Demystifying Machine Learning

Machine learning can help organizations improve manufacturing operations and increase efficiency, productivity, and safety by analyzing data from connected machines and sensors, machine. For example, its algorithms can predict when equipment will likely fail, so manufacturers can schedule maintenance before problems occur, thereby reducing downtime and repair costs.

How machine learning works

Machine learning teaches computers to learn from data – to do things without being specifically told how to do them. It is a type of artificial intelligence that enables computers to automatically learn or improve their performances by learning from their experiences.

machine learning stepsImagine you have a bunch of toy cars and want to teach a computer to sort them into two groups: red and blue cars. You could show the computer many pictures of red and blue cars and say, “this is a red car” or “this is a blue car” for each one.

After seeing enough examples, the computer can start to guess which group a car belongs in, even if it’s a car that it hasn’t seen before. The machine is “learning” from the examples you show to make better and better guesses over time. That’s machine learning!

Steps to translate it to industrial use case

As in the toy car example, we must have pictures of each specimen and describe them to the computer. The image, in this case, is made up of data points and the description is a label. The sensors collecting data can be fed to the machine learning algorithm in different stages of the machine operation – like when it is running optimally, needs inspection, or needs maintenance, etc.

Data taken from vibration, temperature or pressure measures, etc., can be read from different sensors, depending on the type of machine or process to monitor.

In essence, the algorithm finds a pattern for each stage of the machine’s operation. It can notify the operator about what must be done given enough data points when it starts to veer toward a different stage.

What infrastructure is needed? Can my PLC do it?

The infrastructure needed can vary depending on the algorithm’s complexity and the data volume. Small and simple tasks like anomaly detection can be used on edge devices but not on traditional automation controllers like PLCs. Complex algorithms and significant volumes of data require more extensive infrastructure to do it in a reasonable time. The factor is the processing power, and as close to real-time we can detect the machine’s state, the better the usability.

Why Invest in Smart Manufacturing Practices?

We’re all privy to talks about smart manufacturing, smart factory, machine learning, IIOT, ITOT convergence, and so on, and many manufacturers have already embarked on their smart manufacturing journeys. Let’s take a pause and really think about it… Is it really important or is it a fad? If it is important, then why?

In my role traveling across the U.S. meeting various manufacturers and machine builders, I often hear about their needs to collect data and have certain types of interfaces. But they don’t know what good that data is going to do. Well, let’s get down to the basics and understand this hunger for data and smart manufacturing.

Manufacturing goals

Since the dawn of industrialization, the industry has been focused on efficiency – always addressing issues of how to produce more, better and quicker. The goal of manufacturing always revolved around these four things:

    1. Reduce total manufacturing and supply chain costs
    2. Reduce scrap rate and improve quality
    3. Improve/increase asset utilization and machine availability
    4. Reduced unplanned downtime

Manufacturing megatrends

While striving for these goals, we have made improvements that have tremendously helped us as a society to improve our lifestyle. But we are now in a different world altogether. The megatrends that are affecting manufacturing today require manufacturers to be even more focused on these goals to stay competitive and add to their bottom lines.

The megatrends affecting the whole manufacturing industry include:

    • Globalization: The competition for a manufacturer is no longer local. There is always somebody somewhere making products that are cheaper, better or more available to meet demand.
    • Changing consumer behavior: I am old enough to say that, when growing up, there were only a handful of brands and only certain types of products that made it over doorsteps. These days, we have variety in almost every product we consume. And, our taste is constantly changing.
    • Lack of skilled labor: Almost every manufacturer that I talk to expresses that keeping and finding good skilled people has been very difficult. The baby boomers are retiring and creating huge skills gaps in the workplaces.
    • Aging equipment: According to one study, almost $65B worth of equipment in the U.S. is outdated, but still in production. Changing regulations require manufacturers to track and trace their products in many industries.

Technology has always been the catalyst for achieving new heights in efficiency. Given the megatrends affecting the manufacturing sector, the need for data is dire. Manufacturers must make decisions in real-time and having relevant and useful data is a key to success in this new economy.

Smart manufacturing practices

What we call “smart manufacturing practices” are practices that use technology to affect how we do things today and improve them multifold. They revolve around three key areas:

    1. Efficiency: If a line is down, the machine can point directly to where the problem is and tell you how to fix it. This reduces downtime. Even better is using data and patterns about the system to predict when the machine might fail.
    2. Flexibility: Using technology to retool or change over the line quickly for the next batch of production or responding to changing consumer tastes through adopting fast and agile manufacturing practices.
    3. Visibility: Operators, maintenance workers, and plant management all need a variety of information about the machine, the line, or even the processes. If we don’t have this data, we are falling behind.

In a nutshell, smart manufacturing practices that focus on one or more of these key areas, helps manufacturers boost productivity and address challenges presented by the megatrends. Hence, it is important to invest in these practices to stay competitive.

One more thing: There is no finish line when it comes to smart manufacturing. It should become a part of your continuous improvement program to evaluate and invest in technology that offers you more visibility, improves efficiency, and adds more flexibility to how you do things.