All too often, the process and manufacturing industry reaches the headlines because of serious and sometimes fatal accidents that occurred in process plants. In the last 12 months alone, over 100 people have died and hundreds more have been injured by explosions and leaks at refineries and chemical plants.
Just to mention a few examples:
In July 2019, an explosion at a gasification plant in China killed 15 people, injured 15 more, damaged dozens of buildings and shattered windows within a 3km radius, and contaminated a local water source.
In June 2019, 5 people were injured in 3 simultaneous explosions at a gas refinery in Philadelphia, PA. The 71 tons of hydrogen fluoride used in the plant could have caused up to several million deaths, if an alert worker hadn’t activated the emergency procedure to drain poisonous acid from the unit before it was released into the atmosphere.
In China, another explosion at a chemical plant in March 2019 killed 76 people, and was so powerful that earthquake detection equipment mistook it for a 2.2 magnitude tremor. It came just a few months after 23 people died in an explosion caused by a vinyl chloride gas leak at another Chinese chemical plant in November 2018.
One person was killed and 2 were injured in an aluminum dust explosion at a German chemical plant in October 2018. A similar incident had occurred at the same plant just a few months earlier, although no one was hurt in that event.
Another person was killed and others injured while cleaning out a pipeline at a gas processing plant in Pittsburgh, PA, in December 2018.
New opportunities for AI
These terrible accidents highlight the need for new tech, and its ongoing evolution in the manufacturing and process industry. When AI, predictive analytics, and other cutting edge tools entered plants and refineries, their main role was to lower the cost of maintenance.
Since then, we’ve seen AI move into other areas to bring about improvements to multiple aspects of the process industry such as improving OEE and raising quality. However, headline-grabbing fatal incidents like the ones mentioned above have propelled plant safety and environmental impact to the forefront of new AI-powered solutions.
What’s more, new stakeholders are entering the picture. Insurance companies have noted the potential for predictive analytics to enhance their risk assessment, since AI-powered predictions can be more accurate at predicting the likelihood of a claim being filed, and even how severe a potential claim would be.
In a similar vein, equipment certification companies like TÜV SÜD, UL, Intertek and SGS are combining predictive analytics with their existing equipment monitoring and maintenance services. With the added input of AI, these companies can refine their ability to keep equipment up to date. At the same time, they aim to expand into the new field of validating the underlying AI algorithms that form the foundation of all AI-powered tools.
In light of these serious incidents, it’s no surprise that numerous plants and refineries also want to put predictive analytics to use to improve their safety record.
Using AI to improve plant safety
For every massive explosion at a plant or refinery, there are scores of minor safety incidents that lead to injuries and sickness onsite or pollute the surrounding environment, making AI safety solutions highly valuable. AI-based software like SAM GUARD aims to prevent a potential crisis by spotting the early signs of equipment failure or serious chemical buildup. By delivering these advance alerts, AI solutions help companies to repair weaknesses while they are still minor, long before they could cause a chemical leakage or disastrous explosion.
Cutting edge predictive analytics and ML solutions also help by reducing the number of false alarms that plant supervisors have to deal with. At least one serious incident may have occurred because oil workers disabled crucial alarms out of frustration at the number of false alerts they received. Ensuring that the majority of alerts are valid helps stop workers from ignoring safety alerts that seem to permanently “cry wolf.” SAM GUARD minimizes the number of daily alerts to just the few that merit investigation, avoiding “alert fatigue” that can cause unnecessary harm.
Ongoing tech innovations such as robots are also succeeding in taking over many of the highly dangerous jobs in the field, reducing the risk of serious or fatal injuries to workers. For example, inspecting the inside of a fuel tank can be better handled by a robot. Other tech tools are working to minimize the environmental impact of manufacturing and process industries, reducing oil spills and leaks of hazardous substances that can affect plant, animal, and human health.
Predictive analytics still has potential to improve plant safety
Every serious incident at a plant or refinery has a different cause, and frequently multiple causes. It can be very difficult to pinpoint a single change that would have prevented the accident, but that doesn’t stop R&D teams from working on new ways to use AI and other advanced technology for accident prevention. SAM GUARD’s sandbox features include root cause analysis to help with this challenging task of identifying the cause of plant incidents.
AI has come a long way from its use solely in equipment maintenance, and it still has a great deal of potential to actualize in the realms of safety, risk assessment, certification, and more.
To learn more Request a Demo