How Analytics and AI-driven Processes Will Revolutionize the Industrial Sector

How Analytics and AI-driven Processes Will Revolutionize the Industrial Sector
How Analytics and AI-driven Processes Will Revolutionize the Industrial Sector

From driverless cars to virtual doctors, artificial intelligence (AI) is increasingly going to transform the way we live, work, travel and do business in the 21st century. PwC estimates that AI could add as much as $15.7 trillion to the global economy by 2030.

What do we mean when by "AI" and "Analytics?" Artificial intelligence as a broad set of technologies that leverage big data to create knowledge and help derive actionable conclusions for our customers. Artificial Intelligence and analytics fall into four categories reflecting the type of insight delivered; these categories are predictive, performance, prescriptive and prognostic insights–the Four P’s of industrial AI. When combined, they provide significantly more value through complex AI thought processes.

There is no doubt that AI is starting to disrupt the workplace through digital transformation, resulting in extensive use of the digital twin. This "digital twin" is effectively a virtual representation of a physical object or system. As it has evolved, it has come to also encompass larger entities such as buildings, factories, and cities. It includes IOT data, advanced computer systems, digital processes, electronic documents and advanced analytics which all model physical space.

The combination of AI with the digital twin results in significantly enhanced productivity. This is not theory; this is a fact and is quantifiable. AI enhances workforce productivity and improves safety, reliability, quality and security. Through efficiency gains and reduced waste, AI is creating an overall greener environment with enhanced sustainability. AI also helps the workers themselves–by upskilling them and allowing staff to make more accurate data driven decisions. Studies show that there is not enough new qualified staff to replace the knowledge of an aging workforce rapidly approaching retirement. AI also helps to facilitate and reduce this gap.

Unique challenges in the industrial sector 

The industrial sector includes companies who produce capital goods used in construction and manufacturing. Businesses in the industrial goods sector make and sell machinery, equipment, and supplies that are used to produce other goods rather than sold directly to consumers.  A few common industrial sector divisions include the automobile industry, chemical industry, steel production, food and beverages, and the energy industry (electricity, gas, petroleum) for example.

The industrial world has taken longer to digitalize than consumer industries due to their complexity. That is now changing as businesses leverage a number of mega trends:

  • The adoption of Industrial Internet of Things (IIoT) means more information is available today than ever before, giving the potential for unprecedented insight. It is estimated that by 2020, there will be 50 billion assets connected via the Internet, but today less than 3% of data is used in a meaningful way (Source: IDC).

  • Data Visualization is required to clearly interpret complex data sets in a clear and accessible way to enable better decision-making. The easiest way to understand the workings of a plant is to visualize it as a Digital Twin: an interactive, working digital representation of the physical asset.

  • Artificial Intelligence (AI) can interpret and learn from vast volumes of data, using those learnings to achieve specific goals. This facilitates efficient predictive maintenance of assets, reducing costs, minimizing downtime and enhancing safety.

In the industrial sector, AI application is supported by the increasing adoption of devices and sensors connected through the Internet of Things (IoT). Production machines, vehicles or devices carried by human workers generate enormous amounts of data. AI enables the use of such data for highly value-adding tasks such as predictive maintenance or performance optimization at unprecedented levels of accuracy. Hence, the combination of IoT and AI is expected to kick off the next wave of performance improvements, especially in the industrial sector.

Early adopters of AI technology have deployed on-premises, in the cloud, at the edge, and through many types of hybrid architectures. AI itself is not one thing but comprised of several technology types, including neural networks, deep learning, natural language processing, computer vision, unsupervised machine learning, supervised machine learning, reinforcement learning, transfer learning, etc. These various types of AI are applied in different ways throughout the industrial world to create targeted solutions provided as descriptive, predictive, and prescriptive analytics.

A relatively common solution used in a wide range of industries today is predictive analytics in the form of machine learning to identify anomalies with equipment and processes. These anomalies can indicate performance problems or asset health deterioration well in advance of any control system or warning/alarm. Lead times with predictive analytics can be days, weeks, or even months, allowing operators and maintenance personnel adequate time to react and schedule repairs and corrections.

Software tools are becoming more and more sophisticated in order to provide additional insight into these anomalies. This includes identifying which sensors are the key contributors to the problem as well as the probable root cause. With all this level of sophistication, issues can be identified and corrected quickly, well before they have a major impact on operations. This results in less downtime, better product quality, reduced risk and increased overall efficiency and profitability.

Examples of successful predictive analytics include sophisticated turbine “catches” where there were step changes of vibration reductions. Each time, the manufacturer told the customer it was OK because it was a reduction in vibration, not an increase. With this situation, it turned out to be due to the beginning of blade separation within the turbine stages. The system was nowhere near a control system alarm or warning. However, had it gone on, it would have resulted in a failure that could have destroyed the turbine, caused extensive downtime (loss of power production), and a potential for significant injury to personnel. Conservative estimates by the customer showed that over $34 million USD were avoided due to the early warning detection of this issue.

Another example occurred during a major storm with high winds where a transmission grid company leveraged AI and advanced analytics to prevent a catastrophic transformer explosion. The system alarmed due to unusual patterns of dissolved gas analysis (DGA), including methane and carbon dioxide.

Overcoming the fear of automation

Beyond deciding where and how to best employ AI, an organizational culture open to the collaboration of humans and machines is crucial for getting the most out of AI. Trust is among the key mindsets and attitudes of successful human-machine collaboration.

AI disrupts jobs, which sometimes results in the elimination of certain types of occupations. But it also creates a variety of new jobs such as monitoring service technicians, data analysts and data scientists. Forbes estimates that 75 million jobs will be displaced by 2022 due to AI (machines and algorithms). At the same time, 133 million new jobs are expected to be created, resulting in a net increase of 58 million additional jobs in the next 3-4 years. Of course, this is nothing new. The implementation of new technology has been disrupting the workforce for centuries.

History has shown that while innovation does eliminate some jobs, it typically adds more than it destroys, resulting in a net increase in the overall workforce. Unfortunately, AI can sometimes create an overall fear of the unknown, including privacy concerns and anxiety of being replaced. Companies must take measures to ensure that these fears are managed, and that proper employee education and communication channels are in place to minimize fear due to misinformation and a general lack of understanding.

Here are some practical steps to consider if a company is looking to explore the implementation of Artificial Intelligence or Machine learning capability into their business process:

  1. Leverage AI to gain significantly more value out of existing industrial software: SCADA (an acronym for Supervisory Control And Data Acquisition generally refers to industrial control systems) and other types of control systems have become standard practice in most industrial facilities.  In addition, data historians are generally installed alongside these systems to collect and archive the resulting Big Data. Today, this near real-time and historical data is typically used for trending, reporting, and HMI visualization. Artificial Intelligence allows companies to get much more value and insight from this historian data through state-of-the-art technologies such as multi-variate machine learning and deep learning. By integrating software infused with AI into existing industrial IT infrastructures, companies can greatly amplify the value and return on investment by detecting and solving operational and maintenance issues before they become larger problems that often result in unplanned downtime. This alone can increase uptime by greater than 10% annually, resulting in substantial avoided costs and efficiency gains.

  2. Leverage the cloud to ease the implementation of AI, allowing companies to quickly scale: Artificial Intelligence is fast becoming the brains behind the cloud. Consequently, companies can quickly deploy and access a variety of industrial software capabilities that are driven by various types of AI technology. The cloud is the delivery mechanism and SaaS is the commercial model; however, AI drives much of the value gained. Now more than ever before, AI is becoming more easily accessible and more cost effective to deploy into industrial environments.

  3. Bridge the gap between AI and humans: In order to glean maximum value from AI, companies must ensure that they bridge the gap between AI and human understanding. A significant portion of the workforce today is somewhat distrustful or fearful of AI. Some don’t believe that it can really help them, and others are afraid that it might replace them. It is critical that companies do everything they can to ensure that the benefits from AI-infused software is translated into the vernacular of the targeted worker. The benefits provided by AI must be in context, useful, and actionable. If this does not happen, then much of the value of AI is wasted.

  4. Be open to continued innovation and change: AI capabilities continue to evolve and improve.  Software will become more intelligent through combinations of AI capabilities in order to achieve more sophisticated machine-based thought and reasoning.  Amid these changes, companies can reap more and more benefit through deeper insight into cost vs risk decisions, an improved understanding of business processes and associated efficiencies, and better forecasts of future events. By continuing to plan for and incorporate change, companies can take advantage of ever-improving AI capabilities and insight.

State-of-the-art artificial intelligence technologies improves industrial processes, proactively detect and solve problems, and provide guidance for risk-based decisions resulting in significant cost savings and improved competitiveness for the enterprise.

This new technology is transforming capabilities across all areas of the business by infusing AI and Engineering, Operations, and Maintenance software to deliver intelligent, outcome-driven analytics.  When businesses apply AI to address industrial pain points for productivity improvement, insight discovery, risk management, and cost optimization–it results in unrivalled, transformative value for businesses.

About The Author

With over 30 years of experience in the industrial software sector, Jim Chappell is currently head of Artificial Intelligence (AI) and Advanced Analytics across all AVEVA business units, products, and markets.  Prior to his current position, he led the Asset Performance Management (APM) suite of software products and related engineering/analytics services for Schneider Electric.  
Jim holds a B.S. in Nuclear Engineering from Rensselaer Polytechnic Institute (RPI) in Troy, NY, a M.S. in Nuclear Engineering from the Naval Nuclear Power School in Orlando, FL, and a M.B.A. (with concentration in MIS) from Chaminade University in Honolulu, Hawaii.  In addition, he graduated from the Civil Engineer Corps Officer's School (CECOS) in Port Hueneme, CA.   
AVEVA Group plc provides innovative industrial software to transform complex industries such as Oil & Gas, Construction, Engineering, Marine, and Utilities. AVEVA’s software solutions and platform enable the design and management of complex industrial assets like power plants, chemical plants, water treatment facilities and food and beverage manufacturers – deploying IIoT, Big Data and Artificial Intelligence to digitally transform industries. For further information visit

Did you enjoy this great article?

Check out our free e-newsletters to read more great articles..