FREE: Introduction to Uptime Elements Reliability Framework and Asset Management System

In any process automation & control industry, the most widely used control algorithm is proportional-integral-derivative (PID), according to National Instruments. PID control has been widely adopted throughout industrial control markets, dating back to the beginning of trying to optimize any process. What makes the PID algorithm/controller a fan favorite among engineers and operators is the algorithm’s robust performance by nature under a breadth and range of operating conditions. Its popularity also can be attributed to its functional simplicity, enabling control engineers to shorten the learning curve on its mathematical application, all while operating the PID controller with confidence and efficiency.

The day has come when process engineers can optimize their control processes with out of the box, user-friendly machine learning (ML) technology as bolt on features to preexisting PID controllers? To some, this may seem like a pie in the sky concept, but as computing power continues to increase, so will the realm of possibilities. Machine learning will rewrite the definition of how to properly control and tune a PID loop to drive efficiency in a process.

PID loop optimization and tuning will be able to process big data in minutes with machine learning web-driven tools and software packages aimed at detecting and predicting anomalies down to the equipment level before failures or unwarranted process variability overshoots. Just think of the standard software packages used today for visual programming language or to enhance the agility of your operation and add another layer of preconfigured, code free, advanced analytics and ML algorithms to augment their current offerings.

Predictive analytics, a subset of ML, is the key to both monitoring and analyzing vast amounts of asset sensor data and other variables not being factored into the equation today or collected during a multi-variate automation control processes. By adapting to the development of smart infrastructures end users can embrace ML technologies that are web based and simple to configure without having to hire resource intensive, data science or consultants.

SCADA Operator, Meet Your New Copilot: Predictive Analytics

For supervisory control and data acquisition (SCADA) operators, these technologies will act as a real-time, 24-7 virtual operator. Future-proofed advanced process control solutions will collect sensor data for analysis on premises, eliminating the worry for security concerns in hosted cloud solutions and analysis. The key to closing the loop in successful deployments of predictive analytics solutions is pushing the intelligence generated in the Cloud down to the edge in real time. Without overloading the central processing unit (CPU) on programmable logic controllers (PLCs), sensors and controllers, these devices will have embedded, mapped out, advanced algorithms that serve as your extra horsepower and boots on the ground in detecting failures or real-time optimization of the current process at hand. This same copilot will learn, detect and classify patterns within your existing process, enabling operators/engineers adjust the setpoints for optimal control results when transferring that gained knowledge over a hierarchy of similar assets and processes. This concept or theory is known as a digital twin and has been loosely thrown around by all the large industrial giants in the space without properly defining its real-life application or what it means in terms of improving the bottom line of business that drives revenue.

This process of collecting data and deploying edge machine intelligence is iterative. Think of it in parallel of how a newborn baby begins to grow and mature as he or she eats, sleeps and repeats that cycle. Take this same concept and apply it to these levels of algorithms that only get more accurate and confident in their ability to make predictions and optimization decisions with more amounts of big data fed to it. Your co-pilot will create and deploy smart agents, which are advanced machine learning algorithms that proactively monitor vital areas in your process for early stage failures, quality issues, safety concerns and environmental events. What was traditionally performed using teams of aging subject matter experts (SMEs), process control engineers and data analysts has now been digitalized into an extra set of virtual eyes and ears that never complains, gets sick, or throws in the towel when the going gets tough.

Advanced Process Control: The Technology of the Future Isn’t Smoke and Mirrors

Historical, present and future data, coupled with external or unforeseen variables, have yet to be utilized for PID loop optimization calculations until the advent of machine learning. Engineers have traditionally resorted to their own applied education, tuning controller inputs to the best of their ability in order to achieve optimal PID loop process calculations. Advanced process control incorporates both supervised and unsupervised learning capabilities, combining state-of-the-art machine learning technology with an operator’s input for validation of the results. Eliminating the need for time-consuming data scientists’ consensus, advanced process control will automatically set the conditions necessary to achieve a near perfect PID loop.

Adopt an Agnostic Approach to Collecting, Processing and Analyzing Big Data

When it comes to implementing predictive analytic solutions for process automation industries, hybrid approaches, such as cloud computing, fog computing and edge computing, should be adopted according to how critically exposed your industrial control systems are. Utilities for example, need the ability to select modular, transparent systems that can scale with various third-party devices and databases, from float sensors and pressure transducers to existing work order management systems. These same solutions must also be able to handle millions of deployed algorithms in real time, with a hierarchy asset framework that mimics the historian infrastructure already running. Advanced process control should perform bulk industrial data collection that is both scalable and flexible for existing infrastructures. Engineering war rooms should be developing solutions centered on device and platform agnostic methodologies that are seamless with native integration toward critical industrial control systems (ICS) and able to handle current industrial protocols that transfer gained knowledge over similar plants and sites.

Now’s the Time to Disrupt the Process Control Industry Paradigm

Advanced process control solutions will enable legacy driven industries to accelerate their data collection and advanced analytics capabilities beyond what was once considered costly and resource intensive. Ideal PID loop tuning, automatically performed in real time, positions manufacturing companies and utilities to experience key competitive advantages across all areas of their organization. The value proposition behind AI IIoT technologies is its ability to:

  • Decrease susceptibility to costly governmental penalties;
  • Increase energy efficiency and improve public perception for conservation efforts;
  • Accelerate return on investment (ROI) driven labor and organizational efficiencies;
  • Decrease production waste and optimize raw material costs in overhead savings.

Big data is real and there is no denying that AI IIoT applications will continue to surge exponentially. Those who are able to manage these process optimization models, systems and applications will capture the biggest piece of the Industrial Internet of Things (IIoT)/advanced process control pie. To date, very few enterprise process optimization solutions can offer under one umbrella:

  • Horizontal enterprise IoT management from the edge device to the cloud;
  • Data collection supporting all industrial communication protocols;
  • Connectors to industry-leading, real-time data historian applications;
  • Simple, configuration-free, predictive analytics software to enable the deployment of production ready ML models tied to business outputs;
  • Training platform for unlimited ML model training and creation at the edge;

There are large market research firms going on record stating that the system integrators of the world are best positioned to bridge the gap between operational technology (OT) and information technology (IT) silos and deliver complete process centric IoT solutions that provide proven unparalleled economic and operational success for their customers.

This solution enablement framework will be the first of its kind in the water industry, providing simple big data collection, predictive maintenance and process optimization in the ever demanding industry of process automation & control. 

Aldo Ferrante

Aldo Ferrante, is the president and CEO of ITG Technologies. With more than 30 years of experience in automation and information technology industries, Aldo achieved great success in providing turnkey solutions to clients in the technology sector, including the manufacturing, transportation, and municipality industries. www.sorbasoft.com

Upcoming Events

August 8 - August 10, 2023

Maximo World 2023

View all Events
banner
80% of Reliabilityweb.com newsletter subscribers report finding something used to improve their jobs on a regular basis.
Subscribers get exclusive content. Just released...MRO Best Practices Special Report - a $399 value!
DOWNLOAD NOW
IMC-2022 Who's Who: The World's Best Run Companies

The International Maintenance Conference (IMC) provides a fresh, positive community-based curated experience to gain knowledge and a positive perspective for advancing reliability and asset management through people, their managers, the strategy, the processes, the data and the technology.

Uptime Elements Root Cause Analysis

Root Cause Analysis is a problem solving method. Professionals who are competent in Root Cause Analysis for problem solving are in high demand.

Reliability Risk Meter

The asset is not concerned with the management decision. The asset responds to physics

Why Reliability Leadership?

If you do not manage reliability culture, it manages you, and you may not even be aware of the extent to which this is happening!

Asset Condition Management versus Asset Health Index

Confusion abounds in language. Have you thought through the constraints of using the language of Asset Health?

Seven Chakras of Asset Management by Terrence O'Hanlon

The seven major asset management chakras run cross-functionally from the specification and design of assets through the asset lifecycle to the decommissioning and disposal of the asset connected through technology

Reliability Leader Fluid Cleanliness Pledge

Fluid Cleanliness is a Reliability Achievement Strategy as well as an asset life extension strategy

MaximoWorld 2022 Conference Austin Texas

Connect with leading maintenance professionals, reliability leaders and asset managers from the world's best-run companies who are driving digital reinvention.

“Steel-ing” Reliability in Alabama

A joint venture between two of the world’s largest steel companies inspired innovative approaches to maintenance reliability that incorporate the tools, technology and techniques of today. This article takes you on their journey.

Three Things You Need to Know About Capital Project Prioritization

“Why do you think these two projects rank so much higher in this method than the first method?” the facilitator asked the director of reliability.