Welding production monitoring and data analysis system and metal cutting production monitoring and data analysis system and method for identifying and grouping welding or cutting data

Abstract

This refers to a system for monitoring welding production and data analysis, and a system for monitoring metal cutting production and data analysis. These are types of systems and methods that provide pattern recognition and data analysis in welding and cutting. In one embodiment, a system includes a server computer and a data storage device connected to the server computer. The server computer receives welding data, including main welding data and auxiliary welding data, via a computer network from welding systems used to generate multiple welds in order to produce multiple instances of the same type of part. The server computer performs an analysis on the welding data to identify and group identical individual welds among the multiple welds, without relying on weld profile identification numbers as part of the analysis.A group of identical individual welds corresponds to the same weld location in multiple instances of the same part type. The data storage receives the welding data from the server computer and digitally stores the welding data as identified and grouped.

Description

SYSTEM FOR MONITORING WELDING PRODUCTION AND DATA ANALYSIS AND SYSTEM FOR MONITORING METAL CUTTING PRODUCTION AND DATA ANALYSIS, AND METHOD FOR IDENTIFYING AND GROUPING WELDING OR CUTTING DATA FIELD

[001] The embodiments of the present invention relate to systems and methods related to welding and cutting and, more specifically, to systems and methods that provide pattern recognition and data analysis in welding and cutting. BACKGROUND

[002] In a competitive global economy, efficiency is paramount on the factory floor, especially when it comes to overall equipment effectiveness. Well-managed manufacturing shops have become increasingly vigilant about keeping costs under control while striving to achieve higher levels of productivity and quality in all aspects of the operating cycle. Welding and cutting operations are no exception.

[003] Any improvement in the welding and cutting process demands the ability to evaluate and measure successes. There is a desire to increase productivity without increasing costs. While some resort to tools such as automation and other methods that simplify the actual process, simpler tools that allow for the evaluation and analysis of productivity and yield can have a major impact on a company's bottom line.

[004] The welding and cutting industries have access to monitoring tools that enable them to Petition 870250041321, dated 05 / 20 / 2025, page 8 / 79 2 / 46 Any networked welding and cutting power source transmits its performance data. These systems can track metrics and provide analysis down to the level of a single weld or cut performed by a specific operator on a specific welder or cutter during a certain work shift, in order to establish parameters for productivity, support, troubleshooting capabilities, and more.

[005] Over the past decade, solutions have evolved to assist fabrication shops and manufacturers in developing customized tracking solutions based on their needs and core technologies, in order to provide a detailed view of the welding or cutting production environment. While early such programs ran on PCs connected to specific power supplies and lacked remote tracking capabilities, some of today's systems have expanded beyond the limiting desktop environment and automatically move data to the cloud. This makes the concept of 24 / 7 production monitoring, from anywhere in the world, on virtually any device, be it a laptop, smartphone, iPad® or other tablet computer, a functional reality.

[006] Production monitoring allows users at any level of an organization to view relevant live information about each welder or cutter and analyze performance at a highly granular level. These systems also help organizations track preventive maintenance activities and warning signaling issues related to welding or cutting at any station on the production line, allowing engineers to prevent problems. Petition 870250041321, dated 05 / 20 / 2025, page 9 / 79 3 / 46 before they occur.

[007] Although production monitoring solutions were initially designed to focus solely on production metrics, user demands for record retention and other quality assessment support have increased and begun to expand the functionality of these systems. The monitoring technologies themselves have continued to evolve to include a focus on quality metrics. Quality tracking is now a hallmark of any satisfactory production monitoring system. New tools can reliably assess welds created at each station and, while not intended to replace actual quality assurance testing methods, provide a parameter that reflects a high probability of whether the part is good or not.

[008] But that wasn't the only notable evolution in these systems over the past few years. As larger companies with multi-site facilities adopted the technology and the widespread means of mobile communication increased, users began demanding something even more accessible, enabling them to access data not only locally but also globally, instantly from the road or the factory, the welding or cutting station, from any device, without relying on the company's own computer servers and intranet access.

[009] Furthermore, when attempting to analyze welding or cutting data collected with advanced machine learning (ML) algorithms, there is a high degree of difficulty in grouping data for individual welds or cuts. This is difficult because welding or cutting data are generally not Petition 870250041321, dated 05 / 20 / 2025, page 10 / 79 4 / 46 marked from a traceability standpoint. The data source is known, and it is usually easy to record the part number of a part type, but the individual identification of a weld or cut that occurs in a part is generally unknown / unmarked. Furthermore, several welds (or cuts) can easily overlap from a grouping standpoint, since the data parameters are similar, but the welds (or cuts) need to be allocated to different groups.

[0010] The collection of welding information data exists in the Lincoln Electric CheckPoint™ design, which has been available for over 10 years. This system has the capability to select and define weld profiles that serve to uniquely identify welds on a specific part. However, there is a risk that the weld profile identification numbers may be inadvertently reused; this would incorrectly group a dissimilar batch of weld records (welding data for different types of welds). Incorrect identification would cause additional problems with defect detection, traceability, and data grouping for analysis. In another example, the weld profile identification numbers may not be defined or may only be partially defined by the system controller; this would also cause problems with defect detection, traceability, and data grouping. BRIEF DESCRIPTION

[0011] The embodiments of the present invention include systems and methods related to welding and cutting and, more specifically, systems and methods that provide Petition 870250041321, dated 05 / 20 / 2025, page 11 / 79 5 / 46 Pattern recognition and data analysis in welding and cutting.

[0012] In one embodiment, a system for monitoring welding production and data analysis is provided. The system includes at least one server computer that has an analytical component and at least one data storage operationally connected to at least one server computer. The server computer is configured to receive welding data, including main welding data and auxiliary welding data, via a computer network from a plurality of welding systems operationally connected to the computer network and used to generate multiple welds in order to produce multiple instances of the same type of part, with the welding data corresponding to the multiple welds.The server computer is also configured to perform an analysis on the welding data to identify and group identical individual welds among multiple welds, without relying on the weld profile identification numbers received from the plurality of welding systems as part of the analysis. A group of identical individual welds corresponds to the same weld location in multiple instances of the same part type. The data storage is configured to receive the welding data, which corresponds to each individual weld among the identical individual welds, from the server computer and digitally store the welding data as identified and grouped. In one embodiment, the analysis is a cluster analysis. In one embodiment, the system is located remotely from the plurality of welding systems. In one embodiment, the main welding data includes... Petition 870250041321, dated 05 / 20 / 2025, page 12 / 79 6 / 46 data relating to at least one of the following: welding output voltage, welding output current, wire feed speed, arc length, adhesion, contact tip to workpiece distance (CTWD), working angle, travel angle, travel speed, gas flow rate, welding tool movements, wire type, amount of wire used, and deposition rate. In one embodiment, auxiliary welding data includes data relating to pre-inactivity times (i.e., the inactivity time before a weld is initiated). In another embodiment, auxiliary welding data includes data relating to non-welding movements of a welding tool (torch) between consecutive welds on multiple instances of the same workpiece type.In one embodiment, auxiliary welding data includes data related to the temperatures of multiple instances of the same part type after each weld among the multiple welds is generated. In one embodiment, auxiliary welding data includes data related to one or more of the time, day, and date (e.g., when the weld was generated). In one embodiment, the multiple welds are generated robotically by a plurality of welding systems. In one embodiment, the multiple welds are generated by human operators using a plurality of welding systems. In one embodiment, the server computer and data storage are configured as a database system that can be queried for the welding data, as stored, by a client computer operationally connected to the computer network.

[0013] In one embodiment, a system for monitoring metal cutting production and data analysis. Petition 870250041321, dated 05 / 20 / 2025, p. 13 / 79 7 / 46 is provided. The system includes at least one server computer that has an analytical component and at least one data storage device operationally connected to at least one server computer. The server computer is configured to receive cutting data, including main cutting data and auxiliary cutting data, via a computer network from a plurality of metal cutting systems operationally connected to the computer network and used to generate multiple cuts in order to produce multiple instances of the same part type, with the cutting data corresponding to the multiple cuts. The server computer is also configured to perform an analysis on the cutting data to identify and group identical individual cuts among the multiple cuts, without relying on the identification numbers of the cutting profiles received from the plurality of metal cutting systems as part of the analysis.A group of identical individual cuts corresponds to the same cut location in multiple instances of the same part type. The data storage is configured to receive the cut data, which corresponds to each individual cut among the identical individual cuts, from the server computer and digitally store the cut data as identified and grouped. In one embodiment, the analysis is a cluster analysis. In one embodiment, the system is located remotely from the plurality of metal cutting systems. In one embodiment, the main cut data includes data related to at least one of the following: arc voltage, cutting current, various gas pressures, various gas flow rates, initial piercing height, cutting tool working angle, tool travel angle. Petition 870250041321, dated 05 / 20 / 2025, page 14 / 79 8 / 46 of a cut, cutting speed of the cutting tool, distance from the tool to the workpiece, and cutting movements of the cutting tool. In one embodiment, auxiliary cutting data includes data related to pre-idle times (i.e., the idle time before a cut is initiated). In one embodiment, auxiliary cutting data includes data related to non-cutting movements of a cutting tool (torch) between consecutive cuts on multiple instances of the same workpiece type. In one embodiment, auxiliary cutting data includes data related to the temperatures of multiple instances of the same workpiece type after each cut among the multiple cuts is generated. In one embodiment, auxiliary cutting data includes data related to one or more of the time, day, and date (e.g., when a cut was generated). In one embodiment, the multiple cuts are generated robotically by a plurality of metal cutting systems.In one embodiment, multiple cuts are generated by human operators using a plurality of metal cutting systems. In another embodiment, at least one server computer and at least one data storage device are configured as a database system that can be queried for the stored cutting data by a client computer operationally connected to the computer network.

[0014] Several aspects of the general inventive concepts will become readily apparent from the following detailed description of the exemplary embodiments, from the claims and accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The attached drawings, which are here Petition 870250041321, dated 05 / 20 / 2025, page 15 / 79 Figures 9 / 46, incorporated and forming part of the descriptive report, illustrate various embodiments of the disclosure. It will be noted that the element boundaries illustrated (e.g., boxes, groups of boxes, or other formats) in the Figures represent one embodiment of the boundaries. In some embodiments, an element may be designed as multiple elements, or these multiple elements may be designed as one element. In some embodiments, an element shown as an internal component of another element may be deployed as an external component, and vice versa. Furthermore, the elements may not be drawn to scale.

[0016] Figure 1 illustrates a first embodiment of a system architecture that has a system (a server computer and a data storage) that is located, for example, in the cloud remotely from a plurality of welding systems and client computers;

[0017] Figure 2 illustrates a schematic block diagram of an exemplary embodiment of a welding system of the system architecture of Figure 1;

[0018] Figure 3 illustrates a second embodiment of a system architecture that has a system (a server computer and a data storage) that is located, for example, in the cloud remotely from a plurality of metal cutting systems and client computers;

[0019] Figure 4 illustrates a schematic block diagram of an exemplary embodiment of a metal cutting system of the system architecture of Figure 3;

[0020] Figure 5 illustrates an exemplary embodiment of the server computer of Figure 1 or Figure 3, emphasizing a hardware architecture; Petition 870250041321, dated 05 / 20 / 2025, page 16 / 79 10 / 46

[0021] Figure 6 illustrates an exemplary embodiment of the system in Figure 1 and Figure 3, emphasizing a functional component architecture of the server computer;

[0022] Figure 7 is a flowchart of one embodiment of a method for identifying and grouping welding (or cutting) data that correspond to identical individual welds (or cuts) using, for example, the system in Figure 1, in Figure 3 or in Figure 6; and

[0023] Figure 8A and Figure 8B illustrate a part and a table, respectively, providing an example of the method in Figure 7. DETAILED DESCRIPTION

[0024] Instead of having the production monitoring solution hosted on a server at a company location, some embodiments of the present invention can be deployed in the cloud, where data is uploaded to a central server that provides a distinct database for each client. However, other embodiments may not be deployed in the cloud in this way. Cloud-based production monitoring provides a permanent connection whereby data routinely flows from a company's welding or cutting power sources to a secure data center and to any device, for example, via a standard internet browser on a desktop PC or laptop computer, or via mobile applications on a smartphone or tablet computer.

[0025] Cloud-based production monitoring provides a huge advantage over the previous VPN platform, especially for companies with multiple locations, Petition 870250041321, dated 05 / 20 / 2025, p. 17 / 79 11 / 46 providing a simple way to accumulate data from these locations into an easily accessible central database that can be accessed from anywhere.

[0026] Ready-to-use mobile applications for portable devices further simplify the collection and review of information. These dedicated applications, which run through the cloud, provide only the information users want to view at their fingertips. While users are unlikely to attempt to create a detailed report on an iPhone®, a line manager might want to view the performance of a specific machine for troubleshooting while in the shop at their workstation or after hours when they are off-site. Through a mobile application, the necessary relevant information can be obtained without being tied to a desktop computer. Cloud monitoring also eliminates the need to invest in IT manpower and equipment, as local servers are no longer required. No local software installation is necessary.Software maintenance and updates are performed automatically on the cloud server.

[0027] In one embodiment, a user can simply connect the welder or cutter via Ethernet and log in with a unique access name and a secure password. After setup, users can log in and begin tracking welding performance data on any welder or cutter in the system, all of which are identified by their unique serial number. It is basically plug and play using an internet connection.

[0028] Once online, the power supply of Petition 870250041321, dated 05 / 20 / 2025, page 18 / 79 12 / 46 welding or cutting initiates communication with the server, sending data packets at periodic intervals to the cloud database. Thanks to serial number tracking, all welders or cutters in a facility, or even across the entire company in multiple locations, can be found in the cloud. This is done securely through encryption, user authentication, and other security features (e.g., using blockchain technology). A user can use a secure username and password to access relevant data at any time of day.

[0029] Once logged in, users can customize the system interface to suit their own requirements, mirroring the system to the factory floor layout in one or many locations. These systems can also provide different access layers based on role and data dissemination for any user level. For example, senior management may only want the “50,000-foot view” for asset utilization purposes, while production managers and supervisors may focus more closely on things like shift statistics, daily production statistics, and other metrics for analysis and quick decision-making. Production monitoring solutions can assist production-level management in strategically identifying issues such as persistent bottlenecks and help them use this information to develop long-term solutions from a production perspective.

[0030] At the welding / cutting engineer and supervisor level, the data received typically focuses on Petition 870250041321, dated 05 / 20 / 2025, page 19 / 79 13 / 46 Quality. For example, production monitoring can help personnel in these positions track the day, time, and type and use of wire, how much solder metal was used, the wire feed speed, and deposition rates—to name just a few parameters. In short, it can provide all the information about a weld (or cut) that any manufacturing function would need. And it captures it for every weld (or cut) on every machine connected to the system.

[0031] In one embodiment, the system can also track consumable usage and welding wire changes. The consumable type and package size for each welder can be defined so that the level of wire to be consumed can be digitally measured. The monitoring system will then alert a designated individual or individuals, via email, when the wire supply is low.

[0032] Even those involved in welding or cutting operations in the field now have the option of detailed tracking, thanks to the cloud. In the past, connecting a network to a line of welders on a construction site or an oil pipeline project in Alaska was not so simple. With cloud computing, all that is needed is internet access, through a low-cost and readily available mobile access point device such as a MiFi® or others. An important difference, in addition to cloud functionality, is traceability, which can be accessed in full reports from a PC, or in abbreviated form from a mobile device.

[0033] The solutions offer traceability reports, an important consideration for those manufacturers who must, in turn, retain records for Petition 870250041321, dated 05 / 20 / 2025, page 20 / 79 14 / 46 Customer review of welding consumable certifications, maintaining records for quality initiatives and other similar activities. In one mode, three user-defined fields can be tracked - Operator ID, Part ID, and Consumable - in short, who performed the welding, on which part, and with which welding wire spool or package. All of this can be easily viewed on mobile devices or downloaded for record retention.

[0034] From assisting with manufacturing flow tracking and minimizing material movement to examining equipment or operator performance, the monitoring solutions described in this document have gone beyond basic production tracking and metrics to provide detailed, customized analytical insights for all levels of an organization. A centrally located, reliable database helps maintain continuous record retention by capturing relevant audit trail data.

[0035] However, for the data to be useful, whether stored in the cloud or not, the data must be properly collected from the welding (or cutting) systems and properly organized. One embodiment of the present invention is a method for identifying and grouping data (e.g., in the cloud) for individual welds of a part using additional parameters outside the main welding data. Examples include pre-inactivity time (i.e., inactivity time before a weld is started) and / or data related to the non-welding movement of the tool (torch) or workpiece between welds. The use of these Petition 870250041321, dated 05 / 20 / 2025, page 21 / 79 15 / 46 Additional auxiliary welding data along with the main welding data (i.e., the use of two separate categories of welding data) provides an improved method for recognizing a sequential pattern of events (and welds) related to the complete welding / production cycle of a part. By following the sequential pattern for a specific part, individual welds can be identified (e.g., marked for subsequent use by machine learning algorithms) and correctly grouped without the need to explicitly use weld profile identification numbers.

[0036] Another embodiment of the present invention is a method for identifying and grouping data (e.g., in the cloud) for individual cuts in a metal workpiece using additional parameters outside the main cut data. Examples include pre-idle time (i.e., idle time before a cut is initiated) and / or data related to non-cutting movement of the cutting tool or between cuts. The use of this additional auxiliary cut data together with the main cut data (i.e., the use of two separate categories of cut data) provides an improved method for recognizing a sequential pattern of events (and cuts) related to the complete cutting / production cycle of the workpiece.Following the sequential pattern for a specific part, individual cuts can be identified (e.g., marked for subsequent use by machine learning algorithms) and correctly grouped, without the need to explicitly use identification numbers for the cutting profiles.

[0037] The examples and figures in this document are for illustrative purposes only and are not intended to limit Petition 870250041321, dated 05 / 20 / 2025, p. 22 / 79 16 / 46 the present invention, which is limited by the scope and essence of the claims. Now with reference to the drawings, where the displays are intended only to illustrate exemplary embodiments of the present invention and not to limit it, Figure 1 and Figure 3 place embodiments of the present invention in context.

[0038] With reference to Figure 1, Figure 1 illustrates a first embodiment of a system architecture 100 that has a system 110 (including a server computer 114 and a data storage 112) that is located, for example, in the cloud remotely from a plurality of welding systems 200, a client computer (or client computers) 140 (e.g., desktop or laptop-type PCs) and a mobile device (or mobile devices) 150 (e.g., smartphones). In alternative embodiments, the system 110 is not located in the cloud (e.g., the system 110 is located in a manufacturing facility with the welding systems 200). The mobile device (or mobile devices) 150 is also effectively a type of client computer. Therefore, at times in this document, the term “client computer” may be used broadly to refer to any type of client computer.Each welding system 200 (for example, an arc welding system) may include, for example, a power source, a welding tool (torch), a wire feeder, and a robotic subsystem to move the welding tool (torch) or a workpiece to be welded, relative to each other, to perform welds on the workpiece. Alternatively, instead of having a robotic subsystem, a human operator may move the welding tool (torch). Petition 870250041321, dated 05 / 20 / 2025, page 23 / 79 17 / 46 in relation to a workpiece during a welding operation (e.g., a manual welding operation or a semi-automatic welding operation).

[0039] In Figure 1, the welding systems 200, the client computer (or client computers) 140, and the mobile device (or mobile devices) 150 communicate with the system 110 via a computer network 120. According to one embodiment, the computer network 120 is the Internet, and the system 110 is located remotely from the welding systems 200, the client computer (or client computers) 140, and the mobile device (or mobile devices) 150 in the cloud. According to other embodiments, the computer network 120 may be, for example, a local area network (LAN), a wide area network (WAN), or some other type of computer network that is suitable for the environment (e.g., the cloud, a campus, or a manufacturing facility) in which the system 110 exists with respect to the welding systems 200, the client computers 140, and the mobile devices 150.Furthermore, the 120 computer network can be wired, wireless, or some combination thereof, according to various modalities. According to one modality, the 200 welding systems connect to the 120 computer network via an Ethernet connection.

[0040] As discussed in more detail later in this document, in one embodiment, the server computer 114 is configured to receive welding data from the welding systems 200 via the computer network 120, analyze the welding data, and store the analysis results (e.g., aggregated welding data) in the data storage 112. Furthermore, in a Petition 870250041321, dated 05 / 20 / 2025, page 24 / 79 In this embodiment, the server computer 114 is configured to receive client requests for data from the client computer (or client computers) 140 and the mobile device (or mobile devices) 150, retrieve the requested data from the data storage 112, and provide the requested data to the client computer (or client computers) 140 and the mobile device (or mobile devices) 150 via the computer network 120. In this embodiment, the server computer 114 and the data storage 112 can be configured as a database system that can be queried for welding data, as stored, by a client computer 140 or mobile device 150 operationally connected to the computer network 120.

[0041] Figure 2 illustrates a schematic block diagram of an exemplary embodiment of a welding system 200 of the system architecture 100 of Figure 1 operationally connected to a consumable wire electrode 272. The welding system 200 includes a switching power source 205 which has a power conversion circuit 210 and a bridge switching circuit 280 that provides welding output power between the wire 272 and a workpiece part 274 to melt the wire 272 during welding, forming an arc between the wire 272 and the workpiece 274. The power conversion circuit 210 may be of the transformer type, based on a half-bridge output topology. For example, the power conversion circuit 210 may be of the inverter type which includes an input power side and an output power side, for example, as outlined by the primary and secondary sides, respectively, of a welding transformer. Petition 870250041321, dated 05 / 20 / 2025, page 25 / 79 19 / 46 Other types of power conversion circuits are also possible, such as, for example, a pulsed type that has a DC output topology. The welding system 200 may also include an optional bridge switching circuit 280 that is operationally connected to the power conversion circuit 210 and is configured to switch one direction of the welding output current polarity (e.g., for AC operation).

[0042] The welding system 200 also includes a waveform generator 220 and a controller 230. The waveform generator 220 generates welding waveforms at the command of the controller 230. The waveform generated by the waveform generator 220 modulates the output of the power conversion circuit 210 to produce the output current between the wire 272 and the workpiece part 274. The controller 230 also commands the switching of the bridge switching circuit 280 and can provide control commands to the power conversion circuit 210.

[0043] In one embodiment, the welding system also includes a voltage feedback circuit 240 and a current feedback circuit 250 to monitor the current and output voltage of the welding wire. 272 and the workpiece part 274 and provide the monitored current and voltage back to the controller 230 as main welding data. The feedback voltage and current can be used by the controller 230 to make decisions regarding the modification of the welding waveform generated by the waveform generator 220 and / or to make other decisions affecting the operation of the welding system 200, for example.

[0044] According to one modality, the source of Petition 870250041321, dated 05 / 20 / 2025, p. 26 / 79 The 20 / 46 switching power supply 205, the waveform generator 220, the controller 230, the voltage feedback circuit 240, the current feedback circuit 250, and the network interface 260 constitute a welding power supply. The welding system 200 may also include a wire feeder 270 that feeds consumable metal wire 272 towards the workpiece part 274 through the welding tool (torch) (not shown) at a selected wire feed rate (WFS), according to an embodiment. The wire feeder 270, the consumable metal wire 272, and the workpiece part 274 are not part of the welding power supply, but may be operationally connected to the power supply via one or more output cables, for example.

[0045] According to one embodiment, the controller 230 measures, calculates, and collects various types of welding data from the welding system 200 for each weld created, including main welding data and auxiliary welding data. Techniques for measuring, calculating, and collecting various types of main welding data are well known in the art. Auxiliary welding data may include data related to the parameters of one or more of, for example, welding output voltage, welding output current, wire feed speed, arc length, adhesion, contact tip to workpiece distance (CTWD), working angle, travel angle, travel speed, gas flow rate, welding movements of the welding tool (torch), wire type, amount of wire used, and deposition rate. Such main welding parameters are well known in the art. Petition 870250041321, dated 05 / 20 / 2025, page 27 / 79 21 / 46

[0046] Auxiliary welding data may include data related to, for example, pre-inactivity times (i.e., the inactivity time before a weld is initiated), non-welding movements of a welding tool (torch) between consecutive weld generation on a workpiece, temperatures of a workpiece after each weld, time, day, and date. Other types of primary welding data and auxiliary welding data are also possible, according to other modalities. For example, other data may include operator ID, workpiece ID, consumable coil type, or packaging type.

[0047] Data relating to pre-inactivity times (i.e., the inactivity time before a weld is initiated) can be generated, for example, by a set of timer circuits (not shown) in the controller 230, according to one embodiment, based on moments when the data relating to the welding output current and voltage do not indicate that a weld is being generated, for example. Data relating to movements of a welding tool (torch) during welding or non-welding movements of a welding tool (torch) between the generation of consecutive welds on a workpiece can be generated, for example, by a gyroscope, an accelerometer or some other type of inertial measurement unit (not shown) fixed to or integrated into the welding tool (torch) and operationally connected to the controller 230, according to various embodiments.Data relating to the temperatures of a part after each weld can be generated, for example, by an infrared sensor (not shown) or some other type of temperature sensor of the welding system 200 connected in mode. Petition 870250041321, dated 05 / 20 / 2025, page 28 / 79 22 / 46 operational to controller 230, according to various modalities.

[0048] Network interface 260 (e.g., an Ethernet interface in one embodiment) is configured to obtain main welding data and auxiliary welding data from controller 230 for each weld generated on a part by welding system 200, and to communicate the main welding data and auxiliary welding data via computer network 120 (e.g., the Internet) to system 110 (e.g., the cloud). In this way, system 110 has the capability to collect welding data (main and auxiliary) from each welding system 200 of the system architecture 100 for analysis. According to one embodiment, network interface 260 is part of controller 230.

[0049] Similar to Figure 1, Figure 3 illustrates a second embodiment of a system architecture 300 that has a system 110 (including a server computer 114 and a data storage 112) that is located, for example, in the cloud remotely from a plurality of metal cutting systems 400, a client computer (or client computers) 140 (e.g., desktop or laptop PCs) and a mobile device (or mobile devices) 150 (e.g., smartphones). In alternative embodiments, the system 110 is not located in the cloud (e.g., the system 110 is located in a manufacturing facility with the cutting systems 400). The mobile device (or mobile devices) 150 is also effectively a type of client computer. Therefore, at times in this document, the term “client computer” may be used broadly to refer to any type of computer. Petition 870250041321, dated 05 / 20 / 2025, page 29 / 79 23 / 46 customer. Each 400 metal cutting system (e.g., a plasma cutting system) may include, for example, a power supply, a cutting tool (torch), and a robotic subsystem to move the cutting tool (torch) or a workpiece relative to each other to perform cuts on the metal workpiece. Alternatively, instead of having a robotic subsystem, a human operator may move the cutting tool (torch) relative to a metal workpiece during a cutting operation (e.g., a manual cutting operation).

[0050] In Figure 3, the metal cutting systems 400, the client computer (or client computers) 140 and the mobile device (or mobile devices) 150 communicate with the system 110 via a computer network 120. According to one embodiment, the computer network 120 is the Internet and the system 110 is located remotely from the cutting systems 400, the client computer (or client computers) 140 and the mobile device (or mobile devices) 150 in the cloud. According to other embodiments, the computer network 120 may be, for example, a local area network (LAN), a wide area network (WAN), or some other type of computer network that is suitable for the environment (e.g., the cloud, a campus, or a manufacturing facility) in which the system 110 exists in relation to the cutting systems. 400, to client computers 140 and mobile devices 150. Furthermore, the computer network 120 can be wired, wireless, or some combination thereof, according to various embodiments. According to one embodiment, the metal cutting systems 400 connect to the computer network 120 via an Ethernet connection.

[0051] As discussed in more detail Petition 870250041321, dated 05 / 20 / 2025, page 30 / 79 24 / 46 later in this document, in one embodiment, the server computer 114 is configured to receive cutting data from the metal cutting systems 400 via the computer network 120, analyze the cutting data, and store the analysis results (e.g., grouped cutting data) in the data storage 112. Furthermore, in another embodiment, the server computer 114 is configured to receive client requests for data from the client computer (or client computers) 140 and the mobile device (or mobile devices) 150, retrieve the requested data from the data storage 112, and provide the requested data to the client computer (or client computers) 140 and the mobile device (or mobile devices) 150 via the computer network 120.In this mode, the server computer 114 and the data storage 112 are configured as a database system that can be queried for cutting data, as stored, by a client computer 140 or mobile device 150 operationally connected to the computer network 120.

[0052] Figure 4 illustrates a schematic block diagram of an exemplary embodiment of a metal cutting system 400 of the system architecture 300 of Figure 3. The metal cutting system 400 includes a computer numerical control (CNC) device 401 that can control the overall operation of the cutting process and system 400. In one embodiment, the CNC 401 is configured, used, and constructed in accordance with known automated systems and need not be described in detail in this document. The system 400 includes a power source 403 that supplies the cutting current to the torch 450 (cutting tool) to generate the arc of Petition 870250041321, dated 05 / 20 / 2025, p. 31 / 79 25 / 46 plasma for cutting. As is generally known, the CNC 401 can control the power source 403 to provide the desired output through the power line 425 at the desired time in the cutting operation. The embodiments of the present invention are not limited by the design and construction of the power source 403, which can be constructed in a manner consistent with known power sources. Additionally, the system 400 includes a gas console 405 which can normally be constructed similarly to known gas consoles and includes gas lines and valves to distribute the gases required for the cutting tool (torch) 450. In the embodiment shown, the console has four gas lines fed from sources (not shown), such as tanks. As shown, there is an air line 409, a nitrogen line 411, an oxygen line 413 and a cutting gas line 415.These gases can be used to create the cutting plasma, and air, nitrogen, and oxygen can be used for shielding. These gases are used, and combined, to provide a shielding gas and a plasma gas to the torch. The mixing and use of these gases are generally known and do not need to be discussed in detail in this document. As shown, the gas lines feed a 417 pipe which may contain a plurality of valves (not shown) that control the flow and mixing of the gases. Each of these valves may be electronically controlled, so that it can be controlled by means of a controller, such as a DSP 407 digital signal processor. The DSP receives control signals from the controller / CNC 401 and thus the flow of the respective gases can be controlled. In some exemplary embodiments, the controller / CNC 401 can be used to select the types. Petition 870250041321, dated 05 / 20 / 2025, page 32 / 79 26 / 46 of gas is required, and flow control is managed by the DSP. As shown, as an outlet of pipe 417, there is a shielding gas line 421 and a plasma gas line 423 that feed the torch 450 with each of these respective gas mixtures. Additionally, as shown in Figure 4, in some exemplary embodiments, there is a plurality of pressure sensors (such as pressure transducers) positioned on and / or inside pipe 417, so that the respective pressures of each of the lines (inlet and outlet) can be detected and signaled to the DSP 407, and ultimately to the controller 401.

[0053] For example, in some exemplary embodiments, the inlet gas lines 409, 411, 413 and 415 each have a pressure sensing device 410, 412, 414 and 416, respectively, which detects the inlet gas pressure at the console and / or piping. This pressure data can be used by the CNC / controller 401 to ensure that an adequate inlet pressure is achieved. For example, a specific cutting operation may require a certain amount of pressure / flow from each of the respective gas sources, and the controller 401 uses the pressure sensing from each of these sensors to ensure that adequate pressure / flow from the gas sources is available.

[0054] Additionally, as shown in exemplary embodiments of the present invention, each of the upstream ends of the shielding gas and plasma lines (421 and 423, respectively) may have pressure sensors 419 and 420 to detect the initial pressure in each of these lines. This pressure data is also transmitted by Petition 870250041321, dated 05 / 20 / 2025, page 33 / 79 27 / 46 means of the DSP 407 to the controller 401, wherein the controller 401 can, again, use this detected pressure data to ensure that an adequate gas flow is supplied to the torch. That is, the controller 401 can use this pressure data to control each of the respective flow control valves (not shown) to ensure that the adequate gas flow / pressure is achieved for any given cutting operation. Thus, instead of using an open-loop control methodology or a closed-loop feedback limited only to the gas console feedback, the embodiments of the present invention can use a closed-loop feedback control methodology, wherein the captured pressure is used by the controller to ensure that a desired amount of gas pressure and / or flow is supplied to gas lines 421 and 423.The 401 controller would control the valves to achieve the desired gas flow for a given cutting operation and / or a given state in a cutting operation (e.g., purging, drilling, cutting, withdrawal, etc.).

[0055] As shown, each of the shielding and plasma gases is directed to a cutting tool assembly (torch) 450. The torch assembly 450 can be constructed similarly to known plasma cutting tools (torches), including liquid-cooled plasma cutting tools (torches) used, for example, in mechanized plasma cutting operations. Since the construction of such tools (torches) is commonly known, a detailed discussion of their function and construction is not included in this document. However, unlike known tools (torches), the Petition 870250041321, dated 05 / 20 / 2025, page 34 / 79 28 / 46 tool (torch) sets of one embodiment of the present invention include pressure sensors that detect gas pressures at different locations in the tool (torch) 450. These detected pressures are, again, used by the DSP 407 and / or controller 401 to control the gas flow to the tool (torch) 450.

[0056] For example, as shown in an exemplary embodiment of the present invention, pressure sensors 451 (shielding gas) and 453 (plasma gas) can be used to detect the pressure of the gas flowing into the torch assembly. For example, these sensors 451 / 453 can be located at the upstream end of the torch assembly 450 to detect the pressure of the gases as they enter the torch 450. The sensors can be located at the gas connections of the gas lines to the torch body assembly, or they can be located between the torch body assembly and the torch head assembly. The pressure sensors must be of a type that can fit into the gas lines and / or connections and not obstruct the gas flow so that the flow or operation of the torch is compromised. These sensors can then be used by controller 401 to detect a pressure drop, if any, from console 405 to torch 450.

[0057] Additionally, as shown, in Figure 4, the torch assembly includes at least one protective cap 454, a nozzle 455, and an electrode 456. Obviously, the torch assembly may also contain other components, such as a rotating ring, a retaining cap, etc. As shown, the torch assembly 450 contains additional pressure sensors (e.g., transducers) to capture Petition 870250041321, dated 05 / 20 / 2025, page 35 / 79 29 / 46 the pressure of the torch gases at different locations in the torch 450. For example, as shown, a sensor 457 is located on an inner surface of the protective cover to detect the shielding gas pressure during operation, and a plasma chamber pressure gauge 458 is located in the cavity between the nozzle 455 and the electrode 456 to detect the plasma gas pressure in the plasma gas chamber. These sensors 457 / 458 provide the captured pressure data to the DSP 407 and / or the controller 401, so that the controller 401 can use the captured pressure to monitor the operation of the cutting process / torch and provide dynamic control of the cutting operation based on the detected pressures.

[0058] According to one embodiment, the controller 401 measures, calculates, and collects various types of cutting data from the metal cutting system 400 for each cut created, including main cutting data and auxiliary cutting data. Techniques for measuring, calculating, and collecting various types of main cutting data are well known in the art. Main cutting data may include data related to the parameters of one or more of, for example, arc voltage, cutting current, various gas pressures, various gas flow rates, initial piercing height, working angle of the cutting tool (torch), displacement angle of the cutting tool (torch), cutting speed of the cutting tool (torch), distance of the tool (torch) to the workpiece, and cutting movements of the cutting tool (torch). Such main cutting parameters are well known in the art.

[0059] Ancillary cutoff data may include data relating to, for example, pre-inactivity times. Petition 870250041321, dated 05 / 20 / 2025, page 36 / 79 30 / 46 (i.e., the downtime before a cut is initiated), non-cutting movements of a cutting tool (torch) between the generation of consecutive cuts on a workpiece, temperatures of a workpiece after each cut, time, day, and date. Other types of primary cutting data and auxiliary cutting data are also possible, according to other modalities. For example, other data may include operator ID and workpiece ID.

[0060] Data relating to pre-inactivity times (i.e., the inactivity time before a cut is initiated) can be generated, for example, by a set of timer circuits (not shown) in the 401 controller, according to one embodiment, based on moments when the data relating to arc voltage and / or cutting current do not indicate that a cut is being generated, for example. Data relating to non-cutting movements of a cutting tool (torch) between the generation of consecutive cuts on a workpiece can be generated, for example, by a gyroscope, an accelerometer or some other type of inertial measurement unit (not shown) fixed to or integrated into the cutting tool (torch) and operationally connected to the 401 controller, according to various embodiments.Data relating to the temperatures of a workpiece after each cut can be generated, for example, by an infrared sensor (not shown) or some other type of temperature sensor of the metal cutting system 400 connected operationally to the controller 401, according to various modes.

[0061] The 400 metal cutting system includes a 460 network interface operationally connected to the 401 controller, according to one embodiment. The interface of Petition 870250041321, dated 05 / 20 / 2025, page 37 / 79 Network 460 (e.g., an Ethernet interface in one embodiment) is configured to obtain the main cutting data and auxiliary cutting data from controller 401 for each cut generated on a workpiece by the metal cutting system 400, and to communicate the main cutting data and auxiliary cutting data via computer network 120 (e.g., the Internet) to system 110 (e.g., the cloud). In this way, system 110 has the capability to collect cutting data (main and auxiliary) from each metal cutting system 400 of the system architecture 100 for analysis. According to one embodiment, network interface 460 is part of controller 401.

[0062] Figure 5 illustrates an exemplary embodiment of the server computer 114 of Figure 1 and Figure 3, emphasizing a hardware architecture. The server computer 114 includes at least one processor 514 that communicates with various peripheral devices through a bus subsystem 512. These peripheral devices may include a storage subsystem 524, including, for example, a memory subsystem 528 and a file storage subsystem 526, user interface input devices 522, user interface output devices 520, and a network interface subsystem 516. The input and output devices allow user interaction with the server computer 114. The network interface subsystem 516 provides an interface to external networks (e.g., the Internet) and is coupled to corresponding interface devices in other computer systems.For example, the 230 controller of the 200 welding system and the 401 controller / CNC of the 400 metal cutting system can. Petition 870250041321, dated 05 / 20 / 2025, page 38 / 79 32 / 46 share one or more characteristics with the server computer 114 and may be, for example, a conventional computer, a digital signal processor and / or other computing device.

[0063] User interface input devices 522 may include a keyboard, pointing devices such as a mouse, trackball, touch-sensitive keyboard, or graphic tablet computer, a scanner, a touch-sensitive screen embedded in the display, audio input devices such as voice recognition systems, microphones, and / or other types of input devices. In general, the use of the term “input device” is intended to include all possible types of devices and ways of entering information into the server computer 114 or into a communication network.

[0064] User interface output devices 520 may include a display subsystem, a printer, a fax machine, or non-visual displays such as audio output devices. The display subsystem may include a cathode ray tube (CRT), a flat panel device such as a liquid crystal display (LCD), a projection device, or some other mechanism for creating a visible image. The display subsystem may also provide non-visual display, such as through audio output devices. In general, the use of the term “output device” is intended to include all possible types of devices and forms for emitting information from the server computer 114 to the user or to another machine or computer system.

[0065] Storage subsystem 524 stores Petition 870250041321, dated 05 / 20 / 2025, page 39 / 79 33 / 46 programming constructs that provide or support some or all of the functionalities described in this document (for example, as software modules / components). For example, storage subsystem 524 may include analytical software modules (for example, a cluster analysis module) to identify and group welds and cuts.

[0066] Software modules are generally executed by the 514 processor in isolation or in combination with other processors. The 528 memory used in the storage subsystem may include various memories, including a main random access memory (RAM) 530 for storing instructions and data during program execution and a read-only memory (ROM) 532 in which fixed instructions are stored. A 526 file storage subsystem may provide persistent storage for program files and data and may include a hard disk drive, a floppy disk drive along with associated removable media, a CD-ROM drive, an optical drive, or removable media cartridges. Modules that implement the functionality of certain modes may be stored by the 526 file storage subsystem in the 524 storage subsystem or on other machines accessible by the 514 processor(s).

[0067] According to some embodiments, the data storage 112 of Figure 1 and Figure 3 may have elements similar to the elements of the storage subsystem 524 of Figure 5. The information in data storage 112 may be stored in a variety of data structures, including, for example, lists, arrays Petition 870250041321, dated 05 / 20 / 2025, page 40 / 79 34 / 46 and / or databases. In addition, the information stored in data storage 112 may include one or more of the following: data stored in a relational database, data stored in a hierarchical database, text documents, graphic images, audio information, video transmissions, and other information associated with welding or cutting.

[0068] The 512 bus subsystem provides a mechanism to allow the various components and subsystems of the server computer 114 to communicate with each other as intended. Although the 512 bus subsystem is shown schematically as a single bus, alternative embodiments of the bus subsystem may use multiple buses.

[0069] Due to the constantly changing nature of computing and networking devices, the description of the server computer 114 shown in Figure 5 is intended only as a specific example to illustrate some modalities. Many other configurations of the server computer 114 are possible, having more or fewer components than the server computer shown in Figure 5.

[0070] Figure 6 illustrates an exemplary embodiment of the system 110 of Figure 1 and Figure 3, emphasizing a functional component architecture of the server computer 114. In Figure 6, the server computer 114 includes an analytical component 610, a security component 620, a query component 630, a search component 640, and a filter component 650. According to one embodiment, these components are software components or software modules that are executed, for example, by Petition 870250041321, dated 05 / 20 / 2025, page 41 / 79 35 / 46 processor (or processors) 514 of Figure 5.

[0071] Security component 620 is configured to establish a secure connection between a welding system, a cutting system, a client computer, and / or their users. Additionally, security component 620 is configured to establish access rights for a welding system, a cutting system, a client computer, and / or their users. Given that welding or cutting data can be transferred over public networks, such as the Internet, security component 620 can provide encrypted data communication along with authentication and authorization services between system 110 and a welding system, a cutting system, or a client computer. Such encryption, authentication, and authorization techniques are well-known and can be applied to the server computer 114. For example, document no. US 8,224,881, which is incorporated herein by reference, elaborates on such techniques.

[0072] Query component 630 is configured to assist a user in formulating search criteria to be used by search component 640 to locate welding data or cutting data, as stored, in data storage 112. Once a query has been formulated, search component 640 searches data storage 112 based on information received from a client computer and the search criteria formulated using query component 630. For example, in one embodiment, query component 630 can be adapted to extract welding information or cutting information from a user query (e.g., based on input Petition 870250041321, dated 05 / 20 / 2025, page 42 / 79 36 / 46 of natural language). Such query techniques are well known and can be applied on server computer 114. For example, document no. US 8,224,881, which is incorporated herein by reference, elaborates on such techniques. In response to receiving a query from query component 630, search component 640 searches for welding information or cutting information. Search component 640 can employ various techniques (e.g., based on a Bayesian model, an artificial intelligence model, probability tree networks, fuzzy logic, and / or neural network) when searching for welding or cutting data. Such search techniques are well known and can be applied on server computer 114. For example, document no. US 8,224,881, which is incorporated herein by reference, elaborates on such techniques.

[0073] Filter component 650 is configured to filter the results of search component 640 to facilitate the preparation of datasets to be used as input data in, for example, a machine learning (ML) algorithm. The filtering is based, at least in part, on information received from the client computer requesting the search. For example, in one embodiment, filter component 650 can filter search results in preparation for use by an ML algorithm that is configured to operate on input data to, for example, track preventive maintenance activities and warning signaling issues related to welding or cutting at any station on a production line, allowing engineers to prevent problems before they occur. Such filtering techniques are well known and can be applied on the server computer. Petition 870250041321, dated 05 / 20 / 2025, page 43 / 79 37 / 46 114. For example, document no. US 8,224,881, which is incorporated herein by reference, elaborates on such techniques. According to one embodiment, the analytical component 610 of the server computer 114 may implement the ML algorithm. Alternatively, the ML algorithm may be implemented on the client computer, for example.

[0074] However, according to one embodiment, the analytical component 610 is configured to perform a data preprocessing analysis before storing the data in the data store 112 and therefore before a client computer connects to the system 110 and searches for the data stored in the data store 112. As indicated earlier in this document, when attempting to analyze the collected welding or cutting data with advanced machine learning (ML) algorithms, there is a high degree of difficulty in grouping data for individual welds or cuts. This is difficult because welding or cutting data are generally not tagged from a traceability standpoint. The data source is known, and it is usually easy to record the part number of a part type, but the individual identification of a weld or cut that occurs on a part is usually unknown / untagged.Furthermore, several welds (or cuts) can easily overlap from a grouping perspective, since the data parameters are similar, but the welds (or cuts) need to be allocated to different groups. Therefore, in one embodiment, the analytical component 610 of the server computer 114 is configured to perform an analysis on the welding (or cutting) data to identify and group identical individual welds (or cuts) produced in multiples. Petition 870250041321, dated 05 / 20 / 2025, page 44 / 79 38 / 46 instances of the same type of part, without relying on the identification numbers of the weld profiles (or identification numbers of the cutting profiles) as part of the analysis, as discussed below in this document.

[0075] Figure 7 is a flowchart of an embodiment of a method 700 for identifying and grouping welding (or cutting) data that correspond to identical individual welds (or cuts) using, for example, system 110 in Figure 1, Figure 3 or Figure 6. In step 710 of method 700, a server computer 114, which has an analytical component 610, receives welding (or cutting) data, including main welding (or cutting) data and auxiliary welding (or cutting) data, via a computer network 120 from multiple welding (or cutting) systems 200 (or 400) operationally connected to the computer network 120 and used to generate multiple welds (or cuts) to produce multiple instances of the same part type. The welding (or cutting) data correspond to the multiple welds (or cuts). The multiple instances of the same part type may be, for example, multiple instances of a truss for a bridge.

[0076] In block 720 of method 700, server computer 114 performs an analysis on the welding (or cutting) data to identify and group identical individual welds (or cuts) among multiple welds (or cuts), without relying on the identification numbers of the weld (or cut) profiles as part of the analysis. A grouping of identical individual welds (or cuts) corresponds to the same weld (or cut) location in multiple instances of the same part type. Petition 870250041321, dated 05 / 20 / 2025, page 45 / 79 39 / 46

[0077] A weld (or cut) profile identification number is a numerical value that ideally identifies individual welds (or cuts) that correspond to the same location in multiple instances of the same part type. However, as discussed earlier in this document, weld (or cut) profile identification numbers can be inadvertently reused, resulting in the incorrect grouping of a dissimilar batch of weld (or cut) records (welding or cut data for different types of welds or cuts). Incorrect identification would cause additional problems with defect detection, traceability, and data grouping for later analysis. In another example, weld (or cut) profile identification numbers may not be defined or may only be partially defined by the system controller. This again would cause problems with defect detection, traceability, and data grouping.In method 700, the use of two different categories of data (i.e., auxiliary welding (or cutting) data along with primary welding (or cutting) data) allows for the correct grouping of welds (or cuts), without the use of or reliance on profile identification numbers or any other type of index that might attempt to specifically identify a particular weld (or cut) location on a part.

[0078] In block 730 of method 700, a data storage device 112 receives the welding (or cutting) data, which corresponds to each individual weld (or cut) among identical individual welds (or cuts), from the server computer 114 and digitally stores the welding (or cutting) data as identified and grouped. Petition 870250041321, dated 05 / 20 / 2025, page 46 / 79 40 / 46 In this way, the welding (or cutting) data originally received from the welding (or cutting) systems were effectively pre-processed and stored in a way that makes them more useful for further processing, for example, by machine learning (ML) algorithms. Such ML algorithms can be used, for example, to analyze welding (or cutting) performance and to schedule and track preventive maintenance activities.

[0079] According to one embodiment, the analysis performed in block 720 of method 700 includes a cluster analysis that appropriately groups data related to welds (or cuts) that correspond to the same location in multiple instances of the same type of part to be manufactured. The use of auxiliary welding (or cutting) data together with the main welding (or cutting) data in the cluster analysis greatly improves the probability that correct groupings of welding (or cutting) data will be formed.

[0080] In general, cluster analysis is a type of classification analysis that groups sets of data (e.g., data corresponding to objects) in such a way that the elements of the resulting groups (or clusters) are more similar to each other than to the elements in other groups. Cluster analysis algorithms are used to perform cluster analysis. Some types of cluster analysis algorithms include connectivity-based clustering algorithms, centroid-based clustering algorithms, distribution-based clustering algorithms, and density-based clustering algorithms. Such types of cluster analysis algorithms are well known in the technique of Petition 870250041321, dated 05 / 20 / 2025, page 47 / 79 41 / 46 Cluster analysis. Other types of clustering algorithms may also be possible.

[0081] Figures 8A and 8B illustrate a part 800 and a table 850, respectively, providing an example of method 700 of Figure 7. With reference to Figure 8A, one type of part that was manufactured includes four (4) welds, including a first weld 810, a second weld 820, a third weld 830 and a fourth weld 840. Part type 800 can be, for example, a metal frame structure that has four (4) sides that have been welded together at the corners of the resulting frame structure. Multiple instances of the same part type 800 can be produced in the same way, generating four (4) welds.

[0082] Figure 8B shows a table 850 of data corresponding to the four (4) welds for four (4) of the same type of part 800 that were manufactured. There are eight (8) rows of data in table 850. According to one embodiment, the data that are actually sent to system 110 for each instance of a weld are the weld number, voltage, amperage (current), and pre-idle time. The weld number simply indicates an individual weld, but does not provide any other indication of which weld it is. Furthermore, no weld profile identification number is provided that corresponds to the weld locations on the part. The voltage is the welding output voltage used to produce the weld, and the amperage is the welding output current used to produce the weld. The voltage and amperage constitute the main welding data.

[0083] However, if only the main welding data (voltage and amperage) are processed in the analysis Petition 870250041321, dated 05 / 20 / 2025, page 48 / 79 42 / 46 of clustering, the cluster analysis would generate only two (2) groups of welds...a first group of welds that has a voltage of 24.0 volts and an amperage of 200 amperes, and a second group of welds that has a voltage of 26.5 volts and an amperage of 350 amperes. However, it is known from Figure 8A (and the part weld ID column of Figure 8B which is not sent to system 110) that part 800 actually has four (4) different welds (810, 820, 830 and 840) that correspond to the four (4) different weld locations. Therefore, the clustering would be incorrect and misleading for subsequent algorithms (e.g., ML algorithms) that use these incorrect weld data clusterings.

[0084] However, by adding the auxiliary welding data for pre-inactivity time, the cluster analysis would be able to correctly discern and group the four (4) different welds. As previously discussed in this document, pre-inactivity time is the inactivity time before a weld (or cut) is started. As shown in Figure 8B, Table 850 includes welding data for the four (4) different welds of at least two (2) different parts of the same type (i.e., part type 800). Therefore, by including the auxiliary welding data for pre-inactivity time, the cluster analysis would correctly form four (4) groups (clusters) of the identical individual welds.In Table 850 of Figure 8B, the first group (cluster) is indicated by a part weld ID of 1, the second group (cluster) is indicated by a part weld ID of 2, the third group (cluster) is indicated by a part weld ID of 3, and the fourth group (cluster) is indicated by a part weld ID of 4. Petition 870250041321, dated 05 / 20 / 2025, page 49 / 79 43 / 46 although these part weld IDs are not part of the weld data actually sent to system 110 for analysis.

[0085] In this way, suitable groups (groupings) of welding data (or cutting data) for the same weld locations (or cutting locations) on a part can be achieved without the use of profile identification numbers sent, for example, by welding systems 200 (or cutting systems 400). Furthermore, depending on other parameters (e.g., data timestamps) entered into system 110 from welding systems 200 (or cutting systems 400), analysis (e.g., a type of pattern recognition analysis) can be performed on the main data and auxiliary data, along with the other parameters (also considered auxiliary data), to properly determine a sequence (i.e., an order in time) in which the multiple welds (or cuts) on a specific part were generated.

[0086] As discussed earlier in this document, for welding, key welding data may include one or more of the following: welding output voltages, welding output currents, wire feed speeds, arc lengths, tacks, contact tip-to-workpiece distances (CTWD), working angles, travel angles, travel speeds, gas flow rates, welding tool (torch) movements, wire types, amounts of wire used, and deposition rates. For cutting, key cutting data may include one or more of the following: arc voltages, cutting currents, various gas pressures, various gas flow rates, initial piercing heights, angles of Petition 870250041321, dated 05 / 20 / 2025, page 50 / 79 44 / 46 cutting tool (torch) operation, cutting tool (torch) displacement angles, cutting tool (torch) cutting speeds, distances from the tool (torch) to the workpiece, and cutting movements of the cutting tool (torch).

[0087] Auxiliary welding (or cutting) data may include pre-inactivity time data. Auxiliary welding (or cutting) data may include data related to non-welding (or non-cutting) movements of a welding tool (torch) (or cutting tool (torch)) between consecutive welds (or cuts) on multiple instances of the same part type. Auxiliary welding (or cutting) data may include data related to the temperatures of multiple instances of the same part type, for example, after each weld (or cut) is produced. Other types of primary and auxiliary welding (or cutting) data are also possible, according to other embodiments.

[0088] Again, the embodiments of welding systems (or cutting systems) may include robotic welding systems (or robotic cutting systems), manual welding systems (or manual cutting systems), or semi-automatic welding systems. Furthermore, according to one embodiment and as previously discussed in this document, the server computer 114 and the data storage 112 may be configured as a database system that can be queried for welding data (or cutting data), as stored in the data storage 112, by a client computer (e.g., 140 or 150) operationally connected to the computer network 120. Petition 870250041321, dated 05 / 20 / 2025, page 51 / 79 45 / 46

[0089] Welding data or cutting data as identified, grouped and stored in system 110 can subsequently be used effectively by machine learning (ML) algorithms of system 110 (or by ML algorithms of other external systems) to, for example, classify welds (or cuts) as meeting or not meeting one or more specifications. ML algorithms can also be employed for other purposes (e.g., predictive and / or preventive maintenance purposes).Depending on the approach, machine learning (ML) algorithms can be developed (i.e., trained) using at least one of the following techniques: linear regression, logistic regression, decision tree, K-nearest neighbor, K-means, support vector machine, neural network, Bayesian network, tensor processing unit, genetic algorithm, evolutionary algorithm, learning classifier system, gradient boosting technique, or AdaBoost technique. Other techniques may also be possible depending on the approach.

[0090] Although the embodiments disclosed have been illustrated and described in considerable detail, the intention is not to restrict or limit in any way the scope of the claims to such details. Naturally, it is not possible to describe any conceivable combination of components or methodologies for the purpose of describing the various aspects of the present matter. Therefore, the disclosure is not limited to the specific details or illustrative examples shown and described. Thus, this disclosure is intended to encompass alterations, modifications, and variations covered. Petition 870250041321, dated 05 / 20 / 2025, p. 52 / 79 46 / 46 by the scope of the claims, which satisfy the statutory matter requirements set forth in Title 35 of the USC §101. The above description of specific embodiments is given by way of example. From the description provided, those skilled in the art will not only understand the general inventive concepts and advantages present, but will also find several changes and modifications evident to the structures and methods disclosed. The aim, therefore, is to cover all such changes and modifications encompassed by the essence and scope of the general inventive concepts, as defined by the claims and their equivalents.

Claims

1. SYSTEM (100) FOR WELDING PRODUCTION MONITORING AND DATA ANALYSIS, the system comprising: at least one server computer (114) having an analytical component (610); and at least one data storage device (112) operationally connected to at least one server computer (114); wherein the at least one server computer (114) is configured to: receive welding data, including main welding data and auxiliary welding data, via a computer network (120) from a plurality of welding systems (200) operationally connected to the computer network (120) and used to generate multiple welds in order to produce multiple instances of the same type of part, wherein the welding data corresponds to the multiple welds, and perform an analysis on the welding data to identify and group identical individual welds among the multiple welds,without relying on the identification numbers of the weld profiles received from the plurality of welding systems (200) as part of the analysis, wherein a group of identical individual welds corresponds to the same weld location in multiple instances of the same type of part, and wherein at least one data storage (112) is configured to receive the welding data, which correspond to each individual weld among the identical individual welds, from the server computer (114) and Petition 870260067462, dated 08 / 07 / 2026, page 6 / 28 2 / 9 digitally storing the welding data as identified and grouped, characterized in that the main welding data include data relating to at least one of the following: welding output voltage, welding output current, wire feed speed, arc length, adhesion, contact tip distance to workpiece (CTWD), working angle, travel angle, travel speed,gas flow rate, welding tool movements, wire type, amount of wire used and deposition rate; auxiliary welding data include data relating to: (i) pre-inactivity time, wherein the inactivity time occurs before a weld is initiated on multiple instances of the same part type, wherein the data relating to pre-inactivity times are generated by a timer circuit in a welding controller (230) based on moments when the data relating to the welding output current and voltage do not indicate that a weld is being generated; (ii) non-welding movements of a welding tool between consecutive welds on multiple instances of the same part type, wherein the data relating to non-welding movements of the welding tool between the generation of consecutive welds of the same part type are generated by a gyroscope,an accelerometer or some other type of inertial measuring unit fixed to or integrated into the welding tool Petition 870260067462, dated 08 / 07 / 2026, page 7 / 28 3 / 9 and operationally connected to a welding controller (230); and / or (iii) temperatures of multiple instances of the same type of workpiece after each weld among the multiple welds are generated, wherein the temperature-related data are generated by an infrared sensor or some other type of temperature sensor of one of the welding systems (200) operationally connected to the welding controller (230).

2. SYSTEM, according to claim 1, characterized in that the analysis is a cluster analysis.

3. SYSTEM, according to claim 1, characterized in that the system (100) is located remotely from the plurality of welding systems (200).

4. SYSTEM, according to any one of claims 1 to 3, characterized by multiple welds being generated robotically by a plurality of welding systems (200).

5. SYSTEM, according to any one of claims 1 to 4, characterized in that multiple welds are generated manually or semi-automatically by human operators using a plurality of welding systems (200).

6. SYSTEM, according to any one of claims 1 to 5, characterized in that at least one server computer (114) and at least one data storage device (112) are configured as a database system that can be queried for welding data, as stored, by a client computer (140) operationally connected to the computer network (120). Petition 870260067462, dated 08 / 07 / 2026, page 8 / 28 4 / 9 7. SYSTEM (300) FOR MONITORING METAL CUTTING PRODUCTION AND DATA ANALYSIS, the system comprising: at least one server computer (114) having an analytical component (610); and at least one data storage device (112) operationally connected to at least one server computer (114); wherein the at least one server computer (114) is configured to: receive cutting data, including main cutting data and auxiliary cutting data, via a computer network (120) from a plurality of metal cutting systems (400) operationally connected to the computer network (120) and used to generate multiple cuts in order to produce multiple instances of the same type of part, wherein the cutting data correspond to the multiple cuts, and perform an analysis on the cutting data to identify and group identical individual cuts among the multiple cuts,without relying on the identification numbers of the cutting profiles received from the plurality of metal cutting systems (400) as part of the analysis, wherein a group of identical individual cuts corresponds to the same cutting location in multiple instances of the same part type, and wherein at least one data storage (112) is configured to receive the cutting data, which correspond to each individual cut among the identical individual cuts, from the server computer (114) and digitally store the cutting data as identified and grouped; Petition 870260067462, dated 08 / 07 / 2026, page 9 / 28 5 / 9 characterized by: the main cutting data including data relating to at least one of arc voltage, cutting current, various gas pressures, various gas flow rates, initial piercing height, cutting tool working angle, cutting tool displacement angle, cutting tool speed,distance from the tool to the workpiece and cutting movements of the cutting tool; the auxiliary cutting data include data related to pre-inactivity time, wherein the inactivity time occurs before a cut is initiated in multiple instances of the same part type, wherein the data related to pre-inactivity times are generated by a set of timer circuits in the controller (230) based on moments when the data related to the welding output current and voltage do not indicate that a cut is being generated; and / or the auxiliary cutting data include data related to non-cutting movements of a cutting tool between consecutive cuts in multiple instances of the same part type, wherein the data related to non-cutting movements of a cutting tool between the generation of consecutive cuts in a part are generated by a gyroscope,an accelerometer or some other type of inertial measuring unit fixed or integrated into the cutting tool and operationally connected to a cutting controller (230); and / or the auxiliary cutting data include temperature-related data from multiple instances of the same type of workpiece after each cut among the multiple cuts is generated, wherein the temperature-related data are generated by an infrared sensor or some other type of temperature sensor of one of the welding systems (200) operationally connected to the welding controller (230).

8. SYSTEM, according to claim 7, characterized in that the analysis is a cluster analysis and / or the system is located remotely from the plurality of cutting systems.

9. SYSTEM, according to claim 7 or 8, characterized in that multiple cuts are generated robotically by a plurality of metal cutting systems (400); and / or the multiple cuts are generated by human operators using the plurality of metal cutting systems (400); and / or at least one server computer (114) and at least one data storage device (112) are configured as a database system that can be queried for the cutting data, as stored, by a client computer (140) operationally connected to the computer network (120).

10. METHOD (700), implemented by the system as defined in any one of claims 1 to 9, for identifying and grouping welding or cutting data corresponding to the same individual welds or cuts, the method comprising: receiving (710) welding or cutting data, including main data and auxiliary welding or cutting data, wherein the welding or cutting data correspond to multiple welds or cuts generated by a plurality of welding or cutting systems, so as to produce multiple instances of the same type of part;Petition 870260067462, dated 08 / 07 / 2026, page 11 / 28 7 / 9 perform (720) an analysis of the welding or cutting data to identify and group identical individual welds or cuts among multiple welds or cuts, without relying on welding or cutting profile identification numbers received from multiple welding or cutting systems as part of the analysis, wherein a group of the same individual welds or cuts corresponds to the same weld or cut location in multiple instances of the same part type; and receive (730), in at least one data storage (112), the welding or cutting data corresponding to each individual weld or cut among the same welds or cuts, and digitally store the welding or cutting data as identified and grouped;characterized by: the main welding data including data relating to at least one of: welding output voltage, welding output current, wire feed speed, arc length, wire extension (stick out), contact tip to workpiece distance (CTWD), working angle, travel angle, travel speed, gas flow rate, welding movements of the welding tool, wire type, amount of wire used and deposition rate; the auxiliary welding data including data relating to: (i) pre-sleep time, being the idle time before a weld is initiated in multiple instances of the same workpiece type, the data being generated by a timer circuit in a welding controller (230), Petition 870260067462, dated 08 / 07 / 2026, page 12 / 28 8 / 9 based on moments when the output voltage and current data do not indicate that a weld is being generated;(ii) non-welding movements of a welding tool between consecutive welds on multiple instances of the same type of part, the data being generated by a gyroscope, an accelerometer or some other type of inertial measuring unit fixed or integrated into the welding tool and operatively connected to a welding controller (230); and / or (iii) temperatures of multiple instances of the same type of part after each weld is performed, the data being generated by an infrared sensor or some other type of temperature sensor of one of the welding systems (200) operatively connected to the welding controller (230);The main cutting data shall include data relating to at least one of the following: arc voltage, cutting current, various gas pressures, various gas flow rates, initial drilling height, cutting tool working angle, cutting tool travel angle, cutting tool speed, tool distance to workpiece and cutting tool movements; the auxiliary cutting data shall include data relating to: (i) pre-idle time, being the idle time before a cut is initiated in multiple instances of the same workpiece type, the data being generated by a timer circuit in a cutting controller (230), based on moments when the output voltage and current data do not indicate that a cut is being performed;and / or Petition 870260067462, of 08 / 07 / 2026, page 13 / 28 9 / 9 (ii) non-cutting movements of a cutting tool between consecutive cuts on multiple instances of the same type of part, the data being generated by a gyroscope, an accelerometer or some other type of inertial measurement unit fixed or integrated into the cutting tool and operatively connected to a cutting controller (230); and / or (iii) temperatures of multiple instances of the same type of part after each cut is made, the data being generated by an infrared sensor or some other type of temperature sensor of one of the cutting systems operatively connected to the cutting controller (230).;

Images