AI is key to broad manufacturing productivity increase

Over the last several years of deploying AI into manufacturing, we have realized that the time value of our manufacturing engineers is quite high. Any time they spend transferring their knowledge to AI teams is frowned upon by them and seen as being unproductive. On the other hand, any time savings for them is seen as being really valuable to their organizations. A prominent #manufacturing executive we work with even said, “I worry that we can’t produce more even if we put up a new plant because it would take 5 to 10 years to produce a senior manufacturing engineer who runs such a plant. We just don’t have enough trained manufacturing engineers to meet demand.”?

Today AI is well equipped to broadly increase the productivity of manufacturing engineers and, as a result, the entire plant. Remember that increasing productivity means to get the most out of the available resources. As an example, if one manufacturing engineer can drive work through 15 CNC machines now, #AI should easily be able to help us drive work through 20 or 25 such machines.

How? Manufacturing engineers spend a lot of their time identifying events from data. They also tend to chase after yesterday’s problems because their tools do not enable proactive or predictive action. AI can substitute that with automatically identified events and a system of automated explanations that provides a faster understanding of events where intervention or action is needed. This is why we created Falkonry Insight and Falkonry Clue so that we can automate the analysis and do it well before someone asks about it. That also allows us to act based on data and in the moment when the data understanding can be higher.

To address the scourge of upfront effort into setting up the AI, Falkonry’s new patent-pending unattended AI incorporated into Falkonry Insight can go from the initial connection of an entire line to a live AI-based dashboard of proactive events within a matter of 1 week. The elapsed time is simply to establish a baseline of behavior for every single signal. This makes it possible to remove the effort, risk, and cost of AI deployment and judge the AI on its benefits for the manufacturing process engineer as well as the operations team.

Check out our blog and new product announcement for Falkonry Insight to gain an understanding of our approach and how it is vastly different from what conventional machine learning offers. We’re eager to give you a taste of this industry-leading AI capability so hit us up for a demo and let's discuss how Falkonry Insight can transform your manufacturing toward data-driven operations.

In other news

Falkonry Unveiled Automated High-Speed Time Series Anomaly Detection Application The new application, Falkonry Insight, provides a novel way to automatically surface anomalies from machine and process data and equips operations teams to zero in on emerging hotspots, enabling proactive resolutions to issues before they impact the production.

Falkonry presented a new paper at the recent #APCSM conference At the Advanced Process Control Smart Manufacturing Conference in Austin, TX, we presented a?paper titled “Automated, fast multi-timescale, time series anomaly detection for industrial data with Time Series AI”. The paper explains the inner workings of our automated #AI engine and how it can enable an efficient AI-based FDC approach.

Falkonry will be attending the Oracle CloudWorld conference next week We have some news to share about our role in the Oracle ecosystem and we’ll talk about it at the upcoming Oracle #CloudWorld conference. Stay tuned.

Original Content

Falkonry Insight: Automated plant-scale anomaly detection Read on to learn how Falkonry’s unattended AI overcomes the limitations of prevalent AI methods that require the creation and tuning of individual models. Our hands-free approach to data-driven automation increases personnel and operational efficiencies and allows the plant team to stay one step ahead of production challenges.

Interesting Reads

Explainable AI explained. Someday machine learning models may be more ‘glass box’ than ‘black box’. Until then ‘Explainable AI’ can help us understand how a black box model makes its decisions. An interesting deep dive into the topic, this article explains how several types of explainable AI algorithms work.

Prognostic Quality. We've all seen a variation of the popular data analytics maturity model, which starts from descriptive analytics and charts an aspirational path to prescriptive analytics. Now, organizations can aspire to achieve a further step – self-learning prognostic analytics. Find out how the concept maps to quality defect prevention.