In mid-2017, in Seoul, South Korea, Falkonry CEO, Nikunj Mehta, appeared at the world’s largest start-up Demo Day , sponsored by SparkLabs. He presented Falkonry’s world-changing technology and described how these innovations can help accelerate continuous improvements of operations through condition recognition of time-series industrial data.

Introducing Falkonry’s Capabilities (2m30s)

Keywords: industrial IoT, industrial pattern analytics, industrial condition recognition, industrial pattern recognition, quality, uptime, yield, uptime, performance, creating more revenues and profits, improve throughput, customer issue, problem with ore grade, loss production, cost effective.

Helping Companies achieve Yield Optimization (1m14s)

Keywords: recognize invisible warning signs, classify conditions, 12-hour advanced warning, confidence grows, revenue & profits increase, spiral-up effect, condition recognition, industrial predictive analytics, empowers existing staff, real-time results, time-series pattern recognition, more conditions monitored, predictions get better, democratizes industrial IoT.

Differentiating Falkonry from Others (3m16s)

Keywords: automated, pre-packaged, time-series pattern recognition, machine learning, horizontal, general, practitioner, multi-system, industry, chemicals, energy, mining, automative, reliable, actionable early warning, industrial pattern recognition, predictive analytics without a data scientist, power technology leader, heavy equipment manufacturer, chemicals maker, electric utility, deep expertise, computer science, artificial intelligence, mechanical engineering, electrical engineering, nuclear engineering, operational data, labeling patterns, recognizing conditions, IIoT, 4.0.

At the March 2017 OSIsoft User Conference in San Francisco, joint customer, Ciner Resources (pronounced “jin-ner”) spoke about the digital transformation they were experiencing by employing OSIsoft’s PI system along with Falkonry’s condition recognition software.
 
The three Ciner speakers included their CIO, SMART plant lead and a process engineer.  They spoke about the challenges, triumphs and future goals of transforming their business.  The 25-minute presentation has been segmented into 5 bite-sized nuggets and associated keywords to make for easier viewing consumption.
 
Overall Summary: Ciner’s mine and processing plant in Wyoming has a vertical mill, called a vertimill, that was experiencing unexpected downtime due to “unknown” low quality ore grade. Each time the vertimill clogged, it cost the company $30,000/hour of production potentially leading to a loss of $720,000 per day. 
 
Ciner’s engineers and practitioners worked with OSIsoft and Falkonry to look into historical data to devise a solution. Together they employed the PI System and Falkonry’s machine learning software and within a few weeks, were able to recognize the patterns that led to blockage conditions. From there, an early-warning system was created to detect low-quality ore grade upstream of the vertimill in order to mitigate downtime events.
 Watch Ciner execs talk about their transformation below: 

An Overview of Ciner’s Digital Transformation (3m21s)

Scott Schemmel, CIO, Head of IT at Ciner

Keywords: alignment, digital transformation, value creation, predictive maintenance, IIoT, process optimization, asset health, market value, OsiSoft PI, Microsoft, Falkonry, matter of weeks

Ciner’s “Grade Variance” Problem (5m29s)

Jolene Baker, SMART Plant Lead, PI Admin at Ciner

Keywords: soda ash, ore grade variance, process operators, impurities, grade separation, particle size, expensive losses.

Existing Signals + Falkonry (6m28s)

Wyatt Keller, Process Engineer at Ciner

Keywords: existing signals, inconsistent data, traditional analytics not working, Falkonry trial, no data scientists, SME, analytics, visual patterns, categorizing, labeling, adding context, operating conditions, less reactive, more proactive, enlightenment.

Operationalize Falkonry  (6m27s)

Scott Schemmel, CIO, Head of IT at Ciner

Keywords: two month timeframe, ore grade increases, positive operator feedback, significant benefits, visibility, confidence, tons more production, relatable visual patterns, data science in software not data scientists, cost savings, top line revenue growth, opportunity, time to institutionalize.

Q&A (5m02s)

Scott Schemmel and Jolene Baker from Ciner

Keywords: quicker alarm reactions, more collaboration, empowering, operators, subject matter experts, improvement iterations, detecting operational anomalies, justified our hypotheses, Falkonry with PI, identifies 1st, 2nd, 3rd-level problems, incredible.