基于知识数据化表达的制冷空调系统故障诊断方法

doi:10.11949/0438-1157.20211830

摘要/Abstract

摘要：

制冷空调系统广泛用于建筑环境调节，是建筑能耗的重要组成部分，而系统故障运行会造成15%~20%的能耗增加。以深度学习为代表的数据驱动方法是故障诊断的热点技术。然而，数据驱动需要依赖大量标记数据从而限制了其应用。针对上述问题，提出一种基于知识数据化表达的故障诊断方法，通过将故障诊断先验知识以数据化的形式表达弥补真实标记数据不足的难题。首先，提出以随机缩放策略为信息扩增手段的知识数据化方法，并利用添加噪声达到生成样本与真实样本一致性更优的目的。然后，提出基于基准模型的目标系统偏离特性表征方法，将目标系统数据与生成数据的格式统一。最后，利用生成数据训练模型并在ASHRAE RP-1043数据集上验证，综合诊断正确率达82.67%，与经典的监督学习方法效果接近且完全无须标记数据，具有广泛应用前景。

关键词: 神经网络, 热力学性质, 算法, 故障诊断, 制冷空调系统

Abstract:

Refrigeration and air-conditioning systems are widely used in building environmental regulation and are an important part of building energy consumption, and system failures will increase energy consumption by 15%—20%. The data-driven method represented by deep learning has become the mainstream method for fault diagnosis. However, data-driven method needs to rely on a large amount of labeled data, which limits their applications. Focus on the above problems, a fault diagnosis method based on digitized knowledge representation is proposed, which makes up for the problem of insufficient real labeled data by prior knowledge of fault diagnosis in a data form. A method of knowledge digitization using random scaling strategy is proposed, and a noise addition strategy is used to achieve the goal of better consistency between the generated sample and the real sample. A characterization method of target system deviation characteristics based on benchmark model is proposed, which unifies the format of target system data and generated data. Using the generated data to train the model and verify it on the ASHRAE RP-1043 data set, the comprehensive diagnosis accuracy rate is 82.67%, which is close to the supervised learning method. Combined with that it does not need to labeled data at all, makes it has a wide range of application prospects.

Key words: neural network, thermodynamic property, algorithm, fault diagnosis, refrigeration and air-conditioning system

中图分类号:

TK 38

孙哲, 金华强, 李康, 顾江萍, 黄跃进, 沈希. 基于知识数据化表达的制冷空调系统故障诊断方法[J]. 化工学报, 2022, 73(7): 3131-3144.

Zhe SUN, Huaqiang JIN, Kang LI, Jiangping GU, Yuejin HUANG, Xi SHEN. Fault diagnosis method of refrigeration and air-conditioning system based on digitized knowledge representation[J]. CIESC Journal, 2022, 73(7): 3131-3144.

图/表 13

参考文献 32

3	Kim W, Katipamula S. A review of fault detection and diagnostics methods for building systems[J]. Science and Technology for the Built Environment, 2018, 24(1): 3-21.
4	王姝婷. 基于贝叶斯网络单元的全空气空调系统故障检测与诊断方法研究[D]. 杭州: 浙江大学, 2021.
	Wang S T. Research on fault detection and diagnosis of all-air air conditioning systems using Bayesian network-based diagnostic units[D]. Hangzhou: Zhejiang University, 2021.
5	Sun Z, Jin H Q, Gu J P, et al. Gradual fault early stage diagnosis for air source heat pump system using deep learning techniques[J]. International Journal of Refrigeration, 2019, 107: 63-72.
6	Sun Z, Jin H Q, Gu J P, et al. Studies on the online intelligent diagnosis method of undercharging sub-health air source heat pump water heater[J]. Applied Thermal Engineering, 2020, 169: 114957.
7	Wang Z W, Wang Z W, Gu X W, et al. Feature selection based on Bayesian network for chiller fault diagnosis from the perspective of field applications[J]. Applied Thermal Engineering, 2018, 129: 674-683.
8	van de Sand R, Corasaniti S, Reiff-Stephan J. Data-driven fault diagnosis for heterogeneous chillers using domain adaptation techniques[J]. Control Engineering Practice, 2021, 112: 104815.
9	刘旭婷, 李益国, 孙栓柱, 等. 基于稀疏局部嵌入深度卷积网络的冷水机组故障诊断方法[J]. 化工学报, 2018, 69(12): 5155-5163.
	Liu X T, Li Y G, Sun S Z, et al. Fault diagnosis of chillers using sparsely local embedding deep convolutional neural network[J]. CIESC Journal, 2018, 69(12): 5155-5163.
10	王路瑶, 吴斌, 杜志敏, 等. 基于长短期记忆神经网络的数据中心空调系统传感器故障诊断[J]. 化工学报, 2018, 69(S2): 252-259.
	Wang L Y, Wu B, Du Z M, et al. Sensor fault detection and diagnosis for data center air conditioning system based on LSTM neural network[J]. CIESC Journal, 2018, 69(S2): 252-259.
11	Xiao F, Zhao Y, Wen J, et al. Bayesian network based FDD strategy for variable air volume terminals[J]. Automation in Construction, 2014, 41: 106-118.
12	Fan C, Xiao F, Zhao Y. A short-term building cooling load prediction method using deep learning algorithms[J]. Applied Energy, 2017, 195: 222-233.
13	Zhao Y, Li T, Fan C, et al. A proactive fault detection and diagnosis method for variable-air-volume terminals in building air conditioning systems[J]. Energy and Buildings, 2019, 183: 527-537.
14	Li T, Zhao Y, Zhang C, et al. A semantic model-based fault detection approach for building energy systems[J]. Building and Environment, 2022, 207: 108548.
15	Li Z F, Shi S B, Chen H X, et al. Machine learning based diagnosis strategy for refrigerant charge amount malfunction of variable refrigerant flow system[J]. International Journal of Refrigeration, 2020, 110: 95-105.
16	Hu M, Chen H, Shen L, et al. A machine learning Bayesian network for refrigerant charge faults of variable refrigerant flow air conditioning system[J]. Energy and Buildings, 2018, 158: 668-676.
17	Guo Y, Tan Z, Chen H, et al. Deep learning-based fault diagnosis of variable refrigerant flow air-conditioning system for building energy saving[J]. Applied Energy, 2018, 225: 732-745.
18	Fan Y Q, Cui X Y, Han H, et al. Chiller fault diagnosis with field sensors using the technology of imbalanced data[J]. Applied Thermal Engineering, 2019, 159: 113933.
19	张钹, 朱军, 苏航. 迈向第三代人工智能[J]. 中国科学: 信息科学, 2020, 50(9): 1281-1302.
	Zhang B, Zhu J, Su H. Toward the third generation of artificial intelligence[J]. Scientia Sinica (Informationis), 2020, 50(9): 1281-1302.
20	Liang J, Du R. Model-based fault detection and diagnosis of HVAC systems using support vector machine method[J]. International Journal of Refrigeration, 2007, 30(6): 1104-1114.
1	胡鞍钢. 中国实现2030年前碳达峰目标及主要途径[J]. 北京工业大学学报(社会科学版), 2021, 21(3): 1-15.
	Hu A G. China's goal of achieving carbon peak by 2030 and its main approaches[J]. Journal of Beijing University of Technology (Social Sciences Edition), 2021, 21(3): 1-15.
21	Fan B, Du Z M, Jin X Q, et al. A hybrid FDD strategy for local system of AHU based on artificial neural network and wavelet analysis[J]. Building and Environment, 2010, 45(12): 2698-2708.
22	Zhu Y, Jin X, Du Z. Fault diagnosis for sensors in air handling unit based on neural network pre-processed by wavelet and fractal[J]. Energy and Buildings, 2012, 44: 7-16.
23	Beghi A, Brignoli R, Cecchinato L, et al. Data-driven fault detection and diagnosis for HVAC water chillers[J]. Control Engineering Practice, 2016, 53: 79-91.
2	Zhao Y, Li T T, Zhang X J, et al. Artificial intelligence-based fault detection and diagnosis methods for building energy systems: advantages, challenges and the future[J]. Renewable and Sustainable Energy Reviews, 2019, 109: 85-101.
24	Li D, Hu G, Spanos C J. A data-driven strategy for detection and diagnosis of building chiller faults using linear discriminant analysis[J]. Energy and Buildings, 2016, 128: 519-529.
25	Li G, Hu Y, Chen H, et al. An improved fault detection method for incipient centrifugal chiller faults using the PCA-R-SVDD algorithm[J]. Energy and Buildings, 2016, 116: 104-113.
26	Srivastava N, Hinton G E, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15(1): 1929-1958.
27	Iyer A, Nath S, Sarawagi S. Maximum mean discrepancy for class ratio estimation: convergence bounds and kernel selection[C]// Proceedings of the 31st International Conference on Machine Learning. New York: PMLR, 2014: 530-538.
28	Rüschendorf L. The Wasserstein distance and approximation theorems[J]. Probability Theory and Related Fields, 1985, 70(1): 117-129.
29	Obukhov A, Krasnyanskiy M. Quality assessment method for GAN based on modified metrics inception score and Fréchet inception distance[C]//Proceedings of the Computational Methods in Systems and Software. Berlin: Springer, 2020: 102-114.
30	孙哲. 热泵系统亚健康及其智能在线诊断方法研究[D]. 杭州: 浙江工业大学, 2020.
	Sun Z. Study on the sub-health operation and its intelligent online diagnosis method for heat pump systems[D]. Hangzhou: Zhejiang University of Technology, 2020
31	Comstock M, Braun J. Development of analysis tools for the evaluation of fault detection and diagnostics in chillers [R]. West Lafayette, IN: Purdue University, 1999: 99-20.
32	Comstock M C, Braun J E, Groll E A. The sensitivity of chiller performance to common faults[J]. HVAC&R Research, 2001, 7(3): 263-279.

编辑推荐 0

Metrics

阅读次数

全文

302

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	15	19	0	268

来源	本网站	其他网站

次数	120	182
比例	40%	60%

摘要

526

最新录用	在线预览	正式出版

26	0	500

来源	本网站	其他网站

次数	237	289
比例	45%	55%

网络层	输出尺寸	参数数量
卷积层	(none, 9, 6, 32)	416
批归一化	(none, 9, 6, 32)	128
Dropout层	(none, 9, 6, 32)	0
卷积层	(none, 6, 5, 64)	16448
批归一化	(none, 6, 5, 64)	256
Dropout层	(none, 6, 5, 64)	0
卷积层	(none, 4, 4, 128)	49280
批归一化	(none, 4, 4, 128)	512
Dropout层	(none, 4, 4, 128)	0
Flatten层	(none, 2048)	0
全连接层	(none, 128)	262272
Softmax层	(none, 6)	774

网络层	输出尺寸	参数数量
卷积层	(none, 9, 6, 32)	416
批归一化	(none, 9, 6, 32)	128
Dropout层	(none, 9, 6, 32)	0
卷积层	(none, 6, 5, 64)	16448
批归一化	(none, 6, 5, 64)	256
Dropout层	(none, 6, 5, 64)	0
卷积层	(none, 4, 4, 128)	49280
批归一化	(none, 4, 4, 128)	512
Dropout层	(none, 4, 4, 128)	0
Flatten层	(none, 2048)	0
全连接层	(none, 128)	262272
Softmax层	(none, 6)	774

故障类别	Level1程度	Level2程度	Level3程度	Level4程度
冷凝器结垢（cf）	堵塞10%的换热管	堵塞20%的换热管	堵塞30%的换热管	堵塞40%的换热管
冷却水流量减少（fwc）	水流量减少10%	水流量减少20%	水流量减少30%	水流量减少40%
冷冻水流量减少（fwe）	水流量减少10%	水流量减少20%	水流量减少30%	水流量减少40%
含非凝性气体（nc）	含1%非凝性气体	含2%非凝性气体	含3%非凝性气体	含4%非凝性气体
制冷剂泄漏（rl）	泄漏10%制冷剂	泄漏20%制冷剂	泄漏30%制冷剂	泄漏40%制冷剂
制冷剂过充（ro）	过充10%制冷剂	过充20%制冷剂	过充30%制冷剂	过充40%制冷剂

故障类别	Level1程度	Level2程度	Level3程度	Level4程度
冷凝器结垢（cf）	堵塞10%的换热管	堵塞20%的换热管	堵塞30%的换热管	堵塞40%的换热管
冷却水流量减少（fwc）	水流量减少10%	水流量减少20%	水流量减少30%	水流量减少40%
冷冻水流量减少（fwe）	水流量减少10%	水流量减少20%	水流量减少30%	水流量减少40%
含非凝性气体（nc）	含1%非凝性气体	含2%非凝性气体	含3%非凝性气体	含4%非凝性气体
制冷剂泄漏（rl）	泄漏10%制冷剂	泄漏20%制冷剂	泄漏30%制冷剂	泄漏40%制冷剂
制冷剂过充（ro）	过充10%制冷剂	过充20%制冷剂	过充30%制冷剂	过充40%制冷剂

故障类别	TEI-TEO	TCO-TCI	PRE	PRC	TRC_sub	Tsh_suc	Tsh_dis
cf	●	↑	●	↑↑	●	●	●
fwc	●	↑↑↑	↑	↑↑	↑↑	↓	●
fwe	↑↑↑	●	↑	●	●	↓	●
nc	●	↑	↑	↑↑↑	↑↑↑↑	●	↑↑
rl	●	●	●	↓↓	↓↓↓	●	●
ro	●	?	↓	↑↑	↑↑↑	●	↑