Artificial Intelligence/Machine Learning, ASA(ALT), Phase I
Artificial Intelligence/Machine Learning for Nitramine Recrystallization and Coating
Objective
The goal is to develop a suite of probe technology and machine learning algorithms to improve the energetics manufacturing process. Technologies will be selected based on time resolution, ruggedness, data output, safety and suitability in reducing costs and increasing product consistency.
Description
The Army seeks to leverage probe technologies that will collect data on material manufacturing. This data will provide instantaneous recommendations to plant operators on how to adjust the efficiency of their processes.
There are two key steps for this technology to be successful. The first is the development and deployment of novel probes that produce large amounts of data in real time. The second is an advanced machine learning system that will use the probe readings and provide manufacturing adjustments in real time to produce higher quality products.
These technologies could also reduce costs, environmental footprint and increase throughput from existing lines. In the long run, the insights gained from this program will drive an easier transition of novel energetic formulations as well.
Phase I
Demonstrate that the proposed probe technology can produce the required data over the course of several manufacturing runs.
Phase II
Implement the probes during the manufacturing process to collect data for machine learning algorithms.
Phase III
Expand the usage of probes to direct and control manufacturing lines while producing data for machine learning systems. Ensure moderate, dual-use application, as using AI/ML-based chemical manufacturing may have potential benefits for commercial capabilities beyond energetics.
All HMX/RDX batches are currently examined to determine if they meet the desired specifications. These include assessing purity, particle size and thermal stability. This analysis can compare against the predictions of the machine learning algorithms and the measurements provided by the probes. These machine learning predictions may also be compared against the predictions of crystallization modeling software, when appropriate.
For the actual submission dates and to submit your full proposal package, visit the DSIP Portal.
References:
TPOC-1: Rajen Patel
Email: Rajen.b.patel.civ@army.mil
TPOC-2: Jermaine Dunham
Email: Jermaine.a.dunham.civ@army.mil
Objective
The goal is to develop a suite of probe technology and machine learning algorithms to improve the energetics manufacturing process. Technologies will be selected based on time resolution, ruggedness, data output, safety and suitability in reducing costs and increasing product consistency.
Description
The Army seeks to leverage probe technologies that will collect data on material manufacturing. This data will provide instantaneous recommendations to plant operators on how to adjust the efficiency of their processes.
There are two key steps for this technology to be successful. The first is the development and deployment of novel probes that produce large amounts of data in real time. The second is an advanced machine learning system that will use the probe readings and provide manufacturing adjustments in real time to produce higher quality products.
These technologies could also reduce costs, environmental footprint and increase throughput from existing lines. In the long run, the insights gained from this program will drive an easier transition of novel energetic formulations as well.
Phase I
Demonstrate that the proposed probe technology can produce the required data over the course of several manufacturing runs.
Phase II
Implement the probes during the manufacturing process to collect data for machine learning algorithms.
Phase III
Expand the usage of probes to direct and control manufacturing lines while producing data for machine learning systems. Ensure moderate, dual-use application, as using AI/ML-based chemical manufacturing may have potential benefits for commercial capabilities beyond energetics.
All HMX/RDX batches are currently examined to determine if they meet the desired specifications. These include assessing purity, particle size and thermal stability. This analysis can compare against the predictions of the machine learning algorithms and the measurements provided by the probes. These machine learning predictions may also be compared against the predictions of crystallization modeling software, when appropriate.
For the actual submission dates and to submit your full proposal package, visit the DSIP Portal.
References:
TPOC-1: Rajen Patel
Email: Rajen.b.patel.civ@army.mil
TPOC-2: Jermaine Dunham
Email: Jermaine.a.dunham.civ@army.mil