Generative AI in the industry


Surely you have tried or at least read about ChatGPT, Bard, Dall-e 2, Midjourney or any other.
Nowadays generative artificial intelligences (AI) allow you to create images, videos, voices, texts or generate many other answers with the database they already have "learned" plus the input data that the user provides them.any of these AI when you start using them warns you about privacy and that what you ask or the data you provide will pass to the AI's own knowledge. Sometimes it tells you in large advises and sometimes in the fine print.

Data security


Samsung among many others, has banned its employees from using artificial intelligences because of the loss of confidential data.

If the data we provide to the AI stays inside the AI, as the basis of its knowledge, connecting any industrial element or providing it with data from our plant to ask questions is as dangerous as connecting your servers or production machines to the Internet openly so that anyone can see it and copy or modify it.

It is not safe to use AI tools as they are offered to non-business users because of the risk of losing important data.

How we can use it?...


Of course we can take advantage of this new technology by doing it securely.

At OT Factory we are clear, first is the privacy of the data.

It is possible to use an AI that takes advantage of the immense knowledge database of state-of-the-art generative algorithms, along with our data in a strictly private way, with secure access so that we guarantee the confidentiality of the entire process.

From data collection to the result, all in a secure way with Edge technologies, connecting the necessary data and only those to obtain answers that a few years ago would have seemed like science fiction.

Real-life example


In a production line we capture only 7 variables during a couple of hours, just a few data, motor consumptions, revolutions, pump power consumption, compressed air pressure, final instantaneous production in Kg and operating ambient temperature in the plant.

This data is what we use as a basis for the AI to analyze and give us answers and useful information.

A few simple tests and the real answers from generative AI:

The following answers are generic tests of only a couple of hours of operation of a bottling line.

Generative algorithm response


Certainly, let's analyze the relationship between external temperature and other parameters in more detail:

1. **External Temperature and Production:** It is observed that as the external temperature increases from 20°C to 24°C, the machine's production decreases from 10 KG to 6 KG. This suggests a negative correlation between external temperature and production, which could indicate that higher temperatures may negatively impact the machine's efficiency or production quality.

2. **External Temperature and Energy Consumption:** As the external temperature rises, there is a trend towards increased motor energy consumption. This is more evident in the change from 12:00 to 12:40 when the external temperature increases from 20°C to 22°C, and motor energy consumption increases from 1 KW to 1.5 KW. This suggests that higher temperatures may require more effort from the motor to maintain machine performance.

3. **External Temperature and Anomalous Behavior at 13:25:** At 13:25, the external temperature rises to 23°C, and anomalous behavior is observed in the machine. Motor RPM decreases to 800, pump consumption increases to 7, and production also increases to 9 KG. This could indicate that the machine is trying to compensate for the higher external temperature by increasing pump flow and decreasing motor speed to maintain production.

4. **External Temperature and Subsequent Changes:** At 13:40, when the external temperature rises to 24°C, motor energy consumption increases even further to 2 KW, and pump consumption also increases. This could indicate that the machine is struggling to maintain performance in higher temperature conditions, resulting in higher energy consumption.

In summary, external temperature appears to play a significant role in the performance and energy consumption of the machine in the factory. As the temperature increases, there is a trend towards increased energy consumption and decreased production. This suggests that the machine may benefit from adjustments or modifications to better adapt to varying external temperature conditions and maintain optimal performance. Additionally, the anomalous behavior at 13:25 may indicate that the machine is trying to compensate for the effects of higher temperatures through changes in operation.

We then asked the AI to make suggestions for improvements to our line. Want to know what suggestions the AI made?