Prediction of Metro Train Air-conditioning Return Air Temperature Based on Real-time Field-measured Data

Journal Title: Urban Mass Transit - Year 2024, Vol 27, Issue 12

Abstract

[Objective] To enable proactive adjustment of the cooling capacity for metro train AC (air-conditioning) system based on ambient temperature, it is essential to study the prediction of return air temperature in metro train AC systems. [Method] A time series forecasting method is employed to predict the variation trend in return air temperature of metro train AC systems. Real-time operational data from the air-conditioning system of a Guangzhou Metro train are collected through AC sensors. Outliers are removed using a boxplot, and a sliding window approach is applied to handle the time span of input and output data. An LSTM (long short-term memory) neural network model is then constructed to predict the return air temperature of the AC units, and the impact of different sample sizes on the model prediction accuracy is comparatively analyzed. [Result & Conclusion] The LSTM neural network model can learn the temperature control logic of metro train AC system, with the predicted temperature curve closely matching the actual temperature curve, therefore is suitable for predicting the return air temperature of metro AC units. Through parameter optimization, the model accuracy is improved to 0.84, enabling precise prediction of unit return air temperature. Increasing the sample size for a single training session can shorten model training time but may reduce the model final prediction accuracy to some extent correspondently.

Authors and Affiliations

Chuang YANG, Yu YANG, Liang CHEN, Huanxin CHEN, Hengda CHENG

Keywords

Related Articles

Insight on the Planning and Construction of Shanghai City Railway Network

[Objective] In recent years, pushed by new urbanization with metropolitan areas and urban clusters as carriers, the planning and construction of Shanghai city railway develop rapidly. In order to better comply with dev...

In-situ Protection of Underground High-voltage Cable Crossing Metro Foundation Pit

Objective With the increase in underground engineering projects, more and more projects are adopting in-situ protection technology targeting the issues caused by relocating urban underground high-voltage cables. Therefor...

Study on Integration Mode of Station-level Weak Current System in Urban Rail Transit

Objective Restricted by operation and maintenance management modes, the traditional station-level weak current systems generally adopt a separate computer room mode, causing a certain waste of civil construction scale. T...

Research on Adaptability of Zoning Fare System in Metropolitan Area Rail Transit

[Objective] The zoning fare system is widely used in European rail transit systems, but has not yet been put into practice in many Chinese cities with rail transit operation. Following the rapid urban rail transit cons...

Overview of Rail Potential Suppression Technology in Urban Rail Transit Running Rail Circuit Return System

Objective In the DC (direct current) traction power supply system of urban rail transit, excessive rail potential and stray current issues are persistent problems and common ailments for operational routes. Therefore, it...

Download PDF file
  • EP ID EP752723
  • DOI 10.16037/j.1007-869x.2024.12.018
  • Views 6
  • Downloads 0

How To Cite

Chuang YANG, Yu YANG, Liang CHEN, Huanxin CHEN, Hengda CHENG (2024). Prediction of Metro Train Air-conditioning Return Air Temperature Based on Real-time Field-measured Data. Urban Mass Transit, 27(12), -. https://europub.co.uk/articles/-A-752723