Temperature monitoring method for welded joints in thermoplastic composite welding scenarios

Abstract

The present application relates to the field of temperature monitoring technology, and specifically to a method for monitoring the temperature of welded joints in a thermoplastic composite material welding scenario. The method comprises: collecting temperature data of different positions of the thermoplastic composite material at each collection moment in the welding scenario to form a temperature image matrix at each collection moment; obtaining fluctuation data of the temperature image matrix at each temperature fluctuation moment; dividing the fluctuation data in the temperature image matrix at each temperature fluctuation moment into clusters of fluctuation data; calculating the fluctuation distribution factor at each temperature fluctuation moment; and then obtaining the temperature mutation factor of each fluctuation data cluster of the temperature image matrix at each temperature fluctuation moment; obtaining the fluctuation mutation factor at each temperature fluctuation moment; obtaining the laser intensity uneven weight at each temperature fluctuation moment; and monitoring the temperature of the welded joint in the thermoplastic composite material welding scenario based on the laser intensity uneven weight. The present application improves the accuracy of welded joint temperature monitoring.

Description

Technical Field

[0001] The present application relates to the field of temperature monitoring technology, and in particular to a method for monitoring the temperature of a welded joint in a thermoplastic composite material welding scenario. Background Art

[0002] Thermoplastic composites are widely used in industrial welding due to their superior strength and stiffness, as well as their ability to melt when heated and retain their original mechanical properties after cooling. When laser welding thermoplastic composites, any temperature fluctuations beyond the set limits at the weld joint can result in poor welds and product defects. Therefore, the temperature of the weld joint must be monitored during the welding process.

[0003] Temperature monitoring allows welders to adjust welding parameters promptly to ensure the temperature remains within the appropriate range during the welding process, thereby guaranteeing weld quality. Temperature data can also be used to determine if there are defects in the weld quality of the product during the welding process. Common temperature monitoring methods include infrared temperature measurement, thermocouple temperature measurement, fiber optic sensor temperature measurement, and infrared camera temperature measurement. Thermocouple sensors are generally not used due to their large size and are not suitable for embedding within structures. Infrared temperature measurement and fiber optic sensor methods measure the average temperature of a surface and cannot reflect the temperature distribution at different locations on the weld joint. Infrared thermal imagers, on the other hand, can measure the temperature distribution across the entire plane of the weld joint and are therefore widely used for weld joint temperature monitoring. When infrared thermal imagers collect the surface temperature of weld joints, the collected temperature data is easily interfered with by electromagnetic waves in the environment, resulting in the collected temperature data not accurately reflecting the actual temperature of the weld joint. Summary of the Invention

[0004] In order to solve the above technical problems, the present application provides a welding joint temperature monitoring method in a thermoplastic composite material welding scenario to solve the existing problems.

[0005] The welding joint temperature monitoring method in the thermoplastic composite material welding scenario of this application adopts the following technical solutions:

[0006] One embodiment of the present application provides a method for monitoring the temperature of a welded joint in a thermoplastic composite material welding scenario, the method comprising the following steps:

[0007] Collect temperature data of different positions of thermoplastic composite materials at each collection time in welding scenarios to form a temperature image matrix at each collection time;

[0008] Obtain each temperature fluctuation moment based on the discrete degree of local temperature data in the temperature image matrix and the distance between local temperature data;

[0009] Based on the deviation of the temperature data of the welding joint, the fluctuation data of the temperature image matrix at each temperature fluctuation moment is obtained;

[0010] Dividing the fluctuation data in the temperature image matrix at each temperature fluctuation moment into clusters of fluctuation data;

[0011] Based on the average number of elements in the fluctuation data clusters, the number of fluctuation data clusters and the distribution of fluctuation data, the fluctuation distribution factor at each temperature fluctuation moment is obtained;

[0012] Obtaining the temperature mutation factor of each fluctuation data cluster of the temperature image point matrix at each temperature fluctuation moment based on the fluctuation range of all fluctuation data in the neighborhood of the edge fluctuation data in the fluctuation data cluster;

[0013] Obtain the fluctuation mutation factor at each temperature fluctuation moment based on the average of the temperature mutation factor;

[0014] The laser intensity uneven weight at each temperature fluctuation moment is obtained based on the fluctuation distribution factor and the fluctuation mutation factor;

[0015] The temperature of the weld joint in thermoplastic composite welding scenarios is monitored based on the laser intensity uneven weight.

[0016] Furthermore, the method for obtaining the temperature fluctuation moment is:

[0017] For the temperature image matrix at each acquisition moment, the temperature data in the temperature image matrix is ​​used as the input of the Otsu threshold segmentation algorithm to obtain the optimal segmentation threshold, and the temperature data greater than the optimal segmentation threshold is used as the welding joint temperature data;

[0018] At each acquisition moment, the sequence of all welding joint temperature data from left to right and from top to bottom in the temperature image matrix is ​​used as the welding temperature sequence at each acquisition moment;

[0019] The joint temperature difference coefficient of each collection moment is obtained based on the discrete degree of the welding joint temperature data and the distance between the welding joint temperature data, and the collection moment when the joint temperature difference coefficient is greater than the preset fluctuation threshold is taken as the temperature fluctuation moment.

[0020] Furthermore, the calculation formula of the joint temperature difference coefficient is: S i =var i +dtw(t i ,t i―1 );where S i Indicates the joint temperature difference coefficient at the i-th acquisition moment; var i represents the variance of all welding joint temperature data at the i-th acquisition moment, t i , t i―1They represent the welding temperature sequences at the i-th acquisition moment and the i-1-th acquisition moment respectively; dtw() represents the DTW distance.

[0021] Furthermore, the method for obtaining the fluctuation data is:

[0022] For each temperature fluctuation moment, all welding joint temperature data of the temperature image point matrix at the temperature fluctuation moment are used as the input of the Z-score algorithm to obtain the Z score of each welding joint temperature data, and the welding joint temperature data with a Z score greater than the first preset value and less than the second preset value are used as the fluctuation data of the temperature image point matrix at each temperature fluctuation moment.

[0023] Furthermore, the method for obtaining the fluctuation data cluster is:

[0024] A density clustering algorithm is used to obtain clusters of fluctuation data of the temperature image point matrix at each temperature fluctuation moment, as clusters of fluctuation data of the temperature image point matrix at each temperature fluctuation moment.

[0025] Furthermore, the calculation formula of the volatility distribution factor is: Where, F j is the fluctuation distribution factor at the jth temperature fluctuation moment; e j represents the mean number of elements in all fluctuation data clusters at the jth temperature fluctuation moment, k j represents the number of clusters of fluctuation data at the i-th temperature fluctuation moment, h j Represents the area of ​​the minimum circumscribed rectangle of all fluctuation data in the temperature image matrix at the jth temperature fluctuation moment.

[0026] Furthermore, the method for obtaining the temperature mutation factor is:

[0027] For each fluctuation data cluster of the temperature image point matrix at each temperature fluctuation moment, calculate the range of all fluctuation data within a neighborhood with a preset radius as the center and the fluctuation data with the smallest horizontal coordinate in the fluctuation data cluster as the mutation coefficient of the fluctuation data with the smallest horizontal coordinate;

[0028] The same method as the mutation coefficient of the fluctuation data with the smallest horizontal coordinate is used to obtain the mutation coefficients of the fluctuation data with the largest horizontal coordinate, the fluctuation data with the largest vertical coordinate, and the fluctuation data with the smallest vertical coordinate in the fluctuation data cluster. The sum of all the mutation coefficients in the fluctuation data cluster is used as the temperature mutation factor of each fluctuation data cluster in the temperature image point matrix at each temperature fluctuation moment.

[0029] Furthermore, the fluctuation mutation factor is the average of the temperature mutation factors of all fluctuation data clusters at each temperature fluctuation moment.

[0030] Furthermore, the laser intensity uneven weight is the ratio of the fluctuation distribution factor to the fluctuation mutation factor.

[0031] Furthermore, the monitoring of the welding joint temperature in the thermoplastic composite material welding scenario based on the laser intensity uneven weight includes:

[0032] Calculate the Z score of the laser intensity uneven weight at each temperature fluctuation moment in the welding process of thermoplastic composite materials among the laser intensity uneven weights at all temperature fluctuation moments;

[0033] For each temperature fluctuation moment, when the Z score of the laser intensity unevenness weight at the temperature fluctuation moment is greater than or equal to the third preset value, the temperature of the weld joint is abnormal; when the Z score of the laser intensity unevenness weight at the temperature fluctuation moment is less than the third preset value, the temperature of the weld joint is normal.

[0034] This application has at least the following beneficial effects:

[0035] This application addresses the problem that infrared thermal imagers are easily affected by electromagnetic interference when monitoring the surface temperature of welded joints, resulting in inaccurate monitored temperature data. A method for monitoring welded joint temperature in thermoplastic composite welding scenarios is proposed. First, a joint temperature difference coefficient is constructed based on the temperature changes before and after the temperature data and the temperature unevenness at the current moment. This accurately detects the moment when temperature fluctuations occur, improving the accuracy of temperature monitoring. Then, based on the distribution characteristics and mutation characteristics of the fluctuation data, a laser intensity unevenness weight is constructed to determine whether the current fluctuation data is caused by laser intensity unevenness. This eliminates the influence of electromagnetic interference on the temperature data, making temperature monitoring of welded joints more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0037] Figure 1 A flow chart of a method for monitoring weld joint temperature in a thermoplastic composite welding scenario provided in this application;

[0038] Figure 2 Flowchart for obtaining uneven weights for laser intensity. DETAILED DESCRIPTION

[0039] To further illustrate the technical means and effectiveness of this application's implementation of the intended invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of the weld joint temperature monitoring method for thermoplastic composite welding scenarios proposed in this application. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0040] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0041] The specific scheme of the welding joint temperature monitoring method in the thermoplastic composite material welding scenario provided by the present application is described in detail below with reference to the accompanying drawings.

[0042] An embodiment of the present application provides a method for monitoring the temperature of a welded joint in a thermoplastic composite material welding scenario. Specifically, the following method for monitoring the temperature of a welded joint in a thermoplastic composite material welding scenario is provided. Figure 1 , the method comprises the following steps:

[0043] Step S1 : collecting temperature data of different positions of the thermoplastic composite material at each collection moment in a welding scene, and forming a temperature image matrix at each collection moment.

[0044] Laser welding uses a highly focused laser beam to heat and melt the thermoplastic composite material at the joint, causing the materials to fuse as they cool. Laser welding methods are categorized as quasi-simultaneous welding, simultaneous welding, and mask welding. Simultaneous welding uses a laser emitter with multiple laser ports. Optical devices adjust the direction and shape of the laser beam, allowing the laser beam to weld along the contour of the weld layer, melting and bonding the entire contour simultaneously.

[0045] During the process of welding thermoplastic composite materials using synchronous laser welding, an infrared thermal imager is installed above the welding area of ​​the thermoplastic composite material so that the infrared thermal imager can directly observe the temperature distribution on the surface of the weld joint.

[0046] Furthermore, an infrared thermal image of the thermoplastic composite material at each acquisition moment is obtained by an infrared thermal imager, and a matrix composed of temperature data of each pixel in the infrared thermal image according to the position of the pixel is used as a temperature image point matrix at each acquisition moment.

[0047] Specifically, the data in the temperature pixel matrix represents the surface temperature of objects within the infrared thermal imager's observation range. Due to environmental noise interference, the collected temperature pixel matrix may contain noise. This embodiment uses a sampled median filter algorithm to denoise the collected temperature pixel matrix. Implementers may choose other denoising methods based on their specific circumstances. The median filter algorithm is a well-known technique, and the specific process will not be described in detail here.

[0048] Step S2, obtaining each temperature fluctuation moment based on the degree of discreteness of local temperature data in the temperature image point matrix and the distance between local temperature data; obtaining the fluctuation data of the temperature image point matrix at each temperature fluctuation moment based on the deviation of the temperature data of the welding joint; dividing the fluctuation data in the temperature image point matrix at each temperature fluctuation moment into each fluctuation data cluster; obtaining the fluctuation distribution factor at each temperature fluctuation moment based on the average number of elements in the fluctuation data cluster, the number of fluctuation data clusters and the distribution of fluctuation data.

[0049] Generally speaking, any object above absolute zero generates infrared radiation, with the higher the temperature, the stronger the intensity. Infrared thermal imagers can capture this infrared radiation, visually displaying the temperature distribution in the weld area. During laser welding, electromagnetic interference from the laser and other electrical equipment in the environment can cause inaccurate temperature data collected by the infrared imager. Therefore, the temperature data collected by the infrared thermal imager needs to be processed.

[0050] During simultaneous laser welding of thermoplastic composites, the weld joints of the thermoplastic composites receive the laser light simultaneously, causing the weld contours to melt simultaneously. Normally, the temperature distribution at the weld joint should be similar at different times. Temperature fluctuations could be due to temperature measurement errors caused by electromagnetic interference and laser radiation, or to fluctuations in the actual temperature at the weld joint.

[0051] Specifically, the temperature at the weld joint is significantly higher than that in other areas. Therefore, for each temperature image matrix collected at each time, the temperature data in the temperature image matrix is ​​used as input to the Otsu threshold segmentation algorithm to obtain the optimal segmentation threshold. Temperature data greater than the optimal segmentation threshold is used as the weld joint temperature data. The Otsu threshold segmentation algorithm is a well-known technique and is not described in detail in this embodiment.

[0052] For each acquisition moment, a sequence of all welding joint temperature data from left to right and from top to bottom in the temperature image point matrix is ​​used as the welding temperature sequence at each acquisition moment.

[0053] Furthermore, the joint temperature difference coefficient is constructed to characterize the temperature fluctuation degree of the welding joint at each acquisition time. The calculation formula is: Si =var i +dtw(t i ,t i―1 );where S i Indicates the joint temperature difference coefficient at the i-th acquisition moment; var i represents the variance of all welding joint temperature data at the i-th acquisition moment, t i , t i―1 They represent the welding temperature sequences at the i-th acquisition moment and the i-1-th acquisition moment respectively; dtw() represents the DTW distance.

[0054] It should be noted that var i The larger the value of , the greater the difference in the temperature data collected in the welding joint at the i-th collection time; dtw(t i ,t i―1 ) is larger, indicating that the temperature at the i-th acquisition moment has changed significantly compared to the temperature at the previous moment, which further indicates that the temperature at the i-th acquisition moment has fluctuated significantly; the joint temperature difference coefficient S i The larger the value of , the greater the fluctuation of the temperature data collected in the welding joint at the i-th collection time; conversely, the smaller the fluctuation of the temperature data collected in the welding joint at the i-th collection time.

[0055] For each collection moment, when the joint temperature difference coefficient at the collection moment is greater than the preset fluctuation threshold, the collection moment is taken as the temperature fluctuation moment. In this embodiment, the preset fluctuation threshold is 5, and the implementer can select other values ​​according to actual conditions.

[0056] Furthermore, it is necessary to determine whether the cause of the temperature fluctuation is a temperature measurement error caused by electromagnetic interference, or a change in the actual temperature of the weld joint. Specifically, during the operation of the infrared thermal imager, other electrical equipment in the environment will emit electromagnetic interference. This electromagnetic interference will cause the electronic components inside the infrared thermal imager to work unstably, thereby causing fluctuations in the temperature data. When the temperature data is subject to electromagnetic interference, it will appear as a large data fluctuation in the temperature data, and the area occupied by the fluctuating data will be smaller but more widely distributed. It will occur in the entire weld joint area, resulting in noise in the data in the weld joint area. When the temperature data is not subject to electromagnetic interference, the temperature data fluctuation is usually due to the uneven laser intensity emitted by the laser at different positions. This data fluctuation often does not occur in the entire weld joint area, but only a small part of the weld joint has temperature changes. Then the area occupied by the fluctuating data will be larger and more concentrated.

[0057] At each temperature fluctuation moment, all weld joint temperature data in the temperature image matrix at that moment is used as input to the Z-score algorithm. The Z score of each weld joint temperature data is obtained. The weld joint temperature data with a Z score greater than a first preset value and less than a second preset value is used as the fluctuation data for the temperature image matrix at that temperature fluctuation moment. In this embodiment, the first preset value is 2, and the second preset value is -2. Implementers may select other values ​​based on actual circumstances.

[0058] Furthermore, a DCP density clustering algorithm is used to obtain clusters of fluctuation data of the temperature image point matrix at each temperature fluctuation moment, which are used as clusters of fluctuation data of the temperature image point matrix at each temperature fluctuation moment. The Z-score algorithm and the DCP density clustering algorithm are well-known technologies and are not described in detail in this embodiment.

[0059] Based on the above analysis, a fluctuation distribution factor is constructed to characterize the similarity between the distribution characteristics of the fluctuation data collected in the weld joint at each temperature fluctuation moment and the distribution characteristics of the fluctuation data when the laser intensity is uneven. The calculation formula is: Where, F j is the fluctuation distribution factor at the jth temperature fluctuation moment; e j represents the mean number of elements in all fluctuation data clusters at the jth temperature fluctuation moment, k j represents the number of clusters of fluctuation data at the jth temperature fluctuation moment, h j Represents the area of ​​the minimum circumscribed rectangle of all fluctuation data in the temperature image matrix at the jth temperature fluctuation moment.

[0060] It should be noted that when e j When the value of is large, it means that the area occupied by each fluctuation data cluster at the jth temperature fluctuation moment is large, which further indicates that the temperature data fluctuation at the jth temperature fluctuation moment is more likely to be caused by uneven laser intensity. j The smaller the value of h is, the smaller the number of fluctuation data clusters at the jth temperature fluctuation moment is, which further indicates that the temperature data fluctuation at the jth temperature fluctuation moment is more likely to be caused by laser unevenness; j The smaller the value of , the more concentrated the fluctuation data at the j-th temperature fluctuation moment is, and further, the more likely the temperature data fluctuation at the j-th temperature fluctuation moment is the data fluctuation caused by laser unevenness. At this time, the larger the value of the fluctuation distribution factor obtained is; conversely, the smaller the value of the fluctuation distribution factor obtained is.

[0061] Step S3, obtaining the temperature mutation factor of each fluctuation data cluster of the temperature image point matrix at each temperature fluctuation moment based on the fluctuation range of all fluctuation data in the neighborhood of the fluctuation data at the edge of the fluctuation data cluster; obtaining the fluctuation mutation factor at each temperature fluctuation moment based on the average of the temperature mutation factor; obtaining the laser intensity uneven weight at each temperature fluctuation moment based on the fluctuation distribution factor and the fluctuation mutation factor.

[0062] When the infrared thermal imager is not subject to electromagnetic interference, if the temperature fluctuates due to uneven laser intensity, the temperature change between the high temperature area and the low temperature area is gradual, and the data with temperature fluctuations changes gradually relative to the data at the surrounding locations, without sudden changes. However, when the infrared thermal imager is subject to electromagnetic interference, the data with temperature fluctuations may change suddenly relative to the data at the surrounding locations.

[0063] Furthermore, in order to reflect the degree of mutation of the fluctuation data at each temperature fluctuation moment, for each fluctuation data cluster of the temperature image point matrix at each temperature fluctuation moment, the range of all fluctuation data within the neighborhood with the fluctuation data with the smallest horizontal coordinate in the fluctuation data cluster as the center and a preset radius as the radius is calculated as the mutation coefficient of the fluctuation data with the smallest horizontal coordinate. Similarly, the mutation coefficients of the fluctuation data with the largest horizontal coordinate, the fluctuation data with the largest vertical coordinate and the fluctuation data with the smallest vertical coordinate in the fluctuation data cluster are obtained, and the sum of all mutation coefficients in the fluctuation data cluster is used as the temperature mutation factor of each fluctuation data cluster of the temperature image point matrix at each temperature fluctuation moment.

[0064] It should be noted that, for each fluctuation data cluster of the temperature image point matrix at each temperature fluctuation moment, the values ​​of the mutation coefficients of the fluctuation data with the smallest horizontal coordinate, the fluctuation data with the largest horizontal coordinate, the fluctuation data with the largest vertical coordinate, and the fluctuation data with the smallest vertical coordinate reflect the degree of mutation of the fluctuation data at the edge of the fluctuation data cluster. The larger the value of the mutation coefficient, the greater the degree of mutation, and the greater the value of the temperature mutation factor of each fluctuation data cluster obtained at this time; conversely, the smaller the value of the temperature mutation factor obtained.

[0065] Furthermore, for each temperature fluctuation moment, the mean of the temperature mutation factors of all fluctuation data clusters is calculated as the fluctuation mutation factor at each temperature fluctuation moment.

[0066] Furthermore, for each temperature fluctuation moment, the ratio of the fluctuation distribution factor to the fluctuation mutation factor is calculated as the laser intensity uneven weight at each temperature fluctuation moment. The laser intensity uneven weight acquisition flow chart is as follows: Figure 2 shown.

[0067] When the value of the fluctuation mutation factor is small, it means that the temperature change of the fluctuation data at the temperature fluctuation moment is relatively gentle compared with the temperature data at the adjacent positions, which further indicates that the fluctuation data at the temperature fluctuation moment is more likely to be the fluctuation data caused by uneven laser intensity; when the value of the fluctuation distribution factor is large, it means that the distribution characteristics of the fluctuation data at the temperature fluctuation moment are more similar to the distribution characteristics of the fluctuation data when the laser intensity is uneven, which further indicates that the temperature data at the temperature fluctuation moment is more likely to be the fluctuation data caused by uneven laser intensity. At this time, the larger the value of the laser intensity uneven weight obtained, the more likely the fluctuation data at the temperature fluctuation moment is the fluctuation data caused by uneven laser intensity; otherwise, it means that the fluctuation data at the temperature fluctuation moment is less likely to be the fluctuation data caused by uneven laser intensity.

[0068] Step S4: monitoring the temperature of the weld joint in the thermoplastic composite material welding scenario based on the laser intensity uneven weight.

[0069] Furthermore, in order to reflect the degree to which the temperature data at the temperature fluctuation moment deviates from the normal situation due to the uneven laser intensity, the Z score of the laser intensity uneven weight at each temperature fluctuation moment in the thermoplastic composite welding process is calculated among the laser intensity uneven weights at all temperature fluctuation moments. The Z score is obtained using the Z-score algorithm.

[0070] For each temperature fluctuation moment, when the Z score of the laser intensity unevenness weight at the temperature fluctuation moment is greater than or equal to a third preset value, the fluctuation data at the temperature fluctuation moment is considered to be fluctuation data caused by laser intensity unevenness, indicating that the temperature of the weld joint is abnormal. At this time, an early warning is issued to remind the staff to adjust the welding parameters in a timely manner so that the temperature at the weld joint returns to normal. When the Z score of the laser intensity unevenness weight at the temperature fluctuation moment is less than the third preset value, the temperature fluctuation data at the temperature fluctuation moment is temperature fluctuation caused by electromagnetic interference, not temperature fluctuation caused by laser intensity unevenness. The temperature at the weld joint is normal, and there is no need to adjust the relevant parameters of the laser, and no early warning is issued. In this embodiment, the value of the third preset value is 2, and the implementer can select other values ​​according to actual conditions.

[0071] It should be noted that the order in which the embodiments of the present application are presented is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. Furthermore, the above descriptions are of specific embodiments of the present application. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order or sequential sequence shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0072] The various embodiments in this application are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0073] The above-described embodiments are only used to illustrate the technical solutions of the present application, and not to limit them. Modifications to the technical solutions described in the aforementioned embodiments, or equivalent replacements of some of the technical features therein, do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for monitoring the temperature of a welded joint in a thermoplastic composite material welding scenario, characterized in that: The method comprises the following steps: Collect temperature data of different positions of thermoplastic composite materials at each collection time in welding scenarios to form a temperature image matrix at each collection time; Obtain each temperature fluctuation moment based on the discrete degree of local temperature data in the temperature image matrix and the distance between local temperature data; Based on the deviation of the temperature data of the welding joint, the fluctuation data of the temperature image matrix at each temperature fluctuation moment is obtained; Dividing the fluctuation data in the temperature image point matrix at each temperature fluctuation moment into various fluctuation data clusters; Based on the average number of elements in the fluctuation data clusters, the number of fluctuation data clusters and the distribution of fluctuation data, the fluctuation distribution factor at each temperature fluctuation moment is obtained; Obtaining the temperature mutation factor of each fluctuation data cluster of the temperature image point matrix at each temperature fluctuation moment based on the fluctuation range of all fluctuation data in the neighborhood of the edge fluctuation data in the fluctuation data cluster; Obtain the fluctuation mutation factor at each temperature fluctuation moment based on the average of the temperature mutation factor; The laser intensity uneven weight at each temperature fluctuation moment is obtained based on the fluctuation distribution factor and the fluctuation mutation factor; Monitoring the weld joint temperature in thermoplastic composite welding scenarios based on laser intensity uneven weight; The method for obtaining the temperature fluctuation moment is: For the temperature image matrix at each acquisition moment, the temperature data in the temperature image matrix is ​​used as the input of the Otsu threshold segmentation algorithm to obtain the optimal segmentation threshold, and the temperature data greater than the optimal segmentation threshold is used as the welding joint temperature data; At each acquisition moment, the sequence of all welding joint temperature data from left to right and from top to bottom in the temperature image matrix is ​​used as the welding temperature sequence at each acquisition moment; The joint temperature difference coefficient of each collection moment is obtained based on the discrete degree of the welding joint temperature data and the distance between the welding joint temperature data, and the collection moment when the joint temperature difference coefficient is greater than the preset fluctuation threshold is taken as the temperature fluctuation moment.

2. The method for monitoring the temperature of a welded joint in a thermoplastic composite material welding scenario according to claim 1, wherein: The calculation formula of the joint temperature difference coefficient is: Where, represents the joint temperature difference coefficient at the i-th acquisition moment; represents the variance of all welding joint temperature data at the i-th acquisition moment, 、 Represent the welding temperature sequences at the i-th acquisition moment and the i-1-th acquisition moment respectively; represents the DTW distance.

3. The method for monitoring the temperature of a welded joint in a thermoplastic composite material welding scenario according to claim 1, wherein: The method for obtaining the fluctuation data is: For each temperature fluctuation moment, all welding joint temperature data of the temperature image point matrix at the temperature fluctuation moment are used as the input of the Z-score algorithm to obtain the Z score of each welding joint temperature data, and the welding joint temperature data with a Z score greater than the first preset value and less than the second preset value are used as the fluctuation data of the temperature image point matrix at each temperature fluctuation moment.

4. The method for monitoring the temperature of a welded joint in a thermoplastic composite material welding scenario according to claim 3, wherein: The method for obtaining the fluctuation data cluster is: A density clustering algorithm is used to obtain clusters of fluctuation data of the temperature image point matrix at each temperature fluctuation moment, as clusters of fluctuation data of the temperature image point matrix at each temperature fluctuation moment.

5. The method for monitoring the temperature of a welded joint in a thermoplastic composite material welding scenario according to claim 1, wherein: The calculation formula of the volatility distribution factor is: Where, is the fluctuation distribution factor at the jth temperature fluctuation moment; represents the mean number of elements of all fluctuation data clusters at the jth temperature fluctuation moment, represents the number of clusters of fluctuation data at the jth temperature fluctuation moment, Represents the area of ​​the minimum circumscribed rectangle of all fluctuation data in the temperature image matrix at the jth temperature fluctuation moment.

6. The method for monitoring the temperature of a welded joint in a thermoplastic composite material welding scenario according to claim 1, wherein: The method for obtaining the temperature mutation factor is: For each fluctuation data cluster of the temperature image point matrix at each temperature fluctuation moment, calculate the range of all fluctuation data within a neighborhood with a preset radius as the center and the fluctuation data with the smallest horizontal coordinate in the fluctuation data cluster as the mutation coefficient of the fluctuation data with the smallest horizontal coordinate; The same method as the mutation coefficient of the fluctuation data with the smallest horizontal coordinate is used to obtain the mutation coefficients of the fluctuation data with the largest horizontal coordinate, the fluctuation data with the largest vertical coordinate, and the fluctuation data with the smallest vertical coordinate in the fluctuation data cluster. The sum of all the mutation coefficients in the fluctuation data cluster is used as the temperature mutation factor of each fluctuation data cluster in the temperature image point matrix at each temperature fluctuation moment.

7. The method for monitoring the temperature of a welded joint in a thermoplastic composite material welding scenario according to claim 1, wherein: The fluctuation mutation factor is the mean of the temperature mutation factors of all fluctuation data clusters at each temperature fluctuation moment.

8. The method for monitoring the temperature of a welded joint in a thermoplastic composite material welding scenario according to claim 1, wherein: The laser intensity uneven weight is the ratio of the fluctuation distribution factor to the fluctuation mutation factor.

9. The method for monitoring the temperature of a welded joint in a thermoplastic composite material welding scenario according to claim 3, wherein: The monitoring of the welding joint temperature in the thermoplastic composite material welding scenario based on the laser intensity uneven weight includes: Calculate the Z score of the laser intensity uneven weight at each temperature fluctuation moment in the welding process of thermoplastic composite materials among the laser intensity uneven weights at all temperature fluctuation moments; For each temperature fluctuation moment, when the Z score of the laser intensity unevenness weight at the temperature fluctuation moment is greater than or equal to the third preset value, the temperature of the weld joint is abnormal; when the Z score of the laser intensity unevenness weight at the temperature fluctuation moment is less than the third preset value, the temperature of the weld joint is normal.

Images