It may seem hard to believe that a majority of manufacturers are using technology that is at least 30 years old. Many of these decades-old systems work wonderfully for collecting and storing data, as well as monitoring systems. But these systems alone cannot help industrial companies meet the current challenges posed by digital transformation and the Industrial Internet of Things (IIoT).
Many companies hesitate to take advantage of new IIoT opportunities because they believe such a change is too difficult and expensive.
A recent LNS Research survey of more than 400 manufacturing executives showed the vast majority of companies do not have plans to invest in IIoT technology in the near future.
Considering the high cost of many existing systems, it can be easy to understand why industrial companies are reluctant to invest in new technology.
The upside is that there are affordable technologies developed specifically for the internet age that work with existing systems. These technologies can help manufacturers gain deep insights into process behavior and translate those into fast returns.
Supervisory control and data acquisition (SCADA) systems were originally designed to collect data and monitor processes. Since they generate enormous amounts of data, historians were added to store this information. Initially, these data historians (also known as process historians or operational historians) were used to fulfill regulatory requirements, such as generating reports for government agencies.
Leading industrial companies recognized that the data hidden in their historians could provide valuable insight on plant processes and production, but accessing and using the data was difficult. Historians were not designed for “read” purposes or a two-way transfer of information.
Manufacturing execution systems (MES) were introduced in the early 1990s in an attempt to bridge the gap between plant floor SCADA systems and enterprise resource planning (ERP) software. They also promised to provide analytics—such as key performance indicator (KPI) data—to improve plant floor operations. While they have been able to provide more advanced capabilities than SCADA systems, they are expensive and often require extensive engineering to implement. Additionally, they were developed for a different business era in which systems were still largely siloed and internet optimization was an afterthought.
21st Century Technology
The amount of time and money industrial companies have invested in traditional software explains the reluctance of some manufacturers to enhance their systems. Companies are apprehensive about becoming locked into a cycle of difficult and expensive upgrades, patches and limited scalability.
To take advantage of the IIoT, companies need next-generation solutions that were developed for that purpose. These solutions offer users the best of new technologies, particularly in terms of ease of use and affordability.
While historians hold a wealth of valuable data for improving operations, accessing and turning it into actionable information is time consuming and difficult. As a result, only mission-critical applications were targeted, leaving vast areas of improvement opportunities hidden.
In 2008, engineers from Covestro (then known as Bayer MaterialScience) knew there must be a better way to leverage time-series data. They worked with different types of analytics models and identified their limitations for scaling-up beyond pilot projects. Eventually, they created software that leveraged pattern recognition to deliver discovery and predictive analytics solution to the average user. This platform’s unique multi-dimensional search capabilities enabled users to find precise information quickly and easily, without requiring expensive modeling projects or the involvement of data scientists.
A simple example of this concept is the song title recognition app Shazam. Instead of trying to map every note in a song, Shazam uses pattern recognition software that seeks “high energy content” or the most unique features of a song, then matches it to similar patterns in its database.
This is a simple explanation of a complex process, but it has the same result: giving the user a quick and accurate answer.
Industry demands more sophisticated algorithms that are capable of going beyond mere searches. This type of next-generation software works by connecting to existing historian databases and implementing a column store database layer for an index. This makes it easy to find, filter, overlay and compare interesting time periods to search through batches or continuous processes.
This type of solution enables users to search for particular operating regimes, process drifts, operator actions, process instabilities or oscillations. Users can also combine these advanced searches.
For example, an operator can compare multiple data layers or time periods to discover which sensors are deviating from the baseline. Based on this information, they can make adjustments to improve production efficiency during a process.
Bringing It Together
This technology also provides process data contextualization and predictive analytics capabilities. Engineers and operators can add annotations to events in order to provide greater insight and share knowledge. It also enables monitoring and early-warning detection of abnormal and undesirable process events.
The software can calculate the possible trajectories of a running process and predict process variables and behavior by comparing saved historical patterns with live process data. This gives operators the ability to see if recent process changes match the expected process behavior and proactively adjust settings if they do not.
A great benefit of this next-generation analytics software is that it employs a modern business model: subscription-based pricing. In addition to making process analytics affordable to companies, it frees businesses from having to spend time and money on adding licenses and upgrades. Instead, users automatically get the latest version of the software with every log in.
Today, companies can enhance the value of their existing historian investment with a low-cost predictive analytics solution. This enables them to better use the historian data collected and gain valuable business insights from their process data.
An affordable plug-and-play solution now exists that can deliver predictive analytics without requiring a long implementation or unreasonable expenditure.