Introduction

It all started last year during the COVID pandemic. We did some brainstorming in our team and dug through 10 years of our implementations at factories, and we contrasted it all with the capabilities of the cloud technology which we use as the base of our LogiX platform. LogiX- which we’ve been developing since 2018 - is a solution for monitoring the production processes at factories and increasing their efficiency.

That’s how we came up with the concept of extending the platform with intelligent recommendations about the ongoing production process and the condition of machines that are used in it. The recommendations are meant to minimize unplanned downtimes and increase the number of manufactured goods, minimizing at the same time the energy consumption and making sure that people involved in the production process are working in a hospitable environment.

We want LogiX to help factories become eco-factories that do not waste energy by idle work, but instead, we want them to work with maximum effectiveness. It means that every unit produced has lower energy cost while people receive recommendations given “on a plate” which allows them to focus on their tasks rather than on looking for solutions to typical problems.

Open

We want the implementation process of such a platform with such intelligence and a self-learned recommendation system to be very simple for the end-user. Our goal was that the users would simply connect their machines to our platform and immediately start benefiting from the self-learning system without the time-consuming creation of rules, algorithms, or predictive models.

We kept on talking to large companies who were involved in big projects related to predictive maintenance. For example, one of those companies was in the airline industry, and their project was concerned with detecting possible engine failures when airplanes were parked in hangars. It meant collecting hundreds of measuring points together with hundreds of thousands of measurements - and a short time frame for making a go/no-go decision. Those projects were always huge and expensive, and when they were brought over to the manufacturing industry, they simply didn’t defend themselves financially.

We came to the conclusion that what was key was building a library of machines, types of machines, and types of production processes. Next, we had to catalog it all and create failure prevention models. Then you could connect such ready models to the definitions of machines in the library, and, what is vital here, generalize them to a specific class of machines, not only to a single machine in the library. We approached the rules for detecting bottlenecks in the production process in a similar way: by cataloging them in the library of processes (for example, the packing process or the number of machines are connected on the production line).

Open

Ready-made Solutions That Can Be Used at Your Factory

Using such a ready-made model, you could receive recommendations as to when you should replace the chain on your bicycle because otherwise, the chain may break or the level of wear may negatively impact the cogs in the drivetrain. You could also receive suggestions on how to use your bike to make it last longer without needing to service it so often. Without actually measuring the level of wear (by measuring, for example, the size of the links in the chain), but estimating it based on the wear model (failure prediction).

Our goals

We want to be able to:

• Determine the aging functions of machines and their elements (the health factor) so that any servicing can be planned for the time after the wear warning point has been reached (as it may impact the quality of products). The aging functions will also show how to use such a machine to increase failure-free work between servicing sessions which will be done in optimal time, that is, not too early (as it increases servicing costs) and not too late (as you risk unplanned downtimes).

• Establish failure prediction models based on anomaly detection in the process parameters (process time, energy consumption, temperature) in order to warn the user that there is a possibility of failure.

• Establish simulation models in order to provide the user with suggestions to adjust parameters when atypical problems arise (for example, problems with the speed with which fillers are moved up and bottles positioned in fillers: if it's done too fast, foam starts flowing out of bottles which overfloods transporters and the bottles that are coming next are not positioned the way they should be).

• Define what data we collect for a specific machine or class of machines.

• Define what states we use to describe a machine from the monitoring viewpoint.

This all is completed with a supporting vision system that is set to automatically recognize problems (for example, it notices when bottles get knocked over and, because of this, they start blocking the transporter).

All those features, once defined, set, and linked to a machine definition in the machine library, are readily available for you to use on the LogiX platform to which you connect your factory.

We are doing it all so that you, our Dear Client, could easily connect your factory to LogiX and use a self-learned system and benefit from the recommendations it provides. It's as easy as using a car navigation system: you simply enter the destination and follow the directions (“turn left”, “turn right” and so on). At a factory, those directions will be recommendations on what you should do to manufacture goods in the most efficient way which means avoiding unplanned downtimes, optimally planning servicing sessions, and reducing energy consumption. Those suggestions are so trustworthy that it’s enough for operators and shift foremen to follow them and “drive” the optimal route.

It's done without frantic clicking from screen to screen, digging in piles of reports, or looking for some kind of a clue.

Quick and Easy Configuration

It will take you 10 minutes to configure a ready-to-use monitoring system with anomaly detection and failure prediction - a system that can also recognize hidden causes of downtimes on your production lines.

• Without data scientists.

• Without months of collecting data.

• Without model learning.

Just sit back, fire up LogiX and log in to it just as you log in to your email account, open the digital version of your factory, and drag a machine from the machine library, for example, a Unilogo Futureproof 120. You can’t find it in the library? No problem! Simply select an appropriate machine category.

Then drag your production process, for example, packaging, and you will get a complete chain of connected machines: a filler connected to a capper, a cap sorter to a capper, a capper to a labeler, and so on.

Your Factory’s Digital Twin is ready to work and support you in your decisions by giving you intelligent recommendations.

All this in no more than 10 minutes and with the full potential of AI that we had built into the digital twins of your machines and processes in our library.

The suggestions that we will generate for you will include warning you about specific failures, changes in machine setpoints, finding connections between human actions and problems with machines, determining non-obvious causes of problems (for example, problems resulting from servicing sessions in the past), and automatically finding root causes based on the graph of interconnected machines.

Some examples of recommendations that you may get:

• Replace the capper element that holds caps because, based on the time of the process, we detected that it must be seriously worn.

• We have noticed that this week, John has been handling this type of failure, on average, 8 minutes longer than others. Maybe he is overworked? Maybe he needs some training?

• We have noticed that you have been experiencing downtimes due to the several failures of a lid press that occurred after John had serviced the machine. Perhaps you could offer John an additional training session?

• If you reduce the speed with which fillers are lifted, you will avoid downtimes resulting from the foam overflowing the transporter.

• If you lower the temperature during the mixing of cosmetic mass by 10 degrees, you will save up to 10% of energy while retaining the same quality of your products.

• The manufacturing order on Production Line 1 will be finished in 6 hours and 30 minutes. We have calculated the time based on the historical data from the past 6 months related to the manufacturing of such products.

• Once again, you are experiencing a problem with cartons for the case packer from one of your suppliers. Talk to them, because you are losing 50% of your productivity because o this.

• Reduce the operational speed of one of the robots by 5%. This will lower the number of incidental holdups by 20%.

• The supporting vision system has notified us that many problems related to the transporting machine blockages result from bottles being knocked over because they are not held in a stable position.

With our project defined the way we showed you above, we went to The National Centre for Research and Development (NCBR) and we were granted 2 million EUR in funding. We simply fascinated the NCBR experts with our project.

However, to develop it, we are in need of partners:

• Factories manufacturing machines because they can help us define their machines in our library (that's how we've been collaborating with Unilogo, for example).

• Factories manufacturing goods because we need to catalog manufacturing processes, identify bottlenecks, and establish rules of recognizing them and warning about them. We also need to prepare definitions of machines in our library and try them out in action.

Thinking of becoming a LogiX partner? Drop us a line at SLF@ilabo.com

How does the partner program work?

• We will connect your machines to LogiX which is our execution platform.

• Together, we will decide which of those interconnected machines should be included in the project and in the partner program.

• This is what we will be figuring out:

  • Prediction models

  • Anomaly detection

  • Algorithms that evaluate the health of machines

  • Determining hidden root causes

We will provide all this for your LogiX instance and for your machines for free, however, we reserve the right to generalize the results and include them in our library (of course, the data will be collected anonymously which we guarantee in the partner agreement).