Device information acquisition method and system based on MQTT open protocol

Abstract

The invention relates to the field of welding automation, in particular to an equipment information acquisition method and system based on an MQTT open protocol, the system comprises a welding terminal, an MQTT server and a plurality of user clients which are in communication connection in sequence, and the MQTT server comprises an intermediate processor and an MQTT proxy server which are in communication connection; wherein the welding terminal is configured to collect welding data of welding equipment at a preset frequency and upload the welding data to the intermediate processor; the intermediate processor is configured to: determine welding encapsulation data based on the welding parameters and the welding data, where the welding encapsulation data includes abnormal welding data and / or feature welding data; the welding packaging data are sent to an MQTT proxy server; the MQTT proxy server is configured to determine a target client paying attention to a data type from a plurality of user clients based on the data type of the welding encapsulation data; and sending the welding packaging data to the target client.

Description

Technical Field

[0001] The present invention relates to the field of welding automation, and in particular to a method and system for acquiring device information based on the MQTT open protocol. Background Art

[0002] During the welding process, real-time monitoring of parameters such as temperature, current, and gas concentration is crucial to ensure welding quality and safety. Existing technologies often cannot achieve real-time and accurate monitoring of these parameters, resulting in equipment failure or low production efficiency. At the same time, traditional monitoring methods cannot effectively integrate multiple data sources, making data analysis difficult and making it difficult to adjust the welding process in a timely manner.

[0003] In view of this, some embodiments of the present specification provide a method and system for obtaining device information based on the MQTT open protocol, which is more suitable for resource-constrained devices and low-bandwidth, low-reliability network environments. Summary of the invention

[0004] One of the embodiments of the present specification provides a device information acquisition system implemented based on the MQTT open protocol, including: a welding terminal, an MQTT server and multiple user clients connected in sequence for communication, the MQTT server including an intermediate processor and an MQTT proxy server connected in communication; wherein: the welding terminal is configured to collect welding data of the welding equipment at a preset frequency, and upload the welding data to the intermediate processor; the intermediate processor is configured to: determine welding package data based on welding parameters and the welding data, wherein the welding package data includes abnormal welding data and / or feature welding data; send the welding package data to the MQTT proxy server; the MQTT proxy server is configured to: determine a target client that is interested in the data type from the multiple user clients based on the data type of the welding package data; and send the welding package data to the target client.

[0005] One of the embodiments of the present specification also provides a method for acquiring device information based on the MQTT open protocol, including: collecting welding data of welding equipment at a preset frequency; determining welding package data based on welding parameters and the welding data, wherein the welding package data includes abnormal welding data and / or characteristic welding data; based on the data type of the welding package data, determining a target client that is interested in the data type from multiple user clients; and sending the welding package data to the target client.

[0006] One of the embodiments of this specification also provides a device information acquisition apparatus based on the MQTT open protocol, comprising a processor, wherein the processor is used to execute the above-mentioned device information acquisition method based on the MQTT open protocol.

[0007] One of the embodiments of this specification also provides a computer-readable storage medium, which stores computer instructions, and is characterized in that when the computer reads the computer instructions in the storage medium, the computer executes the above-mentioned device information acquisition method based on the MQTT open protocol. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 It is a schematic diagram of an application scenario of a device information acquisition system implemented based on the MQTT open protocol according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a method for acquiring device information based on the MQTT open protocol according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart of an intermediate processor determining welding compensation parameters and adjusting a welding terminal according to some embodiments of the present specification;

[0012] Figure 4 It is a schematic diagram of a model for determining the cause of an abnormality according to some embodiments of this specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0015] As shown in this specification and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may also be added to these processes, or one or more operations may be removed from these processes.

[0017] In some embodiments, the monitoring system of welding equipment relies on wired connections or regional connections within the factory. When the user is far away from the welding equipment, data transmission delays are prone to occur, making it difficult to achieve real-time monitoring. In view of this, in some embodiments of this specification, a device information acquisition system based on the MQTT open protocol is provided, which uses the MQTT open protocol to ensure that data is transmitted with the lowest delay, solving the problem of monitoring lag. MQTT (Message Queuing Telemetry Transport) protocol: It is a lightweight publish / subscribe message transmission protocol suitable for resource-constrained devices and low-bandwidth, low-reliability network environments.

[0018] Figure 1 It is a schematic diagram of an application scenario of a device information acquisition system implemented based on the MQTT open protocol according to some embodiments of this specification.

[0019] In some embodiments, the device information acquisition system 100 implemented based on the MQTT open protocol may include a welding terminal 110, an MQTT server 120, and multiple user clients 130 that are sequentially connected in communication. In some embodiments, the MQTT server 120 may include an intermediate processor 122 and an MQTT proxy server 124 that are connected in communication.

[0020] The welding terminal 110 is a device for obtaining welding data of a welding device. In some embodiments, the welding device may include but is not limited to a welding machine, a welding robot or other welding devices.

[0021] Welding data is data that can be collected by the welding terminal 110 during the operation of the welding equipment. In some embodiments, the welding data can be determined based on the actual welding equipment. For example, it may include the welding area temperature, the current and voltage of the welding machine, the welding speed, the flow and concentration of the shielding gas, the image and vibration of the welded workpiece, etc.

[0022] In some embodiments, the welding terminal 110 may include a processing system and a data acquisition module. The processing system may include a PLC (programmable logic controller) for collecting data acquired by various types of sensors. The data acquisition module may collect and package the data collected by the processing system and send it to the MQTT server 120.

[0023] In some embodiments, the welding terminal 110 is configured to collect welding data of the welding equipment at a preset frequency and upload the welding data to the intermediate processor 122.

[0024] In some embodiments, the preset frequency for collecting welding data can be set by the user. For example, the welding terminal 110 can be configured to collect welding data of the welding equipment every 30 seconds or every 1 minute.

[0025] The intermediate processor 122 is used to provide data transmission and queue management. In some embodiments, the equipment information acquisition system 100 implemented based on the MQTT open protocol may include multiple welding terminals 110. The intermediate processor 122 can realize data connection with the multiple welding terminals 110 to receive welding data from the multiple welding terminals 110.

[0026] In some embodiments, the intermediate processor 122 is configured to: determine welding package data based on welding parameters and welding data; and send the welding package data to the MQTT proxy server 122. In some embodiments, the welding package data includes abnormal welding data and / or characteristic welding data. For more description of welding parameters and welding package data, please refer to the relevant content below.

[0027] The MQTT proxy server 124 is a server based on the MQTT protocol built in the cloud or locally. The MQTT proxy server 124 can be responsible for receiving the data processed by the intermediate processor 122 and sending it to a specific user client 130 according to the content (topic) of the data. In some embodiments, the MQTT proxy server 124 is configured to: determine a target client that is interested in the data type from multiple user clients 130 based on the data type of the welding package data; and send the welding package data to the target client.

[0028] The data type of the welding package data indicates that the welding package data only includes characteristic welding data, or only includes abnormal welding data, or includes abnormal welding data and characteristic welding data. The MQTT proxy server 124 can choose to push characteristic welding data or abnormal welding data, or push characteristic welding data and abnormal welding data at the same time according to the data type of the welding package data subscribed by the user.

[0029] For example, maintenance personnel only pay attention to the anomalies that occur during welding, so they can subscribe to abnormal welding data in the MQTT proxy server 124. When the MQTT proxy server 124 receives the welding package data sent by the intermediate processor 122 and contains abnormal welding data, it is pushed to the maintenance personnel's client in a timely manner.

[0030] In some embodiments, the user client 130 may include a device with a display function such as a user's mobile phone 130-1, a tablet computer 130-2, or a computer 130-3. In some embodiments, a monitoring platform or similar mobile application may also be installed in the user client 130, so that the user can easily access real-time welding data or pay attention to real-time monitoring of welding status and abnormalities.

[0031] It should be understood that Figure 1 The system 100 and its components shown can be implemented in various ways. It is understandable that, after understanding the principle of the system, those skilled in the art may arbitrarily combine the components or form a subsystem to connect with other modules without departing from the principle.

[0032] Figure 2 is an exemplary flow chart of a method for acquiring device information based on the MQTT open protocol according to some embodiments of this specification. Figure 2 As shown, process 200 includes the following steps:

[0033] Step 210, collecting welding data of the welding equipment at a preset frequency. In some embodiments, step 210 can be performed by the welding terminal 110. For more description of welding equipment and welding data, please refer to Figure 1 Related content.

[0034] Step 220 , determining welding package data based on the welding parameters and the welding data. In some embodiments, step 220 may be performed by the intermediate processor 122 .

[0035] Welding parameters refer to pre-set parameters related to welding work or welding process. In some embodiments, welding parameters may include welding preset parameters and welding equipment parameters.

[0036] In some embodiments, the preset welding parameters may include a preset welding method, a preset welding position, a preset weld length, a preset welding thickness, a preset welding time, etc. In some embodiments, the preset welding method may include, for example, fusion welding, pressure welding, and brazing. Taking fusion welding as an example, it may further include gas welding, arc welding, and electroslag welding, etc., which are not further limited in this specification. The preset welding position may be divided into flat welding, vertical welding, and horizontal welding, etc. according to the position of the weld.

[0037] In some embodiments, the welding equipment parameters may include welding equipment type and preset welding equipment operating parameters (such as equipment temperature, current, voltage, etc.).

[0038] The welding package data includes abnormal welding data and / or characteristic welding data. Abnormal welding data is data that is determined to be abnormal during welding. For example, the abnormal welding data may be a parameter whose value exceeds the corresponding range in the welding preset parameters.

[0039] Characteristic welding data is welding data other than abnormal welding data, and the key point data is further extracted. These key points can reflect the important characteristics of the welding process, allowing users to quickly and accurately analyze the actual changes in the welding process based on a small amount of key point data. For example, for a parameter that changes linearly, it is only necessary to extract the data of several key points at the beginning, end, and intermediate process, which is enough for users to analyze the actual data changes based on the key point data without the need to transmit a large amount of intermediate process data.

[0040] In some embodiments, if the welding equipment and the welding process are normal, the welding package data may not include abnormal welding data. For ease of description, the following text will explain that the welding package data includes abnormal welding data and characteristic welding data, which is not intended to limit the scope of this specification.

[0041] In some embodiments, the intermediate processor 122 can determine the estimated data range of each welding data at each stage of the welding process based on the welding parameters by querying the working parameter table. When a certain data in the welding parameter exceeds the estimated data range at the corresponding stage, the data can be determined as abnormal welding data. In some embodiments, the working parameter table can be constructed from historical welding data.

[0042] In some embodiments, the stages in the welding process can be divided according to actual conditions. For example, when the welding work includes 3 welds, the welding work of each weld can be divided into one stage; for example, if the welding is expected to take 10 minutes, then every 2 minutes of work time can be divided into one stage.

[0043] In some embodiments, the intermediate processor 122 may treat the remaining welding data other than the abnormal welding data as non-abnormal welding data, then determine an estimated data pattern based on the non-abnormal welding data, and finally select data of several key points in the non-abnormal welding data as feature welding data based on the estimated data pattern.

[0044] The estimated data pattern represents the data variation form of a type of welding data. For example, the estimated data pattern may include a linear pattern, a parabolic pattern, a periodic pattern, and an unconventional pattern. In some embodiments, the estimated data pattern corresponding to the data variation form of a certain type of non-abnormal welding data may be specified by a technician, or the technician may perform statistical analysis (such as data visualization, linear regression analysis, etc.) on multiple historical welding data of this type to determine the corresponding estimated data pattern. For example, if the technician finds through statistics that the welding temperature changes linearly with time, it can be determined that the estimated data pattern corresponding to the welding temperature is a linear pattern.

[0045] Continuing with the example of the estimated data mode corresponding to the welding temperature being a linear mode, the intermediate processor 122 can use the data point corresponding to the welding temperature at the beginning of the welding process as the starting key point; the data point corresponding to the welding temperature at the end of the welding process as the ending key point; according to the change trend corresponding to the welding temperature, select several intermediate points as intermediate key points, and use the data of the above key points as characteristic welding data of the welding temperature, wherein the intermediate key points can be the turning points of the data change or the data points selected at equal intervals.

[0046] For another example, assuming that the estimated data pattern corresponding to a certain type of non-abnormal welding data is a parabolic pattern, in addition to the aforementioned starting key points, ending key points and intermediate key points, the maximum or minimum value points of the data change can also be taken as extreme value key points as characteristic welding data.

[0047] In some embodiments, for welding data whose estimated data pattern is not a normal format, all data may be used as characteristic welding data or corresponding data may be selected at each preset time interval as characteristic welding data.

[0048] Since the actual welding conditions of different workpieces are also different, the intermediate processor 122 can also determine the welding packaging data according to the actual conditions of the welded workpieces. In view of this, in some embodiments, step 220 may include: acquiring workpiece feature data and welding environment data; determining estimated rule data based on the workpiece feature data, welding environment data and welding parameters; determining welding packaging data based on the estimated rule data and welding data.

[0049] The workpiece feature data is a variety of feature data of the workpiece to be welded. In some embodiments, the workpiece feature data may include: workpiece size data, workpiece material data, workpiece process data (type and thickness of workpiece surface coating, whether the workpiece is preheated before welding, etc.). In some embodiments, the workpiece feature data may be manually input or obtained by the intermediate processor 122 through a server storing welding process information.

[0050] The welding environment data refers to the environment conditions when the workpieces to be welded are welded. In some embodiments, the welding environment data may include: the gas pressure value, temperature, type and concentration of the shielding gas used in welding, etc. In some embodiments, the welding environment data may be acquired by a sensor disposed in the welding environment and sent to the intermediate processor 122.

[0051] In some embodiments, the estimated regularity data may include an estimated data range and an estimated data pattern.

[0052] In some embodiments, the intermediate processor 122 can construct a welding feature vector based on the workpiece feature data, welding environment data, and welding parameters, and then perform vector retrieval in a feature vector database based on the welding feature vector to obtain estimated regularity data. The feature vector database can be constructed based on historical welding data by expert experience, and vector retrieval is a conventional vector matching method, which is not further described in this specification.

[0053] When the estimated regular data is determined and the estimated data range and the estimated data pattern are obtained, the intermediate processor 122 can obtain the welding packaging data in the manner described above, which will not be repeated here.

[0054] By retrieving appropriate estimated regularity data from a feature vector database containing historical data and expert experience, the estimated data range and estimated data pattern can be quickly obtained, and the welding package can be accurately determined, thereby enabling timely delivery of welding-related information and risks.

[0055] In some embodiments, characteristic welding data can be determined based on communication bandwidth data and estimated regularity data.

[0056] In some embodiments, the communication bandwidth data may be the bandwidth between the intermediate processor 122 and the MQTT proxy server 124 or the bandwidth of the data connection in the entire system. In some embodiments, the communication bandwidth data may include bandwidth size and bandwidth quality. The bandwidth size indicates the available bandwidth of the communication link, and the bandwidth quality indicates the stability of the communication link, which may include indicators such as packet loss rate, delay, and jitter.

[0057] In some embodiments, if the bandwidth is larger and the bandwidth quality is higher, the intermediate processor 122 can transmit more feature welding data within a certain period of time. At this time, the feature welding data as shown in the previous example can include more data corresponding to intermediate key points. Conversely, the data of key points without large data fluctuations in the feature welding data can be reduced as much as possible.

[0058] By dynamically adjusting the characteristic welding data according to the communication bandwidth data, more characteristic welding data can be transmitted when the bandwidth is sufficient and the quality is high, ensuring that the client obtains detailed welding process information; while in the case of limited bandwidth and low quality, fewer key points are transmitted to reduce the burden of data transmission and ensure the real-time and stability of data transmission. This method significantly improves the flexibility and adaptability of the system, ensuring that the welding process can be efficiently and reliably monitored and controlled under various network conditions.

[0059] In the case of poor bandwidth conditions, more important data can be transmitted preferentially. Therefore, in some embodiments, the intermediate processor 122 can also be configured to: in response to the communication bandwidth data satisfying the delay condition, determine the priority of multiple data in the packaging welding data, and transmit the multiple data in the packaging welding data in sequence based on the priority of the packaging welding data.

[0060] In some embodiments, the delay condition may be that the bandwidth size is lower than a first bandwidth threshold and / or the bandwidth quality is lower than a first quality threshold, wherein the first bandwidth threshold and the first quality threshold may be manually specified.

[0061] In some embodiments, the intermediate processor 122 may assign a higher data priority to the abnormal welding data relative to the characteristic welding data. In some embodiments, the greater the proportion of the abnormal welding data exceeding the estimated data range, the higher the data priority of the abnormal welding data. In some embodiments, the intermediate processor 122 may also determine a higher data priority based on a preset strategy, such as if the welding temperature has a greater impact on the welding quality than the welding shielding gas concentration, then the characteristic welding data corresponding to the welding temperature has a higher data priority.

[0062] By determining the priority of the data to be transmitted by the intermediate processor 122, it is ensured that more critical data can be transmitted in a timely manner, so that the system can still push data in a timely manner even in a poor network situation, thereby improving the system's response speed and risk resistance.

[0063] In some embodiments, in step 220, the intermediate processor 122 may also: determine an actual data pattern based on the welding data; and determine characteristic welding data based on the actual data pattern.

[0064] In some embodiments, the actual data pattern can be determined based on welding data or welding data acquired within a period of time (e.g., within 5 minutes) using statistical analysis methods such as linear regression analysis, polynomial regression analysis, or periodic analysis. The above statistical analysis methods are conventional statistical means and are not further described in this specification.

[0065] In some embodiments, the intermediate processor 122 may determine the actual data pattern based on all welding data acquired within a period of time. This solution may obtain a more accurate actual data pattern but may consume more time and computing resources. In some embodiments, considering the computing power of the intermediate processor 122, the actual data pattern may be determined based on only part of the welding data. For example, if there is abnormal welding data in a certain type of welding data, other non-abnormal welding in the welding data of this type is also analyzed to determine the actual data pattern and determine the characteristic welding data according to the actual data pattern.

[0066] Determining the actual data pattern and obtaining characteristic welding data through statistical analysis methods can make the characteristic welding data more accurate than that determined based on estimated regular data, but it consumes more computing resources. When the data volume is small, more accurate characteristic welding data can be obtained through this solution.

[0067] In some embodiments, considering that there may be points on the workpiece that are more difficult to weld, in step 220, the intermediate processor 122 can also determine the key welding points based on the workpiece feature data, welding parameters and welding quality requirements; and determine the characteristic welding data based on the key welding points and welding data.

[0068] The welding quality requirement indicates the demand for welding quality during quality inspection / acceptance. In some embodiments, the welding quality requirement can be divided into three levels: high, medium, and low. The higher the welding quality requirement level, the more welding key points are determined. In some embodiments, the welding quality requirement can be specified by process standards or manually.

[0069] The critical welding points are the positions where welding defects / errors are prone to occur during the welding process, or the positions where welding quality requirements are not met, for example, the positions where defects such as lack of fusion, pores, and cracks are prone to occur after welding. In some embodiments, the critical welding points may also include positions where the weld structure is relatively complex, for example, the inflection points on the weld or the positions where multiple welds intersect.

[0070] In some embodiments, the intermediate processor 122 can directly determine the inflection point on the aforementioned weld or the location where multiple welds intersect as the key welding point. For locations that cannot be directly derived from the shape and are prone to welding defects / errors, or locations that do not meet the welding quality requirements, the intermediate processor 122 can construct a quality feature vector based on the workpiece feature data, welding parameters and welding quality requirements, and then perform vector retrieval in the quality vector database based on the quality feature vector to obtain the key welding points. The quality vector database can be obtained by manually analyzing historical welding failure workpieces or using simulation methods such as finite element analysis (FEA) to predict the stress distribution and deformation of welds at different locations, and then determine the key points and store them in the vector database.

[0071] In some embodiments, the intermediate processor 122 can directly obtain welding data of key welding points as feature welding data.

[0072] By determining the key points of welding, we can focus on the welding process from the perspective of the workpiece structure, and better monitor the welding process when no abnormalities occur. This ensures the stability of the welding process and that the level of monitoring is related to the quality requirements, thus avoiding frequent pushes when quality requirements are not high.

[0073] In some embodiments, when bandwidth conditions are good, data can be transmitted quickly, and the intermediate processor 122 can have more time to process the welding data to obtain more accurate abnormal welding data and / or characteristic welding data.

[0074] In some embodiments, the intermediate processor 122 is also configured to: in response to the communication bandwidth data satisfying preset conditions, input the workpiece feature data, welding environment data, welding parameters, estimated law data and welding data into the welding data analysis model to determine abnormal welding data and / or feature welding data.

[0075] In some embodiments, the preset condition may be that the bandwidth size is higher than a second bandwidth threshold and / or the bandwidth quality is higher than a second quality threshold, wherein the second bandwidth threshold and the second quality threshold may be manually specified.

[0076] In some embodiments, the welding data analysis model may be a machine learning model obtained by training with training samples. In some embodiments, the welding data analysis model may be a neural network model, such as a recurrent neural network (RNN).

[0077] In some embodiments, the welding data analysis model can be used to obtain welding package data based on input data. In some embodiments, the input of the welding data analysis model can include welding data sequence, workpiece feature data, welding environment data, welding parameters, and estimated regularity data, wherein the welding data sequence is arranged in chronological order, including all welding data from the start of this welding work to the current time; the workpiece feature data, welding environment data, and estimated regularity data can be obtained in the manner described above; the output of the welding data analysis model is abnormal welding data and / or feature welding data.

[0078] In some embodiments, the welding data analysis model can be obtained by training multiple labeled training samples. Specifically, multiple labeled training samples can be input into the initial welding data analysis model, and a loss function can be constructed by using the labels and the results of the initial welding data analysis model. The parameters of the initial welding data analysis model can be iteratively updated based on the loss function by gradient descent or other methods. When the preset conditions are met, the model training is completed and a trained welding data analysis model is obtained. The preset conditions can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0079] In some embodiments, the training samples of the welding data analysis model may include sample welding data sequences, sample workpiece feature data, sample welding environment data, sample welding parameters, and sample estimated regularity data, and the labels of the training samples are sample abnormal welding data and / or sample feature welding data corresponding to the training samples. The sample welding data sequences, sample workpiece feature data, sample welding environment data, sample welding parameters, and sample estimated regularity data may be obtained from historical welding work.

[0080] In some embodiments, sample abnormal welding data can be obtained through expert experience by marking in a sample welding data sequence acquired from historical welding work based on sample workpiece feature data, sample welding environment data, sample welding parameters, and sample predicted regularity data; alternatively, the final weld of the historical welding work can be quality inspected, and the sample welding data corresponding to the abnormal / defective position obtained through analysis can be used as sample abnormal welding data.

[0081] In some embodiments, the sample characteristic welding data can be obtained by analyzing the non-abnormal data and annotating or correcting it by an expert, for example, manually specifying key points on the curve after fitting the non-abnormal data as the sample characteristic welding data.

[0082] By using a machine learning model when there is a margin in the bandwidth, more accurate abnormal welding data and / or characteristic welding data can be obtained without affecting the response speed of the system, thereby improving the reliability of monitoring.

[0083] Step 230, based on the data type of the welding package data, determine a target client that is interested in the data type from multiple user clients. In some embodiments, step 230 may be performed by the MQTT proxy server 124. For more description of the data type of the welding package data and the user client, see Figure 1 Related content.

[0084] Step 240 , sending the welding package data to the target client. In some embodiments, step 240 may be performed by the MQTT proxy server 124 .

[0085] In some embodiments, the MQTT proxy server 124 sends the welding package data to the target client according to the user's subscription status, so that the user can obtain abnormal welding data during the welding process or understand the actual situation of the welding work in a timely manner.

[0086] The device information acquisition system and method based on the MQTT open protocol provided in this specification utilizes the MQTT protocol to ensure real-time transmission of data with minimal latency, thereby solving the problem of monitoring lag. At the same time, the communication connection design between the welding terminal and the intermediate processor 122 can easily add new welding terminals and improve the scalability of the system. In addition, the intermediate processor 122 can select the optimal means to analyze and process the welding data in real time based on the actual network bandwidth while ensuring low latency of the system.

[0087] In some embodiments, based on the welding image data and data such as the abnormal welding data determined in the previous text, the intermediate processor 122 can determine the cause of the abnormality, determine the welding compensation parameters and adjust the welding terminal in time to ensure the smooth progress of the welding work.

[0088] Figure 3 FIG. 1 is an exemplary flow chart of the intermediate processor 122 determining welding compensation parameters and adjusting welding terminals according to some embodiments of the present specification. Figure 3 As shown, one or more steps in process 300 may be performed by the intermediate processor 122, including the following steps:

[0089] Step 310, determining abnormal analysis information based on equipment maintenance data, abnormal welding data, welding parameters and welding environment data.

[0090] Equipment maintenance data may include historical maintenance data of welding equipment, including maintenance records, maintenance cycles, and defects / faults found during maintenance, etc. Welding image data is image data of welds collected during welding work. In some embodiments, welding image data may be acquired by an image sensor, and welding image data may be an image corresponding to the same time point as other welding data.

[0091] In some embodiments, the abnormality analysis information includes the abnormality cause and the abnormality damage degree corresponding to the abnormality cause.

[0092] The abnormal reason is the main factor causing abnormal welding data. In some embodiments, the abnormal reason may include one or more abnormal devices causing the abnormality. For example, the abnormal reason may include the welding gun moving too fast, the welding gun having an angle deviation, the welding machine current being too large, etc.

[0093] The degree of abnormal damage indicates the degree of damage caused by the abnormal cause to this welding work. If the degree of abnormal damage is large, you can consider stopping this welding work. If the degree of damage is small, you can take actions such as adjusting the welding parameters related to the abnormal cause or not adjusting them for the time being.

[0094] refer to Figure 4 In some embodiments, the intermediate processor 122 may determine the abnormal cause and the abnormal damage extent through an abnormal cause determination model. The abnormal cause determination model may be a machine learning model including an abnormal cause determination layer and a damage extent determination layer, the abnormal cause determination layer may be composed of a neural network (NN), and the damage extent determination layer may be composed of a convolutional neural network (CNN), wherein the output of the abnormal cause determination layer is one of the inputs of the damage extent determination layer.

[0095] In some embodiments, the input of the abnormal cause determination layer is equipment maintenance data, abnormal welding data, welding parameters and welding environment data, and the output is the abnormal cause; the input of the damage degree determination layer is welding image data and the abnormal cause output by the abnormal cause determination layer, and the output is the abnormal damage degree.

[0096] The abnormal cause determination layer and the damage degree determination layer can be trained separately through training samples. The training method of the abnormal cause determination layer and the damage degree determination layer can be similar to the welding data analysis model, which will not be repeated here.

[0097] In some embodiments, the training samples of the abnormal cause determination layer may include sample equipment maintenance data, sample abnormal welding data, sample welding parameters, and sample welding environment data, and the labels of the training samples are the sample abnormal causes corresponding to the training samples. The sample equipment maintenance data, sample abnormal welding data, sample welding parameters, and sample welding environment data may be obtained from historical welding work, and the sample abnormal causes may be determined based on expert experience.

[0098] In some embodiments, the training samples of the damage degree determination layer may include sample welding image data, sample abnormality causes, and the label is the sample abnormality damage degree of the welding workpiece corresponding to the training sample. The sample abnormal damage degree may include at least one or more of the offset of the weld, the area of ​​the leaked weld, the disconnection length of the weld, and the depth of the over-welding. When multiple abnormalities are included, the sample abnormal damage degree can be determined based on the comprehensive determination.

[0099] Step 320 , in response to the damage degree satisfying the damage condition, determining welding compensation parameters based on the abnormality analysis information.

[0100] The welding compensation parameters are parameters or adjustment strategies that the welding terminal needs to adjust for the welding equipment.

[0101] In some embodiments, when the degree of damage satisfies the damage condition, indicating that continued welding may cause damage to the workpiece (eg, weld offset may gradually increase as welding progresses), the operating parameters of the welding equipment may be adjusted.

[0102] In some embodiments, the damage conditions can be divided into minor damage conditions, moderate damage conditions and severe damage conditions according to the degree of damage. The intermediate processor 122 determines different strategies according to different damage conditions. Specifically: for minor damage conditions, the welding feedback parameters can be such that the welding terminal does not adjust the working parameters of the welding equipment, but increases the frequency of the welding terminal collecting welding data; for moderate damage conditions, welding feedback parameters are generated to adjust the working parameters of the welding equipment according to the abnormal cause (if the abnormal cause is that the welding speed is too fast, then the generated welding feedback parameters can indicate to reduce the welding speed by an adjustment amplitude, and at the same time increase the collection frequency, where the adjustment amplitude can be positively correlated to the degree of abnormal damage); for severe damage conditions, the welding feedback parameters can be such that the welding terminal controls the welding equipment to stop welding. At this time, the MQTT proxy server 124 can simultaneously push the maintenance request to the user.

[0103] Step 330, sending the welding compensation parameters to the welding terminal.

[0104] In some embodiments, the intermediate processor 122 may also synchronously send the welding compensation parameters to the MQTT proxy server 124 in real time and push them to the target client in a timely manner.

[0105] By determining the cause and extent of the abnormality through abnormal welding parameters, the intermediate processor 122 can timely adjust the welding work of the welding terminal to reduce the losses caused by abnormal welding to ensure the smooth progress of the welding work; at the same time, the adjustment status can also be pushed to each client in time.

[0106] In some embodiments, the intermediate processor 122 may further adjust the priority of multiple data in the welding package data based on the abnormal analysis information.

[0107] In some embodiments, for one or more abnormal devices corresponding to the aforementioned abnormal causes, the intermediate processor 122 may set the welding data related to the abnormal devices in a subsequent certain time period to have a higher priority.

[0108] In some embodiments, the priority of the data may be positively correlated to the abnormal damage degree and the importance of the device, and the importance of the device may be preset manually. In response to the high priority of the data, the intermediate processor 122 may allow the data collected in a certain period of time to be directly transmitted to the MQTT proxy server 124 for transmission to the user without processing, thereby meeting the real-time transmission of the abnormal data.

[0109] By real-time detection and analysis of anomalies in the welding process and subsequently increasing the priority of relevant data of the corresponding abnormal equipment, important data can be transmitted first, optimizing the utilization of bandwidth resources, reducing network congestion and data processing burden, and being able to identify and handle abnormal situations more quickly, preventing production interruptions and quality problems.

[0110] It should be noted that the above description of processes 200 and 300 is only for example and explanation, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to processes 200 and 300 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification. For example, the intermediate processor 122 can execute process 300 after the end of process 200, or can execute process 300 while executing step 220 or when step 220 is completed. In addition, one or more steps in processes 200 and 300 can be interspersed.

[0111] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0112] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0113] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0114] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0115] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A device information acquisition system based on the MQTT open protocol, characterized in that: include: A welding terminal, an MQTT server and a plurality of user clients connected in communication in sequence, wherein the MQTT server includes an intermediate processor and an MQTT proxy server connected in communication; wherein: The welding terminal is configured to collect welding data of the welding equipment at a preset frequency and upload the welding data to the intermediate processor; The intermediate processor is configured to: Determining welding package data based on welding parameters and the welding data, wherein the welding package data includes abnormal welding data and / or characteristic welding data; Sending the welding package data to the MQTT proxy server; The MQTT proxy server is configured to: Based on the data type of the welding package data, determining a target client that is interested in the data type from the multiple user clients; The welding package data is sent to the target client.

2. The system according to claim 1, characterized in that The step of determining welding packaging data based on welding parameters and the welding data comprises: Acquire workpiece feature data and welding environment data; Determining estimated regularity data based on the workpiece feature data, the welding environment data and the welding parameters; The welding packaging data is determined based on the estimated regularity data and the welding data.

3. The system according to claim 2, characterized in that The intermediate processor is further configured to: In response to the communication bandwidth data satisfying a preset condition, the workpiece feature data, the welding environment data, the welding parameters, the estimated law data and the welding data are input into a welding data analysis model to obtain the abnormal welding data and / or the feature welding data.

4. The system according to claim 1, characterized in that The welding data also includes welding image data, and the intermediate processor is further configured to: Determining abnormality analysis information based on equipment maintenance data, welding environment data, the abnormal welding data and the welding parameters, wherein the abnormality analysis information includes an abnormality cause and a degree of damage corresponding to the abnormality cause; In response to the damage degree satisfying a damage condition, determining a welding compensation parameter based on the abnormality analysis information; The welding compensation parameters are sent to the welding terminal.

5. A device information acquisition method based on the MQTT open protocol, characterized in that: include: Collect welding data of welding equipment at a preset frequency; Determining welding package data based on welding parameters and the welding data, wherein the welding package data includes abnormal welding data and / or characteristic welding data; Based on the data type of the welding package data, determining a target client that is interested in the data type from a plurality of user clients; The welding package data is sent to the target client.

6. The method according to claim 5, characterized in that The step of determining welding packaging data based on welding parameters and the welding data comprises: Acquire workpiece feature data and welding environment data; Determining estimated regularity data based on the workpiece feature data, the welding environment data and the welding parameters; The welding packaging data is determined based on the estimated regularity data and the welding data.

7. The method according to claim 6, characterized in that Also includes: In response to the communication bandwidth data satisfying a preset condition, the workpiece feature data, the welding environment data, the welding parameters, the estimated law data and the welding data are input into a welding data analysis model to obtain the abnormal welding data and / or the feature welding data.

8. The method according to claim 5, characterized in that Also includes: Determining abnormality analysis information based on equipment maintenance data, welding environment data, the abnormal welding data and the welding parameters, wherein the abnormality analysis information includes an abnormality cause and a degree of damage corresponding to the abnormality cause; In response to the damage degree satisfying a damage condition, determining a welding compensation parameter based on the abnormality analysis information; The welding compensation parameters are sent to the welding terminal.

9. A device information acquisition device based on the MQTT open protocol, comprising a processor, characterized in that: The processor is used to execute the device information acquisition method based on the MQTT open protocol as described in any one of claims 5-8.

10. A computer-readable storage medium storing computer instructions, characterized in that: After the computer reads the computer instructions in the storage medium, the computer executes the device information acquisition method based on the MQTT open protocol as described in any one of claims 5 to 8.

Images