Deploying artificial intelligence (AI) and the Industrial Internet of Things (IIoT) within a process manufacturing environment can deliver a number of business benefits for companies, and one of the biggest areas of impact is asset performance management (APM).
The discipline of APM has gained a lot of momentum in recent years. Industrial companies are looking for ways to generate more revenue from their assets without the added expense of buying new ones or upgrading the existing infrastructure. APM software, with the help of AI, enables companies to achieve this goal.
APM lets companies leverage the large amounts of data being generated by the industrial sensors that are monitoring critical assets. A good APM solution takes advantage of AI algorithms to achieve positive business results.
When companies operate assets such as membranes, clarifiers, condensers, cooling systems, or clean-in-place systems, several standard practices are typically in place. These rules are used to maintain production at a reasonable level, and to ensure adequate performance and quality of the assets.
The standards are by no means perfect, but the system works in general. If operators had a better understanding of the specific process and its unique response to future conditions, they would agree that the performance could be improved.
The problem is there are a large number of varying conditions to monitor. In addition to that, the amount of data they need to sift through with standard analytics is too vast to be useful. It’s also time-consuming. Always detecting and measuring the changing relationships is difficult to do manually. Without continually doing the work and getting lucky in identifying correlations, any improvements made will fade over time. They become no better, and possibly even worse, than the rules of thumb they replaced.
AI and APM
AI can address these challenges. It allows users to discern correlations, find the cause of a specific problem, and predict its impact by using algorithms to analyze large volumes of data.
An APM solution can use these AI algorithms to predict business outcomes. It continues to analyze data and optimize setting recommendations to address likely future conditions. The result is companies can deploy the best actual settings to reduce costs, improve quality and mitigate unplanned downtime.
When AI is implemented properly, instead of using static or semi-static conservative settings, operators would receive the best settings for a specific duration. But what about the cases when the predictions are off? After all, if the information provided by AI is wildly incorrect, some of these processes might affect the health of a community and the reputation of a company.
This is where APM comes in. In a good solution, advanced analytics or predictions are an important but small part of the information delivered. The rest includes useful metrics and key indicators that provide evidence of the conditions and support the recommendations derived by AI.
The value of these indicators is usually more important on a daily basis than the advanced analytics or predictions. For an APM solution to be effective, it should provide a way to continuously track the impact of asset performance over future revenue metrics. This doesn’t necessarily refer to predictions, but rather hidden patterns that are not visible to the naked eye.
APM solutions centered on business processes, as opposed to machines themselves, are more likely to succeed.
More manufacturers are adopting digital transformations through Industrial Internet of Things (IIoT) technology, with the move from metrics to analytics leading the way, according to a recent report from LNS Research.
The study highlights how companies should move away from metrics to focus on advanced analytics. The manufacturing sector has seen a variety of new analytics applications launched over the past three to five years, including a strong focus on APM and other maintenance-related processes.
Traditionally, companies began with a dashboard of simple metrics to show “up-to-the-moment” status of machines and operations. This helped with response times and improved time to resolution when issues occurred. But little live data from systems actually moved into data stores outside a plant. It’s this shift that will help companies start to leverage real-time analytics.
As AI and the IIoT continue to advance, they will become increasingly important to manufacturing operations. Leveraging AI is not easy and success is not guaranteed, otherwise everyone would do it all the time. It remains a rapidly emerging field that involves a learning curve.
Still, the benefits are compelling when AI is implemented correctly. APM can provide information and recommendations that will give companies a significant competitive advantage.
Prateek Joshi is the founder and CEO of Plutoshift, which provides asset performance management solutions to process industries including water, food and beverage, and chemicals. He is an artificial intelligence researcher, the author of eight published books and a TEDx speaker. Joshi has been featured on Forbes 30 Under 30, CNBC, TechCrunch and more.