According to a recent study, unplanned downtime costs the industry an estimated US$50 billion annually. Kaspersky Machine Learning for Anomaly Detection helps to identify deviations in production processes at an early stage and thus reduce downtimes. Kaspersky MLAD is one of the TOP products of 2022 for security. Kaspersky MLAD took 3rd place in the "Safety and Security" category in the Computer & Automation Magazine readers' poll.
The solution is equipped with machine learning algorithms that analyze telemetry from machine sensors in real time. As soon as the parameters of the manufacturing process (tags) behave unexpectedly, warnings are triggered. The innovative approach was also recently confirmed by a US patent.
Discover anomalies through machine learning
The solution is equipped with machine learning algorithms that analyze telemetry from machine sensors. It warns of machine failures by triggering alerts when manufacturing process parameters (tags) behave unexpectedly. Kaspersky Machine Learning for Anomaly Detection also provides a feature-rich visual interface for detailed anomaly analysis and tools to integrate the product with existing systems to send alerts to users' dashboards.
A smooth process is essential in industrial environments; Equipment malfunctions, operating errors or cyber attacks on industrial control systems must be avoided. However, if the worst comes to the worst, early detection can help reduce the cost of downtime, waste of raw materials, and the effects of other serious consequences. Kaspersky estimates that reducing downtime by 50 percent can save up to $ 1 million annually for a large power plant or $ 2,5 million for an oil refinery.
Downtime costs billions of dollars
Kaspersky Machine Learning for Anomaly Detection neural network analyzes in real time the telemetry of various sensors used in the production process. The solution detects even minor anomalies, such as a change in signal dynamics or signal correlations, and notifies users before they reach their limits and affect performance. This enables plant operators to take preventive measures. In order to be able to detect anomalies, the neural network learns the normal behavior of the machine from historical telemetry data.
Should a parameter of the production process change, for example because a new type of raw material is introduced or a part of the machine is replaced, an operator can run the machine learning training again to update the neural network. In addition to a machine learning based detector, custom diagnostic rules can also be added for specific cases. Kaspersky Machine Learning for Anomaly Detection provides a visual interface for analyzing detected anomalies. Due to the visualized diagrams of all monitored processes, an expert can see what went wrong, when and in which part of the system.
More at Kaspersky.com
About Kaspersky Kaspersky is an international cybersecurity company founded in 1997. Kaspersky's in-depth threat intelligence and security expertise serve as the basis for innovative security solutions and services to protect companies, critical infrastructures, governments and private users worldwide. The company's comprehensive security portfolio includes leading endpoint protection as well as a range of specialized security solutions and services to defend against complex and evolving cyber threats. Kaspersky technologies protect over 400 million users and 250.000 corporate customers. More information about Kaspersky can be found at www.kaspersky.com/