A calculation system and method for ultrasonic welding control model

Abstract

The present invention provides a computing system and method for an ultrasonic welding control model, including: a path generation module, used to obtain the to-be-welded portion of the material on the template, and generate a welding path according to the shape of the to-be-welded portion; a path division module, used to divide the welding path and obtain a number of turning sections; a difficulty analysis module, used to classify the steering control difficulty of each turning section through a preset difficulty assessment model; a mode selection module, used to select different control modes through a preset mode control model based on the steering control difficulty of different turning sections; a welding control module, used to control the ultrasonic welding equipment to perform welding operations on the material based on the control mode selection of each turning section. The present invention has a good ultrasonic welding control effect, improves the ultrasonic welding accuracy, thereby optimizes the welding quality of the ultrasonic equipment, and takes into account the ultrasonic welding efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of ultrasonic welding, and in particular to a calculation system and method of an ultrasonic welding control model. Background Art

[0002] Ultrasonic welding is a technology that uses high-frequency ultrasonic vibration energy to connect materials. It is often used for welding materials. Ultrasonic welding is widely used in industries such as medical equipment and clothing production.

[0003] In the clothing production process, ultrasonic welding does not require the addition of any welding materials. It only replaces traditional sewing threads by fusing two layers of fabric together at the molecular level under the action of ultrasound.

[0004] However, the lines of clothing are becoming increasingly complex. In the prior art, when using ultrasonic welding, the control effect of some complex welding paths or welding routes is poor, which often leads to poor process quality or affects the production efficiency of clothing.

[0005] Therefore, there is a need for a solution to solve at least one of the above problems. Summary of the invention

[0006] In view of the defects in the prior art, the present application proposes a calculation system and method for an ultrasonic welding control model. To solve at least one of the above technical problems, the technical solution of the present application is:

[0007] A computing system of an ultrasonic welding control model is applied to an ultrasonic welding device, wherein the ultrasonic welding device comprises an ultrasonic welding head, a pressing device and a template control device; the shape of the ultrasonic welding head comprises a disc shape, a pressing wheel is arranged on the pressing device, the ultrasonic welding head and the pressing wheel are arranged opposite to each other, the template is located between the ultrasonic welding head and the pressing wheel, and the template control device is used to fix the template or drive the template to rotate;

[0008] The computing system includes:

[0009] A path generation module is used to obtain the to-be-welded portion of the material on the template and generate a welding path according to the shape of the to-be-welded portion;

[0010] A path division module, used for dividing the welding path to obtain a plurality of turning sections;

[0011] A difficulty analysis module, used to classify the steering control difficulty of each turning section through a preset difficulty evaluation model to obtain a turning section including a first difficulty and a second difficulty;

[0012] A mode selection module, for selecting different control modes through a preset mode control model based on the steering control difficulty of different turning sections;

[0013] The welding control module is used to control the ultrasonic welding equipment to perform welding operations on the material based on the control mode selection of each turning section.

[0014] In a specific embodiment, the mode control model is used to select a first control mode when the steering control difficulty of the turning section is the first difficulty, so that the welding control module controls the ultrasonic welding head and the pressing wheel to move synchronously at a first speed along a first direction or controls the template to move at a first speed along a first direction, and feeds back the synchronous movement state of the ultrasonic welding head and the pressing wheel or the movement state of the template at a first feedback frequency;

[0015] When the steering control difficulty of the turning section is the second difficulty, the second control mode is selected, so that the welding control module mainly controls the ultrasonic welding head and the pressing wheel to rotate synchronously at the second speed along the first direction, and simultaneously controls the template to rotate along the first direction in coordination with the ultrasonic welding head as an auxiliary, and feeds back the relative motion state of the ultrasonic welding head, the pressing wheel and the template at the second feedback frequency, so as to realize the welding of the turning section;

[0016] Wherein, the first speed is not less than the second speed, and the first feedback frequency is not greater than the second feedback frequency;

[0017] The establishment of the mode control model includes: obtaining a sample set, the sample set includes a plurality of training samples, and the training samples include input data and output data;

[0018] The input data includes one or any multiple of steering control difficulty, preset quality requirements, production efficiency requirements, material characteristics and production costs;

[0019] The output data includes selecting the first control mode or the second control mode and the control parameters corresponding to each control mode, wherein the control parameters include: one or any multiple of feedback frequency, movement speed, pressing force and ultrasonic transducer amplitude;

[0020] The input data and the output data are used to perform deep learning model training. If the control mode output by the deep learning model and the control parameters corresponding to the control mode meet the preset targets, the training is terminated to obtain the mode control model.

[0021] In a specific embodiment, the computing system further includes: a visual detection module;

[0022] The visual inspection module is used to perform effect inspection on the welding path after welding to obtain the path inspection result;

[0023] And according to the path detection result, the control parameters output in the mode control model are adjusted.

[0024] In a specific embodiment, the ultrasonic welding device is further provided with an ultrasonic transducer, and the ultrasonic welding head and the pressing wheel are both connected with a first rotating device and a second rotating device;

[0025] The ultrasonic transducer is coaxially arranged with the center of the ultrasonic horn so that the vibration energy converted by the ultrasonic transducer is transmitted along the radial direction of the ultrasonic horn, the ultrasonic horn has a welding portion, the pressing wheel has a pressing portion, and the shape of the welding portion and / or the pressing portion includes an arc;

[0026] The welding control module is also used to control the first rotating device to drive the ultrasonic welding head and / or the pressing wheel to rotate along a first direction, so as to switch the welding part and / or the pressing part to different positions of the template;

[0027] The welding control module is used to control the second rotating device to drive the ultrasonic welding head and / or the pressing wheel to rotate along the second direction to switch the contact between the welding part and / or different parts on the pressing part and the template;

[0028] Among them, the first direction uses the first rotation axis as the rotation axis, and the first rotation axis is perpendicular or approximately perpendicular to the plane where the template is located; the second direction uses the second rotation axis as the rotation axis, and the second rotation axis is parallel or approximately parallel to the plane where the template is located.

[0029] In a specific embodiment, the path division module is used to divide the welding path to obtain a plurality of turning sections, which specifically includes:

[0030] generating a reference path based on the welding path;

[0031] Acquire a plurality of welding points on the welding path at preset intervals;

[0032] Taking any welding point as the target, the two welding points adjacent to it are the first welding point and the second welding point respectively;

[0033] If any two of the welding points and the corresponding first welding point and second welding point are located at different sides of the reference path, the welding path between the first welding point and the second welding point is used as a turning section.

[0034] In a specific embodiment, if each of the welding points, and its corresponding first welding point and second welding point are all located on the same side of the reference path;

[0035] then calculating the shortest straight-line distance from each welding point to the reference path as a first distance, and comparing a first distance trend from a first welding point to the welding point with a second distance trend from the welding point to the second welding point;

[0036] If the first distance trend and the second distance trend change, the welding path between the first welding point and the second welding point is used as a turning section.

[0037] In a specific embodiment, the difficulty analysis module is used to classify the steering control difficulty of each turning section and specifically includes:

[0038] Obtaining the steering control difficulty influencing factors of each turning section, and inputting the steering control difficulty influencing factors into the difficulty assessment model;

[0039] The difficulty assessment model obtains the weight values ​​of the preset steering control difficulty influencing factors;

[0040] The factors affecting the difficulty of steering control include one or more of steering angle, smoothness, and curvature change;

[0041] The difficulty assessment model calculates and outputs a steering control difficulty score for each of the turning sections based on the weight values ​​and the steering control difficulty influencing factors and in combination with the interactions between the steering control difficulty influencing factors;

[0042] Furthermore, the difficulty assessment model further classifies each of the turning sections into a first difficulty and a second difficulty according to the steering control difficulty score.

[0043] In a specific embodiment, the computing system further includes: a path determination module;

[0044] The path judgment module is used to judge whether the welding path is new; if the welding path is new, after the welding control module completes controlling the ultrasonic welding equipment to perform welding operations on the material, the welding path and the welding control method corresponding to the welding path are stored.

[0045] In a specific embodiment, the computing system further includes: a control and regulation module;

[0046] The control and adjustment module is used to sort all the turning sections according to the welding sequence on the welding path and store them in the form of a queue;

[0047] The data corresponding to the first control mode is the first data, and the data corresponding to the second control mode is the second data;

[0048] Traversing all the data in the queue, filtering out all the first data, and determining the position of the first data; if the first data is located at the first and / or the last of the queue, keeping the first data unchanged;

[0049] If the first data is in the queue, and a preset number of data on both sides of the first data are second data, the turning section corresponding to the first data is adjusted from the first control mode to the second control mode, and the corresponding control parameters are adjusted accordingly.

[0050] A calculation method of an ultrasonic welding control model is applied to a calculation system of an ultrasonic welding control model described in any one of the first part, and the calculation method comprises:

[0051] Obtaining the to-be-welded portion of the material on the template, and generating a welding path according to the shape of the to-be-welded portion;

[0052] Dividing the welding path to obtain a plurality of turning sections;

[0053] Classifying the steering control difficulty of each turning section by a preset difficulty assessment model to obtain a turning section including a first difficulty and a second difficulty;

[0054] Based on the steering control difficulty of different turning sections, different control modes are selected through a preset mode control model;

[0055] Based on the selection of different control modes, the ultrasonic welding equipment is controlled to perform welding operations on the materials.

[0056] Beneficial effects:

[0057] The present invention provides a calculation system and method for an ultrasonic welding control model, which has a good ultrasonic welding control effect, improves the ultrasonic welding accuracy, thereby optimizing the welding quality of ultrasonic equipment, and takes into account the ultrasonic welding efficiency;

[0058] Specifically, the shape of the ultrasonic horn includes a disc shape, and the ultrasonic horn and the pressing wheel are arranged opposite to each other to press the template and the material, thereby changing the contact position between the ultrasonic horn and the template, and also changing the abutment position between the ultrasonic horn and the pressing wheel, thereby optimizing the welding accuracy and flexibility of ultrasonic welding, and helping to improve the welding quality;

[0059] Based on the structural characteristics of the improved ultrasonic welding head and the pressing wheel, the welding flexibility is improved, the ultrasonic welding control is facilitated, and thus it helps to strengthen the control of the ultrasonic welding head welding. The control difficulty of the turning sections in the welding path is classified through a preset difficulty assessment model, and the control mode is selected for the classified turning sections through a preset mode control model. When the first control mode is selected, the welding efficiency can be effectively improved. When the second control mode is selected, the welding quality of the turning sections with high complexity can be effectively reduced, and the wrinkles generated during the welding process can be reduced. By switching and selecting the first control mode and the second control mode, the problems of production quality and production efficiency can be effectively balanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0061] Figure 1 Computational system structure of ultrasonic welding control model for the embodiment Figure 1 ;

[0062] Figure 2 Computational system structure of ultrasonic welding control model for the embodiment Figure 2 ;

[0063] Figure 3 is a flow chart of a calculation method of an ultrasonic welding control model of an embodiment;

[0064] Figure 4 A flow chart for establishing a mode control model of an embodiment;

[0065] Figure 5 A three-dimensional structural diagram of an ultrasonic welding device according to an embodiment;

[0066] Figure 6 It is a diagram showing the internal structure of the ultrasonic welding equipment of the embodiment;

[0067] Figure 7 is a schematic diagram of a first rotation direction of an embodiment;

[0068] Figure 8 is a schematic diagram of a second rotation direction of an embodiment;

[0069] Fig. 9 It is a position relationship diagram of the pressing device and the ultrasonic welding head of the embodiment.

[0070] Reference numerals:

[0071] 1-path generation module; 2-path division module; 3-difficulty analysis module; 4-mode selection module; 5-welding control module; 6-visual inspection module; 7-path judgment module; 8-control and adjustment module; 1a-ultrasonic welding head; 11a-welding part; 2a-pressing device; 21a-pressing wheel; 210a-pressing part; 3a-ultrasonic transducer; 4a-first rotating device; 5a-second rotating device; 6a-template; 7a-template control device. DETAILED DESCRIPTION

[0072] In the following, various embodiments of the present disclosure will be described more fully. The present disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but rather the present disclosure should be understood to cover all adjustments, equivalents and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.

[0073] Hereinafter, the terms "include" or "may include" that may be used in various embodiments of the present disclosure indicate the presence of disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. In addition, as used in various embodiments of the present disclosure, the terms "include", "have", and their cognates are intended only to indicate specific features, numbers, steps, operations, elements, components, or a combination of the foregoing, and should not be understood as first excluding the presence of one or more other features, numbers, steps, operations, elements, components, or a combination of the foregoing or the possibility of adding one or more features, numbers, steps, operations, elements, components, or a combination of the foregoing.

[0074] In various embodiments of the present disclosure, the expression "or" or "at least one of A or / and B" includes any combination or all combinations of the words listed at the same time. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.

[0075] The expressions (such as "first", "second", etc.) used in the various embodiments of the present disclosure may modify the various constituent elements in the various embodiments, but may not limit the corresponding constituent elements. For example, the above expressions do not limit the order and / or importance of the elements. The above expressions are only used for the purpose of distinguishing one element from other elements. For example, the first user device and the second user device indicate different user devices, although both are user devices. For example, without departing from the scope of the various embodiments of the present disclosure, the first element may be referred to as the second element, and similarly, the second element may also be referred to as the first element.

[0076] It should be noted that if it is described that one component element is “connected” to another component element, the first component element may be directly connected to the second component element, and a third component element may be “connected” between the first component element and the second component element. Conversely, when one component element is “directly connected” to another component element, it can be understood that there is no third component element between the first component element and the second component element.

[0077] The term “user” used in various embodiments of the present disclosure may indicate a person using an electronic device or a device (eg, an artificial intelligence electronic device) using the electronic device.

[0078] The terms used in the various embodiments of the present disclosure are only used for the purpose of describing specific embodiments and are not intended to limit the various embodiments of the present disclosure. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the meanings commonly understood by ordinary technicians in the field to which the various embodiments of the present disclosure belong. The terms (such as the terms defined in the generally used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in the various embodiments of the present disclosure.

[0079] Example 1

[0080] The present application embodiment proposes a computing system for an ultrasonic welding control model, such as Figure 1 and Figure 2 As shown, it is applied to ultrasonic welding equipment, such as Figures 5 to 9 As shown, the ultrasonic welding equipment includes an ultrasonic welding head 1a, a pressing device 2a and a template control device 7a;

[0081] The shape of the ultrasonic horn 1a includes a disc shape, a pressing wheel 21a is provided on the pressing device 2a, the ultrasonic horn 1a and the pressing wheel 21a are arranged opposite to each other, the template 6a is located between the ultrasonic horn 1a and the pressing wheel 21a, and the template control device 7a is used to fix the template 6a or drive the template 6a to rotate;

[0082] More specifically, the template 6a is located between the ultrasonic horn 1a and the pressing wheel 21a. The pressing wheel 21a presses the template 6a. Under the joint action of the ultrasonic horn 1a, a pressing force is applied to the template 6a, which helps to fix the template 6a and the material.

[0083] It can be understood that the disc-shaped ultrasonic welding head 1a has greater flexibility and can be flexibly adjusted according to the shape of the welding path, which helps to improve the control accuracy and thus improve the quality of ultrasonic welding. The ultrasonic welding head 1a and the pressing wheel 21a are arranged relative to each other. The ultrasonic welding head 1a and the pressing wheel 21a act together on the welding area of ​​the material, which can transmit ultrasonic energy more accurately, so that the force is evenly applied during the entire welding process, thereby improving the consistency of ultrasonic welding.

[0084] like Figure 1 As shown, the computing system includes:

[0085] A path generation module 1 is used to obtain the to-be-welded portion of the material on the template and generate a welding path according to the shape of the to-be-welded portion;

[0086] Specifically, in some embodiments of the present application, the shape of the material to be welded on the template is mainly obtained based on the analysis of the material processing order;

[0087] Optionally, in other embodiments of the present application, the location to be welded of the material on the template can be obtained through material management data stored in a database, and can also be obtained by taking a photo and identifying the photo.

[0088] Of course, there is no limitation on the specific shape of the part to be welded on the template.

[0089] A path division module 2 is used to divide the welding path to obtain a number of turning sections;

[0090] The turning section is the part of the welding path that needs to change direction, which can generally be the corner or turning point of the welding path. In clothing welding and sewing, in order to adapt to the complex shapes of clothing, such as pockets, sleeves, trouser legs, etc., such turning sections are generally required. Ultrasonic equipment usually needs to move and turn in these parts to complete the welding goal;

[0091] The path division module 2 breaks down the welding path into several turning sections, which helps to subsequently optimize the turning points in the welding path individually, achieve precise control of each turning section, and thus reduce the vibration or deviation of the equipment during turning, thereby improving the uniformity and firmness of the welding points, and can further balance production efficiency and production quality.

[0092] A difficulty analysis module 3, for classifying the steering control difficulty of each turning section by a preset difficulty evaluation model, and obtaining turning sections including a first difficulty and a second difficulty;

[0093] Specifically, in some embodiments of the present application, the preset difficulty assessment model is a deep learning model;

[0094] Of course, there is no restriction on whether the difficulty assessment model is a deep learning model.

[0095] A mode selection module 4, for selecting different control modes through a preset mode control model based on the steering control difficulty of different turning sections;

[0096] Understandably, selecting different control modes through a preset mode control model helps the computing system to more accurately and efficiently handle welding paths of different difficulties and optimize operations and resource allocation.

[0097] The welding control module 5 is used to control the ultrasonic welding equipment to perform welding operations on the materials based on the control mode selection of each turning section.

[0098] Therefore, the calculation system of the ultrasonic welding control model proposed in this embodiment improves the accuracy of welding control according to the actual state of the welding path, realizes targeted processing of different turning sections, obtains relatively good welding effects, reduces resource waste, focuses on improving production efficiency, has strong adaptability, and can automatically adjust the control mode according to changes in materials and welding environment, thereby improving the adaptability of the system under different working conditions.

[0099] Further, the mode control model is used to select the first control mode when the steering control difficulty of the turning section is the first difficulty, so that the welding control module 5 controls the ultrasonic welding head 1a and the pressing wheel 21a to move synchronously at a first speed along a first direction or controls the template 6a to move at a first speed along a first direction, and feeds back the synchronous movement state of the ultrasonic welding head 1a and the pressing wheel 21a or the movement state of the template 6a at a first feedback frequency;

[0100] When the steering control difficulty of the turning section is the second difficulty, the second control mode is selected, so that the welding control module 5 controls the ultrasonic welding head 1a and the pressing wheel 21a to rotate synchronously along the first direction at the second speed as the main, and controls the template 6a to rotate along the first direction in coordination with the ultrasonic welding head 1a as the auxiliary, and feeds back the relative motion state of the ultrasonic welding head 1a, the pressing wheel 21a and the template 6a at the second feedback frequency, so as to realize the welding of the welding path corresponding to the turning section;

[0101] It can be understood that the ultrasonic welding head 1a and the pressing wheel 21a are controlled to rotate synchronously along the first direction as the main control, and the template 6a is controlled to rotate in coordination along the first direction as the auxiliary control, thereby reducing the control of the rotation of the template 6a, and can avoid the position offset between the material and the template 6a to a certain extent, reduce the generation of wrinkles at the material welding point, and thus improve the quality of the finished product.

[0102] Wherein, the first speed is not less than the second speed, and the first feedback frequency is not greater than the second feedback frequency;

[0103] It can be understood that by adaptively adjusting the welding speed and feedback frequency, different welding requirements can be flexibly adapted; selecting a suitable control mode based on the steering control difficulty of different turning sections can make the welding process more accurate, wherein the turning section belonging to the first difficulty is a relatively simple section, and a relatively simple control mode is adopted to control the ultrasonic welding head 1a and the pressing wheel 21a to turn, which is completed at a higher speed and a lower feedback frequency, thereby avoiding over-adjustment, shortening the welding time, and helping to improve production efficiency;

[0104] The turning section of the second difficulty is a more complicated section. Through a more detailed control mode, the ultrasonic welding head 1a and the pressing wheel 21a rotate synchronously. At the same time, the relative movement of the template 6a and the ultrasonic welding head 1a is also coordinated. This is achieved using a lower speed and a higher feedback frequency to ensure that the welding effect is not affected by the complex shape, thereby optimizing the welding quality.

[0105] Furthermore, there may be differences in feedback control strategies between the first control mode and the second control mode. For example, in the first control mode, the computing system may adopt a simpler feedback control method, such as proportional control, to respond quickly and reduce the amount of calculation; while the second control mode may adopt a more sophisticated feedback strategy, such as adaptive control, fuzzy control or robust control.

[0106] There may also be differences in signal processing and filtering methods between the first control mode and the second control mode. For example, when in the first control mode, signal processing can focus on low-frequency filtering to reduce sensitivity to high-frequency interference; when in the second control mode, signal processing can focus on high-frequency filtering and multi-band analysis. In addition, noise suppression technology can be combined to improve processing accuracy.

[0107] The first control mode and the second control mode may also have differences in motion control, energy regulation, power control, etc.

[0108] Among them, when in the first control mode, a direct trajectory generation algorithm can be used to generate a turning section of the first difficulty. The motion control strategy of the ultrasonic welding head is relatively rough, and linear interpolation or simple straight line interpolation can be used to achieve welding; and energy regulation may be carried out in a relatively constant power manner to ensure welding speed and efficiency.

[0109] When in the second control mode, a more sophisticated trajectory generation algorithm can be used for the turning section of the second difficulty, such as Bezier curves, spline curves and other methods; the motion control strategy of the ultrasonic welding head can involve joint space control or task space control to reduce errors; dynamic energy adjustment can also be used to adapt to the tortuosity of the turning section, such as instantaneous power adjustment and power feedback control.

[0110] In addition, the second control mode also has higher real-time adjustment and dynamic compensation functions, for example, using real-time data to adjust welding parameters, or using model predictive control (MPC) to predict possible deviations on the path and compensate for them.

[0111] Furthermore, if Figure 4 As shown, the establishment of the mode control model includes:

[0112] S601: Acquire a sample set, where the sample set includes multiple training samples, and the training samples include input data and output data;

[0113] More specifically, in some embodiments of the present application, the data of the sample set needs to be standardized or normalized to ensure that the numerical range of the input features is consistent, so as to speed up the training and improve the stability of the model.

[0114] S602: Input data includes one or more of steering control difficulty, preset quality requirements, production efficiency requirements, material characteristics, and production costs;

[0115] S603: Outputting data includes selecting the first control mode or the second control mode and corresponding control parameters under each control mode, wherein the control parameters include: one or more of feedback frequency, movement speed, pressing force and ultrasonic transducer amplitude;

[0116] Exemplarily, the input data may be steering control difficulty: 0.8, preset quality requirement: high, production efficiency requirement: medium, material property: hard material, and production cost: low.

[0117] The output data can be: select control mode: first control mode, feedback frequency: 50Hz, movement speed: 5mm / s, pressing force: 5N.

[0118] S604: Use the input data and output data to train the deep learning model. If the control mode output by the deep learning model and the control parameters corresponding to the control mode meet the preset goals, the training is terminated to obtain the mode control model.

[0119] For example, assuming that the control mode predicted by the deep learning model on the test set is the "first control mode", and the control parameters are a feedback frequency of 50 Hz and a movement speed of 5 mm / s, which is consistent with the preset target: "first control mode", feedback frequency of 45-60 Hz, and movement speed of 3 mm / s-6 mm / s, then the model has completed training.

[0120] In addition, the welding quality can be judged in actual welding operations to verify the accuracy of the deep learning model.

[0121] Furthermore, if Figure 2 As shown, the computing system further includes: a visual detection module 6;

[0122] Specifically, in some embodiments of the present application, an industrial camera may also be provided on the ultrasonic welding equipment to capture high-resolution images or videos with a high frame rate and precise focusing function, which helps the visual inspection module 6 to obtain the required input images or videos.

[0123] A visual inspection module 6 is used to inspect the welding path after welding and obtain the path inspection result;

[0124] And according to the path detection results, the control parameters output in the mode control model are adjusted.

[0125] It can be understood that the visual inspection module 6 can capture and analyze the welding path in the welding process in real time, detect path deviations, welding defects (such as welds that are too wide, too narrow, unwelded areas, etc.). According to the detection results, the system can promptly detect quality problems and adjust the control mode and parameters (such as movement speed, ultrasonic transducer 3a amplitude, etc.) to correct these deviations; the visual inspection module 6 provides accurate welding path feedback, so that the computing system can fine-tune the control parameters based on the actual welding effect.

[0126] Furthermore, if Figures 6 to 9 As shown, the ultrasonic welding device is also provided with an ultrasonic transducer 3a, and the ultrasonic welding head 1a and the pressing wheel 21a are both connected with a first rotating device 4a and a second rotating device 5a;

[0127] The ultrasonic transducer 3a is coaxially arranged with the center of the ultrasonic horn 1a, so that the vibration energy converted by the ultrasonic transducer 3a is transmitted along the radial direction of the ultrasonic horn 1a, the ultrasonic horn 1a has a welding portion 11a, the pressing wheel 21a has a pressing portion 210a, and the shape of the welding portion 11a and / or the pressing portion 210a includes an arc;

[0128] It can be understood that the shape of the ultrasonic welding head 1a includes a disc shape, and the curved surface of the disc shape is the welding part 11a. The curved surface of the ultrasonic welding head 1a is the direct transmission surface of the ultrasonic vibration. When the ultrasonic generator generates high-frequency vibrations, the curved surface will evenly transmit these vibrations to the welding point of the material; the disc-shaped design can help the ultrasonic vibration to act on the entire welding contact surface in a more uniform manner, avoiding uneven distribution of energy, and also helping to achieve more precise ultrasonic welding control, thereby helping to improve the ultrasonic welding effect.

[0129] The welding control module 5 is also used to control the first rotating device 4a to drive the ultrasonic welding head 1a and / or the pressing wheel 21a to rotate along the first direction to switch the welding part 11a and / or the pressing part 210a to different positions of the template 6a;

[0130] The welding control module 5 is used to control the second rotating device 5a to drive the ultrasonic welding head 1a and / or the pressing wheel 21a to rotate along the second direction to switch the contact between different parts of the welding part 11a and / or the pressing part 210a and the template 6a;

[0131] The ultrasonic welding head 1a and the pressing wheel 21a can rotate synchronously along the first direction and the second direction, which helps the welding head to achieve precise control of the contact position of welding paths in different positions and shapes, making the ultrasonic welding operation more flexible to meet the welding requirements of complex welding paths.

[0132] Among them, Figure 7 As shown, the first direction uses the first rotation axis as the rotation axis, and the first rotation axis is perpendicular or approximately perpendicular to the plane where the template 6a is located. The dotted line portion in the figure represents the first rotation axis, and the arrow direction in the figure represents the first direction;

[0133] like Figure 8 As shown, the second direction is the second rotation axis, the second rotation axis is parallel or approximately parallel to the plane where the template 6a is located, the dotted line portion in the figure represents the second rotation axis, and the arrow direction in the figure represents the second direction;

[0134] When the ultrasonic welding head 1a rotates with the second rotation axis as the rotation axis, it can also achieve a certain cooling and heat dissipation effect by switching different parts of the welding part 11a to contact the material. It can avoid a fixed part of the welding part 11a from being subjected to heat for a long time, thereby reducing local overheating. Such dynamic contact method can make the welding process more stable and improve cooling efficiency.

[0135] The mode control model is also used to select the first control mode when the steering control difficulty of the turning section is the first difficulty, so that the welding control module 5 controls the ultrasonic welding head 1a and the pressing wheel 21a to move synchronously along the second direction at a third speed;

[0136] When the steering control difficulty of the turning section is the second difficulty, the second control mode is selected to make the welding control module 5 control the ultrasonic welding head 1a and the pressing wheel 21a to rotate synchronously along the second direction at a fourth speed;

[0137] Among them, the fourth speed is not higher than the third speed.

[0138] Furthermore, the path division module 2 is used to divide the welding path to obtain a number of turning sections, specifically including:

[0139] Generate a reference path based on the welding path;

[0140] Specifically, in some embodiments of the present application, the starting point and the end point of the welding path are first obtained, and the starting point and the end point of the reference path are connected by a straight line to generate the reference path;

[0141] This can achieve a faster reference path generation speed and reduce system processing load. Of course, there is no restriction on the reference path generation method.

[0142] Obtaining a number of welding points on the welding path at preset intervals;

[0143] Specifically, in some embodiments of the present application, the preset interval can be a fixed-length interval distance made according to the length of the welding path. After the turning section is obtained, the turning section is further divided once or multiple times according to a smaller preset interval, so as to capture the welding path change trend with greater accuracy.

[0144] In other embodiments of the present application, the preset interval may also be a dynamically changing interval made based on the length, curvature shape and geometric characteristics of the welding path. For example, in areas with larger bends, the preset interval may be reduced to increase the density of discrete points and ensure that changes in the welding path are fully captured.

[0145] Of course, there is no limitation on the processing and setting of the preset interval.

[0146] Taking any welding point as the target, the two welding points adjacent to it are the first welding point and the second welding point respectively;

[0147] If any two of the welding points and their corresponding first welding points and second welding points are located on different sides of the reference path, that is, as long as one of the three is not on the same side of the reference path as the other two, the welding path between the first welding point and the second welding point is used as the turning section.

[0148] Specifically, in some embodiments of the present application, a normal vector (a direction perpendicular to the reference path) can be used to more accurately determine whether the welding point is on different sides of the reference path. By calculating the dot product of the welding point and the normal vector, it can be determined on which side of the reference path the welding point is, or the concept of curve tangent can be used to determine the relative position relationship between the welding path and the reference path.

[0149] Of course, there is no restriction on the positional relationship between the welding point and the reference path.

[0150] Further, if each welding point, and its corresponding first welding point and second welding point are all located on the same side of the reference path;

[0151] The shortest straight-line distance from each welding point to the reference path is calculated as the first distance, and the first distance trend from the first welding point to the welding point and the second distance trend from the welding point to the second welding point are compared. The first distance trend is the change trend of the first distance from the first welding point to the welding point, which may be, for example, an increase or a decrease; the second distance trend is the change trend of the first distance from the welding point to the second welding point, which may be, for example, an increase or a decrease;

[0152] If the first distance trend and the second distance trend change, for example, from an increasing trend to a decreasing trend, or the rate increases or decreases, the welding path between the first welding point and the second welding point is used as a turning section.

[0153] Specifically, in some embodiments of the present application, a turning threshold is preset, and the turning threshold can be determined based on experience or through data analysis. If the distance trend change between the welding point and the corresponding first welding point and the welding path between the second welding point is greater than the set threshold, and the change conforms to the geometric characteristics of the path bending or turning, the welding path between the first welding point and the second welding point is used as a turning section.

[0154] Of course, the method and criterion for determining the change between the first distance trend and the second distance trend are not limited here.

[0155] Furthermore, the difficulty analysis module 3 is used to classify the steering control difficulty of each turning section, specifically including:

[0156] Obtaining the steering control difficulty influencing factors of each turning section, and inputting the steering control difficulty influencing factors into the difficulty assessment model;

[0157] The difficulty assessment model obtains the weight values ​​of the preset steering control difficulty influencing factors;

[0158] Specifically, in some embodiments of the present application, the weight value may be set based on expert experience, relying on the knowledge and experience of experts in the field, and setting the weight of each factor through subjective judgment; the weight value may also be set based on data-driven weight learning, automatically learning the weight of each factor by analyzing historical data; it may also be based on adaptive weight setting of an optimization algorithm, automatically adjusting the weight value of each factor through an optimization algorithm, specifically, some optimization algorithms (such as genetic algorithms, particle swarm optimization, gradient descent, etc.) may be used to find the optimal weight combination in the model;

[0159] Of course, there is no limitation on the method of setting the weight value.

[0160] Factors affecting steering control difficulty include one or more of steering angle, smoothness, and curvature change;

[0161] The difficulty assessment model calculates and outputs the steering control difficulty score of each turning section based on the weight value and the steering control difficulty influencing factors, and combines the interaction between the steering control difficulty influencing factors;

[0162] Specifically, in some embodiments of the present application, the interaction between the factors affecting the difficulty of steering control can be realized by using a multivariate regression model, a machine learning method (such as a decision tree, a neural network, etc.), or an interaction term, etc., which helps the difficulty assessment model capture the special effects of certain combinations of factors on the difficulty of steering control;

[0163] Of course, the specific implementation method of the interaction between the factors affecting the steering control difficulty is not limited here.

[0164] The difficulty assessment model further classifies each turning section into a first difficulty and a second difficulty according to the steering control difficulty score.

[0165] Specifically, a control difficulty threshold may be set, and turning sections with a steering control difficulty score less than the control difficulty threshold are classified as first difficulty, and turning sections with a steering control difficulty score equal to or greater than the control difficulty threshold are classified as second difficulty.

[0166] Furthermore, if Figure 2 As shown, the computing system further includes: a path determination module 7;

[0167] The path judgment module 7 is used to judge whether the welding path is new; if the welding path is new, after the welding control module 5 completes the control of the ultrasonic welding equipment to perform welding operations on the material, the welding path and the welding control method corresponding to the welding path are stored.

[0168] It is understandable that if the welding path already exists and has been recorded, the computing system can skip the control setting of the welding path, avoiding repeated design processes, thereby saving time.

[0169] Specifically, the path judgment module 7 can query the welding paths stored in the database, and judge whether the newly obtained welding path is new by comparing the welding paths stored in the database with the newly obtained welding path.

[0170] Furthermore, if Figure 2 As shown, the computing system further includes: a control and adjustment module 8;

[0171] A control and adjustment module 8 is used to sort all the turning sections according to the welding sequence on the welding path and store them in the form of a queue;

[0172] The data corresponding to the first control mode is the first data, and the data corresponding to the second control mode is the second data;

[0173] Traverse all the data in the queue, filter out all the first data, and determine the position of the first data. If the first data is located at the first and / or last one in the queue, keep the first data unchanged.

[0174] If the first data is in the queue, and a preset number of data on both sides of the first data are second data, the turning section corresponding to the first data is adjusted from the first control mode to the second control mode, and the corresponding control parameters are adjusted accordingly.

[0175] It can be understood that adjusting the control mode of the turning section corresponding to the first data that meets the conditions, on the one hand, ensures the quality of ultrasonic welding, and on the other hand, helps to avoid frequent switching between control modes. For example, if the second control mode is mainly used for a period of time, and the first control mode only exists once or twice in the middle, the first control mode can be adjusted to the second control mode to maintain the stability of the control mode and avoid frequent switching of the control mode.

[0176] Specifically, in some embodiments of the present application, the preset number can be made according to the actual data length of the queue. The longer the queue is, the greater the preset number can be;

[0177] Exemplarily, the preset number can be 2, namely, two data on the left side and two data on the right side of the first data. If the two data on the left side and the two data on the right side are both second data, the turning section corresponding to the first data is adjusted from the first control mode to the second control mode, and the corresponding control parameters are adjusted accordingly.

[0178] Furthermore, in some embodiments of the application itself, after screening out the first data that meets the conditions, the difference between the time for ultrasonic welding using the second control mode and the time for ultrasonic welding using the first control mode for the turning section corresponding to the first data can also be predicted and compared with twice the time for switching the control mode. If twice the time for switching the control mode is longer, the first control mode of the turning section can be adjusted to the second control mode.

[0179] Of course, there is no limit to the number of presets that can be set.

[0180] The embodiments of the present application have at least the following beneficial effects:

[0181] The embodiment of the present application provides a computing system of an ultrasonic welding control model, which has a good ultrasonic welding control effect, improves the ultrasonic welding accuracy, thereby optimizing the welding quality of the ultrasonic equipment, and takes into account the ultrasonic welding efficiency;

[0182] Specifically, the shape of the ultrasonic horn 1a includes a disc shape, and the ultrasonic horn 1a and the pressing wheel 21a are arranged opposite to each other to press the template 6a and the material, thereby changing the contact position between the ultrasonic horn 1a and the template 6a, and also changing the abutment position between the ultrasonic horn 1a and the pressing wheel 21a, thereby optimizing the welding accuracy and flexibility of ultrasonic welding, and helping to improve the welding quality;

[0183] Based on the structural characteristics of the improved ultrasonic welding head 1a and the pressing wheel 21a, the welding flexibility is improved, the ultrasonic welding control is facilitated, and thus it helps to strengthen the control of the welding of the ultrasonic welding head 1a. The control difficulty of the turning sections in the welding path is classified through a preset difficulty assessment model, and the control mode is selected for the classified turning sections through a preset mode control model. When the first control mode is selected, the welding efficiency can be effectively improved. When the second control mode is selected, the welding quality of the turning sections with high complexity can be effectively reduced, and the wrinkles generated by the material during the welding process can be reduced. By switching and selecting the first control mode and the second control mode, the problems of production quality and production efficiency can be effectively balanced.

[0184] Example 2

[0185] The present application embodiment provides a method for calculating an ultrasonic welding control model, which is applied to a calculation system of an ultrasonic welding control model in embodiment 1, such as Figure 3 As shown, the calculation method includes:

[0186] S100: obtaining the to-be-welded portion of the material on the template, and generating a welding path according to the shape of the to-be-welded portion;

[0187] S200: Divide the welding path to obtain a number of turning sections;

[0188] S300: Classifying the steering control difficulty of each turning section by using a preset difficulty evaluation model to obtain a turning section including a first difficulty and a second difficulty;

[0189] S400: Based on the steering control difficulties of different turning sections, different control modes are selected through a preset mode control model;

[0190] S500: Based on the control mode selection of each turning section, control the ultrasonic welding equipment to perform welding operations on the material.

[0191] Since the technical problem to be solved by this embodiment, the technical solution used to solve the technical problem, and the technical effect achieved are the same as those of the above-mentioned computing system, the technical details of the calculation method in this embodiment can be found in the above-mentioned computing system embodiment 1, and will not be repeated here.

[0192] Those skilled in the art will appreciate that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more devices different from the implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0193] The above serial numbers of the present invention are only for description and do not represent the advantages or disadvantages of the implementation scenarios.

[0194] The above disclosure is only a few specific implementation scenarios of the present invention, but the present invention is not limited thereto, and any changes that can be conceived by those skilled in the art should fall within the protection scope of the present invention.

Claims

1. A computing system for an ultrasonic welding control model, characterized in that: Applicable to ultrasonic welding equipment, the ultrasonic welding equipment includes an ultrasonic welding head, a pressing device and a template control device; the shape of the ultrasonic welding head includes a disc shape, the pressing device is provided with a pressing wheel, the ultrasonic welding head and the pressing wheel are arranged opposite to each other, the template is located between the ultrasonic welding head and the pressing wheel, and the template control device is used to fix the template or drive the template to rotate; The computing system includes: A path generation module is used to obtain the to-be-welded portion of the material on the template and generate a welding path according to the shape of the to-be-welded portion; A path division module, used for dividing the welding path to obtain a plurality of turning sections; A difficulty analysis module, used to classify the steering control difficulty of each turning section through a preset difficulty evaluation model to obtain a turning section including a first difficulty and a second difficulty; A mode selection module, for selecting different control modes through a preset mode control model based on the steering control difficulty of different turning sections; A welding control module, for controlling the ultrasonic welding equipment to perform welding operations on the material based on the control mode selection of each turning section; The mode control model is used to select a first control mode when the steering control difficulty of the turning section is the first difficulty, so that the welding control module controls the ultrasonic welding head and the pressing wheel to move synchronously at a first speed along a first direction or controls the template to move at a first speed along a first direction, and feeds back the synchronous movement state of the ultrasonic welding head and the pressing wheel or the movement state of the template at a first feedback frequency; When the steering control difficulty of the turning section is the second difficulty, the second control mode is selected, so that the welding control module mainly controls the ultrasonic welding head and the pressing wheel to rotate synchronously at the second speed along the first direction, and simultaneously controls the template to rotate along the first direction in coordination with the ultrasonic welding head as an auxiliary, and feeds back the relative motion state of the ultrasonic welding head, the pressing wheel and the template at the second feedback frequency, so as to realize the welding of the turning section; Wherein, the first speed is not less than the second speed, and the first feedback frequency is not greater than the second feedback frequency; The establishment of the mode control model includes: obtaining a sample set, the sample set includes a plurality of training samples, and the training samples include input data and output data; The input data includes one or any multiple of steering control difficulty, preset quality requirements, production efficiency requirements, material characteristics and production costs; The output data includes selecting the first control mode or the second control mode and the control parameters corresponding to each control mode, wherein the control parameters include: one or any multiple of feedback frequency, movement speed, pressing force and ultrasonic transducer amplitude; The input data and the output data are used to perform deep learning model training. If the control mode output by the deep learning model and the control parameters corresponding to the control mode meet the preset targets, the training is terminated to obtain the mode control model.

2. The computing system of the ultrasonic welding control model according to claim 1, characterized in that: The computing system also includes: a visual detection module; The visual inspection module is used to perform effect inspection on the welding path after welding to obtain the path inspection result; And according to the path detection result, the control parameters output in the mode control model are adjusted.

3. The computing system of the ultrasonic welding control model according to claim 1, characterized in that: The ultrasonic welding equipment is also provided with an ultrasonic transducer, and the ultrasonic welding head and the pressing wheel are both connected with a first rotating device and a second rotating device; The ultrasonic transducer is coaxially arranged with the center of the ultrasonic horn so that the vibration energy converted by the ultrasonic transducer is transmitted along the radial direction of the ultrasonic horn, the ultrasonic horn has a welding portion, the pressing wheel has a pressing portion, and the shape of the welding portion and / or the pressing portion includes an arc; The welding control module is also used to control the first rotating device to drive the ultrasonic welding head and / or the pressing wheel to rotate along a first direction, so as to switch the welding part and / or the pressing part to different positions of the template; The welding control module is used to control the second rotating device to drive the ultrasonic welding head and / or the pressing wheel to rotate along the second direction to switch the contact between the welding part and / or different parts on the pressing part and the template; Among them, the first direction uses the first rotation axis as the rotation axis, and the first rotation axis is perpendicular or approximately perpendicular to the plane where the template is located; the second direction uses the second rotation axis as the rotation axis, and the second rotation axis is parallel or approximately parallel to the plane where the template is located.

4. The computing system of the ultrasonic welding control model according to claim 1, characterized in that: The path division module is used to divide the welding path to obtain a number of turning sections, specifically including: generating a reference path based on the welding path; Acquire a plurality of welding points on the welding path at preset intervals; Taking any welding point as the target, the two welding points adjacent to it are the first welding point and the second welding point respectively; If any two of the welding points and the corresponding first welding point and second welding point are located at different sides of the reference path, the welding path between the first welding point and the second welding point is used as a turning section.

5. The computing system of the ultrasonic welding control model according to claim 4, characterized in that: If each of the welding points, and the corresponding first welding point and second welding point are all located on the same side of the reference path; then calculating the shortest straight-line distance from each welding point to the reference path as a first distance, and comparing a first distance trend from a first welding point to the welding point with a second distance trend from the welding point to the second welding point; If the first distance trend and the second distance trend change, the welding path between the first welding point and the second welding point is used as a turning section.

6. The computing system of the ultrasonic welding control model according to claim 1, characterized in that: The difficulty analysis module is used to classify the steering control difficulty of each turning section and specifically includes: Obtaining the steering control difficulty influencing factors of each turning section, and inputting the steering control difficulty influencing factors into the difficulty assessment model; The difficulty assessment model obtains the weight values ​​of the preset steering control difficulty influencing factors; The factors affecting the difficulty of steering control include one or more of steering angle, smoothness, and curvature change; The difficulty assessment model calculates and outputs a steering control difficulty score for each of the turning sections based on the weight values ​​and the steering control difficulty influencing factors and in combination with the interactions between the steering control difficulty influencing factors; Furthermore, the difficulty assessment model further classifies each of the turning sections into a first difficulty and a second difficulty according to the steering control difficulty score.

7. The computing system of the ultrasonic welding control model according to claim 1, characterized in that: The computing system also includes: a path determination module; The path judgment module is used to judge whether the welding path is new; if the welding path is new, after the welding control module completes controlling the ultrasonic welding equipment to perform welding operations on the material, the welding path and the welding control method corresponding to the welding path are stored.

8. The computing system of the ultrasonic welding control model according to claim 1, characterized in that: The computing system also includes: a control and regulation module; The control and adjustment module is used to sort all the turning sections according to the welding sequence on the welding path and store them in the form of a queue; The data corresponding to the first control mode is the first data, and the data corresponding to the second control mode is the second data; Traversing all the data in the queue, filtering out all the first data, and determining the position of the first data; if the first data is located at the first and / or the last of the queue, keeping the first data unchanged; If the first data is in the queue, and a preset number of data on both sides of the first data are second data, the turning section corresponding to the first data is adjusted from the first control mode to the second control mode, and the corresponding control parameters are adjusted accordingly.

9. A calculation method for an ultrasonic welding control model, characterized in that: A computing system for an ultrasonic welding control model according to any one of claims 1 to 8, wherein the computing method comprises: Obtaining the to-be-welded portion of the material on the template, and generating a welding path according to the shape of the to-be-welded portion; Dividing the welding path to obtain a plurality of turning sections; Classifying the steering control difficulty of each turning section by a preset difficulty assessment model to obtain a turning section including a first difficulty and a second difficulty; Based on the steering control difficulty of different turning sections, different control modes are selected through a preset mode control model; Based on the selection of different control modes, the ultrasonic welding equipment is controlled to perform welding operations on the material; The mode control model is used to select a first control mode when the steering control difficulty of the turning section is the first difficulty, so that the welding control module controls the ultrasonic welding head and the pressing wheel to move synchronously at a first speed along a first direction or controls the template to move at a first speed along a first direction, and feeds back the synchronous movement state of the ultrasonic welding head and the pressing wheel or the movement state of the template at a first feedback frequency; When the steering control difficulty of the turning section is the second difficulty, the second control mode is selected, so that the welding control module mainly controls the ultrasonic welding head and the pressing wheel to rotate synchronously at the second speed along the first direction, and simultaneously controls the template to rotate along the first direction in coordination with the ultrasonic welding head as an auxiliary, and feeds back the relative motion state of the ultrasonic welding head, the pressing wheel and the template at the second feedback frequency, so as to realize the welding of the turning section; Wherein, the first speed is not less than the second speed, and the first feedback frequency is not greater than the second feedback frequency; The establishment of the mode control model includes: obtaining a sample set, the sample set includes a plurality of training samples, and the training samples include input data and output data; The input data includes one or any multiple of steering control difficulty, preset quality requirements, production efficiency requirements, material characteristics and production costs; The output data includes selecting the first control mode or the second control mode and the control parameters corresponding to each control mode, wherein the control parameters include: one or any multiple of feedback frequency, movement speed, pressing force and ultrasonic transducer amplitude; The input data and the output data are used to perform deep learning model training. If the control mode output by the deep learning model and the control parameters corresponding to the control mode meet the preset targets, the training is terminated to obtain the mode control model.

Images