled and converted into a series of discrete data points. By sampling the time axis at equal intervals, the spray chamber temperature recording information and coating viscosity recording information at the first moment, the second moment, and the Mth moment can be obtained. These discrete data points will be used as the input and output of the neural network for training the coating viscosity prediction network.

[0047] Next, the BP neural network is used, with the spray chamber temperature record information and paint viscosity record information at the kth moment as input, and the paint viscosity record information at the k+1th moment as the supervision signal, to iteratively optimize the weights and thresholds of the neural network so that the network's predicted output is as close to the actual viscosity value as possible. By cyclically calling the data samples from the first moment to the Mth moment, the network is repeatedly trained until the prediction error converges to the desired accuracy level, thereby obtaining the paint viscosity prediction network and establishing the relationship between the spray chamber temperature, the current viscosity of the paint, and the future viscosity of the paint. Through the paint viscosity prediction network, the rheological properties of the coating at future moments can be predicted based on the current material state, and the online estimation and dynamic update of the viscosity can be achieved, thereby improving the timeliness and accuracy of the coating viscosity prediction.

[0048] Furthermore, the embodiment of the present application also includes: Step S23621: disassemble the time sequence information of the spray chamber temperature assigned in the first time zone to obtain the spray chamber temperature assigned at the first moment, the spray chamber temperature assigned at the second moment, and finally the spray chamber temperature assigned at the Qth moment; Step S23622: inputting the spray chamber temperature and the initial viscosity of the paint at the first moment into the paint viscosity prediction network to obtain the paint viscosity at the second moment; Step S23623: inputting the coating viscosity at the second moment and the assigned spray chamber temperature at the second moment into the coating viscosity prediction network to obtain the coating viscosity at the third moment; Step S23624: iterative analysis until the coating viscosity at the Qth moment is obtained; Step S23625: Connect the initial viscosity of the paint, the viscosity of the paint at the second moment, the viscosity of the paint at the third moment, and the viscosity of the paint at the Qth moment to obtain the time series information of the first paint viscosity.

[0049] In a preferred embodiment, the trained coating viscosity prediction network is used to analyze the temperature time series information of the spray chamber in the first time zone to obtain the corresponding coating viscosity time series information. This process realizes the mapping conversion from temperature time series to viscosity time series through recursive calculation at each moment.

[0050] First, the obtained time series information of the spray chamber temperature assigned in the first time zone is disassembled and converted into a series of discrete temperature values. By sampling the time axis at equal intervals, the assigned spray chamber temperatures at the first moment, the second moment, and the Qth moment are obtained. These discrete temperature values ​​will be used as the input of the paint viscosity prediction network to gradually estimate the change in paint viscosity. Among them, it is necessary to pay attention to the matching of the time scale to ensure the temporal consistency of the temperature sampling point and the viscosity prediction point. Then, the spray chamber temperature assigned at the first moment and the initial viscosity of the paint are input into the trained paint viscosity prediction network, and the paint viscosity at the second moment is obtained through forward propagation calculation. Among them, the initial viscosity of the paint refers to the viscosity property of the paint at the beginning of spraying. Subsequently, the obtained paint viscosity at the second moment and the spray chamber temperature assigned at the second moment are input into the paint viscosity prediction network again, and the paint viscosity at the third moment is obtained through forward propagation calculation. Since the input of the network contains the viscosity information of the previous moment, it is possible to establish a dynamic relationship between temperature change and viscosity change, and realize viscosity prediction based on time series characteristics. Repeat the execution, continuously input the viscosity prediction value of the previous moment and the assigned spray chamber temperature of the current moment into the paint viscosity prediction network, and after multiple iterations, obtain the paint viscosity at the Qth moment. Through iterative prediction at each moment, a discrete sequence of the change of paint viscosity over time in the entire first time zone is obtained. Then, the obtained initial viscosity of the paint, the viscosity of the paint at the second moment, the viscosity of the paint at the third moment until the viscosity of the paint at the Qth moment are connected in chronological order to form a complete first paint viscosity time series information. This time series information corresponds one-to-one with the time series information of the assigned spray chamber temperature in the first time zone on a time scale, and describes the continuous change process of the paint viscosity in the first time zone.

[0051] The wear resistance detection method of a nano-carbon fiber molding provided by an embodiment of the present invention has at least the following technical effects: The interactive nano-carbon fiber forming spraying machine receives the spraying posture timing information, nozzle moving position timing information, nozzle flow timing information and spray chamber temperature timing information of the first nano-carbon fiber forming body, providing comprehensive actual operation data for subsequent analysis, reflecting the dynamic changes of the entire spraying process. According to the model of the first nano-carbon fiber forming body and the wear-resistant coating model, the spraying posture reference timing information, nozzle moving position reference timing information, nozzle flow reference timing information and spray chamber temperature reference timing information are matched, and the evaluation criteria are established, which provides a benchmark for subsequent deviation analysis and represents the spraying parameters that should be achieved under ideal conditions. Based on the spraying posture reference timing information, nozzle moving position reference timing information, nozzle flow reference timing information and spray chamber temperature reference timing information, deviation analysis is performed on the spraying posture timing information, nozzle moving position timing information, nozzle flow timing information and spray chamber temperature timing information, and the spraying control deviation vector matrix is ​​obtained, which quantifies the degree of difference between the actual spraying process and the ideal state. When the spray control deviation vector matrix does not satisfy the spray control deviation threshold matrix, the first nano-carbon fiber molded body is marked for wear resistance detection and transported to the wear resistance detection area for wear resistance detection. The multiple attributes of the spray control deviation threshold matrix are logically ANDed, which determines whether it is necessary to perform wear resistance detection on a specific nano-carbon fiber molded body. When the spray control deviation vector matrix does not satisfy the spray control deviation threshold matrix, the molded body is marked and sent to the wear resistance detection area, achieving selective detection and improving overall detection efficiency. At the same time, the use of logical AND relationships ensures that the wear resistance test can be skipped only when all parameters meet the requirements, ensuring the strictness of quality control.

[0052] Embodiment 2: like Figure 2 As shown, based on the same inventive concept as the wear resistance detection method of nano-carbon fiber molding provided in Example 1, the embodiment of the present invention also provides a wear resistance detection device for nano-carbon fiber molding, comprising: The spraying information receiving unit 11 is used for interacting with the nano-carbon fiber forming spraying machine to receive the spraying posture timing information, the nozzle movement position timing information, the nozzle flow timing information and the spraying chamber temperature timing information of the first nano-carbon fiber forming body; A reference information matching unit 12 is used to match the spraying posture reference timing information, the nozzle movement position reference timing information, the nozzle flow reference timing information, and the spraying chamber temperature reference timing information according to the first nano-carbon fiber molded body model and the wear-resistant coating model; a deviation analysis unit 13, configured to perform deviation analysis on the spraying posture timing information, the nozzle moving position timing information, the nozzle flow timing information and the spraying chamber temperature timing information based on the spraying posture reference timing information, the nozzle moving position reference timing information, the nozzle flow timing information and the spraying chamber temperature reference timing information to obtain a spraying control deviation vector matrix; The detection decision unit 14 is used to mark the first nano-carbon fiber molded body for wear resistance detection when the spray control deviation vector matrix does not satisfy the spray control deviation threshold matrix, and transport it to the wear resistance detection area for wear resistance detection. The multiple attributes of the spray control deviation threshold matrix are logically ANDed.

[0053] Furthermore, the reference information matching unit 12 includes the following execution steps: Constructing a three-dimensional model of the first carbon nanofiber molded body according to the model of the first carbon nanofiber molded body; Constructing a spray chamber space coordinate system, and configuring the first nano-carbon fiber molded body three-dimensional model activity area and the nozzle activity area; The spraying control is optimized according to the active area of ​​the three-dimensional model of the first nano-carbon fiber molded body, the active area of ​​the nozzle and the model of the wear-resistant coating, and the spraying posture reference timing information, the nozzle movement position reference timing information, the nozzle flow reference timing information and the spray chamber temperature reference timing information are obtained.

[0054] Furthermore, the reference information matching unit 12 further includes the following execution steps: The first three-dimensional model of the nano-carbon fiber molded body has a first posture positioning point, a second posture positioning point and a third posture positioning point, and the first posture positioning point, the second posture positioning point and the third posture positioning point are not in the same straight line; The first positioning point of the posture, the second positioning point of the posture and the third positioning point of the posture are randomly positioned in the activity area of ​​the first three-dimensional model of the nano-carbon fiber molded body based on the preset spraying time, and the first time zone assigned spraying posture, the second time zone assigned spraying posture and the Nth time zone assigned spraying posture are obtained; According to the nozzle activity area, random positioning is performed based on the preset spraying time, and the first time zone assigned nozzle movement position timing information, the second time zone assigned nozzle movement position timing information, and the Nth time zone assigned nozzle movement position timing information are obtained; According to the nozzle flow interval, random positioning is performed based on the preset spraying time, and the nozzle flow timing information assigned to the first time zone, the nozzle flow timing information assigned to the second time zone, and the nozzle flow timing information assigned to the Nth time zone are obtained; According to the spray chamber temperature range, random positioning is performed based on the preset spraying time, and the spray chamber temperature timing information assigned to the first time zone, the spray chamber temperature timing information assigned to the second time zone, and so on until the spray chamber temperature timing information assigned to the Nth time zone is obtained; Based on the first time zone assigned spraying posture and the wear-resistant paint model, paint flow simulation is performed according to the first time zone assigned nozzle movement position timing information, the first time zone assigned nozzle flow timing information and the first time zone assigned spraying chamber temperature timing information to obtain the first time zone spraying simulation result; Based on the spraying simulation result of the first time zone, the spraying posture assigned by the second time zone and the wear-resistant coating model, the coating flow simulation is performed according to the nozzle movement position timing information assigned by the second time zone, the nozzle flow timing information assigned by the second time zone and the spraying chamber temperature timing information assigned by the second time zone to obtain the spraying simulation result of the second time zone; Until based on the spraying simulation result of the N-1th time zone, the spraying posture assigned to the Nth time zone and the wear-resistant coating model, the coating flow simulation is performed according to the timing information of the nozzle movement position assigned to the Nth time zone, the timing information of the nozzle flow rate assigned to the second time zone and the timing information of the spraying chamber temperature assigned to the second time zone, to obtain the spraying simulation result of the Nth time zone; When the coating coverage of the Nth time zone spraying simulation result is greater than or equal to the coating coverage threshold, and the coating thickness mean is greater than or equal to the coating thickness threshold, and the coating thickness variance is less than or equal to the coating thickness variance threshold, the first time zone assigned spraying posture, the second time zone assigned spraying posture, and the Nth time zone assigned spraying posture are set as the spraying posture reference timing information, the first time zone assigned nozzle movement position timing information, the second time zone assigned nozzle movement position timing information, and the Nth time zone assigned nozzle movement position timing information are set as the nozzle movement position reference timing information, the first time zone assigned nozzle flow timing information, the second time zone assigned nozzle flow timing information, and the Nth time zone assigned nozzle flow timing information are set as the nozzle flow reference timing information, and the first time zone assigned spray chamber temperature timing information, the second time zone assigned spray chamber temperature timing information, and the Nth time zone assigned spray chamber temperature timing information are set as the spray chamber temperature reference timing information.

[0055] Furthermore, the reference information matching unit 12 further includes the following execution steps: According to the wear-resistant coating model, matching the coating viscosity prediction network and coating density information; By using the coating viscosity prediction network, analyzing the first time zone assigned spray chamber temperature time series information to obtain the first coating viscosity time series information; According to the spraying posture assigned by the first time zone, fluid motion simulation is performed based on the nozzle movement position timing information assigned by the first time zone, the nozzle flow timing information assigned by the first time zone, the first paint viscosity timing information and the paint density information to obtain the first time zone spraying simulation result.

[0056] Furthermore, the reference information matching unit 12 further includes the following execution steps: According to the wear-resistant coating model, matching the coating viscosity prediction network and coating density information; Connect the first time zone assigned spray chamber temperature timing information and the second time zone assigned spray chamber temperature timing information to obtain the first time zone and the second time zone fused spray chamber temperature timing information; By using the coating viscosity prediction network, analyzing the time series information of the temperature of the spray chamber fused in the first time zone and the second time zone, obtaining the time series information of the viscosity of the second coating; By using the coating viscosity prediction network, analyzing the second time zone assigned spray chamber temperature time series information to obtain third coating viscosity time series information; According to the spraying simulation result of the first time zone, fluid motion simulation is performed based on the nozzle movement position timing information assigned in the second time zone, the nozzle flow timing information assigned in the second time zone, the second paint viscosity timing information, the third paint viscosity timing information and the paint density information to obtain the spraying simulation result of the second time zone.

[0057] Furthermore, the reference information matching unit 12 further includes the following execution steps: Collect the spray chamber temperature record time sequence information and the paint viscosity record time sequence information of the preset wear-resistant paint model; Disassembling the spray chamber temperature recording timing information and the paint viscosity recording timing information to obtain the spray chamber temperature recording information at the first moment and the paint viscosity recording information at the first moment, until the spray chamber temperature recording information at the Mth moment and the paint viscosity recording information at the Mth moment; The spray chamber temperature record information at the kth moment and the paint viscosity record information at the kth moment are used as the input of the BP neural network, and the paint viscosity record information at the k+1th moment is used as the supervision of the BP neural network. The spray chamber temperature record information at the first moment and the paint viscosity record information at the first moment are retrieved until the spray chamber temperature record information at the Mth moment and the paint viscosity record information at the Mth moment are used to train the paint viscosity prediction network.

[0058] Furthermore, the reference information matching unit 12 further includes the following execution steps: Decomposing the time sequence information of the spray chamber temperature assigned in the first time zone to obtain the spray chamber temperature assigned at the first moment, the spray chamber temperature assigned at the second moment, and finally the spray chamber temperature assigned at the Qth moment; Inputting the spray chamber temperature and the initial viscosity of the coating at the first moment into the coating viscosity prediction network to obtain the coating viscosity at the second moment; Inputting the coating viscosity at the second moment and the assigned spray chamber temperature at the second moment into the coating viscosity prediction network to obtain the coating viscosity at the third moment; Iterate the analysis until the coating viscosity at the Qth moment is obtained; The initial viscosity of the coating, the viscosity of the coating at the second moment, the viscosity of the coating at the third moment, and the viscosity of the coating at the Qth moment are connected to obtain the time series information of the viscosity of the first coating.

[0059] Embodiment three: See also Figure 3 , Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, an electronic device 200 provided by an embodiment of the present invention includes a memory 210, a processor 220, and a computer program 211 stored in the memory 210 and executable on the processor 220. When the processor 220 executes the computer program 211, a method for detecting the wear resistance of nano-carbon fiber molding is implemented.

[0060] Embodiment 4: See also Figure 4 , Figure 4 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 4 As shown, this embodiment provides a computer-readable storage medium 300 on which a computer program 311 is stored. When the computer program 311 is executed by a processor, a method for detecting the wear resistance of nano-carbon fiber molding is implemented.

[0061] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0062] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0063] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0064] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0065] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0066] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0067] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technology, the present invention is also intended to include these changes and variations.

Claims

1. A method for detecting the wear resistance of carbon nanofiber molding, characterized in that: include: An interactive nano-carbon fiber forming spraying machine receives the spraying posture timing information, the nozzle movement position timing information, the nozzle flow timing information and the spraying chamber temperature timing information of the first nano-carbon fiber forming body; According to the model of the first carbon nanofiber molded body and the model of the wear-resistant coating, the spraying posture reference timing information, the nozzle movement position reference timing information, the nozzle flow reference timing information, and the spraying chamber temperature reference timing information are matched; Based on the spraying posture reference timing information, the nozzle movement position reference timing information, the nozzle flow reference timing information, and the spraying chamber temperature reference timing information, deviation analysis is performed on the spraying posture timing information, the nozzle movement position timing information, the nozzle flow timing information, and the spraying chamber temperature timing information to obtain a spraying control deviation vector matrix; When the spray control deviation vector matrix does not satisfy the spray control deviation threshold matrix, the first nano-carbon fiber molded body is marked for wear resistance detection and transported to the wear resistance detection area for wear resistance detection, and the multiple attributes of the spray control deviation threshold matrix are logically ANDed.

2. The method according to claim 1, characterized in that According to the first carbon nanofiber molded body model and the wear-resistant coating model, the spraying posture reference timing information, the nozzle movement position reference timing information, the nozzle flow reference timing information, and the spraying chamber temperature reference timing information are matched, including: Constructing a three-dimensional model of the first carbon nanofiber molded body according to the model of the first carbon nanofiber molded body; Constructing a spray chamber space coordinate system, and configuring the first nano-carbon fiber molded body three-dimensional model activity area and the nozzle activity area; The spraying control is optimized according to the active area of ​​the three-dimensional model of the first nano-carbon fiber molded body, the active area of ​​the nozzle and the model of the wear-resistant coating, and the spraying posture reference timing information, the nozzle movement position reference timing information, the nozzle flow reference timing information and the spray chamber temperature reference timing information are obtained.

3. The method according to claim 2, characterized in that The spraying control optimization is performed according to the active area of ​​the first carbon nanofiber molded body three-dimensional model, the active area of ​​the nozzle and the wear-resistant coating model, and the spraying posture reference timing information, the nozzle movement position reference timing information, the nozzle flow reference timing information, and the spray chamber temperature reference timing information are obtained, including: The first three-dimensional model of the nano-carbon fiber molded body has a first posture positioning point, a second posture positioning point and a third posture positioning point, and the first posture positioning point, the second posture positioning point and the third posture positioning point are not in the same straight line; The first positioning point of the posture, the second positioning point of the posture and the third positioning point of the posture are randomly positioned in the activity area of ​​the first three-dimensional model of the nano-carbon fiber molded body based on the preset spraying time, and the first time zone assigned spraying posture, the second time zone assigned spraying posture and the Nth time zone assigned spraying posture are obtained; According to the nozzle activity area, random positioning is performed based on the preset spraying time, and the first time zone assigned nozzle movement position timing information, the second time zone assigned nozzle movement position timing information, and the Nth time zone assigned nozzle movement position timing information are obtained; According to the nozzle flow interval, random positioning is performed based on the preset spraying time, and the nozzle flow timing information assigned to the first time zone, the nozzle flow timing information assigned to the second time zone, and the nozzle flow timing information assigned to the Nth time zone are obtained; According to the spray chamber temperature range, random positioning is performed based on the preset spraying time, and the spray chamber temperature timing information assigned to the first time zone, the spray chamber temperature timing information assigned to the second time zone, and so on until the spray chamber temperature timing information assigned to the Nth time zone is obtained; Based on the first time zone assigned spraying posture and the wear-resistant paint model, paint flow simulation is performed according to the first time zone assigned nozzle movement position timing information, the first time zone assigned nozzle flow timing information and the first time zone assigned spraying chamber temperature timing information to obtain the first time zone spraying simulation result; Based on the spraying simulation result of the first time zone, the spraying posture assigned by the second time zone and the wear-resistant coating model, the coating flow simulation is performed according to the nozzle movement position timing information assigned by the second time zone, the nozzle flow timing information assigned by the second time zone and the spraying chamber temperature timing information assigned by the second time zone to obtain the spraying simulation result of the second time zone; Until based on the spraying simulation result of the N-1th time zone, the spraying posture assigned to the Nth time zone and the wear-resistant coating model, the coating flow simulation is performed according to the timing information of the nozzle movement position assigned to the Nth time zone, the timing information of the nozzle flow rate assigned to the second time zone and the timing information of the spraying chamber temperature assigned to the second time zone, to obtain the spraying simulation result of the Nth time zone; When the coating coverage of the Nth time zone spraying simulation result is greater than or equal to the coating coverage threshold, and the coating thickness mean is greater than or equal to the coating thickness threshold, and the coating thickness variance is less than or equal to the coating thickness variance threshold, the first time zone assigned spraying posture, the second time zone assigned spraying posture, and the Nth time zone assigned spraying posture are set as the spraying posture reference timing information, the first time zone assigned nozzle movement position timing information, the second time zone assigned nozzle movement position timing information, and the Nth time zone assigned nozzle movement position timing information are set as the nozzle movement position reference timing information, the first time zone assigned nozzle flow timing information, the second time zone assigned nozzle flow timing information, and the Nth time zone assigned nozzle flow timing information are set as the nozzle flow reference timing information, and the first time zone assigned spray chamber temperature timing information, the second time zone assigned spray chamber temperature timing information, and the Nth time zone assigned spray chamber temperature timing information are set as the spray chamber temperature reference timing information.

4. The method according to claim 3, characterized in that Based on the first time zone assigned spraying posture and the wear-resistant paint model, paint flow simulation is performed according to the first time zone assigned nozzle movement position timing information, the first time zone assigned nozzle flow timing information and the first time zone assigned spraying chamber temperature timing information, to obtain the first time zone spraying simulation result, including: According to the wear-resistant coating model, matching the coating viscosity prediction network and coating density information; By using the coating viscosity prediction network, analyzing the first time zone assigned spray chamber temperature time series information to obtain the first coating viscosity time series information; According to the spraying posture assigned by the first time zone, fluid motion simulation is performed based on the nozzle movement position timing information assigned by the first time zone, the nozzle flow timing information assigned by the first time zone, the first paint viscosity timing information and the paint density information to obtain the first time zone spraying simulation result.

5. The method according to claim 3, characterized in that Based on the first time zone spraying simulation result, the second time zone assigned spraying posture and the wear-resistant coating model, the coating flow simulation is performed according to the second time zone assigned nozzle movement position timing information, the second time zone assigned nozzle flow timing information and the second time zone assigned spraying chamber temperature timing information, to obtain the second time zone spraying simulation result, including: According to the wear-resistant coating model, matching the coating viscosity prediction network and coating density information; Connect the first time zone assigned spray chamber temperature timing information and the second time zone assigned spray chamber temperature timing information to obtain the first time zone and the second time zone fused spray chamber temperature timing information; By using the coating viscosity prediction network, analyzing the time series information of the temperature of the spray chamber fused in the first time zone and the second time zone, obtaining the time series information of the viscosity of the second coating; By using the coating viscosity prediction network, analyzing the second time zone assigned spray chamber temperature time series information to obtain third coating viscosity time series information; According to the spraying simulation result of the first time zone, fluid motion simulation is performed based on the nozzle movement position timing information assigned in the second time zone, the nozzle flow timing information assigned in the second time zone, the second paint viscosity timing information, the third paint viscosity timing information and the paint density information to obtain the spraying simulation result of the second time zone.

6. The method according to claim 4, characterized in that By using the coating viscosity prediction network, the first time zone assigned spray chamber temperature time series information is analyzed to obtain the first coating viscosity time series information, which includes: Collect the spray chamber temperature record time sequence information and the paint viscosity record time sequence information of the preset wear-resistant paint model; Disassembling the spray chamber temperature recording timing information and the paint viscosity recording timing information to obtain the spray chamber temperature recording information at the first moment and the paint viscosity recording information at the first moment, until the spray chamber temperature recording information at the Mth moment and the paint viscosity recording information at the Mth moment; The spray chamber temperature record information at the kth moment and the paint viscosity record information at the kth moment are used as the input of the BP neural network, and the paint viscosity record information at the k+1th moment is used as the supervision of the BP neural network. The spray chamber temperature record information at the first moment and the paint viscosity record information at the first moment are retrieved until the spray chamber temperature record information at the Mth moment and the paint viscosity record information at the Mth moment are used to train the paint viscosity prediction network.

7. The method according to claim 4, characterized in that The coating viscosity prediction network is used to analyze the first time zone assigned spray chamber temperature time series information to obtain the first coating viscosity time series information, including: Decomposing the time sequence information of the spray chamber temperature assigned in the first time zone to obtain the spray chamber temperature assigned at the first moment, the spray chamber temperature assigned at the second moment, and finally the spray chamber temperature assigned at the Qth moment; Inputting the spray chamber temperature and the initial viscosity of the coating at the first moment into the coating viscosity prediction network to obtain the coating viscosity at the second moment; Inputting the coating viscosity at the second moment and the assigned spray chamber temperature at the second moment into the coating viscosity prediction network to obtain the coating viscosity at the third moment; Iterate the analysis until the coating viscosity at the Qth moment is obtained; The initial viscosity of the coating, the viscosity of the coating at the second moment, the viscosity of the coating at the third moment, and the viscosity of the coating at the Qth moment are connected to obtain the time series information of the viscosity of the first coating.

8. A wear resistance testing device for nano-carbon fiber molding, characterized in that: include: A spraying information receiving unit, the spraying information receiving unit is used for interacting with the nano-carbon fiber forming spraying machine, receiving the spraying posture timing information of the first nano-carbon fiber forming body, the nozzle movement position timing information, the nozzle flow timing information and the spraying chamber temperature timing information; A reference information matching unit, wherein the reference information matching unit is used to match the spraying posture reference timing information, the nozzle movement position reference timing information, the nozzle flow reference timing information, and the spraying chamber temperature reference timing information according to the first nano-carbon fiber molded body model and the wear-resistant coating model; A deviation analysis unit, the deviation analysis unit is used to perform deviation analysis on the spraying posture timing information, the nozzle moving position timing information, the nozzle flow timing information and the spraying chamber temperature timing information based on the spraying posture reference timing information, the nozzle moving position reference timing information, the nozzle flow timing information and the spraying chamber temperature reference timing information to obtain a spraying control deviation vector matrix; A detection decision unit is used to mark the first nano-carbon fiber molded body for wear resistance detection when the spray control deviation vector matrix does not satisfy the spray control deviation threshold matrix, and transport it to a wear resistance detection area for wear resistance detection, wherein the multiple attributes of the spray control deviation threshold matrix are logically ANDed.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the wear resistance detection method of a nano-carbon fiber molding as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the method for detecting the wear resistance of nano-carbon fiber molding as described in any one of claims 1 to 7 is implemented.

Images