Sensor fault detection and diagnosis for data center air conditioning system based on LSTM neural network

WANG Luyao; WU Bin; DU Zhimin; JIN Xinqiao

doi:10.11949/j.issn.0438-1157.20181084

您当前的位置：

首页 >

文章列表页 >

Sensor fault detection and diagnosis for data center air conditioning system based on LSTM neural network

更新时间：2025-12-10

- Sensor fault detection and diagnosis for data center air conditioning system based on LSTM neural network
- CIESC Journal Issue S2, Pages: 252-259(2018)
- 作者机构：
  
  上海交通大学制冷与低温工程研究所,上海,200240
- 作者简介：
- 基金信息：
- DOI：10.11949/j.issn.0438-1157.20181084
  CLC： U831.3
- Online First：31 December 2018，
  
  Published：31 December 2018
- 稿件说明：
移动端阅览
WANG Luyao, WU Bin, DU Zhimin, et al. Sensor fault detection and diagnosis for data center air conditioning system based on LSTM neural network[J]. CIESC Journal, 2018, (S2): 252-259.
DOI：

WANG Luyao, WU Bin, DU Zhimin, et al. Sensor fault detection and diagnosis for data center air conditioning system based on LSTM neural network[J]. CIESC Journal, 2018, (S2): 252-259. DOI： 10.11949/j.issn.0438-1157.20181084.

摘要

数据中心空调系统的故障直接影响其能耗及运行可靠性。结合深度学习技术，利用长短时间记忆神经网络提出了一种空调系统传感器故障检测与诊断的方法。经实验验证，该方法可通过对液管温度传感器、排气温度传感器分别建立故障诊断模型，成功检测出传感器固定偏差故障和漂移偏差故障。对于无故障数据，该方法的检测正确率在90%左右；对于偏差程度大于该方法的最小检测偏差的传感器故障数据，其检测正确率在94%以上。

Abstract

The faults of data center air-conditioning system directly results in increasing energy consumption and reducing operation reliability. Combined with deep learning technology

a fault detection and diagnosis method of sensors for air conditioning system is proposed by using LSTM (long short term memory) neural network. Verified by the experiment

the method can identify the fixed biases and drifting biases of both liquid line temperature sensor and discharge temperature sensor through building the fault detection and diagnosis models for them respectively. For the fault-free condition

the detection accuracy of this method is about 90%. For the sensor fault whose deviation degree is greater than the minimum detection deviation of the method

the detection accuracy is above 94%.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Study on dissolution kinetics of erythromycin thiocyanate

Study on entropy wave production and dissipation in partially premixed swirl flames subject to inlet perturbations

Methods of adaptive prediction and abnormal states traceability for sulphur content in flue gas desulfurization process

Thermo-gas-elastic coupling performance analysis of high-speed and high-temperature foil face seals

A hybrid modeling and optimization strategy for sequential simulated moving bed

Related Author

No data

Related Institution

No data

⁰