FPTD researchers completed preliminary modeling and testing of key cutting control techniques for their Intelligent Deboning System, which they believe will allow automated deboning systems to match if not exceed the yield and quality performance of the best manual deboning processes. Specifically, the team developed a system to identify the initial cutting point and specify the nominal cutting trajectory. This system is known as the tendon prediction system. In order to identify the initial cutting point, the team developed an algorithm that can accurately predict that point as well as the internal structure of the joint based on the location of three key points on the bird. In the past, the team has manually located these points and passed that data to a program that calculated the initial cutting point. During FY 2009, the team implemented an image processing cell to automatically identify these key points on the bird. The image processing algorithms and the imaging cell were developed and successfully tested individually.
The team also focused on the development of a key technology required to automatically perform the wing cut – the real-time identification of bone material prior to cutting into or through a bone. Fast force-based feedback that identifies bone material is critical given the complexities of cutting through the product with its natural variation in material properties and the interactions of the blade with the product. Initial tests demonstrated the system’s ability to recognize bone during a cut, and in FY 2010, the team will focus on the development of a control algorithm to guide the blade around the bone without cutting through the bone while still cutting the tendons. In addition, the development of an active wing manipulation system was initiated. Researchers began the development of models for the musculoskeletal system of the bird as well as the biological joints that more accurately represent the motion of the joints in the bird. This work would allow the system to predict the joint location based on the position and orientation of the wing tip.
The team’s next steps are to refine the prototype to allow for more integrated control testing, including the use of 3D imaging technology. The 3D imaging is critical in the placement of the blade at the start of the cut. Researchers believe the Intelligent Deboning System could potentially help the poultry industry lower costs, achieve higher yields, and improve product safety by reducing the amount of bone or bone chips remaining in the product.
Project Director: Gary McMurray - email@example.com