The story of industry centers around advances in efficiency and production. Any enterprise that doesn’t constantly optimize their production processes risks being surpassed by a competitor that has innovated their way to higher margins. If you add in rising energy costs, the imperative for refineries, manufacturers, mines and other asset-intensive companies to make a profit is even stronger. To succeed in today’s market, companies must aggressively pursue and decisively implement production optimization strategies. Production optimization is the practice of maximizing production from a given facility with the available equipment. It involves upgrading a factory or facility’s operating parameters to increase margins—without necessarily upgrading the assets themselves.
A company’s practices, processes and attitudes about production are often inherited, either through company culture or general industry practices. Even a new process or innovation will draw on precedents and industry standards. Basing decisions on past performance and historical industry data fails to consider that even the smallest change, like a slight rise in the cost per watt of energy, can change what defines an optimal configuration. Inability to adapt poses risk. Furthermore, what is optimal for one company or production process may not be optimal for another. This is why companies should view production optimization as a continuous process, rather than a set-and-forget upgrade.
To undertake a production optimization program, an organization needs high-quality data on how its operation normally functions prior to optimization. This information should be as complete as possible, as there may be issues hidden in the data that only appear over the long run. A company that has adopted industrial internet of things (IIoT) technology should have a significant amount of information coming from the networked sensors that dot the production line. These data are invaluable for production optimization, as they provide granular insight into the entire production process.
Companies must not overlook the human element of production optimization. The plant digitalization technology that is providing new opportunities for production optimization has matured to the point of reliability in the last decade. But the personnel who are best positioned to make decisions that will take advantage of these new tools may have developed their skills before the rise of these new technologies. These workers must be prepared to fully implement the necessary changes in order for the firm to practice production optimization, or risk making costly and inefficient decisions. An abundance of caution is a great strategy when managing expensive and dangerous equipment and processes but can hinder optimization.
Every industrial process will require a different approach and each facility may have different requirements. There is no one-size-fits-all solution for production optimization, at least in terms of the actual changes that need to be implemented. Companies should be prepared to undergo an iterative process; the changes and tweaks made at an early stage of optimizing production may reveal further refinements and sources of waste.
This is where process simulation software can be a huge boon for optimization. By creating a digital model of the process that is being optimized, companies can explore the impact of changes in a simulation instead of having to risk a loss of production by actually making changes to an asset. Digital models can simulate a variety of scenarios; adjusting this parameter or altering this arrangement may make sense in certain market conditions, but what happens if the price of the product drops? Operational teams can review many options quickly to identify the best path forward.
The simulation can also help assuage any misgivings about data-based decision-making. Showing a living representation of proposed changes may be more reassuring than simply communicating, for instance, that the compressor should be running at 10% more than the normal pressure.
Optimizing production calls for organizations to sift through a staggering amount of data and choices. The layout of a facility alone presents a nearly infinite amount of choices. Any given piece of equipment can have hundreds of parameters to consider, and each setting can affect production. Factor in unknowable market conditions, and the picture is daunting.
Advances in machine learning provide a powerful tool for meeting this challenge. Artificial intelligence (AI) algorithms chew through huge reams of data, looking for patterns and associations. Industrial AI can identify the links between thousands of different production variables and suggest ways to adjust them, leading to much more informed production optimization. Industrial AI can be industry-specific, as in AI for oil and gas, or more generalized. Artificial intelligence algorithms can be holistic in their approach, overcoming the coordination problem of making all the required changes at once to find a new, more efficient equilibrium.
How is production optimization related to value chain optimization?
Production optimization limits itself to the functions under the direct control of an enterprise, whereas value chain optimization will also optimize inputs and outputs. Value chain optimization incorporates information about the upstream supply chain, extending the optimization from the limits of what the company makes, to what the company takes as well. This includes intelligent scheduling of deliveries from suppliers to reduce inventory costs.
How is production optimization related to the smart enterprise?
Production optimization practices are crucial in the journey to the smart enterprise. It would be an enormous waste of resources to undergo an extensive digitalization program, alter the command structure to enable data-driven changes, and then stop short of actually using the information and structural changes to optimize production. Adopting production optimization practices and letting the insights from the data lead the strategic planning are keys to becoming a smart enterprise.
How do refineries use production optimization?
Refinery optimization is a specialized subdiscipline of production optimization that focuses on chemical refining. A refinery may already employ refinery modeling to simulate their processes, which provides an important starting point for optimization efforts. If the operators of the refinery leverage data to drive decisions about production optimization, the refinery may be considered a smart refinery.