Representative End User Clients
Representative Automation Clients
Representative Software Clients
Manufacturers that use machine tools in production need parametric models that can predict the quality of a production workpiece that can be difficult to inspect nondestructively. This has been difficult to justify, but the economic viability of leveraging the Cloud and advanced analytics has finally arrived. Real time process parameters can be extracted from connected machines operating in many locations. Production machinery process models can be developed and then continuously improved upon to offer manufacturers mathematical models that predict the finish quality of a production workpiece.
Connected Machines Open the Door to Develop Process Models
For content on the web, information is generally unstructured and we rely on search engines to make sense out of it. But, this requires a tremendous amount of computing power on back end systems to provide accurate results. But this model, with computing power in back end systems hosted in the Cloud, is an opportunity for machinery builders to develop system models of machinery that can be used to predict production quality.
As more digitally controlled machines become connected, machine builders should look to this as a resource to collect a wide array of real time process parameters. This data can be used to develop accurate mathematical models of the machine behavior under innumerable operating conditions that are difficult to set up in a laboratory test bed. Cloud storage can be employed as a repository for large unstructured data sets comprised of machine process variables, tooling, and workpiece information. It is now economically viable to leverage analytical tools to process these large unstructured data sets to develop new machinery models that can accurately predict the quality of a finished production workpiece. Connected machines are a vast pool of process information that is extremely difficult for machine builders to replicate during the development cycle. General Dynamics Trials Analytics in a Forging Operation
As an example, General Dynamics’ Scranton, Pennsylvania, USA operation is currently working on a machine modeling project with the SMLC (Smart Manufacturing Leadership Coalition). This is a joint project with University of Texas and UCLA where they are using a Cloud based platform to collect data from the forging operation to develop accurate machine models to improve product quality and reduce energy consumption. The data collection system does not go through the standard General Dynamics IT network, but uses a separate server. A separate server is used because General Dynamics is a military subcontractor that employs highly rigorous security measures. They will not take any security risk by allowing third parties to gain access to the corporate IT network. However, the use of a separate server has allowed this project to move forward so that researchers can collect data from these production operations.
Connected Machines Open the Door to Develop Process Models
For content on the web, information is generally unstructured and we rely on search engines to make sense out of it. But, this requires a tremendous amount of computing power on back end systems to provide accurate results. But this model, with computing power in back end systems hosted in the Cloud, is an opportunity for machinery builders to develop system models of machinery that can be used to predict production quality.
As more digitally controlled machines become connected, machine builders should look to this as a resource to collect a wide array of real time process parameters. This data can be used to develop accurate mathematical models of the machine behavior under innumerable operating conditions that are difficult to set up in a laboratory test bed. Cloud storage can be employed as a repository for large unstructured data sets comprised of machine process variables, tooling, and workpiece information. It is now economically viable to leverage analytical tools to process these large unstructured data sets to develop new machinery models that can accurately predict the quality of a finished production workpiece. Connected machines are a vast pool of process information that is extremely difficult for machine builders to replicate during the development cycle. General Dynamics Trials Analytics in a Forging Operation
As an example, General Dynamics’ Scranton, Pennsylvania, USA operation is currently working on a machine modeling project with the SMLC (Smart Manufacturing Leadership Coalition). This is a joint project with University of Texas and UCLA where they are using a Cloud based platform to collect data from the forging operation to develop accurate machine models to improve product quality and reduce energy consumption. The data collection system does not go through the standard General Dynamics IT network, but uses a separate server. A separate server is used because General Dynamics is a military subcontractor that employs highly rigorous security measures. They will not take any security risk by allowing third parties to gain access to the corporate IT network. However, the use of a separate server has allowed this project to move forward so that researchers can collect data from these production operations.