FLSmidth Technical Product Line Manager Group Digital, Javier Pigazo Merino, gives us the low-down on ECS/ProcessExpert V8.5 and the importance of AI to the future of industrial digitalisation.
Q. You are releasing the next version of your flagship advanced process control (APC) software, ECS/ProcessExpert® (PXP) V8.5. What's new?
We are introducing some exciting new cognitive technologies and functions in PXP V8.5 that contribute to the development of the Smart Factory concept in the cement and mining industries and support the drive to greater sustainability.
For example, for the first time, we’ve incorporated the capability to use non-symbolic artificial intelligence (AI) technologies based on machine learning and deep learning algorithms. These technologies create their own understanding of a process by finding patterns in the raw process data – and then use that understanding to solve problems.
Meanwhile, the new PXP DataBooks module aims to bridge the gap between automation engineers and data scientists by enabling customers’ data scientists to integrate their existing machine learning and deep learning algorithms into the PXP applications and control strategies.
And when it comes to sustainability, ECS/ProcessExpert software supports ambitions to reduce the impact of cement production and mining on the natural world by calculating the environmental benefits of using PXP and then turning them in meaningful KPIs – but more on this below!
Q. AI is becoming more commonplace in everyday life. Are you finding that customers are also demanding this functionality in their process optimisation solutions?
Yes, absolutely. AI is driving many of the technological advances today – and customers now expect to be able to take advantage of such technologies in their operations. That doesn't mean however that AI technologies have achieved a level of development and maturity to replace everything we now use to control and optimise cement and minerals processes.
Q. We are living in a world where collaborations and partnerships are paramount. How is ECS/ProcessExpert software helping with this?
There is no doubt that a collaborative environment opens the doors to create products that efficiently offer more value. With PXP V8.5, we have expanded this collaboration to include our customers. As mentioned above, PXP V8.5 comes with PXP DataBooks, a module that allows the customers’ data scientists to integrate their own machine learning or deep learning algorithms, trained and developed using their preferred platforms, into the PXP applications and control strategies. The module currently includes the capability to build Python scripts using Jupyter Notebooks, but can potentially be expanded to cover other technologies and programming languages in the future. The customer's feedback will be the main factor driving the future inclusion of other technologies and development languages.
Q. We hear a lot about machine learning, advanced analytics and AI for Smart Factory. Can you explain what these are and how they impact traditional APC?
APC systems are very often seen as one of the main drivers needed to reach the dream of autonomous operations. In this context, it’s commonly heard in the media that AI is replacing APC systems. But this wrongly assumes that AI is already a synonym for fully-autonomous operations. This kind of misrepresentation does not help, as such fully-autonomous continuous-process plants are still not that close to reality.
However, there are many examples where new technologies and workflows can heavily enhance the level of information that is gathered and analysed, transforming it into much better actionable insights, to take decisions faster than ever. This is what we call ‘intelligence augmentation’ and can clearly assist and elevate the performance of either existing APC systems or human-based control.
We truly believe that the ability to collect, centralise and analyse vast amounts of data (e.g. from logistics or sales forecasts to maintenance and operations) in real time, combined with the ability to build more accurate and reliable models of the world around us, opens up an exciting future where, step by step, we can analyse the needs and build new productivity solutions for our customers.
Q. What are the main benefits that AI offers to cement producers and mineral processors in relation to APC? Can you provide some real examples?
There are three main areas where APC can and will benefit from AI:
Cognitive augmentation. As explained before, the ability to gather, analyse and combine various data streams in real time can bring relatively quick benefits from operational and safety perspectives. One example would be building new virtual sensors to replace unreliable or unavailable signals, particularly when the instrumentation is placed in risky areas or is often out of service.
Smart controllers. In certain contexts, controllers, such as linear and non-linear MPCs or fuzzy, can be enhanced and complemented by virtual models of machinery or processes, known as digital twins. If the digital twins are done well, they can be used to find the controller’s optimum parameters, which leads to more stable processes, achieves higher production and quality levels, or decreases the amount of energy or water used.
Dynamic adaptiveness. Many industrial processes (cement and mining among them) are by nature nonlinear and time-varying: this means that actions that were optimal to achieve specific goals yesterday (or even an hour ago) may be suboptimal or even inefficient now. A clear example of this is the cement kiln, where a strong push to substitute fossil fuels with alternative fuels, in as high a ratio as possible, makes stabilisation and optimisation a challenging task, both for human and expert systems. The ability of AI technologies to continuously adapt to changing conditions to find the optimal operating parameters and targets is one of the key areas in which AI can improve the ability of APC systems to optimise cement and mining processes.
Q. How do the new technologies introduced in PXP V8.5 complement or augment existing intelligent control technologies?
The new technologies and collaboration possibilities introduced in PXP V8.5 will bring multiple options for cognitive augmentation and smart controllers. For example, we are facilitating techniques to create, train and utilise neural networks to build smart predictors, replace faulty or missing instrumentation, or forecast the future of certain signals in the form of time series. This creates the option to connect those new synthetic measurements with MPC controllers, which will thereby react earlier, preventing undesired situations from happening or sticking constantly to optimal setpoints.
Q. Whilst new technology and associated operational changes present the possibility of significant benefits, are there barriers that could limit these benefits from being realised?
Definitely. There are two main barriers to pay attention to.
Firstly, it should be noted that the new capabilities we have discussed not only involve new technologies but also bring the need for new procedures, workflows and skillsets. It is therefore important to understand that multidisciplinary views and cross-functional collaboration are more crucial than ever. Process specialists (domain experts), automation engineers and IT technicians should open their arms to and work closely with data scientists, data engineers and industrial AI experts in order to explore potential new solutions to specific process problems. This human and social aspect is commonly overlooked but, in reality, working as a strong team of people with complementary skills is a key element to success.
The second aspect relates to a concept called the ‘Hype Cycle’. Especially with emerging technologies and trends in the industrial landscape, we (very quickly) hear bold promises from marketing materials or sales presentations (sometimes inherited from other sectors where maturity levels and/or conditions are far from similar). This can make it very difficult for a non-technical audience to discern hype from what is technically viable and commercially profitable for their specific business needs.
This overinflation of expectations, combined with low resistance to failure, leads to huge doses of frustration and early dropping of the investment, even before the learnings are incorporated into a new iteration or before a good productivity level is reached.
Q. What are the benefits for customers when it comes to sustainability and how does ECS/ProcessExpert V8.5 software support the FLSmidth MissionZero strategy?
We’re now also better able to demonstrate the sustainability advantage that intelligent process control technologies, such as PXP, bring to cement and mining operations. The PXP Insights analytics module automatically converts operational benefits into meaningful environmental KPIs, for example, CO2 footprint benchmarks. These KPIs are then visualised using pre-defined dashboards that are delivered with the solution. The solution also calculates and compares the KPIs when the system was in operation versus when it wasn't. In doing so, we can clearly show how PXP enables more sustainable operations.
Q. What's next?
PXP V8.5 brings exciting new functionality and modules that will augment the intelligence of our APC solution and improve the level of support it provides to human operators. More importantly, it will promote and nurture collaboration between automation, process control engineers and data scientists.
At FLSmidth, we believe that the new digital landscape promises much. We will continue developing and adopting technologies that enable smart industrialisation using advanced analytics, deep reinforcement learning, digital twins, etc. And ECS/ProcessExpert software is at the top of our efforts. We are continuing to research and test technologies that will further improve the intelligence of our process control solutions as part of our commitment to making cement and minerals plants smarter.