Laser welding process early warning method, server and storage medium
Through real-time analysis and dynamic adjustment of welding parameter range, the early warning accuracy problem caused by dynamic changes in welding parameters in the laser welding process is solved, and more efficient early warning and higher quality products are achieved.
Patent Information
- Application Number
- CN202411979124.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-30
- Publication Date
- 2025-06-03
AI Technical Summary
In the laser welding process, due to the dynamic changes in welding parameters, it is difficult for the existing technology to accurately predict and respond to process deviations, resulting in the monitoring system being unable to effectively warn.
By analyzing the values of welding parameters in real time and dynamically adjusting the upper and lower limit thresholds of the parameter range based on historical measured data, the parameter range adapts to the dynamic changes of the welding process, thereby improving the accuracy and reliability of early warning.
It reduces the occurrence of false triggering and missed triggering warnings, improves the accuracy and reliability of warnings, reduces the cost of shutdown caused by false alarms, and improves product quality.
Smart Images
Figure CN120079998A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the technical field of laser welding process control, and particularly to a laser welding process warning method, a server, and a storage medium. Background Art
[0002] In the laser welding process, precise control of welding parameters is crucial for ensuring product quality. However, since the welding process often involves dynamic changes in process requirements and the environment, the monitoring system cannot accurately predict and respond to process deviations. Summary of the Invention
[0003] In view of the above, it is necessary to provide a laser welding process warning method, a server, and a storage medium, which can dynamically adjust the parameter range for monitoring the welding process by analyzing the values of welding parameters in real time during the welding process, so that the parameter range adapts to the dynamic changes of the welding process, and improve the accuracy and reliability of the welding process warning.
[0004] In a first aspect, this application provides a laser welding process warning method, including: obtaining the value of the welding parameter in the laser welding process in real time; determining whether the value of the welding parameter belongs to a preset parameter range, where the preset parameter range includes a first upper limit threshold and a first lower limit threshold; when it is determined that the value of the welding parameter does not belong to the preset parameter range, updating the first upper limit threshold to a second upper limit threshold, and updating the first lower limit threshold to a second lower limit threshold; generating a first data sequence corresponding to the welding parameter based on the value of the welding parameter obtained in real time; and determining whether to trigger an alarm mechanism based on the first data sequence, the second upper limit threshold, and the second lower limit threshold.
[0005] In some embodiments of this application, the updating the first upper limit threshold to a second upper limit threshold and updating the first lower limit threshold to a second lower limit threshold includes: obtaining a preset number of measured data corresponding to the welding parameter; generating multiple sets of analysis samples based on the preset number of measured data according to the acquisition time corresponding to each measured data; and updating the first upper limit threshold to the second upper limit threshold and updating the first lower limit threshold to the second lower limit threshold based on the multiple sets of analysis samples.
[0006] In some embodiments of the present application, the preset parameter range further includes a first mid-threshold value between the first upper threshold value and the first lower threshold value; updating the first upper threshold value to the second upper threshold value and updating the first lower threshold value to the second lower threshold value based on multiple groups of the analysis samples includes: obtaining a plurality of reference average values by respectively calculating the average value of each group of the analysis samples; taking the average value of the plurality of reference average values as a second mid-threshold value between the second upper threshold value and the second lower threshold value; calculating the range corresponding to each group of the analysis samples according to the maximum value and the minimum value in each group of the analysis samples to obtain a plurality of reference ranges; obtaining a reference range average value by calculating the average value of the plurality of reference ranges; and determining the second upper threshold value and the second lower threshold value based on the reference range average value, the second mid-threshold value, and a preset adjustment coefficient.
[0007] In some embodiments of the present application, the adjustment coefficient is determined according to the number of each group of the analysis samples.
[0008] In some embodiments of the present application, determining whether to trigger an alarm mechanism based on the first data sequence, the second upper threshold value, and the second lower threshold value includes: performing smoothing processing on the first data sequence by using a moving average algorithm to obtain a second data sequence including a plurality of average values; determining whether an abnormal condition occurs in the laser welding process based on the plurality of average values and a plurality of data control ranges, wherein each data control range in the plurality of data control ranges is determined based on at least one of the second upper threshold value, the second mid-threshold value, and the second lower threshold value; and if it is determined that an abnormal condition occurs in the laser welding process, giving a warning in a preset manner.
[0009] In some embodiments of the present application, the first data sequence includes a plurality of values of the welding parameters respectively corresponding to a plurality of acquisition times, and each value corresponds to one of the acquisition times; performing smoothing processing on the first data sequence to obtain a second data sequence including a plurality of average values includes: traversing each value in the first data sequence based on a preset sliding window in the order of the acquisition time corresponding to each value to obtain the average value of all the values in the sliding window corresponding to each acquisition time; and generating the second data sequence based on the average value of all the values in the sliding window corresponding to each acquisition time.
[0010] In some embodiments of the present application, the size of the sliding window is represented as N. Traversing each value in the first data sequence based on the preset sliding window in the order of the acquisition time corresponding to each value, and obtaining the average value of all the values in the sliding window corresponding to each acquisition time includes: sliding the sliding window starting from the first value in the first data sequence until all the values in the first data sequence are traversed. Each time the sliding window slides, determine the number of values currently included in the sliding window, denoted as M, and calculate the average value of all the values in the current sliding window. The first value corresponds to the earliest acquisition time. Wherein, calculating the average value of all the values in the current sliding window includes: when M is equal to N, taking the average value of the M values as the average value of all the values in the sliding window; and when M is less than N, generating (N - M) standard values, and taking the (N - M) standard values and the average value of the M values currently included in the sliding window as the average value of all the values in the sliding window.
[0011] In some embodiments of the present application, the method further includes: when it is determined that the value of the welding parameter does not belong to the preset parameter range, in response to the user's input signal, updating the first upper threshold to the second upper threshold, and updating the first lower threshold to the second lower threshold.
[0012] In a second aspect, the present application provides a server, including: a memory storing computer-readable instructions; and a processor executing the computer-readable instructions to implement the laser welding process warning method described above.
[0013] In a third aspect, the present application provides a computer-readable storage medium storing computer-readable instructions; when the computer-readable instructions are processed and executed, the laser welding process warning method described above is implemented.
[0014] Compared with the prior art, the present application dynamically adjusts the upper and lower threshold values of the parameter range by analyzing the values of the welding parameters in the welding process in real time and based on the measured data collected historically, so that the adjusted parameter range adapts to the dynamic changes of the welding process, reduces false alarms and missed alarms, and improves the accuracy and reliability of the warning. While improving production efficiency, it reduces the downtime cost caused by false warnings. In addition, timely response to the warning triggered by the process deviation can reduce the generation of defective products, improve the quality of the product while reducing the need for manual intervention by operators, and reduce errors caused by human factors. Description of the Drawings
[0015] Figure 1 is a flowchart of the laser welding process warning method provided by an embodiment of the present application.
[0016] Figure 2 It is a detailed flowchart of S203 in the laser welding process warning method provided by an embodiment of the present application.
[0017] Figure 3 It is a detailed flowchart of S2033 in the laser welding process warning method provided by an embodiment of the present application.
[0018] Figure 4 It is a detailed flowchart of S205 in the laser welding process warning method provided by an embodiment of the present application.
[0019] Figure 5 It is a functional module diagram of the laser welding process warning device provided by an embodiment of the present application.
[0020] Figure 6 It is a schematic structural diagram of the server provided by an embodiment of the present application. Detailed implementation manners
[0021] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described in detail below with reference to the accompanying drawings and specific embodiments.
[0022] It should be noted that, in the present application, "at least one" means one or more, and "a plurality" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B may be singular or plural. The terms "first", "second", "third", "fourth", etc. (if any) in the specification, claims and drawings of the present application are used to distinguish similar objects, rather than to describe a specific order or sequence.
[0023] In the embodiments of the present application, words such as "exemplary" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary" or "for example" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, using words such as "exemplary" or "for example" is intended to present related concepts in a specific manner. Without conflict, the following embodiments and the features in the embodiments may be combined with each other.
[0024] As Figure 1 shown, it is a flowchart of the laser welding process warning method provided by an embodiment of the present application.
[0025] In an embodiment of the present application, the laser welding process warning method is applied to a server, such as Figure 6In the server 1 shown. According to different requirements, the order of each step in the flowchart can be changed, and some steps can be omitted.
[0026] S201, obtain the values of welding parameters in the laser welding process in real time.
[0027] In some embodiments of the present application, the welding parameters can be the welding speed, solder joint power, solder joint welding radius, camera ring angle, solder joint concentricity, right ring Y-direction deviation, right ring X-direction deviation, solder joint included angle, left ring X-direction deviation, or left ring Y-direction deviation, etc. collected during the welding of the workpiece.
[0028] In some embodiments of the present application, sensors suitable for the laser welding process environment can be pre-installed, including but not limited to, photoelectric sensors, power meters, and vision sensors, etc., for collecting various welding parameters. In addition, the sensors are pre-calibrated precisely to ensure that their measurement range, accuracy, and resolution meet the requirements of process monitoring. Additionally, by configuring appropriate sampling frequencies for the sensors, it is ensured that various welding parameters in the process can be captured.
[0029] S202, determine whether the value of the welding parameter belongs to a preset parameter range, where the preset parameter range includes a first upper threshold and a first lower threshold.
[0030] In some embodiments of the present application, if the value of the welding parameter does not belong to the preset parameter range, the process step then proceeds to S203 at this time. If the value of the welding parameter belongs to the preset parameter range, then continue to determine whether the real-time collected welding parameter belongs to the preset parameter range.
[0031] In some embodiments of the present application, the preset parameter range refers to the numerical range determined by the first upper threshold and the first lower threshold. Each welding parameter has a corresponding preset parameter range. For example, the welding speed has a corresponding preset parameter range, and the welding power has a corresponding preset parameter range. Specifically, when determining whether the value of the welding parameter belongs to the preset parameter range, it is determined by comparing the value of the welding parameter with the corresponding preset parameter range of the welding parameter.
[0032] To clearly illustrate the present invention, the following takes D1max to represent the first upper threshold and D1min to represent the first lower threshold as an example for illustration. Correspondingly, the preset parameter range can be expressed as [D1min, D1max].
[0033] In some embodiments of the present application, the preset parameter range further includes a first middle threshold between the first upper threshold and the first lower threshold. To clearly illustrate the present invention, the following takes D1med to represent the first middle threshold.
[0034] S203, update the first upper threshold to the second upper threshold, and update the first lower threshold to the second lower threshold.
[0035] In some embodiments of the present application, updating the first upper threshold to the second upper threshold and updating the first lower threshold to the second lower threshold is also to update the preset parameter range, so as to obtain the updated parameter range. For the sake of clearly illustrating the present invention, hereinafter, taking D2max to represent the second upper threshold and D2min to represent the second lower threshold as an example, correspondingly, the updated parameter range can be expressed as [D2min, D2max].
[0036] In some embodiments of the present application, the server 1 also updates the first middle threshold to the second middle threshold. Hereinafter, taking D2med to represent the second middle threshold as an example. Regarding how to specifically update the first upper threshold to the second upper threshold, the first middle threshold to the second middle threshold, and the first lower threshold to the second lower threshold, please refer to the following introduction of Figure 2 of.
[0037] In other embodiments of the present application, when it is determined that the value of the welding parameter does not belong to the preset parameter range, the server 1 can also respond to the input signal of the user, update the first upper threshold to the second upper threshold, update the first middle threshold to the second middle threshold, and update the first lower threshold to the second lower threshold.
[0038] S204, generate a first data sequence corresponding to the welding parameter based on the value of the welding parameter obtained in real time.
[0039] In some embodiments of the present application, the first data sequence includes multiple values of the welding parameter corresponding to multiple acquisition times respectively, and each value corresponds to an acquisition time.
[0040] For example, the first data sequence includes the values of the welding parameter (such as welding speed) collected at times t1, t2, t3, t4... tn, which are d1, d2, d3, d4... dn respectively.
[0041] S205, determine whether to trigger the alarm mechanism based on the first data sequence, the second upper threshold, and the second lower threshold.
[0042] In some embodiments of the present application, for determining whether to trigger the alarm mechanism based on the first data sequence, the second upper threshold, and the second lower threshold, please specifically refer to the following introduction of Figure 4 of.
[0043] Such as Figure 2As shown, it is a detailed flowchart of S203 in the laser welding process warning method provided by the embodiments of the present application. According to different requirements, the order of the steps in the detailed flowchart can be changed, and some steps can be omitted.
[0044] S2031, obtain a preset number of measured data corresponding to the welding parameters.
[0045] In some embodiments of the present application, the preset number can be set according to actual needs. For example, it can be set to 1000. The measured data is the value of the welding parameters collected during the welding process.
[0046] In some embodiments of the present application, the preset number of measured data can be the value of the welding parameters collected within a preset time period. For example, it can be the value of the welding parameters within one month before the current time point.
[0047] In some embodiments of the present application, each of the preset number of measured data belongs to a preset parameter range.
[0048] For example, assume that the values of 1000 welding parameters (such as welding speed) collected in the previous month are obtained. It should be noted that each of the 1000 values corresponds to a collection time. That is, the 1000 values correspond to 1000 collection times, and each collection time corresponds to a value. All 1000 values are within the preset parameter range corresponding to the welding parameters (such as welding speed).
[0049] S2032, based on the collection time corresponding to each measured data, generate multiple groups of analysis samples based on the preset number of measured data.
[0050] In some embodiments of the present application, the number of measured data included in each group of the multiple groups of analysis samples is the same. For example, each group includes 10 measured data.
[0051] For example, assume that in S2031, the values of the welding parameters (such as welding speed) collected at times t1, t2, t3, t4... t1000 are d1, d2, d3, d4... d1000 respectively. Then, in the order of the collection time corresponding to each value, every 10 measured data are divided into a group, and a total of 100 groups of analysis samples are formed. For example, the values of the welding parameters d1, d2, d3, d4... d10 collected at times t1, t2, t3, t4... t10 can be used as a group of analysis samples; the values of the welding parameters d11, d12, d13, d14... d20 collected at times t11, t12, t13, t14... t20 can be used as a group of analysis samples, and so on, forming 100 groups of analysis samples.
[0052] S2033. Update the first upper threshold to a second upper threshold and update the first lower threshold to a second lower threshold based on multiple sets of analysis samples.
[0053] In some embodiments of the present application, for the detailed steps of updating the first upper threshold to a second upper threshold and updating the first lower threshold to a second lower threshold based on multiple sets of analysis samples, reference can be made to the following description of Figure 3 .
[0054] As Figure 3 shown, it is a detailed flowchart of S2033 in the laser welding process warning method provided by an embodiment of the present application. According to different requirements, the order of steps in this detailed flowchart can be changed, and some steps can be omitted.
[0055] S20331. Obtain multiple averages (hereinafter referred to as "reference averages" for convenience of description) by calculating the average of each set of analysis samples respectively.
[0056] For example, taking a total of 100 sets of analysis samples as an example, an average value can be calculated for each set of analysis samples, so 100 average values can be obtained.
[0057] S20332. Use the average of the multiple reference averages as a second middle threshold between the second upper threshold and the second lower threshold.
[0058] For example, assuming that 100 reference averages are obtained in S20331, the average of these 100 reference averages is used as the second middle threshold between the second upper threshold and the second lower threshold.
[0059] S20333. Calculate the range corresponding to each set of analysis samples according to the maximum and minimum values in each set of analysis samples, and obtain multiple ranges (hereinafter referred to as "reference ranges" for convenience of description).
[0060] In some embodiments of the present application, for each set of analysis samples, the difference between the maximum and minimum values in each set of analysis samples is the range corresponding to each set of analysis samples. Therefore, if there are a total of 100 sets of analysis samples, 100 ranges can be obtained.
[0061] S20334. Obtain the average value of the reference ranges by calculating the average of the multiple reference ranges.
[0062] S20335. Determine the second upper threshold and the second lower threshold based on the average value of the reference ranges, the second middle threshold, and a preset adjustment coefficient.
[0063] In some embodiments of the present application, the second upper threshold = the second middle threshold + the adjustment coefficient Reference range mean; Second lower threshold = Second middle threshold - Adjustment coefficient Reference range mean.
[0064] In some embodiments of the present application, the server determines the value of the adjustment coefficient according to the number of samples included in each group of analysis samples.
[0065] For the convenience of describing the present invention, taking a as the adjustment coefficient and b as the number of samples included in each group of analysis samples as an example, the server has predefined the corresponding adjustment coefficients when b is different values. Therefore, the magnitude of the adjustment coefficient a can be determined according to the number of samples included in each group of analysis samples.
[0066] For example, the server has predefined that when b is 2, the corresponding adjustment coefficient is 1.88; when b is 3, the corresponding adjustment coefficient is 1.023; when b is 4, the corresponding adjustment coefficient is 0.729; when b is 5, the corresponding adjustment coefficient is 0.577; when b is 6, the corresponding adjustment coefficient is 0.483; when b is 7, the corresponding adjustment coefficient is 0.419; when b is 8, the corresponding adjustment coefficient is 0.373; when b is 9, the corresponding adjustment coefficient is 0.337; when b is 10, the corresponding adjustment coefficient is 0.308. Then when the number of samples in each group of analysis samples is 10, the value of the adjustment coefficient a is 0.308.
[0067] As Figure 4 shown, it is a detailed flowchart of S205 in the laser welding process warning method provided by the embodiments of the present application. According to different requirements, the order of the steps in this detailed flowchart can be changed, and some steps can be omitted.
[0068] S2051, perform smoothing processing on the first data sequence using a moving average algorithm to obtain a second data sequence including multiple average values.
[0069] As described above, the first data sequence includes multiple values of welding parameters corresponding to multiple acquisition times respectively, and each value corresponds to an acquisition time.
[0070] In some embodiments of the present application, performing smoothing processing on the first data sequence to obtain a second data sequence including multiple average values includes: traversing each value in the first data sequence based on a preset sliding window in the order of the acquisition time corresponding to each value in the first data sequence, and obtaining the average value of all values in the sliding window corresponding to each acquisition time; generating a second data sequence based on the average value of all values in the sliding window corresponding to each acquisition time.
[0071] In some embodiments of the present application, the server may predefine the size of the sliding window as N, for example, N is equal to 30. That is, the sliding window can include at most 30 values.
[0072] In some embodiments of the present application, in the order of the acquisition time corresponding to each value in the first data sequence, traversing each value in the first data sequence based on a preset sliding window to obtain the average value of all values in the sliding window corresponding to each acquisition time includes: sliding the sliding window starting from the first value in the first data sequence until all values in the first data sequence are traversed. Each time the sliding window slides, determining the number of values currently included in the sliding window, denoted as M, and calculating the average value of all values in the current sliding window. The first value corresponds to the earliest acquisition time.
[0073] In some embodiments of the present application, calculating the average value of all values in the current sliding window includes: when M is equal to N, taking the average value of the M values as the average value of all values in the sliding window; and when M is less than N, generating (N - M) standard values corresponding to the welding parameters, and taking the (N - M) standard values and the average value of the M values currently included in the sliding window as the average value of all values in the sliding window.
[0074] In some embodiments of the present application, the standard value corresponding to the welding parameter may be a preset value, and the size of the preset value is determined according to the updated parameter range corresponding to the welding parameter. For example, the preset value is a value greater than the second lower threshold of the updated parameter range and less than the second upper threshold of the updated parameter range.
[0075] To clearly illustrate the present invention, assume that the first data sequence includes the values of welding parameters (such as the value of welding speed) collected at times t1, t2, t3, t4... tn, which are d1, d2, d3, d4... dn respectively. Then first, the sliding window with a size of 30 slides to the first value d1 of the welding parameter corresponding to the earliest acquisition time t1 in the first data sequence. At this time, there is only one value (i.e., d1) in the sliding window, so the number of values in the sliding window at this time is 1. Since 1 is less than the size N of the sliding window (N = 30), the server generates 29 standard values d0 corresponding to the welding parameter (such as welding speed), and takes the average value of the 29 standard values d0 and d1 as the average value of all values in the sliding window corresponding to the acquisition time t1. Then the sliding window slides to the value d2 corresponding to the acquisition time t2 in the first data sequence. At this time, there are two values (i.e., d1 and d2) in the sliding window, so the number of values in the sliding window at this time is 2. Since 2 is less than the size N of the sliding window (N = 30), the server generates 28 standard values d0 corresponding to the welding parameter (such as welding speed), and takes the average value of the 28 standard values d0, d1, and d2 as the average value of all values in the sliding window corresponding to the acquisition time t2. And so on until each value corresponding to the acquisition time in the first data sequence is traversed, thereby obtaining a second data sequence including multiple average values ( ). The multiple average values ( ) respectively correspond to times t1, t2, t3, t4... tn.
[0076] S2052. Based on the multiple average values in the second data sequence and multiple data control ranges, determine whether an abnormal condition occurs in the laser welding process, where each data control range in the multiple data control ranges is determined based on at least one of a second upper threshold, a second middle threshold, and a second lower threshold.
[0077] In some embodiments of the present application, if any one of the average values in the second data sequence does not belong to the data control range [D2min, D2max] determined by the second upper threshold and the second lower threshold, it is determined that an abnormal condition occurs in the laser welding process, there may be a process deviation, and a warning needs to be triggered.
[0078] For example, assume that the average value in the second data sequence is less than the second lower threshold D2min or greater than the second upper threshold D2max, then it is determined that an abnormal condition occurs in the laser welding process and a warning needs to be triggered.
[0079] In some embodiments of the present application, if at least B (e.g., 2) of the continuous A (e.g., 3) average values in the second data sequence fall outside the range of twice the sample standard deviation on the same side of the second middle threshold D2med, it is determined that an abnormal condition occurs in the laser welding process, there may be a deviation in the welding process, and a warning needs to be triggered. Where A and B are positive integers, and B is less than or equal to A.
[0080] In some embodiments of the present application, the sample standard deviation S of the second data sequence can be calculated first, where ; where S represents the sample standard deviation of the second data sequence; n represents the number of samples in the second data sequence; represents the i-th value in the second data sequence; represents the average value of the second data sequence.
[0081] In some embodiments of the present application, the range of twice the sample standard deviation on the same side of the second middle threshold D2med includes [D2med, D2med + 2S] and [D2med - 2S, D2med]. Accordingly, at least B of the continuous A average values in the second data sequence falling outside the range of twice the sample standard deviation on the same side of the second middle threshold D2med means that the at least B average values are all greater than (D2med + 2S) or all less than (D2med - 2S) at the same time.
[0082] In some embodiments of the present application, if at least B (e.g., 4) out of consecutive A (e.g., 5) averages in the second data sequence fall outside the range of one sample standard deviation on the same side of the second median threshold D2med, it is determined that an abnormal condition occurs in the laser welding process, there may be a variation in the welding process, and a warning needs to be triggered.
[0083] In some embodiments of the present application, the range of one sample standard deviation on the same side of the second median threshold D2med includes [D2med, D2med + S] or [D2med - S, D2med]. Accordingly, at least B averages out of consecutive A averages in the second data sequence falling outside the range of one sample standard deviation on the same side of the second median threshold D2med means that these at least B averages are all greater than (D2med + S) or all less than (D2med - S) simultaneously.
[0084] In some embodiments of the present application, if more than consecutive A (e.g., 9) averages in the second data sequence all fall on the same side of the second median threshold D2med, it is determined that an abnormal condition occurs in the laser welding process, there may be a loss of control in the welding process, and a warning needs to be triggered.
[0085] In some embodiments of the present application, more than consecutive A averages in the second data sequence falling on the same side of the second median threshold D2med means that these more than consecutive A averages are all greater than D2med or all less than D2med simultaneously.
[0086] In some embodiments of the present application, if consecutive multiple (e.g., 6) averages in the second data sequence show a monotonically increasing or decreasing trend, it is determined that an abnormal condition occurs in the laser welding process, there may be improper adjustment of welding parameters or a change in equipment performance during the welding process, and a warning needs to be triggered.
[0087] In some embodiments of the present application, if consecutive multiple (e.g., 8) averages in the second data sequence alternate on both sides of the second median threshold D2med but none fall within the range of one sample standard deviation of the second median threshold D2med, it is determined that an abnormal condition occurs in the laser welding process, there may be an uneven distribution in the welding process, and a warning needs to be triggered.
[0088] In some embodiments of the present application, if consecutive multiple (e.g., 15) averages in the second data sequence all fall within the range of one sample standard deviation on both sides of the second median threshold D2med, it is determined that an abnormal condition occurs in the laser welding process, there may be a situation where the process is in an abnormal stable control state, and a warning needs to be triggered.
[0089] In some embodiments of the present application, if consecutive multiple (e.g., 14) average values in the second data sequence show alternating changes of adjacent points up and down, it is determined that an abnormal condition occurs in the laser welding process, there may be a periodic deviation, and a warning needs to be triggered.
[0090] S2053, if it is determined that an abnormal condition occurs in the laser welding process, a warning is issued in a preset manner.
[0091] In some embodiments of the present application, issuing a warning in a preset manner may refer to sending a notice to relevant personnel in the form of an acoustic and optical signal, an email, a text message, or through a mobile application.
[0092] In some embodiments of the present application, after receiving the warning, relevant personnel can perform some remedial measures, including, for example, reviewing the laser welding process and data, verifying the accuracy of data collection and recording, and eliminating data acquisition errors; according to the process of the remedial operation, adjusting the parameters of the machine platform for different warning situations; performing a secondary confirmation based on the actual detection data of the product to determine whether the warning rule is normal, and adjusting or optimizing the warning rule, etc.
[0093] Compared with the prior art, the present application dynamically adjusts the upper threshold and the lower threshold of the parameter range by analyzing the values of the welding parameters in the welding process in real time and based on the measured data collected historically, so that the adjusted parameter range adapts to the dynamic changes of the welding process, reduces false warnings and missed warnings, and improves the accuracy and reliability of the warning. While improving production efficiency, it reduces the shutdown cost caused by false warnings. In addition, timely responding to the process deviation to trigger a warning can reduce the generation of defective products, improve the quality of the product while reducing the need for manual intervention by operators, and reduce errors caused by human factors.
[0094] As Figure 5 shown, it is a functional module diagram of a laser welding process warning device provided by an embodiment of the present application. The laser welding process warning device 10 runs on the server 1. The laser welding process warning device 10 includes an acquisition module 101, a judgment module 102, and an execution module 103. The module / unit referred to in the present application means a series of computer-readable instruction segments that can be acquired by a processor and can complete a fixed function, and is stored in a storage device.
[0095] The obtaining module 110 is configured to obtain the values of the welding parameters in real time during the laser welding process. The determining module 102 is configured to determine whether the values of the welding parameters belong to a preset parameter range, where the preset parameter range includes a first upper threshold and a first lower threshold. The execution module 103 is configured to update the first upper threshold to a second upper threshold and update the first lower threshold to a second lower threshold when it is determined that the values of the welding parameters do not belong to the preset parameter range. The obtaining module 110 is further configured to generate a first data sequence corresponding to the welding parameters based on the values of the welding parameters obtained in real time; the execution module 103 is further configured to determine whether to trigger an alarm mechanism based on the first data sequence, the second upper threshold, and the second lower threshold.
[0096] Another embodiment of the present application further provides a server. As Figure 6 shown, in an embodiment of the present application, the server 1 includes, but is not limited to, a memory 11, a processor 12, a display device 13, and a computer program 110 stored in the memory 11 and executable on the processor 12. The computer program 110 may be a software program for implementing early warning of the laser welding process, and may, for example, implement each step as Figures 1 to 4 shown. The memory 11 and the processor 12 are communicatively connected via a bus 13. The display device 13 may be a touch display screen or other device capable of displaying the data during the operation of the server 1.
[0097] Those skilled in the art can understand that the schematic diagram is only an example of the server 1 and does not constitute a limitation on the server 1. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, the server 1 may further include input / output devices, network access devices, buses, etc.
[0098] In some embodiments of the present application, the server 1 is further communicatively connected to a plurality of sensors 15 (only three are schematically shown in the figure). The plurality of sensors 15 include, but are not limited to, photoelectric sensors, power meters, and vision sensors, which are respectively configured to collect relevant welding parameters during the laser welding process, such as welding speed, solder joint power, solder joint welding radius, camera ring angle, solder joint concentricity, right ring Y-direction deviation, right ring X-direction deviation, solder joint angle, left ring X-direction deviation, left ring Y-direction deviation, etc. during the laser welding process.
[0099] The processor 12 can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc. The processor 12 is the computing core and control center of the server 1, connecting various parts of the entire server 1 through various interfaces and lines, and executing the operating system of the server 1 and various installed application programs, program codes, etc.
[0100] Exemplarily, the computer program 110 can be divided into one or more modules / sub-modules / units. One or more modules / sub-modules / units are stored in the memory 11 and executed by the processor 12 to complete this application. One or more modules / sub-modules / units can be a series of computer-readable instruction segments capable of performing specific functions, and these computer-readable instruction segments are used to describe the execution process of the computer-readable instructions in the server 1. For example, the computer program 110 can be divided into an acquisition module 101, a judgment module 102, and an execution module 103.
[0101] The memory 11 can be used to store computer-readable instructions and / or modules. The processor 12 realizes various functions of the server 1 by running or executing the computer-readable instructions and / or modules stored in the memory 11, and by calling the data stored in the memory 11. The memory 11 mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store the data created according to the use of the server 1. The memory 11 can include non-volatile and volatile memories, such as: hard disks, memory, plug-in hard disks, Smart Media Cards (SMCs), Secure Digital (SD) cards, Flash Cards, at least one magnetic disk storage device, flash memory device, or other storage devices.
[0102] The memory 11 can be an external memory and / or an internal memory of the server 1. Further, the memory 11 can be a memory in physical form, such as a memory stick, a TF card (Trans-flash Card), etc.
[0103] If the modules / units integrated in Server 1 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of the present application, computer-readable instructions can also be used to instruct relevant hardware to complete. The computer-readable instructions can be stored in a computer-readable storage medium. When the computer-readable instructions are executed by a processor, the steps of the above-described method embodiments can be implemented.
[0104] Among them, the computer-readable instructions include computer-readable instruction codes, and the computer-readable instruction codes can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer-readable medium can include: any entity or device capable of carrying the computer-readable instruction code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory).
[0105] Combined with Figure 6 , the memory 11 in Server 1 stores computer-readable instructions, and the processor 12 can execute the computer-readable instructions stored in the memory 11 to implement each method step in the laser welding process warning method as Figures 2 to 4 shown.
[0106] Specifically, for the specific implementation method of the above computer-readable instructions by the processor 12, reference can be made to the description of the relevant steps in the Figures 2 to 4 corresponding embodiment, which will not be elaborated here.
[0107] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of modules is only a logical function division, and there can be other division methods in actual implementation.
[0108] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0109] In addition, in each embodiment of the present application, each functional module may be integrated in a processing unit, may exist separately as individual physical units, or two or more units may be integrated in one unit. The above integrated unit may be implemented in the form of hardware, or in the form of a combination of hardware and software functional modules.
[0110] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-limiting. The scope of the present application is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any reference signs in the claims should not be construed as limiting the claims involved.
[0111] In addition, it is obvious that the term "including" does not exclude other units or steps, and the singular does not exclude the plural. A plurality of units or devices may also be implemented by one unit or device through software or hardware. The terms such as "first" and "second" are used to represent names and do not indicate any specific order.
[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit them. Although the present application has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present application can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present application.
Claims
1. A laser welding process early warning method, characterized in that: The method comprises: Real-time acquisition of welding parameter values during laser welding; Determining whether the value of the welding parameter belongs to a preset parameter range, wherein the preset parameter range includes a first upper threshold and a first lower threshold; When it is determined that the value of the welding parameter does not belong to the preset parameter range, updating the first upper threshold value to a second upper threshold value, and updating the first lower threshold value to a second lower threshold value; generating a first data sequence corresponding to the welding parameter based on the value of the welding parameter acquired in real time; and Determine whether to trigger an alarm mechanism based on the first data sequence and the second upper threshold and the second lower threshold.
2. The laser welding process early warning method according to claim 1, characterized in that: The updating of the first upper threshold value to a second upper threshold value, and the updating of the first lower threshold value to a second lower threshold value comprises: Acquiring a preset number of measured data corresponding to the welding parameters; Generating multiple groups of analysis samples based on a preset number of the measured data according to the collection time corresponding to each of the measured data; and The first upper threshold is updated to the second upper threshold, and the first lower threshold is updated to the second lower threshold based on a plurality of groups of the analysis samples.
3. The laser welding process early warning method according to claim 2, characterized in that: The preset parameter range also includes a first middle threshold value between the first upper threshold value and the first lower threshold value; The updating of the first upper threshold to the second upper threshold based on the plurality of analysis samples, and the updating of the first lower threshold to the second lower threshold comprises: By respectively calculating the average value of each group of the analysis samples, a plurality of reference average values are obtained; Taking the average of the plurality of reference average values as a second middle threshold value between the second upper threshold value and the second lower threshold value; Calculate the range corresponding to each group of analysis samples according to the maximum value and the minimum value in each group of analysis samples to obtain multiple reference ranges; Obtaining a reference range mean by calculating an average value of a plurality of the reference ranges; and The second upper threshold and the second lower threshold are determined based on the reference range mean, the second middle threshold and a preset adjustment coefficient.
4. The laser welding process early warning method according to claim 3, characterized in that: The adjustment coefficient is determined according to the number of the analysis samples in each group.
5. The laser welding process early warning method according to claim 4, characterized in that: The determining whether to trigger an alarm mechanism based on the first data sequence and the second upper threshold and the second lower threshold comprises: Smoothing the first data sequence using a moving average algorithm to obtain a second data sequence including a plurality of average values; Determine whether an abnormal condition occurs in the laser welding process based on a plurality of the average values and a plurality of data control ranges, wherein each of the plurality of the data control ranges is determined based on at least one of the second upper threshold, the second middle threshold, and the second lower threshold; and If it is determined that an abnormal condition occurs during the laser welding process, an alarm is issued in a preset manner.
6. The laser welding process early warning method according to claim 5, characterized in that: The first data sequence includes multiple values of the welding parameter corresponding to multiple acquisition times, each value corresponding to one acquisition time; the first data sequence is smoothed to obtain a second data sequence including multiple average values, including: According to the order of the collection time corresponding to each of the values, traverse each value in the first data sequence based on a preset sliding window to obtain an average value of all the values in the sliding window corresponding to each collection time; The second data sequence is generated based on the average value of all values in the sliding window corresponding to each acquisition time.
7. The laser welding process early warning method according to claim 6, characterized in that: The size of the sliding window is represented as N, and traversing each value in the first data sequence based on a preset sliding window in the order of the collection time corresponding to each value to obtain the average value of all values in the sliding window corresponding to each collection time includes: Slide the sliding window from the first value in the first data sequence until all values in the first data sequence are traversed, and each time the sliding window slides, determine the number of values currently included in the sliding window, recorded as M, and calculate the average value of all values in the current sliding window, where the first value corresponds to the earliest collection time; The step of calculating the average value of all values in the current sliding window includes: When M is equal to N, taking the average of the M values as the average of all values in the sliding window; and When M is less than N, (NM) standard values corresponding to the welding parameters are generated, and the average value of the (NM) standard values and the M values currently included in the sliding window is taken as the average value of all values in the sliding window.
8. The laser welding process early warning method according to claim 1, characterized in that: When it is determined that the value of the welding parameter does not belong to the preset parameter range, updating the first upper threshold to a second upper threshold, and updating the first lower threshold to a second lower threshold comprises: When it is determined that the value of the welding parameter does not belong to the preset parameter range, in response to a user input signal, the first upper threshold is updated to the second upper threshold, and the first lower threshold is updated to the second lower threshold.
9. A server, characterized in that: The server comprises: a memory storing computer-readable instructions; and A processor executes the computer-readable instructions to implement the laser welding process early warning method as described in any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions; when the computer-readable instructions are processed and executed, the laser welding process early warning method as described in any one of claims 1 to 8 is implemented.