Predicting Production Delays and Expected Yields in Future Batches

Predikto will be releasing a new Advanced Analytics solution that will enable operators at continuous manufacturing facilities to predict production delays, asset failures, and expected production yield for future batches without the need to send us sensor data on a daily basis.

Operators will enter future batch settings like Steel Quality, Billets, Speed, Temperature, and a handful of other information.  Predikto will show in a simple graphical web form the risks embedded in the batch and the recommended settings to maximize yield and reduce the probability of having delays or failures with their equipment.  This could be a game changer. Stay tuned…


4% of companies over $1B are really good at analytics. Are you one of them?

A recent blog posting by Bain & Company called “The Value of Big Data: How Analytics Differentiates Winners” surveyed executives at more than 400 companies around the world, most with revenues of more than $1 billion. A small excerpt from the article is below:

The results were surprising: We found that only 4% of companies are really good at analytics, an elite group that puts into play the right people, tools, data and intentional focus. These are the companies that are already using analytics insights to change the way they operate or to improve their products and services. And the difference is already visible. These companies are:

– Twice as likely to be in the top quartile of financial performance within their industries
– Three times more likely to execute decisions as intended
– Five times more likely to make decisions faster

It is important for companies to develop advanced analytical capabilities around data, tools, people, and organizational intent. Predikto offerings are one small portion of analytics with an emphasis on predictive analytics, but customers sometimes tell us “The ability to predict is the holy grail, we just need help with advance analytics to help understand root cause and the past”.

IPEMAN – Peruvian Institute of Maintenance

I had the pleasure of meeting Victor Ortiz at the IPEMAN offices in Peru earlier this month. Mr. Ortize heads the Peruvian Institute of Maintenance (IPEMAN) in Lima, Peru. The institute is the leading organization in Peru (and third largest in Latin America) providing training, certifications, audits, and overall maintenance and reliability excellence to asset intensive enterprises in Peru and throughout Latin America. He has been in this journey of knowledge sharing and best practices for asset reliability for over 20 years. I was not able to attend their 13th symposium “Congreso” last month due to the SMRP show in Indianapolis, but I will plan on attending next year. Over 500 representatives from organizations throughout Latin America attending the event. For more information, visit IPEMAN at

If it has sensors and it failed in the past, we can predict future failures!

Predictive Analytics is a proven technology for detecting and diagnosing emerging reliability problems far earlier than traditional methods. It is also a non intrusive method that should not be introduced to complete other predictive maintenance techniques and processes.

Some maintenance experts or operational executives believe it is difficult to predict failures in advance. They are correct that is is difficult, but Predikto makes the process very simple by performing a Proof of Concept on a few key assets without the need to install any software or build automated interfaces.

We love these challenges. We have a simple answer for skeptics: “If it has sensors and it has failed in the past, then we can predict when it will fail in the future”. It all starts by clients giving us some sample data and Predikto shows them what can be predicted in that particular case.

Reliability Analytics – Get Ready For It

Predikto spent two days at the SMRP show in Indianapolis last week. It was our first show and there were hundreds of representatives from many large organizations looking to learn about the latest technologies and process improvements to increase asset reliability and maintenance. It was very interesting to see Predictive Analytics or Reliability Analytics (as some people call it) as a trend that everyone was talking about and very few companies are actively doing. Some reliability experts where asking a lot of questions about Predictive Analytics and how it actually works, what type of predictions can be provided, and more importantly how to get started. Some clients were getting ready to hire IBM for large initiatives involving software and services acquisitions. Others had tried it inside SAP or other EAMs with limited success. Predikto recommends clients to start small with a targeted Proof of Concept and build from the early successes.

7 Railroad companies spend $9B in maintenance and still experience 23,000 failures / yr


Class I railroad companies spend $9 Billion a year to maintain their network of 140,000 miles of rail, 28,000 locomotives, and 1.4M rail cars. Reliability has improved dramatically in the past 30 years, but they still experience about 23,000 equipment caused failures and 150 derailments each year.

Railroad companies must implement Predictive Analytics capabilities to take their operational performance to the next level. Railroad companies have invested in advanced monitoring technologies that are capturing a wealth of information. Unfortunately, this data is not being used to predict likely failures in the future.

Predikto invites you to attend a live 30 minute webinar that highlights the ways Predictive Analytics can have a significant impact in railroad reliability and cost reductions.

Attendees will learn:
– How railroad companies are using Predictive Analytics
– How to prepare and get started with Predictive Analytics
– 5 specific examples where data you are capturing today can be used to improve reliability

Join a 30min webinar to learn more about Predictive Analytics in the Railroad Industry.


Traditional Predictive Maintenance is missing a key component

Predictive Analytics complements and improves on traditional DCS, vibration, and other systems making up traditional predictive maintenance practices. These predictive systems are not intended to provide early warning. Rather, they are deployed to prevent significant equipment damage or failure.

Traditional monitoring systems are set to detect and prevent catastrophic damage. Alert levels must be set relatively broadly in order to prevent false alarms due to a wide range of operating conditions. Once a potential failure is detected, the time an operator has before equipment functional failure is often very brief, thereby limiting the options available to correct the situation.

Predictive Analytic software by using statistical models leverages existing infrastructure and systems to provide analysis and earlier warning of emerging issues.  Instead of reacting to the emergency alarm, statistical models for predictive analytics can give you warnings days in advance.

Predikto has developed these predictive analytics models.  Give us a call to see if your data and maintenance processes qualify.