Start driving decisions with machine data.
Categories:

     

    Do you remember HAL from the movie“2001: A Space Odyssey”?

    It was considered to be a sentient computer; that is, it had artificial intelligence. Released in 1968, this ‘character’ was prescient to the world of today! If you don’t know the story, the simple version is that HAL is considered a member of the crew on a spaceship. As it begins to malfunction, the human crew decide to shut it down. But HAL has other ideas, namely to do everything it can to continue the mission it has been designed to do. It sets out to kill the crewmen, who are planning to shut it down. In the now famous line, HAL responds to Dave’s (one of the two main character crewmen) request to open the pod bay doors with: “I'm sorry, Dave. I'm afraid I can't do that.” HAL had, in effect, learned to think.

    The movie is a perfect example of how machine learning leads to AI. Since the terms AI and machine learning are often used interchangeably, it’s important to note that there is a distinction between these two areas:

    Machine learning as a subset of AI but is important in that it is also the driving force behind AI. It is more than the notion of applying algorithms to data to elicit a result from the machine. Instead, it is about machines learning how to engage in tasks without being explicitly programmed to engage in them. This shouldn’t be confused with basic robotics, which creates operations with little human involvement, but prone to all the errors and inefficiencies that humans produce in production cycles.

    Machine learning is not quite decision making, so much as building on reacting to parameters input by humans. Machine learning comes first, with automated processes and exception detection, among other “learned” maintenance activities. The next step is for it to make its own decisions and interact with humans.

    “When a machine can tell the difference between objects and make a choice to discard or accept them, AI is born.” (Source)

    Artificial intelligence—AI— is about the evolution of machines into smart machines. In other words, machines that can do more than simply input or output data and respond to process algorithms, but can actually leverage the data from a variety of sources to provide an ‘intelligent’, almost human, response. The machine is in effect replicating human behavior, in terms of decision making and other tasks. In other words, with AI, machines can learn.

    If this is all sounding a little “2001: A Space Odyssey” come to life, that’s because we’re not far off this level of machine / human connectivity and interaction. In fact, the recent uptick in consumer products that use machine learning to assist with our day to day lives, such as the Natural Language Processing (NLP) devices like Siri and Alexa.

    “NLP applications attempt to understand natural human communication, either written or spoken, and communicate in return with us using similar, natural language. ML is used here to help machines understand the vast nuances in human language, and to learn to respond in a way that a particular audience is likely to comprehend.” (Source)

    Why does machine learning and AI matter in manufacturing?

    In a business model that is steeped in legacy technology and age old processes, finding ways to grow, improve product quality, limit unplanned downtime and innovate with short lead times for customer satisfaction are not easy goals to achieve. That is, until the advent of machine learning and AI.

    How can machine learning and AI benefit manufacturing today?

    Smart, lean manufacturing is the goal and technology, including machine learning and AI, is the way to get there. Machine learning can affect factories and manufacturing in many ways:

    1. Automatically detecting degradation in performance in any given production run, for example, can not only improve quality but allow for predictive maintenance, reducing unplanned downtime and ensuring that applicable parts are available on a needs basis. This results in a major benefit to the area of cost controls.
    2. Automating quality testing to limit defects being produced; reducing scrap rates by having higher, more visible control on production.
    3. 24 hour a day production cycles with less manual intervention are possible, with machines able to learn from past production cycles and apply that data going forward, therefore increasing yields.
    4. Eliminating human error when there are complex process controls that need to be exercised in manufacturing a product.
    5. Integrating OEE to ensure that each machine is performing at peak capacity, including applying preventive maintenance to ensure ongoing high yields.
    6. Having data available throughout the factory, at all levels of operations, in real time. This leads to optimized operations on the shop floor, including machine loads and performance indicators for any given production schedule.
    7. Reducing lead time by ensuring optimized inventory control on raw supplies.
    8. Reducing time spent on processes, such as machine calibration, which can be more accurately managed with machine learning.
    9. More flexibility and innovation in being able to create short run products and new designs on a shorter timeline.

    “Knowing in real-time how each machine’s load level impacts overall production schedule performance leads to better decisions managing each production run. Optimizing the best possible set of machines for a given production run is now possible using machine learning algorithms.” (Source)

    Machine learning and AI, as applied to create smart manufacturing, is essential to optimizing performance at all levels of production, eliminating error or guesswork and implementing predictive maintenance and management.

    “In some forms of AI, on the other hand, machines can actually teach themselves how to optimize their performance as they can run through various scenarios at lightning speeds, identify the best processes and train themselves to achieve a desired outcome.” (Source)

    All of these are in the aim of increasing production capacity with a minimum of additional cost (including downtime) and improved quality and customer satisfaction. Ultimately, speed of production relative to high production quality will be a major driver for manufacturers, now and in the future.

    Comments

    Leave a comment

    Subscribe to our mailing list

    Related posts

    Data Driven Manufacturing: Benefits, Challenges, and Strategies

    Data Driven Manufacturing: Benefits, Challenges, and Strategies

    Optimizing Production Efficiency through Data-Driven Manufacturing Strategies Although diverse data capturing technologies exist, manufacturers still struggle to use them. It's due to this major chall...

    MachineMetrics
    MES vs. IIoT Platform: Why Not Both?

    MES vs. IIoT Platform: Why Not Both?

    Is an MES or IIoT Platform (or Both) the Best Option for You? The increasing use of industrial automation in process and discrete manufacturing facilities have put the manufacturing execution system (...

    MachineMetrics
    A Manufacturer's Guide to Edge Computing

    A Manufacturer's Guide to Edge Computing

    Below is what we will cover in this in-depth article on edge computing in manufacturing. Select a link if you would like to jump to a particular section:

    MachineMetrics
    A Long-Term Strategy for Manufacturers Adopting Industry 4.0

    A Long-Term Strategy for Manufacturers Adopting Industry 4.0

    It’s not uncommon for a factory to operate several generations of the same type of production equipment within a single factory. Except for extremely large companies with very deep pockets, most compa...

    MachineMetrics
    MachineMetrics, World Economic Forum Join Forces to Support Sustainable Future for Manufacturing

    MachineMetrics, World Economic Forum Join Forces to Support Sustainable Future for Manufacturing

    Boston, MA -- MachineMetrics, a leading data and digital app platform for manufacturing, today announced that it has joined the World Economic Forum’s Global Innovators Community, a group of the world...

    MachineMetrics
    The Downside to Do-It-Yourself IoT

    The Downside to Do-It-Yourself IoT

    The digital transformation of industrial production enterprises relies on the internet of things (IoT) for connectivity, visibility, and deeper insight into performance. And although the success of In...

    MachineMetrics
    5 Steps to Bring Your Legacy Systems Online with IIoT

    5 Steps to Bring Your Legacy Systems Online with IIoT

    The move to industry 4.0 will be defined by how effectively legacy systems and assets within shop floors are integrated into online or cloud platforms. This is because a large percentage of enterprise...

    MachineMetrics
    Finding the Payback for Smart Manufacturing

    Finding the Payback for Smart Manufacturing

    Industry 4.0 is defined by smart manufacturing processes such as data-driven plant optimization, industrial automation, and predictive maintenance. Since these processes rely on shop floor data, confi...

    MachineMetrics
    Industrial IoT Security: Challenges and Solutions

    Industrial IoT Security: Challenges and Solutions

    With 2020 firmly underway, the exponential growth of Industrial IoT is on track with recent predictions.  And as we head toward a world with over 75 billion connected devices by 2025, almost a third w...

    MachineMetrics