Case study

Industrial IoT Predictive Maintenance Solution for Manufacturing Hubs

We’ve built an intelligent monitoring platform for condition-based predictive maintenance to ensure asset health and 100% equipment uptime

Cloud & DevOpsInternet of ThingsPlatform Development
Project highlights
  • Provide real-time visibility into the condition of plant assets 
  • Proactively maintain and manage mission-critical industrial equipment
  • Maximize uptime and prevent asset failure with predictive alerts
Team size:
30 engineers
February 2020 – present

Business challenge

Our client is a renowned inventor of novel technology platforms and a world-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 on the research component of their pioneering projects, our client was in search of a capable engineering partner with a product-oriented 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 a scalable IoT predictive maintenance solution for industrial equipment to prevent malfunctions and unplanned plant downtime.

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 These risks are made even more severe by outdated and expiring machinery at plants, which require continuous diagnostics and predictive maintenance services.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 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 Manufacturing Hubs

Solution delivered

Discovery phase

Our cooperation started from a discovery phase driven by a core team of Intellias experts. After a two-week workshop with the client, we began carrying out deep user research on our client’s pilot plants. Our research was focused on the end user experience and gave us an understanding of user personas and user roles as well as processes and limitations of industrial environments. Our team worked out user flows and wireframes and turned them into a clickable prototype, conducted business analysis, and defined the key features needed for the product to meet end users’ needs.

Our experts provided consulting to our client on optimal technologies that would allow them to launch their project right away. We went with an open source IoT platform that provides critical user management functionality and is sufficiently optimized and scalable. In the course of the project, Intellias engineers completely customized the platform for our client’s needs by reworking most of its components to fit project requirements.

Our team came up with a product development strategy that outlined the product requirements and the goals for implementing the platform. We built the design and architecture of the system from scratch, developed a proof of concept and prototype, tested the product on end users, and pivoted it based on user feedback and insights from senior management. Together with our client, we held a prioritization workshop where we mapped out the next steps toward MVP development and what functionality needed to be added during MVP and post-MVP stages.

Team composition

After finalizing the development pipeline, we built an end-to-end engineering team of diverse competencies by bringing together experts from across the technology spectrum. Our team consists of solution architects, UI/UX designers, frontend and backend developers, AQA engineers, business analysts, a Scrum master, DevOps engineers, and a delivery manager.

Over two and a half years of partnership with our client, our managed delivery team has grown from 6 to 30 people and has been divided into three subteams, each responsible for a different product component: a platform, an agent and data acquisition, and a portal.

Platform implementation

The system we’ve developed is an intelligent predictive maintenance solution for remote facility monitoring and management in the manufacturing industry. It provides predictive analytics to eliminate equipment failure and unscheduled downtime and helps manufacturers save significant costs on assets and resources through efficient asset use and maintenance.

Through a network of sensors embedded in mission-critical assets and a set of interactive dashboards, plant operators and maintenance crews can continuously monitor the health of equipment across multiple locations. Dashboards provide real-time visibility into asset conditions, supply chains, loss prevention, financial savings, incident-free production cycles, spare parts replacements, and more.

  • Edge computing

Our team built an agent and a server of the 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.

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 physics-based forecasting algorithms and models developed by our client’s team of data scientists. Unlike ML-based algorithms that require large volumes of data for precise predictions, physics-based algorithms enable accurate forecasts even in non-data-rich environments, such as plants that have been operating for decades. Using processed sensor data, the algorithms determine the remaining useful life (RUL) of an asset and generate systematic alerts and notifications for hidden defects and unexpected events to prevent incipient issues and breakdowns.

Our team was 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 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 and integrations with other systems

Our client’s IoT platform also provides:

  • Optimization of MRO (maintenance, repairs, operations) inventory
  • Supply chain management
  • Integration with distribution resource planning (DRP) solutions
  • Integration with industrial IoT systems and plant control systems

The platform’s inventory management capabilities allow warehouse professionals to eliminate deadstock and ensure all critical components are in stock, especially for those products that take a long time to produce and need to be ordered well in advance.

  • Cloud migration

Initially, for safety and security considerations, our client’s predictive maintenance solution was installed on-premises, with all data stored locally at the client’s plants. However, the external customer demand for cloud-based solutions called for migration from on-premises data storage to the cloud. We suggested the AWS cloud using Kubernetes technology. Our DevOps architect implemented the entire migration process, and our client’s solution is now completely cloud-ready.

From MVP to rollout: Challenges and wins

Despite COVID travel and communication constraints, an MVP for our client’s IoT platform was built from scratch in one year. The MVP stage included on-site pilot installations, integration with industrial IoT systems, data acquisition workflows, execution of algorithms, and generation of accurate results. Acquiring external customers for our client’s predictive maintenance services marked the MVP a success and gave us the green light for full-scale product development leading to production.

The platform is already bringing tangible value to our client’s customers by helping their data analysts detect anomalies and report them to maintenance teams for further diagnostics. The capabilities of our solution are also scaling fast. For one customer, the platform now monitors 36 assets as compared to 4 assets initially.

As our team is helping our client onboard new customers, we handle the challenges associated with the specifics of each customer’s business. We provided a rapid switch to less costly hardware to meet one customer’s need for cost optimization. We helped another customer whose facilities were beyond the internet’s reach change the connection approach from Ethernet to mobile. Even though going mobile with a data-intensive system involved additional hardware and multiple configurations, our experts managed to implement this solution.

Our team is now building a portal for our client that will give enterprise-level manufacturers a macro picture of all their installations across facilities and regions. We’ve also built an effective go-to-market strategy for our client that includes a promotional website and a custom demo version to showcase the platform’s capabilities. With these tools, our client was able to quickly start marketing and sales activities and hold an official product release.

Business outcome

With a combination of IoT expertise and advanced technology services, Intellias has become a software engineering enabler of our client’s predictive maintenance platform for industrial settings. Keeping end users’ needs in mind, our team has delivered a scalable IoT-powered solution for our client from ideation to PoC, MVP, and first pilots up to production and an official product launch.

The platform ensures 100% equipment uptime and has the potential to transform asset maintenance and management across various domains and help our client broaden their market impact by bringing massive cost savings, recurring revenue, and ultimate value to customers.

Since our client’s platform has gone live, demand has rapidly grown among asset-intensive manufacturers. The platform is already operational in the chemical, oil and gas, and construction industries and continues to gain traction in other sectors.

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 Intellias Privacy Policy.
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 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.