Automatic adjustment method and system for enameled wire production process

Abstract

The present invention relates to the technical field of enameled wire production, and in particular to an automated adjustment method and system for an enameled wire production process, comprising: obtaining real-time linear velocity data of a wire in a coating process of the enameled wire production; determining wire motion characteristics based on the real-time linear velocity data; inputting the wire motion characteristics and wire velocity characteristics into a pre-built risk prediction model for prediction processing to obtain a wire motion risk coefficient; determining the steepness of all sequences based on the real-time linear velocity data, and generating an automated adjustment strategy based on the wire operation complexity obtained by outputting the steepness of all sequences; extracting the maximum steepness and wire motion characteristics in the sequence, and inputting them into a multi-dimensional learning model to obtain a wire pay-off speed control ratio. The present invention automatically adjusts the linear velocity by considering the comprehensive degree of linear velocity fluctuation, early warning, trend and complexity while ensuring safety and adjustability, thereby ensuring uniform coating of the enameled wire.

Description

Technical Field

[0001] The present invention relates to the technical field of enameled wire production, and in particular to an automated adjustment method and system for an enameled wire production process. Background Art

[0002] In the existing technology, especially in the painting process, when the wire is at a low speed, the paint liquid maintains a laminar state in the coating mold and flows steadily; when the wire speed exceeds a certain value, the paint liquid flow rate accelerates and the Reynolds number increases, which may cause turbulence, causing "fish scale patterns" or local accumulation on the surface of the paint film. When the high-speed wire passes through the paint liquid, air is easily drawn into the paint film, forming bubbles or pinholes; if the paint layer is uneven, it may cause the insulation performance to fail to meet the standards, or breakdown problems may occur in subsequent use. Summary of the Invention

[0003] The purpose of the present invention is to provide an automated adjustment method and system for the enameled wire production process. The technical problem solved by the present invention is that the line speed fluctuates during wire coating, resulting in uneven paint film on the wire surface and affecting the quality of the enameled wire.

[0004] The purpose of the present invention can be achieved through the following technical solutions:

[0005] The automated adjustment method for the enameled wire production process comprises the following steps:

[0006] S1. In the coating process of enameled wire production, obtaining real-time linear velocity data of the wire; determining the movement characteristics of the wire based on the real-time linear velocity data;

[0007] S2. Inputting the wire motion characteristics and wire speed characteristics into a pre-established risk prediction model for prediction processing to obtain a wire motion risk coefficient; and determining the wire speed risk level based on the wire motion risk coefficient;

[0008] S3. Based on the determined line speed hazard level, the steepness of all sequences is determined according to the real-time line speed data, and the wire running complexity obtained by the steepness output of all sequences is used to generate an automated adjustment strategy;

[0009] S4. When receiving the adjustment instruction in the automatic adjustment strategy, the maximum steepness and wire movement characteristics in the sequence are extracted and input into the multi-dimensional learning model to obtain the wire pay-off speed control ratio.

[0010] As a further solution of the present invention: a method for determining wire motion characteristics based on real-time wire velocity data includes:

[0011] An analysis period is set, and the real-time wire speed data of the analysis period is analyzed in terms of fluctuation degree, warning degree, and trend degree in turn to obtain wire movement fluctuation characteristics, wire movement warning characteristics, and wire movement trend characteristics.

[0012] As a further solution of the present invention, the fluctuation degree analysis is performed on the real-time linear velocity data of the analysis period in turn to obtain the fluctuation characteristics of the wire movement in the following process:

[0013] The real-time linear velocity data of the analysis period is obtained, and the linear velocity curve is obtained by least square fitting. All the peak points in the linear velocity curve are extracted, and a linear velocity peak time series is constructed. The fluctuation of the linear velocity peak time series is calculated to obtain the fluctuation characteristics of the wire motion.

[0014] As a further solution of the present invention, the process of performing early warning degree analysis on the real-time wire speed data of the analysis period and obtaining the wire movement early warning characteristics is as follows:

[0015] Real-time linear speed data of the analysis period is obtained, and the linear speed curve is obtained by least squares fitting. All peak points in the linear speed curve are extracted, and a linear speed peak time series is constructed. The maximum value in the linear speed peak time series is extracted, and the degree of proximity between the maximum value and the preset risk value is calculated to obtain the wire movement warning characteristics.

[0016] As a further solution of the present invention, the trend degree analysis is performed on the real-time linear velocity data of the analysis period in sequence to obtain the trend characteristics of the wire movement as follows:

[0017] Real-time linear velocity data of the analysis period is obtained, and the linear velocity curve is obtained by least squares fitting. All peak points in the linear velocity curve are extracted, and a linear velocity peak time series is constructed. The wire movement trend characteristics are obtained based on the distribution difference between the central linear velocity data of the initial sequence segment and other linear velocity data.

[0018] As a further solution of the present invention: the wire movement risk coefficient includes two levels, corresponding to 1 and 2 respectively, 1 indicates that the movement speed of the wire during the coating process is in a safe state, and 2 indicates that the movement speed of the wire during the coating process is in a dangerous state.

[0019] As a further solution of the present invention: a method for determining the complexity of wire motion based on real-time wire speed data is as follows:

[0020] The real-time linear velocity data of the analysis period is obtained, and the linear velocity curve is obtained by least square fitting. All peak segments are extracted, and a time series of linear velocity peak segments is constructed. The total steepness value of all sequences is calculated to obtain the wire motion complexity.

[0021] Calculate the steepness of all series by combining the steepness coefficient and frequency coefficient of each series.

[0022] As a further solution of the present invention, a method for generating an automatic adjustment strategy based on the wire running complexity obtained by outputting the steepness of all sequences is as follows:

[0023] If the wire operation complexity exceeds the wire operation complexity threshold, an adjustment instruction is generated;

[0024] If the wire operation complexity does not exceed the wire operation complexity threshold, a stop instruction is generated.

[0025] As a further solution of the present invention: the input of the input layer is the maximum steepness in the extraction sequence, the wire movement fluctuation characteristics, the wire movement warning characteristics, and the wire movement trend characteristics; the hidden layer contains 7 nodes, the activation function of the hidden layer is the ReLU activation function, the output layer contains 2 nodes, and the output of the output layer is the wire pay-off speed control ratio.

[0026] The enameled wire production process automation adjustment system includes:

[0027] Analysis module: During the painting process of enameled wire production, it obtains the real-time linear velocity data of the wire and determines the movement characteristics of the wire based on the real-time linear velocity data;

[0028] Evaluation module: Inputs the wire motion characteristics and wire speed characteristics into the pre-built risk prediction model for prediction processing to obtain the wire motion risk coefficient; and determines the wire speed risk level based on the wire motion risk coefficient;

[0029] Strategy module: Based on the determined line speed hazard level, the steepness of all sequences is determined according to real-time line speed data. The wire running complexity obtained by the steepness output of all sequences is used to generate an automated adjustment strategy.

[0030] Adjustment module: When receiving the adjustment instruction in the automated adjustment strategy, it extracts the maximum steepness and wire movement characteristics in the sequence and inputs them into the multi-dimensional learning model to obtain the wire pay-off speed control ratio.

[0031] Beneficial effects of the present invention:

[0032] (1) In the coating process of enameled wire production, the present invention obtains real-time linear speed data of the wire; determines the movement characteristics of the wire based on the real-time linear speed data; inputs the wire movement characteristics and the wire speed characteristics into a pre-constructed risk prediction model for prediction processing to obtain a wire movement risk coefficient; the present invention takes the linear speed of the enameled wire as the analysis object, and comprehensively analyzes the linear speed from the perspectives of fluctuation, warning and trend, and comprehensively and accurately evaluates the risk of whether the current linear speed of the wire exceeds a certain value, so that when the movement speed of the wire faces a dangerous state, the tension of the coating die can be controlled in a timely manner;

[0033] (2) The present invention determines the steepness of all sequences based on the determined line speed danger level and the real-time line speed data, and generates an automated adjustment strategy based on the wire running complexity obtained by outputting the steepness of all sequences; when receiving the adjustment instruction in the automated adjustment strategy, the maximum steepness and wire movement characteristics in the sequence are extracted and input into the multi-dimensional learning model to obtain the wire unwinding speed, and the line speed in the painting process of the enameled wire is controlled; the present invention then evaluates the complexity of the line speed data, and automatically adjusts the line speed by considering the comprehensive degree of line speed changes, early warnings, trends and complexity, so as to ensure the uniform coating effect of the enameled wire, provided that the safety and adjustability are qualified. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0035] Figure 1 This is a flow chart of an automated adjustment method for an enameled wire production process provided by an embodiment of the present invention;

[0036] Figure 2 It is a structural diagram of an automated adjustment system for an enameled wire production process provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0038] Example 1

[0039] like Figure 1 As shown, an embodiment of the present invention provides an automated adjustment method for the enameled wire production process, wherein the enameled wire production process mainly includes the preparation, painting, drying, curing, and testing of metal wires. In particular, in the painting process, if the paint layer is uneven, it may cause the insulation performance to be substandard or a breakdown problem to occur in subsequent use. Therefore, among the many enameled wire processes, the specific painting process is selected for automated adjustment to ensure the uniform coating effect of the enameled wire. The automated adjustment includes the following steps:

[0040] S1. In the coating process of enameled wire production, obtaining real-time linear velocity data of the wire; determining the movement characteristics of the wire based on the real-time linear velocity data;

[0041] In S1, first, specifically, the process of acquiring the real-time linear velocity data of the wire is as follows:

[0042] Installing a rotary encoder (incremental or absolute) on the production line drive roller or take-up / pay-off shaft can convert the linear speed by measuring the roller's rotational speed and circumference, which has the advantages of high accuracy (±0.1%) and fast response.

[0043] Linear speed refers to the rate at which the enameled wire moves during the coating and curing process, that is, the distance the wire travels per unit time, and is usually measured in meters per minute (m / min) or meters per second (m / s). This parameter directly affects production efficiency and coating quality for the following reasons: When the wire is moving at low speed, the paint liquid maintains a laminar flow and stable flow within the coating die. When the linear speed exceeds a certain value, the paint liquid flow rate accelerates, and the Reynolds number increases, which may cause turbulence and cause "fish scales" or localized accumulation on the paint film surface. Furthermore, when high-speed wire passes through the paint liquid, air is easily drawn into the paint film, forming bubbles or pinholes. Therefore, analyzing the wire linear speed and adjusting and controlling the enameled wire coating process can effectively improve the quality of the enameled wire.

[0044] Second, specifically, a method for determining wire motion characteristics based on real-time wire velocity data includes:

[0045] An analysis period is set, and the real-time wire speed data of the analysis period is analyzed in terms of fluctuation degree, warning degree, and trend degree in turn to obtain wire movement fluctuation characteristics, wire movement warning characteristics, and wire movement trend characteristics.

[0046] The fluctuation degree of the real-time linear velocity data of the analysis period is analyzed in sequence, and the process of obtaining the fluctuation characteristics of the wire movement is as follows:

[0047] Acquire real-time linear velocity data of the analysis period, obtain a linear velocity curve by fitting using the least squares method, extract all peak points in the linear velocity curve, construct a linear velocity peak time series, perform fluctuation calculation on the linear velocity peak time series, and obtain the wire motion fluctuation characteristics. For example, the fluctuation calculation method can use a variance formula;

[0048] The process of analyzing the warning degree of the real-time wire speed data of the analysis period in turn and obtaining the wire movement warning characteristics is as follows:

[0049] Acquire real-time linear velocity data during the analysis period, obtain a linear velocity curve using the least squares method, extract all peak points in the linear velocity curve, construct a linear velocity peak time series, extract the maximum value in the linear velocity peak time series, calculate the degree of proximity between the maximum value and the preset risk value, and obtain the wire movement warning feature;

[0050] For example, the process of calculating the closeness between the maximum value and the preset risk value is as follows:

[0051] Calculate the difference between the preset risk value and the maximum value, calculate the ratio of the difference to the preset risk value, and obtain the degree of proximity between the maximum value and the preset risk value, which is the wire movement warning feature;

[0052] It should be explained that the preset risk value is pre-set by technical personnel based on the enameled wire production process, that is, the certain value mentioned above. If the value is exceeded, abnormalities will occur on the paint film surface.

[0053] The trend degree analysis of the real-time line speed data of the analysis period is carried out in sequence to obtain the trend characteristics of the wire movement as follows:

[0054] Real-time linear velocity data of the analysis period is acquired, and a linear velocity curve is obtained by least squares fitting. All peak points in the linear velocity curve are extracted, and a linear velocity peak time series is constructed. The wire movement trend characteristics are obtained based on the distribution difference between the central linear velocity data of the initial sequence segment and other linear velocity data.

[0055] For example, the specific process according to the distribution difference between the center line velocity data of the initial sequence segment and the other line velocity data is as follows:

[0056]

[0057] Wherein, Y represents the wire movement trend characteristic; V1 represents the first linear velocity data in the linear velocity peak time series; V2 represents the center linear velocity data in the linear velocity peak time series; V3 represents the last linear velocity data in the linear velocity peak time series; a represents a preset hyperparameter, and a preferably takes a value of 0.01 to prevent the denominator from being 0; | | represents the absolute value compliance;

[0058] It can be understood that: the wire motion fluctuation feature reflects the stability of the wire speed during the analysis period. The larger the wire motion fluctuation feature, the more unstable the wire speed and the higher the risk of wire coating. The wire motion warning feature reflects the degree of proximity between the wire speed and the risk value during the analysis period. The smaller the wire motion warning feature, the higher the warning level of the wire speed during the coating and the higher the risk of wire coating. The wire motion trend feature reflects the growth trend of the wire speed during the analysis period. The larger the wire motion trend feature, the more the wire speed shows an increasing trend and the higher the risk of wire coating.

[0059] S2. Inputting the wire motion characteristics and wire speed characteristics into a pre-established risk prediction model for prediction processing to obtain a wire motion risk coefficient; and determining the wire speed risk level based on the wire motion risk coefficient;

[0060] In S2, first, specifically, the construction of the risk index prediction model is based on the training of the Multi-Layer Perceptron (MLP) model. The input layer of the model can set multiple nodes to input data on the mean wire speed, wire movement fluctuation characteristics, wire movement warning characteristics, and wire movement trend characteristics. In order to improve the expressiveness of the model and improve the generalization ability of the model and reduce the complexity of parameter calculations, the hidden layer can be divided into multiple hidden layer groups. Each hidden layer group can share a part of the data, which helps to reduce the computational burden of the model and improve the efficiency of training and prediction. At the same time, multiple hidden layer groups can help the model better generalize to unseen data. Each group can focus on learning different types of data features, processing data from different regions, and more effectively capturing local patterns and signs in the data set, thereby improving the model's adaptability to different data distributions and reducing the risk of overfitting. Preferably, three hidden layer groups can be selected to process the data of wire speed mean, wire motion fluctuation characteristics, wire motion warning characteristics, and wire motion trend characteristics input from multiple input nodes of the input layer. During the entire model training process, the outputs of multiple hidden layer groups need to be fused using the attention mechanism to obtain the wire motion risk coefficient.

[0061] It should be explained that the wire movement risk coefficient includes two levels, corresponding to 1 and 2 respectively. 1 means that the wire movement speed during the coating process is in a safe state, and 2 means that the wire movement speed during the coating process is in a dangerous state.

[0062] The technical solution of an embodiment of the present invention is as follows: in the painting process of enameled wire production, real-time linear speed data of the wire is obtained; the wire movement characteristics are determined based on the real-time linear speed data; the wire movement characteristics and wire speed characteristics are input into a pre-built risk prediction model for prediction processing to obtain a wire movement risk coefficient; the present invention takes the linear speed of the enameled wire as the analysis object, and through a comprehensive analysis of the linear speed from the perspectives of fluctuation, warning and trend, a comprehensive and accurate assessment is made of the risk of whether the current linear speed of the wire exceeds a certain value, so that when the movement speed of the wire is facing a dangerous state, the tension of the coating mold can be controlled in time.

[0063] Example 2

[0064] Based on the above embodiment 1, the automatic adjustment further includes the following steps:

[0065] S3. Based on the determined line speed hazard level, the steepness of all sequences is determined according to the real-time line speed data, and the wire running complexity obtained by the steepness output of all sequences is used to generate an automated adjustment strategy;

[0066] In S3, first, specifically, a method for determining the wire motion complexity based on the real-time wire speed data is as follows:

[0067] The real-time linear velocity data of the analysis period is obtained, and the linear velocity curve is obtained by least square fitting. All peak segments are extracted, and a time series of linear velocity peak segments is constructed. The total steepness value of all sequences is calculated to obtain the wire motion complexity.

[0068] It should be explained that the peak segment refers to a curve segment that connects any peak point in the linear velocity curve as a reference point, obtains the trough point adjacent to the reference point, and is defined as a peak segment;

[0069] Exemplarily, the steepness of all sequences is calculated by combining the steepness coefficient and the frequency coefficient of each sequence. Specifically, the steepness is obtained by multiplying the steepness coefficient and the frequency coefficient;

[0070] The calculation process of the steepness coefficient of each sequence is:

[0071] Take any peak point as the reference point to determine the peak height H: , where y peak is the peak value, y baseline is the adjacent trough value;

[0072] Calculate half-height position y HM : ;

[0073] Determine the left and right boundaries of the half-height width: left boundary x left: Search from the peak to the left to find the first coordinate y i ≤y HM The position of the right boundary x right : Search from the peak to the right to find the first coordinate y i ≤y HM location;

[0074] Calculate the half-height width F WHM : ;

[0075] The steepness factor is determined by the half-height width F WHM Calculated by comparing with the peak height H;

[0076] The frequency coefficient calculation process of each sequence is:

[0077] Take any peak point as the reference point, determine the positions of the two adjacent peak points on the left and right of the reference point, and calculate the time length of the two adjacent peak points on the left and right; calculate the ratio of the time length to the analysis period to obtain the frequency coefficient;

[0078] It can be understood that the steepness coefficient reflects the proportional relationship between the height and half-height width of each peak. The smaller the steepness coefficient, the higher the degree of linear velocity change in the peak segment. The frequency coefficient reflects the proportional relationship between each peak in time. The smaller the frequency coefficient, the higher the degree of time change in the peak segment. Therefore, the wire motion complexity can effectively evaluate the complexity of the linear velocity change within the analysis period. The smaller the wire motion complexity, the higher the degree of linear velocity change. It can not only characterize the urgency of the current linear velocity data change, but also characterize the controllability of the subsequent automatic adjustment of the linear velocity.

[0079] Secondly, specifically, the method for generating an automated adjustment strategy based on the wire running complexity obtained by outputting the steepness of all sequences is as follows:

[0080] Compare the wire run complexity to the wire run complexity threshold:

[0081] If the wire operation complexity exceeds the wire operation complexity threshold, an adjustment instruction is generated; when the adjustment instruction is received, the linear speed of the wire is regulated by the conveying equipment;

[0082] If the wire operation complexity does not exceed the wire operation complexity threshold, a stop instruction is generated; when the stop instruction is received, the painting process of the enameled wire is stopped and the related equipment involved in the painting process is repaired;

[0083] S4. When receiving the adjustment instruction from the automated adjustment strategy, the maximum steepness and wire motion characteristics in the sequence are extracted and input into the multi-dimensional learning model to obtain the wire pay-off speed control ratio, and the line speed in the enameled wire painting process is controlled;

[0084] In S4, the construction process of the multi-dimensional learning model is as follows:

[0085] The multidimensional learning model is built based on the BP neural network. It consists of one input layer, one hidden layer, and one output layer. The input layer contains five nodes. The input of the input layer is the maximum steepness in the extraction sequence, the wire movement fluctuation characteristics, the wire movement warning characteristics, and the wire movement trend characteristics. The hidden layer contains seven nodes, and the activation function of the hidden layer is the ReLU activation function. The output layer contains two nodes, and the output of the output layer is the wire pay-off speed control ratio. The activation function of the output layer is the linear activation function. The learning rate (learning_rate) of the multi-parameter learning model is 0.001, the loss function (loss) is the mean square error (MSE), the optimization algorithm (optimizers) is Adam, the number of training rounds (epochs) is 500, and the batch size (batch_size) is 64.

[0086] The process of controlling the line speed in the painting process of enameled wire is as follows:

[0087] The wire pay-off speed control ratio is sent to the wire pay-off controller to adjust and control the wire pay-off speed;

[0088] The technical solution of the embodiment of the present invention is as follows: based on the determined degree of danger of the line speed, the steepness of all sequences is determined according to the real-time line speed data, and the wire operation complexity is obtained by outputting the steepness of all sequences to generate an automatic adjustment strategy; when the adjustment instruction in the automatic adjustment strategy is received, the maximum steepness and wire movement characteristics in the sequence are extracted, and the multi-dimensional learning model is input to obtain the wire pay-off speed, so as to control the line speed in the painting process of the enameled wire; the present invention then evaluates the complexity of the line speed data, and automatically adjusts the line speed by considering the comprehensive degree of line speed changes, early warnings, trends and complexity, so as to ensure the uniform coating effect of the enameled wire.

[0089] Example 4

[0090] like Figure 2 As shown, the embodiment of the present invention provides an automated adjustment system for the production process of enameled wire, including:

[0091] Analysis module: During the painting process of enameled wire production, it obtains the real-time linear velocity data of the wire and determines the movement characteristics of the wire based on the real-time linear velocity data;

[0092] In this embodiment, the process of acquiring the real-time linear velocity data of the wire is specifically as follows:

[0093] Install a rotary encoder on the production line drive roller or take-up / pay-off shaft;

[0094] The method for determining the wire motion characteristics based on real-time wire velocity data includes:

[0095] An analysis period is set, and the real-time wire speed data of the analysis period is analyzed in terms of fluctuation degree, warning degree, and trend degree in turn to obtain wire movement fluctuation characteristics, wire movement warning characteristics, and wire movement trend characteristics.

[0096] The fluctuation degree of the real-time linear velocity data of the analysis period is analyzed in sequence, and the process of obtaining the fluctuation characteristics of the wire movement is as follows:

[0097] Acquire real-time linear velocity data during the analysis period, obtain the linear velocity curve through least squares fitting, extract all peak points in the linear velocity curve, construct a linear velocity peak time series, perform fluctuation calculation on the linear velocity peak time series, and obtain the wire motion fluctuation characteristics;

[0098] The process of analyzing the warning degree of the real-time wire speed data of the analysis period in turn and obtaining the wire movement warning characteristics is as follows:

[0099] Acquire real-time linear velocity data during the analysis period, obtain a linear velocity curve using the least squares method, extract all peak points in the linear velocity curve, construct a linear velocity peak time series, extract the maximum value in the linear velocity peak time series, calculate the degree of proximity between the maximum value and the preset risk value, and obtain the wire movement warning feature;

[0100] The trend degree analysis of the real-time line speed data of the analysis period is carried out in sequence to obtain the trend characteristics of the wire movement as follows:

[0101] Real-time linear velocity data of the analysis period is obtained, and the linear velocity curve is obtained by least squares fitting. All peak points in the linear velocity curve are extracted, and a linear velocity peak time series is constructed. The wire movement trend characteristics are obtained based on the distribution difference between the central linear velocity data of the initial sequence segment and other linear velocity data.

[0102] Evaluation module: Inputs the wire motion characteristics and wire speed characteristics into the pre-built risk prediction model for prediction processing to obtain the wire motion risk coefficient; and determines the wire speed risk level based on the wire motion risk coefficient;

[0103] In this embodiment, the risk index prediction model is constructed based on the training of a multi-layer perceptron (MLP) model. The input layer of the model can be configured with multiple nodes to input data on the mean wire speed, wire motion fluctuation characteristics, wire motion warning characteristics, and wire motion trend characteristics. To improve the model's expressiveness and generalization capabilities and reduce the complexity of parameter calculations, the hidden layer can be divided into multiple hidden layer groups. Each hidden layer group can share a portion of data, which helps to reduce the model's computational burden and improve the efficiency of training and prediction. At the same time, multiple hidden layer groups can help the model better generalize to unseen data. Each group can focus on learning different types of data features and processing data from different regions, more effectively capturing local patterns and signs in the data set, thereby improving the model's adaptability to different data distributions and reducing the risk of overfitting. Preferably, three hidden layer groups can be selected to process the data on the mean wire speed, wire motion fluctuation characteristics, wire motion warning characteristics, and wire motion trend characteristics input by multiple input nodes of the input layer. During the entire model training process, the outputs of multiple hidden layer groups need to be fused using an attention mechanism to obtain a wire motion risk coefficient.

[0104] It should be explained that the wire movement risk coefficient includes two levels, corresponding to 1 and 2 respectively. 1 means that the movement speed of the wire during the coating process is in a safe state, and 2 means that the movement speed of the wire during the coating process is in a dangerous state.

[0105] Strategy module: Based on the determined line speed hazard level, the steepness of all sequences is determined according to real-time line speed data. The wire running complexity obtained by the steepness output of all sequences is used to generate an automated adjustment strategy.

[0106] In this embodiment, the method for determining the wire motion complexity based on real-time wire speed data is as follows:

[0107] The real-time linear velocity data of the analysis period is obtained, and the linear velocity curve is obtained by least square fitting. All peak segments are extracted, and a time series of linear velocity peak segments is constructed. The total steepness value of all sequences is calculated to obtain the wire motion complexity.

[0108] It should be explained that the peak segment refers to a curve segment that connects any peak point in the linear velocity curve as a reference point, obtains the trough point adjacent to the reference point, and is defined as a peak segment;

[0109] Exemplarily, the steepness of all sequences is calculated by integrating the steepness coefficient and the frequency coefficient of each sequence. Specifically, the steepness is obtained by multiplying the steepness coefficient and the frequency coefficient.

[0110] Adjustment module: Upon receiving adjustment instructions from the automated adjustment strategy, it extracts the maximum steepness and wire motion characteristics from the sequence, inputs them into a multi-dimensional learning model to obtain the wire payoff speed control ratio, and controls the wire speed during the enameled wire coating process.

[0111] In this embodiment, the process of constructing the multi-dimensional learning model is as follows:

[0112] The multidimensional learning model is built based on the BP neural network. It consists of one input layer, one hidden layer, and one output layer. The input layer contains five nodes. The input of the input layer is the maximum steepness in the extraction sequence, the wire movement fluctuation characteristics, the wire movement warning characteristics, and the wire movement trend characteristics. The hidden layer contains seven nodes, and the activation function of the hidden layer is the ReLU activation function. The output layer contains two nodes, and the output of the output layer is the wire pay-off speed control ratio. The activation function of the output layer is the linear activation function. The learning rate (learning_rate) of the multi-parameter learning model is 0.001, the loss function (loss) is the mean square error (MSE), the optimization algorithm (optimizers) is Adam, the number of training rounds (epochs) is 500, and the batch size (batch_size) is 64.

[0113] The process of controlling the line speed in the painting process of enameled wire is as follows:

[0114] The wire pay-off speed control ratio is sent to the wire pay-off controller to adjust and control the wire pay-off speed.

[0115] The above is a detailed description of an embodiment of the present invention. However, the content described is only a preferred embodiment of the present invention and should not be considered to limit the scope of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. The method for automatically adjusting the production process of enameled wire is characterized in that: The following steps are involved: S1. In the coating process of enameled wire production, obtaining real-time linear velocity data of the wire; determining the movement characteristics of the wire based on the real-time linear velocity data; S2. Inputting the wire motion characteristics and wire speed characteristics into a pre-established risk prediction model for prediction processing to obtain a wire motion risk coefficient; and determining the wire speed risk level based on the wire motion risk coefficient; S3. Based on the determined line speed hazard level, the steepness of all sequences is determined according to the real-time line speed data, and the wire running complexity obtained by the steepness output of all sequences is used to generate an automated adjustment strategy; Obtain real-time linear velocity data during the analysis period, obtain the linear velocity curve through least squares fitting, extract all peak segments, and construct a linear velocity peak segment time series; Calculate the steepness of all sequences by combining the steepness coefficient and frequency coefficient of each sequence: Multiply the steepness coefficient by the frequency coefficient to get the steepness; The steepness factor is determined by the half-height width F WHM Calculated by comparing with the peak height H; The frequency coefficient calculation process of each sequence is: Take any peak point as the reference point, determine the positions of the two adjacent peak points on the left and right of the reference point, and calculate the time length of the two adjacent peak points on the left and right; calculate the ratio of the time length to the analysis period to obtain the frequency coefficient; S4. When receiving the adjustment instruction in the automatic adjustment strategy, the maximum steepness and wire movement characteristics in the sequence are extracted and input into the multi-dimensional learning model to obtain the wire pay-off speed control ratio.

2. The method for automatically adjusting the enameled wire production process according to claim 1, characterized in that: The method for determining the wire motion characteristics based on real-time wire velocity data includes: An analysis period is set, and the real-time wire speed data of the analysis period is analyzed in terms of fluctuation degree, warning degree, and trend degree in turn to obtain wire movement fluctuation characteristics, wire movement warning characteristics, and wire movement trend characteristics.

3. The method for automatically adjusting the enameled wire production process according to claim 2, characterized in that: The fluctuation degree of the real-time linear velocity data of the analysis period is analyzed in sequence, and the process of obtaining the fluctuation characteristics of the wire movement is as follows: The real-time linear velocity data of the analysis period is obtained, and the linear velocity curve is obtained by least square fitting. All the peak points in the linear velocity curve are extracted, and a linear velocity peak time series is constructed. The fluctuation of the linear velocity peak time series is calculated to obtain the fluctuation characteristics of the wire motion.

4. The method for automatically adjusting the enameled wire production process according to claim 2, characterized in that: The process of analyzing the warning degree of the real-time wire speed data of the analysis period in turn and obtaining the wire movement warning characteristics is as follows: Real-time linear speed data of the analysis period is obtained, and the linear speed curve is obtained by least squares fitting. All peak points in the linear speed curve are extracted, and a linear speed peak time series is constructed. The maximum value in the linear speed peak time series is extracted, and the degree of proximity between the maximum value and the preset risk value is calculated to obtain the wire movement warning characteristics.

5. The method for automated adjustment of the enameled wire production process according to claim 2, characterized in that: The trend degree analysis of the real-time line speed data of the analysis period is carried out in sequence to obtain the trend characteristics of the wire movement as follows: Real-time linear velocity data of the analysis period is obtained, and the linear velocity curve is obtained by least squares fitting. All peak points in the linear velocity curve are extracted, and a linear velocity peak time series is constructed. The wire movement trend characteristics are obtained based on the distribution difference between the central linear velocity data of the initial sequence segment and other linear velocity data.

6. The method for automated adjustment of the enameled wire production process according to claim 1, characterized in that: The wire movement risk coefficient includes two levels, corresponding to 1 and 2 respectively. 1 means that the wire movement speed is in a safe state during the coating process, and 2 means that the wire movement speed is in a dangerous state during the coating process.

7. The method for automated adjustment of the enameled wire production process according to claim 5, characterized in that: The method for determining the complexity of wire motion based on real-time wire speed data is as follows: The real-time linear velocity data of the analysis period is obtained, and the linear velocity curve is obtained by least square fitting. All peak segments are extracted, and a time series of linear velocity peak segments is constructed. The total steepness value of all sequences is calculated to obtain the wire motion complexity. Calculate the steepness of all series by combining the steepness coefficient and frequency coefficient of each series.

8. The method for automated adjustment of the enameled wire production process according to claim 7, characterized in that: The method for generating an automated adjustment strategy based on the wire running complexity obtained by the steepness output of all sequences is as follows: If the wire operation complexity exceeds the wire operation complexity threshold, an adjustment instruction is generated; If the wire operation complexity does not exceed the wire operation complexity threshold, a stop instruction is generated.

9. The method for automated adjustment of the enameled wire production process according to claim 8, characterized in that: The input of the input layer is the maximum steepness in the extraction sequence, the wire movement fluctuation characteristics, the wire movement warning characteristics, and the wire movement trend characteristics. The hidden layer contains 7 nodes, and the activation function of the hidden layer is the ReLU activation function. The output layer contains 2 nodes, and the output of the output layer is the wire pay-off speed control ratio.

10. The automated regulation system for the production process of enameled wire is characterized by: The system is used to execute the method according to any one of claims 1 to 9, and the system comprises: Analysis module: During the painting process of enameled wire production, it obtains the real-time linear velocity data of the wire and determines the movement characteristics of the wire based on the real-time linear velocity data; Evaluation module: Inputs the wire motion characteristics and wire speed characteristics into the pre-built risk prediction model for prediction processing to obtain the wire motion risk coefficient; and determines the wire speed risk level based on the wire motion risk coefficient; Strategy module: Based on the determined line speed hazard level, the steepness of all sequences is determined according to real-time line speed data. The wire running complexity obtained by the steepness output of all sequences is used to generate an automated adjustment strategy. Adjustment module: When receiving the adjustment instruction in the automated adjustment strategy, it extracts the maximum steepness and wire movement characteristics in the sequence and inputs them into the multi-dimensional learning model to obtain the wire pay-off speed control ratio.

Images