Virtual Reality in Chemical Industry

The New Reality

Next month Winter Olympics will be staged in Pyeongchang, South Korea and many of the exciting events like Alpine Skiing, Figure Skating, Ice Hockey etc will be broadcast around the world in Virtual Reality (VR), providing an immersive experience for millions of viewers. And when that happens VR would have arrived big time on the centerstage of the world. Older readers would remember the days when people listened to cricket commentary, not even on radios owned by them but in store displays. Grandmothers fueled our imagination by narrating folktales and epics, which then assumed a new shape as we read those accounts in comics and storybooks. The imagination got further altered and intensified as we watched those stories being enacted, first in 2D and then 3D. VR is expected to refine this experience even further. The power of VR lies in its ability to provide an order of magnitude boost to our visualisation and imagination. This can be harnessed not just for entertainment, but also education, research, training, design, construction, operation and maintenance. In the coming decade no industry is expected to be untouched by VR. VR is predicted to grow into a trillion-dollar industry by 2035.

Origins

VR is not such a new idea; it has been around for six decades. The father of VR is Morton Heilig, an American cinematographer, who in 1957 built the Sensorama Simulator, a machine that allowed you to virtually ride a bike while experiencing the sounds, vibrations, wind and even smells of the road. Probably too ahead of its time, it was a spectacular flop. The content of VR is created using CGI (Computer Generated Images) or by capturing images using a cluster of cameras to provide 360-degrees point of view. In the playback mode, sensors in the headset track the user’s head movements and alter the view accordingly. Optimal VR experience requires high resolution screens, and powerful processors so that images move in-sync with the user’s head providing a seamless experience. It is only recently that screen and processor technology have improved so much in both performance and price that VR is becoming commercially affordable.

Education

It is quite easy to foresee the benefits of VR in chemistry and chemical engineering education, where the students can get a deeper understanding of molecular structures, reaction mechanisms and other molecular-level phenomena. The earliest known application of VR in chemical engineering education was Vicher, a VR based simulator developed at University of Michigan in 1995. Vicher was used as an aid to teach Chemical Reaction Engineering to undergraduates. Students were able to travel through pipes and enter inside the reactor to observe the reaction. The objective of the model was to get a better appreciation of the reaction mechanisms both outside and inside the catalyst. It is remarkable that John Bell and Scott Fogler were able to build such a VR model way back in 1995 from “primitive” hardware, compared to what is available today. VR transforms learning into an enjoyable experience as students feel empowered and have control over the learning process. VR is advantageous for learning the abstract concepts of chemistry and chemical engineering, particularly for spatially-challenged students as it does away with the traditional language-based instruction, that would often commence with “imagine you are on….”

Research

Perhaps the most mind-bending application of VR is in discovering new molecules. Scientists at Novartis, for example, are using VR headsets to immerse themselves in a protein and walk around, with a view to understand how drugs interact with proteins in our body. By this way, they hope to alter the molecular structure of a drug and thus improve its efficacy in arresting a disease. VR has great potential to speed up the discovery of new drugs.

Plant Design and Construction

Forty years ago, the only tools for plant design were paper, pencil and tons of imagination. Then came the plastic model in 1980s. They improved visualisation considerably, but were cumbersome to construct and handle. The plastic models usually ended up as displays in the reception area to be showcased to VIP visitors. Computer Aided Design (CAD) generated 3D models are now the mainstay of plant engineering. While the 3D models facilitate collaborative efforts in plant design, the workflow gets mired in multiple time-consuming reviews for operability, accessibility, constructability and safety. Reviews are performed on computer monitors or projected screens and the comments generated during these reviews are usually captured on paper and then painstakingly incorporated into the model. The iterative process of create – review – recreate – review takes time and effort. This is where VR would make a world of difference. It has the potential to reduce the cycle time by boosting collaborative effort and an entirely different human-model interface. The alterations could be done in real-time through hand gestures and eye movements. The reduction in engineering efforts and time would be very significant.

Such collaborative visualisations can be extended to the construction phase, usually the most difficult and complex phase of the project.  Supervisors equipped with VR headsets can track the progress of construction in real-time.

Operator Training

While building new plants, many chemical companies invest in Operator Training Simulator to prepare their personnel for plant operation. This simulator only addresses the control room staff. Adding VR environment to such a simulator will not only raise the training experience to a new level but also expand it to include the field operators who are in the “firing line”.   With human failing responsible for over 90% of industrial accidents, improved and regular operator training on a VR platform will minimise catastrophic incidents. Stressful conditions associated with an emergency like fire or explosion can be simulated realistically and operators’ response can be measured. This will improve the preparedness to deal with disasters.

Final Thoughts

VR is now a very mature technology. In the Gartner Hype Cycle (referred to in previous editions of this column), VR is on the Plateau of Productivity and is marching ahead for widespread commercial adoption. VR is poised to grow and thrive in a culture that is becoming increasingly comfortable with processing images and less adept at handling text. Many businesses are likely to gain significant competitive advantage from VR. As also pointed out, on more than one occasion, the chemical industry is a laggard when it comes to adopting new tools and techniques. It will show little urgency to adopt VR. VR does not need chemical industry; chemical industry needs VR. Chemical industry has to seize the initiative and get developers to build relevant applications for it on VR platform.

Unchaining the Blocks

The final column of this year cannot but be on Blockchain, the disruptive technology behind Bitcoin, the phenomenon of 2017. The value of Bitcoin after crossing the $1000 threshold on 1^st January, leapfrogged to $19000 in mid-December. This spectacular, probably speculative, rise lends a certain notoriety, not just to Bitcoin but Blockchain itself. Bitcoin is just one of the many cryptocurrencies that Blockchain has spawned. As of last month, there were more than 1300 cryptocurrencies, with a market capitalisation in excess of $600 billion. This discourse is about Blockchain, the backbone on which cryptocurrencies, especially Bitcoin, stands tall. But for Bitcoin’s meteoric dazzle, Blockchain would have remained obscured in the shadows.

Blockchain Technology

Blockchain technology is not easy to comprehend, let alone describe in 1000 odd words. What is germane however are its principles that hold out the promise to its adoption in various commercial and industrial applications. It is easy to visualise Blockchain as a distributed digital platform to carryout transactions. Such transactions could be financial, say between two or more banks, or between buyers and sellers. Or they could be exchange of confidential information like data and knowledge between two or more parties. The salient feature of the Blockchain platform is that it is distributed and decentralised. The transactions occur peer to peer (P2P) without being overseen by a central regulator. The cost of transactions is reduced substantially and this is perhaps the biggest benefit of Blockchain technology. Investment banks estimate that their infrastructure costs would be slashed by an average of 30%

.

Types of Blockchain

The information that is exchanged over Blockchain is secure and transparent. They are safe from deletion, revision and manipulation, leaving behind a trail that can be verified, validated and audited. These are valuable attributes for a business transaction, especially when it comes at a low cost. There are three kinds of Blockchain – public, private and hybrid. Bitcoin, or any other cryptocurrency, is the best example of a public Blockchain, a network that is completely open to everyone to join and participate. A private Blockchain, on the other hand, needs an invitation or permission to join. While individuals within a single business entity are invited to participate in a private Blockchain, a hybrid or consortium Blockchain extends this to several entities in a business cluster. It is the private and hybrid Blockchains that are of great interest to the business enterprise.

Smart Contract

A major application of Blockchain across industries comes in the form of Smart Contract. Smart Contracts are self-executing contracts with the terms of agreement between two or more parties written into a computer program, that resides on a decentralised Blockchain network. This allows transactions to be carried out without the intervention of an external enforcement mechanism. The transactions are speedy, transparent and auditable. Smart Contracts need not be limited to the financial transactions involved in buying and selling of goods; it can be extended to virtually any process that consists of a sequence of events with the outcome of one event defined as the enabling conditions to start the subsequent event. Such a Smart Contract enabled workflow based on “if-then” principle can be used in an engineering design office to smoothen and speed up the work. It can be used to streamline batch processes. The application of Smart Contract principle in manufacturing industry is limited only by our imagination.

Supply Chain Management

Blockchain technology has the potential to disrupt many industries; manufacturing is only one among them. The applications of Blockchain in the chemical industry are no different from rest of the manufacturing sector. One of the obvious benefits would be in supply chain management. The chemical industry has a long and complex supply chain and by getting all the parties together on a hybrid Blockchain platform, inventory can be managed transparently. Inventory carrying costs can be brought down significantly. Further, Smart Contracts can be used to reduce the cost and time of transactions.

Internet of Things

The chemical industry has been wary of adopting Internet of Things (IoT), widely touted as the harbinger of a new revolution in manufacturing, due to concerns of security. The industry is rightly worried about the vulnerability of the networks on which the machines communicate with each other. The consequences of a cyberattack on IoT networks can be catastrophic in the chemical industry. Blockchain promises to bring the same level of security to IoT networks as in cryptocurrencies. A lot of research is currently underway on Blockchain-based IoT security. This has promise to build a robust IoT network that can be trusted by the chemical industry, eventually paving the way for its widespread adoption.

Compliance and Sharing

The integrity and trustworthiness of data on a Blockchain network is useful for those sectors of the chemical industry, pharma and food processing for example, that are governed by external regulators. Instead of managing cumbersome paperwork that fosters mistrust, all concerned parties can be brought on a common platform of trust powered by Blockchain. The regulator’s task of monitoring compliance becomes a cakewalk. The same principle can be used by a cluster of industries to share a common infrastructure, say utilities or CETP. By coming together on a hybrid Blockchain platform, the users can provide real-time data to the utility provider for planning and optimising operations. This argument can be further extended to share best practices by multiple locations of a common business entity. Instead of the conventional practice of reports and annual meetings, where such lessons get distorted and manipulated due to human bias, multiple sites can be linked together on a private Blockchain platform of trust and transparency.

Critics

It must be mentioned here that the applications mentioned above are possible even in a non-Blockchain environment. But Blockchain brings certain unique properties that bear repetition – trust, transparency, integrity and low cost. Blockchain technology is not without its fair share of critics and sceptics. Most of the scepticism flows from viewing the technology through the lens of Bitcoin. Bitcoin is a powerful demonstration of the power and potential of Blockchain, but it is built on a public platform. The number of transactions is so large that it requires a great deal of effort and energy to validate them. This validation is done by gatekeepers, who are known as miners, because they are rewarded by a Bitcoin for their efforts. This validation or “proof of work” to use the jargon, requires the miners to perform energy-intense computational work to decipher a code, that can be then appended to the digital transaction. The energy required for this mining is currently estimated to be consuming 0.13% of global electricity and by 2020 is expected to equal the consumption of Denmark. The enterprise-level applications would however be on a private or consortium platform, with far fewer transactions requiring only a minuscule amount of power.

The chemical industry has always been conservative in adopting digital technologies and practices. The industry’s giant BASF revealed mid-year that it is working with a start-up to explore the potential of Blockchain in supply chain management. This could unblock the industry’s mindset soon. 

Lessons from Harvey - IV

PART - I

PART - II

PART - III

Revisiting plant siting

Reasons for siting refineries on the coast are obvious. But they are sitting ducks for hurricanes. And if hurricanes and typhoons are likely to be more frequent we need a radical rethink. New refineries, not that many new ones are likely to be built, should be located inland. Existing refineries should consider erecting multiple barriers to avoid loss of containment.

One of the most horrific accidents in the aftermath of Harvey was the fire and explosion in a Peroxides plant. Peroxides are very unstable compounds and need to be stored under refrigeration. When the hurricane knocked out main power supply to the plant, the backup generators failed to start because they were submerged in water. Locating the generators at grade level was clearly a bad idea. But it appears bad only on hindsight. The company had refrigerated trucks to move out the Peroxides to a safer inland location. But by the time they decided to act, the roads were overwhelmed with water. The accident could have been totally avoided had the backup generators been located at a height beyond reasonable access of flood waters.

Post Script

Seismic zones are taken into account while designing structures in a chemical plant. Now that hurricanes are expected to become even more frequent than killer earthquakes, we need an improved system and response in place from design techniques to disaster management. Ironically, the response to Harvey was hampered by industries taking shelter under the fig-leaf of an anti-terrorism act, under which they were not obligated to disclose to authorities the nature and quantity of chemicals they stored in their premises. 

Lessons from Harvey - III

PART - I 

PART - II

Revisiting plant inventory

Many chemical plants, especially those built in the last millennium, carry far too much inventory. This excess baggage harks back to the pre-computer and pre-Internet era when supply chain management practices, as we know them today, were not prevalent. Online procurement now has done away with time consuming paperwork and approvals. RFID tracking of shipment has reduced uncertainties. Logistics planning, optimised shipping methods and routes, synergy with suppliers etc helps the industry to prune down the inventory. Inventory reduction not only brings down the operating expenses significantly, but is a giant step towards improving plant safety.

Consider what happened during Harvey. Nearly half a million gallons of gasoline spilled out from just two tanks owned by one of the largest pipeline operators. The exact cause of the leak is still under investigation. The pounding rainfall also reportedly sank floating roofs of at least a dozen large storage tanks leading to leaks. At least two dozen storage tanks holding various refinery materials have collapsed spewing out carcinogenic aromatics – Benzene, Toluene and Xylene. API standards mandate that floating roofs should be designed to withstand a rainfall of 250 mm in 24 hours. Harvey brought more than double that rain. Perhaps on hindsight, we need to redesign and strengthen floating roof tanks for a higher rate of rainfall. It will most certainly add to the cost, but would be a small price to pay for protecting the environment. Increased frequency of inspection, maintenance and structural audit of large storage tanks should also help. Clearly storage tanks bore the brunt of the storm surge. The damage would have been less with reduced inventory.

It must be mentioned here that some refineries were able to increase the levels in their storage tanks during the build-up to Harvey. This made the tanks less buoyant and less vulnerable to floating when the water swamped the tank farm. 

Lessons from Harvey - II

PART - I 

Revisiting risk assessment

Hurricanes like Katrina, Harvey and Irma can no longer be considered as “acts of God” or Black Swan events. They are now the new normal and risk matrices need to be reconstructed. Weather experts believe that hurricanes will get more frequent and more powerful as a fallout of Global Warming. Chemical Industry needs to have plans in place to deal with them. Mathematically speaking, risk is a product of severity and likelihood. Likelihood of monster hurricanes like Harvey and Irma need to be ratcheted up by one or even two levels. This will alter our risk perception completely and will call for new safeguards and disaster management plans.

Hazop is another risk management tool that needs a serious rethink. While a lot of attention gets lavished on the ISBL plant during Hazop study, the OSBL plant gets a short shrift. It is the OSBL that has the biggest foot print, usually several multiples of the ISBL. Again, it is the OSBL that holds most of the inventory in the plant. OSBL comes across as a poor unglamorous cousin of ISBL during design, engineering, personnel training, operation and maintenance of a process plant. Even in education curricula it hardly gets the importance it deserves. This approach and attitude needs to change.

Plants, especially those on sea coasts, can be asked to redo Hazops considering flooding and power outage as a cause. The worst credible consequence and safeguards for this scenario should be placed in public domain. This will go a long way to improve the trust and confidence of the larger community around the plant. 

Lessons from Harvey - I

Hurricane Harvey is on course to join the dubious list of disasters - headed by Bhopal, Flixbourough and Seveso - in the Chemical Industry. Not only did the category 4 hurricane cripple the refining and petrochemical hub of the world in Texas, but it also led to unprecedented spillage and release of toxic and carcinogenic chemicals into the atmosphere. According to a report in New York Times, more than 2000 additional tonnes of chemicals were released from 46 industrial facilities during the week Aug 23- Aug 30. In addition, 14 sites holding toxic wastes were inundated. It is not that Harvey arrived unannounced. It was known for a week and its lethal potential was assessed at least 48 hours before it struck Texas. Yet the chemical plants in arguably the most industrially advanced country of the globe were caught napping and their responses turned out woefully inadequate. How did this happen? A silver lining of every accident is that it mandates us to raise the bar for safe practices. But for Flixbourough we would not be having Hazop; Responsible Care emerged out of Bhopal’s graveyard. So, what do we learn from Harvey? I can quickly think of following three lessons.

Revisiting risk assessment

Revisiting plant inventory

Revisiting plant siting

Artificial Intelligence in Chemical Industry - IV : Materials

Part 1

Part 2

Part 3

Materials

It might take a decade or more for the AI scenarios described above to be turned into reality. The most immediate impact of AI is likely to be in the area of materials, more specifically on how materials are discovered and synthesised. Historically scientists have stumbled upon new materials by accident. It has taken several years before their properties were fully understood and the material was put to commercial use. Graphene, touted as a wonder material, is still floundering 13 years after its discovery. AI is poised to turn around this process, putting application first and synthesis second. Material databases containing hundreds of thousands of compounds are now available. Properties of these “yet to be made” compounds are in the process of being predicted. AI based systems will zero in on a specific candidate in these databases to meet the required application. Such tailor-made materials will rule our future in energy, healthcare, transportation and many other areas. 

Artificial Intelligence in Chemical Industry - III : Anticipation

Part I

Part 2

Anticipation

e-commerce juggernaut Amazon patented “anticipatory shipping”, a system which helps them to predict what customers are going to buy before they actually order. Let us imagine a similar scenario in chemical industry. A fertiliser company manufactures 3 crop-specific product grades. The company’s product slate mirrors the likely cropping pattern, which in turn is largely influenced by the rainfall prediction. Each year the company management plans to make the 3 grades in a proportion that is primarily determined by the long-term rainfall forecast issued by the meteorological department. Because the experts of the recommendation committee invariably fail to arrive at a consensus, the final decision is always a compromise of their subjective opinions. Farmers in turn do not rely completely on the forecasts put out, but supplement the information with their own gut feeling before deciding what to sow. An AI based system using historical inputs can be trusted to provide a more objective recommendation in this case. AI based system will help the company management to stay abreast with the farmer’s mind and improve its bottom-line. Such AI based production planning can be profitably adopted for most agrochemicals, whose consumption depends on nature’s vagaries. 

Artificial Intelligence in Chemical Industry - II : Quality

Part I 

Quality

Another area where AI can contribute immensely is quality. Many quality parameters are not possible to be measured online and need the intervention of a laboratory. The granulometry of a prilled product, for example. Or the Iodine Value of oil; or the opacity of a pigment. Any measurement in a laboratory is riddled with three problems: sampling error, contamination during sampling and time-lag. Oftentimes, if the results are not as per expectation, there is no alternative but to recycle the product or label it as off-spec. Now compare this with the scenario in a kitchen, a veritable chemical plant, where quality requirements are equally stringent and complex, if not greater. Corrections to perceived shortfall in quality are instantaneous and intuitive in the kitchen. If AI systems be taught to replicate such actions in a chemical plant, laboratories will be rendered redundant. 

Artificial Intelligence in Chemical Industry - I : Safety

Space Odyssey 2001, a cult sci-fi film of 1968 by Stanley Kubrick, describes a journey to Jupiter. HAL, a computer onboard the spaceship has intelligence to take decisions. In a spine-chilling finale, HAL decides that humans are a threat to its mission and plans a clever stratagem to do away with the crew. This is the kind of “artificial intelligence” that the noted sci-fi writer Arthur C Clarke envisioned more than 5 decades ago. Today “Artificial Intelligence” has been reduced to AI and bandied about in many unintelligible ways.

AI has become a buzzword and interchangeably intermixed with Robotics and Internet of Things (IoT). Robotics and IoT are tools of convenience; AI is far more. Robots and machines on IoT perform as per the way we humans program them. AI systems think for themselves and may perform actions that we don’t expect them to. We don’t program AI systems; we teach them to think for themselves, just as we do.  Intrinsic in this is our acceptance of the limitations of human brain; both its size and speed of information processing. 

Automation

What inroads will AI make into the chemical industry? The degree of automation in the chemical process industry is already very high. Control algorithms are getting sophisticated and the response times are becoming shorter. Advanced and predictive control systems are allowing plants to be operated very close to the theoretical efficiency. Feed-Forward control systems allow process parameters to be adjusted in anticipation of changes in the quality of raw material. Equipment fitted with smart sensors monitor and announce their health in real-time, thereby improving the plant reliability immensely. All these have become possible because of human intervention aided by computer technology and are not to be confused with AI.

Safety

Despite the high degree of automation, the chemical industry has been plagued by horrific accidents. The safety Guru, Trevor Kletz, in his seminal work – An Engineer’s View of Human Error – says that statistics support the view that as many as 90% of industrial accidents are due to human failing. Kletz then proceeds to catalogue various types of human error – error due to momentary lapse of attention, error due to improper training or instruction, error because the task is beyond a person’s ability, error due to noncompliance. All these four types of errors can be eliminated by a robust artificial mind that is intelligent and free of fatigue and emotions. “Zero Accident” can thus be a lofty goal for adopting AI in chemical industry. 

Chemical Industry - Jamming Unfriendly Drones

In my previous posts, I have described 3 potential benefits of drones in the chemical industry - Inspection, 3D-Modelling, Monitoring. 

But drones are invasive and intrusive. Even the most rudimentary chemical company is paranoid about security. All of them forbid photography expressly, and require some kind of permit to enter the premises. The Jubail industrial complex in Saudi Arabia is in a sterile zone with armed police guarding the outer perimeter and each plant site has two levels of fencing. Drones will make mockery of even this kind of security. Inspection and espionage are two sides of the same coin. When an evil eye inspects, it is espionage. So the chemical industry is rightly worried about the misuse and abuse of drones. At stake is intellectual property worth trillions of dollars. It also makes the industry very vulnerable to terrorist threats. Chemical companies will have to conjure something equally innovative to detect and jam unfriendly drones.

And now comes the news that such a cutting edge defence system has been developed and is being tested in a UK prison. The system will seize control of the drone once it crosses the "fence" 

Drones : A futuristic application in the Chemical Industry

Read the earlier 2 posts on Drones here and more : 

Another futuristic application of drones that I envisage is using them as an advanced warning system about the safety and health of the plant as a whole. Every chemical plant has fugitive emissions from hundreds of components: flange gaskets, pump seals, valve packing etc. These fugitive emissions constitute a unique “chemical signature” of the plant. A sudden spike in the fugitive emissions can be used as an alert to a possible malfunction and preventive intervention before things go out of hand. This would require fitting drones with sophisticated sensors which can sniff out chemicals in trace concentrations. Such sensors, for example Fourier Transform Infrared Spectroscopy, are already becoming available and the technology is poised for further improvement. Drones would obviate the need to fit multiple sensors at many locations and make data collection simple and inexpensive. Such drones can also be deployed to keep tabs on illicit production of chemical weapons and enforce CWC. 

More on Drones and the Chemical Industry

Read my earlier post on Drones here first. 

Another potential application of drones is in reconstructing 3D models of old plants. A large proportion of today’s plants are built during the time when CAD has not made its mark, using paper drawings or at best plastic models. This primitive documentation becomes a hurdle when these plants have to be revamped or modified, because the present generation engineers are more conversant and comfortable with 3D design. Some of the plant owners have undertaken exercises to reconstruct their plant in 3D formats. These are based on laser scanning techniques and are expensive and time-consuming and also far from perfect. Drones fitted with special cameras can fly computer controlled sorties to construct 3D images of plants. Such services are already being offered by more than one company in USA.

Drones in Chemical Industry

Drones or Unmanned Aerial Vehicles (UAV) as they are known technically have been around for a very long time now. The term ‘Drone’ was coined by US Navy, since it was inspired by Queen Bee, the remotely controlled aircraft used by British Navy. This was in 1935 and since then drones have got smaller, swifter and smarter. One industry which hopes to benefit immensely from drones is the US$ 4 trillion chemical industry.

Drones literally elevate process plant inspection into a different orbit. Firstly the frequency of inspection can be as warranted by the situation and not tied down to the availability of infrastructure and / or experts. No need to fly out experts to the site. High resolution images can be viewed by experts sitting in the comfort of their offices or homes. No time wasted on erecting clumsy scaffoldings in difficult to access areas. Flying a drone is as simple as throwing up a paper plane. And the drones can fly irrespective of the rough weather. 

Secondly the quality of drone inspection is superior. The probes carried by the drones can get much close to the metal than the human face or hand without fear of making contact. The human subjectivity while collecting data can be completely eliminated by building artificial intelligence into the drone. Some people are calling Drones “the flying computers”. Also the data collected by the drone can be analysed by more than one expert at multiple locations, in real time. And lastly, but most importantly, Drones make inspections safer, totally eliminating the need for workmen weighed down by protective equipment to ascend vertiginous heights in inclement weather. Dow Chemical became the first company to use drones for plant inspection after getting approval from US Federal Aviation Administration (FAA) in 2015.