Method for evaluating a soldering process in a soldering unit for liquid solder by means of a monitoring device, computer program product, computer-readable memory device and monitoring device
Patent Information
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- SIEMENS AG
- Filing Date
- 2024-07-31
- Publication Date
- 2026-05-27
Smart Images
Figure EP2024071660_06032025_PF_FP_ABST
Abstract
Description
[0001] 202309527 Foreign Version 1 Description Method for evaluating a soldering process in a soldering system for liquid solder using a monitoring device, computer program product, computer-readable storage medium, and monitoring device. The invention relates to a method for evaluating a soldering process in a soldering system for liquid solder using a monitoring device according to the applicable patent claim 1. Furthermore, the invention relates to a computer program product, a computer-readable storage medium, and a monitoring device. In so-called selective soldering processes, wetting solder nozzles are often used, which are subject to high wear. This limits the wettability of the solder nozzle surface, and results in areas not wetted by the solder circulating around the solder nozzle. This leads to an uneven solder wave geometry and thus to unstable processes and reduced product quality during the selective soldering process. CurrentThere is no automated evaluation to determine unwetted solder nozzle surface areas. Only sporadic visual observation takes place, usually using a process camera and monitor display, with a subjective assessment of whether or not a reaction to changes is necessary. For a high-quality soldering process, a reproducible, even solder flow over the wetted solder nozzle surface is essential. Automated monitoring of solder nozzle wetting during production is currently not possible, so fluctuations in the wetting of the solder nozzles lead to soldering problems, such as solder penetration, solder bridges, or unsoldered areas. Due to wear and contamination, wave soldering systems with a wide solder wave often have problems achieving a uniform wave formation across the entire wave width of the liquid solder, which is used to create the solder connection between the component leads and the circuit board.An automated inspection of the solder wave characteristics during production is currently only possible to a limited extent for individual contact or temperature measuring points, so that fluctuations in the solder wave characteristics can lead to soldering problems. Dip soldering systems with multiple soldering chimneys of different geometries often have problems achieving a uniform solder filling in the chimneys for all individual solder chimneys over the entire product surface to be soldered due to wear and contamination. An automated inspection of the solder filling characteristics of the individual chimneys during production is currently only possible to a limited extent using individual contact or temperature measuring points, so that fluctuations can lead to soldering problems. Non-wetting solder nozzles can also exhibit fluctuations in the solder wave characteristics due to wear, damage, or contamination. These are difficult toand can thus also lead to soldering problems. WO 2019208039 and WO 2022039193 describe soldering systems that assess the quality of solder joints on printed circuit boards using a thermal imaging camera. However, defects in solder joints are only detected when they have already occurred. The object of the present invention is to create a method, a computer program product, a computer-readable storage medium, and a monitoring device by means of which a soldering process can be reliably monitored and evaluated, and soldering defects can be better avoided before the soldering process compared to the prior art. This object is achieved by a method, a computer program product, a computer-readable storage medium, and a monitoring device according to the independent patent claims. Advantageous embodiments are specified in the subclaims. 202309527 Foreign version 3 One aspect of the invention relates toA method for evaluating a soldering process in a liquid solder soldering system using a monitoring device. A reference solder pattern is provided for the soldering system using an electronic computing device of the monitoring device. A current solder pattern of the soldering system is captured using a thermal imaging camera of the monitoring device. The current solder pattern is compared with the reference solder pattern using the electronic computing device, and the soldering process is evaluated based on the comparison using the electronic computing device. Thus, the soldering process can be reliably monitored and evaluated based on a thermal image. The monitoring of the solder pattern can also be performed in real time; defects are not only detected in components that have already been soldered, but can be identified before the actual soldering process of a component based on irregularities in the solder pattern on the solder nozzle.The defect detection can not only be observed manually, for example, by a worker on a monitor on the soldering system, but can also be carried out by the control system (computer) by comparing it with the reference solder pattern. With automated detection of a defect in the solder pattern, a corrective action (such as replacing the solder nozzle) can be initiated before the soldering process. The term "real time" means that certain results (such as indicating the need to initiate the corrective action) can be reliably achieved within a predetermined period of time. A solder pattern is understood to be a characteristic flow structure of the liquid solder that continuously emerges from a solder nozzle. In this case, there can also be a plurality of solder nozzles along a line, from each of which liquid solder emerges, forming a solder wave.A soldering nozzle is an outlet device that generates either a point-like solder discharge or a linear solder discharge (solder wave) through several point-like or elongated outlet slots. In particular, the invention utilizes the underlying principle that differences in the surface due to temperature, an emission coefficient in thermal image analysis, or a gray or color value analysis in visual image analysis between exposed, in particular non-wetted, soldering nozzle areas and areas that are surrounded (wetted) with liquid solder are determined using a thermal imaging camera or visual camera and corresponding measured value or image evaluations. A flexibly configurable evaluation range for a nozzle geometry-specific evaluation can be realized. By setting the maximum permissible temperature or color toneor grayscale difference for the defined evaluation range, if these values are exceeded, corresponding predefined actions can also be initiated as close-loop scenarios. Compared to previous solutions, the implementation of this principle enables quality control and regulation for wetting solder nozzles as well as for the shape and characteristics of solder waves and areas filled with liquid solder. This can be done immediately before soldering products or during the selective, wave, or dip soldering of assemblies. This enables the reduction of rework and waste costs and also the use of short control loops to automatically initiate appropriate actions such as automatic nozzle cleaning, the request for a nozzle change, or similar, based on objective criteria. Compared to previous sporadic subjective evaluations, this represents a significant improvement.represents a significant advantage. Continuous monitoring of solder nozzle wetting, in particular, also allows for the detection of changes such as batch fluctuations, different uses of the solder nozzles, and the like. This allows for the setting of a quality filter for subsequent products and, if necessary, for flexible switching to other solder nozzles or, with appropriate system capabilities, for an automatic solder nozzle change to be initiated. According to an advantageous embodiment, a solder nozzle of the soldering system is monitored. In particular, in a soldering system with one solder nozzle, the solder nozzle can be monitored accordingly, and the functionality of the solder nozzle can be evaluated. It is also advantageous if the solder nozzle is provided as a wetting solder nozzle. The wetting solder nozzle can thus be monitored accordingly, making the soldering system with wetting solder nozzles more reliable.can be operated. A further advantageous embodiment provides for the soldering system to be provided as a wave soldering system. With the thermal imaging camera or visual image recording, specific local detection is possible with respect to the area to be evaluated. This allows for targeted, specific quality control to be carried out during the process, and deviations can be assigned to specific products, as well as actions initiated, for example, automatic nozzle cleaning or a request to change the nozzle. This method is suitable for predictive maintenance and complements regular inspections of the system and nozzle service life. It has also proven advantageous to specify a reference thermal image as the reference solder pattern, and to compare the reference thermal image with a current thermal image. For example, corresponding temperatures or color codes can be used for this purpose.be used to perform a comparison. This makes it easy to perform a corresponding comparison. It is also advantageous if a warning message is issued if the current solder pattern deviates from the reference solder pattern. For example, an operator of the soldering system can be warned accordingly if corresponding deviations occur. It is also advantageous if the monitoring and evaluation are carried out continuously during operation of the soldering system. This way, for example, appropriate monitoring can be carried out both when the soldering system is initiated and during operation, and thus continuously during operation. This way, monitoring can also be carried out during operation, whereby the soldering system can be permanently monitored and evaluated accordingly. It is also advantageous if, depending on the evaluationAutomated cleaning of the soldering system is initiated. For example, the soldering system's cleaning devices can be operated accordingly to initiate appropriate cleaning of the soldering system. This ensures a reliable soldering process. It is also advantageous if, depending on the evaluation, an automated change of a soldering nozzle is initiated. If, for example, a soldering nozzle is defective and therefore no longer adequately supports the soldering process, an automatic change of the soldering nozzle can be initiated. Alternatively, a soldering nozzle change can also be suggested to a soldering system operator. It has also proven advantageous if, depending on the evaluation, a stop to the operation of the soldering system is initiated. If, for example, a corresponding soldering nozzle is defective, the operation of the soldering system can be stopped so that no defective products are produced.It has also proven advantageous if the assessment is carried out depending on an expected area for liquid solder on the soldering system and an actual area with liquid solder. For example, corresponding areas where solder must be provided for a correct product can be monitored accordingly. If no solder is detected in this area, a faulty process can be determined. Furthermore, in areas where no solder is expected but solder is detected, a corresponding assessment can be carried out to determine that a faulty soldering process is being carried out. A further advantageous embodiment provides for a horizontal recording and / or a vertical recording of the soldering system. For example, the soldering system can have two differently arranged thermal imaging cameras for this purpose, one for a horizontalMonitoring both for vertical monitoring. Thus, the soldering process can be monitored accordingly from different directions, whereby improved monitoring of the soldering process can be realized. The presented method is, in particular, a computer-implemented method. Therefore, a further aspect of the invention relates to a computer program product with program code means which, when the program code means are processed by the electronic computing device, cause an electronic computing device to carry out a method according to the preceding aspect. A further aspect of the invention therefore also relates to a computer-readable storage medium with at least the computer program product. Furthermore, the invention also relates to a monitoring device for evaluating a soldering process in a soldering system for liquid solder, with at least one electronic computing device and a thermal imaging camera, whereinthe monitoring device is designed to carry out a method according to the preceding aspect. In particular, the method is carried out by means of the monitoring device. 202309527 Foreign version 8 Furthermore, the invention also relates to a soldering system with a monitoring device according to the preceding aspect. Advantageous embodiments of the method are to be regarded as advantageous embodiments of the computer program product, the computer-readable storage medium, the monitoring device and the soldering system. The monitoring device and the soldering system have material features for this purpose in order to be able to carry out corresponding method steps. In the context of the present disclosure, an object recognition algorithm, in particular for detecting / detecting the liquid solder, can be understood as a computer algorithm that is capable of detecting one or more objects within a providedInput data set, for example, input image, to identify and localize, for example, by defining corresponding bounding boxes or regions of interest (ROI) and, in particular, by assigning a corresponding object class to each of the bounding boxes, wherein the object classes can be selected from a predefined set of object classes. The assignment of an object class to a bounding box can be understood as providing a corresponding confidence value or probability that the object identified within the bounding box belongs to the corresponding object class. For example, for a given bounding box, the algorithm can provide such a confidence value or probability for each of the object classes. The assignment of the object class can, for example, involve selecting or providing the object class with the highest confidence value.or the greatest probability. Alternatively, the algorithm can also simply specify the bounding boxes without assigning a corresponding object class. Algorithms for automatic visual perception, which can also be referred to as computer vision algorithms, machine vision algorithms, or machine vision algorithms, can be regarded as computer algorithms for automatically performing a visual perception task. A visual perception task, also referred to as a computer vision task, can be understood, for example, as a task for extracting visual information from image data. In particular, the visual perception task can, in principle, in some cases be performed by a human who is able to visually perceive an image corresponding to the image data. In the present context, however, visual perception tasks are alsocarried out automatically, without the need for human assistance. A computer vision algorithm can, for example, contain an image processing algorithm or an image analysis algorithm that is or was trained by machine learning and can, for example, be based on an artificial neural network, in particular a convolutional neural network. The computer vision algorithm can, for example, comprise an object recognition algorithm, an obstacle detection algorithm, an object tracking algorithm, a classification algorithm, a semantic segmentation algorithm, and / or a depth estimation algorithm. Corresponding algorithms can also be carried out analogously based on input data other than images visually perceivable by a human. For example, point clouds or images from infrared cameras, lidar systems, etc. can also be processed using appropriately adaptedComputer algorithms are evaluated. Strictly speaking, the corresponding algorithms are not algorithms for visual perception, since the corresponding sensors can operate in ranges that are not visually perceptible, i.e., not perceptible to the human eye, for example, in the infrared range. Therefore, such algorithms are referred to as algorithms for automatic perception within the scope of the present invention. Algorithms for automatic perception therefore include algorithms for automatic visual perception, but are not limited to this with regard to human perception. Consequently, an algorithm for automatic perception according to this understanding can contain a computer algorithm for automatically performing a perception task, which is or was trained, for example, by machine learning and is based in particular on an artificial neural network.Such generalized automatic perception algorithms can also include object detection algorithms, object tracking algorithms, classification algorithms, and / or segmentation algorithms, for example, semantic segmentation algorithms. If an artificial neural network is used to implement an automatic visual perception algorithm, a frequently used architecture is that of a convolutional neural network (CNN). In particular, a 2D CNN can be applied to corresponding 2D camera images. CNNs can also be used for other automatic perception algorithms. For example, 3D CNNs, 2D CNNs, or 1D CNNs can be applied to point clouds, depending on the spatial dimensions of the point cloud and the details of the processing. The result or output of an automatic perception algorithm depends on the specific underlyingPerception task. For example, the output of an object recognition algorithm may contain one or more bounding boxes that define a spatial position and optionally an orientation of one or more corresponding objects in the environment and / or corresponding object classes for the one or more objects. An output of a semantic segmentation algorithm applied to a camera image may contain a pixel-level class for each pixel of the camera image. Analogously, an output of a semantic segmentation algorithm applied to a point cloud may contain a corresponding point-level class for each of the points. The pixel-level or point-level classes may, for example, define an object type to which the respective pixel or point belongs. A computing unit / electronic computing device may, in particular, be a data processing devicebe understood as containing a processing circuit. The computing unit can therefore, in particular, process data to perform computing operations. This may also include operations to perform indexed accesses to a data structure, for example a look-up table (LUT). The computing unit can, in particular, contain one or more computers, one or more microcontrollers, and / or one or more integrated circuits, for example one or more application-specific integrated circuits (ASICs), one or more field-programmable gate arrays (FPGAs), and / or one or more single-chip systems (SoCs). The computing unit can also contain one or more processors, for example one or more microprocessors, one or more central processing units (CPUs).one or more graphics processing units, GPU (English: "graphics processing unit") and / or one or more signal processors, in particular one or more digital signal processors, DSP. The computing unit can also contain a physical or virtual network of computers or other of the mentioned units. In various embodiments, the computing unit contains one or more hardware and / or software interfaces and / or one or more memory units. A memory unit can be a volatile data memory, for example a dynamic random access memory, DRAM (English: "dynamic random access memory") or a static random access memory, SRAM (English: "static random access memory"), or a non-volatile data memory, for example a read-only memory, ROM (English: "read-only memory"), a programmable read-only memory, PROM (English:The memory can be configured as an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a flash memory or flash EEPROM, a ferroelectric random access memory (FRAM), a magnetoresistive random access memory (MRAM), or a phase-change random access memory (PCRAM). For applications or application situations that may arise during the method and are not explicitly described here, it can be provided that, in accordance with the method, an error message and / or a request for user feedback is output and / or a default setting is set.and / or a predetermined initial state is set. Regardless of the grammatical gender of a particular term, persons with male, female or other gender identity are also included. Further features of the invention emerge from the claims, the figures and the description of the figures. The features and combinations of features mentioned above in the description as well as the features and combinations of features mentioned below in the description of the figures and / or shown in the figures can be encompassed by the invention not only in the respective combination specified, but also in other combinations. In particular, embodiments and combinations of features can also be encompassed by the invention which do not have all the features of an originally formulated claim. Furthermore, embodiments and combinations of features can be encompassed by the invention 202309527 Foreign Version 13 which go beyond the features stated in the backreferences of the1 shows a schematic block diagram according to an embodiment of a soldering system with an embodiment of a monitoring device; FIG. 2 shows a schematic side view of an embodiment of a soldering nozzle; FIG. 3 shows a further schematic side view of an embodiment of a soldering nozzle; FIG. 4 shows a schematic side view of a further embodiment of a soldering nozzle; FIG. 5 shows a schematic side view of a wave soldering system; and FIG. 6 shows a schematic flow diagram according to an embodiment of the method. The invention is explained in more detail below with reference to specific embodiments and associated schematic drawings. In the figures, identical or functionally equivalent elements may be provided with the same reference numerals. The description of identical or functionally equivalent elements is not necessarily based onvarious figures. FIG. 1 shows a schematic side view of an embodiment of a soldering system 10 with a monitoring device 12. In the soldering system 10, a product 14 is soldered using a soldering nozzle 16 in the previous embodiments. Liquid solder 18 flows from the soldering nozzle 16 in order to solder the component 14 accordingly. 202309527 Foreign version 14 In the present exemplary embodiment, the monitoring device 12 has, in particular, at least one thermal imaging camera 20 and an electronic computing device 22. The electronic computing device 22 provides, in particular, a reference solder pattern 24. In particular, FIG. 1 shows that a soldering process of the soldering system 10 can be monitored and evaluated accordingly by means of the monitoring device 12. The reference solder pattern 24 for the soldering system 10 is provided by means of the electronic computing device 22. A current solder pattern 26 of the soldering system 10 is provided by means ofthe thermal imaging camera 20. The current solder pattern 26 of the soldering system 10 is compared with the reference solder pattern 24 by means of the electronic computing device 22, and depending on the comparison, an evaluation of the soldering process takes place by means of the electronic computing device 22. As already described, the solder pattern is understood to be the structure of the liquid solder as it leaves the soldering nozzle 16 and flows over it. If, for example, the solder pattern is uneven and not all areas around the nozzle are evenly or even not evenly thickly flowed around by the solder 18, this becomes visible in the form of temperature anomalies in a thermal image taken by the thermal imaging camera. This means that the solder pattern captured by the thermal imaging camera differs from the reference solder pattern 24. FIG. 2 shows a schematic sectional view on the left and a schematicSide view of a soldering nozzle 16. In particular, it shows how the liquid solder 18 is pumped out of the soldering nozzle 16. A corresponding image taken by the thermal imaging camera 20 during a correct soldering process is again shown on the right-hand side of FIG. 2. FIG. 3 shows a further embodiment of a soldering nozzle 16. On the left, a sectional view of the soldering nozzle 16 202309527 foreign version 15 is shown, and on the right-hand side, a corresponding actually recorded image, as would be recorded during a correct soldering process. FIG. 4 again shows the soldering nozzle 16 from FIG. 3. On the left, a sectional view is shown of how a correct soldering process would take place. On the right-hand side, an incorrect solder flow is shown, for example because the soldering nozzle 16 is clogged. In particular, FIGS. 2 to 4 therefore show that a soldering nozzle 16 of the soldering system 10 is being monitored. The soldering nozzle 16 is particularly designed as a wettingSoldering nozzle 16 is provided. FIG. 5 shows a schematic side view of a soldering system 10 designed as a wave soldering system 28. Here, a soldering wave 16 with liquid solder 18 is generated, wherein the component 14 is then guided, for example, over this soldering wave 16. In particular, FIGS. 1 to 5 show that, for example, a reference thermal image is specified as the reference solder pattern 24 and the reference thermal image is compared with the current thermal image. If the current solder pattern 26 deviates from the reference solder pattern 24, a warning message can be issued, in particular. Furthermore, it can be provided that the monitoring and evaluation are carried out continuously during operation of the soldering system 10. Furthermore, it can be provided that, depending on the evaluation, an automated cleaning of the soldering system 10 is initiated. Furthermore, an automated change of a soldering nozzle 16 can be initiated depending on the evaluation.Furthermore, it can be provided that a stop of the operation of the soldering system 10 is initiated depending on the evaluation. It can also be provided that the evaluation is carried out depending on an expected area for liquid solder 18 on the soldering system 10 and an actual area with liquid solder 18. 202309527 Foreign version 16 FIG. 5 shows in particular that both a horizontal image and / or a vertical image of the soldering system 10 is carried out. FIG. 6 shows a schematic flow diagram according to an embodiment of the method. The method begins in a first step S1. In a second step S2, a thermal image is taken before production. In a third step S3, this thermal image is evaluated accordingly. In a fourth step S4, it is checked whether the result of the evaluation is OK. If, for example, the result is not OK, an automaticA nozzle change may be suggested in a fifth step S5. Furthermore, a nozzle cleaning may also be suggested in a sixth step S6. Furthermore, an error message and a stop may also be initiated in a seventh step S7. If the evaluation in an eighth step S8 is deemed OK, a continuous thermal image recording during product soldering can be performed in a ninth step S9. A continuous evaluation can then be performed accordingly in a tenth step S10. If the result is OK, the soldering process continues in an eleventh step S11. However, if the result is deemed not OK during operation, which is represented here in the twelfth step S12, an automatic nozzle cleaning may be generated in a thirteenth step S13 and / or an error message and a stop may be generated in a fourteenth step S14. Furthermore,A so-called close-loop action should be performed in a fifteenth step S15, for example, if automatic nozzle cleaning is to be performed. Starting from the tenth step S10 and the third step S3, a data analysis can be performed in a sixteenth step S16. This can, for example, enable quality assessment of the soldering nozzle 16 for each product. Furthermore, quality and service life information for the soldering nozzles 16 can also be performed in a seventeenth step S17. den.
[0002] 202309527 Foreign version 18 List of reference symbols 10 Soldering system 12 Monitoring device 14 Component 16 Soldering nozzle 18 Liquid solder 20 Thermal imaging camera 22 Electronic computing device 24 Reference solder sample 26 Current solder sample 28 Wave soldering system S1 to S17 Steps of the method
Claims
202309527 Foreign version 19 patent claims 1. Method for evaluating a soldering process in a soldering system (10) for liquid solder (18) by means of a monitoring device (12), comprising the steps of: - providing a reference solder pattern (24) for the soldering system (10) by means of an electronic computing device (22) of the monitoring device (12); - detecting a current solder pattern (26) of the soldering system (10) by means of a thermal imaging camera (20) of the monitoring device (12); - comparing the current solder pattern (26) with the reference solder pattern (24) by means of the electronic computing device (22); and - evaluating the soldering process as a function of the comparison by means of the electronic computing device (22).
2. Method according to claim 1, characterized in that a solder nozzle (16) of the soldering system (10) is monitored.
3. The method according to claim 2, characterized in that the soldering nozzle (16) is provided as a wetting soldering nozzle (16).Method according to claim 1, characterized in that the soldering system (10) is provided as a wave soldering system (28).
5. Method according to one of the preceding claims, characterized in that a reference thermal image is specified as the reference solder pattern (26), and the reference thermal image is compared with a current thermal image.
6. Method according to one of the preceding claims, characterized in that a warning message is issued if the current solder pattern (26) deviates from the reference solder pattern (24). 202309527 Foreign version 20 7. Method according to one of the preceding claims, characterized in that the monitoring and evaluation are carried out continuously during operation of the soldering system (10).
8. Method according to one of the preceding claims, characterized in that an automated cleaning of the soldering system (10) is initiated depending on the evaluation.
9. Method according to one of the preceding claims, characterized in that an automated change of a soldering nozzle (16) is initiated depending on the evaluation.
10. Method according to one of the preceding claims, characterized in that a stop of operation of the soldering system (10) is initiated depending on the evaluation.Method according to one of the preceding claims, characterized in that the evaluation is carried out as a function of an expected area for liquid solder (18) on the soldering system (10) and an actual area with liquid solder (18).
12. Method according to one of the preceding claims, characterized in that a horizontal recording and / or a vertical recording of the soldering system (10) is carried out.
13. Computer program product with program code means which cause an electronic computing device (22) to carry out a method according to one of claims 1 to 12 when the program code means are processed by the electronic computing device (22).
14. Computer-readable storage medium with at least one computer program product according to claim 13.
15. Monitoring device (12) for evaluating a soldering process in a soldering system for liquid solder (18), with at least one. 202309527 Foreign version 21 electronic computing device (22) and a thermal imaging camera (20), wherein the monitoring device (12) is designed to carry out a method according to one of claims 1 to 12.