scholarly journals Applications of predictive maintenance techniques in industrial systems

2011 ◽  
Vol 8 (3) ◽  
pp. 263-279 ◽  
Author(s):  
Aleksandra Marjanovic ◽  
Goran Kvascev ◽  
Predrag Tadic ◽  
Zeljko Djurovic

Prognostic methods represent a new methodology for system maintenance which offers significant time and cost savings. The paper offers a short overview of the available prognosis techniques and proposes the implementation of one model-based and one data-driven method. As a representative of the model-based methods the autoregressive moving average (ARMA) modeling approach is chosen. The estimated model parameters are further used for implementing the early change detector which is realized as a Neyman-Pearson hypothesis test. On the other hand, hidden Markov model (HMM) based prognosis illustrates the use of data-driven techniques. Using the cross-correlation input-output functions, HMM prognosis algorithm is proposed, as a suitable way of timely detection. Both techniques were implemented to detect performance changes of the water level sensor in a steam separator system in thermal power plants.

2021 ◽  
Vol 264 ◽  
pp. 04057
Author(s):  
Boboraim Urishev ◽  
Muradilla Mukhammadiev ◽  
Abdurauf Abduaziz uulu ◽  
Hojiakbar Murodov

Information about the problems arising from the uneven production and consumption of energy in power systems, including in the power system of the Republic of Uzbekistan, is given on the example of a daily electrical load schedule. It is noted that to successfully solve these problems, energy is accumulated in the hours of minimum consumption so that it can be used in peak hours with high consumption, and for this purpose, pumped storage power plants are used. A diagram of hydraulic energy storage is given at large pumping stations used to accumulate water in the upper reservoir in hours of minimum loads, and the accumulated volume of water is directed to generate energy, which can be used by pumping stations to supply additional water to its consumers, replenishing its losses in hours of hydraulic energy storage. The method of selection and optimization of the main parameters of this complex, based on minimizing fuel consumption in power plants while limiting the amount of accumulated energy based on the capabilities of water and energy resources of pumping stations, is presented. The calculations using the example of the Syrdarya thermal power plant show that with the integration of five nearby pumping stations into the process of energy storage and generation, significant cost savings are achieved, and the daily load schedule is significantly leveled.


Sensors ◽  
2020 ◽  
Vol 20 (8) ◽  
pp. 2425 ◽  
Author(s):  
Jonas Fausing Olesen ◽  
Hamid Reza Shaker

Thermal power plants are an important asset in the current energy infrastructure, delivering ancillary services, power, and heat to their respective consumers. Faults on critical components, such as large pumping systems, can lead to material damage and opportunity losses. Pumps plays an essential role in various industries and as such clever maintenance can ensure cost reductions and high availability. Prognostics and Health Management, PHM, is the study utilizing data to estimate the current and future conditions of a system. Within the field of PHM, Predictive Maintenance, PdM, has been gaining increased attention. Data-driven models can be built to estimate the remaining-useful-lifetime of complex systems that would be difficult to identify by man. With the increased attention that the Predictive Maintenance field is receiving, review papers become increasingly important to understand what research has been conducted and what challenges need to be addressed. This paper does so by initially conceptualising the PdM field. A structured overview of literature in regard to application within PdM is presented, before delving into the domain of thermal power plants and pump systems. Finally, related challenges and trends will be outlined. This paper finds that a large number of experimental data-driven models have been successfully deployed, but the PdM field would benefit from more industrial case studies. Furthermore, investigations into the scale-ability of models would benefit industries that are looking into large-scale implementations. Here, examining a method for automatic maintenance of the developed model will be of interest. This paper can be used to understand the PdM field as a broad concept but does also provide a niche understanding of the domain in focus.


2021 ◽  
Author(s):  
Jiangkuan Li ◽  
Meng Lin

Abstract With the development of artificial intelligence technology, data-driven methods have become the core of fault diagnosis models in nuclear power plants. Despite the advantages of high flexibility and practicability, data-driven methods may be sensitive to the noise in measurement data, which is inevitable in the process of data measurement in nuclear power plants, especially under fault conditions. In this paper, a fault diagnosis model based on Random Forest (RF) is established. Firstly, its diagnostic performance on noiseless data and noisy data set containing 13 operating conditions (one steady state condition and 12 fault conditions) is analyzed, which shows that the model based on RF has poor robustness under noisy data. In order to improve the robustness of the model under noisy data, a method named ‘Train with Noisy Data’ (TWND) is proposed, the results show that TWND method can effectively improve the robustness of the model based on RF under noisy data, and the degree of improvement is related to the noise levels of added noisy data. This paper can provide reference for robustness analysis and robustness improvement of nuclear power plants fault diagnosis models based on other data-driven methods.


2020 ◽  
pp. 188-188
Author(s):  
Martin Bricl ◽  
Jurij Avsec

The article presents the model for the rehabilitation of existing conventional thermal power plants in order to lower the consumption of fossil fuels. Instead of them, the model uses an alternative energy source - sun irradiation. The proposed rehabilitation model is theoretically calculated and designed. The model in the software environment Matlab Simulink was developed, based on previous calculations and determined parameters. In this article, it is presented the combination of Clausius - Rankine process and solar central receiver system. The model enables simultaneous calculations of exit model parameters for the complete model, based on predetermined entering parameters of the model.


Energies ◽  
2018 ◽  
Vol 11 (4) ◽  
pp. 690 ◽  
Author(s):  
Yongping Yang ◽  
Xiaoen Li ◽  
Zhiping Yang ◽  
Qing Wei ◽  
Ningling Wang ◽  
...  

Author(s):  
Jaewon Choi ◽  
Mohsen Nakhaeinejad ◽  
Michael D. Bryant

This study illustrates a data driven system identification method for loudspeaker model estimation using the knowledge of the underlying physics of loudspeakers. In this study, diaphragm displacement is analyzed to estimate the model structure and parameters based on impulse response equivalent sampling and autoregressive moving average model. The estimated loudspeaker models are compared in the frequency response function plot. It is shown that the autoregressive moving average (ARMA) based loudspeaker models are comparable to the model estimated by the conventional method based on electrical impedance. Also ARMA modeling strategies with and without knowledge of the physics-based model are compared. Some issues related to ARMA modeling are addressed.


2010 ◽  
Vol 7 (2) ◽  
pp. 231-252 ◽  
Author(s):  
Slobodan Vukosavic ◽  
Nikola Popov ◽  
Zeljko Despotovic

Thermal power stations emit significant amounts of fly ash and ultra fine particles into the atmosphere. Electrostatic precipitators (ESP) or electro filters remove flying ashes and fine particles from the flue gas before passing the gas into the chimney. Maximum allowable value of dust is 50 mg/m3 and it requires that the efficiency of the ESPs better than 99 %, which calls for an increase of active surface of the electrodes, hence increasing the filter volume and the weight of steel used for the filter. In previous decades, electrostatic precipitators in thermal power plants were fed by thyristor controlled, single phase fed devices having a high degree of reliability, but with a relatively low collection efficiency, hence requiring large effective surface of the collection plates and a large weight of steel construction in order to achieve the prescribed emission limits. Collection efficiency and energy efficiency of the electrostatic precipitator can be increased by applying high frequency high voltage power supply (HF HV). Electrical engineering faculty of the University of Belgrade (ETF) has developed technology and HF HV equipment for the ESP power supply. This solution was subjected to extensive experimental investigation at TE Morava from 2008 to 2010. High frequency power supply is proven to reduce emission two times in controlled conditions while increasing energy efficiency of the precipitator, compared to the conventional thyristor controlled 50Hz supply. Two high frequency high voltage unit AR70/1000 with parameters 70 kV and 1000 mA are installed at TE Morava and thoroughly testes. It was found that the HF HV power supply of the ESP at TE Morava increases collection efficiency so that emission of fine particles and flying ashes are halved, brought down to only 50 % of the emissions encountered with conventional 50 Hz thyristor driven power supplies. On the basis of this study, conclusion is drawn that the equipment comprising HF HV supplies are the best solution for new ESP installations, as well as for the reconstruction of existing facilities. The paper describes the topology of the HF HV power supply, power management and controls, and brings the most important details of the implementation. It is found that the HF HV solution achieves several significant improvements over the conventional thyristor system. It is possible to provide more precise control of the ESP parameters such as the output voltages and currents. It is also possible to make a rapid increase or decrease in voltage and to effectuate a very fast response to load changes. Due to this advantages it is possible to suppress the supply quickly in the case of sparking, reducing the spark energy and the quantity of ionized gasses produced by the electric arc. Reduction in the spark energy is up to 10 times compared to conventional thyristors solution. This means that the erosion of the electrode system is significantly reduced, and that the quality of the collection plates is preserved for much longer periods. At the same time, lower quantity of ionized gasses produced by the spark contribute to much shorter deionization intervals, required to quit sparking and evacuate charged particles in order to reinstate the voltage and proceed with the operation. In addition, HF HV power supply provides a significant reduction in size and weight of the complete ESP installation, hence reducing the tons of steel that has to be built in. Therefore, the HF HV power supply may be the key instrument to reducing the cost of the dedusting ecological equipment. Besides, size and weight reduction leads to cost savings of installation and maintenance. According to estimates, savings in steel may reach 30%, contributing to the overall cost savings of roughly 20%. Within this paper, in addition to describing the AR70/1000 unit topology and principles of operation, the paper presents the results and measurements obtained during extensive experimental investigations wherein performances of 50 Hz based thyristor units with T/R sets are compared to HF HV power supply.


Sign in / Sign up

Export Citation Format

Share Document