Case study

Minimizing Downtime and Eliminating Equipment Failures with Industrial IoT: From Reactive to Predictive Maintenance

Industrial-focused PreFix IoT concept for early anomaly detection and effective predictive maintenance

Internet of ThingsSupply Chain & Logistics

Project snapshot

Maintaining machinery in the chemical and manufacturing industries is costly. With the rise of the Industrial Internet of Things, artificial intelligence and machine learning, and data engineering, companies have shifted towards tech-powered solutions to save money.

How does Intellias help? We deliver industrial-focused software solutions, from ideation to innovation, to guide businesses through adopting advanced technology. PreFix, our latest predictive maintenance concept, is designed to help companies maximize uptime and limit potential complications in production.

Minimizing Downtime and Eliminating Equipment Failures with Industrial IoT: From Reactive to Predictive Maintenance

Business challenge

We consider predictive maintenance to be the most efficient model for maintaining industrial equipment, combining our expertise and industry knowledge to bring our clients’ ideas to life. To simplify operations for manufacturers, we’ve developed an industrial equipment monitoring solution concept for detecting anomalies that may indicate heat exchange system breakdowns, liquid leaks in chemical storage tanks, pump system failures, motor vibrations, and more.

Before implementing large-scale IoT innovations, companies prefer to validate initial prototypes. Not many companies would go all-in without evaluating the financial benefits based on a smaller solution such as a proof of concept (PoC).

Global Fortune 500 manufacturing and industrial companies claim to lose over 3 million hours a year due to unexpected downtime, resulting in an $864 billion loss — the equivalent of 8% of their combined annual revenue. Moreover, according to Gartner, the average cost of machine downtime is $5,600 per minute.

Solution overview

The core objective of our project was to address the main problems of the chemical, manufacturing, energy and utility, and construction industries — such as oil and gas leaks and expensive reactive machinery maintenance — with remote monitoring and instant alerting.

We built an edge computing system with pressure sensors and machine learning algorithms for data acquisition and aggregation on edge gateways to monitor and ensure the health of industrial equipment. Working with high-frequency data (around 10,000 records per second), we tried to detect various anomalies to provide early warnings and prevent all kinds of potential failures of critical equipment.

As a result, we implemented an intelligent microservices-based IoT platform for collecting, storing, and analyzing real-time data. Correct interpretation of sensor data allowed us to apply that data further in our predictive maintenance models to minimize repairs and system damage.

Minimizing Downtime and Eliminating Equipment Failures with Industrial IoT: From Reactive to Predictive Maintenance

Intellias PreFix IoT concept

One of the biggest challenges was to monitor a wide variety of high-rate sensor data. With the help of DAQ cards and time-series streams for accurate detection and identification of unexpected issues, we ensured our solution provided real-time visibility into asset conditions and created a single point for high-resolution data analysis and instant leakage or breakdown alerts.

By narrowing down insights from the platform, PreFix models normal conditions and detects abnormalities. PreFix demonstrates our hands-on experience in rapidly validating the feasibility of IoT implementations and outlining the benefits of IIoT for a specific organization. Such an approach not only indicates the state of an asset but also helps our clients validate assumptions regarding the use of their hardware. This way, we can evolve the PreFix concept into a full-scale, comprehensive IoT solution that meets our clients’ particular needs.

Ensure 100% equipment uptime with Intellias technical capabilities and IIoT expertise

Outcomes and business value

Assessing the feasibility of automation ideas while validating key assumptions in terms of solution design and interoperability of components is a critical step before proceeding to a full-scale IoT implementation. That’s why we focused on building a concept the combines development of hardware and software components, including real-time data acquisition, anomaly detection algorithms, data/results visualization, and closed-loop system control deployment to react to changing operating conditions or faults within industrial systems and stop further equipment degradation.

To bring PreFix to life, we aggregated Intellias’ IIoT and predictive maintenance expertise in a comprehensive concept. PreFix showcases real-life IIoT implementations for asset-intensive manufacturers, plants, and factories to optimize hardware costs, prevent downtime losses, and set up issue-free production cycles.

Apart from reducing expenses on fixing issues that have already occurred, another goal of our concept is to showcase the practical implementation of technology to ensure safety in industrial environments. Incidents in chemical or manufacturing facilities may result in personnel coming into contact with toxic liquids or vapors and may lead to catastrophic consequences. Proactive asset management can help companies avoid incidents and unlock new value and growth opportunities instead. The numbers on predictive maintenance presented by Deloitte speak for themselves:

20%

increased equipment uptime

25%

lower maintenance costs

25%

increased productivity

How can we help you?

Get in touch with us. We'd love to hear from you.

    I give consent to the processing of my personal data given in the contact form above as well as receiving commercial and marketing communications under the terms and conditions of the Intellias Privacy Policy.

    We use cookies to bring best personalized experience for you.
    By clicking “Accept” below, you agree to our use of cookies as described in the Cookie Policy

    Thank you for your message.
    We will get back to you shortly.