Predictive Maintenance for Switch Machine Based on Digital Twins

Abstract

As a unique device of railway networks, the normal operation of switch machines involves railway safe and efficient operation. Predictive maintenance becomes the focus of the switch machine. Aiming at the low accuracy of the prediction state and the difficulty in state visualization, the paper proposes a predictive maintenance model for switch machines based on Digital Twins (DT). It constructs a DT model for the switch machine, which contains a behavior model and a rule model. The behavior model is a high-fidelity visual model. The rule model is a high-precision prediction model, which is combined with long short-term memory (LSTM) and autoregressive Integrated Moving Average model (ARIMA). Experiment results show that the model can be more intuitive with higher prediction accuracy and better applicability. The proposed DT approach is potentially practical, providing a promising idea for switching machines in predictive maintenance.

Systematic review of predictive maintenance and digital twin technologies challenges, opportunities, and best practices

“…The fundamental concept of PdM using DT was applied in various applications such as a battery for vehicles ( Das et al, 2021 ), CNC machine tool (CNCMT) ( Luo et al, 2020 ), aero-engine ( Xiong et al, 2021 ), railways ( Pillai, Shih & Roberts, 2021 ; Yang et al, 2021 ), hydraulic equipment and system ( Wang et al, 2022 ; Zhang et al, 2022 ), robots, ( Aivaliotis et al, 2023 ; Aivaliotis, Georgoulias & Chryssolouris, 2019 ; Aivaliotis et al, 2019 ; Mourtzis, Tsoubou & Angelopoulos, 2023 ), ventilation systems ( Yakhni et al, 2022 ) and others. Several types of models can be discovered in the results of previous studies related to the field of interest.…”

“…Several model representations of PdM using DT were developed. In total, 14 studies used such a hybrid model ( Das et al, 2021 ; Harries et al, 2023 ; Hosamo et al, 2022 , 2023 ; Hu et al, 2023a ; Luo et al, 2020 ; Mrzyk et al, 2023 ; Panagou et al, 2022a , 2022b ; Wang et al, 2022 ; Werner, Zimmermann & Lentes, 2019 ; Xiong et al, 2021 ; Yang et al, 2021 ; Zhang et al, 2022 ) with a percentage of 41% from these studies.…”

“…AHU stability is essential for maintaining high efficiency and increasing the lifespan of HVAC systems. For railway engineering ( Yang et al, 2021 ), a separate model DT is used for switch drives to enhance the outcomes’ forecasting accuracy. RUL estimation is used in seven studies for this hybrid model, which is of interest for various domains, such as flexible IT architectures, indoor climate, and others ( Harries et al, 2023 ; Hosamo et al, 2023 ; Hu et al, 2023a ; Luo et al, 2020 ; Mrzyk et al, 2023 ; Werner, Zimmermann & Lentes, 2019 ; Xiong et al, 2021 ).…”

“…DNNs are formed by stacking these layered networks ( Brownlee, 2017 ). In the review, four studies focus on DL, such as the LSTM approach ( Hu et al, 2023a ; Xiong et al, 2021 ; Yang et al, 2021 ). The issue of a series’ long-term reliance can be resolved with LSTM by analysing the inputs in time a series ( Li, Wang & Li, 2022 ).…”

“…Unsupervised learning is typically applied to clustering issues and looks for hidden patterns or intrinsic structures in the input data ( Abd-Elrazek et al, 2021 ). ML techniques such as naive Bayes, random forest, support vector machine (SVM), decision tree, and regression models are the most widely used AI approaches ( Khairuddin et al, 2022 , 2023 ; Neo et al, 2022 ), artificial neural network (ANN), and decision trees ( Hosamo et al, 2022 ) and ML is also used for Autoregressive Integrated Moving Average (ARIMA) ( Yang et al, 2021 ). From the review, 19 studies use ML approaches for PdM using DT ( Altun & Tavli, 2019 ; Avornu et al, 2022 ; Das et al, 2021 ; Harries et al, 2023 ; Heim et al, 2020 ; Hosamo et al, 2022 , 2023 ; Hu et al, 2023a ; Luo et al, 2020 ; Mourtzis, Tsoubou & Angelopoulos, 2023 ; Mubarak et al, 2022 ; Panagou et al, 2022a , 2022b ; Rajesh et al, 2019 ; Rossini et al, 2020 ; Siddiqui, Kahandawa & Hewawasam, 2023 ; Singh et al, 2023 ; Wang et al, 2022 ; Werner, Zimmermann & Lentes, 2019 ).…”