Sigma Labs Inc (SASI)

[jjsmith77]

3DSIM is the same as INSPECT in regards to have predictive capabilities. 3DSIM predicts the MOST correct parameter set before the machine is turned on. INSPECT compares desired and actual welding conditions. If the conditions don't match, then an anomaly will occur. So, if the conditions don't match, the laser does not fire to melt the metal powder to create an erroneous melt pool. Rather, INSPECT creates an interrupt and the parameter set is examined and adjusted as need be. The new parameter set is then noted as the reference that created quality melt pool.

See how both 3DSIM and INSPECT are forward-looking? See how INSPECT can prediction that an erroneous melt pool will occur?

[0041] The optimizer module can have a fitness function… defined by comparing the measured thermal response to the predicted thermal response…and iterates on parameter sets until this fitness is within a pre-determined tolerance…

[0054] When the weld pool volume varies from its desired setpoint, this can be detected by the thermal sensors, the weld pool frequency sensors, or combinations thereof…

[0055] Once a shift is detected, the real-time controller 14 can have an internal logic table that analyzes the nature… Based on pre-determined rules.., the controller 14 can decide which machine variable will be the best choice

Controller 14 being a quality engineer. This is how a process is controlled as automatic machine behavior is not a desired feature in aerospace manufacturing.

So you wonder about other monitoring systems. Yes, they monitor. The issue is big data from all those layers. We need data reduction by extracting features that are critical to quality. The scientist at SGLB are ones who can decide what is quality feature or not by their research experience at LANL. Otherwise, IPQA (or pre-determined rules) cannot be defined.

DEFORM not ready as in Honeywell engineer Godfrey prematurely enthusiastic?
What other NDT then?