Use of machine-learning for monitoring solar thermal plants

被引：0

作者：

Hofmann, Joachim Werner ^{[1
]}

Sitzmann, Bernd ^{[2
]}

Dickinson, John ^{[2
]}

Kunz, Dominique ^{[1
]}

Eismann, Ralph ^{[1
]}

机构：

[1] Univ Appl Sci & Arts Northwestern Switzerland, Inst Sustainabil & Energy Bldg INEB, Hofackerstr 30, CH-4132 Muttenz, Switzerland

[2] Energie Zukunft Schweiz AG, Viaduktstr 8, CH-4051 Basel, Switzerland

来源：

CARBON-NEUTRAL CITIES - ENERGY EFFICIENCY AND RENEWABLES IN THE DIGITAL ERA (CISBAT 2021) | 2021年 / 2042卷

关键词：

D O I：

10.1088/1742-6596/2042/1/012007

中图分类号：

TU [建筑科学];

学科分类号：

0813 ;

摘要：

A machine-learning algorithm (MLA) was developed to assess the operational state of solar thermal plants, based on the data of only one temperature sensor, and the irradiance and ambient temperature data from the nearest weather station. A detailed requirements analysis of the situation results in the classification of a multivariate time series problem. Neural networks used in the field of data science are ideally suited for problems of this type. Data from the operational monitoring system, which runs a rule-based algorithm, were used to train the neural network using the software framework TensorFlow. It was shown that the chosen MLA can detect malfunctions such as heat loss due to gravity-driven circulation during night. However, further development towards a practical tool requires not only far more data for training and validation. It became clear that corresponding pressure data are needed to classify temperature transients and to attribute these classes to certain malfunctions.

引用

页数：6

共 50 条

[41] Machine-learning the classification of spacetimes [J].

He, Yang-Hui ;

Ipina, Juan Manuel Perez .

PHYSICS LETTERS B, 2022, 832

[42] Machine Learning for Solar Array Monitoring, Optimization, and Control [J].

Rao S. ;

Katoch S. ;

Narayanaswamy V. ;

Muniraju G. ;

Tepedelenlioglu C. ;

Spanias A. ;

Turaga P. ;

Ayyanar R. ;

Srinivasan D. .

Synthesis Lectures on Power Electronics, 2020, 7 (01) :1-91

[43] Monitoring Solar Panels using Machine Learning Techniques [J].

Haba, Cristian-Gyozo .

PROCEEDINGS OF 2019 8TH INTERNATIONAL CONFERENCE ON MODERN POWER SYSTEMS (MPS), 2019,

[44] Machine-Learning Based Fault Monitoring System for Electric Vehicle Onboard Chargers [J].

Gaona Cardenas, Luis Fernando ;

Rodriguez Licea, Martin Antonio ;

Vazquez Nava, Nimrod .

2022 IEEE INTERNATIONAL AUTUMN MEETING ON POWER, ELECTRONICS AND COMPUTING (ROPEC), 2022,

[45] Comprehensive review of hydrothermal liquefaction data for use in machine-learning models [J].

Haarlemmer, Geert ;

Matricon, Lucie ;

Roubaud, Anne .

BIOFUELS BIOPRODUCTS & BIOREFINING-BIOFPR, 2024, 18 (05) :1782-1798

[46] Machine Learning for Testing Machine-Learning Hardware: A Virtuous Cycle [J].

Chaudhuri, Arjun ;

Talukdar, Jonti ;

Chakrabarty, Krishnendu .

2022 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER AIDED DESIGN, ICCAD, 2022,

[47] On the use of causal feature selection in the context of machine-learning indirect test [J].

Barragan, M. J. ;

Leger, G. ;

Cilici, F. ;

Lauga-Larroze, E. ;

Bourdel, S. ;

Mir, S. .

2019 DESIGN, AUTOMATION & TEST IN EUROPE CONFERENCE & EXHIBITION (DATE), 2019, :276-279

[48] Use of machine-learning algorithms to aid in the early detection of leptospirosis in dogs [J].

Reagan, Krystle L. ;

Deng, Shaofeng ;

Sheng, Junda ;

Sebastian, Jamie ;

Wang, Zhe ;

Huebner, Sara N. ;

Wenke, Louise A. ;

Michalak, Sarah R. ;

Strohmer, Thomas ;

Sykes, Jane E. .

JOURNAL OF VETERINARY DIAGNOSTIC INVESTIGATION, 2022, 34 (04) :612-621

[49] Detection of packaged and encrypted PE files with the use of machine-learning algorithm [J].

Gevorgyan, R. A. ;

Abramov, E. S. .

11TH INTERNATIONAL CONFERENCE ON SECURITY OF INFORMATION AND NETWORKS (SIN 2018), 2018,

[50] Comparative studies among machine learning models for performance estimation and health monitoring of thermal power plants [J].

Hundi, Prabhas ;

Shahsavari, Rouzbeh .

APPLIED ENERGY, 2020, 265

← 1 2 3 4 5 →