Reconfigurable Manufacturing Systems (RMS) is a modern engineering technology addressing changes in manufactured products via rapid reconfiguration and improved flexibility of manufacturing systems – machines, controllers, design methods, and software modules. RMS consists of networked robotic machines working in collaboration with humans. To transition existing machine tools and industrial robots to RMS, it is necessary to enable self-awareness in these robots, namely, real-world situational awareness and a capability to adapt their modes of operation to the situation. Self-awareness is a computational capability for which this proposal provides estimation, planning, and control technology.

Briefly, the proposed technology relies on capturing user specifications in the form of Linear Temporal Logic (LTL) formulas. The proposed technology uses advanced graph search algorithms to find an optimal sequence of decisions or actions (namely, the shortest path) to satisfy these specifications, which can adapt quickly to changing requirements. The long-term project objective is to develop mathematical, algorithmic, and simulation tools to enable a networked collaborative self-aware robotic RMS solution to be prototyped at Warner-Robins Air Logistics Complex and later commercialized for deployment in other manufacturing facilities.

Following a successful Phase II Air Force SBIR award, ALAE Solutions is now actively demonstrating the value of integrating Smart Manufacturing Technology (SMT) with the typical manufacturing process by developing, testing, and evaluating novel Predictive Maintenance and Digital Twin technologies.  Working closely with researchers from Georgia Southern University we hope to ascertain that AF depot component inspection, repair, and quality control processes are operating reliably, efficiently, and expeditiously. Current AF depot maintenance practices are reactive and lack the tools to improve the assets’ readiness further.  There is an urgent need to improve industrial processes and introduce analytical methods to produce a product that meets or exceeds Navy and Air Force requirements and specifications.

Many Condition Based Maintenance (CBM) technologies have failed to provide optimum maintenance strategies because of inadequate and poor choices for extracted features or Condition Indicators (CIs).  ALAE Solutions proposes a dual approach Predictive Maintenance (PM) Paradigm to address critical shop components/systems’ on-process maintenance/systems in real-time.   Our approach involves the utilization of Intelligent CBM to develop, test, and evaluate a dynamic Smart Predictive Maintenance (SPM) methodology for critical manufacturing systems supported by a novel Digital Twin framework to optimize the manufacturing system design, maintenance practices, and policies.

Data has become an essential part of new and “smart” technology insertion to the manufacturing floor in recent years. Most industrial processes are controlled by PLCs or computer control apparatus and are instrumented with sensors dedicated to the control activities. ALAE Solutions has taken advantage of these sensors and complemented them with devices specifically designed to monitor faults of failure modes (for example, accelerometers measuring vibration signals). By maximizing SMT use in sensing and data mining, ALAE Solutions is presently developing and demonstrating intelligent software technologies for CBM, advanced diagnostic, prognostic, real-time health monitoring, and remaining-useful-life (RUL) reporting. This will enable all information about the manufacturing process to be available when needed, where it is needed, and in the form that it is needed across entire manufacturing supply chains, complete product lifecycles, and multiple ALCs. The benefits to the AF depot at WR AFB and other ALCs and the maintenance community, in general, include continuous online health monitoring and assessment, optimum maintenance overhaul/repair schedules for equipment spare-parts/personnel/facilities/tools, maintenance cost reduction, improvement of equipment reliability/safety (avoiding catastrophic failures), optimum planning/scheduling for equipment and facilities and reduced maintenance induced failures.

Commercial applications span numerous industries, and broad interest is expected from governmental and private entities, within the U.S. and abroad concerned with the maintenance or production of complex end-items or systems.  Potential beneficiaries include DoD and other governmental aircraft and other system maintainers, private manufacturers, and other professional services.  Commercialization would increasingly extend to all sectors requiring highly adaptable, reconfigurable modes of industrial operation.

Ezebuugo Nwaonumah joined the ALAE Solutions Team in 2020 to augment our effort to demonstrate Prognostic Health Management (PHM) technologies targeting Air Force depot machinery. Mr. Nwaonumah brings a masters in Mechatronics (with AI Robotics Research and PLC Projects) to the team and will play a major role in developing our Digital Twin Framework and realizing a systematic approach to Predictive Maintenance.  Eze has relevant experience creating continuous improvement plans for CNC machines by applying FMEA and LEAN manufacturing standards to minimize machine part failure. His experience at Anthony Inc.  where he designed CAD drawings and programmed CNC and product testers along with his research in wheeled mobile robots will underpin our current and future clients.