Big Data Processing and Analytics Platform Architecture for Process Industry Factories

Abstract

This paper describes the architecture of a cross-sectorial Big Data platform for the process industry domain. The main objective was to design a scalable analytical platform that will support the collection, storage and processing of data from multiple industry domains. Such a platform should be able to connect to the existing environment in the plant and use the data gathered to build predictive functions to optimize the production processes. The analytical platform will contain a development environment with which to build these functions, and a simulation environment to evaluate the models. The platform will be shared among multiple sites from different industry sectors. Cross-sectorial sharing will enable the transfer of knowledge across different domains. During the development, we adopted a user-centered approach to gather requirements from different stakeholders which were used to design architectural models from different viewpoints, from contextual to deployment. The deployed architecture was tested in two process industry domains, one from the aluminium production and the other from the plastic molding industry.

Towards the use of LSTM-based Neural Network for Industrial Alarm Systems

“…According to (Sarnovsky et al (2018)), predictive models can offer effective gains when applied to the optimization of productive processes. At this point, it is important to enlighten that masses of data generated are alarm and event logs are a potential source of knowledge that can be better explored.…”

An Improved Stream Processing Access

“…Big data is of different types basically dependent on how they are generated and how they are used. The processing types can be as [3] I. Batch processing II.…”

Cross-Sectorial Semantic Model for Support of Data Analytics in Process Industries

“…Data modeling elements represent the main concepts used to describe the data and relationships between the physical data stored in the Data Lab, particular data elements of those datasets (e.g., attributes), and how they are related to overall KPIs specified for a particular process segment. High-level descriptions of those elements were introduced by Sarnovsky et al [5]. The next sections provide a more in-depth description.…”

“…This results in an open, extendable semantic description of all data entities handled by all systems available in the production site. The proposed semantic model was designed in the context of the MOdel based coNtrol framework for Site-wide OptimizatiON of data-intensive processes (MONSOON), a SPIRE (Sustainable Process Industry through Resource and Energy Efficiency) research project, which aims to develop an infrastructure with the main objective of establishing a data-driven methodology supporting the identification and exploitation of optimization potentials by applying model-based predictive controls in the production processes [5]. The platform was evaluated in two domains: Aluminum production and plastic injection.…”