Om Prasad Patri

The process-oriented event model (PoEM): a conceptual model for industrial events

The paper presents a comprehensive theoretical framework for modeling events and semantics of event processing at a level of abstraction that captures the different processes in industrial applications but is not limited to a specific application domain. The model, called Process-oriented Event Model (PoEM), provides a formal approach to model real-world entities and their interrelationships, and specifies the process of moving from data streams to event detection to event-based goal planning. The model links event detection to states, actions, and roles, enabling event notification, filtering, context awareness and escalation. PoEM defines event and non-event concepts and combines information from them to build an event processing workflow. Usage of the PoEM model is illustrated in case studies from the oil and gas industry and maritime piracy events.

Extracting discriminative shapelets from heterogeneous sensor data

We study the problem of identifying discriminative features in Big Data arising from heterogeneous sensors. We highlight the heterogeneity in sensor data from engineering applications and the challenges involved in automatically extracting only the most interesting features from large datasets. We formulate this problem as that of classification of multivariate time series and design shapelet-based algorithms for this task. We design a novel approach, called Shapelet Forests (SF), which combines shapelet extraction with feature selection. We evaluate our proposed method with other approaches for mining shapelets from multivariate time series using data from real-world engineering applications. Quantitative analysis of the experiments shows that SF performs better than the baseline approaches and achieves high classification accuracy. In addition, the method enables identification of noisy sensors from multivariate data and discounts their use for classification.

Predicting Failures from Oilfield Sensor Data using Time Series Shapelets

Increasing instrumentation of the modern digital oilfield produces streams of data from sensors that monitor the functioning of different components in the field. This data should be converted to actionable information rapidly in order to respond to events as they happen or are predicted. The challenge is therefore to develop technologies that can process these large sensor datasets rapidly and with minimal manual supervision to ensure a data processing system that can scale with the increasing instrumentation. We consider as a use-case an oilfield with several Electrical Submersible Pumps (ESPs), each instrumented with sensors that continually measure electrical properties of the pump (the streams of sensor data), which are then relayed to a central location. In this paper, we demonstrate how a time-series analysis approach can be applied to failure detection and failure prediction from the streams of sensor data. The method involves identifying “shapelets” – short instances that are particularly distinct – in the streams of sensor data. The shapelets approach is particularly applicable to large oil and gas enterprise datasets because the algorithm does not need access to the entire historical data. This greatly reduces the amount of data that needs to be stored for data analysis. Moreover, unlike model-based approaches, shapelet-based analysis does not make any assumptions about the underlying nature of the data, making it practical for applications where a detailed physical model of the pump is not available. We validate our proposed method by analysis on a representative set of instrumented ESPs. We describe the preprocessing steps that were applied in our analysis. We report the results of experiments to study the effects of varying the data processing parameters on the accuracy of fault detection and prediction. These results indicate that shapelet-based approaches are promising for analysis of time-series data in the oil and gas industry.

Event-driven Information Integration for the Digital Oilfield

Several operations in the Exploration and Production (E&P) sector are event-driven in nature and are supported by specialized systems and applications. Narrow focus of applications results in application silos that restrict the information sharing across verticals, which is a critical requirement for coordinated cross-functional efforts. Effective response to events warrants due emphasis on an integration strategy that facilitates desired information flow across verticals. Event-driven methods can be used to make strategic asset management decisions across silos in real-time, thus reducing response time and costs while improving asset performance. Complex event processing is an emerging research area that involves detecting complex events, processing the events, deciding actions for each event and notifying the relevant personnel about the event. In the E&P sector, the adoption of CEP and messaging-based systems in conjunction with semantic methods can facilitate components of the oilfield to communicate in real-time across different software platforms. Such an approach helps not only in detecting complex events across various sources, but also in processing them and deciding the actions to be taken, with the help of a knowledge base – thereby reducing information overload. Consider a typical application scenario a pump failure event in an oilfield, which should elicit response not only by the pump operator but also by the maintenance engineers, production managers, reservoir engineers and other involved personnel. A proactive event-driven system enables quick detection of the failure across heterogeneous data sources and takes corrective actions while notifying the appropriate personnel. This facilitates effective communication across the teams and software systems involved. We propose a semantic complex event processing architecture for the digital oilfield that facilitates enterprise information integration. We delineate an illustrative use case of such integration for production optimization. Value propositions of the proposed framework include efficient interaction patterns, reduction in data seeking efforts, faster response times, building of consistent best practices and management by exception.

Sensors to Events: Semantic Modeling and Recognition of Events from Data Streams

Detecting and responding to real-world events is an integral part of any enterprise or organization, but Semantic Computing has been largely underutilized for complex event processing (CEP) applications. A primary reason for this gap is the difference in the level of abstraction between the high-level semantic models for events and the low-level raw data values received from sensor data streams. In this work, we investigate the need for Semantic Computing in various aspects of CEP, and intend to bridge this gap by utilizing recent advances in time series analytics and machine learning. We build upon the Process-oriented Event Model, which provides a formal approach to model real-world objects and events, and specifies the process of moving from sensors to events. We extend this model to facilitate Semantic Computing and time series data mining directly over the sensor data, which provides the advantage of automatically learning the required background knowledge without domain expertise. We illustrate the expressive power of our model in case studies from diverse applications, with particular emphasis on non-intrusive load monitoring in smart energy grids. We also demonstrate that this powerful semantic representation is still highly accurate and performs at par with existing approaches for event detection and classification.

Semantic management of Enterprise Integration Patterns: A use case in Smart Grids

Enterprise Integration Patterns are a set of design patterns for linking multiple systems using asynchronous messaging interfaces. This approach to system integration is increasingly popular due to its relatively simple loose coupling requirement. Implementations of these patterns are available in current integration frameworks but these are not semantic in nature. This paper introduces the concept of automatic management of messaging resources in an integration application via the use of a semantic representation of the Enterprise Integration Patterns. We have developed semantic representations of some of the commonly used integration patterns, which include a description of the expected resource requirements for each pattern. We then demonstrate this approach by considering the design of an application to connect mobile customers to Smart Power Grid companies (for the purpose of near real-time regulation of electricity usage). We illustrate potential savings in messaging resources and automatic lifecycle management using real-world sensor data collected in a Smart Grid project.

Enriching employee ontology for enterprises with knowledge discovery from social networks

To enhance human resource management and personalized information acquisition, employee ontology is used to model business concepts and relations between them for enterprises. In this paper, we propose an employee ontology that integrates user static properties from formal structures with dynamic interests and expertise extracted from informal communication signals. We mine users interests at both personal and professional level from informal interactions on communication platforms at the workplace. We show how complex semantic queries enable granular analysis. At the microscopic level, enterprises can utilize the results to better understand how their employees work together to complete tasks or produce innovative ideas, identify experts and influential individuals. At the macroscopic level, conclusions can be drawn, among others, about collective behavior and expertise in varying granularities (i.e. single employee to the company as a whole).

Modeling and recognition of events from multidimensional data: doctoral symposium

The recent rise in scale of sensors has led to the need for faster processing of events from multiple sensor data streams in a variety of real-world applications. We need an approach to model real-world entities and their interrelationships, and specify the process of moving from sensor data streams to event detection to event-based goal planning. Recent advances in analysis of temporal data, such as time series shapelets, provide methods for identifying these discriminative events for classification. In this dissertation, I make connections between event processing and time series data mining as part of a comprehensive event detection and representation framework.

Personalized trip planning by integrating multimodal user-generated content

We address the problem of record linkage and semantic integration in the context of large collections of user-generated content. These datasets are often large since it contains the contributions of millions of Internet users. We present an approach based on approximate string matching between the metadata associated with such data. The discovered linkages are stored in an ontology for answering queries on the integrated data sources. We demonstrate this approach in Photo Odyssey, an interactive web application which integrates multimodal content from image hosting and travel websites to create a user interface with a graphical trip plan and personalization options.We discuss several practical challenges faced in building such an application - integrating and mining large-scale multimodal user-generated data, resolving semantic heterogeneity, and machine learning for matching and ranking items. Photo Odyssey operates in an online manner without using any previously stored knowledge base. We also describe methods to compute relevance of images, remove bad data instances and duplicates, perform contextual filtering, and assign a category to uncatalogued images which enable an interactive application even on Big Data with real-world characteristics.

Rapid Data Integration and Analysis for Upstream Oil and Gas Applications

The increasingly large number of sensors and instruments in the oil and gas industry, along with novel means of communication in the enterprise has led to a corresponding increase in the volume of data that is recorded in various information repositories. The variety of information sources is also expanding: from traditional relational databases to time series data, social network communications, collections of unsorted text reports, and linked data available on the Web. Enabling end-to-end optimization considering these diverse types of information requires creating semantic links between them. Though integration of data across silo-ed databases has been recognized as a problem for a long time, it has proven to be difficult to accomplish due to the complexity of the data arrangement within databases, scarcity of metadata that describe the content, lack of a direct mapping between related entities across databases, and the several types of data represented within a database. In addition, there are large amounts of unstructured text data such as text entries in databases and document repositories. These contain valuable information on processes from the field but there is currently no method to convert this raw data to useable information. The Center for Interactive Smart Oilfield Technologies (CiSoft) is a USC-Chevron Center of Excellence for Research and Academic Training on Smart Oilfield Technologies. We describe the Integrated Optimization project at CiSoft which has the goal of developing a framework for automated linking of heterogeneous data sources and analysis of the integrated data in the context of upstream applications.