scholarly journals Predictive Maintenance for Switch Machine Based on Digital Twins

Information ◽  
2021 ◽  
Vol 12 (11) ◽  
pp. 485
Author(s):  
Jia Yang ◽  
Yongkui Sun ◽  
Yuan Cao ◽  
Xiaoxi Hu
Keyword(s):  
Short Term Memory ◽  
Moving Average ◽  
Predictive Maintenance ◽  
Normal Operation ◽  
Behavior Model ◽  
Efficient Operation ◽  
Visual Model ◽  
Rule Model ◽  
Digital Twins ◽  
Moving Average Model

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.

Analisis Data Time Series Menggunakan LSTM (Long Short Term Memory) Dan ARIMA (Autocorrelation Integrated Moving Average) Dalam Bahasa Python.

2020 ◽  
Vol 11 (1) ◽  
pp. 1-7
Author(s):  
Adhitio Satyo Bayangkari Karno
Keyword(s):  
Time Series ◽  
Short Term Memory ◽  
Moving Average ◽  
Average Model ◽  
Short Term ◽  
Term Memory ◽  
Moving Average Model ◽  
Long Short Term Memory

Abstrak - Penelitian ini bertujuan untuk memprediksi data deret waktu dengan menggunakan dua metode, metode pertama yang umum digunakan adalah statistik Autocorrelation Integrated Moving Average (model ARIMA) dan metode kedua yang relatif baru, yaitu pembelajaran mesin Long Short Term Memory (LSTM). Sebelum data diproses dengan kedua metode, pembersihan data dan pengoptimalan data dilakukan. Optimalisasi data adalah proses transformasi untuk menghilangkan elemen tren dan variasi dari data. Transformasi terdiri dari 7 hasil kombinasi dari proses Log, Moving Average (MA), Exponential Weigh Moving Average (EWMA), dan Differencing (Diff). Tujuh proses masing-masing digunakan dalam proses ARIMA dan LSTM. Sehingga 14 prediksi akan diperoleh (7 dari proses ARIMA dan 7 dari proses LSTM). Dari 14 hasil prediksi diperoleh nilai RMSE terkecil untuk ARIMA adalah 2% dan nilai RMSE terkecil untuk LSTM adalah 1%. Hasil penelitian ini menggunakan 7 kombinasi proses transformasi, dapat meningkatkan tingkat akurasi prediksi dari ARIMA dan LSTM. Dimana akurasi mesin pembelajaran LSTM dengan menggunakan data stok Telkom memiliki akurasi lebih tinggi dari ARIMA.

scholarly journals On-Line Remaining Useful Life Estimation of Power Connectors Focused on Predictive Maintenance

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3739
Author(s):  
Jordi-Roger Riba ◽  
Álvaro Gómez-Pau ◽  
Jimmy Martínez ◽  
Manuel Moreno-Eguilaz
Keyword(s):  
Power Systems ◽  
Electrical Resistance ◽  
Voltage Drop ◽  
Moving Average ◽  
Remaining Useful Life ◽  
Predictive Maintenance ◽  
Moving Average Model ◽  
On Line ◽  
Useful Life ◽  
Two Parameters

Connections are critical elements in power systems, exhibiting higher failure probability. Power connectors are considered secondary simple devices in power systems despite their key role, since a failure in one such element can lead to major issues. Thus, it is of vital interest to develop predictive maintenance approaches to minimize these issues. This paper proposes an on-line method to determine the remaining useful life (RUL) of power connectors. It is based on a simple and accurate model of the degradation with time of the electrical resistance of the connector, which only has two parameters, whose values are identified from on-line acquired data (voltage drop across the connector, electric current and temperature). The accuracy of the model presented in this paper is compared with the widely applied autoregressive integrated moving average model (ARIMA), showing enhanced performance. Next, a criterion to determine the RUL is proposed, which is based on the inflection point of the expression describing the electrical resistance degradation. This strategy allows determination of when the connector must be replaced, thus easing predictive maintenance tasks. Experimental results from seven connectors show the potential and viability of the suggested method, which can be applied to many other devices.

Research of pressure influence in the gas supply system on the energy consuption level of gas devices

2019 ◽  
Vol 6 (2) ◽  
pp. 56-63
Author(s):  
L. D. Pylypiv ◽  
І. І. Maslanych
Keyword(s):  
Natural Gas ◽  
Residential Buildings ◽  
Supply System ◽  
Normal Operation ◽  
Gas Combustion ◽  
Efficient Operation ◽  
Gas Consumption ◽  
Natural Gas Combustion ◽  
Gas Supply

There are investigated the influence of operating pressures in the gas supply system on the level of such energy indicators as efficiency, gas flow and gas overrun by gas equipment in residential buildings. There is established a relationship between the values of operating pressures in the gas supply system and the gas consumption level of household appliances. The causes of insufficient pressure in the gas networks of settlements are analyzed in the article. There is also developed an algorithm for calculating the change in the efficiency of gas appliances depending on the operational parameters of the gas network. It has been found that the most efficient operation of gas appliances is observed at an overpressure at the inlet of gas appliances of about 1200 Pa.To ensure the required quality of natural gas combustion among consumers and minimize gas consumption there are justified the following measures in the article: coordinating a domestic regulatory framework for assessing the quality of natural gas with international norms and standards; improving the preparation of gas coming from local wells before supplying it to gas distribution networks; auditing low pressure gas pipelines and reconstructing areas affected by corrosion; ensuring standard gas pressure in the network for the normal operation of domestic gas appliances; stating quality indicators of natural gas combustion by gas sales organizations.

Sign in / Sign up

Export Citation Format

Share Document