SBIR-STTR Award

Digital Twin technology has the potential to close the gap that currently exists in the life-cycle management loop. The operations goal is application and integration of appropriate processes, technologies, and knowledge-based capabilities to improve performance, reliability, and maintenance effectiveness. By synchronizing real-time asset operation, physics based virtual models, and logistics intelligence the operator has a complete cradle to grave view of an assets design, current state, and predicted state under a wide range of operating load conditions. BluEyeQs Phase I research objective is to close the mission readiness loop between the physical and virtual world via a Digital Twin platform using data from all available entities. For success we focus our efforts on a scalable platform approach that accurately predicts and models life-cycle operation across a broad component mix. This approach features innovative Computational Intelligence that monitors machine vital signs and diagnoses health based on measured and predicted performance parameters. We build off our existing industrial solution and demonstrate feasibility on active industrial gearboxes.

Benefit:
The Navy faces mission critical challenges for maintaining the operational mission readiness of the fleets air, sea, and logistics support assets. Managing the acquisition and sustainment of DOD systems across the entire life-cycle requires focused attention by leadership and program managers to develop and support advanced monitoring strategies. Digital Twin technology can lead to an overall total cost of ownership reduction and maximize mission readiness with clear insight into all facets of machine operation. With enhanced machine state visibility, minimized downtime, and optimized inventory management there is a clear path to commercial application of our research and development. BluEyeQ is currently an active industrial supplier of IoT based predictive maintenance solutions in the steel, amusement park, automotive, pharmaceutical, and performance racing markets. Transition of our enhanced Digital Twin solution will be targeted toward Naval Fleet Readiness Centers, Cost Guard, Homeland Security, and other DOD agencies.

Keywords:
Edge Computing, Edge Computing, IOT, FOG computing, Predictive maintenance, Digital twin, Condition Based Maintenance, AI, Machine Learning

In Phase II, BluEyeQ proposes full prototype implementation and airframe validation of our Internet of Digital Twins mission readiness platform. Our basis project goal is delivery of a rapidly adaptable, cost effective, and scalable platform for adoption across many components not only within a specific airframe, but across many machines and industries. In Phase I we defined and demonstrated feasibility of our proposed Digital Twin anatomy as applied to Industrial equipment and showed a valid transition path to the V-22 Osprey drivetrain. In Phase II we propose a similar tact where we leverage data access to our Industrial customer equipment for Digital Twin development and in parallel validate our model operation on Navy assets including the V-22, potentially the H-1 platform, and others as available.

Benefit:
The key Digital Twin benefit is reduction in system total cost of ownership. Reductions are achieved by maximizing and extending asset useful life, reducing unplanned down time, and reducing total maintenance costs. Unplanned maintenance is typically the most expensive and unpredictable on labor resources and supply chains. Additionally, reductions in standard, and often unnecessary, preventative maintenance cycles limits the incremental burden of labor and parts due to sheer scale across the asset fleet. Cumulatively process inefficiencies create a death by a thousand cuts scenario where valuable monetary, human capital, and inventory resources are unnecessarily applied. BluEyeQs Digital Twin approach factors information from all the life-cycle maintenance categories. We make machine health decisions and display that information to the consumer in a 3D modeled representation of the digital twin . The Prognostic model without physics gives no insight as to the why something failed, nor does it provide complete certainty that it will fail or is failing. Physics coupled with statistics adds the dimension of knowing why something will likely fail but is also based in likelihood . Coupling these techniques with Predictive (vibration analysis) provides the validation that something really is in early-stage failure and needs to be replaced. By coupling all maintenance disciplines, a much higher degree of component replacement confidence can be achieved. Logistically, inventory purchasing decisions are made well in advance of a failure, maintenance and repair personnel and materials are scheduled and prepared, and potential failures are first validated without the risk of unnecessary repair.

Keywords:
Predictive maintenance, Condition Based Monitoring, Digital twin, IOT, Machine Learning, Artificial Intelligence