The expert spoke about the "breakthrough" in the field of industrial safety thanks to AI

Artezio Business Development Director (part of LANIT Group of Companies) Denis Kharchenko assessed the impact of AI on production safety in a conversation with Izvestia. According to him, modern algorithms check compliance with safety regulations and can work in places where people are not able to be, for example, in workshops with high temperatures.

Over the abyss of lies: neural networks began to give fake answers more often

The share of erroneous statements from AI has increased from 18 to 35 over the past year.%

Such systems are capable of recording up to 350 critical events in one shift. This includes the appearance of an outsider in a protected area, a violation of the regime of wearing overalls, and an attempt to enter or fall of a person. Moreover, AI can predict dangerous situations before they occur.

"Let's take a concrete example. The system may notice that the employee has started moving more slowly than usual, stops more often, and that his posture has changed. For a human observer, these are imperceptible changes, but the algorithm already understands that the employee may be tired or unwell, which means that the risk of error increases dramatically," he said.

The system may recommend an additional break or a change of tasks before fatigue leads to injury and other serious consequences, the expert notes.

In his opinion, a "real breakthrough" can be expected in the security sector in the next 2-3 years. AI systems will become multimodal — they will analyze not only video and images, but also sound, vibrations, and temperature maps.

"Imagine: the system hears the uncharacteristic sound of the machine and compares it with the micro-movements of the operator, realizes that the equipment is working hard, and warns of the need for maintenance before failure. This is the next level of predictive security," says Denis Kharchenko.

Earlier it became known that Russian scientists have created a highly accurate program based on artificial intelligence, which identifies actions that can lead to industrial accidents.

Read more about how neural networks in Russia monitor industrial safety in the Izvestia article:

Factory settings: neural networks will start monitoring safety in production facilities