Illinois Tool Works Inc.

Stephen P Ivkovich

Leland D Falde

Vincent N Romano

Craig Jeffords

Adam Kirk Pliska

Praveen Dandu

Todd Michael McEllis

Jason Bonnell

Tret West

Ben Buhr

Systems and methods for missing weld identification using machine learning techniques are described. In some examples, a part tracking system uses machine learning techniques to identify whether an operator has missed one or more welds when assembling a part. The part tracking system may additionally identify which specific welds were missed (e.g., the first weld, the third weld, the fifteenth weld, etc.). The part tracking system may be able to identify missing welds after a part has been completed, or in real-time, during assembly of the part. Identification of the particular weld(s) missed during the welding process can help an operator quickly assess and resolve any issues with the part being assembled, saving time and ensuring quality.

Systems and methods for identifying missing welds using machine learning techniques

Systems and methods for part tracking using machine learning techniques are described. In some examples a part tracking system analyzes feature characteristics related to one or more welds to identify, determine characteristics of, and/or label one or more parts repeatedly assembled by the welds. Identifying parts assembled from the welds may make it possible to do part based analytics (e.g., related to part quality, cost, production efficiency, etc.), as opposed to just weld based analytics, on past welding data. Additionally, identifying a part assembled from several welds results in an ordering of those several welds used to create the part, which can make it easier to compare/contrast similar welds across parts. Further, determining the characteristics of the parts can assist in configuring certain part tracking systems, thereby reducing the expertise, time, and personnel required.

Systems and methods for part tracking using machine learning techniques

Systems and methods for distributed weld monitoring using jobs and job sessions are described. In some examples, a distributed monitoring system comprises a central monitoring station in communication with a user device and a local monitoring station. A user may use the user device to enter weld monitoring data that is subsequently received by the central monitoring station and stored in a central data repository. The central data repository may associate the weld monitoring data with welding data received from a welding device, as well as with a job session that is, in turn, associated with a job.

Distributed weld monitoring system with job tracking

Some examples relate to a welding-type monitoring system configured to track parts, production, and/or operations within a welding-type production cell. In some examples, the monitoring system comprises a computing system, one or more tags attached to one or more first items, and/or one or more tag readers attached to one or more second items. In some examples, the one or more tags store data relating to the first items, and the one or more tag readers are configured to read the data using a close proximity communication protocol when in range of the one or more tags. After the tag reader reads the data from the tag, the computing system may determine whether one or more workflow events are associated with the data. If so, the computing system may execute an event script corresponding to the workflow event.

Automated monitoring systems for welding-type production cells

Systems and methods for weld monitoring systems with unknown downtime disabling are described. In some examples, a local monitoring station may perform activity tracking as part of a larger weld monitoring system. A welding device may send welding data to the local monitoring system, which may be used to determine a current activity. A user may also manually input an activity to use as the current activity. If the local monitoring station is unable to determine a current activity from the welding data or user input, then the local monitoring station determines that an unknown downtime has occurred. If the local monitoring station cannot determine a reason for the unknown downtime, the welding device may be disabled until the user provides a reason for the unknown downtime.

Weld monitoring systems with unknown downtime disabling

Systems and methods to design part weld processes are disclosed. An example system for monitoring welding of components of a workpiece with multiple arc welds in a fixture includes: one or more weld sensors configured to collect data associated with the multiple arc welds; and a computing device configured to: access a weld program; provide weld instructions defined in the weld program and associated with a sequence of welds for the workpiece, the weld instructions comprising a visual slide including an image of the workpiece and a visual indication of a first location of a first weld; based on the weld program, display the visual slide at a first zoom level; based on the weld program, display the visual slide at a second zoom level; and monitor first weld data from the one or more sensors during a first weld to determine a status of the first weld.

Systems and methods to design part weld processes

Systems and methods for welding are described. The welding system can include, for example, a welding power source, a welding torch, and a computer. The computer and the welding torch can be operatively coupled to the power source. A first weld is performed and its signature is saved by the computer. It is considered a high quality weld and is selected as a weld reference. A second weld is performed and its signature is saved by the computer. The computer then computes a single weld confidence result for the second weld based on a comparison between the signature data of the second weld and the signature data of the reference weld. A weld fault condition is triggered based on the single weld confidence result which causes the welding system to stop or to modify the welding operation, and/or which causes the welding system to send out communications relating to the triggering of the weld fault condition.

Systems and methods for providing weld quality confidence

Systems and methods for labeling non-welding time periods using machine learning techniques are described. In some examples, a weld monitoring system may collect various data from sensors and/or welding equipment in a welding area over a time period. The data may evaluated to divide the time period into welding time periods and non-welding time periods. The weld monitoring system may use one or more machine learning models and/or techniques in combination with the collected data to determine what non-welding activities took place during the non-welding time periods. In some examples, the machine learning models may be continuously trained, updated, and/or improved using feedback from operators and/or other individuals, data from ongoing welding and/or non-welding activities, as well as data from other weld monitoring systems and/or machine learning models.

System and methods for labeling weld monitoring time periods using machine learning techniques

Systems and methods for part quality confidence are described. In some examples a part quality confidence system may receive inputs (e.g., via sensor measurements, operator input(s), etc.) related to one or more stages of a part assembly process. The inputs may be representative of certain feature characteristics of the part and/or one or more of the assembly stages. A computational engine of the system may determine one or more quality characteristics of the part based on the feature characteristics, and assign a quality metric to the part (and/or part assembly process) based on the quality characteristics. In some examples, a quality rating may be assigned to the part based on the quality metric, so as to provide an even simpler abstraction.

Systems and methods for providing part quality confidence

Systems and methods for welding are described. The welding system can include, for example, a power source, a computer, and a welding torch. The computer and the welding torch can be operatively coupled to the power source. The power source controls a wire feed and one of a current or a voltage to the welding torch. When the welding torch is performing pulsed welding, the computer is configured to receive a weld signature. The computer is configured to synthesize features from the weld signature and to analyze the features for each pulse of the weld signature to determine whether particular limits have been exceeded or met. If particular limits are exceed or met, a weld fault condition is triggered which causes the welding system to stop or to modify the pulsed welding operation, and/or which causes the welding system to send out communications relating to the triggering of the weld fault condition.

Growing community of inventors

East Lansing, MI, United States of America

Stephen P Ivkovich