AI-Supported Workflows for Chemical Batch Plants

Optimizing quality, efficiency and safety

Abstract

Digitalization, Internet of Things, Big Data, Artificial Intelligence and Smart Sensors are some examples of rapidly developing technology areas with high impact on how industrial processes will be operated in the future. Here, we present an AI supported solution for cross-application workflows in batch plants. Based on a digital virtual assistant, industrial digital services are connected in workflows and support users in making the best use of the digital infrastructure at hand. We present two digital services which allow for early detection of failures in the production and root cause analysis: (1) a novel approach to online identification of batch failures building on an adjusted form of multiway principal component analysis; (2) a low-cost sensing infrastructure to perform root cause analysis for different failure modes which occur in batch plants. A case study of the implementation of the installation in a test plant is reported together with insights into the benefits and limitations of the approach gained via several process executions.