System and Method to Facilitate Welding Software as a Service
A weld production knowledge system for processing welding data collected from one of a plurality of welding systems, the weld production knowledge system comprising a communication interface communicatively coupled with a plurality of welding systems situated at one or more physical locations. The communication interface may be configured to receive, from one of said plurality of welding systems, welding data associated with a weld. The weld production knowledge system may comprise an analytics computing platform operatively coupled with the communication interface and a weld data store. The weld data store employs a dataset comprising (1) welding process data associated with said one or more physical locations, and/or (2) weld quality data associated with said one or more physical locations. The analytics computing platform may employ a weld production knowledge machine learning algorithm to analyze the welding data vis-à-vis the weld data store to identify a defect in said weld.
1 . (canceled)
2 . A welding analysis system comprising:
first processing circuitry to process a first welding input from a first data source to define first welding data, wherein the first data source is associated with a weld, weldment, or weld process;
second processing circuitry to process a second welding input from a second data source to define second welding data, wherein the second data source is associated with the weld, weldment, or weld process; and
a remotely situated analytics computing platform configured to:
receive the first welding data and the second welding data via a communication network communicatively coupled with the first processing circuitry and the second first processing circuitry; and
process the first welding data and the second welding data using an unsupervised learning technique to identify anomalies in at least one of the weld, the weldment, or the weld process.
3 . The welding analysis system as defined in claim 2 , wherein the remotely situated analytics computing platform is configured to identify the anomalies in at least one of: weld quality; arc time patterns; idle time patterns; equipment duty cycle patterns; input power consumption and fluctuation patterns; welding consumable consumption patterns; or usage patterns on functions available from welding equipment associated with the first welding data or the second welding data.
4 . The welding analysis system as defined in claim 2 , wherein the unsupervised learning technique comprises a data clustering technique to identify the anomalies based on the first welding data and the second welding data.
5 . The welding analysis system as defined in claim 4 , wherein the data clustering comprises at least one of k-means, hierarchical, conceptual, probability-based, or Bayesian clustering.
6 . The welding analysis system as defined in claim 4 , wherein the remotely situated analytics computing platform further comprises a supervised learning technique to detect the presence of the identified anomalies in subsequent welding data.
7 . The welding analysis system as defined in claim 2 , wherein the identified anomalies comprise at least one of an equipment condition, equipment usage, or imminent equipment failure.
8 . The welding analysis system as defined in claim 2 , wherein the identified anomalies comprise at least one of a welding gas anomaly, a welding wire anomaly, a flux anomaly, a contact tip anomaly, a torch nozzle anomaly, or a wire liner anomaly.
9 . The welding analysis system as defined in claim 2 , wherein the identified anomalies comprise at least one anomaly in a part being welded.
10 . The welding analysis system as defined in claim 2 , wherein the identified anomalies comprise at least one anomaly in a weld fixture being used.
11 . The welding analysis system as defined in claim 2 , wherein the identified anomalies comprise at least one batch-to-batch difference in manufacturing.
12 . The welding analysis system as defined in claim 2 , wherein the identified anomalies comprise a deviation from a weld procedure specification.
13 . A welding analysis system comprising:
first processing circuitry to process a first welding input from a first data source to define first welding data, wherein the first data source is associated with a weld, weldment, or weld process;
second processing circuitry to process a second welding input from a second data source to define second welding data, wherein the second data source is associated with the weld, weldment, or weld process; and
a remotely situated analytics computing platform configured to:
receive the first welding data and the second welding data via a communication network communicatively coupled with the first processing circuitry and the second first processing circuitry; and
process the first welding data and the second welding data using an unsupervised learning technique to predict at least one characteristic of the weld, weldment, or weld process, the at least one characteristic comprising at least one of spatter, fume, defects, arc stability, distortion, microstructure, residual stress, corrosion, creep, fatigue, a metallurgical property, or a mechanical property.
14 . A welding analysis system comprising:
first processing circuitry to process a first welding input from a first data source to define first welding data, wherein the first data source is associated with a weld, weldment, or weld process;
second processing circuitry to process a second welding input from a second data source to define second welding data, wherein the second data source is associated with the weld, weldment, or weld process; and
a remotely situated analytics computing platform configured to:
receive the first welding data and the second welding data via a communication network communicatively coupled with the first processing circuitry and the second first processing circuitry; and
process the first welding data and the second welding data using an unsupervised learning technique to identify features in that are critical to quality (CTQs) associated with at least one of the lean manufacturing Define Measure Analyze Design Verify (DMADV) methodology or the Design for Six Sigma (DFSS) methodology.