Questions tagged with Manufacturing
Content language: English
Sort by most recent
Browse through the questions and answers listed below or filter and sort to narrow down your results.
I would like to know how could a customer route messages from different devices, e.g. life sciences lab or manufacturing instruments, at the edge using AWS IoT services. The idea is to allow a mesh connectivity at the edge and only some messages will need to be routed to the AWS Cloud for storage or further processing.
Hi everyone, I have a project in manufacturing area that I would like to improve by implementing computed vision capability. I already work with AWS services, but I still have no experience with Rekognition and Sagemaker, so I will explain my application below and would like to know if it is possible to make and what are the key point I need to put my attention and study. Today in a manufacturing plant, anytime a machine stops, the worker annotates the downtime cause on a tablet(running my app) with predefined options. I'd like to implement computed vision to automate this annotation, or suggest the most probable cause. I'm expecting a way for the application to auto train and improve itself given the historical data composed by: downtime cause annotated by operator + period of time when that downtime occurred + video. I plan to run on an edge through greengrass with a tpu processor. Thanks in advance.
Starting to use AWS IOT for collecting manufacturing data off of machines on the floor. That data could be productivity (when was the machine on or cycled) or process (what temperature is the over). Of course the kinds of data collected could get out of hand real quick, the potential is endless. My question is about hardware. It is confusing. Let's say I have 50 machines and I want to send a MQTT packet to AWS IOT for each machine each time that machine was cycled. We currently have one machine and I am using a [Opto22 Rio](https://www.opto22.com/products/groov-rio) to collect a few simple data points and sent a MQTT message to AWS. They run in the $750 each range currently. We started out using Raspberry Pi's for this but they were a bit painful. For us the pain of writing the python, securing the devices, putting the pi in a plastic din rail was not worth the low cost of the equipment. The questions: * Is this a reasonable piece of hardware to use for this? Seems a bit overpowered and expensive for no more than what it is doing. * Would this be considered a gateway and my sensors/inputs be considered things? * In our use case (many machines with a few inputs) what kind of hardware solution would you recommend for collecting the data and sending the MQTT packet to AWS with?