| NSF Org: |
TI Translational Impacts |
| Recipient: |
|
| Initial Amendment Date: | February 1, 2019 |
| Latest Amendment Date: | February 10, 2020 |
| Award Number: | 1843858 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Benaiah Schrag
bschrag@nsf.gov (703)292-8323 TI Translational Impacts TIP Directorate for Technology, Innovation, and Partnerships |
| Start Date: | February 1, 2019 |
| End Date: | June 30, 2020 (Estimated) |
| Total Intended Award Amount: | $224,757.00 |
| Total Awarded Amount to Date: | $249,757.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
104 PRESCOTT ST WORCESTER MA US 01605-1703 (508)733-1808 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
54 Rockdale St WORCESTER MA US 01606-2761 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): |
SBIR Phase I, SBIR Outreach & Tech. Assist |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.084 |
ABSTRACT
The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is increased revenue and processing potential for scrap recyclers in the US. The artificially-intelligent algorithm designed in this project will enable domestic scrap processors to become more competitive within the material supply chain by giving them the ability to adapt, in real-time, to an ever-changing material consumption climate. With unstable international commodity trade, US scrap processors must reduce reliance on exporting low-value scrap to maintain profitable business models. Additionally, US scrap must exercise optimal processing schedules to prevent scrap surplus domestically while providing consumers with recycled products that are functionally equivalent to new products. The latter offers an environmentally-friendly scrap-to-product option that reduces the energy required for production and the amount of harmful CO2 released. Aluminum scrap recycling has been practiced for decades; however, the majority of post-consumer scrap is downcycled leaving revenue and environmental benefits untapped. Non-ferrous auto-shred was, on average, sold for $0.33/lb. less than its actual value in 2017, which equates to nearly $1 billion in opportunity cost. Artificially intelligent sorting systems will enable scrap processors to reach higher profit margins and meet environmental goals.
The proposed project will completely automate scrap sortation. The advent of multi-sort capability encourages the need for preliminary research to identify how to operate sensor-based sorters optimally. Artificial intelligence can meet this need. The intellectual merit of this project is the development of an artificially-intelligent algorithm that is capable of optimizing scrap sortation in real-time. The research objectives include: (1) identify all data sources in the scrap recycling process that can influence intelligent decision making (2) design a database to host identified data sources such as compositional, market, inventory, and sales data and (3) design a customized artificially-intelligent algorithm for the scrap recycling industry to develop sorting criteria in real-time. To meet these objectives, a dynamic material flow model will be designed to analyze and host all relevant sensor, market, and experimental data streams to minimize data pre-processing requirements. Concurrently, aluminum scrap will be characterized to investigate how frequently and to what degree composition fluctuates. The database that hosts all supportive data streams will be designed to store and integrate all relevant data streams seamlessly. Finally, using an 80/20 training/testing data split with 5-fold cross-validation, the machine learning algorithm will be selected and optimized to provide the lowest error rate for suggested sorting criteria.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
This Small Business Innovation Research Phase I project resulted in prototype development of an artificially intelligent sorting software (AISS) for the metal scrap processing industry. The two-fold goal of the AISS is to (1) enable the production of high quality, maximum value scrap by combining market and compositional data to optimize sorting criteria and (2) use artificial intelligence to predict what scrap packages are optimally salable regardless of economic state. This solution will address the unsustainable, business as usual practices of the nonferrous scrap recycling industry which has led to an annual missed opportunity cost of $1 billion, over 4% of total industry revenue. Integration of the AISS into commercial sensor-based sorting (SBS) systems will address the needs of three, key industry stake holders:
(1) The scrap processor - need to maintain profitability by selling maximum value products
(2) The scrap consumer - need to minimize melt losses and primary aluminum consumption by receiving high quality scrap with known composition
(3) The SBS original equipment manufacturer (OEM) - primary need is to sell their equipment and increase revenue generation
The intellectual merit of this project is based upon the utilization of an artificially intelligent algorithm with a blending optimization model to connect market value and compositional data to produce maximum value nonferrous scrap sortation decisions. The completed Phase I effort contributes toward delivering an AISS to scrap processors that identifies, in real-time, a maximum value commodity package by analyzing several data streams. It will recommend optimized sorting criteria for maximum profit generation, predict scrap stream composition, and monitor scrap package composition for guaranteed quality. The following objectives were set to accomplish this goal and were successfully completed through the Phase I period:
(1) Optimization of the metal alloy blending model
(2) Characterization of mixed nonferrous scrap
(3) Identification of key market drivers and data streams
(4) Database design to host all necessary data streams
(5) Artificial intelligence algorithm design and testing
The completion of these five objectives resulted in key results addressing the needs of the scrap processors, scrap consumer and SBS OEM.
For the Scrap Processor: Value Added & Sort Optimization Results
The effectiveness of the algorithm was tested using both real pricing data and mock pricing data. Two metrics, $/lb and $/sec, were used to analyze the ability of the AISS algorithm to determine maximum value sorts for each day of the simulation. The results show a constant revenue increase over the 20-day sorting period. The AISS algorithm can increase sort value by up to 8.01 cents/lb and 1.15 cents/lb compared to the average values of Zorba and Twitch, respectively. The increased sort values result in additional revenue generation of $11,280/day for a processing plant operating 80 hours/week.
For the Scrap Consumer: Quality Control
It was proven through Phase I work that AISS created scrap packages can be used to create alloys with minimal post-processing required, referring to addition of virgin material to balance out composition. This key result directly addresses the needs of the scrap consumer.
For the SBS OEM: Decreased Payback Period and Added Revenue Generation
Solvus Global can guarantee an increase in package value of 8.01cents/lb for a scrap processor when utilizing an SBS system equipped with the AISS per the data processed including time-period and scrap characteristics. This reduces a major barrier to market for SBS OEMs by decreasing the payback period associated with this capital investment from 2-3 years to less than 150 working days based on typical operating parameters (i.e. throughput, operating hours in a week, etc.). Payback period was a critical factor for scrap processors, many of which, during customer interviews, stated a payback period of less than one year is highly interesting and a "no brainer" for purchasing equipment.
Through partnership with a leading sensor-based sorter original equipment manufacturer and major nonferrous scrap processor the R&D work throughout Phase II will result in a fully optimized AISS that is ready for integration at commercial-scale scrap processing facilities.
Last Modified: 07/27/2020
Modified by: Sean Kelly
Please report errors in award information by writing to: awardsearch@nsf.gov.
