Using a Digital Twin in Predictive Maintenance

Abstract

The oil and gas industry is facing unprecedented and brutal market conditions. While the industry was already in the midst of digitalization, the oil price crash has instilled a fresh impetus on its adoption to cut costs through innovation and new technologies. One such technology is predictive maintenance. When equipment on a rig breaks down, the resulting problem often is not that of replacement but the forced downtime in production or drilling. Therefore, predicting when equipment or a system is going to fail and determining the root cause of failure unlocks significant value. Predictive maintenance has rapidly gained in popularity, spurred by well publicized advances in high-performing computing and Internet of Things (IoT) technologies. Some companies are experiencing the benefits of predictive maintenance firsthand. For example, engineers at Baker Hughes implemented predictive maintenance on the company’s fleet of fracturing trucks. They collected nearly a terabyte of data from pumps on these trucks and then used signal-processing techniques to identify the relevant sensors. Finally, they applied machine-learning techniques to distinguish a healthy pump from an unhealthy one and reduced overall costs by $10 million (MathWorks 2019). This success story and others like it have made pursuing predictive maintenance projects a priority among both oilfield operators and services firms.

Future of precision manufacturing: Integrating advanced metrology and intelligent monitoring for process optimization

“…It has also been utilized for the prescriptive maintenance of protective coating systems on wind turbine structures, integrating various parameters and sensor data into the digital twin concept (Momber et al, 2021). Furthermore, the digital twin technology has been leveraged for the development of a building intelligent operation and maintenance system, integrating machine learning for state prediction and analysis of building operation and maintenance (Rao, 2020).…”

Aplicação de técnicas de mineração em dados sintéticos para manutenção preditiva: um estudo de caso

“…Atacando o problema da falta de dados reais de falha para construc ¸ão de modelos preditivos, [Rao 2020] propõe a utilizac ¸ão de dados sintéticos gerados por um gêmeo digital, onde os dados são gerados a partir de um modelo físico em um simulador com defeitos modelados, para que fossem simuladas situac ¸ões de desgaste extremo do equipamento não contempladas pelo histórico de operac ¸ão. O trabalho compara as curvas de dados simulados e dados reais medidos em campo, mas não explora a cobertura dos dados sintéticos para os estados relevantes para a indústria.…”

Data Reduction of Digital Twin Simulation Experiments Using Different Optimisation Methods

“…If recombination is also used as in other evolutionary algorithms, ρ = 2 holds. A special case of (µ/ρ, λ) algorithms is the (µ/µ, λ) evolution strategy [1] (µ/ρ + λ)-analogously to (µ/ρ, λ)-evolution strategies, the (µ/ρ + λ)-evolution strategies are (µ, λ) approaches where ρ denotes the number of parents of an offspring individual; (µ ,λ (µ,λ)γ)-Geyer et al [2][3][4] have developed nested evolution strategies [62], where λ offspring are created and isolated for γ generations from a population of the size µ . In each of the γ generations, λ children are created from which the fittest µ are passed on to the next generation.…”

“…The increasing use of digital twins (DTs) is one of the most important trends in the Industry 4.0 concept and industrial engineering [1], and some authors directly refer to the Industry 4.0 era as the era of DT [2]. The concept of Industry 4.0 extends the possibilities and use of DTs for, e.g., decision support and production planning [3], solving unexpected situations/problems or predicting such situations [4], as well as training and knowledge transfer of leadership, management, and executives [5,6].…”