Replies to post #32686 on Sigma Labs Inc (SASI)

[EDMGUY]

jjsmith77,
Thanks for the reasoned response. Here is where I think some of the details are overlooked:
1: The INSPECT closed loop link you used is talking about monitoring/guiding an automated welding machine based on the weld pool data it captures. It is sending that data over to the expert system(software). When the process starts to get out of control it decides which parameters to adjust. Which in turn sends a corrective action over to the machine.
My point is that expert systems are not perfect. They learn as you use them. I run CNC EDM (hence the EDMGUY) machines every day with expert systems.They are a huge benefit to making consistently good parts.They react to a potentially destructive situation far faster(micro seconds) than I can. Once I prove out my process on that part I can run my machine all night/weekend unattended with a high confidence of good parts.

2:A welding process although similar is far less sophisticated than a powder bed AM process. Making it much more difficult to develop an expert system for AM.

Does that mean INSPECT is not a closed loop process? No
But it doesn't mean that you can just install it on any machine and start making any part you need that day and they will all be good parts.

The true benefit to me is once you have a good process for making a good part you can use the captured build data to prove that nothing bad happened for every part. Your inspection needs are greatly reduced.
And it can stop the build if an event is detected that would likely result in a bad part(less scrap and wasted machine time).

I know this is getting long but one last thing.
I don't think the speed issue is strictly the cm3/hr. It's more the difference between making a nozzle in 1 piece with AM or a 10 pc assembly with conventional machining(slower and more expensive).
I have done a fair amount of machining with Nickel and Inconel and they are extremely difficult metals to handle.

Great discussion
Regards

[chef911]

So we know that Sigma Labs called INSPECT the "closed-loop process controller". If INSPECT is not a closed-loop process, then Sigma Labs wrongly advertised INSPECT for years?

So what if that is the case? What if you are all correct? I don't have much to back up my opinion, but that IS what I think. This is not fact, it is opinion: Cola and Dave and 2 other men invented a process and they patented it, "Method and apparatus for in-process sensing of manufacturing quality." But it was done at LANL, and the patent was assigned to the USG.

http://www.google.com/patents/US6857553

Method and apparatus for in-process sensing of manufacturing quality
US 6857553 B1
ABSTRACT
A method for determining the quality of an examined weld joint comprising the steps of providing acoustical data from the examined weld joint, and performing a neural network operation on the acoustical data determine the quality of the examined weld joint produced by a friction weld process. The neural network may be trained by the steps of providing acoustical data and observable data from at least one test weld joint, and training the neural network based on the acoustical data and observable data to form a trained neural network so that the trained neural network is capable of determining the quality of a examined weld joint based on acoustical data from the examined weld joint. In addition, an apparatus having a housing, acoustical sensors mounted therein, and means for mounting the housing on a friction weld device so that the acoustical sensors do not contact the weld joint. The apparatus may sample the acoustical data necessary for the neural network to determine the quality of a weld joint.

And Cola and Dave together also developed and patented this (bold mine for emphasis):

Methods for control of a fusion welding process by maintaining a controlled weld pool volume
ABSTRACT
A new method of process control for fusion welding maintains a controlled weld pool size or volume, for example in some applications a substantially constant weld pool size or volume. The invention comprises a method of linking machine and process variables to the weld pool size or volume in real time, thereby enabling constant weld pool volume control. The invention further comprises a method of using thermal inverse models to rapidly process real-time data and enable models-based control of welding processes so as to implement constant weld pool volume control.

I speculate that they know/scientifically believe it is sound science (wordplay, because I keep hearing over and over that what makes Sigma's product superior to all others is that it does not rely on optics, but instead acoustics, something that is in the quality patent, but I cannot find anywhere the Weld Pool patent)

I propose that one reason the Sigma technology is not being purchased (as we know there are probably others) is because what they are pitching is the Weld pool Control, something that will leapfrog (streamline) the inspection process because it will potentially solve the defect issue before or immidiately as (That non-human no-logic table controller #14) it happens. But, it will be extremely cumbersome and costly to customer because possible void OEM warranty, AND require huge data processing to train the neural network.

I don't know...I can envision Sigma Labs having control, Materialise having a way to express that control, and a closed-loop processor soon.

Then I can see how GE can build all those nozzles. Remember also that we have not even taken inspection time into consider. How long to we need for inspection? If qualification is performed during the build, then the time is saved.

IMO, there are 2 patents that are relevant here. One looks exactly like an inspection system, one looks like a control system.

I asked this on the conference call. Does the weld pool patent cover all of IPQA? I deliberately phrased it like that to included DEFORM, INSPECT and the 2 other modules in development) The way I heard the answer, after Cola declined to reply and handed it over to Dave, is that they proport it applies to AM and not just traditional welding, because that's what AM is, modern welding.

On the recent discussion, plus the answer that Dave gave me on the call, I have stepped down my holdings reflectively, from nearly 600,000 to current 80,000 where I am much more comfortable.