Enameled aluminum wire on-line quality detection method

Abstract

The invention is applicable to the technical field of enameled aluminum wire production, and particularly relates to an enameled aluminum wire on-line quality detection method, which comprises the following steps: acquiring real-time defect data of an aluminum wire; obtaining predicted defect data of the first painting link according to the real-time defect data; determining equipment parameters of a first painting link based on the predicted defect data and the real-time defect data; and according to the equipment parameters of the first-time painting link, controlling painting equipment, and obtaining actual defect data of the first-time painting link. Therefore, the online quality detection method for the enameled aluminum wire provided by the embodiment of the invention can solve the problem that the quality defect of the enameled aluminum wire is covered in the painting process.

Description

Technical Field

[0001] This application belongs to the technical field of enameled aluminum wire production, and particularly relates to an on-line quality inspection method for enameled aluminum wire. Background Art

[0002] On-line quality inspection of enameled aluminum wire refers to the real-time and continuous monitoring of the key quality indicators of products through automated inspection equipment on the enameled aluminum wire production line to ensure that the products meet the technical standards and customer requirements.

[0003] The painting process will form an insulating paint film on the surface of the aluminum conductor. This paint film has optical shielding properties, making some conductor surface defects (such as micro-cracks and oxidation spots) physically covered after painting. And inappropriate process parameters in the painting process will have a superimposed impact on the quality of the aluminum wire. For example, high-viscosity paint liquid may produce "paint tumors" during the curing process due to insufficient leveling, covering local pits on the conductor; uneven furnace temperature will cause differences in the curing speed of the paint film, covering the problem of excessive conductor ovality. Therefore, in the prior art, there is a problem that quality defects of enameled aluminum wire are covered up during the painting process. Summary of the Invention

[0004] The embodiments of this application provide an on-line quality inspection method for enameled aluminum wire, which can solve the problem that quality defects of enameled aluminum wire are covered up during the painting process.

[0005] In a first aspect, the embodiments of this application provide an on-line quality inspection method for enameled aluminum wire, including:

[0006] Obtain real-time defect data of the aluminum wire; wherein, the real-time defect data is used to reflect the defects of the aluminum wire before painting, and the real-time defect data includes a defect area and a defect type, and the defect area includes a defect position and a defect area;

[0007] Obtain predicted defect data for the first painting process according to the real-time defect data; wherein, the predicted defect data includes a defect probability, a defect area, and a defect type;

[0008] Determine the equipment parameters for the first painting process based on the predicted defect data and the real-time defect data; wherein, the equipment parameters include the painting speed, the paint viscosity, and the baking temperature;

[0009] Control the painting equipment according to the equipment parameters for the first painting process, and obtain the actual defect data for the first painting process.

[0010] The above technical solutions in the embodiments of this application have at least the following technical effects:

[0011] The online quality detection method for enameled aluminum wire provided in the embodiments of the present application obtains real-time defect data for the aluminum wire; obtains predicted defect data for the first painting step based on the real-time defect data; determines the equipment parameters for the first painting step based on the predicted defect data and the real-time defect data; controls the painting equipment based on the equipment parameters for the first painting step, and obtains actual defect data for the first painting step. Therefore, the online quality detection method for enameled aluminum wire provided in the embodiments of the present application dynamically adjusts the parameters of the painting equipment based on the predicted defect data, enabling the painting process to compensate for or avoid potential defects and improve the quality of the paint film. Through pre-detection, predictive analysis, and parameter optimization, the problem of defects being concealed during the painting process is effectively solved, improving the overall quality of the enameled aluminum wire.

[0012] In a possible implementation of the first aspect, the method further includes:

[0013] Determine whether the actual defect data is within the tolerance range;

[0014] If the actual defect data is within the tolerance range, the actual defect data of the next painting step is obtained according to the equipment parameters;

[0015] If the actual defect data is not within the tolerance range, adjust the equipment parameters according to the actual defect data;

[0016] The actual defect data of the next painting process is obtained based on the adjusted equipment parameters;

[0017] Repeat the above steps until the painting is complete.

[0018] In a possible implementation of the first aspect, obtaining predicted defect data for the first painting step based on the real-time defect data includes:

[0019] Acquiring historical painting data; wherein the historical painting data includes defect areas, defect types, and corresponding equipment parameters;

[0020] Obtaining defect evolution data based on the historical painting data; wherein the defect evolution data includes the probability and path of defect evolution of different types and areas;

[0021] Establishing a defect influence matrix based on the real-time defect data and the defect evolution data; wherein the defect influence matrix is used to reflect the probability and path of the defects in the real-time defect data evolving in the subsequent painting process;

[0022] Calculate the basic probability of the current defect state transferring to each subsequent state according to the defect influence matrix;

[0023] The predicted defect data of the first painting step is obtained according to the basic probability.

[0024] In a possible implementation of the first aspect, obtaining the defect evolution data based on the historical painting data includes:

[0025] Obtaining a state transition matrix based on the historical painting data; wherein, the state transition matrix is used to reflect the transition frequencies between various states in the historical data, and the states include the type and area of the defect;

[0026] Obtaining the defect evolution data based on the state transition matrix.

[0027] In a possible implementation of the first aspect, establishing a defect influence matrix based on the real-time defect data and the defect evolution data includes:

[0028] Calculating the similarity between the real-time defect data and the defect evolution data, and obtaining a similarity matrix;

[0029] Obtaining the defect influence matrix based on the similarity matrix.

[0030] In a possible implementation of the first aspect, obtaining the predicted defect data for the first painting step based on the basic probability includes:

[0031] Obtaining the conditional probability of generating a defect under the condition of the real-time defect data based on the historical painting data;

[0032] Determining the predicted defect data for the first painting step based on the basic probability and the conditional probability.

[0033] In a possible implementation of the first aspect, determining the device parameters based on the predicted defect data and the real-time defect data includes:

[0034] Obtaining an error term and an error change rate based on the predicted defect data and the real-time defect data; wherein, the error term is the difference between the predicted defect area and the tolerable defect area, and the error change rate is the defect area change rate per unit time;

[0035] Mapping the error term and the error change rate to obtain a fuzzy set; wherein, the fuzzy set is used to reflect the fuzzy state of the error term and the corresponding error change rate;

[0036] Obtaining a fuzzy output quantity based on the fuzzy set and a preset fuzzy rule base; wherein, the fuzzy output quantity is used to reflect the adjustment amplitude and direction of the device parameters, and the fuzzy rule base is used to reflect the non-linear relationship between the error term, the error change rate, and the fuzzy output quantity;

[0037] Obtain a real-time correction value according to the fuzzy output quantity; wherein, the real-time correction value is used to correct device parameters;

[0038] Obtain device parameters according to the real-time correction value and the predicted defect data.

[0039] In a possible implementation manner of the first aspect, the mapping of the error term and the error change rate to obtain a fuzzy set includes:

[0040] Substitute the error term and the error change rate into a membership function to obtain membership degrees; wherein, the membership degrees are used to reflect the degrees to which the error term and the error change rate belong to various sets;

[0041] Determine the fuzzy set based on the membership degrees.

[0042] In a possible implementation manner of the first aspect, the obtaining of the fuzzy output quantity according to the fuzzy set and a preset fuzzy rule base includes:

[0043] Match the fuzzy set with the preset fuzzy rule base to obtain activation rules; wherein, the activation rules are used to reflect the device parameter adjustment strategies taken under the combination of the error term and the error change rate;

[0044] Obtain the fuzzy output quantity according to the activation rules.

[0045] In a possible implementation manner of the first aspect, the obtaining of the device parameters according to the real-time correction value and the predicted defect data includes:

[0046] Obtain device parameters according to the defect regions and weights of different defects in the real-time correction value and the predicted defect data.

[0047] In a possible implementation manner of the first aspect, after controlling the painting device according to the device parameters of the first painting link and obtaining the actual defect data of the first painting link, the method further includes:

[0048] Adjust the fuzzy rule base according to the actual defect data and the predicted defect data.

[0049] In a second aspect, an on-line quality detection device for enameled aluminum wire provided by an embodiment of the present application includes:

[0050] An acquisition module, configured to acquire real-time defect data of an aluminum wire; wherein, the real-time defect data is used to reflect defects of the aluminum wire before painting, and the real-time defect data includes a defect region and a defect type, and the defect region includes a defect position and a defect area;

[0051] A prediction defect module, configured to obtain prediction defect data of the first painting process according to the real-time defect data; wherein, the prediction defect data includes defect probability, defect area and defect type;

[0052] An equipment parameter module, configured to determine the equipment parameters of the first painting process based on the prediction defect data and the real-time defect data; wherein, the equipment parameters include painting speed, paint viscosity and baking temperature;

[0053] An actual defect module, configured to control the painting equipment according to the equipment parameters of the first painting process and obtain the actual defect data of the first painting process.

[0054] In a third aspect, an embodiment of the present application provides an online quality inspection device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in any one of the above first aspects is implemented.

[0055] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the method described in any one of the above first aspects is implemented.

[0056] In a fifth aspect, an embodiment of the present application provides a computer program product, and when the computer program product runs on an online quality inspection device, the online quality inspection device is enabled to execute the method described in any one of the above first aspects.

[0057] It can be understood that the beneficial effects of the above second aspect to fifth aspect can refer to the relevant descriptions in the above first aspect, and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0059] Figure 1 is a schematic flowchart of an online quality inspection method for enameled aluminum wire provided by an embodiment of the present application;

[0060] Figure 2 is a schematic implementation flowchart of steps S200, S220, S230 and S250 in the online quality inspection method for enameled aluminum wire provided by an embodiment of the present application;

[0061] Figure 3It is a schematic diagram of the implementation processes of steps S300, S320, S330, S350, and S400 in the on-line quality inspection method for enameled aluminum wire provided by an embodiment of the present application;

[0062] Figure 4 It is another schematic diagram of the implementation process of the on-line quality inspection method for enameled aluminum wire provided by an embodiment of the present application;

[0063] Figure 5 It is a schematic structural diagram of the on-line quality inspection device for enameled aluminum wire provided by an embodiment of the present application;

[0064] Figure 6 It is a schematic structural diagram of the on-line quality inspection equipment provided by an embodiment of the present application. Detailed implementation manners

[0065] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0066] It should be understood that when used in the specification of the present application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0067] It should also be understood that the term " / and" as used in the specification of the present application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0068] As used in the specification of the present application and the appended claims, the term "if" can be interpreted as "when", "once", "in response to determining", or "in response to detecting" according to the context. Similarly, the phrase "if determined" or "if detecting [the described condition or event]" can be interpreted as meaning "once determined", "in response to determining", "once detecting [the described condition or event]", or "in response to detecting [the described condition or event]" according to the context.

[0069] In addition, in the description of the specification of the present application and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0070] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "comprising", "including", "having" and their variants all mean "including but not limited to", unless otherwise specifically emphasized.

[0071] In the related art, a paint film is formed on the surface of an aluminum conductor during the painting process. This paint film has optical shielding properties, such that some conductor surface defects (such as minute cracks, oxidation spots) are physically covered after painting. Moreover, inappropriate process parameters in the painting step can have a cumulative impact on the quality of the aluminum wire. For example, high-viscosity paint liquid may produce "paint tumors" during the curing process due to insufficient leveling, covering local pits on the conductor; uneven furnace temperature can lead to differences in the curing speed of the paint film, covering the problem of excessive conductor ovality. Therefore, there is a problem that quality defects are masked during the quality inspection of enameled aluminum wire.

[0072] To solve the above problems, an embodiment of this application provides an on-line quality inspection method for enameled aluminum wire. In this method, real-time defect data of the aluminum wire is obtained; predicted defect data for the first painting step is obtained based on the real-time defect data; equipment parameters for the first painting step are determined based on the predicted defect data and the real-time defect data; and the painting equipment is controlled according to the equipment parameters for the first painting step, and actual defect data for the first painting step is obtained. Therefore, the on-line quality inspection method for enameled aluminum wire provided by the embodiment of this application dynamically adjusts the parameters of the painting equipment according to the predicted defect data, enabling the painting process to compensate for or avoid potential defects and improving the quality of the paint film. Through pre-detection, predictive analysis, and parameter optimization, the problem that defects are masked during the painting process is effectively solved, and the overall quality of the enameled aluminum wire is improved.

[0073] The on-line quality inspection method for enameled aluminum wire provided by the embodiment of this application can be applied to an on-line quality inspection device. At this time, the on-line quality inspection device is the execution subject of the on-line quality inspection method for enameled aluminum wire provided by the embodiment of this application, and this application does not impose any restrictions on the specific type of the on-line quality inspection device.

[0074] For example, the on-line quality inspection device may be a station (STAION, ST) in a WLAN, and may be a mobile phone, a tablet computer, a vehicle-mounted device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a desktop computer, a handheld device with wireless communication function, a computing device, or other processing devices connected to a wireless modem, a vehicle-mounted device, a vehicle-to-internet terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, etc., but not limited thereto.

[0075] To better understand the on-line quality inspection method for enameled aluminum wire provided by the embodiments of the present application, the following provides an exemplary introduction to the specific implementation process of the on-line quality inspection method for enameled aluminum wire provided by the embodiments of the present application.

[0076] Figure 1 FIG. shows a schematic flowchart of the on-line quality inspection method for enameled aluminum wire provided by the embodiments of the present application. The on-line quality inspection method for enameled aluminum wire includes:

[0077] S100, obtaining real-time defect data of the aluminum wire. Among them, the real-time defect data is used to reflect the defects of the aluminum wire before painting. The real-time defect data includes a defect area and a defect type. The defect area includes a defect position and a defect area.

[0078] Exemplarily, a high-resolution industrial camera can be used to continuously photograph the aluminum wire to obtain a surface image of the aluminum wire. Preprocessing operations such as grayscale conversion and filtering denoising are performed on the surface image. A target detection algorithm based on deep learning (such as YOLO, Faster R-CNN, etc.) is used to detect defects in the preprocessed surface image, and the defect area and defect type are identified. For example, if a defect area is identified with a center position coordinate of (x = 100, y = 200), an area of 50 square millimeters, and a defect type of scratch, the real-time defect data can be recorded as: {defect position: (100, 200), defect area: 50, defect type: scratch}; if a defect area in the shape of an approximate rectangle is identified, with the upper left corner coordinate of the rectangle frame being (x1 = 90, y1 = 190) and the lower right corner coordinate being (x2 = 110, y2 = 210) (for some defects with complex shapes, the defect position is represented by the coordinates of polygon vertices, etc.), and an area of (110 - 90) × (210 - 190) = 400 / 2 = 200, and the defect type is scratch, the real-time defect data can be recorded as: {defect position: [(90, 190), (110, 210)], defect area: 200, defect type: scratch}.

[0079] S200. Obtain the predicted defect data for the first painting process based on the real-time defect data. Among them, the predicted defect data includes defect probability, defect area, and defect type.

[0080] Exemplarily, a prediction model (such as a neural network, support vector machine, etc.) can be trained based on historical painting data and real-time defect data, and the real-time defect data is input into the trained prediction model to obtain the predicted defect data for the first painting process.

[0081] In a possible implementation, please refer to Figure 2 , S200. Obtain the predicted defect data for the first painting process based on the real-time defect data, including:

[0082] S210. Obtain historical painting data. Among them, the historical painting data includes defect area, defect type, and corresponding equipment parameters.

[0083] Exemplarily, the historical painting data can be collected and cleaned from the enterprise's production management system, quality inspection system, or database.

[0084] S220. Obtain defect evolution data based on the historical painting data. Among them, the defect evolution data includes the probabilities and paths of defect evolution of different types and areas.

[0085] Exemplarily, data mining algorithms (such as association rule mining, clustering analysis, etc.) can be used to mine the historical painting data to find the association relationships between defects of different types and areas and the evolution laws during the painting process, and calculate the probabilities and paths of defect evolution of different types and areas. For example, for a scratch defect with an area of 10 - 20 square millimeters, the probability of evolving into a bubble defect in the subsequent painting process is 0.3, the probability of evolving into a color difference defect is 0.2, and the probability of remaining a scratch defect is 0.5; its evolution path is scratch defect → (30% probability) bubble defect, scratch defect → (20% probability) color difference defect, scratch defect → (50% probability) scratch defect.

[0086] Optionally, please refer to Figure 2 , S220. Obtain defect evolution data based on the historical painting data, including:

[0087] S221. Obtain a state transition matrix based on the historical painting data. Among them, the state transition matrix is used to reflect the transition frequencies between various states in the historical data, and the states include the type and area of the defect.

[0088] Exemplarily, a state transition matrix can be obtained based on historical painting data. Here, the rows and columns of the state transition matrix respectively correspond to all defined states. The elements in the state transition matrix represent the frequencies of transitioning from one state to another. Initially, all elements are set to 0. Traverse all state transition sequences. For each transition, increment the value of the corresponding element in the state transition matrix by 1.

[0089] S222. Obtain defect evolution data based on the state transition matrix.

[0090] Exemplarily, the state transition matrix can be normalized by dividing each element by the sum of the elements in its row to obtain a state transition probability matrix. Here, the elements in the state transition probability matrix represent the probabilities of transitioning from one state to another. For example, for the above state transition matrix, the probability of state A transitioning to state B is 2 / (2 + 1) = 2 / 3, and the probability of transitioning to state C is 1 / (2 + 1) = 1 / 3. Obtain defect evolution data based on the transition probability matrix.

[0091] Through the above steps S221 to S222, the defect evolution data obtained based on the state transition matrix can accurately reflect the transfer law of defects during the historical painting process, thereby accurately predicting the evolution of defects during future painting processes, helping to take measures in advance to reduce the generation of defects, improve the painting quality, and after understanding the evolution law of defects, the process parameters of the painting link can be adjusted targeted.

[0092] S230. Establish a defect influence matrix based on real-time defect data and defect evolution data. Here, the defect influence matrix is used to reflect the probabilities and paths of the defects in the real-time defect data evolving during subsequent painting processes.

[0093] Exemplarily, a defect influence matrix can be constructed based on real-time defect data and defect evolution data. Here, the rows of the defect influence matrix represent different defect states in the real-time defect data, the columns represent possible defect states during subsequent painting processes, and the elements therein represent the probabilities of the real-time defect states transitioning to subsequent defect states.

[0094] Optionally, please refer to Figure 2 , S230. Establish a defect influence matrix based on real-time defect data and defect evolution data, including:

[0095] S231. Calculate the similarity between the real-time defect data and the defect evolution data and obtain a similarity matrix.

[0096] Exemplarily, the similarity between the real-time defect data and the defect evolution data can be calculated by similarity measurement methods such as Euclidean distance and cosine similarity, and a similarity matrix can be obtained.

[0097] S232. Obtain the defect influence matrix based on the similarity matrix.

[0098] Exemplarily, the similarity matrix can be normalized to convert the similarity values into values between 0 and 1, and the defect influence matrix can be calculated according to the assigned weights, as shown in Table 1 below.

[0099] State A State B State C State 1 0.4 0.2 0.4 State 2 0.1 0.6 0.3

[0100] Table 1

[0101] Through the above steps S231 to S232, the defect influence matrix can clearly show the influence degree of each real-time defect data on defect evolution, thereby helping to accurately locate key defects. By focusing on defects with greater influence, resources can be concentrated for key monitoring and intervention, improving the efficiency of defect control.

[0102] S240. Calculate the basic probabilities of the current defect state transferring to each subsequent state according to the defect influence matrix.

[0103] Exemplarily, the matrix operation method can be used to calculate the basic probabilities of the current defect state transferring to each subsequent state according to the defect influence matrix and the probability distribution of the current defect state. For example, if the probability of the current defect state being state 1 is 0.6 and the probability of state 2 is 0.4, then according to the defect influence matrix shown in Table 1 above, calculate the basic probabilities of transferring to each subsequent state: the probability of transferring to state A = 0.6×0.4 + 0.4×0.1 = 0.28, the probability of transferring to state B = 0.6×0.2 + 0.4×0.6 = 0.36, the probability of transferring to state C = 0.6×0.4 + 0.4×0.3 = 0.36. After normalizing the above probabilities, the basic probability of transferring to state A is 0.28 / (0.28 + 0.36 + 0.36) ≈ 0.298, the basic probability of transferring to state B is 0.36 / (0.28 + 0.36 + 0.36) ≈ 0.383, and the basic probability of transferring to state C is 0.36 / (0.28 + 0.36 + 0.36) ≈ 0.319.

[0104] S250. Obtain the predicted defect data for the first painting process according to the basic probabilities.

[0105] Exemplarily, the predicted defect data for the first painting process can be obtained according to the above calculated basic probabilities and the possible defect states in the subsequent painting process.

[0106] By performing the above steps S210 to S250 and continuously updating the historical painting data and real-time defect data, the dynamic optimization of the painting process can be achieved; adjusting the equipment parameters in a timely manner according to the predicted defect data can improve the stability and consistency of the painting quality; accurate defect prediction and dynamic optimization can reduce the waste of painting materials and the extension of painting time, and lower the production cost.

[0107] Optionally, please refer to Figure 2 , S250, to obtain the predicted defect data for the first painting session based on the basic probability, including:

[0108] S251, to obtain the conditional probability of defects occurring under the condition of real-time defect data based on the historical painting data.

[0109] Exemplarily, the conditional probability of defects occurring under the condition of real-time defect data can be calculated based on the historical painting data. For example, where Y represents whether a defect occurs, X represents the real-time defect data (which can be regarded as a combination of multiple features), P(Y∣X) represents the conditional probability of defects occurring under the condition of real-time defect data, P(X∣Y) represents the probability of the real-time defect data appearing under the condition of a defect occurring, P(Y) represents the prior probability of a defect occurring, P(X) represents the probability of the real-time defect data appearing, and using the historical painting data, the conditional probability P(Y∣X) of defects occurring under the condition of real-time defect data is calculated.

[0110] S252, to determine the predicted defect data for the first painting session based on the basic probability and the conditional probability.

[0111] Exemplarily, the weighted average method can be used to assign different weights to the basic probability and the conditional probability of the current defect state transitioning to each subsequent state, and determine the predicted defect data for the first painting session.

[0112] By performing the above steps S251 to S252, combining the historical painting data and the real-time defect data, and using the conditional probability and the basic probability for prediction, the possibility of defects occurring in the first painting session can be more accurately reflected, reducing the prediction error; accurate defect prediction data can provide strong support for production decisions. For example, according to the prediction results, the production process parameters can be adjusted in advance, quality inspection can be strengthened, etc., so as to reduce the risk of defect occurrence and improve the product quality; effective defect prediction can reduce the reject rate and rework rate caused by defects, and lower the production cost. At the same time, by optimizing the production decision, the production efficiency can also be improved, further reducing the production cost.

[0113] S300, to determine the equipment parameters for the first painting session based on the predicted defect data and the real-time defect data. Among them, the equipment parameters include the painting speed, the viscosity of the paint solution, and the baking temperature.

[0114] Exemplarily, an optimization algorithm (such as a genetic algorithm, a particle swarm algorithm, etc.) can be used to optimize the parameters of the painting equipment. With the goal of reducing defects after painting, an objective function is constructed, and the optimal equipment parameters obtained by searching through the optimization algorithm are the equipment parameters for the first painting step.

[0115] In a possible implementation, please refer to Figure 3 , S300, determining the equipment parameters based on the predicted defect data and the real-time defect data, including:

[0116] S310, obtaining the error term and the error change rate according to the predicted defect data and the real-time defect data. Among them, the error term is the difference between the predicted defect area and the tolerable defect area, and the error change rate is the change rate of the defect area per unit time.

[0117] Exemplarily, the error term and the error change rate can be obtained according to the predicted defect data and the real-time defect data. For example, the error term e = A p -A t , where A p is the predicted defect area, A t is the tolerable defect area, and the error change rate where A t+1 is the real-time defect area at the current moment, A t is the real-time defect area at the previous moment, and Δt is the time interval.

[0118] S320, mapping the error term and the error change rate to obtain a fuzzy set. Among them, the fuzzy set is used to reflect the fuzzy state of the error term and the corresponding error change rate.

[0119] Exemplarily, according to the value ranges of the error term and the error change rate, appropriate membership functions (such as triangular membership functions, trapezoidal membership functions, and Gaussian membership functions, etc.) can be defined. For example, for the error term, five sets of "Negative Big (NB)", "Negative Small (NS)", "Zero (ZO)", "Positive Small (PS)", and "Positive Big (PB)" can be defined, and their membership functions are respectively determined. Substitute the actual values of the error term and the error change rate into the corresponding membership functions, calculate the membership degrees of them belonging to each set, and determine the fuzzy set according to the membership degrees.

[0120] Optionally, please refer to Figure 3 , S320, mapping the error term and the error change rate to obtain a fuzzy set, including:

[0121] S321, substituting the error term and the error change rate into the membership function to obtain the membership degree. Among them, the membership degree is used to reflect the degree to which the error term and the error change rate belong to various sets.

[0122] Exemplarily, the actual values of the error term and the error change rate can be substituted into the corresponding membership functions (such as triangular membership functions, trapezoidal membership functions, Gaussian membership functions, etc.) to calculate the membership degrees for each set.

[0123] S322. Determine the fuzzy set based on the membership degree.

[0124] Exemplarily, a membership degree threshold can be set. When the membership degree corresponding to a certain set is greater than the membership degree threshold, that set is determined as the fuzzy set.

[0125] Through the above steps S321 to S322, by using the membership function and the fuzzy rule base, the device parameters can be adjusted more accurately according to real-time data, improving the scientificity and effectiveness of the decision-making; fuzzy control has strong adaptability to the nonlinearity and uncertainty of the system and can maintain stable operation in a complex and changeable production environment; applying the fuzzy control method to actual production, by obtaining prediction and real-time defect data in real time and dynamically adjusting the device parameters, the product quality and production efficiency can be ensured to be improved.

[0126] S330. Obtain the fuzzy output quantity according to the fuzzy set and the preset fuzzy rule base. Among them, the fuzzy output quantity is used to reflect the adjustment range and direction of the device parameters, and the fuzzy rule base is used to reflect the nonlinear relationship between the error term, the error change rate and the fuzzy output quantity.

[0127] It can be understood that the fuzzy rule base is used to reflect the nonlinear relationship between the error term, the error change rate and the fuzzy output quantity.

[0128] Exemplarily, according to the fuzzy sets to which the input error term and error change rate belong, using the fuzzy rule base, reasoning can be performed according to the Mamdani inference method to obtain the fuzzy output quantity.

[0129] Optionally, please refer to Figure 3 , S330. Obtain the fuzzy output quantity according to the fuzzy set and the preset fuzzy rule base, including:

[0130] S331. Match the fuzzy set and the preset fuzzy rule base to obtain the activation rule. Among them, the activation rule is used to reflect the device parameter adjustment strategy adopted under the combination of the error term and the error change rate.

[0131] Exemplarily, each rule in the fuzzy rule base can be traversed, and the input fuzzy set is matched with the conditions in the rule. If the input fuzzy set meets the conditions of the rule (that is, the membership degree of each input variable in the corresponding fuzzy set is greater than 0), then that rule is determined as the activation rule.

[0132] S332. Obtain the fuzzy output quantity according to the activation rule.

[0133] Exemplarily, the input fuzzy information can be converted into output fuzzy information according to the activation rule to obtain the fuzzy output quantity. For example, the activation rule is: "If the error term is positive large (PB) and the error change rate is positive small (PS), then the device parameter adjustment strategy is large increase (LA)", then the fuzzy output quantity is "large increase (LA)".

[0134] Through the above steps S331 to S332, fuzzy control can process uncertain and non-linear information. Through the matching of the fuzzy rule base and the activation rule, the device parameters can be dynamically adjusted according to different combinations of error terms and error change rates, improving the flexibility and adaptability of decision-making. Since fuzzy control has a strong tolerance for noise and interference, during the operation of the device, even if there are some small errors and fluctuations, the on-line quality inspection device for enameled aluminum wire can still operate stably, enhancing the robustness. By accurately calculating the membership degree of the fuzzy output quantity, the fuzzy information can be converted into a specific device parameter adjustment strategy to achieve precise adjustment of device parameters and improve product quality and production efficiency.

[0135] S340, obtain the real-time correction value according to the fuzzy output quantity. Among them, the real-time correction value is used to correct the device parameters.

[0136] Exemplarily, a defuzzification method (such as the centroid method, the maximum membership degree method, etc.) can be used to convert the fuzzy output quantity into an accurate numerical value, that is, the real-time correction value.

[0137] S350, obtain the device parameters according to the real-time correction value and the predicted defect data.

[0138] Exemplarily, according to the defect probability, defect area and defect type in the predicted defect data, a group of basic device parameters can be initially determined, corresponding weight coefficients are assigned to different types of defects, and the basic device parameters are linearly combined with the real-time correction value to obtain the device parameters.

[0139] Through the above steps S310 to S350, the influence of the error term and the error change rate is comprehensively considered, and the device parameters can be adjusted more accurately, reducing the generation of defects caused by improper parameter settings. Fuzzy control has a strong adaptability to the non-linearity and uncertainty of the on-line quality inspection device for enameled aluminum wire, can operate stably in a complex and changeable production environment, and improves the robustness.

[0140] Optionally, please refer to [[ID=2 or 23]] Figure 3 S3 --

[0141] S351, obtain the device parameters according to the real-time correction value and the defect area and weight of different defects in the predicted defect data.

[0142] Exemplarily, a mathematical model (such as a finite element analysis model, etc.) can be adopted to construct a defect influence function according to the defect regions of different defects in the predicted defect data, and combined with the real-time correction value and the weights in the predicted defect data, the defect influence function is weighted and calculated to obtain the adjustment amount of the device parameters. For example, where ΔP represents the adjustment amount of the device parameters, ω i represents the weight of the i-th defect, and f i (R i , C) represents the influence function of the i-th defect, R i represents the defect region of the i-th defect, C represents the real-time correction value, and the device parameters are determined according to the adjustment amount of the device parameters.

[0143] Through the above step S351, by precisely adjusting the device parameters, the influence of defects on the device performance can be reduced, and the operation efficiency and stability of the device can be improved; timely discovery and adjustment of the device parameters can avoid the further expansion of defects, reduce the wear and damage of the device, and thus extend the service life of the device; precise adjustment of the device parameters can reduce the frequency of device failures and lower the maintenance and repair costs of the device.

[0144] S400, control the painting equipment according to the device parameters of the first painting process, and obtain the actual defect data of the first painting process.

[0145] It can be understood that the painting equipment is controlled to perform painting operations according to the device parameters of the optimized painting equipment in the first painting process. After the first painting process is completed, the painted aluminum wire is subjected to defect detection to obtain the actual defect data.

[0146] In a possible implementation manner, please refer to Figure 3 , after S400, controlling the painting equipment according to the device parameters of the first painting process and obtaining the actual defect data of the first painting process, the method further includes:

[0147] S401, adjust the fuzzy rule base according to the actual defect data and the predicted defect data.

[0148] Exemplarily, the actual defect data can be compared with the predicted defect data to analyze the accuracy and deviation of the prediction. For example, the matching degree of the predicted defect data and the actual defect data in terms of type, location, and frequency can be statistically analyzed. According to the comparison and analysis results, the effectiveness of each rule in the fuzzy rule base is evaluated. If the difference between the predicted defect data corresponding to a certain rule and the actual defect data is greater than the preset threshold, it is considered that the effectiveness of this rule is relatively low, and the fuzzy rule base is adjusted in different cases: for the cases that exist in the actual defect data but are not covered in the predicted defect data, new fuzzy rules are analyzed, summarized, and added to the rule base; for the rules with relatively low prediction accuracy, the conditions and conclusions of the rules are adjusted according to the actual defect data. For example, if the predicted defect location of a certain rule deviates greatly from the actual location, then modify the condition description about the location in the rule; for the rules that have not been activated for a long time or have extremely poor prediction effects, delete these rules from the fuzzy rule base.

[0149] Through the above step S401, by continuously adjusting the fuzzy rule base to make it more in line with the actual operation of the online quality inspection equipment, the accuracy of defect prediction can be improved, false alarms and missed detections can be reduced. The adjusted rule base can better adapt to the changes in the operating environment of the online quality inspection equipment, making the adjustment of equipment parameters more accurate, and improving the stability and reliability of the online quality inspection equipment. Accurate defect prediction and equipment parameter adjustment can reduce the failure occurrence frequency of the online quality inspection equipment, lower the maintenance and repair costs of the online quality inspection equipment, increase the service life of the online quality inspection equipment. The process of dynamically adjusting the fuzzy rule base can automatically optimize the rules according to the actual data, improving the adaptive ability and decision-making level.

[0150] In a possible implementation, please refer to Figure 4 , the method further includes:

[0151] S500, determining whether the actual defect data is within the tolerance range.

[0152] Exemplarily, the tolerance range of the defect can be preset according to product standards, customer requirements, or historical experience data. For example, the upper limit of the tolerable area of scratches is 10 square millimeters, and the upper limit of the tolerable number of bubbles is 2 per meter, etc. Compare the actual defect data (such as defect area, defect number, etc.) obtained in the first painting process with the preset tolerance range to determine whether the actual defect data is within the tolerance range.

[0153] S600, if the actual defect data is within the tolerance range, obtain the actual defect data of the next painting process according to the equipment parameters.

[0154] Exemplarily, the painting equipment can be controlled to perform a painting operation according to the equipment parameters of the preset painting equipment in the next painting step. After the next painting step is completed, the painted aluminum wire is subjected to defect detection to obtain actual defect data.

[0155] S700. If the actual defect data is not within the tolerance range, the equipment parameters are adjusted according to the actual defect data.

[0156] Exemplarily, the predicted defect data for the next painting step can be obtained based on the actual defect data, where the predicted defect data includes defect probability, defect area, and defect type. The equipment parameters for the next painting step are determined based on the predicted defect data and the actual defect data.

[0157] S800. The actual defect data for the next painting step is obtained according to the adjusted equipment parameters.

[0158] Exemplarily, the painting equipment can be controlled to perform a painting operation according to the equipment parameters of the adjusted painting equipment in the next painting step. After the next painting step is completed, the painted aluminum wire is subjected to defect detection to obtain actual defect data.

[0159] S900. Repeat the above steps until the painting is completed.

[0160] Exemplarily, the steps from S500 to S800 can be cyclically executed for each painting step. When the painting is completed or the preset number of painting times is reached, the loop is terminated.

[0161] Through the above steps S500 to S900, the equipment parameters are monitored and adjusted in real time, which can effectively reduce the generation of defects after painting and improve product quality; optimizing the painting process and equipment parameters can reduce the waste of painting materials and the extension of painting time, thereby reducing production costs; automated and intelligent painting process control can reduce manual intervention and human errors and improve production efficiency.

[0162] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0163] Corresponding to the on-line quality detection method of enameled aluminum wire described in the above embodiments, the embodiments of the present application further provide an on-line quality detection device for enameled aluminum wire. Each module of the device can implement each step of the on-line quality detection method of enameled aluminum wire. Figure 5 The structural block diagram of the on-line quality detection device for enameled aluminum wire provided by the embodiments of the present application is shown. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown.

[0164] Refer toFigure 5 , the device includes:

[0165] An acquisition module, configured to acquire real-time defect data of an aluminum wire; wherein, the real-time defect data is used to reflect the defects of the aluminum wire before painting, and the real-time defect data includes a defect area and a defect type, and the defect area includes a defect position and a defect area;

[0166] A predicted defect module, configured to obtain predicted defect data for the first painting process according to the real-time defect data; wherein, the predicted defect data includes a defect probability, a defect area, and a defect type;

[0167] A device parameter module, configured to determine device parameters for the first painting process based on the predicted defect data and the real-time defect data; wherein, the device parameters include a painting speed, a paint viscosity, and a baking temperature;

[0168] An actual defect module, configured to control the painting device according to the device parameters for the first painting process and obtain actual defect data for the first painting process.

[0169] It should be noted that for the information interaction, execution process, etc. between the above modules, since they are based on the same concept as the method embodiment of the present application, the specific functions and the technical effects brought thereby can be specifically referred to the method embodiment part, and will not be elaborated here.

[0170] Those skilled in the art can clearly understand that for the convenience and brevity of description, only the above division of each functional unit and module is used as an example for illustration. In practical applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above device can refer to the corresponding process in the foregoing method embodiment and will not be elaborated here.

[0171] The embodiment of the present application further provides an on-line quality inspection device, Figure 6 which is a schematic structural diagram of the on-line quality inspection device provided by an embodiment of the present application. As Figure 6 shown, the on-line quality inspection device 6 of this embodiment includes: at least one processor 60 ( Figure 6 only one is shown herein), at least one memory 61 ( Figure 6only one is shown) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the on-line quality detection device 6 implements the steps in any of the above-described embodiments of the on-line quality detection method for enameled aluminum wires, or the on-line quality detection device 6 implements the functions of each module / unit in the above-described device embodiments.

[0172] Exemplarily, the computer program 62 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 62 in the on-line quality detection device 6.

[0173] The on-line quality detection device 6 may be a computing device such as a desktop computer, a notebook, a palm computer, or a cloud server. The on-line quality detection device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that Figure 6 merely examples of the on-line quality detection device 6, and do not constitute a limitation on the on-line quality detection device 6. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, buses, etc.

[0174] The processor 60 may be a central processing unit (CPU), and the processor 60 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0175] In some embodiments, the memory 61 may be an internal storage unit of the online quality inspection device 6, such as the hard disk or memory of the online quality inspection device 6. In some other embodiments, the memory 61 may also be an external storage device of the online quality inspection device 6, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a FlashCard, etc. equipped on the online quality inspection device 6. Further, the memory 61 may also include both the internal storage unit and the external storage device of the online quality inspection device 6. The memory 61 is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of the computer program, etc. The memory 61 may also be used to temporarily store data that has been output or will be output.

[0176] An embodiment of the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0177] An embodiment of the present application provides a computer program product, and when the computer program product runs on an online quality inspection device, the online quality inspection device implements the steps in any of the above method embodiments.

[0178] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above method embodiments of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps in the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, an executable file, or some intermediate form, etc. The computer-readable medium can at least include: any entity or device capable of carrying the computer program code to the online quality inspection device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc.

[0179] In the above embodiments, the descriptions of the various embodiments each have their own emphasis. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0180] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0181] In the embodiments provided in this application, it should be understood that the disclosed on-line quality detection equipment and methods can be implemented in other ways. For example, the on-line quality detection equipment embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, indirect couplings or communication connections of devices or units, and can be in electrical, mechanical or other forms.

[0182] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0183] The above-described embodiments are only used to illustrate the technical solutions of this application, rather than to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of this application, and should all be included within the protection scope of this application.

Claims

1. An on-line quality inspection method for enameled aluminum wire, characterized in that, Applied to an on-line quality inspection device, the on-line quality inspection device is communicatively connected to a painting device; the method includes: Obtaining real-time defect data of an aluminum wire; wherein, the real-time defect data is used to reflect the defects of the aluminum wire before painting, the real-time defect data includes a defect area and a defect type, and the defect area includes a defect position and a defect area; Obtaining predicted defect data for the first painting step according to the real-time defect data; wherein, the predicted defect data includes a defect probability, a defect area, and a defect type; Determining device parameters for the first painting step based on the predicted defect data and the real-time defect data; wherein, the device parameters include a painting speed, a paint viscosity, and a baking temperature; Controlling the painting device according to the device parameters for the first painting step and obtaining actual defect data for the first painting step.

2. The on-line quality inspection method of enameled aluminum wire according to claim 1, characterized in that The method further includes: Judging whether the actual defect data is within a tolerance range; If the actual defect data is within the tolerance range, obtaining actual defect data for the next painting step according to the device parameters; If the actual defect data is not within the tolerance range, adjusting the device parameters according to the actual defect data; Obtaining actual defect data for the next painting step according to the adjusted device parameters; Repeating the above steps until painting is completed.

3. The online quality inspection method of enameled aluminum wire according to claim 1, characterized in that, The obtaining the predicted defect data for the first painting step according to the real-time defect data includes: Obtaining historical painting data; wherein, the historical painting data includes a defect area, a defect type, and corresponding device parameters; Obtaining defect evolution data according to the historical painting data; wherein, the defect evolution data includes the probabilities and paths of evolution of defects of different types and areas; Establishing a defect influence matrix according to the real-time defect data and the defect evolution data; wherein, the defect influence matrix is used to reflect the probabilities and paths of evolution of the defects in the real-time defect data during subsequent painting processes; Calculating the basic probabilities of the current defect state transitioning to each subsequent state according to the defect influence matrix; Obtaining the predicted defect data for the first painting step according to the basic probabilities.

4. The on-line quality inspection method of enameled aluminum wire according to claim 3, characterized in that, The obtaining the defect evolution data according to the historical painting data includes: Obtaining a state transition matrix according to the historical painting data; wherein, the state transition matrix is used to reflect the transition frequencies between states in the historical data, and the states include the type and area of the defect; Obtaining the defect evolution data according to the state transition matrix.

5. The online quality inspection method of enameled aluminum wire according to claim 3, characterized in that, The establishing a defect influence matrix according to the real-time defect data and the defect evolution data includes: Calculating the similarity between the real-time defect data and the defect evolution data and obtaining a similarity matrix; Obtaining the defect influence matrix according to the similarity matrix.

6. The on-line quality inspection method of enameled aluminum wire according to claim 3, characterized in that The obtaining the predicted defect data for the first painting step according to the basic probabilities includes: Obtaining the conditional probability of a defect occurring under the condition of the real-time defect data according to the historical painting data; Determining the predicted defect data for the first painting step based on the basic probabilities and the conditional probability.

7. The on-line quality inspection method of enameled aluminum wire according to claim 1, characterized in that The determining device parameters based on the predicted defect data and the real-time defect data includes: An error term and an error change rate are obtained based on the predicted defect data and the real-time defect data; wherein, the error term is the difference between the predicted defect area and the tolerance defect area, and the error change rate is the defect area change rate per unit time; The error term and the error change rate are mapped to obtain a fuzzy set; wherein, the fuzzy set is used to reflect the fuzzy state of the error term and the corresponding error change rate; A fuzzy output quantity is obtained according to the fuzzy set and a preset fuzzy rule base; wherein, the fuzzy output quantity is used to reflect the adjustment amplitude and direction of the device parameters, and the fuzzy rule base is used to reflect the non-linear relationship between the error term, the error change rate and the fuzzy output quantity; A real-time correction value is obtained according to the fuzzy output quantity; wherein, the real-time correction value is used to correct the device parameters; Device parameters are obtained according to the real-time correction value and the predicted defect data; And / or, the obtaining of the device parameters according to the real-time correction value and the predicted defect data includes: Device parameters are obtained according to the defect regions and weights of different defects in the real-time correction value and the predicted defect data.

8. The on-line quality inspection method of enameled aluminum wire according to claim 7, characterized in that, The mapping of the error term and the error change rate to obtain a fuzzy set includes: The error term and the error change rate are substituted into a membership function to obtain membership degrees; wherein, the membership degrees are used to reflect the degrees to which the error term and the error change rate belong to various sets; The fuzzy set is determined based on the membership degrees.

9. The on-line quality inspection method of enameled aluminum wire according to claim 7, characterized in that, The obtaining of the fuzzy output quantity according to the fuzzy set and the preset fuzzy rule base includes: The fuzzy set and the preset fuzzy rule base are matched to obtain activation rules; wherein, the activation rules are used to reflect the device parameter adjustment strategies adopted under the combination of the error term and the error change rate; The fuzzy output quantity is obtained according to the activation rules.

10. The online quality inspection method of enameled aluminum wire according to claim 7, characterized in that, After controlling the painting device according to the device parameters of the first painting step and obtaining the actual defect data of the first painting step, the method further includes: Adjusting the fuzzy rule base according to the actual defect data and the predicted defect data.

Images