Let’s start with an apology. A non-technical explanation of Automated Machine Learning is probably an oxymoron. If you continue reading further, you will come across terms such as “big data,” “anomaly detection” and “Artificial Intelligence”. Nevertheless, we will not delve into the specifics of how algorithms work but provide a high-level explanation of some of the concepts at the core of Industry 4.0.
Merely a few years ago, the field of Machine Learning was limited to academic research. This has changed significantly for three reasons. First, the cost to store, access and analyze big data has fallen significantly thereby opening the potential for its use. Second, cutting-edge technological innovations including Artificial Intelligence applications can now be accessed by organizations of all sizes due to advances in cloud-computing. Third, there is a push on the part of industry to cut costs and improve yield rates by reducing asset downtime. Ultimately, it’s a combination of economic drivers and technological enablers that is bringing Machine Learning to the factory floor.
How is Machine Learning and Artificial Intelligence applied? Industrial plants have hundreds or even thousands of sensors that generate operational data. Traditionally, factories have monitored signals such as machine temperature or vibrations in order to track the health of an asset. Based on past experience, there are warning signals for such as an overheated boiler.
There will always be a role for condition-based monitoring, but when we are dealing with complex and interconnected systems, it is a herculean task to isolate the root cause of a machine breakdown before it occurs.
With Artificial Intelligence, we are looking for abnormal data patterns. This is referred to as anomaly detection. Just like an irregular heartbeat or change in white blood cell count is used by medical practitioners to diagnose a patient, algorithms look for unusual behavior (or patterns of unusual behavior) within the data generated by machines’ sensors.
There are two basic types of Machine Learning – Supervised and Unsupervised. With Supervised Machine Learning, we “train” the algorithm on the underlying asset by providing it with data labels or classifications. When Machine Learning that is Supervised recognizes new data, it then associates it with the data labels that it has already learned. To use a simple analogy: we can train an algorithm to recognize the difference between an apple and orange. When a new fruit is analyzed, the algorithm will apply one of these labels to it and classify the apple and orange accordingly.
With Unsupervised Machine Learning data labels are not provided to the algorithm. Instead, vast amounts of data are analyzed and the algorithm itself generates the label. Returning to our example: the algorithm analyzes large quantities of fruit and categorizes. It was not given an example or definition of an apple or orange.
In the past, data scientists would need to decide about which algorithm to use in a given situation. With Automated Machine Learning, there is a library of hundreds or even thousands of algorithms that can be used. The system itself selects the optimal algorithm for the data without the need for human input.
It is not surprising that Gartner is calling Applied Artificial Intelligence & Machine Learning one of the top technology trends in 2017. Machine Learning is now an integral part of the Smart Factory roadmap. These include GE Predix or Siemens MindSphere offering of the Digital Twin (Supervised Machine Learning) and Presenso’s Automated Machine Learning for Asset Maintenance (Unsupervised Machine Learning).
Like all revolutions, Industry 4.0 brings disruptive change and we expect new leaders to emerge in the industrial sphere. The adoption of IIoT practices requires the convergence of Information Technology (IT) and Operational Technology. In order to benefit from the operational and economic potential from Industry 4.0, the science underlying Machine Learning needs to be a core element of the Operational Technology discipline.
Does Machine Learning for Asset Maintenance apply to your organization? To learn more about Presenso or to schedule a demo, please contact us here.