top of page
Writer's pictureMatthew Barber

The Future of Smart Manufacturing: Harnessing the Power of MES Intelligence and AI

Introduction

In today's fast-paced manufacturing landscape, the role of Manufacturing Execution Systems (MES) has evolved significantly. Once seen as merely a tool for tracking and monitoring production processes, MES now offers a gateway to the future of smart manufacturing. By harnessing the power of MES intelligence, manufacturers can unlock unparalleled operational efficiency, agility, and innovation.


MES is a rapidly growing market, and the gap between the most advanced and least advanced manufacturers is growing. Many manufacturers are still on paper based systems, Excel, or a mismatch of operational applications. Advanced companies are already leveraging some of these technologies to gain a competitive edge in the market.


MES is already the centre of Operational Intelligence

At the core of smart manufacturing lies the ability to collect, analyse, and utilise real-time data. MES serves as the central hub for operational intelligence, providing manufacturers with a comprehensive view of their production processes, pulling in data from various sources. This data-centric approach enables manufacturers to make informed decisions, optimise resources, and improve overall productivity.


Imagine a bustling factory floor, filled with workers, machines, and a constant flow of materials. In this dynamic environment, MES acts as the brain of the factory, capturing and processing data in real-time. It collects information on machine performance, production rates, quality metrics, and more, transforming raw data into actionable insights.


MES allows manufacturers to gain real-time visibility into their operations. They can track the progress of each production order, monitor machine utilisation, and identify bottlenecks or inefficiencies. This level of transparency allows for proactive decision-making, helping operators to quickly address issues and make adjustments to optimise their processes.


But increasingly, MES doesn't stop at data collection and visualisation. It goes beyond that by integrating with other cutting-edge technologies, such as Artificial Intelligence (AI) and Machine Learning (ML). These technologies bring a new dimension to operational intelligence, enabling manufacturers to unlock the true potential of their data.


Often, people throw around terms like AI and ML, but let me just give you my take on these topics. I believe there are two key ways these technologies can be leveraged for MES:

  1. MES performs analysis in real-time on it's own data-sets. I'd argue that MES has already been operating in this sphere for a long time. For example though the use of SPC (Statistical Process Control) for measurement data, and by offering predictive maintenance for asset care (see more below). Insights are immediate, and can easily be shared with the operational users.

  2. MES shares it's rich data set with a technology platform designed for AI/ML, and other emerging technologies such as RPA (Robotic Process Automation). Not many MES systems are currently able to leverage this advancement in technology, there is a lot of hype and marketing out there, but watch this space, as it will evolve. There are some vendors with this technology available (ask if you want to know more), which is incredibly exciting. Insights here are more focussed on continuous improvement, or retrospective analysis of the process. There must be a feedback loop to MES for the insights to be displayed in the MES to operational users.


SPC (Statistical Process Control)

Many MES applications already take advantage of SPC for quality control. By continuously monitoring production parameters, MES can detect deviations from desired specifications and trigger alerts. This early detection allows manufacturers to take corrective actions promptly, preventing the production of defective products or minimising their impact. With MES, manufacturers can ensure consistent product quality and compliance with industry standards.


Predictive Maintenance

By leveraging AI and ML algorithms, manufacturers can analyse vast amounts of data and identify patterns or anomalies that might go unnoticed by human operators. For example, detecting subtle changes in machine behaviour that could indicate an upcoming breakdown or failure. This predictive maintenance capability not only helps prevent costly breakdowns but also extends the lifespan of equipment, resulting in significant cost savings.


With technological advancements in these fields, new exciting opportunities and use-cases are opening up to further exploit process data, beyond the current capabilities of MES.


MES provides rich real-time data sets for use in AI/ML

MES has revolutionised the way manufacturers operate by providing access to vast amounts of accurate, real-time data direct from the shopfloor. This data is a goldmine for companies looking to leverage Artificial Intelligence (AI) and Machine Learning (ML) algorithms for advanced analytics and predictive modelling.


Advanced algorithms like these are only as good as the data and hypothesis they are built on. MES provides the data - so is absolutely crucial to these initiatives.

By harnessing the power of AI and ML, manufacturers can gain valuable insights and actionable intelligence from their MES data. One of the key benefits is the ability to analyse both historical and real-time data to identify patterns and trends. This enables AI-powered MES systems to make decisions and predictions based on what it knows. A trained model making decisions is better than a human, and more consistent than multiple humans across shifts - so it doesn't matter who is working, the business processes are always followed in the same way..


Imagine a scenario where a food processing company utilises an AI-driven MES platform to monitor the quality of their products. The system continuously analyses data from various sensors, such as temperature, pressure, and moisture levels, to ensure that the production process is within the desired parameters. If any deviations are detected, the system can automatically adjust the settings or alert the operators to take corrective actions.


Or, a filling plant records a set of parameters around the fill cycle, such as fill speed, fill level, fill pressure. Depending on the parameters, the MES might recommend changing the fill nozzle, increasing the fill speed, or initiating a cleaning procedure.


AI/ML is not a "black box", it doesn't just magic up answers, you need to make a hypothesis, and train a model.

A common misconception is that AI/ML will take all of the data and give you insights. That's not strictly true, what you really need is a use-cases, a hypothesis, and a model. These technologies are incredible, and very powerful, but they aren't a silver bullet. To really leverage advancements like this, you need a team of people working with the technology to gain deeper insights into the process, make predictions around which parameters could have an affect on the output, and to ensure those parameters can be fed into the model. The model will need adjustment and tweaking over time to get right.


Enhancing Manufacturing with Robotic Process Automation (RPA)

The integration of AI in manufacturing processes offers immense possibilities. AI-powered MES will revolutionise the way factories operate, bringing about a new era of efficiency and productivity.


One of the key advantages of AI in manufacturing is its ability to automate routine tasks. With AI-powered MES platforms, repetitive and time-consuming tasks can be delegated to intelligent machines, freeing up human workers to focus on more complex and creative activities. This not only improves productivity but also reduces the risk of human error, ensuring consistent and high-quality output. The automation of tasks through AI is often referred to as Robotic Process Automation (RPA).


Machine Learning (ML) for Data-Driven Decision Making

Machine learning is a way to train an algorithm to predict an output based on a data set. Once the model has been trained, it can analyse future data sets faster and more accurately than a human.


With ML algorithms utilising data from the MES platform, manufacturers can make data-driven decisions with confidence. ML algorithms can monitor and analyse vast amounts of production data in real-time, identifying trends and anomalies that are difficult to detect manually.


Rise of Robotics in Manufacturing

In recent years, robotics has emerged as a key driver of innovation in the manufacturing sector. Robots offer unparalleled precision, efficiency, and flexibility, leading to reduced costs and increased productivity.


MES plays a crucial role integrating robots into the manufacturing environment. By connecting robots with MES systems, manufacturers can achieve seamless communication, monitor performance, and gather real-time data for analysis.


A good example of this is the use of Automated Guided Vehicles (AGV's) on the shopfloor, and in warehouses to automatically move inventory around the factory, at the right time. MES communicates with these vehicles to instruct them on where to deliver inventory, and where to collect materials from.


Leveraging Automation for Efficiency and Agility

Automation on the shopfloor has been around for decades, so it's nothing new. But increasingly, the sophistication around the automation and the integration with MES applications is on the rise. In a modern factory, it's now unthinkable that the equipment would run without high levels of automation, and an MES system in place to harness the data, and in some cases directly control the process.


MES often holds master data, such as machine set points that can be automatically sent to the shopfloor equipment to ensure machines are configured correctly without operator input, speeding up changeovers and reducing errors.


Augmented Reality (AR) in the Manufacturing Environment

AR promises to revolutionise the way manufacturers design, produce, and maintain their products. By overlaying virtual information onto the physical world, AR technology enhances productivity, improves worker training, and simplifies complex assembly processes.


The vision put forward for AR and MES is that real-time information will be displayed to operators, allowing them to seek remote assistance, and step-by-step guidance for their processes.


I'll be honest, I'm unsure on the use of AR on the shopfloor. I have a few objections here:

  1. It can't be AR goggles. If you've ever worn a pair of these you will know how disorientating they are. You are submersed in a virtual world, and the physical world is no longer visible. This isn't practical or safe on the shopfloor, so at the very least we need a step-change in hardware here to make this vision a reality.

  2. General health and safety concerns. On many shop floors, you aren't even permitted to wear your wedding ring, let along additional technological hardware.

  3. The best MES systems allow the operator to get on with their job, supporting them when needed and empowering them through data. Having MES data in your face the whole time is more of a distraction.

  4. AR via a phone could be an alternative option, but do employers really want everyone on the shop floor to have their phones out to run their processes.

I'm sure that in future some of these problems will be solved, and it also depends on the manufacturing process. But right now I'm not convinced when people tell me they think AR on the shop floor is the future.


IIoT (Industrial Internet of Things) Integration with MES

IIoT is a conceptual framework involving data collection from sensors.


MES is a system within this framework, facilitating data capture from IoT devices, through a range of methods.


The integration of IoT devices through MES opens up new dimensions of connectivity and data exchange in manufacturing. By connecting various devices and sensors, manufacturers can gather real-time data, monitor equipment performance, and improve overall operational efficiency.


MES is part of the IIoT landscape. In many cases MES enables IIoT, it's the foundational system that reads in many of the inputs and sensors, and data from other 3rd party applications.


IoT is already a reality for many MES providers, but watch this space as new protocols and capabilities unfold.


Digital Twin

A digital twin is a virtual representation of the physical world, and MES is a virtual representation of a physical factory. So in it's simplest terms MES is a digital twin, keeping track of the current and historic state of the manufacturing facility.


Digital twins are also used for simulations and "what-if?" scenarios. For example, simulating how a production line would run with 1 more operator, or 1 more parallel machine on the bottleneck operation.. Or hypothesising what would happen if the tool was changes later or earlier.


Data-driven decision making is crucial, and this is a tool that could help support investment decisions, and also help drive efficiencies throughout the factories.


Generative AI

It would be remiss of me to not mention Generative AI.


Many people still get Generative AI confused with AI. Generative AI is actually a subset of AI that can create content, such as text, images, or music, by learning patterns from existing data. It's different from normal AI because it doesn't rely solely on pre-programmed rules but can generate novel, human-like content based on the patterns it has learned.


This technology is actually really exciting for MES, and for other Enterprise applications. Particularly around a few key themes:

  1. Being able to ask questions of the MES data, and getting back explanations, charts, reports, and other data visualisations:

    1. Write a 1 page report for my continuous improvement manager explaining OEE trends over the last 12 months, highlighting anything that could have impacted the results, and any suggested improvements.

    2. Show me a pareto of all critical defects this week across all welding machines, and give a short explanation to explain the results I am seeing.

  2. Using generative AI to configure MES systems:

    1. Configure a new packing production line "PACK-7" in the Packing department, ask me any questions you need to successfully configure this new asset and complete all relevant setup.

  3. Using generative AI for help and access to relevant documentation:

    1. What is the calculation for Cpk?

    2. Explain what this screen is showing me.

There will be other use-cases for sure, but just think about the kinds of examples above, and how useful they would be.


Summary

The future of smart manufacturing lies in the effective utilisation of MES intelligence.


By harnessing the power of real-time data, integrating technologies like AI, ML, RPA, robotics, AR, and IoT, manufacturers can unlock unprecedented levels of operational efficiency, agility, and innovation.


MES is the centralised hub for all of these innovations, because MES harnesses they data. MES acts as the central nervous system for the factory, all operations run through MES.


As the manufacturing landscape continues to evolve, embracing MES as the central hub of operational intelligence becomes a necessity. By investing in advanced MES platforms, manufacturers can position themselves at the forefront of smart manufacturing, driving growth and staying ahead of the competition.


223 views0 comments

Recent Posts

See All

Comments


7-01.png
bottom of page