By Amit Kurhekar

As more and more organizations start thinking and investing in Industry 4.0 and advanced analytics, it becomes very important to understand value drivers and focus on a few key areas to drive visible impact.

In an organization, there could be several value drivers in the context of Industry 4.0. We will stay focused with Manufacturing value drivers today and discuss some of the potential use cases in Asset Utilization and Quality and Sustainability.

Manufacturing’s next act | McKinsey

In a typical manufacturing setup; following are the areas where we will find maximum ROI.

  • Productivity and Throughput
  • Maintenance
  • Quality
  • Energy and Water management (Sustainability)

There could be a few more areas where an organization might find a good return on investment depending on their core business e.g. Inventory, etc.

Why start with above 4 areas:

Let’s discuss why do we need to start with focusing on above 3-4 areas to drive value for an organization. This area (Industry 4.0) is still emerging, the majority of the companies (~70%) of them are still undergoing through Proof of concepts and pilots. To drive the maximum ROI and early return we need to focus on the few and key areas and start seeing returns from a very early stage.

The Maturity Model:

The maturity of these areas differs in many ways, primarily because of the availability of data, ease of execution, the capability developed and simply to put cost Vs benefits. Following is the Industry 4.0 value driver and maturity model.

  1. Productivity and Throughput: This is one of the most known and important areas of a Manufacturing organization because it helps the company to be able to deliver the product more consistently and cheaper. The typical KPI (Key performance indicators) tracked within the Manufacturing company are – Availability, Overall Equipment Efficiency, Downtime, MTBF/MTTR etc. The equipment related data is easy to come and descriptive analytics are fairly easy; this helps the organization to start seeing the benefits of the new digitized technologies. Most of the tools and platforms available today focus on descriptive analytics aspects, visualizations. Mid-Long term I do believe we have a good opportunity to use AI and machine learning to drive this area to the next level. The Predictive (Prognostics) and prescriptive capabilities will help us to know what’s coming up next and how to troubleshoot more effectively reducing downtimes, MTTR’s etc. The ultimate ROI from this use case will drive throughput.
  2. Maintenance: This is the most popular capability in Industry4.0/ IIoT area today known as Predictive maintenance. The value is realized by moving from Time based maintenance to Condition based maintenance to reduce the maintenance costs and also unplanned downtime causing up-time losses. This area is also probably one of the most sophisticated (with predictive capabilities); primarily led by aviation, energy and other high-value asset industries. The primary need of these industries was to avoid any unplanned breakdown as it would be either catastrophic or extremely high losses because of unplanned downtime. However, the data availability in Maintenance area is hard to come in the majority of the companies. Most of the data (if available) is unlabelled and unstructured (in the form of logbooks, excels, manual entries etc). This limits ability to use the latest state of the art machine learning/AI driven approaches to be able to provide actionable prognostics. However, there have been a good amount of success stories using few add-on sensors and anomaly detection methodologies to predict potential failures. These use cases use few add-on sensors on key equipment like vibrations, temperature, etc to predict anomalies and potential failures. Some of the capabilities in maintenance are coming up in AR and mixed reality to remotely troubleshoot equipment.
  3. Predictive Quality: Many industries desire of doing 100% inspection, however, are restricted by availability and ability of a human to perform this, hence rely on sampling and manual inspection techniques. This area still is in detection, statistical process control phase where the quality inspections are done on an interval basis and actions are decided based on these sampling inspections. Wouldn’t it be wonderful to be able to detect a quality issue early on with 100% quality checked and assured? ROI in this area will be delivered by avoiding any quality issues, scrap reduction, etc. This is one of the most powerful areas where returns on investment are going to be extremely positive. However, the technological innovation and advancements are also in early stages in most places. The digital systems mostly detect the presence, check for pass/fail scenarios’.
  4. Energy, Water & Sustainability: Energy, Water, and Sustainabilityis another big area where we have not made much progress apart from descriptive analytics. Some of the digital solutions to capture data are also expensive to install and might not pay out in case of large install base. The key is to understand if Energy and water usage in the site is the most critical factor for reducing the cost of operations. Some of the places this could be useful where there are large furnaces, extensive water usage, and manufacturing/ operations are spending a lot of operational costs. Some of the organizations have successfully implemented descriptive analytics by installing digital energy and water meters in their facilities and by taking actions based on the analysis.

The above use cases are just guidelines to help you get started with your prioritization of Industry 4.0 use cases. This is no way a comprehensive comparison and maturity model across all categories of use cases in Industry 4.0.

Disclosure: Amit works for large consumer goods company, but the views expressed in this post are his own and do not necessarily reflect the views of his employer. 


This article is originally published by Amit Kurhekar on LinkedIn

Mr. Amit Kurhekar is currently serving as Senior Technology Manager at a large consumer goods company and has over 15 years of diverse work experience. In his present role, he is responsible for enabling Smart Manufacturing/Industry 4.0 using AI and Analytics.

Amit has completed his Masters in Engineering from BITS-Pilani and is a certified Six Sigma green belt. He has a unique background in Manufacturing, product design, data science, Simulation & Analytics which brings together skills to enable superior process/equipment design, deployment, and ongoing performance improvement.