Case study

Industrial IoT Predictive Maintenance Solution for Chemical Plant Equipment

We’re building an intelligent monitoring system for condition-based predictive maintenance using IoT components, analog sensors, and forecasting algorithms

Key features

  • Proactively maintain and manage mission-critical industrial equipment

    Proactively maintain and manage mission-critical industrial equipment

  • Maximize uptime and prevent asset failure with predictive alerts

    Maximize uptime and prevent asset failure with predictive alerts

  • Build infrastructure to ensure inventory and supply chain visibility in the future

    Build infrastructure to ensure inventory and supply chain visibility in the future

Team size:
15 engineers
February 2020 – present

C++ / Golang / GRPC / InfluxDB / Mainflux / MQTT / NATS / React.js

Business challenge

Our client is a renowned inventor of novel technology platforms and the world’s leading science and research center that has been at the heart of many prominent breakthroughs of our time. For half a century, the company has been serving as an innovation hub for organizations throughout the world, bringing groundbreaking solutions to Fortune 500 companies, startups, and government agencies and helping them respond to the rapidly changing technology landscape.

Focused primarily on the research component of their pioneering projects, our client was in search of a capable engineering partner with a product mindset and ample development capabilities who could create production-ready software for their systems from start to finish. Our client’s goal was to build an IoT predictive maintenance solution for industrial production equipment to prevent malfunctions and unplanned downtime before they occur.

The new system was specifically targeted at process industries — including the chemical industry — based around batch processing. In these industries, any equipment failure, small operational interruption, or even slight deviation from specifications might lead to lengthy production stalls, immense financial and resource losses, or the threat of toxic hazards. These risks are made even more severe by outdated and expiring machinery at plants, which require continuous diagnostics and predictive maintenance services.

With strong expertise in IoT software development, a user-first product thinking approach, and the ability to build a product from scratch to a scalable enterprise-level solution, Intellias was the right fit for this project. Our rich portfolio of industrial IoT solutions and proven experience implementing predictive maintenance using IoT convinced our client to partner with us.

Industrial IoT Predictive Maintenance Solution for Chemical Plant Equipment

Solution delivered

Team composition

We built a professional engineering team of diverse competencies by bringing together experts from across the technology spectrum. Our team consists of solution architects, frontend and backend developers, manual and automation QAs, UX engineers, a business analyst, a Scrum master, a DevOps engineer, and a delivery manager. We provide end-to-end development of an IoT-powered predictive maintenance platform for our client, from architecture and UI/UX design to implementation and testing. Currently, we’re also building a thorough and effective go-to-market strategy for our client.

Choice of technology

Our work started with consulting our client on the most optimal technologies that would allow them to launch their project right away. We went with the Golang programming language and the open source Mainflux IoT platform, as it provides critical user management functionality and is sufficiently optimized and scalable. Intellias engineers have now completely customized the platform for our needs by reworking most of its components to fit the project requirements.

System implementation

Based on our client’s predictive maintenance case study, IoT sensors were embedded in mission-critical assets to continuously monitor the health of equipment across multiple locations.

  • Edge computing

Our team’s primary task was to build an edge computing system that captures and reads analog sensor signals on edge gateways, generates and stores data on the condition of plant assets, and structures this data to make it ready for further analysis. The intensity of data streams reaches 5 million entries per second.

We’re now building the system full speed ahead. We’ve worked out the architecture for the agent and the server, developed the agent, and are now working on the server. The agent is hosted on edge devices and provides a data acquisition flow by collecting data from sensors, processing and optimizing it, and sending it to the server through a secure communication channel. This data is then combined with other data received from plant control systems, stored, and analyzed by algorithms.

  • Predictive algorithms

Our client’s IoT predictive maintenance system is powered by forecasting algorithms and models developed by our client’s team of data scientists. Using processed sensor data, the algorithms determine the remaining useful life (RUL) of an asset and generate alerts and notifications to prevent incipient issues and breakdowns.

Our team is closely involved in developing and testing the predictive algorithms so they can be efficiently integrated into the whole system and produce accurate results. To this end, we came up with an algorithm manifesto that details the ways in which data should be passed to algorithms, how algorithms should perform, and what results should be generated on the output. The manifesto was approved by the client and simplified integration of algorithms with the edge computing system.

  • Inventory management

Besides the predictive maintenance IoT use case, the scope of development for our client’s platform includes:

  • MRO (maintenance, repairs, operations) inventory
  • Supply chain management
  • Integration with distribution resource planning (DRP) solutions

This will allow inventory professionals to eliminate deadstock and ensure the required stock is available, especially for those products that take longer to produce and need to be ordered well in advance.

  • UI/UX approach

Our design team carried out usability research on the potential users of our client’s solution, how it can be leveraged at other plants, and how it can work with other systems. We defined user personas and user roles, worked out wireframes and UI/UX flows, conducted business analysis, developed a style guide, and built a web UI based on React.

Now we’re working on a set of dashboards, each intended to be used by different personas depending on their roles and needs. These dashboards will provide real-time visibility into asset conditions, supply chains, loss prevention, financial savings, incident free production cycles, spare parts replacements, and more.

  • Data security

For safety and security considerations, our client’s predictive maintenance solution is installed on-premises with no online access. All data is stored locally to maximize the system’s security and protect sensitive data from breaches.

Business outcome

With a combination of IoT predictive maintenance expertise and advanced technology services, Intellias has become a software engineering enabler of our client’s bundled solution for industrial settings. Keeping the end user’s needs in mind, our team is developing a product that has the potential to transform asset maintenance and management across various industries and help our client broaden their market impact by bringing ultimate value to customers.

The system we’re developing helps asset-intensive manufacturers:

  • analyze real-time data to identify trends in equipment conditions and predict failures before they arise
  • receive systematic alerts for hidden defects and unexpected events
  • eliminate machine downtime and save money on assets and resources
  • optimize MRO inventory to ensure all critical components are in stock
  • obtain visibility into supply chain processes to schedule equipment delivery.

As our cooperation continues to dynamically unfold, we’re stepping into a new stage of our partnership. Our team is now nearing completion of the MVP, which includes on-site pilot installations, integration with industrial IoT systems, data acquisition workflows, execution of algorithms, and generation of accurate results. Acquiring an external customer for our client’s predictive maintenance services will mark the MVP a success and will give us the green light for full-scale product development.

Tell us about your project

I give consent to the processing of my personal data given in the contact form above under the terms and conditions of Intellias Privacy Policy. I want to receive commercial communications and marketing information from Intellias by electronic means of communication (including telephone and e-mail).
* I give consent to the processing of my personal data given in the contact form above under the terms and conditions of Intellias Privacy Policy.

Awards and recognition


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

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