Source: PURDUE UNIVERSITY submitted to
Sponsoring Institution
National Institute of Food and Agriculture
Project Status
Funding Source
Reporting Frequency
Accession No.
Grant No.
Project No.
Proposal No.
Multistate No.
Program Code
Project Start Date
Sep 1, 2018
Project End Date
Aug 31, 2021
Grant Year
Project Director
Voyles, R. M.
Recipient Organization
Performing Department
Non Technical Summary
Thecurrent state-of-the-art in animal farming practice is somewhat opportunistic and non-uniform in regard to the use of sensors and direct observation to monitor animal health and farm efficiency. In fact,no current cyber-physical systems (CPS) or closed-loop methodologies exist to monitor and control farm productivity of the entire herd while simultaneously monitoring the well-beingof individual animals within theherd in real-time. We believe this limits the production efficiency of the farm, only ensures the well-being of the average animal inthe herd, and opens the possibility of accidental health hazards. Precision animal agriculture provides intensified, data-driven management of both the individual animal and the combined herd in areas of nutrition, health, productivity, and efficiency to address these limitations. Using trans-disciplinary expertise, this 3-yearproject will create a generic CPS for precision animal agriculture applicable to assist in the management of any type of animal farm. Individual dairy cows in conjunction with a dairy herd within a farm will be utilized as a testbed for CPS development to prove feasibility. Tools for the design of such a system for a particular farm will be generated along with prototypes for thecomponents of a dairy farm to create a CPS for sustainable precision animal agriculture. The proposed integrated system will improve the sustainability of the US dairy industry by addressing key inefficiencies in animal metabolism and health, which are the primary drivers of overall farm efficiency. This new system will also serve as an exemplar for the utility of CPS in other animal agriculture applications. This program will have significant impact on the engineering of CPS by providing a reference architecture for precision animal agriculture that applies to any herd of animals (e.g, cows, goats, chickens, fish). It also contributes to the technology of CPS because novel and trusted principles of systems engineering processes will be used to design and integrate components of the dairy CPS.There is a persistent need to mitigate the negative effects of livestock production on non-renewable and renewable resources. Derivative benefits of this work will satisfy this need through the availability of a generic CPS for precision animal agriculture that can be applied across the farming industry. This new CPS will allow for efficient feeding and health management to optimize milk production while simultaneously reducing the environmental footprint of the US dairy industry. Improving efficiency and/or the quality of life for farmers and animals will have an enormous societal benefit with global implications. Further, this grant will provide training opportunities for 4 PhD students and 2 MS student. Four students will be trained as engineers and two will be trained asanimal scientists. In addition, the team will use the concept of "the connected cow" in outreach to K-12 children at science camps in both West Lafayette and Blacksburg as part of existing programs to excite our largely agrarian communities about STEM. Lastly, we plan to expose the potential benefits of this CPS research to practitioners and researchers with a novel workshop format that includes a live hack-a-thon.
Animal Health Component
Research Effort Categories

Knowledge Area (KA)Subject of Investigation (SOI)Field of Science (FOS)Percent
Goals / Objectives
Precision field crop agriculture is seen as one of a handful of key, early-adoption, commercial opportunities for drones and drone-based technologies because of the demonstrated ability to survey large areas from an elevated vantage point to measure and map crop needs. The time scales for these types of interventions, while highly profitable, are often measured in days or weeks. Precision animal agriculture (PAA), on the other hand, presents a much richer environment for cyber-physical systems (CPS) research. Animals, individually, are complex organisms that require constant nutritional adjustment, yet they are social beasts with herd behavior that emerges from the collective. For issues of nutrition, health, productivity and efficiency, animal agriculture must treat both the individuals and the collective, making it ideal for the science and application of CPS principles. With growing global awareness of the negative effects of livestock production on non-renewable and renewable resources, concurrent with the negative effects of global population growth and the need to feed more mouths, the transformational impact of CPS on the largely unexplored realm of precision animal agriculture is enormous. This is particularly critical as a significant portion of the projected increases in global food production is anticipated to come from ruminants. This proposal presents basic science exploring the complex relationship between individual animal and herd behaviors on agriculture systems efficiency, while demonstrating its potential on the specific area of dairy farm management with the goal of improving sustainability and efficiency. The long-term objective of this team's research is to develop the foundations for CPS that apply, generically, to intensified management of the individual animal and herd in areas of nutrition, health, productivity, and efficiency that underpin this new area of precision animal agriculture. In the short term, based on the CPS principles emerging, this team intends to construct and test a CPS for use in the U.S. dairy supply chain.Livestock production can be thought of as two interleaved feedback loops. The first feedback loop is between the animal and the environment and the second feedback loop is between the animal and the manager. Managers make two generalized types of management decisions: 1) immediate; and 2) relaxed. An example of an immediate management decision would be a farmer identifying his animal as sick, isolating the animal, and calling the vet. We term this immediate because the farmer must identify the sick animal as soon as possible and must react to the diagnosis as soon as possible. An example of a relaxed management decision would be the farmer electing to change the feed provided to his animals in response to something observed about their production (ie., the cows are producing poorly, so change the ration to provide higher nutrient density to correct a nutrient shortfall). This decision is more relaxed because its formulation and response are subjected to natural, biological delays.As steps toward these objectives, a set of 4 specific goals have been identified:1. Develop the decision layer of the generic precision animal agriculture CPS that incorporates flexible animal and herd models, guided by real data examples. Utilize existing data to test model parameterization strategies for feeding and health to reformulate supplement mixes based on real-time performance inputs representing both the individuals and the herd.2. Develop the network layer of the generic precision animal agriculture CPS, including body networking to extract embedded sensor data from individual animals; herd networking and tracking to consolidate and report individual and collective herd data with appropriate edge analytic capabilities; cloud computing capacity and software algorithms to receive, log, and interpret data from the edge to the core; and on-farm production interfaces to evaluate the production environment of the entire system.3. Develop the physical layer artifacts for generic animal and herd networking as well as the purpose-built sensors and actuators for the dairy farm example CPS. Generic elements include an enhanced animal collar/mobility sensor and field-ready wireless access points. The purpose-built elements include an in-dwelling rumen sensor (developed separately, but this project is not dependent on its availability), automated feed delivery device, cow weight sensor, and in-line milk analysis equipment.4. Develop new knowledge based on data networks that link animal and herd data with increased efficiency, profitability and animal well-being. Link the physical, network, and decision layers of the CPS and deploy, test and validate on-farm in two separate, networked installations.
Project Methods
This is primarily a design exercise that will look at the tradeoffs and compromises of constructing a networked system for managing and optimizing animal prodcution and efficiency while improving food safety.Goal 1.2 For emergency signalling of SARA:As an initial step in the data processing procedure, time-series pH data will be analyzed using a 36 h timeframe. The data will be analyzed for time below pH 6, 5.5, and 5; mean, minimum and maximum pH in 4 h segments; and slope of pH over 30 m segments. Depressed fiber degradation is thought to be exacerbated at pH below 5.5. If time of pH below 5.5 is greater than 4 hours, the animal will be earmarked for buffer feeding. The minimum, maximum, mean and slope of pH data will be integrated into the supplement preparation algorithm. As a secondary step in pH data evaluation, the long-term (10 d) baseline pH will be monitored and any significant changes in baseline pH will be used to determine the buffer dosing and whether additional intervention (veterinary attention) is required.To determine the feeding regimen in the Feeding Management System:The basal ration will be formulated using a least-cost approach, constrained to ensure sufficient vitamin and mineral concentrations for high producing cows. Energy and protein content of the basal ration will be constrained to provide sufficient nutrition for the bottom 10% of cows (based on milk production level).Goal 2: Desing of the network architecture will proceed as:In the proposed architecture, sensed data will be queued, processed, and wirelessly transmitted heterogeneously within the system. Time critical data and analytics will be handled in accordance with time-deterministic deadlines specified by the feedback controllers while minimizing power consumption. (e.g. Feeding data can wait until an animal approaches a feed station actuator.) Urgent data and analytics must employ exceptional efforts to transmit data and decisions as soon as possible. Work for this aim will span years 1 and 2.Goal 2.1: Network layer design:Network design and real-time systems design expertise will be employed to develop a novel collection of hardware layers, routing protocols, and distributed decision support across the system to support both top-down and bottom-up decisions and control. These techniques will be applied to the three distinct layers of the architecture to achieve desired performance specifications.Goal 2,2: To integratedata from active sensors at the edge:In Year 1 and 2, the focus will be on collecting data from the passive sensor node with pH, temperature, and oxygen sensing capability. We will rely on commercially available wireless micro-sensors for pH, temperature, O2, and liquid density as a long term goal of the project is to map heterogeneity of microbe populations and fermentation parameters. Design of edge analytics protocols will be accomplished with these sensors as the model.Emergency Signaling:Considering the cow exemplar, specifically, we will establish protocols for multi-hop routing (via the collars of multiple cows) of such emergency signaling information. The fact that the cows are mobile causes this problem to fall within the scope of mobile ad hoc networking (MANET) techniques, and the literature on such techniques contains a large number of different protocols for maintaining routing backbones in mobile networks. However, the general techniques proposed in the literature do not consider the specific mobility patterns that cows will exhibit. Thus, in this project, we propose to develop MANET routing protocols that are tailored (and self-adapt) to the specific motion of animal groups that exhibit certain types of herding or flocking behavior. This behavior will lead to highly connected subgroups of mobile devices being maintained over long periods of time. We hypothesize that subgroups will lend themselves to the cluster-based routing approaches that are typically considered in MANETs and we will thus formulate techniques that leverage these inherent clusters to perform routing (e.g., by periodically assigning the cluster head that is responsible for communicating outside that cluster to different cows in the herd, based on the available energy left in their collars).However, cluster-based routing protocols are primarily proactive and, therefore, inefficient for sparse emergency communications even considering our herding hypothesis. Therefore we will rely on hybrid protocols that combine a proactive cluster with a reactive, on-demand discovery method. We will also extend classical geographic-routing techniques to account for the herding behavior. While such routing techniques often require that the individual nodes know their own locations, the energy intensive nature of such technologies will preclude their use in the bovine monitoring application that we are considering. Thus, we will extend location-free techniques to the herding setting, and seek to identify gains in performance that arise due to the specific mobility patterns of herds. Our research will encapsulate both rigorous mathematical analysis of routing protocols for herd-based mobile devices, and simulation-based analysis to evaluate gains in energy efficiency.Goal 4.1 Feed performance Testing:Two cohorts of animals(n=36 each; one at Virginia Tech and one at Purdue) will be fed in Calan gates to measure individual feed efficiency. Cows will undergo a 7 d gate training period, a 35 d screening period, and two experimental periods (14 d diet adaptation followed by 35 d treatment). Cattle will be partitioned into two groups. During the first experimental period, group 1 will be fed a standard lactation total mixed ration and group 2 will be fed a basal TMR supplemented according to the CPS algorithm for her response category. During the second experimental period, the treatments applied to the two groups will be switched. This will be replicated at VT and Purdue to evaluate the stability of cow sorting algorithms and feeding strategies defined in Obj 1.1, across institutions. In addition to providing greater numbers of animals the use of two locations will help to eliminate any potential bias based on the effects of the system, environment, or animals at a single location.Goal 4.2 Network testingRouting performance will be tested by simulating "urgent" and "time critical" conditions and timing message delivery under various topological scenarios. These will be compared to forensic analysis of actual conditions encountered during tests in Goal 4.1.