Intelligent regulation method and system for nondestructive testing

Abstract

The application provides a kind of intelligent regulation and control method and system of nondestructive testing, it is related to intelligent control technical field, method includes: to the data acquisition device obtains the structural parameters of the part to be detected are analyzed, obtains the surface exposure of the part to be detected, the assembly embedding of the part to be detected and the gap variability of the part to be detected are penetrated into complex degree identification, obtains the first complex index input coating control module, and in coating control module optimization is carried out, the coating control parameter corresponding to the coating control index is output, according to coating control parameter, fluorescence detection equipment is adjusted, the application solves the technical problem that the nondestructive testing management and control is insufficient in the prior art, leads to the low efficiency of nondestructive testing, realizes the rationalization precision regulation and control to nondestructive testing, and then improves the efficiency of nondestructive testing.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to an intelligent control method and system for non-destructive testing. Background Art

[0002] With the development of science and technology, especially the development of non-destructive testing, non-destructive testing refers to the use of changes in thermal, acoustic, optical, electrical, magnetic and other reactions caused by abnormal internal structure or defects of materials, under the premise of inspecting the internal structure of mechanical materials without damaging or affecting the performance of the inspected object and without damaging the internal organization of the inspected object. With physical or chemical methods, with the help of modern technology and equipment, the structure, state and type, quantity, shape, nature, position, size, distribution and changes of defects inside and on the surface of the test piece are inspected and tested. Now the present invention solves the technical problem of insufficient control of non-destructive testing in the existing technology, which leads to low efficiency of non-destructive testing. Summary of the Invention

[0003] The present application provides an intelligent control method and system for non-destructive testing, which is used to solve the technical problem of insufficient control over non-destructive testing in the prior art, resulting in low efficiency of non-destructive testing.

[0004] In view of the above problems, the present application provides an intelligent control method and system for non-destructive testing.

[0005] In the first aspect, the present application provides an intelligent control method for non-destructive testing, the method comprising: obtaining structural parameters of a part to be inspected according to a data acquisition device; analyzing the structural parameters of the part to be inspected to obtain the surface exposure of the part to be inspected, the assembly embedding of the part to be inspected, and the gap variability of the part to be inspected; performing penetration complexity identification on the structural parameters of the part to be inspected based on the surface exposure, the assembly embedding of the part to be inspected, and the gap variability of the part to be inspected to obtain a first complex index; inputting the first complex index into a coating control module, the coating control module comprising a plurality of coating control indicators, the coating control indicators comprising the configuration of the coating solution, the control time of the solution coating, and the solution coating method; performing optimization using the coating control module, outputting coating control parameters corresponding to the coating control indicators, and adjusting the fluorescence detection equipment according to the coating control parameters.

[0006] In a second aspect, the present application provides an intelligent control system for non-destructive testing, the system comprising: one or more technical solutions provided in the present application, which have at least the following technical effects or advantages: a parameter acquisition module, the parameter acquisition module is used to obtain the structural parameters of the part to be inspected according to a data acquisition device; a parameter analysis module, the parameter analysis module is used to analyze the structural parameters of the part to be inspected, and obtain the surface exposure of the part to be inspected, the assembly embedding of the part to be inspected, and the gap variability of the part to be inspected; a parameter identification module, the parameter identification module is used to perform penetration complexity identification on the structural parameters of the part to be inspected based on the surface exposure, the assembly embedding of the part to be inspected, and the gap variability of the part to be inspected, and obtain a first complex index; a first input module, the first input module is used to input the first complex index into a coating control module, the coating control module includes multiple coating control indicators, the coating control indicators include the configuration of the coating solution, the control time of the solution coating, and the solution coating method; a parameter adjustment module, the parameter adjustment module is used to optimize with the coating control module, output coating control parameters corresponding to the coating control indicators, and adjust the fluorescence detection equipment according to the coating control parameters.

[0007] The present application provides an intelligent control method and system for non-destructive testing, which relates to the field of intelligent control technology. It solves the technical problem of insufficient control over non-destructive testing in the existing technology, resulting in low efficiency of non-destructive testing, and realizes rational and precise control of non-destructive testing, thereby improving the efficiency of non-destructive testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of a flow chart of an intelligent control method for non-destructive testing is provided for this application;

[0009] Figure 2 This application provides a schematic flow chart of a coating control module in an intelligent control method for non-destructive testing;

[0010] Figure 3 A schematic diagram of the structure of an intelligent control system for non-destructive testing is provided for this application.

[0011] Description of the accompanying drawings: parameter acquisition module 1, parameter analysis module 2, parameter identification module 3, first input module 4, parameter adjustment module 5. DETAILED DESCRIPTION

[0012] This application provides an intelligent control method and system for non-destructive testing to solve the technical problem of insufficient control over non-destructive testing in the existing technology, which leads to low efficiency of non-destructive testing.

[0013] Example 1

[0014] like Figure 1 As shown, an embodiment of the present application provides an intelligent control method for non-destructive testing, the method comprising:

[0015] Step A100: obtaining structural parameters of the part to be inspected using a data acquisition device;

[0016] In the present application, an intelligent control method for non-destructive testing provided in an embodiment of the present application is applied to an intelligent control system for non-destructive testing. The intelligent control system for non-destructive testing is communicatively connected to a data acquisition device, which is used to collect structural parameters in the parts to be inspected.

[0017] In order to inspect the quality and integrity of the parts to be inspected through non-destructive testing methods without destroying the appearance and internal structure of the parts, non-destructive testing methods can include visual inspection, liquid penetrant testing, magnetic particle testing, ultrasonic testing and X-ray testing, etc. Due to the diversity of the structures of the parts to be inspected, liquid penetrant testing can be used to perform subsequent non-destructive testing on the parts to be inspected based on the structural parameters, which serves as an important reference for the later intelligent control of non-destructive testing.

[0018] Step A200: Analyze the structural parameters of the part to be inspected to obtain the surface exposure of the part to be inspected, the assembly embeddability of the part to be inspected, and the gap variability of the part to be inspected;

[0019] In this application, in order to improve the efficiency of non-destructive testing of parts to be inspected, it is necessary to integrate the production sample drawings of the parts to be inspected, and on this basis, analyze the structural parameters of the parts to be inspected obtained above, which means performing structural analysis on the surface and internal structure of the parts to be inspected, so as to obtain the surface exposure of the parts to be inspected, the assembly embeddability of the parts to be inspected, and the gap variability of the parts to be inspected. The surface exposure of the parts to be inspected refers to the percentage of the area in contact with the outside world in the structure of the parts to be inspected to the total area. The higher the percentage, the higher the surface exposure. The assembly embeddability of the parts to be inspected refers to determining whether the parts to be inspected contain complex internal structures and special assembly features. The assembly features can be threaded holes, hoop welding, precision fit, embedded components, etc. The higher the internal complexity of the parts to be tested and / or the more special the assembly features, the greater the complexity of the parts. The gap variability of the parts to be inspected refers to the presence of parts with a large number of internal and external features, holes, grooves, edges and corners, such as arrangement, overlap, intersection, curvature changes, etc., in the parts to be inspected, thereby ensuring the realization of intelligent control of non-destructive testing.

[0020] Step A300: performing penetration complexity identification on the structural parameters of the part to be inspected based on the surface exposure, assembly embeddability of the part to be inspected, and gap variability of the part to be inspected to obtain a first complexity index;

[0021] In this application, in order to ensure more accurate non-destructive testing of the parts to be inspected in the future, it is necessary to identify the complexity of liquid penetration of the parts to be inspected based on the selected non-destructive testing method, that is, liquid penetration testing. This means that the surface exposure of the parts to be inspected, the assembly embedding of the parts to be inspected, and the gap variability of the parts to be inspected obtained through the above analysis are used to identify the complexity of liquid penetration in the structure of the parts to be inspected. The penetration complexity is proportional to the structural complexity of the parts to be inspected. At the same time, the complexity of the structural parameters of the parts to be inspected is improved based on the surface exposure, the assembly embedding of the parts to be inspected, and the gap variability of the parts to be inspected. Since liquid penetration testing uses highly permeable liquids to penetrate into the surface defects of the components and then try to make them show the defects, it is necessary to formulate a complexity index corresponding to the parts to be inspected based on the identified penetration complexity of the parts to be inspected. The complexity index is proportional to the penetration complexity of the parts to be inspected. The higher the penetration complexity, the higher the complexity index, which lays a solid foundation for the subsequent intelligent regulation of non-destructive testing.

[0022] Step A400: inputting the first complex index into a coating control module, wherein the coating control module includes a plurality of coating control indexes, including the configuration of the coating solution, the control time of the solution coating, and the solution coating method;

[0023] Furthermore, if Figure 2 As shown, step A400 of this application also includes:

[0024] Step A410: Obtaining samples of complex indicators and samples of coating control indicators;

[0025] Step A420: controlling the fluorescence detection device to perform multiple detections using the sample of the complex index and the sample of the coating control index to obtain multiple fluorescence detection data sets;

[0026] Step A430: Evaluate the coating quality of the multiple fluorescence detection data sets and output coating quality parameter samples, wherein each set of samples corresponds to a coating quality index sample;

[0027] Step A440: The coating control module is obtained by training based on the coating quality index samples, the complex index samples, and the coating control parameter samples.

[0028] Furthermore, step A440 of the present application includes:

[0029] Step A441: Acquire the multiple fluorescence detection data sets, and acquire the coating uniformity and coating completeness of the part surface according to the multiple fluorescence detection data sets;

[0030] Step A442: Based on the coating uniformity and the coating completeness, a weight network layer is established for calculation to obtain a coating quality index sample, wherein the weight index of the coating uniformity in the weight network layer is less than the weight index of the coating completeness.

[0031] In the present application, by inputting the first complex indicator into the coating control module, the coating control module is in a communication connection with an intelligent control system for non-destructive testing. The coating control module includes multiple coating control indicators, and the coating control indicators include the configuration of the coating solution, the control time of the solution coating, and the solution coating method. The configuration of the coating solution refers to the configuration of the liquid fluidity, liquid viscosity, etc. used in the process of liquid penetration testing of the parts to be inspected. The required configuration of the coating solution can be a coating solution with high fluidity and low viscosity. The control time of the solution coating refers to the time length from the start time of pouring the coating solution into the parts to be inspected to the end time when the coating solution completely covers the parts to be inspected during the liquid penetration testing of the parts to be inspected. The solution coating method can be dissolving the coating in the parts to be inspected and spraying, brushing, dipping, etc.

[0032] When the first complex index is input into the coating control module, the coating control index corresponding to the complex index is extracted. This means that due to the different structures of different parts to be tested, the complex indexes corresponding to different structures are different, that is, the more complex the structure of the part to be tested, the higher the corresponding complex index, and the more complex the coating control required by the part to be tested, the higher the coating control index. On this basis, samples of parts to be tested with complex indicators and samples of parts to be tested with coating control indicators are obtained. Furthermore, samples of complex indicators and samples of coating control indicators are used as reference basic data to control the fluorescence detection equipment to perform multiple tests on the parts to be tested, and obtain multiple fluorescence detection data sets, which means that the fluorescent powder penetrant is sprayed on the parts to be tested. The surface of the part to be tested is cleaned and dried after the fluorescent penetrant has penetrated into the surface defects of the part to be tested, and then the indicator is sprayed on. The residual penetrant in the surface defects of the part to be tested will in turn penetrate into the indicator, and the defects will be displayed under the irradiation of the ultraviolet lamp. This process is iterated multiple times and recorded to generate multiple fluorescence detection data sets. Furthermore, the coating quality of the part to be tested in each fluorescence detection data contained in the multiple fluorescence detection data sets is evaluated based on coating flatness, coating smoothness, coating adhesion, coating durability, etc., so that the evaluation data are summarized and output as coating quality parameter samples, wherein each group of samples corresponds to a coating quality index sample, and the coating quality index sample is used as the coating quality parameter sample. The coating quality index samples, the samples of the complex indexes and the samples of the coating control parameters are used as training data, and the training data are weighted. The process can be to obtain the coating uniformity of the surface of the part to be inspected and the coating completeness of the part surface based on multiple fluorescence detection data sets. The coating uniformity of the surface of the part to be inspected is determined based on the consistency of the coating thickness or coating amount distribution in the coating area. The higher the consistency of the distribution, the more uniform the coating is considered to be. The coating completeness of the surface of the part to be inspected is used to evaluate whether the coating is evenly distributed on the surface of the device. If so, the solution coating on the surface of the part to be inspected is considered to be complete. Furthermore, based on the coating uniformity and coating completeness, a weight network layer is established for calculation, and the coating uniformity is evaluated in the weight network layer. And the coating integrity is weighted calculated, and the weighted calculation needs to be based on a large amount of data aggregation and accurate determination of the weights before targeted calculation. For example, the weight ratio of coating uniformity and coating integrity can be the first influence coefficient: the second influence coefficient is 4:6, then the influence parameters after the weighted calculation process are the first influence parameter * 0.4, the second influence parameter * 0.6, and the coating quality index sample is obtained according to the weighted calculation result. Among them, since the coating integrity has a greater impact on the non-destructive testing of the parts to be inspected than the coating uniformity in the liquid penetration testing method, the weight index of the coating uniformity in the weight network layer is less than the weight index of the coating integrity, which has a limited effect on the intelligent regulation of non-destructive testing.

[0033] Furthermore, step A440 of the present application includes:

[0034] Step A443: obtaining an initial complex index sample and a plurality of coating control parameter groups corresponding to the initial complex index sample, wherein the initial complex index sample is randomly selected from the complex index sample;

[0035] Step A444: establishing a one-to-many mapping relationship between complex indicators and coating parameters using the initial complex indicator sample and the multiple sets of coating control indicators;

[0036] Step A445: using the one-to-many mapping relationship between the complex index and the coating parameter, obtaining a coating quality index sample corresponding to each coating control parameter sample, and outputting a plurality of coating quality index samples;

[0037] Step A446: Generate an optimization space based on the multiple coating quality index samples, obtain an optimization result based on the initial complex index sample, and obtain the coating control parameter obtained by optimization. Similarly, obtain optimization results corresponding to the samples of the complex index one by one, and generate a coating control mapping library;

[0038] Step A447: Connect the coating control mapping library with the coating control module to optimize the complex indicators input in real time.

[0039] Furthermore, step A446 of the present application includes:

[0040] Step A4461: using the coating control index as an optimization variable and the coating control parameter corresponding to the coating control index as the value of the variable;

[0041] Step A4462: using the plurality of coating quality index samples, obtaining the first M coating quality indexes of the index data, and randomly assigning the remaining coating quality index samples to each of the first M coating quality indexes to form a plurality of blocks;

[0042] Step A4463: Perform competition algorithm iteration based on the multiple blocks formed to obtain the maximum coating quality index after a preset number of iterations, and output the corresponding coating control parameters as the optimization result.

[0043] In the present application, in order to improve the accuracy of non-destructive testing of parts to be inspected, the initial complex index sample and multiple sets of coating control parameters corresponding to the initial complex index sample are first extracted through the structural parameters of the parts to be inspected, and the initial complex index sample is randomly selected from the complex index sample. When there are multiple sets of coating control parameters, the coating flatness, coating smoothness, coating adhesion and coating durability are adjusted according to the level of the complex index of the parts to be inspected. Further, according to the correlation between the initial complex index sample and the multiple sets of coating control indicators, a one-to-many mapping relationship between the complex index and the coating parameter is established. When a value is taken in the coating parameter, the complex index has one and only one corresponding value, and when a value is taken in the complex index, the complex index has one and only one corresponding value. Value, there can be multiple values ​​corresponding to the coating parameters, and at the same time, the one-to-many mapping relationship between complex indicators and coating parameters is used to determine the coating quality indicator sample corresponding to each coating control parameter sample of the inspected part, which means that the solution of the inspected part is adjusted during the coating process in the coating control parameters, so that the coating quality formed after the adjustment is recorded as multiple coating quality indicator samples for output. Furthermore, in order to better coat the parts to be inspected, it is necessary to optimize the coating control parameters, and generate an optimization space after data aggregation of multiple coating quality indicator samples. The optimization space is used to optimize parameters within the demarcated data range space, so that the initial complex indicator sample is used as the optimization index. Data is traversed in the optimization space to obtain the optimization result of the initial complex indicator sample. The optimization result is the coating control parameter obtained by optimization, and the iterative optimization is performed in this way to obtain the optimization result of the complex indicator sample one by one. At the same time, the optimization results are sorted and integrated according to the level of the complex indicator to generate a coating control mapping library. Further, the coating control index is used as the optimization variable, and the coating control parameter corresponding to the coating control index is used as the value of the optimization variable to perform competitive iteration of the optimal parameter on the coating control parameter. It refers to extracting a fixed number of indicators based on multiple coating quality indicator samples, obtaining the first M coating quality indicators of the indicator data, where M is an integer greater than 2, and the remaining coating quality indicators are Standard samples, that is, samples corresponding to the M coating quality indicators extracted are randomly assigned to each of the first M coating quality indicators, thereby forming multiple blocks according to the first M coating quality indicators, each of the multiple blocks corresponds to a coating quality indicator, and finally a competitive algorithm is iterated according to the multiple blocks formed, which means that all blocks are simulated and assimilated multiple times to the block where the optimal coating quality indicator is located, and the maximum coating quality indicator after a preset number of iterations is obtained, and its corresponding coating control parameter is output as the optimization result, and the coating control mapping library constructed above is further connected to the coating control module, and a complexity indicator is input into the coating control module, and an optimal control parameter will be output accordingly.The process is to input the coating complexity index extracted from the coating control mapping library into the connected coating control module to optimize the complex index input in real time, so as to serve as reference data for the subsequent intelligent control of non-destructive testing.

[0044] Step A500: Optimizing with the coating control module, outputting coating control parameters corresponding to the coating control index, and adjusting the fluorescence detection device according to the coating control parameters.

[0045] Furthermore, step A500 of the present application also includes:

[0046] Step A510: Connecting to a nondestructive testing system terminal to obtain multiple fluorescence detection circuits, wherein each fluorescence detection circuit corresponds to a coating control module;

[0047] Step A520: Obtain a batch of parts to be inspected, and determine whether the batch of parts to be inspected are parts from the same batch;

[0048] Step A530: When the batch of parts to be inspected are parts from the same batch, output synchronous coating control parameters based on the complex indicators of the batch of parts to be inspected;

[0049] Step A540: Divide the batch of parts to be inspected into equal parts using the multiple fluorescence detection circuits, and synchronously control the coating control module of each circuit according to the synchronous coating control parameters.

[0050] Furthermore, step A510 of the present application includes:

[0051] Step A511: When the batch of parts to be inspected are not from the same batch, the batch of parts to be inspected are graded according to the complexity index corresponding to each other, and multiple complexity index levels corresponding to the multiple fluorescence detection circuits are obtained, and each fluorescence detection circuit is used to detect parts at the same complexity index level;

[0052] Step A512: outputting a plurality of optimal coating control parameters corresponding to a plurality of fluorescence detection circuits according to the plurality of complex index levels;

[0053] Step A513: After dividing the conveying routes of the batch of parts to be inspected according to the multiple complexity index levels, the fluorescence detection equipment on the corresponding fluorescence detection routes is controlled using the multiple optimized coating control parameters.

[0054] In this application, in order to better perform non-destructive testing on the parts to be inspected through the coating control module, the system is first connected to the non-destructive testing system terminal. The non-destructive testing system terminal is used to receive various coating data, fluorescence detection data, etc. during the inspection process of the parts to be inspected, so as to extract multiple fluorescence detection circuits in the parts to be inspected. The multiple fluorescence detection circuits are paths for inspecting the parts to be inspected after coating, and each fluorescence detection circuit corresponds to a coating control module to ensure the accuracy of coating control. When the batch of parts to be inspected are not parts from the same batch, the batch of parts to be inspected are clustered according to the part structure to generate multiple structural categories, which refers to whether the batch of parts to be inspected are The same batch of parts is judged. When the batch of parts to be inspected are from the same batch of parts, since the coating parameters in the parts to be inspected corresponding to different complex indicators are different, the complex indicators corresponding to the batch of parts to be inspected are used as the reference basic data, and the coating parameters under the complex indicators are recorded and integrated, so as to output the synchronous coating control parameters, and then multiple fluorescence detection circuits are used as the dividing and defining data, and the batch of parts to be inspected are divided into equal parts according to the detection routes, and the coating control module in each fluorescence detection circuit is synchronously controlled according to the synchronous coating control parameters, which means that the coating of the parts to be inspected is adjusted synchronously by the coating control module according to the data change amplitude and data change results in the coating control parameters.

[0055] At the same time, the complexity indicators corresponding to the batch of parts to be inspected are graded according to the level of the complexity indicators, which can be divided into level one, level two, and level three. Level one is the parts to be inspected with a complexity indicator greater than or equal to 80%, level two is the parts to be inspected with a complexity indicator less than 80% and greater than 50%, and level three is the parts to be inspected with a complexity indicator less than or equal to 50%. In this way, multiple complexity indicator levels corresponding to multiple fluorescence detection circuits are memorized and obtained. At the same time, in order to ensure the detection accuracy of the parts to be inspected, each fluorescence detection circuit is used to detect parts at the same complexity indicator level. Further, according to the multiple complexity indicator levels, the coating parameters are matched in the multiple fluorescence detection circuits to obtain multiple optimal coating control parameters corresponding to the multiple fluorescence detection circuits. The multiple optimal coating control parameters are used to summarize and output the adjustment data of the solution coating data when inspecting the parts to be inspected in the fluorescence detection circuit. After the conveying routes of the batch of parts to be inspected are divided according to the multiple complexity indicator levels, the fluorescence detection equipment arranged in the corresponding fluorescence detection circuit is controlled by the multiple optimal coating control parameters to perform non-destructive testing on the batch of parts to be inspected, thereby improving the accuracy of intelligent control of non-destructive testing in the later stage.

[0056] In summary, the embodiment of the present application provides an intelligent control method for non-destructive testing, which includes at least the following technical effects, thereby realizing rational and precise control of non-destructive testing, thereby improving the efficiency of non-destructive testing.

[0057] Example 2

[0058] Based on the same inventive concept as the intelligent control method for non-destructive testing in the above embodiment, Figure 3 As shown, the present application provides an intelligent control system for non-destructive testing, the system comprising:

[0059] Parameter acquisition module 1, the parameter acquisition module 1 is used to obtain the structural parameters of the part to be inspected according to the data acquisition device;

[0060] Parameter analysis module 2, the parameter analysis module 2 is used to analyze the structural parameters of the part to be inspected, obtain the surface exposure of the part to be inspected, the assembly embeddability of the part to be inspected, and the gap variability of the part to be inspected;

[0061] A parameter identification module 3 is configured to perform penetration complexity identification on the structural parameters of the part to be inspected based on the surface exposure, the assembly embeddability of the part to be inspected, and the gap variability of the part to be inspected, to obtain a first complexity index;

[0062] A first input module 4, the first input module 4 is used to input the first complex index into a coating control module, the coating control module includes a plurality of coating control indicators, the coating control indicators including the configuration of the coating solution, the control time of the solution coating, and the solution coating method;

[0063] The parameter adjustment module 5 is used to perform optimization based on the coating control module, output coating control parameters corresponding to the coating control index, and adjust the fluorescence detection device according to the coating control parameters.

[0064] Furthermore, the system also includes:

[0065] A sample acquisition module, the sample acquisition module is used to acquire samples of complex indicators and samples of coating control indicators;

[0066] a detection module, the detection module being configured to control the fluorescence detection device to perform multiple detections using the samples of the complex index and the samples of the coating control index to obtain multiple fluorescence detection data sets;

[0067] a first output module, configured to evaluate the coating quality of the multiple fluorescence detection data sets and output coating quality parameter samples, wherein each set of samples corresponds to a coating quality index sample;

[0068] The first training module is used to train the coating control module based on the coating quality index samples, the complex index samples and the coating control parameter samples.

[0069] Furthermore, the system also includes:

[0070] A data acquisition module, the data acquisition module is used to acquire the multiple fluorescence detection data sets, and acquire the coating uniformity and coating completeness of the part surface based on the multiple fluorescence detection data sets;

[0071] The first calculation module is used to establish a weight network layer for calculation based on the coating uniformity and the coating completeness to obtain a coating quality index sample, wherein the weight index of the coating uniformity in the weight network layer is less than the weight index of the coating completeness.

[0072] Furthermore, the system also includes:

[0073] A plurality of parameter acquisition modules, wherein the plurality of parameter acquisition modules are used to obtain an initial complex index sample and a plurality of coating control parameters corresponding to the initial complex index sample, wherein the initial complex index sample is randomly selected from the complex index sample;

[0074] A mapping module, the mapping module is used to establish a one-to-many mapping relationship between complex indicators and coating parameters using the initial complex indicator sample and the multiple groups of coating control indicators;

[0075] a second output module, configured to obtain a coating quality index sample corresponding to each coating control parameter sample by utilizing the one-to-many mapping relationship between the complex index and the coating parameter, and output a plurality of coating quality index samples;

[0076] A first optimization module, wherein the first optimization module is used to generate an optimization space based on the multiple coating quality index samples, obtain an optimization result based on the initial complex index sample, and the optimization result is a coating control parameter obtained by optimization. Similarly, an optimization result corresponding to each sample of the complex index is obtained, and a coating control mapping library is generated;

[0077] The second optimization module is used to connect the coating control mapping library with the coating control module to optimize the complex indicators input in real time.

[0078] Furthermore, the system also includes:

[0079] a third optimization module, the third optimization module being configured to use the coating control index as an optimization variable and a coating control parameter corresponding to the coating control index as a value of the variable;

[0080] A random allocation module, the random allocation module is used to obtain the first M coating quality indicators of the indicator data using the multiple coating quality indicator samples, and randomly allocate the remaining coating quality indicator samples to each of the first M coating quality indicators to form a plurality of blocks;

[0081] The iterative module is used to iterate the competitive algorithm according to the formed multiple blocks, obtain the maximum coating quality index after a preset number of iterations, and output the corresponding coating control parameters as the optimization result.

[0082] Furthermore, the system also includes:

[0083] A terminal connection module, the terminal connection module is used to connect to a nondestructive testing system terminal to obtain multiple fluorescence detection circuits, wherein each fluorescence detection circuit corresponds to a coating control module;

[0084] A first judgment module, the first judgment module is used to obtain a batch of parts to be inspected and determine whether the batch of parts to be inspected are parts from the same batch;

[0085] a third output module, configured to output synchronous coating control parameters based on complex indicators of the batch of parts to be inspected when the batch of parts to be inspected are parts from the same batch;

[0086] A synchronous control module is used to divide the batch of parts to be inspected into equal parts using the multiple fluorescence detection circuits, and synchronously control the coating control module of each circuit according to the synchronous coating control parameters.

[0087] Furthermore, the system also includes:

[0088] a detection module configured to, when the batch of parts to be inspected are not parts of the same batch, classify the batch of parts to be inspected based on the complexity index corresponding to each other, and obtain multiple complexity index levels corresponding to the multiple fluorescence detection circuits, each fluorescence detection circuit being configured to detect parts at the same complexity index level;

[0089] a fourth output module, configured to output a plurality of optimized coating control parameters corresponding to a plurality of fluorescence detection circuits according to the plurality of complex indicator levels;

[0090] A division module is used to divide the conveying routes of the batch of parts to be inspected according to the multiple complexity index levels, and then control the fluorescence detection equipment on the corresponding fluorescence detection routes with the multiple optimal coating control parameters.

[0091] Through the detailed description of the intelligent control method for non-destructive testing in the foregoing specification, those skilled in the art can clearly understand the intelligent control system for non-destructive testing in this embodiment. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0092] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An intelligent control method for non-destructive testing, characterized in that: The method comprises: Acquire the structural parameters of the part to be inspected according to the data acquisition device; Analyzing the structural parameters of the part to be inspected to obtain the surface exposure of the part to be inspected, the assembly embeddability of the part to be inspected, and the gap variability of the part to be inspected; Performing penetration complexity identification on the structural parameters of the part to be inspected based on the surface exposure, assembly embeddability of the part to be inspected, and gap variability of the part to be inspected to obtain a first complexity index; Inputting the first complex index into a coating control module, wherein the coating control module includes a plurality of coating control indexes, wherein the coating control indexes include the configuration of the coating solution, the control time of the solution coating, and the solution coating method; Performing optimization using the coating control module, outputting coating control parameters corresponding to the coating control index, and adjusting the fluorescence detection device according to the coating control parameters; Obtain samples of complex indicators and samples of coating control indicators; Controlling the fluorescence detection device to perform multiple detections using the samples of the complex index and the samples of the coating control index to obtain multiple fluorescence detection data sets; evaluating the coating quality of the multiple fluorescence detection data sets and outputting coating quality parameter samples, wherein each set of samples corresponds to a coating quality index sample; The coating control module is obtained by training according to the coating quality index sample, the complex index sample and the coating control parameter sample; evaluating a coating quality of the fluorescence detection dataset, the method further comprising: Acquire the multiple fluorescence detection data sets, and acquire coating uniformity and coating completeness of the part surface according to the multiple fluorescence detection data sets; According to the coating uniformity and the coating completeness, a weighted network layer is established for calculation to obtain a coating quality index sample, wherein the weighted index of the coating uniformity in the weighted network layer is less than the weighted index of the coating completeness; The coating control module is obtained by training, and the coating control module includes an automatic optimization module. The optimization method of the automatic optimization module includes: Obtaining an initial complex index sample and a plurality of groups of coating control parameters corresponding to the initial complex index sample, wherein the initial complex index sample is randomly selected from the complex index sample; Establishing a one-to-many mapping relationship between complex indicators and coating parameters using the initial complex indicator sample and the multiple groups of coating control indicators; Utilizing the one-to-many mapping relationship between the complex index and the coating parameter, a coating quality index sample corresponding to each coating control parameter sample is obtained, and a plurality of coating quality index samples are output; Generate an optimization space with the multiple coating quality index samples, obtain an optimization result based on the initial complex index sample, the optimization result is the coating control parameter obtained by optimization, and so on, obtain the optimization result of the one-to-one correspondence of the samples of the complex index, and generate a coating control mapping library; The coating control mapping library is connected to the coating control module to optimize the complex indicators input in real time.

2. The method according to claim 1, wherein Generating an optimization space using the plurality of coating quality index samples to obtain an optimization result based on the initial complex index sample, the method comprising: The coating control index is used as the optimization variable, and the coating control parameter corresponding to the coating control index is used as the value of the variable; Using the plurality of coating quality index samples, obtaining first M coating quality indexes of the index data, and randomly assigning the remaining coating quality index samples to each of the first M coating quality indexes to form a plurality of blocks; The competition algorithm is iterated based on the multiple blocks formed to obtain the maximum coating quality index after a preset number of iterations, and the corresponding coating control parameters are output as the optimization result.

3. The method according to claim 1, wherein The method further comprises: Connecting to a nondestructive testing system terminal to obtain multiple fluorescence detection circuits, wherein each fluorescence detection circuit corresponds to a coating control module; Obtaining a batch of parts to be inspected, and determining whether the batch of parts to be inspected are parts from the same batch; When the batch of parts to be inspected are parts from the same batch, outputting synchronous coating control parameters based on the complex indicators of the batch of parts to be inspected; The batch of parts to be inspected is equally divided into the plurality of fluorescence detection circuits, and the coating control module of each circuit is synchronously controlled according to the synchronous coating control parameters.

4. The method according to claim 3, wherein The method further comprises: When the batch of parts to be inspected are not from the same batch of parts, the batch of parts to be inspected are graded according to the complexity index corresponding to each other, and multiple complexity index levels corresponding to the multiple fluorescence detection circuits are obtained, and each fluorescence detection circuit is used to detect parts at the same complexity index level; Outputting a plurality of optimal coating control parameters corresponding to a plurality of fluorescence detection circuits according to the plurality of complex indicator levels; After dividing the conveying routes of the batch of parts to be inspected according to the multiple complexity index levels, the fluorescence detection equipment on the corresponding fluorescence detection routes is controlled using the multiple optimized coating control parameters.

5. An intelligent control system for non-destructive testing, characterized in that: The system comprises: A parameter acquisition module, which is used to acquire structural parameters of the part to be inspected according to the data acquisition device; A parameter analysis module, wherein the parameter analysis module is used to analyze the structural parameters of the part to be inspected, and obtain the surface exposure of the part to be inspected, the assembly embeddability of the part to be inspected, and the gap variability of the part to be inspected; a parameter identification module, the parameter identification module being configured to perform penetration complexity identification on the structural parameters of the part to be inspected based on the surface exposure, the assembly embeddability of the part to be inspected, and the gap variability of the part to be inspected, to obtain a first complexity index; A first input module, the first input module is used to input the first complex index into a coating control module, the coating control module includes a plurality of coating control indicators, the coating control indicators include the configuration of the coating solution, the control time of the solution coating, and the solution coating method; A parameter adjustment module is used to optimize the coating control module, output coating control parameters corresponding to the coating control index, and adjust the fluorescence detection equipment according to the coating control parameters.

Images