October 25, 2017 | Written by: Viswanath Krishnan
Categorized: Industry Insights
Process Manufacturing – typically including refining, petrochemicals and commodities chemicals – has traditionally focused on stability, controllability and optimization. Advanced control techniques and information integration pushed operations closer to economic constraints while maintaining desired objectives around safety, stability and production. The natural progression in smart manufacturing has been to adopt advanced analytics and enhanced decision-support.
As depicted, manufacturing assets and processes have related information ranging from real-time data, operating procedures, and regulatory requirements to new information from sources such as augmented reality. These types of structured and unstructured information remain untapped when it comes to leveraging for decision support.
This untapped potential is where newer technologies such as IoT (Internet of Things) and Cognitive applications are beginning to make impacts. These technologies are gathering significant momentum in process manufacturing in the form of pilots and proofs-of-concepts. That is not to say that the penetration is of the same order for both trends. The success of these initiatives depend on the functional areas in which they are applied and the approaches that are used to deploy them.
IoT – as applied to process manufacturing
IoT, ever since it was coined in the late 90’s, has found broad acceptance as a key transformative enabler of Industrie 4.0. While being more pervasive in household appliances (thermostats or garage doors, for example), the industrial version of IoT is still on the uptake. Industrial IoT (IIoT, as it is sometimes referred to) has seen broader acceptance in automotive and electronics segments where predictability is of a higher order when compared to process manufacturing. The affordability also makes other industries more suitable for IoT, particularly if they were not well instrumented to begin with. A refinery, on the other hand, is highly instrumented and integrated except for the odd ones that are still out there deciphering pneumatic signals. So the question arises as to what additional information this new technology can bring, in what way does it change the operations, and most importantly, what is the substantiated business case. When it comes to the terminology itself, there are multiple interpretations of what IoT is and how it is relevant to Industrie 4.0.
So, what is IoT? Specifically, what does it mean for the asset intensive environment of a refiner or chemicals manufacturer?
Frequently, the meaning gets lost because of the way it is applied, the associated business imperatives and just pure buzzword potential. For example, programs such as Manufacturing Operations Management (or MOM, as they are referred to) are tagged as IoT, though they may not have elements of IoT in the strictest sense. Advanced applications that leverage information from sensors and actuators through process control networks have been around for a long time. IoT is often loosely attached to those initiatives as well, more so because of sales tactics or internal business buy-ins.
In a simplistic sense, IoT provides newer and larger volumes of asset-related information delivered using internet/cloud protocols, that were hitherto not available.
First – the information acquisition, management and delivery…
Traditional sensor information is consumed by DCS or SCADA through fieldbus, HART, etc. But today’s customer demands a different engagement – the same way they consume their daily news feeds and sports updates. That requires delivery of information on different devices using internet protocols such as http, etc. This is in direct conflict with the DMZ (demilitarized zone) requirements of the process control network. How can the sensor information be made available to something outside of PCN (Process Control Network)? Will that compromise the security? The choice of the information gathered, and its intent has a direct bearing on its management and delivery. Adoption of wireless networks in the plant environment is one such example which highlights the route the information takes to reach decision support.
Information acquired through IoT-enabled devices are typically outside of PCN and used primarily for decision support. Controllability, and asset security are still maintained within the DMZ so that it doesn’t become a roadblock for IoT adoption.
Second – the volume of information being delivered…
Typically, decision-support only uses up to 15% of the information gathered from the field as per multiple industry journals. Aggregation and filters are used as a workaround to mask inability to handle large volumes of information. High performance computing, real-time streams and analytics have eliminated that constraint. The information gathered by IoT-enabled sensors are therefore processed, contextualized and made available for consumption by other machines or humans with relative ease. This enhances the productivity of the engineers and operators. Optimization targets transition from hourly to every-minute. Energy management becomes a real-time endeavor instead of a weekly activity. All of this is likely to take another leap forward with the recent advances in quantum computing.
Third – the new type of information that is made available…
Smart, as well as traditional sensors typically measure the process variables such as pressure, temperature, flow and qualities. Enabling newer devices with IoT technology brings information that were not available till now. Examples such as: wireless acoustic monitors for valve leaks, flare monitors in stacks and remote asset inspections using Drones/UAVs provide essential information regarding the assets. The benefits are realized in improving optimal conditions, enhanced worker safety and increased productivity. More innovations in sensor technology will deliver additional information from the field that can be consumed without burdening the PCN.
Cognitive – as applied to process manufacturing
Terms such as deep learning, AI etc. have been swirling since the resurgence of cognitive technology resulting from Watson’s grand entry in the gameshow ‘Jeopardy’. Since then it has been applied to encouraging levels of success in different industries such as healthcare, automotive, education and so forth. As with any other technology, it has taken its time to reach the asset intensive domain of a process manufacturer – refining, petrochemicals or chemicals plant.
To keep things distinct, cognitive is defined as the contextual intelligence gained from unstructured information regarding the asset(s) or operation(s) in question. Though cognitive analytics are derived from both unstructured and structured data, the focus here is on its uniqueness in being able to handle unstructured information.
The type of information that is mined can be varied…
Traditional information – data – is consumed in real-time through the sensor network and DCS at the rate of a few thousand tags per minute. And this is further filtered and aggregated to suit the capability and needs of the decision-support entities. It is an understatement that much is lost in the process. A cognitive tool such as Watson can process a million pages per second. So what sort of applications exist in process manufacturing domain that can leverage this ability? The answer depends on the sort of unstructured information available, its volume and its dynamic varying nature.
Assets possess various types of unstructured information, including design documents, inspection routines, alarm conditions, maintenance manuals, spares specifications, standard operating procedures, asset correlations, etc. They also include external information from bloggers and forums about experiences regarding the assets.
Such information pertains not only to the assets themselves, but also to the corresponding operating conditions. Examples would include process economics, catalyst usage, feedstock variability, impacts on asset corrosiveness, etc. Depending upon the process, some of this information could be dynamic in nature. Published journals, technical forums, conference proceedings, etc. add to the consistently changing knowledge base regarding the process and/or asset. Borrowing from a healthcare example, a doctor cannot be expected to be on top of every breakthrough in his or her field of interest. The same applies to a planner, engineer or operator when it comes to the process operation in their purview.
Capability Progression – Enabled by Cognitive & IoT
In other similarly asset-intensive industries, the adoption of innovations such as autonomous assembly lines and real-time asset condition monitoring has led to the concept of ‘lights-out manufacturing’ environments in the near-future. Automation is enabled not only for physically intensive and hazardous tasks, but is also encroaching the expertise-centric domain. Irrespective of the source and ingestion of information, cognitive or IoT, the derivative analytics are leveraged in decision-support.
Information stored within personal hard-drives and in the minds of an aging workforce are the targets for extraction towards building an enterprise with systemic inherent knowledge. To a large extent, loss of the aging workforce is almost behind us and the level of accessible expertise-based information is close to an all-time low. In order to maintain competitiveness and improve key metrics such as safety and productivity, leveraging new technology becomes imperative.
Between applications of cognitive and IoT innovations, the choice of either or combination would depend on the suitability and need of the functional areas. A planner doesn’t have much use for additional IoT information, but can use the cognitive ability to understand feedstock cost and product pricing opportunities. A console engineer can use the flare information from cameras as well as the cognitive ability to identify the operating conditions that induced it in making the mitigating adjustments.
The value of cognitive and IoT innovations towards augmenting experience of operators doing vital tasks in the field so that they perform as efficiently and safely is without debate. The objective, to put it simply, is to make every operator perform like the best operator and every engineer perform with the knowledge of a thousand engineers. Application of cognitive and IoT innovations go a long way in that direction. A transition from an aging workforce has already occurred in the industry costing a significant loss in expertise over the last few years. It might sound unfathomable at this point in time, but the tipping point is within sight where effect of employee attrition on an organization’s knowledge drain starts diminishing.
Adoption of cognitive or IoT technologies deliver capabilities with varying levels of complexity to the enterprise depending on the area of application. Reliability and maintenance is provided as an example in Figure 4. Asset maintenance and, subsequently, unit operations are driven by effectiveness, utilization and availability. The maturity progression covers statistical approach (typically through univariate analysis), predictive analytics (based on empirical or rigorous models) and cognitive application (leveraging unstructured information). The first two capabilities – statistical and predictive – are further enhanced by application of IoT innovation. For example, augmented reality can improve inspection efficiency and expedite risk mitigation actions. For the same asset, cognitive application might be utilized to look at both internal and external reports about the asset to gain additional insight in terms of mitigating actions.
Without a sufficient level of instrumentation, the integration of information systems is a futile exercise. By the same argument, gaining any reasonable level of predictive capability or operational intelligence is not reliable without the right level of integration. The capability progression would take different technology elements, depending upon on the domain of interest. Some of the examples are provided in the progression curve (Figure 5) as an illustration. Not every functional area needs to aspire to be at the end of the curve. Business value, team readiness, ability to support and complexity of the solution need to be considered for target setting along the maturity curve.
When it comes to the adoption of IoT or Cognitive innovation, there have been many examples of organizations being unclear as to where they should start, or, how comprehensive the pilot should be. The approaches often tend to validate the solution across a functional domain with a limited portion of the technology components. This can lead to an inordinate focus on technology elements resulting in compartmentalization of sensors, analytics or cognitive elements. True business value remains hidden in such an approach. As a result, operations frequently remain unconvinced of the results from the pilot or POC.
A better approach – well tested – is to choose a use case within a functional domain. Upon the development of business benefit estimation for the use case, it should be addressed through all the relevant technology components that are required to deliver the use case. This changes the priority from that of ‘testing a technology’component to ‘validating a business capability’. Process maturity models, benchmarking metrics, business process descriptions, and KPIs collectively help accelerate the process of proving the solution in its delivery of the desired capability to the organization.
The proliferation of information – both structured and unstructured – is experiencing a significant bump in process manufacturing. The argument about aging workforce in our industry is almost history as we are already experiencing the loss of knowledge through attrition. In order to remain competitive and also attract new talent, organizations have no other choice but to adopt the newer technologies as pertinent to data acquisition, information management and conversion to knowledge.
In order to adopt them in a benefits-driven roadmap, a structured approach to defining the use cases and desired capabilities goes a long way in ensuring the success and continued sustenance of these innovations.
The Internet of Things (IoT) has helped process manufacturing become more efficient, and new cognitive technology has the capacity to transform the value of data, whether structured or unstructured, bringing significant operational and strategic benefits. In combination, Cognitive systems will help companies realise the full potential of IoT by delivering deeper insights in near real-time. The capacity of such systems to understand, reason, learn and make prescriptive recommendations is helping the industry ‘buy time’ – a commodity more valuable than oil itself.
Visit ibm.com/chemicalspetroleum to learn more.