Computer-implemented method, computer program product and system for anomaly detection and/or predictive maintenance

Abstract

A computer-implemented method and a respective system for anomaly detection and / or predictive maintenance is provided. The method comprises: receiving a new observation characterizing at least one parameter of the entity; inputting the new observation to a deep neural network (100) having a plurality of hidden layers and being trained using a training data set that includes possible observations; obtaining a second set of intermediate output values that are output from at least one of the plurality of hidden layers of the deep neural network by inputting the received new observation to the deep neural network; mapping, using a latent variable model stored in a storage medium, the second set of intermediate output values to a second set of projected values; determining whether or not the received new observation is an outlier with respect to the training dataset based on the latent variable model and the second set of projected values, calculating, by the deep neural network, a prediction for the new observation; and determining a result indicative of the occurrence of at least one anomaly in the entity based on the prediction and the determination whether or not the new observation is an outlier. The latent variable model stored in the storage medium is constructed by obtaining first sets of intermediate output values that are output from said one of the plurality of hidden layers of the deep neural network, each of the first sets of intermediate output values obtained by inputting a different one of the possible observations included in at least a part of the training dataset; and constructing the latent variable model using the first sets of intermediate output values, the latent variable model providing a mapping of the first sets of intermediate output values to first sets of projected values in a sub-space of the latent variable model that has a dimension lower than a dimension of the sets of the intermediate outputs.

Description

technical field [0001] The present application relates to a computer-implemented method, a computer program product and a system for anomaly detection and / or predictive maintenance, in particular, using outlier detection in structured or unstructured data. Background technique [0002] Anomaly detection in various systems such as those used for predictive maintenance, cybersecurity, fraud prevention, etc. is becoming more and more common. In such systems, it is important to reliably and timely detect anomalies that may disrupt the proper operation of the system. [0003] Predictive maintenance techniques, for example, aim to automatically determine when a piece of equipment, such as a machine or a machine part, needs maintenance to avoid failure. Significant cost savings can be achieved by automatically estimating equipment degradation compared to routine or time-based maintenance. By contrast, by arranging on a fixed schedule, there is a risk that maintenance will be perf...

AI Technical Summary

Problems solved by technology

Unsupervised modeling can answer the question: "Is the device functioning properly?" but does not provide further clues for investigating the system

[0033] However, these methods make assumptions about which type of model to use and may constrain how the network is built or trained and / or rely on making multiple inferences per prediction

This may limit their general applicability to real-time systems where multiple inferences are impractical and / or to existing systems that do not meet the constraints

Images