Forecasting and Predicting, Must be a Cornerstone of the Modern Operational System

For the last couple of weeks Stan and I have been working with a number of leading companies in Oil and Gas, Mining, and F & B around their Operational Landscape or experience of the future.

Too often the conversations start off from a technology point, and we spend the initial couple of days trying to swing the conversation to the way in which they need to operate in the future and what their plans are around operations.

It becomes clear very quickly that there is allot of good intent, but real thought into how they need to operate in order to meet production expectations both in products and margin has not been worked through.

Over and over again we see the need for faster decisions, in a changing agile world, and this requires an "understanding of the future" this maybe only 1/2 hour. The time span of future required for decisions depends on role, (same as history) but it is clear that modeling of future is not just something for the planner, it is will become a native part of all operational systems.

This blog from Stan captures some of the necessary concepts.

  

Operations management systems must deliver better orientation than traditional reporting or decision support systems.  One important aspect of operations is the dynamic nature – there will be a journey of changing schedules, changing raw material capabilities, changing product requirements and changing equipment or process capabilities.

It might be helpful to consider desired and undesired conditions, using the analogy of driving a car on a long trip.  The planned route has turns, and it may involve traffic jams, detours, poor visibility due to heavy rain or fog; the driver and the car must stop periodically; and the driver may receive a telephone call to modify the route.  The following diagram is a sketch which displays how an integrated view might appear:

In the above example, the actual performance is at the upper limit for the target, and the scheduled target and constraints will shift upward in the near future.  The constraint is currently much higher than the scheduled target limits, but it is forecast-ed to change so that in some conditions in the future, the constraint will not allow some ranges of targets and limits.  This simple view shows a single operations measure with its associated constraints and target.

• At this stage, we propose a definition of “forecasting”: a future trend which is a series of pairs of information, where the pairs include a value and a time.  The accuracy of the values will be poorer as the time increases, but the direction of the trend (trending down or up, or cycling) and the values in the near future are sufficiently useful.
• In contrast, “predicting” is an estimate that a recognized event will likely happen in the future, but the timing is uncertain.  This is useful for understanding “imminent” failures.

The following diagram shows an example of estimating the probabilities of 5 failure categories, where the first (rotor thermal expansion) is the most likely.

Given these two definitions, it is helpful to consider industrial equipment behaviors.

• Several types of equipment, especially fixed equipment such as heat exchangers, chillers, fired heaters etc. exhibit a gradual reduction in efficiency or capacity, or exhibit varying capability depending upon ambient temperature and the temperature of the heat transfer fluid (e.g. steam, hot oil, chilled water).  While the performance is changing, the equipment hasn’t failed, although its performance might reach a level which justifies an overhaul.  In extreme cases, sudden failures can occur, such as tube rupture or complete blockage.  These benefit from “forecasting”.
• Other types of equipment, such as agitators, pumps, turbines, compressors etc. exhibit sudden failures.  These benefit from “predicting”.

One analogy of incorporating both “forecasting” and “predicting” is that it is like driving a car without looking forward through the windshield/windscreen, such as shown in the following sketch:

In the above sketch, the road behind the car is clear, but ahead, a potential collision will occur.  High-performance operations requires that teams prevent unplanned shutdowns or other events.

Convergence on Wisdom (applied Knowledge), and Industrial Analytics / Operation Intelligence grow in importance!!!

It seems like a while I have been talking about Operational Intelligence/ Industrial Analystics, and then the movment to Wisdom (Applied Knowledge) all as separate threads but I was asked the question last week:

 “how do they relate?” .

They are different, but all related to empowerment of operational workforce to make faster decisions, and take actions. As I pointed out last week one of the big drivers to platforms is to manage varience. We talk Supervisory, MES, Information, Simulation platforms, but as we pointed out must a “People Platform” that covers:

·         Collaboration between people

·         Supports the hosting of “Activities” with their embedded information/ knowledge and their associated actions.

·         Transformation of Information to Situation ally aware for the particular user interested/ interacting.

·         Management of Operational Work between team members

·         Notifications

·         Plus more

This will abstract the turnover of the workforce, abstracting the different skill levels, and experience levels, with embedded “Applied Knowledge (Wisdom),  so the experience is now in the system. A key concept for the this upcoming Operational Transformation.

Industrial Analytics provides the shift from the past through the present and into the future based on high fidelity models(from experience). Providing a new dimension to the workers tools, and thru the decision they are about to make. Combining the “Future”    providing answers to “what will happen!!!” with the recommended actions to take.

Providing the answer to “What should I do Next?” with experience, fore thought, and understanding. Operation Intelligence also aligns with this by providing a screens, presentation of the situation or “ know Questions” with context and awareness.

Operational Intelligence providing the worker an understanding of “Now” , where he is, and what the future holds, simple and clear. Increasingly I am being asked for this type of “Operational window” and view; it is not analysis it practical information around my current situation and immediate future. No configuration just a simple view of task or question provides the view and clear awareness, providing an answer.

Are these different experiences, No, they are all functional value expansions on each other, and should seen as building blocks in the road to providing and Operational Execution knowledge platform, with built in experience. Providing a foundation for absorbing turnover, transition in the workforce while maintaining operational consistency and efficiency.   

Dynamic Simulation needs to become a Natural Feature of the Industrial Operational Landscape

To empower operational teams, workforce, each role must understand the context of the future, as well as current state and history. In the traditional industrial solutions, the worker is provided with tools for understanding history and NOW. This is the same as driving a car by only looking at the dashboard of the car, and rear vision mirror. Can you drive the car without looking out 100 meters or longer into the future the answer is NO, you would miss judging the next corner?

So why do we think we can run plants in this same manner?

The leading companies are defining the operational experience of empowering the different roles in the plant operations with the ability to “understand the future”. This will then empower the user with:

·         Understanding of the NOW situation

·         Understand the History

·         An expectation of the future based on NOW situation

·         Access to Experience

The concept or words used to describe this capability is “What If” capability. The ability to have at the finger tips of the worker the ability to ask “what if” question and the system will provide the best estimate based upon the current state of the process/ plant, and history. This provides maybe a “times 10” in time look forward so that it provides another reference point for the worker to base their decision on.

An example of how the general day to day market has come to accept using simulation models as day to day is in the weather. I do a lot of ocean sailing; today a natural tool I use on the boat is weather simulation. On my Ipad,  I have two applications, which connect to a cloud application that will allow me to select a location, and run a number of weather simulation models, based upon the current condition. There are a few models with different characteristics that I use to 2 to 3 models and compare feedback, combine this with reading the weather maps, and do a “gut validation”. It is this future, plus my experience from the weather map reading plus applying local conditions such as mountains that allows me to gather enough information to make decisions on what to do. This effects safety, comfort etc, there were examples of friends on other boats that just listened to general weather broadcast especially in remote places, and they made decisions based on this, but these forecasts were over 1000s of miles and extremely general, and open for interpretation as they were line item. In the same situation,  I ran the models; play off scenarios “what if” based upon local navigation, mountains, and my boat. On at least 3 occasions,  these friends left and where caught with young families in life threatening situations. This is decidedly different to when I was a teenager sailing the Australian coast, where we only had the weather maps, and a number of peoples opinions, we got caught a couple of times in particularly severe weather especially 5 hours out. Today I am able to use the models to look 7 days into the future for a trend, and greater accuracy at 12 and 24 hours. Today these models are a natural part of my navigation tools, having on board capability to download the results of the model, and then tools to ask questions based upon routes I want to go, easy to interpret graphic experiences to see results. (As seen below the weather is overlayed on the charts and uses colors to show intensity, I can work through time forward 5 days by hour).

It is easy to receive model results even at sea by sending an email of current locations, areas I am interested by a text email and the results come back in a data file that I load into my local system with my boat parameters, navigation charts, and I can now easily see graphically the results layered on the navigation charts and ask questions, because of this simplicity to use I now use this many times a day to make and validate decisions.

So why, not on the plant? No matter the role, it could be maintenance, performance engineer, safety, operations, where decisions are having to be made, and experience varies, the ability to get these reference points is key.

This must use high fidelity simulation models to predict the future, but the capability of adding this to a solution must be small. Traditionally simulation systems have been offline, and large after thoughts, especially outside of the oil and gas industry. “Why cannot we just add this future capability similar to adding alarm or historic capability to a device supervisory control?”. The answer should be yes. This will require smaller foot print simulation, dynamic and libraries of simulation models for different devices/ processes etc. Again in the oil and gas world this has been done for years, and companies such as Exxon and others have built libraries of optimization, and simulation capability. All industries require this no matter the complexity, but to achieve reality it must be easy (a natural act) and rich this library of simulation models must be rich, and easy to apply, plus domain experts must be able to develop these models easily, these could be device / process vendors, domain experts, and companies. With the models naturally able to be applied to the automation/ operational platform as just another function.

Yes, dynamic simulation is one of fastest growing aspects of Industrial Operational Systems, as we design systems we must assume that this capability should be included.