Since 1970, computer processing speeds have doubled roughly every two years. Moore’s Law predicts that this rate will continue meaning that the ‘brain power’ of most CPU’s will soon out think the human mind.
Considering other factors, such as shared data through cloud computing, quantum computing, the Internet of Things, robotic process automation (RPA), the invention of ever smaller transistors (even as small as a single atom), and artificial intelligence, it is likely that computers will play an increasingly large role in everything.
While this can remind us all of the Terminator movies and thoughts of asking SkyNet to run your defence system, we should totally recall that this is science fiction. Science fact dictates that the practical uses for industry will be enormous and highly profitable for those that grasp the opportunity.
Nowhere will this be more true than in the chemical industry. With its highly technical manufacturing processes, complex logistics, current high use of computers, and advanced R&D programs, the chemical industry will be a clear beneficiary of advanced computers and AI.
But is this the future or the present, because at many chemical companies AI is already making an impact.
One such advocate of investment into artificial intelligence is polymer scientist Dr. Ata Zad. As founder of the Canadian plastics company AxiPolymer he is convinced of the competitive edge that his business has through its implementation of AI. An opinion he made clear in a recent interview with the industry journal Canadian Plastics, “Every plastics manufacturer has the potential to integrate machine learning into their operations and become more competitive by gaining predictive insights into production,” he said. “Machine learning’s core technologies align well with the complex problems manufacturers face daily, especially large manufacturers that have the largest amount of raw data.”
Sandeep Sreekumar, global head of Adhesive Digital Operations at Henkel, also sees the benefits. “We use AI to run efficient analyses of complex data arrays for achieving higher production performance, quick product innovation and scaleup for our self-adjusting production systems,” he explained. “Our focus is not only on collecting internal manufacturing data, but also on actively working with customers on data collection opportunities during product usage to make improvements and adjust to changing customer needs.”
Pushing the Boundaries of AI in the Chemical Industry Even Further
In Japan, SDK (a Toyko-based chemical and technology business) and the hi-tech manufacturer Hitachi have collaborated in the development of an AI-assisted predictive-maintenance platform.
As the online industry journal Chemical Engineering explains, “SDK’s Oita Complex ethylene plant served as the trial facility for demonstrating the commercial practicality of the new AI service, which utilizes adaptive resonance theory (ART) to analyse and classify plant operational data in real-time and identify anomalies that could lead to equipment failure. In trials at the Oita plant, the technology successfully predicted the occurrence of coking. According to Hitachi, this method is able to detect patterns and abnormalities that would not be detected by conventional predictive-maintenance models. Now, SDK plans to roll out the technology into additional plants, while also further refining the AI model for determining different coking mechanisms.”
Meanwhile, in Huelva, Spain, the energy and chemicals producer Cepsa, has employed AI at its phenol production plant resulting in a 2.5% increase in output (an additional 5,500 metric tons per year).
This was achieved through machine learning and real-time predictive models that offer plant personnel recommendations on how to improve production every 15 minutes. The analysis involves the AI considering over 3,000 process variables. It even considers the weather.
And in Madrid, the energy and chemicals producer Repsol has collaborated with Google Cloud to apply AI and advanced data analytics towards optimizing resources at its 186,000 bbl/d petroleum refinery in Tarragona.
As the company’s press release notes, the process will manage, “… around 400 variables, which demands a high level of computational capacity and a vast amount of data control.” This is something that represents, “an unprecedented challenge in the refining world [because] until now, the highest number of functions integrated digitally in an industrial plant is around 30 variables.”
Crucially, the company also highlights the economic gain in using such advanced computers to analyse its refining process, stating that, “The project has the potential to add 30 cents on the dollar to Repsol’s refined barrel margin, which could translate to 20 million dollars annually for the Tarragona refinery, with significant upward growth if all optimization objectives are achieved.”
Evidently, AI computing’s presence in the chemical industry goes beyond mere potential. Leading manufacturers are already implementing machine learning and real-time ‘big data’ analysis.
While predicting the future has always been the task of fools, it would be unwise not to believe that AI has a future in the chemicals industry as it already has a presence.
If nothing else, its potential is truly astounding, such that what was said in the 1990’s about the Internet, when no one fully understood it, now people talk the same way about AI.
As the online journal Chemical Engineering notes, “While advanced technologies like quantum computing are still very new to the chemical processing industry, new applications will certainly continue to arise as more users begin to understand the capabilities of AI.”
If you would like to learn more about AI and its impact on the chemical industry, then you might enjoy reading ‘How Artificial Intelligence is Making Smarter Chemical Products‘. Or take a look at other articles on the SPOTCHEMI blog page.
Photo credit: Nividous, FlynetViewer, GEA, Ohlindustrial, WashingtonUniversity, Repsol, & NKD