Sap Se

Lauren McMullen

Anubhav Bhatia

Simon Lee

Patrick Brose

Lukas Carullo

Leonard Brzezinski

Kun Bao

Martin Weiss

Karthik Mohan Mokashi

Rashmi Shetty B

Harpreet Singh

Rajarshi Ghosh

Oliver Mainka

Ankit Shivhare

Andreas Vogel

Tuan Hung Pham

Provided is a system and method for training and validating models in a machine learning pipeline for failure mode analytics. The machine learning pipeline may include an unsupervised training phase, a validation phase and a supervised training and scoring phase. In one example, the method may include receiving an identification of a machine learning model, executing a machine learning pipeline comprising a plurality of services which train the machine learning model via at least one of an unsupervised learning process and a supervised learning process, the machine learning pipeline being controlled by an orchestration module that triggers ordered execution of the services, and storing the trained machine learning model output from the machine learning pipeline in a database associated with the machine learning pipeline.

Orchestrator for machine learning pipeline

Provided is a system and method for training and validating models in a machine learning pipeline for failure mode analytics. The machine learning pipeline may include an unsupervised training phase, a validation phase and a supervised training and scoring phase. In one example, the method may include receiving a request to create a machine learning model for failure mode detection associated with an asset, retrieving historical notification data of the asset, generating an unsupervised machine learning model via unsupervised learning on the historical notification data, wherein the unsupervised learning comprises identifying failure topics from text included in the historical notification data and mapping the identified failure topics to a plurality of predefined failure modes for the asset, and storing the generated unsupervised machine learning model via a storage device.

Failure mode analytics

A global filter allows data filtering using attributes across multiple Analysis Tools (ATs), by broadcasting semantic filter context objects. Upon selecting object attribute values, the filter context object is created with attribute names and values. A processing engine resolves the filter context object to a data object, and then subsequently to target data. A lateral filter finds related entities in a relational database, without having to maintain and/or duplicate all of the data into a graph database. The processing engine resolves lateral filters using an entity graph path calculation conducted in conjunction with the generation of a bootstrapped graph structure. That graph structure is constructed (bootstrapped) utilizing available database schematic information&#x2014;e.g., pre-calculated (key) relations and metadata read from the relational database. From that information, relationships in the bootstrapped graph structure are determined. Possible paths between entities are used to generate an optimized SQL query to reach target data.

Data filtering utilizing broadcast context object

Data filtering utilizing constructed graph structure

Provided is a system and method for predicting leading indicators for predicting occurrence of an event at a target asset. Rather than rely on traditional manufacturer-defined leading indicators for an asset, the examples herein predict leading indicators for a target asset based on actual operating conditions at the target asset. Accordingly, unanticipated operating conditions can be considered. In one example, the method may include receiving operating data of a target resource, the operating data being associated with previous occurrences of an event at the target resource, predicting one or more leading indicators of the event at the target resource based on the received operating data, each leading indicator comprising a variable and a threshold value for the variable, and outputting information about the one or more predicted leading indicators of the target resource for display via a user interface.

Predicting leading indicators of an event

In an embodiment, a method of providing an arranged display of data associated with a set of time periods is presented. In this method, values of a first data type are accessed, the values being observed during each of multiple time periods. An order for the time periods is determined based on the values of the first data type. A selectable region for each of the time periods is displayed, the regions being arranged according to the order. In response to a user selection of one of the selectable regions, a value of a second data type is displayed, the value of the second data type being observed during the time period of the selected one of the selectable regions.

Arranged display of data associated with a set of time periods

Growing community of inventors

El Dorado Hills, CA, United States of America

Lauren McMullen