Understanding the material stream is key to making adjustments that influence the incoming material stream and recovered material reuse markets. The data generated can be used to improve operational efficiency and more effectively connect waste generators, MRF operations, and the resource value chain.
By Amanda Marrs
Material composition in the recycling industry has been a longstanding challenge due to the complexity of mixed material streams, compounded by ongoing changes in consumer packaging. These obstacles often create impediments to accurate data collection and prevent a clear understanding of what goes into and comes out of the different infrastructure stages that support recycling. Operators have only snapshots of material composition gathered through manual waste audits and human observations once the waste arrives at the material recovery facility (MRF). Periodic waste audits are useful, but they only evaluate small samples of the overall material stream. And audits can be limited by a variety of factors, as well as expensive to undertake regularly enough to inform daily MRF operations. Furthermore, audits expose workers to safety risks, can be cumbersome and time-consuming, and quickly become outdated relative to the pace of market changes.
Images courtesy of AMP Robotics.
MRFs are the centralized material hubs within a waste catchment area and circular economy. Mixed material streams come in, sorting happens, and commodities and residuals come out. Without visibility into what goes into the MRF, it is difficult to control or adapt to inherent material variability. The industry has adjusted by constructing MRFs that tolerate wide-ranging inbound material specifications for a limited number of marketable bale products. This generates an abundance of residuals and low-value baled products. To increase recycling supply, we need better material characterization data. Material characterization at the MRF would offer an unprecedented view of the movement of materials within the economy from a centralized location. There is an enormous opportunity to leverage the MRF function as an information hub.
Essential Technologies
Understanding the material stream is key to making adjustments that influence the incoming material stream and recovered material reuse markets. The data generated can be used to
improve operational efficiency and more effectively connect waste generators, MRF operations, and the resource value chain. These improvements are critical to strengthening the circular economy and providing meaningful progress toward enhancing waste management’s sustainability and resilience.
Artificial intelligence (AI) is the enabling technology essential for MRFs to generate and capture the data to optimize recycling operations. Vision-based AI software identifies and characterizes objects in the waste stream in real time, digitizing each item that passes by. These objects are captured as a new form of data, including object counts, packaging descriptions, and more, over time. Hundreds of robots and sensors that process billions upon billions of objects on conveyor belts in MRFs are deployed today. This effectively enables automated and continuous characterization of this material. Material categories continue to expand thanks to the exploration and development of subcategories useful for MRFs as well as for downstream recyclers. As more robots are deployed, the industry can leverage the networked intelligence of hundreds of units. The more AI-based robots and sensors deployed into production, the more a network effect is created. In the case of these systems, this network effect exponentially increases the sorting intelligence. When a challenging packaging type or new material emerges, the imagery is captured and the AI can be trained to identify the object. This knowledge is then deployed throughout the fleet of robots. In essence, the more robots we deploy, the more each customer is helping another customer by expanding the AI’s material knowledge.
Real-Time Monitoring and Analysis
MRF operators can use the data this machine-learning technology produces for analysis to support inbound, outbound, and product quality questions. It also allows operators, finance
departments, and material auditors to do things like graphically compare material stream data to historical baselines, define material volume thresholds and create alerts triggered by movement above or below these thresholds, export data for further analysis and integration into business intelligence platforms, and more.
This delivery of real-time monitoring and analysis of material as it flows through a facility provides visibility into and feedback about material streams, helping to overcome the perennial data transparency challenge for recyclers. With data and tangible metrics, operators can get ahead of mechanical or configuration-based issues and communicate with business partners or key staff in the facility. Some use cases include:
• How much contamination is entering the facility and from what sources?
• How much valuable material am I losing at the point of residue?
• Can I drive a higher price for scrap bales with data that shows the quantity and quality of the material in the bale?
Digitization and Data Capture
The digitization of scrap objects in the MRF opens up many potential applications. The first two that are deployed into MRFs today are robotic sorting and the descriptive and diagnostic analytics provided by standalone sensors. As the sensors become distributed throughout, MRFs are able to become more data-driven facilities to reduce costs and increase revenue. As noted earlier, the MRF is a centralized material hub, and the proliferation of these sensors begin to transform MRFs into information hubs.
Data capture in MRFs can also influence the design of new facilities. For example, the application of AI for material identification and advanced automation has matured to the point where it has become viable to develop high-diversion secondary sortation facilities that are economical to deploy and sustain nationally. We have demonstrated an automated facility design for advanced secondary sortation, which serves as an infrastructure model that can economically process and aggregate small volumes of mixed plastics, paper, and metals sourced from residue supplied by primary MRFs and other sources. These solutions process historically hard-to-recycle polymers including #3 to #7 plastics and discrete plastic types such as PET thermoforms.
Advancing a Circular Economy
Better data and data capture technology provide opportunities for consumer-packaged goods companies, retailers, and packaging manufacturers to understand the quality, flow, and recovery of their specific containers and packaging. AI technology can help producer initiatives to increase recycling rates and create new value streams for recyclables, ultimately aiding their pursuit of recycled content goals. As Extended Producer Responsibility (EPR) schemes emerge and mature, sensors growing in the fleet of MRFs can help satisfy the demand for reporting recovery rates. Data collection, measurement, and material characterization for recycling also create a mechanism to support federal, state, and local government programs focused on landfilldiversion goals and recycled content standards to advance a more circular economy. | WA
Amanda Marrs is Senior Director of Product for AMP Robotics, responsible for technical product development for the company’s artificial intelligence platform, robotic
sorting systems, and software capabilities. She has more than 10 years of experience in product development at General Electric and Amazon.com with a focus on hardware and software products used in industrial processes. She can be reached at [email protected].