‘Industrial AI’ is a synonym for advanced analytics in Industrial Internet of Things (IIoT). The economic impact of the IIoT has already achieved $1 trillion and is rapidly growing. The Industrial AI applications process IIoT data to impact business processes and provide added value.
Internet Revolution created the Internet of People (IoP) where most of the data is generated by people. The IoP impacts 10-15% of the economy. The ongoing Fourth Industrial Revolution (a.k.a. Industry 4.0 or Digital Transformation) is impacting the rest of the economy, a much bigger part. It creates the Internet of Things (IoT), where the data is generated by connected devices.
What does the industry need from the Industrial AI applications, to get the value? First, AI analytics need to be automated and scalable, data-driven. The scalability means a reduced cost of engineering labor. Second, the Industrial AI must support systems and processes that are mission-critical, have high cost or failure. Such AI analytics require rigorous engineering processes to develop, verify, validate, and operate.
Capital-intensive industries rely on their vital assets. Failures and unavailability of assets mean missed schedules and lost revenue. As such, industries spend billions of dollars annually and 60-80% of the annual budget on Operations and Support (O&S). Mitek Analytics provides AI/ML apps for asset Lifecycle Management that allow achieving optimized, sustainable maintenance strategies and running a fleet of assets at peak performance and availability while reducing costs.
Mitek Analytics provides Industrial AI applications, implemented as Analytics Engines for the Maintenance, Repair, and Operations (MRO) related processes of Lifecycle Management. These are killer apps for the Industrial Internet of Things (IIoT). Industrial AI applications enable enterprise-operation monitoring of lifecycle processes for fleets of industrial assets. Addressing the detected anomalies and bottlenecks and optimizing the operations can bring enormous benefits in costs and asset availability.
A local problem in the work/part flows of maintenance and spare logistics leads to system-wide delays and poor availability. The enterprise costs can be staggering with inefficiencies in a few percent of the total CAPEX.
Our Solution is fleet-level Industrial AI for improving asset availability and reducing costs.
- Machine Learning from data to obtain explainable model
- Explainable AI inference based on the trained ML models
- Decision support to improve availability and cost of asset fleet
- A number of companies offer predictive maintenance analytics that is based on operational data collected prior to part failure.
- We analyze processes that happen after the parts have failed. These processes consume the bulk of the Lifecycle Management budget.
Our Industrial AI Analytics was developed by professors from Stanford and Georgia Tech. Renowned experts have received multiple professional awards for work in practical applications of advanced analytics. The subject matter expertise areas of the team include ML, AI, statistics, optimization, operations research, and controls as well as maintenance, logistics, reliability, and IIoT. The analytics is a result of many R&D projects completed over the last 12 years. The team repeatedly won US Air Force and NASA contracts with competition rates exceeding 20 to one.
We offer advanced analytics software and services that can be integrated with existing enterprise data management systems. Our Industrial AI applications implemented as AI/ML Analytics Engines can be used on-line or for generating periodic reports. Our proven applications include the following:
- Reliability Analytics Engine, a packaged AI/ML software application of Reliability Digital Twin (RDT) to perform reliability analysis of failures, removal, and maintenance records for industrial asset fleet.
- Logistics Analytics Engine, a packaged AI/ML application of Reverse Logistics Digital Twin (RLDT) to monitor flows of reparable parts and reverse logistics flows across the part supply and maintenance process chains, and to predict part availability problems.
- Business Case Analysis (BCA) based on the trained RDT and RLDT models. BCA specifies preferred course of action by comparing predicted outcomes, recommends decisions, and provides supporting information.