Georgia Tech Research Institute spacer Agricultural Technology Research Program


ATRP Research Program Continues Quest to Drive Transformational Innovation in Poultry Production


“Current methods of poultry processing are a combination of historical practices, increased mechanization to replace manual operations, and the application of technologies to meet more stringent sanitation, worker safety, and environmental regulatory demands. As such, modern processing plants today are often the merger of traditional processes retrofitted with modern materials and technologies,” says Dr. Doug Britton, manager of the Agricultural Technology Research Program (ATRP).

Britton likes to call this type of merger “sustaining innovation,” and notes the future viability of the poultry industry will hinge on our ability to foster “transformational innovation,” which is the creation of something entirely new that eventually eclipses the existing norm, creating an entirely new norm. For the poultry community, this will involve fundamentally rethinking the entire production and processing system without the constraints of the current practices. As part of this effort, a strategic initiative of ATRP’s FY 2013 research program is to continue to define the poultry processing plant of the future. Six continuation projects are focused on novel types of engineering and technology research activities that address critical issues facing poultry production from the growout house to the processing plant.

Improving animal health and welfare

Reliable sensors to monitor the condition and welfare of birds being reared in confined housing are not readily available. The goal of ATRP’s Growout Monitoring project is to investigate the use of bird vocalizations to determine whether or not they are under stress due to environmental conditions or disease. In collaboration with fellow researchers at Georgia Tech and the University of Georgia, the ATRP project team has developed an experimental monitoring system. The system has been installed at UGA’s Poultry Science research growout facilities where several studies have been conducted. First, the team studied environmental effects such as temperature, ammonia, and crowding. Results showed that features extracted from bird vocalizations strongly correlated with higher ambient room temperatures and the presence of ammonia. The correlations for crowding were not as strong. Second, the team explored the effects of disease. Two experiments were conducted at the Poultry Disease Research Center (PDRC) in Athens, Georgia, which investigated the effects of Infectious Bronchitis and Laryngotracheitis (LT) in broilers. In both experiments, it appeared that features of the vocalizations could be extracted that strongly correlate with the progress of both diseases. Moving forward, the team will attempt to replicate these studies and improve the existing algorithms and tools to enhance the extraction and classification features used to assess bird welfare.

Under the Chicken Egg Fertility Detection project, ATRP researchers together with colleagues at Auburn University have developed a noninvasive and rapid spectrophotometric technique to track the changing embryo in-ovo or inside the egg. This method allows researchers to predict when individual eggs will hatch, which in turn, should provide insight into a number of practices from animal health and welfare to the inoculation regime. Hatchability experiments were recently conducted where eggs were taken all the way to hatch and spectral readings were recorded at approximately the same time daily for 21 days. Different temperatures, humidity levels, and with/without egg turning were examined. Analysis of the spectral data showed fertile, developing eggs changed at a greater rate than infertile eggs. A number of eggs were removed from the process and placed at a lower temperature to determine if the spectral changes continued. The previously observed spectral changes slowed significantly for the cooled eggs. The results showed that at a very early point spectral data indicates the rate of embryonic development for each egg if the hatchery is running consistently. Currently, the team is expanding the study to investigate whether the spectrophotometric technique can be used to determine the sex of the embryo. This has productivity value as males could be selected for broiler production and females for layer production. It also has animal welfare implications in that male layer chicks would not have to be disposed of since they would not be hatched.

Reducing water usage and environmental impact

ATRP’s Dynamic Filtration project is investigating techniques to more selectively capture target impurities from liquid streams in a way that facilitates the recovery of value-added byproducts while still meeting or exceeding water reuse guidelines. Researchers are focused on three primary applications: poultry chillers, marinations, and brines. A bench-scale dynamic filtration device has been constructed and evaluated. The system employs greater filter flux rates (L/m2*hr) and solids removal as compared with a traditional poultry secondary screening system utilizing approximately 300-micron screen. Preliminary results are promising; however, additional work is needed to complete the assembly of a backwash system. Here, the team is using a servo motor with programmable logic controller (PLC) so that motor RPM and torque can be used for feedback. In addition, the team is augmenting the existing piston pump setup to eliminate liquid flow back to the piston arm so that the overall pressure profile within the pumping system can be monitored. Continued progress will advance the ability of processors to improve water reuse and food safety initiatives.

Achieving labor efficiencies through automation, specifically systems that improve process efficiencies and/or product quality and food safety

Deboning represents a particularly labor-intensive operation in the poultry industry. Due to the natural deformation and variation of bird carcasses, automation of the cutting process has proved to be very challenging and has resulted in significant yield losses and bone chips. ATRP’s Intelligent Cutting and Deboning System uses 3D imaging and a robotic cutting arm to automatically perform precision cuts. Cuts are focused on severing the tendons and joints on bird front-halves in preparation for the removal of the wings and breast meat. Recent efforts have focused on integrating three separate components (trajectory generation for each individual bird, bone detection, and force control) into a single functioning system. Initial performance results were encouraging, and the team is currently refining the system by designing and fabricating an improved knife end-effector and expanding the use of force control. The team also plans to perform a more extensive statistical study of bird features and further explore active wing manipulation.

Screening deboned poultry product for bones is still an intensive manual process. In addition, estimating yield loss due to process inefficiencies is also very difficult to perform during production. ATRP’s Cone Line Screening System project team has developed a vision-based approach to address these issues. Recent efforts have focused on developing and evaluating routines for performing bone detection and yield estimation on deboned poultry products. Researchers collected approximately 2,600 images of deboned product at a poultry processing plant. This included 2,500 images of product taken directly from the deboning line, and 100 samples of birds before and after performing a manual yield assessment process. In addition, several hundred additional frames from different processing facilities were imaged in the laboratory. During testing the system was able to classify 100% of missing clavicle bones from the test data. However, there was a high false positive rate of 20%, primarily due to broken clavicles without missing bone chips. Fan bone detection accuracy was 82%. More promising was the yield results, giving a correlation of 90% with the data tested from the field testing. However, testing the yield estimation routines on birds from a different producer only yielded a correlation of 72%. This approach still shows promise for detecting bones as well as demonstrating the ability of monitoring process yield in real time. Research is underway to refine the yield estimation and bone detection routines and perform robust field testing on the final pre-production prototype system.   

Developing workplace safety methods and technologies

ATRP has several initiatives in the area of Worker Safety specifically targeted for the poultry industry. A recent study investigated the use of the WiiFit gaming system as an intervention method to reduce the risk of lower back injuries during lifting compared to the traditional methods of strengthening hip flexor muscles. Analysis comparing the leg and back motions of the study subjects measured during the lifting tasks conducted before and after the training program showed that using the WiiFit as an intervention improved lifting technique by reducing the change in back and knee angles and increasing the change in hip angle. In addition, participants found the WiiFit to be enjoyable and reported improved cardiovascular endurance over the Traditional and Control groups. Researchers have also used MotionPlus Wiimotes to record human kinematic motion data on a laptop PC. The rate gyro data of the Wiimotes was processed to examine the joint angles of the participants performing the lifting tasks. Overall, the WiiFit gaming system shows promise of being a low-cost and yet effective physical conditioning program for poultry plant workers. Researchers are currently focused on creating a low-cost, portable, and easy-to-use Mobile Motion Capture (MiMiC) system. The new MiMiC system is intended to be a tool for ergonomists and plant managers to use in the plant environment to assess workers’ movements as they perform their jobs without needing assistance from experts and expensive equipment. The envisioned prototype will use a smartphone to record kinematic data from wireless motion modules. Data collection from Bluetooth 6-degree-of-freedom inertial motion units (IMUs) is underway with the ultimate goal of creating a field-testable prototype.