IIoT System Analytics


IIoT System Analytics

Reliable Sensors, Accurate Models, Applied Anywhere

As systems become more complex, technology suites that allow for reliable, predictive condition-based maintenance are more challenging than ever. Schedule-driven maintenance practices can result in expensive and unnecessary inspections early in a system’s life and are insufficient as the system ages and deteriorates.

What’s more, the systems supporting traditional maintenance practices have limited accuracy, require extensive training and often result in too many false alarms. This is where PARC’s MOXI™ IIoT System Analytics solution comes into play. Applying the principles of physics to enhance AI-based predictive systems to 90%+ accuracy, our diversified, agile and experienced research & development team will work as a hub between existing technology providers, engineers & facilities or maintenance teams to develop a fully integrated suite of technology designed to provide:

  • Higher Diagnostic and Prognostic Accuracy (90%+)
  • Improved Uptime
  • Longer System Life
  • Valuable Insights for Accurate Long-Term Planning
  • Better Scheduling Accuracy

Through accurate sensing, this technology suite uses AI and IIoT technologies most effectively. By accurately detecting anomalies, diagnosing problem points and prescribing necessary action based on the variables that are critical to system health, our technology suite will streamline operations. MOXI can rapidly enable the transition to truly smart, self-aware systems which yield actionable insights about health, safety and performance.

Contact Me About MOXI


  • Freight & Passenger Rail
  • Bridge & Infrastructure
  • Power Grid Systems
  • Smart Manufacturing
  • Data Centers


How the Technology Works

Design Excellence from Start to Finish



Key stages of PARC’s MOXI IIoT System Analytics technology suite are:

  • Sensing that’s robust enough to yield accurate system data
  • Modeling that’s customized and which can simulate adverse conditions and failures the system is designed to prevent
  • Condition Monitoring that reliably monitors anomalies from expected system behavior
  • Diagnostics that contain efficient reasoning engines which isolate and infer root causes of faults within sub-systems
  • Prognostics that use system models and data to probabilistically predict a system’s useful life span
  • Actionable Recommendations based on decision-theoretic algorithms to promote accurate planning

PARC’s diverse team of researchers collaborate throughout each stage of this process to produce outcomes with the highest accuracy and fewest false alarms, allowing the system to run smoothly and efficiently.

While each piece of the puzzle is critical to success, MOXI’s team of engineers & researchers have perfected three core elements that inform the process and are essential to producing peak accuracy for each specific system. Explore below to learn more.

Sensing     >     Modeling    >     Predicting    >

The Art of Sensing

Sensing is all about accuracy. Accurate data points produced from the sensors installed in a system are the essential foundation of a useful IIoT prediction solution.

Our team can work with any sensors already installed within a system, assessing them for the metrics they are measuring and assuring that they are detecting the correct information at a high enough level of accuracy.

What if the sensors are insufficient or a sensing solution is not installed? Don’t worry: PARC’s team of researchers will work with the engineers, maintenance staff or contractors on site to improve or invent them. With expertise in physics-based sensing technology, our team champions connecting the physical and digital worlds. This is how we are able to produce reliable sensing results that are accurate 95%+ of the time, with negligible false alarms and near-zero missed detections.

The Science of Modeling

Without the correct system model applied to sensing technology, results and recommendations are less likely to hit the mark. Our team will work to make sure sensors are measuring correctly, capturing the data points significant to the desired prediction and matching them to the right system process identifiers.

By using the suite of technologies to store detailed fault-augmentable models, it is possible to perform rapid diagnoses of system behavior over designated time intervals. Through modeling, PARC is able to understand the context of any system and produce the recommendations that are important to maintenance repair operations, improving uptime and transforming the bottom line.

The Accuracy of Prediction

PARC has developed a suite of technologies that maximizes systems’ abilities to predict the need for maintenance, repair or improvement and fully automates prompts which allow maintenance professionals to act in a timely manner.

This capability is light years away from non-automated traditional reactive maintenance practices in which a system, part or component fails and a maintenance professional performs the necessary repair or replacement.

It’s also a step up from preventive maintenance that’s scheduled based on time elapsed rather than on the need for repair or replacement. PARC enables the transition to reliable predictive maintenance, thus initiating the digital transformation to self-adaptive assets, which are highly autonomous.

By improving upon these previous solutions via the integration of AI and IIoT technology, MOXI is able to more accurately predict needs, identify appropriate timing for maintenance to reduce costly down time, and integrate these recommendations into an existing workflow.

Interested in applying PARC’s MOXI, an IIoT System Analytics to your system? Be in touch with one of our experts by filling out the form below.

Additional information

Focus Areas

Our work is centered around a series of Focus Areas that we believe are the future of science and technology.

Commercialization Opportunities

We’re continually developing new technologies, many of which are available for Commercialization.


PARC scientists and staffers are active members and contributors to the science and technology communities.