scholarly journals Machine Learning-Based Condition Monitoring for PV Systems: State of the Art and Future Prospects

Energies ◽  
2021 ◽  
Vol 14 (19) ◽  
pp. 6316
Author(s):  
Tarek Berghout ◽  
Mohamed Benbouzid ◽  
Toufik Bentrcia ◽  
Xiandong Ma ◽  
Siniša Djurović ◽  
...  
Keyword(s):  
Machine Learning ◽  
Electric Power ◽  
Condition Monitoring ◽  
Failure Modes ◽  
Generative Models ◽  
Operating Conditions ◽  
Detection Methods ◽  
Photovoltaic Systems ◽  
Pv Systems ◽  
Maintenance Program

To ensure the continuity of electric power generation for photovoltaic systems, condition monitoring frameworks are subject to major enhancements. The continuous uniform delivery of electric power depends entirely on a well-designed condition maintenance program. A just-in-time task to deal with several naturally occurring faults can be correctly undertaken via the cooperation of effective detection, diagnosis, and prognostic analyses. Therefore, the present review first outlines different failure modes to which all photovoltaic systems are subjected, in addition to the essential integrated detection methods and technologies. Then, data-driven paradigms, and their contribution to solving this prediction problem, are also explored. Accordingly, this review primarily investigates the different learning architectures used (i.e., ordinary, hybrid, and ensemble) in relation to their learning frameworks (i.e., traditional and deep learning). It also discusses the extension of machine learning to knowledge-driven approaches, including generative models such as adversarial networks and transfer learning. Finally, this review provides insights into different works to highlight various operating conditions and different numbers and types of failures, and provides links to some publicly available datasets in the field. The clear organization of the abundant information on this subject may result in rigorous guidelines for the trends adopted in the future.

scholarly journals Analysis of Residual Current Flows in Inverter Based Energy Systems Using Machine Learning Approaches

Energies ◽  
2022 ◽  
Vol 15 (2) ◽  
pp. 582
Author(s):  
Holger Behrends ◽  
Dietmar Millinger ◽  
Werner Weihs-Sedivy ◽  
Anže Javornik ◽  
Gerold Roolfs ◽  
...  
Keyword(s):  
Machine Learning ◽  
Early Stage ◽  
Residual Current ◽  
Operating Conditions ◽  
Machine Learning Algorithms ◽  
Photovoltaic System ◽  
Detection Methods ◽  
Learning Approaches ◽  
Residual Currents ◽  
Current Flows

Faults and unintended conditions in grid-connected photovoltaic systems often cause a change of the residual current. This article describes a novel machine learning based approach to detecting anomalies in the residual current of a photovoltaic system. It can be used to detect faults or critical states at an early stage and extends conventional threshold-based detection methods. For this study, a power-hardware-in-the-loop approach was carried out, in which typical faults have been injected under ideal and realistic operating conditions. The investigation shows that faults in a photovoltaic converter system cause a unique behaviour of the residual current and fault patterns can be detected and identified by using pattern recognition and variational autoencoder machine learning algorithms. In this context, it was found that the residual current is not only affected by malfunctions of the system, but also by volatile external influences. One of the main challenges here is to separate the regular residual currents caused by the interferences from those caused by faults. Compared to conventional methods, which respond to absolute changes in residual current, the two machine learning models detect faults that do not affect the absolute value of the residual current.

Study of Photovoltaic Systems’ Performances with Different Module Types

2016 ◽  
Vol 856 ◽  
pp. 279-284 ◽  
Author(s):  
Zahari Zarkov ◽  
Ludmil Stoyanov ◽  
Hristiyan Kanchev ◽  
Valentin Milenov ◽  
Vladimir Lazarov
Keyword(s):  
Theoretical Study ◽  
Weather Conditions ◽  
Operating Conditions ◽  
Experimental Results ◽  
Photovoltaic Systems ◽  
Experimental Site ◽  
Pv Systems ◽  
Research Platform ◽  
Pv Modules ◽  
Different Types

The purpose of the work is to study and compare the performance of photovoltaic (PV) generators built with different types of panels and operating in real weather conditions. The paper reports the results from an experimental and theoretical study of systems with PV modules manufactured according to different technologies and using different materials. The experiment was carried out at a research platform for PV systems developed by the authors, built and located at an experimental site near the Technical University of Sofia. Based on the obtained results, comparisons are made between the different PV generators for the same operating conditions. The comparison between the theoretical and the experimental results demonstrates a good level of overlap.

scholarly journals Machine Learning for Photovoltaic Systems Condition Monitoring: A Review

2021 ◽  
Author(s):  
Tarek Berghout ◽  
Mohamed Benbouzid ◽  
Xiandong Ma ◽  
Sinisa Djurovic ◽  
Leila-Hayet Mouss
Keyword(s):  
Machine Learning ◽  
Condition Monitoring ◽  
Photovoltaic Systems

Optimizing Rotating Equipment Maintenance Through Machine Learning Algorithm

2021 ◽  
Author(s):  
Francesco Beduschi ◽  
Fabio Turconi ◽  
Basso De Gregorio ◽  
Francesca Abbruzzese ◽  
Annagiulia Tiozzo ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Failure Modes ◽  
Learning Algorithm ◽  
Principal Component ◽  
Fault Isolation ◽  
Operating Conditions ◽  
Equipment Maintenance ◽  
Predictive Tool ◽  
Rotating Equipment

Abstract This work highlights the development and results of a Rotating equipment predictive maintenance tool that allows to monitor the status of rotating machines through a synthetic "health index" and early detection of anomalies. The data-driven proposed solution is of great help to maintenance engineers, who, alongside the existing methodologies, can apply an effective tool based on artificial intelligence for early prevention of failures. Taking advantage of the high availability of remote sensors data, an anomaly detection machine learning model, which relies on Principal Component Analysis (PCA) and Kernel Density Estimation (KDE), has been built. This model is capable of estimating, in real time, the health status of the machine, by matching the sensors actual values with the reference ones based on the Normal Operating Conditions (NOC) periods, that have been previously identified. If an anomalous behavior is detected, the Fault Isolation step of the model allows to evaluate which are the most contributing sensors for the investigated anomaly. These outcomes, combined with a failure mode matrix, which links the sensors deviations with the possible malfunctions, allows to highlight the most likely failure modes to be associated to the investigated anomaly. The developed predictive tool has been implemented on operating sites and it has demonstrated the capability to generate accurate warnings and detect anomalies to be processed by the maintenance engineers. These alerts may be aggregated into events in order to be monitored and analyzed by remote and on site specialists. The availability of alerts gives to the users the possibility to predict any deterioration of the machines or process fluctuations, that could lead to unplanned events with consequent mechanical breakdowns, production losses and flaring events. As a consequence, tailored operative adjustment to prevent critical events can be taken. Thanks to the tool, it is also possible to monitor over time the equipment behavior in order to provide suggestions for maintenance plans optimization and other useful statistics concerning the most recurrent failure. The tool's innovative feature is the ability to utilize the giant amount of data and to reproduce complex field phenomena by means of artificial intelligence. The proposed tool represents an innovative predictive approach for rotating equipment maintenance optimization.

scholarly journals Blind Application of Developed Smart Vibration-Based Machine Learning (SVML) Model for Machine Faults Diagnosis to Different Machine Conditions

2020 ◽  
Author(s):  
Natalia F. Espinoza Sepúlveda ◽  
Jyoti K. Sinha
Keyword(s):  
Machine Learning ◽  
Fault Diagnosis ◽  
Condition Monitoring ◽  
Operating Conditions ◽  
Machine Vibration ◽  
Identical Machines ◽  
Vibration Responses ◽  
Faults Diagnosis ◽  
Diagnosis Model ◽  
Machine Speed

Abstract Purpose The development and application of intelligent models to perform vibration-based condition monitoring in industry seems to be receiving attention in recent years. A number of such research studies using the artificial intelligence, machine learning, pattern recognition, etc., are available in the literature on this topic. These studies essentially used the machine vibration responses with known machine faults to develop smart fault diagnosis models. These models are yet to be tested for all kinds of machine faults and/or different operating conditions. Therefore, the purpose is to develop a generic machine faults diagnosis model that can be applied blindly to any identical machines with high confidence level in accuracy of the predictions. Methods In this paper, a supervised smart fault diagnosis model is developed. This model is developed using the available measured vibration responses for the different rotor faults simulated on an experimental rotating rig operating at a constant speed. The developed smart vibration-based machine learning (SVML) model is then blindly tested to identify the healthy and faulty conditions of the rig when operating at different speeds. Results and conclusions Several scenarios are proposed and examined during the development of the SVML model. It is observed that scenario of the vibration measurements simultaneously from all bearings from a machine is capable to fully map the machine dynamics in the VML model. Therefore, this developed when applied blindly to the sets of data at a different machine speed, the results are observed to be encouraging. The results clearly show a possibility for a centralised vibration-based condition monitoring (CVCM) model for identical machines operating at different rotating speeds.

A Data-Driven Approach for Condition Monitoring of Reciprocating Compressor Valves

2013 ◽  
Vol 136 (4) ◽  
Author(s):  
Christopher J. Guerra ◽  
Jason R. Kolodziej
Keyword(s):  
Condition Monitoring ◽  
Frequency Analysis ◽  
Failure Modes ◽  
Bayes Theorem ◽  
Data Driven ◽  
Detection Methods ◽  
Reciprocating Compressor ◽  
Valve Seat ◽  
Data Driven Approach ◽  
High Degree

This paper focuses on condition-monitoring of three different valve failure modes common in reciprocating compressors. They are missing valve poppets, valve spring fatigue, and valve seat wear. First, a targeted instrumentation study is performed on a Dresser–Rand ESH-1 industrial reciprocating compressor to investigate detection methods for these failures. This is followed by the development of a novel health classification methodology based on frequency analysis and Bayes theorem. The method is shown to successfully classify the condition of the valves to a high degree of accuracy when applied to actual seeded valve faults in the compressor.

scholarly journals Condition monitoring of wind turbines using machine learning based anomaly detection and statistical techniques for the extraction of 'healthy data'

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Xavier Chesterman ◽  
Timothy Verstraeten ◽  
Pieter-Jan Daems ◽  
Jan Helsen
Keyword(s):  
Machine Learning ◽  
Anomaly Detection ◽  
Condition Monitoring ◽  
Wind Turbines ◽  
Operating Conditions ◽  
Training Data ◽  
Series Data ◽  
Statistical Techniques ◽  
Monitoring Method ◽  
One Year

Premature failures caused by excessive wear are responsible for a large fraction of the maintenance costs of wind turbines. Therefore, it is crucial to be able to identify the propagation of these failures as early as possible. To this end, a novel condition monitoring method is proposed that uses statistical data analysis techniques and machine learning to construct a multivariate anomaly detection framework, based on high-frequency temperature SCADA data from wind turbines. This framework contains several steps. First, there is a preprocessing step in which relevant wind turbine states are extracted from the data. These states are the operating conditions and whether or not the turbine exhibits transient behavior. The second step entails anomaly detection on the temperature time series data. Fleet information is used to filter out exogenous (environmental) factors. Furthermore, multiple models are combined to get more stable and robust anomaly detections. By combining them the weaknesses of the individual models are alleviated resulting in a better overall performance. A limitation of machine learning-based anomaly detection on temperature data is the requirement that at least one year of “healthy” (meaning without anomalies) training data is available to account for seasonal effects. The lack of verified “healthy” data spread out evenly over the seasons generally means that the anomaly detection accuracy is severely compromised for the unrepresented seasons. This research uses smart retraining to reduce this limitation. Statistical techniques that leverage the information of the fleet are used to extract “healthy” data from at least one year, but preferably multiple years, of unverified data. This can then be used as training data for the machine learning-based models. To validate the pipeline, temperature and failure data of a real operational wind farm is used. Although the methodology is general in its scope, the validation case focusses specifically on generator bearing failures.

scholarly journals Developing a 3D decision-making grid based on failure modes and effects analysis with a case study in the steel industry

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Arash Shahin ◽  
Ashraf Labib ◽  
Ali Haj Shirmohammadi ◽  
Hadi Balouei Jamkhaneh
Keyword(s):  
Decision Making ◽  
Condition Monitoring ◽  
Detection Rate ◽  
Failure Modes ◽  
Failure Detection ◽  
Operating Conditions ◽  
Content Type ◽  
Casting Unit ◽  
Third Dimension

PurposeThe aim of this study is to develop a 3D model of decision- making grid (DMG) considering failure detection rate.Design/methodology/approachIn a comparison between DMG and failure modes and effects analysis (FMEA), severity has been assumed as time to repair and occurrence as the frequency of failure. Detection rate has been added as the third dimension of DMG. Nine months data of 21 equipment of casting unit of Mobarakeh Steel Company (MSC) has been analyzed. Then, appropriate condition monitoring (CM) techniques and maintenance tactics have been suggested. While in 2D DMG, CM is used when downtime is high and frequency is low; its application has been developed for other maintenance tactics in a 3D DMG.FindingsFindings indicate that the results obtained from the developed DMG are different from conventional grid results, and it is more capable in suggesting maintenance tactics according to the operating conditions of equipment.Research limitations/implicationsIn failure detection, the influence of CM techniques is different. In this paper, CM techniques have been suggested based on their maximum influence on failure detection.Originality/valueIn conventional DMG, failure detection rate is not included. The developed 3D DMG provides this advantage by considering a new axis of detection rate in addition to mean time to repair (MTTR) and failure frequency, and it enhances maintenance decision-making by simultaneous selection of suitable maintenance tactics and condition-monitoring techniques.

scholarly journals Fault diagnosis with states estimation in PV systems

2021 ◽  
Author(s):  
Ramiro Alejandro Plazas Rosas ◽  
Édinson Franco Mejia ◽  
Martha Lucía Orozco Gutiérrez
Keyword(s):  
Fault Diagnosis ◽  
Electricity Generation ◽  
Power Converter ◽  
Operating Conditions ◽  
Photovoltaic Systems ◽  
Pv System ◽  
Interconnected System ◽  
Pv Systems ◽  
A Cell ◽  
Mechanical Elements

The photovoltaic systems are electrical, electronic, and mechanical elements. These systems also face different environmental and operating conditions susceptible to failure. In addition, photovoltaic systems can be the only source of electricity generation, and an affectation on the energy supply can harm the community. In many places, photovoltaic systems are the only source of energy because they are not part of what is known in Colombia as the National Interconnected System (SIN). Which comprises the direct connection between large generators (hydroelectric and/or thermal plants) and consumers. In fact, PV system damage would affect food refrigeration or everyday things like charging a cell phone. Therefore, it is necessary to register, monitor the operation elements of PV systems, and develop strategies that allow the diagnosis to detect faults. In this work, we propose a fault-diagnosis using the PV systems measurements that is, power converter, photovoltaic panels with also mathematical models to determine the deviation between the estimated and measured signals as voltages and currents.

scholarly journals Advanced PV Performance Modelling Based on Different Levels of Irradiance Data Accuracy

Energies ◽  
2020 ◽  
Vol 13 (9) ◽  
pp. 2166 ◽  
Author(s):  
Julián Ascencio-Vásquez ◽  
Jakob Bevc ◽  
Kristjan Reba ◽  
Kristijan Brecl ◽  
Marko Jankovec ◽  
...  
Keyword(s):  
Machine Learning ◽  
Weather Conditions ◽  
Empirical Models ◽  
Operating Conditions ◽  
Data Accuracy ◽  
Temperate Climate ◽  
Energy Yield ◽  
Pv Systems ◽  
Light Gradient ◽  
Irradiance Data

In photovoltaic (PV) systems, energy yield is one of the essential pieces of information to the stakeholders (grid operators, maintenance operators, financial units, etc.). The amount of energy produced by a photovoltaic system in a specific time period depends on the weather conditions, including snow and dust, the actual PV modules’ and inverters’ efficiency and balance-of-system losses. The energy yield can be estimated by using empirical models with accurate input data. However, most of the PV systems do not include on-site high-class measurement devices for irradiance and other weather conditions. For this reason, the use of reanalysis-based or satellite-based data is currently of significant interest in the PV community and combining the data with decomposition and transposition irradiance models, the actual Plane-of-Array operating conditions can be determined. In this paper, we are proposing an efficient and accurate approach for PV output energy modelling by combining a new data filtering procedure and fast machine learning algorithm Light Gradient Boosting Machine (LightGBM). The applicability of the procedure is presented on three levels of irradiance data accuracy (low, medium, and high) depending on the source or modelling used. A new filtering algorithm is proposed to exclude erroneous data due to system failures or unreal weather conditions (i.e., shading, partial snow coverage, reflections, soiling deposition, etc.). The cleaned data is then used to train three empirical models and three machine learning approaches, where we emphasize the advantages of the LightGBM. The experiments are carried out on a 17 kW roof-top PV system installed in Ljubljana, Slovenia, in a temperate climate zone.

Sign in / Sign up

Export Citation Format

Share Document