Countless process industries rely on distributed control systems (DCSs) and programmable logic controllers (PLCs) — as well as their associated software, spare parts, and related technologies — to maintain productivity and keep their operations moving forward consistently. These systems control vast, repeatable, and essential processes that enable everything from power generation and cement processing to food production and material handling — managing an influx of signals and data from countless other systems and pieces of equipment that fall under their respective control areas. 

However, due to the cost and the complexity of implementing and customizing DCSs and PLCs, these systems are typically static within process industries. In many facilities, the lifecycle for DCSs and PLCs can extend anywhere from 20 to 30 years, requiring process industry teams to retain their knowledge of older technologies, rely on backward compatibility for parts and support, or having to completely shut down a system to update its logic. 

Therein lies another challenge — the fact that DCS and PLC users often cannot be the ones to update systems. Many of the controls and equipment used in the process industry are black-box systems, meaning that unless companies have the time for operators and engineers to undergo extensive training on systems’ programming languages, those vendors are most likely the only ones who can perform configuration, installation, maintenance, and optimization work. This puts engineers and operators at a significant disadvantage in not being able to make updates as needed without third-party support. 

Coupled with the fact that the amount of time between maintenance shutdowns is several years or even longer, any effort to optimize a PLC and DCS performance based on recent events, engineer and operator knowledge, or business changes is: 1) incredibly difficult without outside support, 2) time-consuming due to scheduling that support, 3) and costly to the business in lost productivity and the inability to quickly harness results from new data. 

No-code automation tools are a key solution to this predicament facing many process industry organizations today — and not just for enabling greater use of these essential systems but also for empowering those controlling them to more rapidly model potential changes and see the results of that work sooner. Let’s explore some of the ways that no-code automation tools help process industries get the most out of control systems and other equipment. 

Advantages of No-Code Automation Tools for Process Industries 

1. Intelligent AI is Put to Work for Success 

The most immediate benefit is that no-code automation tools leverage state-of-the-art AI with the features and solutions needed already built into the platform. This means engineers and operators don’t have to spend weeks or even months learning and practicing coding and programming languages (a process that itself takes them away from your environment where they’re most beneficial and productive). 

Using no-code automation tools, variable data from all of your systems below the production control level in the Purdue Model of ISA-95 is continuously gathered from your existing DCS and PLC systems. And based on thresholds or limits specific to your industry and operations, that data is continuously analyzed to identify opportunities for improvement or to notify engineers and operators about potential issues. 

2. Models Can Be Configured More Rapidly and Tested 

Without no-code automation tools, your team would be required to undergo training to learn how to modify black box systems or to partner with its respective vendor to schedule optimization work and create new models. Imagine having to do that for multiple different DCS and PLC systems throughout your environment. Now imagine navigating that for multiple facilities throughout your footprint. And here’s the worst part: what if the optimization work you partnered with the vendor on didn’t work or experienced some issue that your team wasn’t prepared to handle or is trained on solving? 

Clearly, no-code automation tools are the preferable alternative. Using solutions like Adivarent Control and the Griffin AI Toolkit, companies in the process industry gain an all-in-one solution for developing new process control models, supporting optimizations, and even developing custom tuning screens that allow those processes to be modified on the fly. As a result, there’s no need to waste time on outside support when your team can be continually driving the performance of your systems forward and realizing the financial and operational return on those efforts. 

3. Implementation and Optimization Can Be Efficiently Scaled 

Obviously, the benefits of no-code automation tools aren’t and shouldn’t be restricted to one or only a handful of systems throughout your facilities. The intent behind implementing AI and automation in process industries is to put it to use more broadly throughout the organization. While you may wish to pilot your no-code automation tool on a specific control system in one area, it should be scaled out further to ensure other areas benefit as well. 

This way, organizations can make significant progress toward a more complete (yet simplified) digital transformation. Because no-code automation tools like the Griffin AI Toolkit operating at the Adivarent Control layer, leverage a simplified interface and (of course) no coding requirements, they can be implemented more rapidly, configured by team members more efficiently, and put to work on a variety of systems. As solutions are fine-tuned through modeling, the knowledge built into the system from your engineers and operators is institutionalized — allowing it to be scaled in an agile manner for other processes and systems. 

These Benefits Are Just the Beginning 

While we’ve discussed a variety of ways that no-code automation tools support long-lasting success in process industries, we’ve truly only captured a handful of the many advantages that such solutions offer. And at Griffin Open Systems, our technology delivers all these and more in one simple solution that can be deployed, configured, and put to work faster than the alternative of navigating black box system modification or personnel training. 

Ready to put our solution to work? Get in touch with us today.

The post Using No-Code Automation Tools for Process Control appeared first on Griffin Open Systems.

Adivarent Control – The Purdue Model of ISA-95 has been widely accepted across process industries as the gold standard for the layout and architecture of process control & enterprise integration since the mid-1990s. However, this does not easily accommodate the proliferation of edge computing devices and resources operating in the space between control systems and the operator. Adivarent Control is a term coined to represent this layer which is used to assist both the control system with complex tasks and operators with knowledge-based responses that require constant attention.

LEARN MORE ABOUT ADIVARENT CONTROL

Artificial Intelligence (AI) – Broadly speaking, this encompasses several areas where computers control devices (e.g. actuators, robots) to do tasks or adjustments normally done by humans. These types of AI tasks require an ability to discern patterns and correlations, not all of which have been seen before, and react to changes in processes or data sources with the ability to predict proper responses.  AI can be used as advisory-type systems or as actionable real-time control systems.

Data Scientists – A new branch of technical experts whose expertise is using a variety of analytical tools to explore complex or large data. This was formerly the domain of statisticians, engineers, and mathematicians. Many data scientists have these backgrounds, but the complexity and size of data (big data) have made it necessary to learn new tools and techniques to gain additional insights into data correlations, trends, diagnostics, and where to focus for process improvements.

Data Analytics – A set of mathematical techniques and algorithms for examining data sets in order to gain insights into the process being examined. There are a number of specialized tools which may be applied, depending on the desired goals for the analysis. These tools are broadly categorized in the areas of trends, diagnostics, predictions, prescriptive and cognitive (AI). As data analytics covers particular expertise, this type of data analysis is often performed by data scientists, though advanced usages may have automated some aspects, especially in the sub-domain of manufacturing data analytics.

LEARN MORE ABOUT DATA ANALYTICS BY DOWNLOADING OUR SMARTER MAINTENANCE BROCHURE

Digital Factory – A generic term with a wide range of meanings and a range of implementations. In general, it will refer to a centralized organization of digital data which is then used to create dashboards for users to track production processes, data analytics tools for investigating the production process, and digital models for continuous evaluation and optimization of the production process.

DOWNLOAD OUR BUILDING A DIGITAL FACTORY PLAYBOOK

Edge Computing – This term has become popular with the advent of the IIoT (Industrial Internet of Things).  With cloud computing, all computation happens on the cloud which can have some latency and bandwidth issues. To address this, Edge computing is used to set up computing resources closer to the data source to provide real-time analysis. The Edge computer can still connect to the cloud for other services. In the world of IIOT, the edge device will not only collect data but process the data to make it edge computing. This makes data more readily usable by dashboards, data scientists, and implementors of real-time digital factory systems.

On-Premise Computing – This term refers to computing resources set up at the customer’s premise. An on-premise solution is used when data collected is considered sensitive to be trusted by a third-party cloud provider or when the internet cannot be due to the risk of cyber-attacks.

IIoT– Industrial Internet of Things refers to the use of smart sensors and actuators networked together in an industrial application. Control systems, in concert with edge computing devices, allow more sophisticated analysis and processing of data for improving the operation of manufacturing facilities.

Manufacturing Data Analytics – This represents the specific application of data analytics for use in operations for process and product manufacturing industries. They can be applied to improve (ensure) quality, increase throughput, improve efficiency, and optimize the production process. The analytics may be done offline by data scientists or may be incorporated into actionable algorithms modifying the production process to achieve the best circumstances for the given conditions.

LEARN MORE ABOUT MANUFACTURING ANALYTICS BY DOWNLOADING OUR SMARTER MAINTENANCE BROCHURE

Machine Learning (ML) – A sub-field of artificial intelligence (AI), with the goal of providing the capability to machines to learn from data and, in many cases, imitate intelligent human behavior. While AI is useful in learning complex tasks performed by humans, it is the ability to learn these tasks without (or minimally embedded) first principal models that make them attractive. Furthermore, the ability to quickly see multi-dimensional relations and trends offers the potential for high ROI projects when looking to improve operations.

Particle swarm optimizer (PSO) – A biology-inspired search algorithm used to explore many solutions with a defined solution space. The algorithms require an objective function that defines the goals or defines a ‘most fit’ solution. The PSO creates a number of possible solutions (particles) that are evaluated in an iterative process. The closeness (distance) to the objective is shared among the particles to help guide them toward the more successful result(s) and eventually to a near-optimal solution (ideally the optimal solution). The inclusion of random particles helps avoid local optimum solutions.

LEARN MORE ABOUT PARTICLE SWARM OPTIMIZER

The post Griffin Open Systems – Glossary of Commonly Used Terms appeared first on Griffin Open Systems.

Organizational Knowledge is at Risk as the Industrial Workforce Grows Older

The aging U.S. workforce has been a concern for several years now, but as time presses on, companies are seeing the risks that come with a mature workforce. By 2024, the U.S. Bureau of Labor Statistics (BLS) projects that one-quarter of the U.S. workforce will be above the age of 55, and one-third of that segment will be 65 or older. Between 2014 and 2024, older age groups are expected to see more rapid growth than younger groups in the workforce as a whole. 

While this aging workforce presents difficulties for multiple industries, the risk is particularly high in the broad industrial sector, which includes everything from manufacturing and food processing to power generation and steel production. For this sector, BLS showed that the median age of the industrial workforce is 15% higher than the national median (42 as of 2019 and expected to continue increasing well into the 2020s).

As process industries, these organizations leverage vast equipment, systems, and technologies to keep operations running smoothly and efficiently. Central to maximizing this are the people running the operations who often have years of tacit knowledge to handle the everyday items that might disrupt production. As the knowledge is increasingly leaving the building, industry leaders have recognized more and more the value of capturing this knowledge, even while often justifying the new tools on the potential gains through data analytics. While artificial intelligence (AI) and machine learning (ML) have historically taken longer to implement in these industries, adoption is increasing, with more leaders recognizing the importance of these elements in their automation efforts. 

For example, operators will understand what certain alerts or events mean and what to do. While automation enables another system to take action when those triggers occur, employees’ tacit knowledge is the foundation of what informs automated systems (and contributes to them being programmed when automation solutions are being implemented in a facility). 

For engineers, the knowledge of how separate systems best operate together might be able to be documented, but their experience in making that happen and how external variables influence those operations might not be able to be clearly expressed — it’s simply something they know and have learned through experience and time.

How AI Itself Serves as the Solution

So, with an aging industrial workforce, how are process industries able to make the most effective use of AI for automation? While AI and other automation solutions can execute A or B when X or Y occurs, there’s no match for keeping things a bit more fluid. This allows operators, engineers, and other industrial workforce employees involved in automation efforts to use tacit knowledge to build process models, test them, and refine them to achieve the best results in a repeatable way that continues to add value.

Unfortunately, for many process industries, solutions that enable flexible modeling and process optimization are limited. This is because they’re black-box systems — modifying their operations, and indeed even being able to know how to modify them, is almost impossible without involving an external vendor or partner. Fortunately, Griffin Open Systems developed the AI Toolkit (an open architecture AI platform) and Adivarent Control (a control layer for the AI and machine learning tools to assist operators and DCS control) to solve this problem facing the industrial workforce today.

How the AI Toolkit Captures Institutional Knowledge

No Coding is Required, but Adjustment is Available

For the industrial workforce to be able to implement change, its users must be able to actually do what is needed to get results. The requirement to learn programming for DCS and PLC systems or a programming language like Python may or may not be exciting to an experienced operator or engineer, but this pulls them away from their main job of maintaining and improving operations. With the AI Toolkit and Adivarent Control, new models, traditional flow logic, and more can all be built and evaluated quickly and easily, without the need for training or external vendor participation. And at any time, users or developer partners can build their own custom screens and toolbars.

It is also important to have the ability to implement incrementally and not have to “know” ahead of time all of the knowledge that has been built up through years of experience. Starting slowly, expanding, and modifying the knowledge capture over time lowers several barriers to getting started with AI and ML projects.

Dig deeper: Download our playbook to learn more about how the Toolkit helps process industries overcome common optimization challenges.

A Simple Interface Supports User Adoption

In addition to requiring no coding to get started, Adivarent Control and the AI Toolkit feature an accessible drag-and-drop interface that allows any in-house team members to execute their optimization work and build what they need according to their understanding and experience (i.e., their tacit knowledge). There is no need for software engineers to get involved and influence the platform’s functionality — operators, engineers, and other in-house team members can build what they need simply to optimize processes.

Real-world example: Learn how a steel company used the AI Toolkit to create a graphical display and optimization model to improve output.

Adivarent Control Builds on Users’ Knowledge

Capturing operators’ and engineers’ knowledge in the system through model creation and testing is just the beginning. With the AI Toolkit and Adivarent Control, that knowledge becomes institutionalized — part of the norm and baseline — and continues to grow and develop. New inputs, events, and factors can be taken into account quickly, allowing for new models and deeper optimization to be developed, ultimately creating a continuous cycle of improvement. This cycle is based on what in-house experts know — not what external software developers limit off-the-shelf solutions to, restraining the amount of optimization that’s possible.

Listen in: Learn how the AI Toolkit helps process industries overcome the roadblocks to digital transformation in this podcast featuring GOS co-founder Brad Radl.

Preserve — and Grow — the Knowledge of Your Industrial Workforce

If you’ve been struggling with the aging industrial workforce challenge facing so many process organizations today, the AI Toolkit and Adivarent Control will help you capture the tacit knowledge that already exists in your team. With the knowledge institutionalized, you benefit immediately from having their expertise driving your automated optimization efforts and having a system in place to keep you moving forward with confidence as you seek to find and develop new talent.

Connect with us to see the AI Toolkit and Adivarent Control in action in a private demo.

The post AI & The Aging Industrial Workforce appeared first on Griffin Open Systems.

It’s no secret that achieving industrial process optimization goals in today’s facilities and environments is becoming more and more difficult, yet it’s never been more essential for long-term success. 

Various industries face increasing environmental regulations and competitive pressures manifesting themselves as specific but dynamic challenges to optimization work that permits continuous improvement. Too often, external events, personnel shortages, and equipment failures leave producers focused on avoiding and putting out fires instead of focusing on forward-thinking solutions.

Additional demand challenges from the pandemic, the ongoing frustration and competitive setbacks caused by the tariffs, and other supply chain difficulties are keeping companies scrambling to satisfy growing demand and meet customer expectations as opposed to exploring opportunities to streamline processes. 

On top of that, industrial process optimization often requires significant CapEx resources, as the solutions for improving performance, reliability, and other key metrics require updating or replacing equipment and investing in hefty technologies and enterprise systems that come with steep price tags. Time is a cost here as well, as the amount needed to bid on, purchase, and complete this work or implement such solutions is extensive — anywhere from several months to years due to the vastness of their scope. 

In truth, process optimization is often comparable to personal finances. Going too far down the wrong path is akin to going into debt: as the debt grows, so too does the interest — putting you deeper in the hole. Prioritizing the right solutions, however, is more akin to investing and saving. The results compound in a positive direction, leading to greater opportunities.

And yet, each industrial process optimization solution delayed or not taken compounds the challenges and costs — creating even more barriers to improvement. Ideally, more efficient process flows equates to more resources freed up, which can then be prioritized elsewhere or preserved. What is the solution here? Should process industries simply bite the bullet and launch a massive CapEx program to realize improvements a year or more down the road? 

‘Sooner rather than later’ some might say, but fortunately, more financially advantageous solutions are already available that make industrial process optimization attainable sooner — and at dramatically less cost than traditional optimization solutions. At Griffin Open Systems, our AI Toolkit is one such solution. Let’s explore a few ways this innovative artificial intelligence (AI) platform empowers organizations to implement industrial process optimization quickly, efficiently, and affordably.

How the AI Toolkit Enables Industrial Process Optimization

Implementation is Fast and Less Complex

Consider the sheer amount of planning, time, and programming expertise that would be required to upgrade or modify process-related systems like distributed control systems (DCSs) or programmable logic controllers (PLCs). This work would most likely need to be aligned with planned outages on systems, which is when other critical work is often scheduled — thus adding more burden and complexity to already expensive and time-consuming maintenance. Additionally, the manufacturer or vendor for those systems might need to be involved. The bottom line: these factors add significant, prolonged costs to what doesn’t need to be costly.

The Griffin Difference: The AI Toolkit allows for rapid modeling and deployment thanks to its no-code graphical interface. No expert-level programming knowledge is needed, and it can be implemented on existing DCSs, PLCs, and other systems in a matter of weeks. This ensures engineers, operators, and any other team members involved are able to gather data on existing systems, develop new models for optimization, and realize their benefits faster than ever. And the sooner these industrial process optimizations are able to be implemented, the lower the overall program costs will be and the more rapidly the financial benefits can be realized.

Implementation Can Be Less Risky

Making changes to DCS logic or PLC programs often requires waiting until outages occur or requires judicious implementation while the process is active. Mistakes can risk equipment damage or cause unplanned outages.

The Griffin Difference: The AI Toolkit is implemented at the Adivarent Control layer, leaving the existing safety systems and basic control functions intact. Normally, solutions are implemented as biases or fine-tuning adjustments that are responsive to a wider range of processing or manufacturing conditions. This helps operators by automating mundane known corrective actions and the DCS/PLC logic by providing access to advanced AI for optimizing the complex.

The Customization Opportunity is Extensive

Mentioned briefly above, any customization work involved on existing systems — particularly those that are ‘black box’ — means that outside support will be necessary. If more costly technologies or changes are needed, programming may be needed as well. However, these solutions often limit the amount of customization that’s possible — whether that’s due to the limitations of that system, a lack of design flexibility, or generally forcing users into a specific framework for working. What’s needed here is the flexibility to customize processes on-the-fly, rapidly, and as new data comes in.

The Griffin Difference: One of the greatest barriers to digital transformation has been limitations placed on process industries in terms of customization. With the AI Toolkit, internal teams and even third-party developers with whom companies are partnered can develop custom tuning screens, implement custom algorithms, and even capture the knowledge of their operators and engineers in proprietary toolbars. Each of these allows process industries to leverage an already simple and affordable system for greater impact, allowing them to squeeze greater performance out of their systems more efficiently and quickly while reducing costs.

The Payback Period is Shorter

Depending on the number of facilities you have, and the equipment in question that is needing optimization work, the cost to outright replace or upgrade them can be steep (think in the low to middle six figures, if not more). The reality is that when it comes to industrial process optimization, these expenses can be avoided (assuming that the equipment or systems don’t actually require outright replacement due to a complete failure). Instead, an intelligent AI solution can be put in place to better understand how they’re working and where opportunities exist — for less upfront investment.

The Griffin Difference: Compared to sweeping enterprise changes and other technology solutions, the AI Toolkit is vastly more affordable. This has three key benefits: first, the cost to begin optimization work is less steep, meaning you can begin to explore opportunities sooner. Second, those opportunities can be implemented faster thanks to its ease of use, resulting in earlier industrial process optimization wins that produce measurable savings sooner. Third, the no-code interface creates opportunities for a wider group of process experts while keeping ongoing training and support costs lower.

Risk is Mitigated

Whatever your respective industry might be, you face a fair amount of risk in multiple areas: financially, operationally, strategically, and so on. The longer these risks go unaddressed, the more difficult your position becomes. You’ll lose ground to competitors. You might encounter more compliance challenges. Maintaining certain levels of productivity or output might become harder and harder. And along the way, you’ll be losing money.

The Griffin Difference: The AI Toolkit is designed as a flexible, cross-functional solution to many of these risks. By resolving productivity challenges, you thereby solve resultant financial risks. By addressing financial risks, you gain more opportunities to invest in other strategic areas. In doing that, you increase your competitiveness and operation flexibility.

Put the AI Toolkit to Work in Your Facilities

With pressure mounting on manufacturers and other industry organizations to become more efficient, environmentally friendly, and transparent, there’s never been a better opportunity to explore industrial process optimization opportunities. And the AI Toolkit from Griffin Open Systems is the vehicle for those discoveries. 

Coupled with our advanced Adivarent Control AI solution that serves as a bridge between control systems and operators, your team will have the tools and preserved knowledge needed to rapidly refine processes, implement change, achieve digital transformation goals, reduce costs, and more.

Connect with us today to see how the AI Toolkit will support your success.

The post Industrial Process Optimization — Without CapEx Costs appeared first on Griffin Open Systems.

To listen to the podcast interview, click the play button in the player below, or download the Control Amplified podcast on your favorite podcasting platform.

To read a transcript of the conversation click here.

The post Podcast: No-code approach lowers AI roadblocks appeared first on Griffin Open Systems.