Multi-layer multi-pass welding method, computer program product and electronic equipment
By acquiring the bevel information and weld parameters of the weldment and updating the welding parameters using a welding process knowledge graph, the problem of inaccurate parameter settings in multi-layer, multi-pass welding processes has been solved, thereby improving the stability of welding quality and the degree of automation.
Patent Information
- Application Number
- CN202410961079.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-17
- Publication Date
- 2024-11-12
AI Technical Summary
Existing welding technologies cannot handle changes in multi-layer, multi-pass welding processes in real time, leading to inaccurate welding parameter settings, affecting welding quality, and making it difficult to achieve adaptive routing in multi-layer, multi-pass welding processes.
By obtaining the bottom width and depth of the weldment bevel at the current moment, the total number of weld layers and total number of passes are determined. The target process parameters are updated using the welding process knowledge graph. The similarity between the current welding information and historical information is calculated. The historical welding process parameters with the highest similarity are determined as the target process parameters, and the welding robot is controlled to perform welding.
It enables real-time adaptation of welding parameters, improves welding quality and automation, reduces manual workload, and enhances the adaptability and reliability of the welding process.
Smart Images

Figure CN118940828A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of welding technology, and in particular to a multi-layer and multi-pass welding method, a computer-readable storage medium, a computer program product, and an electronic device. Background Art
[0002] Welding is an important way to connect materials and is widely used in various industrial manufacturing fields. However, the welding process is complex and involves the control of multiple parameters, such as welding current, welding voltage, welding speed, etc. The setting of these parameters directly affects the quality of welding. Knowledge graph is a graph-based data structure composed of nodes and edges, which can be used to represent and store complex relationship information. In the field of welding technology, knowledge graphs can be used to represent and store the relationship between welding parameters, as well as the relationship between welding parameters and welding quality, thereby providing a basis for the optimization of welding parameters. Automated welding technology is a technology that automatically controls the welding process through a computer program. It can weld according to preset welding parameters, and can also make real-time adjustments according to the actual welding situation to ensure welding quality.
[0003] Existing welding technology mainly uses manual or mechanical arms, robots and other equipment to perform welding, and the setting of welding parameters mainly depends on the operator's experience and skills. Although the existing methods can complete welding tasks, there are problems such as unstable welding quality and low welding efficiency. In order to solve these problems, some researchers have proposed a welding parameter optimization method based on knowledge graph. This method mainly constructs a welding knowledge graph, and then uses graph database and graph computing technology to analyze and process the welding knowledge graph to obtain the optimal welding parameters. In addition, some researchers have proposed a welding method based on automated preaching technology. This method can perform welding according to preset welding parameters, and can also make real-time adjustments according to actual welding conditions to ensure welding quality.
[0004] Although the existing technology has solved the welding problem to a certain extent, there are still some problems and shortcomings. First, the existing welding parameter optimization method is mainly based on the analysis and processing of offline data, and cannot handle the changes in the multi-layer and multi-pass welding process in real time. Therefore, it may cause inaccurate setting of welding parameters and affect the welding quality. Secondly, it is difficult for the existing preaching method to realize the automation of preaching in the multi-layer and multi-pass welding process. When facing new welds, it is still necessary to manually determine the welding parameters in advance and draw multi-layer and multi-pass preaching diagrams. In the actual welding process, there are problems such as different widths and depths of welds and deformation of the base material caused by excessive heat input. It is difficult for the existing method to realize adaptive preaching in the multi-layer and multi-pass welding process. Summary of the invention
[0005] The main purpose of the present application is to provide a multi-layer and multi-pass welding method, a computer-readable storage medium, a computer program product and an electronic device, so as to at least solve the problem in the prior art that the changes in the multi-layer and multi-pass welding process cannot be processed in real time, resulting in inaccurate setting of welding parameters and affecting welding quality.
[0006] To achieve the above-mentioned purpose, according to one aspect of the present application, a multi-layer and multi-pass welding method is provided, wherein the weldment includes a multi-layer and multi-pass weld, and the method includes: obtaining the groove bottom width of the weldment at the current moment, and determining the groove depth of the weldment at the current moment; determining the total number of layers of the weld to be welded at the current moment according to the groove depth and the thickness of the weld, and determining the total number of passes of the weld to be welded at the current moment according to the groove bottom width and the width of the weld; updating the welding process knowledge graph according to the total number of layers, the total number of passes and current welding information to obtain a target welding process knowledge graph, and the The welding process knowledge graph is a knowledge graph established based on historical welding cases, and the current welding information is information that characterizes the external welding environment at the current moment; using the target welding process knowledge graph, the similarity between the current welding information and the historical welding information is calculated, and the historical welding process parameters corresponding to the historical welding information with the highest similarity are determined as target process parameters, the historical welding information is information that characterizes the external welding environment in the historical welding cases, and the historical welding process parameters are parameters that characterize the welding quality in the historical welding cases; according to the target process parameters, the welding robot is controlled to weld the weldment.
[0007] Optionally, determining the groove depth of the weldment at the current moment includes: obtaining the groove top width of the weldment at the current moment, and obtaining the groove angle of the weldment; determining the groove depth based on the groove top width, the groove bottom width and the groove angle.
[0008] Optionally, the groove depth is determined according to the groove top width, the groove bottom width and the groove angle, including: using the formula Determine the groove depth, where H N is the groove depth, W N is the width of the groove top, w N is the bottom width of the groove, and θ is the angle of the groove.
[0009] Optionally, obtaining the groove angle of the weldment includes: obtaining the initial groove top width, initial groove bottom width, initial base layer thickness and initial weldment thickness of the weldment before welding begins; and determining the groove angle based on the initial groove top width, initial groove bottom width, initial base layer thickness and initial weldment thickness.
[0010] Optionally, determining the groove angle according to the initial groove top width, the initial groove bottom width, the initial base layer thickness and the initial weldment thickness comprises: using the formula Determine the groove angle, where θ is the groove angle, W is the initial groove top width, T is the initial weldment thickness, t is the initial base layer thickness, and w is the initial groove bottom width.
[0011] Optionally, determining the total number of layers of the weld to be welded at the current moment according to the groove depth and the thickness of the weld includes: using the formula Determine the total number of layers, where H N is the groove depth, n is the total number of layers, a is the thickness of the weld, and according to the groove bottom width and the weld width, the total number of welds to be welded at the current moment is determined, including: using the formula Determine the width of the weld, where b is the width of the weld and k is a preset value. is the wire diameter; using the formula Determine the total number of channels, where m is the total number of channels.
[0012] Optionally, according to the target process parameters, controlling the welding robot to weld the weldment, including: according to the total number of layers and the total number of passes, obtaining the historical welding process parameters of the historical welds corresponding to the number of layers and the number of passes of each weld from the target welding process knowledge graph to obtain corrected welding process parameters; correcting the target process parameters according to the corrected welding process parameters; and controlling the welding robot to weld the weldment according to the corrected target process parameters.
[0013] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute any one of the multi-layer and multi-pass welding methods.
[0014] According to another aspect of the present application, a computer program product is provided, comprising computer instructions, wherein when the computer instructions are executed by a processor, any one of the multi-layer and multi-pass welding methods is implemented.
[0015] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include means for executing any one of the multi-layer and multi-pass welding methods.
[0016] Applying the technical solution of the present application, the weldment includes multiple layers and multiple passes of welds. First, the groove bottom width and groove depth of the weldment at the current moment are obtained, and then the total number of layers of welds to be welded at the current moment is determined based on the groove depth and the thickness of the weld, and the total number of passes of welds to be welded at the current moment is determined based on the groove bottom width and the width of the weld. Then, based on the total number of layers, the total number of passes and the current welding information, the welding process knowledge graph is updated to obtain the target welding process knowledge graph, and then the target welding process knowledge graph is used to calculate the similarity between the current welding information and the historical welding information, and the historical welding process parameters corresponding to the historical welding information with the highest similarity are determined as the target process parameters. Finally, according to the target process parameters, the welding robot is controlled to weld the weldment. Compared with the problem in the prior art that changes in the multi-layer and multi-pass welding process cannot be processed in real time, resulting in inaccurate setting of welding parameters and affecting welding quality, the present application determines the total number of layers of welds to be welded at the current moment according to the thickness of the weld and the groove depth at the current moment, and determines the total number of welds to be welded at the current moment according to the width of the weld and the bottom width of the groove at the current moment, thereby ensuring that the total number of layers and the total number of passes of new welds can be obtained in real time, and then the welding process knowledge graph is updated according to the total number of layers, the total number of passes and the current welding information at the current moment to obtain the target welding process knowledge graph, thereby ensuring that the welding process knowledge graph is updated according to the target welding process knowledge graph, calculating the similarity between the current welding information and the historical welding information using the target welding process knowledge graph, and determining the historical welding process parameters corresponding to the historical welding information with the highest similarity as the target process parameters, thereby ensuring that the obtained target process parameters are more adapted to the real-time changes in the multi-layer and multi-pass welding process, that is, ensuring that the target process parameters are more accurate, thereby ensuring better welding quality. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The drawings constituting part of the present application are used to provide a further understanding of the present application. The exemplary embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0018] Figure 1 A hardware structure block diagram of a mobile terminal for performing a multi-layer multi-pass welding method provided in an embodiment of the present application is shown;
[0019] Figure 2A schematic diagram of a multi-layer multi-pass welding method provided according to an embodiment of the present application is shown;
[0020] Figure 3 A structural block diagram of a welding process knowledge base provided according to an embodiment of the present application is shown;
[0021] Figure 4 A structural block diagram of a Neo4j storage model provided according to an embodiment of the present application is shown.
[0022] The above drawings include the following reference numerals:
[0023] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION
[0024] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.
[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.
[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0027] As introduced in the background technology, the prior art is unable to process the changes in the multi-layer and multi-pass welding process in real time, resulting in inaccurate setting of welding parameters and affecting welding quality. To solve the above problems, the embodiments of the present application provide a multi-layer and multi-pass welding method, a computer-readable storage medium, a computer program product and an electronic device.
[0028] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.
[0029] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal for a multi-layer multi-pass welding method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.
[0030] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the multi-layer multi-pass welding method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.
[0031] In this embodiment, a multi-layer and multi-pass welding method running on a mobile terminal, a computer terminal or a similar computing device is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0032] Figure 2 is a flow chart of a multi-layer multi-pass welding method according to an embodiment of the present application. The weldment includes a multi-layer multi-pass weld, such as Figure 2 As shown, the method comprises the following steps:
[0033] Step S201, obtaining the groove bottom width of the weldment at the current moment, and determining the groove depth of the weldment at the current moment;
[0034] Step S202, determining the total number of layers of the weld to be welded at the current moment according to the groove depth and the thickness of the weld, and determining the total number of passes of the weld to be welded at the current moment according to the groove bottom width and the width of the weld;
[0035] Specifically, the weld to be welded is the weld that has not been welded yet.
[0036] Step S203, updating the welding process knowledge graph according to the total number of layers, the total number of passes and the current welding information to obtain a target welding process knowledge graph, wherein the welding process knowledge graph is a knowledge graph established according to historical welding cases, and the current welding information is information representing the external welding environment at the current moment;
[0037] Step S204, using the target welding process knowledge graph, calculating the similarity between the current welding information and the historical welding information, and determining the historical welding process parameters corresponding to the historical welding information with the highest similarity as the target process parameters, the historical welding information is information characterizing the external welding environment in the historical welding case, and the historical welding process parameters are parameters characterizing the welding quality in the historical welding case;
[0038] Step S205, controlling the welding robot to weld the weldment according to the target process parameters.
[0039] Through the above embodiment, the weldment includes multiple layers and multiple passes of welds. First, the groove bottom width and groove depth of the weldment at the current moment are obtained, and then the total number of layers of welds to be welded at the current moment is determined according to the groove depth and the thickness of the weld, and the total number of passes of welds to be welded at the current moment is determined according to the groove bottom width and the width of the weld. Then, according to the total number of layers, the total number of passes and the current welding information, the welding process knowledge graph is updated to obtain the target welding process knowledge graph, and then the target welding process knowledge graph is used to calculate the similarity between the current welding information and the historical welding information, and the historical welding process parameters corresponding to the historical welding information with the highest similarity are determined as the target process parameters. Finally, according to the target process parameters, the welding robot is controlled to weld the weldment. Compared with the problem in the prior art that changes in the multi-layer and multi-pass welding process cannot be processed in real time, resulting in inaccurate setting of welding parameters and affecting welding quality, the present application determines the total number of layers of welds to be welded at the current moment according to the thickness of the weld and the groove depth at the current moment, and determines the total number of welds to be welded at the current moment according to the width of the weld and the bottom width of the groove at the current moment, thereby ensuring that the total number of layers and the total number of passes of new welds can be obtained in real time, and then the welding process knowledge graph is updated according to the total number of layers, the total number of passes and the current welding information at the current moment to obtain the target welding process knowledge graph, thereby ensuring that the welding process knowledge graph is updated according to the target welding process knowledge graph, calculating the similarity between the current welding information and the historical welding information using the target welding process knowledge graph, and determining the historical welding process parameters corresponding to the historical welding information with the highest similarity as the target process parameters, thereby ensuring that the obtained target process parameters are more adapted to the real-time changes in the multi-layer and multi-pass welding process, that is, ensuring that the target process parameters are more accurate, thereby ensuring better welding quality.
[0040] In addition, the degree of automation is high: with the constructed target welding process knowledge graph, the welding robot can automatically calculate the number of welding layers (total number of layers and total number of passes) after scanning the new weld, and plan the welding path, which improves the degree of automation of welding, reduces manual workload, and also improves the stability of welding quality. Strong adaptability: the target welding process knowledge graph can be adaptively changed according to the actual situation. For example, when problems occur during the welding process, the welding path and parameters can be adaptively adjusted to ensure the smooth progress of welding and improve the reliability of welding.
[0041] Specifically, the current welding information includes at least one of the current shielding gas, welding position, welding scene, welding process, welding base material, welding material and welding equipment. The welding material is a filler material for welding, such as welding wire.
[0042] Specifically, the above historical welding process parameters include at least one of the historical welding time, single welding mileage, total welding mileage, welding speed, wire feeding speed, welding current, welding voltage, swing amplitude, left swing speed, right swing speed, left pause, right pause, number of layers and number of passes. Among them, welding time: the time of welding process parameter recording time minus the time of lag error (that is, the actual accurate welding time); single welding mileage: recording single pass welding mileage; total welding mileage: recording total pass welding mileage; welding speed: welding robot moving speed; wire feeding speed: wire feeding speed of wire feeder, proportional to current; swing amplitude: the distance that the welding gun swings from the center point to the side; left swing speed: the rate at which the welding gun swings from the center point to the left side; right swing speed: the rate at which the welding gun swings from the center point to the right side; left pause: the time the welding gun stays when it swings to the left side; right pause: the time the welding gun stays when it swings to the right side; number of layers: the layer that is currently welded; number of passes: the pass that is currently welded.
[0043] Specifically, the framework of the welding process knowledge base is established: the information such as shielding gas, welding position, welding scene, welding process, welding base material, welding material, welding equipment, welding process WPS (Welding Procedure Specification) parameters and groove form are entered into the welding process knowledge base, and the welding knowledge is collected, sorted and classified to obtain the following: Figure 3 The welding process knowledge base shown in the figure, wherein the welding equipment is a welding robot, the welding material is welding wire, and the welding process methods include gas shielded welding, TIG (Tungsten Inert Gas) welding and MIG (Metal Inert Gas) welding.
[0044] Specifically, the welding process knowledge graph is constructed as follows: 1. Data source layer. Structured data: welding process knowledge, parameters, records, etc. in the welding process knowledge base; semi-structured data: Excel tables and CSV (Comma-Separated Values) files generated during welding; unstructured data: welding process documents, standards and manuals, etc. 2. Ontology model construction layer. Based on the multi-layer and multi-pass welding process knowledge content, it is sorted and classified, the concepts, attributes and their relationships in the welding field are defined, and the ontology model is constructed. The relationship types within the multi-layer and multi-pass welding process knowledge are analyzed and expressed in the form of ontology semantic relationships. 3. Knowledge extraction layer. Entity recognition: Natural language processing tools such as SpaCy are used to identify welding entities in the text; relationship extraction: OpenIE and other tools are used to extract the relationship between entities from the text; data mapping: including entity mapping and relationship mapping. Entity mapping maps the extracted entities to the ontology class, and relationship mapping maps the extracted relationships to the ontology attributes. 4. Knowledge graph storage layer. The graph is stored in the knowledge base based on the graph structure storage method, and Neo4j is used to store the knowledge graph data. 5. Reasoning and analysis layer: The reasoning and analysis layer is a key part of the welding knowledge graph application. Through reasoning engines and advanced analysis methods, new knowledge can be derived from existing data, and in-depth analysis and decision support can be performed. Common reasoning engines include HermiT, Pellet, and Fact++. Using description logic for logical reasoning can ensure the consistency and integrity of the knowledge graph; using SWRL to define rules can perform complex reasoning. Advanced analysis uses graph algorithms, statistical analysis, and machine learning to conduct in-depth analysis of the welding knowledge graph. Using the graph algorithm library in the graph database, such as Neo4j's APOC library, centrality analysis, community discovery, path analysis, etc.; through statistical analysis, trends and patterns in the welding process are discovered; using machine learning methods for prediction and classification, using machine learning models such as decision trees and random forests to predict possible defects in the welding process. 6. Application and integration layer: Use historical data and reasoning results in the knowledge graph to optimize the welding process, identify and prevent welding defects through the knowledge graph, improve product quality, and use query languages such as SPARQL for knowledge retrieval and reasoning. Integrate the knowledge graph with the company's welding management system, quality control system, etc., provide a unified query and analysis interface, and develop a RESTful API to allow other applications to access and query the knowledge graph.
[0045] Specifically, the Neo4j storage model is as follows Figure 4As shown in the figure, it shows how various storage files interact on the disk. Each node record contains the ID (Identification) of its first attribute and the ID of the first edge in the relationship chain. When reading the attributes of a node, you can traverse along the one-way linked list structure starting with the pointer pointing to the first attribute; when querying the edges related to a node, you can start from the pointer pointing to the first edge in the node (such as "Favorites" in the figure above). After obtaining the first edge, you can traverse along the two-way edge linked list related to the specified node (first node or last node) until you find the edge of interest. After finding the specified edge record, you can use the same one-way linked list structure as the node attribute to read the edge attribute, or by checking the start node and end node records associated with its ID.
[0046] Specifically, for N layers and M welds, CBR (Case-Based Reasoning) matching technology is used, with N layers and M welds as case nodes in the welding process knowledge graph to describe the scenario problem and its solution. 1. Similarity calculation: Similarity calculation is one of the key steps in case reasoning in the welding process knowledge graph; the similarity calculation formula is used to measure the similarity between the current problem and historical cases, so as to retrieve the most relevant cases; similarity calculation can be based on multiple features, such as welding methods, materials, parameters and defects; each feature can be represented as a vector, and each feature can have different weights to reflect its importance. (1) Overall similarity: Overall similarity Sim total It can be expressed as the weighted sum of the similarities of each feature:
[0047] P and C represent the feature vectors of the current problem and historical cases respectively. Sim i represents the similarity of the i-th feature, w i is the weight of the i-th feature, and n is the total number of features. (2) Individual feature similarity: welding method similarity, material similarity, and defect similarity use simple equality comparison. Taking welding method as an example:
[0048] Parameter similarity uses weighted Euclidean distance to calculate the Euclidean distance between the current question and the case in the parameter space:
[0049] m is the total number of parameters, w j is the weight of the jth parameter. In order to convert the distance into similarity, the exponential function is used to normalize the distance: d maxis a constant, usually 100, used to normalize the distance so that the similarity value is between [0,1]. 2. Similar case retrieval: Use the query language in the graph database to retrieve historical cases similar to the current problem. The following is the formula principle for retrieving the case most similar to the current problem from the case library: Sim(P, C) is the similarity function between problem P and case C. 3. Case reuse and correction: Extract solutions from the retrieved cases. The solutions usually include welding methods and their parameters.
[0050] C * is the most similar case retrieved, \operatorname{Solution}(C^{*}) is the solution to the most similar case, and Adapt is the process of adjusting the case solution to the current problem. Modify the reused solution and adjust the solution of the historical case according to the specific conditions of the current problem (temperature, humidity, rainfall, etc. of the welding environment).
[0051] Solution (P) is the initial solution obtained after reuse, and Revise is the correction process, which usually includes testing and feedback. Adjustment involves modifying welding parameters or selecting different welding methods, etc. In actual operation, the adjusted solution is tested and verified to ensure its effectiveness and feasibility. 4. Case study update: If the adjusted solution successfully solves the current problem, the new case can be added to the case library for future reuse.
[0052] C is the updated case library, and (P, \text{RevisedSolution}(P)) is the combination of the current problem and its final solution.
[0053] Specifically, the pseudo code for multi-layer and multi-pass welding case matching is:
[0054]
[0055] 'solution':{'method':'MIG Welding','parameters':{'Current':120,'Voltage':18,'Speed':5}}},
[0056] #Other Examples ]
[0058] current_problem={'type':'Porosity','parameters':{'Current':150,
[0059] 'Voltage':20,'Speed':5.5}}
[0060] weights={'Current':0.5,'Voltage':0.3,'Speed':0.2}
[0061] #Search for similar cases
[0062] similar_cases=retrieve_similar_cases(current_problem,
[0063] case_library,weights)
[0064] similar_case=similar_cases[0][0]
[0065] #Extract solution
[0066] retrieved_parameters=get_solution_parameters(similar_case)
[0067] #Adjust the solution
[0068] adjusted_parameters=adjust_parameters(retrieved_parameters,
[0069] current_problem['parameters'])
[0070] #Test and verify
[0071] if test_solution(adjusted_parameters):
[0072] print("The solution is valid")
[0073] #Update the case library
[0074] update_case_library(case_library,current_problem,adjusted_parameters)
[0075] else:
[0076] print("The solution is invalid and needs further adjustment")
[0077] In an optional solution, determining the groove depth of the weldment at the current moment includes: obtaining the groove top width of the weldment at the current moment, and obtaining the groove angle of the weldment; determining the groove depth according to the groove top width, the groove bottom width, and the groove angle. In this embodiment, the groove depth is determined according to the groove top width, the groove bottom width, and the groove angle at the current moment, which ensures that the obtained groove depth is relatively accurate and prepares for the subsequent determination of the total number of layers of the weld.
[0078] Specifically, laser scanning is used to obtain the groove top width and the groove bottom width.
[0079] In an exemplary embodiment, the groove depth is determined according to the groove top width, the groove bottom width and the groove angle, including: using the formula Determine the groove depth, where H N is the groove depth, W N is the width of the top of the groove, w N is the groove bottom width, and θ is the groove angle. In this embodiment, a specific groove depth formula is used to further ensure that the groove depth obtained is relatively accurate, thereby further ensuring that the total number of layers obtained subsequently is relatively accurate, and further ensuring that the target process parameters obtained subsequently are relatively accurate.
[0080] Specifically, N means welding to the Nth layer at the current moment. N It is the groove depth when welding to the Nth layer. The groove depth represents the depth from the bottom of the groove to the top of the groove.
[0081] In other embodiments, obtaining the groove angle of the weldment includes: obtaining the initial groove top width, initial groove bottom width, initial base layer thickness, and initial weldment thickness of the weldment before welding begins; and determining the groove angle according to the initial groove top width, initial groove bottom width, initial base layer thickness, and initial weldment thickness. In this embodiment, the groove angle is determined according to the initial groove top width, initial groove bottom width, initial base layer thickness, and initial weldment thickness before welding begins, thereby ensuring that the obtained groove angle is relatively accurate, thereby further ensuring that the groove depth obtained subsequently is relatively accurate.
[0082] Specifically, the initial groove top width is equal to the groove top width.
[0083] In some other exemplary embodiments, the groove angle is determined according to the initial groove top width, the initial groove bottom width, the initial base layer thickness and the initial weldment thickness, including: using the formula Determine the groove angle, wherein θ is the groove angle, W is the initial groove top width, T is the initial weldment thickness, t is the initial base thickness, and w is the initial groove bottom width. In this embodiment, a specific groove angle formula is used to further ensure that the obtained groove angle is relatively accurate.
[0084] Specifically, when N=1, H1=Tt.
[0085] In some other optional solutions, the total number of layers of the weld to be welded at the current moment is determined according to the groove depth and the thickness of the weld, including: using the formula Determine the total number of layers above, where H N is the groove depth, n is the total number of layers, a is the thickness of the weld, and according to the groove bottom width and the weld width, the total number of welds to be welded at the current moment is determined, including: using the formula Determine the width of the weld, where b is the width of the weld and k is a preset value. is the wire diameter; using the formula Determine the total number of passes, where m is the total number of passes. In this embodiment, a specific total layer number formula is used to further ensure that the total layer number obtained at the current moment is relatively accurate, and a specific total layer number formula is used to further ensure that the total layer number obtained at the current moment is relatively accurate, thereby further ensuring that the target process parameters obtained subsequently are relatively accurate.
[0086] In some further optional schemes, according to the above-mentioned target process parameters, controlling the welding robot to weld the above-mentioned weldment includes: according to the above-mentioned total number of layers and the above-mentioned total number of passes, obtaining the above-mentioned historical welding process parameters of the historical welds corresponding to the number of layers and the number of passes of each of the above-mentioned welds from the above-mentioned target welding process knowledge graph to obtain corrected welding process parameters; correcting the above-mentioned target process parameters according to the above-mentioned corrected welding process parameters; and controlling the above-mentioned welding robot to weld the above-mentioned weldment according to the corrected target process parameters. In this embodiment, according to the total number of layers and the total number of passes, the historical welding process parameters of the historical welds corresponding to the number of layers and the number of passes of each weld are obtained from the target welding process knowledge graph to obtain corrected welding process parameters, and then the target process parameters are corrected according to the corrected welding process parameters, which ensures that the corrected target process parameters are relatively accurate, thereby further ensuring better welding quality.
[0087] In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation process of the multi-layer and multi-pass welding method of the present application will be described in detail below in combination with specific embodiments.
[0088] This embodiment relates to a specific multi-layer multi-pass welding method, wherein the weldment includes a multi-layer multi-pass weld, such as Figure 3 As shown, the following steps are included:
[0089] Step S1: obtaining the initial groove top width, initial groove bottom width, initial base layer thickness and initial weldment thickness before welding of the weldment, and determining the groove angle according to the initial groove top width, initial groove bottom width, initial base layer thickness and initial weldment thickness;
[0090] Step S2: Obtain the groove top width and groove bottom width of the weldment at the current moment, and determine the groove depth according to the groove top width, groove bottom width and groove angle;
[0091] Step S3: determining the total number of layers of welds to be welded at the current moment according to the groove depth and the weld thickness, and determining the total number of passes of welds to be welded at the current moment according to the groove bottom width and the weld width;
[0092] Step S4: updating the welding process knowledge graph according to the total number of layers, the total number of passes and the current welding information to obtain a target welding process knowledge graph, wherein the welding process knowledge graph is a knowledge graph established according to historical welding cases, and the current welding information is information representing the external welding environment at the current moment;
[0093] Step S5: using the target welding process knowledge graph, calculating the similarity between the current welding information and the historical welding information, and determining the historical welding process parameters corresponding to the historical welding information with the highest similarity as the target process parameters, the historical welding information is information characterizing the external welding environment in the historical welding cases, and the historical welding process parameters are parameters characterizing the welding quality in the historical welding cases;
[0094] Step S6: according to the total number of layers and the total number of passes, the historical welding process parameters of the historical welds corresponding to the number of layers and the number of passes of each weld are obtained from the target welding process knowledge graph to obtain the corrected welding process parameters;
[0095] Step S7: Correct the target process parameters according to the corrected welding process parameters, and control the welding robot to weld the weldment according to the corrected target process parameters.
[0096] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0097] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the multi-layer and multi-pass welding method.
[0098] Specifically, the multi-layer multi-pass welding method includes:
[0099] Step S201, obtaining the groove bottom width of the weldment at the current moment, and determining the groove depth of the weldment at the current moment;
[0100] Step S202, determining the total number of layers of the weld to be welded at the current moment according to the groove depth and the thickness of the weld, and determining the total number of passes of the weld to be welded at the current moment according to the groove bottom width and the width of the weld;
[0101] Specifically, the weld to be welded is the weld that has not been welded yet.
[0102] Step S203, updating the welding process knowledge graph according to the total number of layers, the total number of passes and the current welding information to obtain a target welding process knowledge graph, wherein the welding process knowledge graph is a knowledge graph established according to historical welding cases, and the current welding information is information representing the external welding environment at the current moment;
[0103] Step S204, using the target welding process knowledge graph, calculating the similarity between the current welding information and the historical welding information, and determining the historical welding process parameters corresponding to the historical welding information with the highest similarity as the target process parameters, the historical welding information is information characterizing the external welding environment in the historical welding case, and the historical welding process parameters are parameters characterizing the welding quality in the historical welding case;
[0104] Step S205, controlling the welding robot to weld the weldment according to the target process parameters.
[0105] Optionally, determining the groove depth of the weldment at the current moment includes: obtaining the groove top width of the weldment at the current moment, and obtaining the groove angle of the weldment; determining the groove depth based on the groove top width, the groove bottom width and the groove angle.
[0106] Optionally, the groove depth is determined according to the groove top width, the groove bottom width and the groove angle, including: using the formula Determine the groove depth, where H N is the groove depth, W N is the width of the top of the groove, wN is the bottom width of the groove, and θ is the angle of the groove.
[0107] Optionally, obtaining the groove angle of the weldment includes: obtaining the initial groove top width, initial groove bottom width, initial base layer thickness and initial weldment thickness of the weldment before welding begins; and determining the groove angle based on the initial groove top width, initial groove bottom width, initial base layer thickness and initial weldment thickness.
[0108] Optionally, the groove angle is determined according to the initial groove top width, the initial groove bottom width, the initial base layer thickness and the initial weldment thickness, including: using the formula Determine the groove angle, wherein θ is the groove angle, W is the initial groove top width, T is the initial weldment thickness, t is the initial base layer thickness, and w is the initial groove bottom width.
[0109] Optionally, according to the groove depth and the thickness of the weld, determining the total number of layers of the weld to be welded at the current moment comprises: using the formula Determine the total number of layers above, where H N is the groove depth, n is the total number of layers, a is the thickness of the weld, and according to the groove bottom width and the weld width, the total number of welds to be welded at the current moment is determined, including: using the formula Determine the width of the weld, where b is the width of the weld and k is a preset value. is the wire diameter; using the formula Determine the total number of channels, where m is the total number of channels.
[0110] Optionally, according to the above-mentioned target process parameters, controlling the welding robot to weld the above-mentioned weldment, including: according to the above-mentioned total number of layers and the above-mentioned total number of passes, obtaining the above-mentioned historical welding process parameters of the historical welds corresponding to the number of layers and the number of passes of each of the above-mentioned welds from the above-mentioned target welding process knowledge graph, and obtaining corrected welding process parameters; according to the above-mentioned corrected welding process parameters, correcting the above-mentioned target process parameters; according to the above-mentioned corrected target process parameters, controlling the above-mentioned welding robot to weld the above-mentioned weldment.
[0111] The present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement at least the following method steps: step S201, obtaining the groove bottom width of the weldment at the current moment, and determining the groove depth of the weldment at the current moment; step S202, determining the total number of layers of the weld to be welded at the current moment according to the groove depth and the thickness of the weld, and determining the total number of passes of the weld to be welded at the current moment according to the groove bottom width and the width of the weld; step S203, updating the welding process knowledge map according to the total number of layers, the total number of passes and the current welding information to obtain the target welding process knowledge map; The welding process knowledge graph is a knowledge graph established based on historical welding cases, and the current welding information is information characterizing the external welding environment at the current moment. Step S204: using the target welding process knowledge graph, the similarity between the current welding information and the historical welding information is calculated, and the historical welding process parameters corresponding to the historical welding information with the highest similarity are determined as the target process parameters. The historical welding information is information characterizing the external welding environment in the historical welding cases, and the historical welding process parameters are parameters characterizing the welding quality in the historical welding cases. Step S205: according to the target process parameters, the welding robot is controlled to weld the weldment.
[0112] Optionally, determining the groove depth of the weldment at the current moment includes: obtaining the groove top width of the weldment at the current moment, and obtaining the groove angle of the weldment; determining the groove depth based on the groove top width, the groove bottom width and the groove angle.
[0113] Optionally, the groove depth is determined according to the groove top width, the groove bottom width and the groove angle, including: using the formula Determine the groove depth, where H N is the groove depth, W N is the width of the top of the groove, w N is the bottom width of the groove, and θ is the angle of the groove.
[0114] Optionally, obtaining the groove angle of the weldment includes: obtaining the initial groove top width, initial groove bottom width, initial base layer thickness and initial weldment thickness of the weldment before welding begins; and determining the groove angle based on the initial groove top width, initial groove bottom width, initial base layer thickness and initial weldment thickness.
[0115] Optionally, the groove angle is determined according to the initial groove top width, the initial groove bottom width, the initial base layer thickness and the initial weldment thickness, including: using the formula Determine the groove angle, wherein θ is the groove angle, W is the initial groove top width, T is the initial weldment thickness, t is the initial base layer thickness, and w is the initial groove bottom width.
[0116] Optionally, according to the groove depth and the thickness of the weld, determining the total number of layers of the weld to be welded at the current moment comprises: using the formula Determine the total number of layers above, where H N is the groove depth, n is the total number of layers, a is the thickness of the weld, and according to the groove bottom width and the weld width, the total number of welds to be welded at the current moment is determined, including: using the formula Determine the width of the weld, where b is the width of the weld and k is a preset value. is the wire diameter; using the formula Determine the total number of channels, where m is the total number of channels.
[0117] Optionally, according to the above-mentioned target process parameters, controlling the welding robot to weld the above-mentioned weldment, including: according to the above-mentioned total number of layers and the above-mentioned total number of passes, obtaining the above-mentioned historical welding process parameters of the historical welds corresponding to the number of layers and the number of passes of each of the above-mentioned welds from the above-mentioned target welding process knowledge graph, and obtaining corrected welding process parameters; according to the above-mentioned corrected welding process parameters, correcting the above-mentioned target process parameters; according to the above-mentioned corrected target process parameters, controlling the above-mentioned welding robot to weld the above-mentioned weldment.
[0118] An embodiment of the present application also provides an electronic device, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the above-mentioned multi-layer and multi-pass welding methods.
[0119] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.
[0120] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0121] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0122] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0123] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0124] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0125] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0126] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0127] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0128] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:
[0129] In the multi-layer and multi-pass welding method of the present application, the weldment includes multi-layer and multi-pass welds. First, the groove bottom width and groove depth of the weldment at the current moment are obtained, and then the total number of layers of welds to be welded at the current moment is determined according to the groove depth and the thickness of the weld, and the total number of passes of welds to be welded at the current moment is determined according to the groove bottom width and the width of the weld. Then, according to the total number of layers, the total number of passes and the current welding information, the welding process knowledge graph is updated to obtain the target welding process knowledge graph, and then the target welding process knowledge graph is used to calculate the similarity between the current welding information and the historical welding information, and the historical welding process parameters corresponding to the historical welding information with the highest similarity are determined as the target process parameters. Finally, according to the target process parameters, the welding robot is controlled to weld the weldment. Compared with the problem in the prior art that changes in the multi-layer and multi-pass welding process cannot be processed in real time, resulting in inaccurate setting of welding parameters and affecting welding quality, the present application determines the total number of layers of welds to be welded at the current moment according to the thickness of the weld and the groove depth at the current moment, and determines the total number of welds to be welded at the current moment according to the width of the weld and the bottom width of the groove at the current moment, thereby ensuring that the total number of layers and the total number of passes of new welds can be obtained in real time, and then the welding process knowledge graph is updated according to the total number of layers, the total number of passes and the current welding information at the current moment to obtain the target welding process knowledge graph, thereby ensuring that the welding process knowledge graph is updated according to the target welding process knowledge graph, calculating the similarity between the current welding information and the historical welding information using the target welding process knowledge graph, and determining the historical welding process parameters corresponding to the historical welding information with the highest similarity as the target process parameters, thereby ensuring that the obtained target process parameters are more adapted to the real-time changes in the multi-layer and multi-pass welding process, that is, ensuring that the target process parameters are more accurate, thereby ensuring better welding quality.
[0130] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims
1. A multi-layer multi-pass welding method, It is characterized in that The weldment includes a multi-layer multi-pass weld, and the method includes: Obtaining the groove bottom width of the weldment at the current moment, and determining the groove depth of the weldment at the current moment; Determine the total number of layers of the weld to be welded at the current moment according to the groove depth and the thickness of the weld, and determine the total number of passes of the weld to be welded at the current moment according to the groove bottom width and the width of the weld; According to the total number of layers, the total number of passes and the current welding information, the welding process knowledge graph is updated to obtain a target welding process knowledge graph, wherein the welding process knowledge graph is a knowledge graph established according to historical welding cases, and the current welding information is information characterizing the external welding environment at the current moment; Using the target welding process knowledge graph, calculating the similarity between the current welding information and the historical welding information, and determining the historical welding process parameters corresponding to the historical welding information with the highest similarity as the target process parameters, wherein the historical welding information is information characterizing the external welding environment in the historical welding case, and the historical welding process parameters are parameters characterizing the welding quality in the historical welding case; According to the target process parameters, the welding robot is controlled to weld the weldment.
2. The multi-layer multi-pass welding method according to claim 1, It is characterized in that Determining the groove depth of the weldment at the current moment includes: Obtaining the groove top width of the weldment at the current moment, and obtaining the groove angle of the weldment; The groove depth is determined according to the groove top width, the groove bottom width and the groove angle.
3. The multi-layer multi-pass welding method according to claim 2, It is characterized in that Determining the groove depth according to the groove top width, the groove bottom width and the groove angle includes: Using the formula Determine the groove depth, where H N is the groove depth, W N is the width of the groove top, w N is the bottom width of the groove, and θ is the angle of the groove.
4. The multi-layer multi-pass welding method according to claim 2, It is characterized in that Obtaining the groove angle of the weldment, including: Obtaining the initial groove top width, initial groove bottom width, initial base layer thickness, and initial weldment thickness of the weldment before welding begins; The groove angle is determined according to the initial groove top width, the initial groove bottom width, the initial base layer thickness and the initial weldment thickness.
5. The multi-layer multi-pass welding method according to claim 4, It is characterized in that Determining the groove angle according to the initial groove top width, the initial groove bottom width, the initial base layer thickness, and the initial weldment thickness includes: Using the formula Determine the groove angle, where θ is the groove angle, W is the initial groove top width, T is the initial weldment thickness, t is the initial base layer thickness, and w is the initial groove bottom width.
6. The multi-layer multi-pass welding method according to claim 1, It is characterized in that Determining the total number of layers of the weld to be welded at the current moment according to the groove depth and the thickness of the weld includes: using the formula Determine the total number of layers, where H N is the groove depth, n is the total number of layers, a is the thickness of the weld, According to the groove bottom width and the weld width, determining the total number of welds to be welded at the current moment includes: using the formula Determine the width of the weld, where b is the width of the weld and k is a preset value. is the wire diameter; using the formula Determine the total number of channels, where m is the total number of channels.
7. The multi-layer multi-pass welding method according to claim 1, It is characterized in that According to the target process parameters, controlling the welding robot to weld the weldment includes: According to the total number of layers and the total number of passes, the historical welding process parameters of the historical welds corresponding to the number of layers and the number of passes of each weld are acquired from the target welding process knowledge graph to obtain corrected welding process parameters; According to the modified welding process parameters, the target process parameters are modified; According to the corrected target process parameters, the welding robot is controlled to weld the weldment.
8. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the multi-layer and multi-pass welding method according to any one of claims 1 to 7.
9. A computer program product comprising computer instructions, It is characterized in that When the computer instructions are executed by a processor, the multi-layer and multi-pass welding method described in any one of claims 1 to 7 is implemented.
10. An electronic device, It is characterized in that include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing the multi-layer multi-pass welding method described in any one of claims 1 to 7.
Citation Information
Patent Citations
Intersecting line multi-layer multi-pass welding weld joint track real-time planning method
CN107378201A
Welding cost and process parameter comprehensive intelligent recommendation method based on knowledge graph
CN114969553A
Groove welding path planning method and device, electronic equipment and storage medium
CN115351450A
Multi-layer multi-pass welding method and device, processor and welding system
CN118342068A
Cited By
Welding process parameter recommendation method for enhancing large model by using knowledge graph retrieval
CN119578525A
