Auto Tuning Algorithm for Vigilance Parameter in the Adaptive Resonance Theory Model and its Application to Fault Diagnosis System of Thermal Power Plants

Author(s):  
Takaaki Sekiai ◽  
Naohiro Kusumi ◽  
Yoshinari Hori ◽  
Satoru Shimizu ◽  
Masayuki Fukai

In order to operate thermal power plants safely, early detection of equipment failure signs is one of the most important issues. To detect the signs before an alarm is issued in the existing monitoring system, we developed a fault diagnosis system based on the Adaptive Resonance Theory (ART). The vigilance parameter, which is a design parameter in the ART model, was shown to influence the diagnosis accuracy. Fixing the value of the vigilance parameter also had problems: we needed to use time-consuming trial and error, and we needed to have empirical knowledge of the parameter tuning. In this paper, using simulations we demonstrated the relationship between the vigilance parameter and diagnosis accuracy. Furthermore, to overcome the problems of the vigilance parameter tuning, we have proposed an auto tuning algorithm to make the parameter the optimum value. The performance of the proposed algorithm was evaluated in several case studies using gas turbine plant data. The effectiveness of the proposed algorithm was confirmed by the obtained results.

2019 ◽  
Vol 118 ◽  
pp. 02064
Author(s):  
Guangyao Ma ◽  
shuai Zhang ◽  
Fanyang Meng

The key equipment of thermal power plants such as feed pump, condensate pump, circulating pump and induced draft fan, blower fan, oxidation fan, air preheater’s vibration information are monitored and tracked. Bearing failure accounted for the largest proportion. Problems such as misalignment and unbalance are still very common. Attention should be paid to the fault diagnosis and maintenance work.


Author(s):  
Xiao-Jin Wan ◽  
Licheng Liu ◽  
Zengbing Xu ◽  
Zhigang Xu

In this work, a soft competitive learning fuzzy adaptive resonance theory (SFART) diagnosis model based on multifeature domain selection for the single symptom domain and the single-target model is proposed. In order to solve the problem that the performance of traditional fuzzy ART (FART) is affected by the order of sample input, the similarity criterion of YU norm is introduced into the fuzzy ART network. In the meanwhile, the lateral inhibition theory is introduced to solve the wasteful problem of fuzzy ART mode node. By combining YU norm and lateral inhibition theory with fuzzy ART network, a soft competitive learning ART neural network diagnosis model that allows multiple mode nodes to learn simultaneously is designed. The feature parameters are extracted from the perspectives of time domain, frequency domain, time series model, wavelet analysis, and wavelet packet energy spectrum analysis, respectively. To further improve the diagnostic accuracy, the selective weighted majority voting method is integrated into the diagnosis model. Finally, the selected feature parameters are inputted to the integrated model to complete the fault classification and diagnosis. Finally, the proposed method is verified with a gearbox fault diagnosis test.


2019 ◽  
Vol 12 (1) ◽  
pp. 22-28
Author(s):  
V. Ye. Mikhailov ◽  
S. P. Kolpakov ◽  
L. A. Khomenok ◽  
N. S. Shestakov

One of the most important issues for modern domestic power industry is the creation and further widespread introduction of solid propellant energy units for super-critical steam parameters with high efficiency (43–46%) and improved environmental parameters. This will significantly reduce the use of natural gas.At the same time, one of the major drawbacks of the operation of pulverized coal power units is the need to use a significant amount of fuel oil during start-up and shutdown of boilers to stabilize the burning of the coal torch in the variable boiler operating modes.In this regard, solid fuel TPPs need to be provided with fuel oil facilities, with all the associated problems to ensure the performance (heating of fuel oil in winter), reliability and safety. All of the above problems increase both the TPP capital construction costs, and the electricity generating cost.A practical solution to the above problems at present is the use of a plasma technology for coal torch ignition based on thermochemical preparation of fuel for combustion. The materials of the developments of JSC “NPO CKTI” on application of plasmatrons in boilers of thermal power plants at metallurgical complexes of the Russian Federation are also considered.Plasma ignition systems for solid fuels in boilers were developed by Russian specialists and were introduced at a number of coal-fi red power plants in the Russian Federation, Mongolia, North Korea, and Kazakhstan. Plasma ignition of solid fuels is widely used in China for almost 30% of power boilers.The introduction of plasma-energy technologies will improve the energy efficiency of domestic solid-fuel thermal power plants and can be widely implemented in the modernization of boilers.During the construction of new TPPs, the construction of fuel oil facilities can be abandoned altogether, which will reduce the capital costs of the construction of thermal power plants, reduce the construction footprint, and increase the TPP safety.


Author(s):  
Ye. G. Polenok ◽  
S. A. Mun ◽  
L. A. Gordeeva ◽  
A. A. Glushkov ◽  
M. V. Kostyanko ◽  
...  

Introduction.Coal dust and coal fi ring products contain large amounts of carcinogenic chemicals (specifically benz[a]pyrene) that are different in influence on workers of coal mines and thermal power plants. Specific immune reactions to benz[a]pyrene therefore in these categories of workers can have specific features.Objective.To reveal features of antibodies specifi c to benz[a]pyrene formation in workers of coal mines and thermal power plants.Materials and methods.The study covered A and G class antibodies against benz[a]pyrene (IgA-Bp and IgG-Bp) in serum of 705 males: 213 donors of Kemerovo blood transfusion center (group 1, reference); 293 miners(group 2) and 199 thermal power plant workers (group 3). Benz[a]pyrene conjugate with bovine serum albumin as an adsorbed antigen was subjected to immune-enzyme assay.Results.IgA-Bp levels in the miners (Me = 2.7) did not differ from those in the reference group (Me = 2.9), but in the thermal power plant workers (Me = 3.7) were reliably higher than those in healthy men and in the miners (p<0.0001). Levels of IgG-Bp in the miners (Me = 5.0) appeared to be lower than those in the reference group (Me = 6.4; (p = 0.05). IgG-Bb level in the thermal power plantworkers (Me = 7.4) exceeded the parameters in the healthy donors and the miners (p<0.0001). Non-industrial factors (age and smoking) appeared tohave no influence on specific immune reactions against benz[a]pyrene in the miners and the thermal power plant workers.Conclusions.Specific immune reactions against benz[a]pyrene in the miners and the thermal power plant workers are characterized by peculiarities: the miners demonstrate lower levels of class A serum antibodies to benz[a]pyrene; the thermal power plant workers present increased serum levels of class G antibodies to benz[a]pyrene. These peculiarities result from only the occupational features, but do not depend on such factors as age, smoking and length of service at hazardous production. It is expedient to study specific immune reactions to benz[a]pyrene in workers of coal mines and thermal power plants, to evaluate individual oncologic risk and if malignancies occur.


2019 ◽  
Author(s):  
Matthias Schnellmann ◽  
David Reiner ◽  
Stuart Scott ◽  
Chi Kong Chyong

Sign in / Sign up

Export Citation Format

Share Document