Modelling stochastic behaviour in simulation digital twins through neural nets

Abstract

In discrete event simulation (DES) models, stochastic behaviour is modelled by sampling random variates from probability distributions to determine event outcomes. However, the distribution of outcomes for an event from a real system is often dynamic and dependent on the current system state. This paper proposes the use of artificial neural networks (ANN) in DES models to determine the current distribution of each event outcome, conditional on the current model state or input data, from which random variates can then be sampled. This enables more realistic and accurate modelling of stochastic behaviour. An application is in digital twin models that aim to closely mimic a real system by learning from its past behaviour and utilising current data to predict its future. The benefits of the approach introduced in this paper are demonstrated through a realistic DES model of load-haul-dump vehicle operations in a production area of a sublevel caving mine.

Research on Issues Related to Digital Twin Modeling

“…In the context of the development of artificial intelligence, introducing intelligent algorithms into the process of establishing digital twin models is an effective measure to improve modeling accuracy [14] . Train the model using real-time transmission data and pre processing data, provide the optimal model parameters and order in the current state, and achieve the transition from a fixed model to a model with dynamic optimization function [15] . By continuously optimizing the model, on the one hand, it can better fit the actual object and more accurately reflect the operating mechanism of the object; On the other hand, it is possible to make more accurate predictions of the operational trends of physical objects, providing reference opinions for expert decision-making [16] .…”

Automatic generation and updating of process industrial digital twins for estimation and control - A review

“…Due to the modeling ability of artificial neural networks (ANN), they have served as a basic tool for various applications in the process industry. In the context of DTs, adaptive ANNs are used to design the DTs and adapt them over time through continuous learning (Reed et al, 2021). Moreover, Bayesian networks can be employed to create and update the DTs.…”

Utilising Digital Twins to Bolster the Sustainability of Logistics Processes in Industry 4.0

“…In [11,12], the authors provided systematic research of current studies on digital twin modelling. Another modelling problem was solved by Reed et al [13]. The authors used artificial neural networks (ANNs) in DES models to determine the current distribution of each event.…”