Hello all. I'm David Paige, I'm the Digital Champions of the Global Business Units of Soda Ash & Derivatives at Solvay . Together with me, we have Carlos Perez, who is Industrial Data Scientist at Solvay at corporate levels, who will be co- presenter of this presentations.
This presentations is about the scaling up of the use of machine learning techniques in the chemical process and concretely at Solvay. Here in this slides, we have the agenda of this presentations. First of all, I will share with you a briefs introduction of our multinational company, Solvay.Q hen some words also about our general business units, Soda Ash & Derivatives.
Then here in the point number three, we will enter in discussion about how machine learning techniques helps improve our production process. Then we will go a little beet deeper about the usage of JMP in our GBU. I will explain to you the awareness sessions and the training that we provided to our population of engineers. A lso, we will see a couple of practical use cases.
Then my colleague Carlos will share with you one add- in that they developed internally at corporate levels at Solvay, which is very useful for us, for the final users to connect to our play source of data, which is the MES, manufacturing execution systems.Finally, I will share with you the play challenges that we faced during this journey and also the lessons learned.
Briefs introduction of our groups, Solvay. We are a science company founded in 1863 whose technologies bring benefits to many aspects of daily life. Our innovative solutions contribute to a safer, cleaner, and more sustainable product found in homes, food, and consumer goods, planes, cars, batteries, smart devices, health care applications, and water and water purification systems.
Very important, our groups sess to create sustainable shared value for all. Notably, through its Solvay One Planets program, we have three pillars: protecting the climate, preserving natural resources, and fostering better life.
Here at the bottom of the slides, you can see some key figures of the groups in 2021. US you can see, we have a little beet more of 21,000 employees all over the world. We have presence in 63 countries and we have 98 industrial manufacturing sites.
Now, if we jump to our general business units of Soda Ash & Derivatives, which is the business units that I work for, coordinating the implementation of what we call the digital transformation initiatives. US you can see, we have 11 production sites distributed around the world.We have six production sites here in Europe, but also we have two production sites in North America and one production site in Asia out of other locations around the world like warehousing and buildings.
Also, we have three R&I centers located in Brussels, in Dombasle, which is our manufacturing site in France, and in Torrelavega in the north of Spain. Globally, we are 3,200 employees all over the world.
Our products. These are the two play products that we produce in our general business units. We produce soda ash and we produce sodium bicarbonate. The soda ash is mainly used for the glass manufacturing production, different types of glass for building, but also for photovoltaics panels or for containers, US you can see here, the example of the bottles.
Also, soda ash is used to produce detergents and very important and very new with the making of the [inaudible 00:04:44] of electrification that we are seeing around the world. Soda Ash is also used for the production of helium for the batteries.
Bicarbonate. Our sodium bicarbonate, it's used for different markets. First one, for the exhaust gas industry cleaning, which is our SOLVAir markets. A lso a very new applications for the same purpose, gas cleaning, but for the ships.The sodium bicarbonate, it's also used for the pharmaceutical industry and for the food industry.
In this slides, I would like just to shows you about the complexity of our production processes to manufacturing our final products. US we said, our final products can be soda ash, light or dense, and also the refined bicarbonate.
To produce them, we need to consume different raw materials such US the limestone, the brine, and also we use the coke and anthracite in our lime fields.US you can see, the the production process is quite complex because we are using different assets like the absorbers, like distillation in the distillation sectors, dissolvers , precipitation columns, filters, compressors.
We have a long variety of assets used in the manufacturing process and very complex chemical reactions, mixing gasses, liquids, solids. We need to take into accounts thousands of parameters in terms of temperature, pressure, flows, and so on.It's very important the use of advanced analytics and machine learning techniques in orders to improve this production process.
Here we are entering in the chapters for how machine learning can help to improve our production process. First of all, to share with you our strategy.Clearly, in the soda ash and bicarbonate, our strategy is to be competitive and keep our leadership worldwide position in this global commodities markets, which is soda Ash, but also in the premium markets US the buyers.
What is our objectives to reach this ambition in our strategy? Our objectives is to reduce US much US possible the variables and fixed cost in our manufacturing sites while ensuring the overalls equipment efficiencies, so the OEE, and the quality of our products.
Let me put some examples of how we can impact in our variables cost and fixed cost. In the variables cost side, clearly, clearly one of the levers that we can improve is the yield. If we are capable to increase our sodium precipitation yield in our carbonation sectors, clearly what we are going to do is to reduce the need of raw material and energy in our production process to produce the same quantity of soda ash.
The same for the topics related with energy efficiency. In the previous slides, I showed you the complexity of the production process and the energy that we need to use in the different sectors such US the distillation sectors, calcination sectors, or lime kilns.If we are capable to improve the play parameters on these sectors, we will be capable to reduce the specific consumption of energy in our production process.
In terms of fixed costs, one of our play fixed cost in our production process is the maintenance cost. We have unplanned events, unplanned mechanical breakdowns in our industrial assets, and also we perform regular maintenance activity and cleaning of our assets.If with these machine learning techniques we are capable to anticipate, to predict these unplanned events, we could also potentially reduce our fixed costs.
Our idea, our ambition is to combine the deep expertise that our process and controls engineers have on the domain, the soda ash production process, together with the I.T and computers science skills and math and statistics skills. This is our ambition.
Traditional method. Traditionally, what our engineers is doing is to use the inputs of our process using a theoretical model. For example, the thermodynamics or the chemistry in orders to understand the process and to get an output.This is the traditional method. But now with the machine learning techniques, what we can benefits for is about the historical data.
In our site, US I explained before in this very complex environment of the production of soda Ash, we store thousands of different sensors data in our MES systems, in the manufacturing execution systems.Data from temperature, flows, pressure in different parts of the process. We have this historical of data, so we can provide with the machine learning algorithms, inputs and outputs of our process. Creating machine learning, big data models that could help us to improve our process and to understand better our process for the future inputs.
Now, here in this slides, just to share some publications, also from Dow, another important multinational chemical company, that is sharing with us here that a chemical company must invest to create a critical mass of chemical engineers with technical skills in statistics, mathematics, modelling, optimization, process control, visualization, simulation, and programming.
But it's much easier to trains chemical engineers on data analytics topics, Rather than to trains data scientists on chemical engineering topics. We completely agree on this statements, and this is what we want to do at Solvay.
We have a lots of very skilled chemical engineers, and we want to trains them with this advanced analytics techniques. Q his is the play reason why we launched the program of Machine Learning Techniques with JMP in our GBU, our Global Business Units.
It was a program that started in 2021. The target population of this program was 47 engineers in our GBU.I t was led by the industrial data science team at corporate levels.
What was the content of this program? We had one- hour sessions, first of all, one day, where we explained why we want to use the machine learning techniques with JMP in orders to improve our production processes, US I explained you before.
Then during seven days, we made an individual on line course for each of the 47 engineers related to a statistical thinking parts. It was just an introduction of a statistical thinking methodology. Then we enter it on the JMP introduction parts, explained the tools, explained the play features, the benefits of using JMP, and the play tips to start creating some graphics, some statistical reports, and some basic things.We combine theoretical lessons with practical exercises and planarizations of the web.
Then during 15 days, we enter it in more details about what we can do related with machine learning techniques, which we did the same individual on line course and also practical exercises and plenary sessions.
All of this program training lastly, let's say, around one month. But then the most important parts was the selection of the real cases to resolve in the different manufacturing sites for the different participants of the training.We made this selection and we provide a license of JMP, of course, and a regular support with weekly, linear meetings and individual coaching.
Let me put two examples of practical use cases about this selection that we did afterwards this training sessions. The first one is about increasing the sodium precipitation yield in the production processes of Rheinberg, our manufacturing site in Germany, and Torrelavega, our site in Spain.
How we use the JMP on this projects? First of all, to screens the multiple variables that we think that can impact our play target variables, which is the sodium precipitation yield, in orders to explain the variability of this target.
The goal was to investigate what are the variables that can explain better the variability of our target. For this, we use one of the tools that we're learning during this one month course, which is the predictor screens.
This is very important, because, US I explained to you before, we have hundreds of variables impacting this output, which is the yield in the process, s o it's very difficult to analyze one by one. This tools allow us to, in a very quick way, in a very fast way and intuitive way, to understand what are the play contributors explained the variability that we have in our tools.
Also, we need to Say that JMP is a very intuitive and code- free advanced analytics tools, and this is very important because the production engineers, note all of them have the knowledge to use these programming code tools.Also, important to Say that to visualize the long- term variability of the target, but also its relationships between the most important variables is a very important features that JMP has.
Finally, also, we use JMP to elaborate the statistical reports about the performance of the different approaches, different trials that we perform along the projects.This is the first example where we use JMP in orders to understand better our process and improve our yield in both of our management designs.
Second one, in this case, we are talking about finding the root causes for the variability of one important parameter of the final products, which is the carbonate content in the sodium bicarbonate.
Here we use JMP similarly, like in the projects that I explained before, we screens the multiple variables and select the most important ones to explain the variability of this target. For this, of course, we use to use it again, the predictor is giving input, US you can see here in the right- hand side of the slides.
Also here, it was very, very important, the visualization in a graphical way, the interaction of the play variables that we identified thanks to the predictor screening. You need to understand that on this type of projects, we need to collaborate with different stakeholders. The production engineers cannot resolve this type of very complex projects alone.
Here we need to align and speak and generate debates with the production operators on the fields, with production operators in the controls room, with site managers, other engineers in other plans, experts at corporate levels, and so on.It's very important to translate what we analyzed in analytical way, in a graphical way to make and generate these debates.
Finally, also very important to help on the decision- making process in orders to, at the end, of course, taking decision on these play variables that we demonstrated in an objectives way to the people that at the end decides to make a modification in the process to take these decisions.
This is what we have done also in this projects. At the end, it's about make a modification, make a small investment to modify a parts of our installation in orders to reduce the variability of this carbon content of the final product.
That's it all for my side for the moments. Now, I will give the floors to my colleagues, Carlos, data scientists at the corporate levels, who will explain to you an add- in that we developed internally at Solvay that allow us to connect the data from our MES, which is the player, US I explained before, where we store all the data into JMP.
Thanks you, David. I will go ahead and share my screens.Can you all see?
Yes.
OK, I want to get started.Do you see this ribbons or it's only me?
Yes, it's visible .
Yes, thank you you, David. In this sections of the presentations, I will shows you one tools, one add- in to demonstrate, an open source add-ins that we have created in the team of industrial data scientists at corporate levels in Solvay.Q his is a team that supports all of the global business units. That's it means that we have to provide for solutions for all of the different MES that exists in Solvay.
We did the automation of this tasks because we saw the situation that was happening before where we had to downloads the data in a spreadsheets sometimes without a lots of advanced capabilities. Then we had to import this data, treat it, and then finally be capable to use it without...
Sometimes it was note even clearly identified because it was only the name of the sensors, but sometimes the name of the sensors is note very clear, because it's note very well standardized, the notation.
To leverage the power of data, we say, "Okay, let's make the process of extracting the data US automated US possible so that all the process engineers can use it." We have leveraged this power in JMP, in GBU soda Ash, and also in other GBUs with an add-ins that is capable to connect to the two most common data bases in Solvay that are the MES historians, IP21 and PI from Aztecs and from AVEVA, respectively.
This add-ins connects directly to the databases if we are in the local networks and is capable to fetch with a query whatever information is saved there. We have automated the tasks of connecting to the servers, selecting the query parameter, downloading the sensors data table in a regular format with the description and units. A lso, we have integrated other functions.
It's also worth it mentioning that in this case, we are dealing with a lots of sites. The sites of soda a sh are among these, of course, where we use, US I mentioned, two play databases for MES historian, and where this is more or less the range of sensors that we have to take into accounts.
This is how it looks today the add-ins which is available from the menu add-ins. It was developed from an application menu, and it has also some scripts on the background.I will shows a clear demo with this, so bear with me.
It's a focused on process engineers. US I mentioned, it integrates a description and engineering units, which is very useful for identifying what data you are using in your analysis.
A t the end of the day you get two data tables. One of them, so what I see, what you have with typical statistics, and the other one, which is a time series with all the details of every sensors according to your extraction.But above that, the functions that I mentioned.
I will go out of this scripts to be capable to shows you the demo of this tools. Just bear with me. This is JMP, US you know it. Here we have an add-ins that when it is connected to the databases, you are capable to see all the lists of servers here in the lists.
It is connected to a servers lists that is maintained by another team, which is an I.T team. In this servers lists, it is also possible to modify the details in cases one of the servers is note available. For example, one can put the IP address and domain here to add a new servers that is connected to the internal networks of Solvay.
After that, after selecting your servers, the next steps is to go ahead and filter your sensors by name or description. This is important because US we mentioned, we have in the orders of thousands of sensors, which means that if you are going to go ahead and try to see everything that is available, it might take a long time or the servers might crashes.
For that reason, we have this filter so that you can see what's relevant to you in cases you want to see flow sensors, temperature sensors, pressure sensors, or you want to looks the three sensors by description or both.
After you are done with this filter, what you need to do is select the relevant tags from this other lists which are given in the presentations, just an example. But in this cases, I'm note connected to a local network, but you can see an example here.
You will see here all the lists of available sensors, and what you need to do is to add them to right -hand side, which is in this way. The right- hand side lists means that these sensors are ready to be extracted for you. Now what you need to choose is the start time and end time for your extraction.
You select that, it perhaps is one day, one month, one years, I don't know. Then you have to choose what type of method you want. The most common is interpolated because it means that you will have evenly spaced data by minutes, by second, by hour or by day.Also, we offers an aggregation that is in this cases is the average. A lso, we offers to extract the actual data US it was recorded by the sensors.
One more thing, if for some reasons you already know the lists of sensors that you want to downloads, and you don't want to browse by name or description, you can directly paste also this lists from a CSV format that you have available.
When you have all these parameters ready, what you have to do is heat from extraction. Q his will take the time it takes the SQL query to go to IP 21 or PI. W hen it finishes, you will get two tables with what I mentioned before.One with summary, which will allow you to understand the typical statistics values for each sensors, row by row.
In this case, you have the name of the sensors, description units, and also the mean, standards deviation, max, mean range of the sensors. In this way, you can understand if the sensors is perhaps note working or something odd is going on so that you don't need to extract.
Furthermore, you will also get the time series data, which in this cases looks like this. You get a columns with the time stamps, then also one columns by sensors with the proper format. For example, this is a continuous amount, this is a discrete amount, and everything is properly formatted.On top of that, you get the description of the sensors US I mentioned, and the units, which is very useful for processing units.This allows you already to apply all the methods from JMP.
Here you have an automated version of the add-ins that allows you to extract data directly to JMP. It's also open source, so if you are interested in contributed, you can go to the community in JMP or in GitHub and contribute your own developments.
On top of that, we also offer three functionalities, which are the updates table. The updates table will make sure that when you are done extracting your data and you perform one analysis, you can keep updating the same analysis the next day.
For example, let's say, yesterday I downloaded this data and I created one columns for calculating some value. L et's Say that today I want to also see how this calculated value is. That's it means I just have to hits this button and this data will be updated with the newest data from yesterday to today.
Also, we offers a refresh functionality in which it's meant to work US some dashboards. This means that it will fixed time windows and you will be capable to see your analysis with respect to the current time.That's it means that if I perform an analysis yesterday and I have a new columns with a new formulas, I can hits this button and only see the relevant data table for the actual period for getting the past.
That's it means that US I said, some fixed windows is fixed, and then you can see the same analysis with the current time instead of with the old time. One of them will only see one time windows and the other one will updates the full time windows.
Furthermore, you also have the add new tags, which means that for some reason you forgot to add a tags and you are remembering that it's very important, you can add a new functionality.
With all this said, I will go to the next slides. That's it means that by this point you have already a nice data table in JMP, which with all these functionalities that we mentioned, updates tables, refresh table and add new tags.This allows you already to use the typical methods for advanced analytics in JMP. For example, this one I am showing here both the JMP and JMP Pro version, but this is up to you.
We also empower the user to use another add-ins that we also developed that is called Predictors Explainer, which will be presented in another Discovery talk. We also have other types of analysis.This will allow us to perform the typical tasks in data analytics, which could be root cause analysis, anomaly detection, process optimization, and others.
With this, I will let David to conclude on the presentations.
Yes, thank you you very much, Carlos. I don't know if you are seeing now my screens. If you stop sharing, maybe.
Yes, stop sharing .
Okay. Good. Let me reshare the screens.
Yeah.
Okay. Could you see now my screens?
Yeah.
Perfect. Thanks, Carlos. Thanks for your support that you provided to our GBU, note only developing this add-ins, but also coaching our production process engineers on JMP, too .
Last slides to share with you what are the play challenges that we faced during this journey of scaling up the usage of JMP in our GBU, and also the lessons learned and the next steps.
Today, let's say, that around 20 % of the target population that two years ago we started with this program, is continue using JMP today in a routine base. The play blocking points that we found are, of course, resistance of change. Some people are more comfortable using another tools like Minitab or only Excel files. In any projects or initiative that requires a change in a tools, there is always this resistance of change that requires time and efforts to change.
But another reason is also the lack of time. Lack of time that is linked also to priorities.The priorities of the roles of production and process engineers is note always completely oriented on process optimization only, because sometimes there are too much reporting to do and other topics to covers in their roles.
The play points to keep during this process are this type of awareness that we did with the practical industry success for example. This is very, very important. In orders to convince the people and to shows the value to use machine learning techniques to improve our process and to reach this competitive levels that we want US a company, US a business, we need to use these practical industry successful, for examples.
Because this is related with a population of chemical engineers that they will note understand if we start to talk about different examples in marketing, in finance, to improve all of these other areas with which we need to shows them clear and concrete examples related to process industry.
Then also an important point about the importance of this predictor screening tools US a kits tools for us for the variability sourcing. The play problem that we have, US I explained it before, is the variability that we have is certain parameters of our process that we need to reduce.
If we are capable to reduce this variability of the key parameters, we are going to really reduce our variables and fixed cost in our production manufacturing sites.This tools is very important for our production engineers to find the root causes of this variability and act on them.
Also an important thing is this combination that we did between planarization, so all together sharing thoughts and experiences, but also with individual practice. P rovide time to the people to practice by their own and then exchange in a common call.
Finally, the points that we identified to reinforce and to implement in the near future are, first of all, of course, in orders to tackles this problem of resistance of change, we need to convince the site management about the importance of analytics for the production and process engineers.We need to launch a series of awareness sessions dedicated for them.This is in the items we are going to do a lots of long this years.
Also very important for us, we identified this strong individual coaching for the production and process engineers when they start to use JMP in the real cases, in the real projects. Because JMP requires time, the different tools US per the tools screening and other tools requires time.It's very important for the very first projects that one engineer developed using JMP to have a good coach, a good trainer to have a company during the process.
That's it all from our side. Thanks a lots for your attention. If you have any questions for me or for Carlos, we are available. Thanks a lots.
