CC BY
7УДК 621 317
Butayev S.I.
doctoral student Azerbaijan State University of Oil and Industry (Baku, Azerbaijan)
GENERATOR MONITORING SYSTEM BASED ON FUZ ZY LOGIC
Abstract: continuous and reliable transmission of electric energy to users and the reliable and stable operation of the electric power system depend on the flawless operation of generators, which are one of the most important elements and are of great importance in power plants. Studies show that despite the existence of a large number of monitoring methods used in the evaluation of the technical condition of generators on a real-time basis in modern times, they create certain limits in the evaluation of some parts or parameters. Thus, the failure of generators can lead to the occurrence of accidents, interruption of electricity supply, disruption of the work functions of the equipment, and the occurrence of situations accompanied by significant economic and environmental damages. This shows that the issue of evaluating the technical condition of generators continues to be an actual issue, as it was before. The main goal of the article is to analyze the modern methods and means of real-time assessment of the technical condition of generators, which are one of the most important research objects of the electric power system.
Keywords: generator, monitoring, accident, diagnostics, unplanned breakdowns, fault detection, real-time monitoring partial discharges.
As we know, the continuous, reliable and efficient operation of the electrical system is one of the main requirements. However, it has been discovered over the years that certain accidents and injuries can occur for reasons beyond the control of the working personnel, due to poor assembly or equipment not meeting the requirements. These damages, in turn, cause a violation of the reliability requirements imposed on the electrical system. 10-20% of such damages are unexpected, even though they occur directly, and 70-80% are caused by the effects of hidden malfunctions in the equipment
for a long time. The main issue before us is to prevent long-term breakdowns in power plants from causing bigger accidents. For this, we must constantly monitor the normal processes in the equipment and the warning or accident situations that may occur in order to detect the damage that may occur in the power equipment at that moment. Constant online monitoring of power plants is one of the important factors to prevent major accidents from occurring.
Electric generators are the most responsible for damage and interruptions in the general electrical system. Since generators are at the first and upper level of electricity generation, any failure that may occur in them directly affects all the devices fed by that generator. In order to prevent damage to generators from the beginning, we must first know the faults that may occur in generators and the severity of these faults.
Based on the observations made during the last 5 years, we can say that the percentages of damage to generators are within the limits shown in the graph below (Figure 1) [4].
Figure 1. Cause of generator failure
Calculating the severity of each problem detected has a direct impact on the assessment of that problem and the time it takes to fix it. This is called risk analysis, which is calculated based on the following formula. The main parameters considered in the formula are the intervals of occurrence of failures (for example: frequent, in
between, sometimes, etc.) and the level of possible losses (for example: insignificant, medium, high, critical).
Risk is (Probability of an accident) * (Losses per accident)
From the interaction of Probability of an accident and Losses per accident, the level of failure is evaluated in 3 ways: high, medium and low.
LOSSES PROBABILITY 1
often likely occasional srnatl negligible
catastrophic DI S В
critica! Б В В
medium В В Г
negligible В
A-high risk — high priority B - medium risk —* medium priority C - low risk — low priority
Real-time monitoring systems should be implemented in generators to detect the problems listed above in time and determine the severity level by analyzing the risk of the detected failure.
Some manufacturers think that the costs of implementing a monitoring system are high and insignificant [6]. However, due to unplanned accidents, the failure of one component can lead to the failure of other components, resulting in the need for more complex and long-term repairs, while the additional costs incurred and the cost of production losses due to interruptions in power generation during idle periods are more than the cost of the monitoring system there are many. Another disadvantage of waiting for machinery to break down is that it can be more expensive to restore it to perfect working condition than to maintain it with systematic and planned measures. With all of this in mind, it can be said that some manufacturers should view their monitoring system costs as an investment rather than a loss. Both materially and taking into
account interruptions in electricity production, the application of monitoring systems is more efficient and appropriate for the purpose.
The application of monitoring systems in the electrical system leads to the following
Reducing unplanned breakdowns or downtime Extending the normal working time of machines Minimizing major equipment problems Reducing the time of fault detection and elimination Reducing repair costs Increasing reliability.
As a basis for predictive maintenance, condition monitoring extracts system health information from the measured condition, and based on this information, future maintenance needs can be predicted.
Its purpose is to detect and track developing faults and predict upcoming failures and possible failures. Thus, maintenance can be planned in time to avoid additional costs and optimize the operation. The most commonly used techniques in Condition Monitoring include vibration monitoring, process parameter monitoring, visual inspection, tribology and thermography. Other types of tracking systems implemented so far have some limitations and disadvantages. Vibration monitoring is manifested in the event of certain vibrations in the generator shaft exceeding the normal limit of damage within the generator. Process parameter monitoring only shows us two types of measurements, minimum and maximum, for the measured parameters and whether it is good or bad based on that measurement. By means of visual inspection, we almost cannot see the malfunctions occurring inside the generator. This is only useful to us if there is physical damage or crushes to the outside of the generator.
It is more appropriate to use a fuzzy logic-based tracking system to detect some faults that cannot be detected by other types of tracking systems. Fuzzy logic gives us more tracking range and more options for parameters.
In order to perform real-time monitoring based on fuzzy logic, we can monitor partial discharge, shaft vibration, temperature, load control, etc. inside the turbogenerator. we install the sensors (Figure 2).
Figure 2. Sensors on the generator
During the normal working process of the turbogenerator, processes are carried out between the sensors and the general controller based on the algorithm shown in the following figure (Figure 3).
!f perforai**:» a SOT xomç lb*
f H^wfd коис)|'
ш
Figure 3. Data collection and analysis algorithm
According to the new method, we put a general controller for the generator. That controller is programmed according to the parameters to be received (Figure 4). Programming is done according to nominal values and provides step-by-step intervention processes according to releasable thresholds. The controller, which receives the necessary information from different parts of the generator, evaluates the parameters according to the pre-programmed limits. In case of deviations from the measurement range, the controller warns on the first level that the values are less or more than the nominal, on the second level, when the values are close to the permissible limits, the controller warns it as a serious fault, and the last level is to prevent the generator from breaking down if it is not intervened within the required time turns itself off automatically [13].
Figure 4. Monitoring process in gas turbines
By applying fuzzy logic, we not only turn our equipment off and on due to a fault, but also provide different levels of tracking and impact based on input parameters.
CONCLUSIONS
This article includes suggestions for monitoring and correcting faults that may occur in turbogenerators. During real-time target monitoring, the measurement limits of the monitored parameters are not minimum and maximum, but more levels between the minimum and maximum limit by applying fuzzy logic, faster control of the generator, which will only monitor the parameters that tend to be determined, rather than alerting after the identification of the equipment. makes it possible to achieve the growth of the scope of the problem.
СПИСОК ЛИТЕРАТУРЫ:
1. Neill, G. D., Reuben, R. L., Sandford, P. M., Brown, E. R. and Steel, J. A. Detection of incipient cavitation in pumps using acoustic emission. Proc. IMechE: Part E, vol. 211 (4), 1997, 267-277.;
2. Gill, J. D., Reuben, R. L., Steel, J. A., Scaife, M. W. and Asquith, J. A study of small HSDI diesel engine fuel injection equipment faults using acoustic emission. Journal of Acoustic Emission, vol. 18, 2000, 211-216.;
3. Li, C. J. and Li, S. Y. Acoustic emission analysis for bearing condition monitoring. Wear, vol. 185, 1995, 67-74.;
4. Armor, A. F., Graham, L. J. and Frank, R. L. Acoustic emission monitoring of steam turbines. Joint ASME/IEEE Power Generation Conference, Oct 4-8, 1981, St. Louis, USA.;
5. Sato, I, Rotating machinery diagnosis with acoustic emission techniques. Electrical Engineering in Japan, vol. 100 (2), 1990, 115-127.;
6. Board, D. B. Stress wave analysis of turbine engine faults. Proc. IEEE Aerospace Conference, vol. 6, 2000, 79-95.;
7. Bates, J. and Webster, J. Engine development application for monitoring turbine seals in a Rolls-Royce RB211-524 G/H gas turbine, in The Acoustic Emission & Ultrasonics Monitoring Handbook. Editor: Holroyd, T. J., Coxmoor, 1st Edition, 2000, 91-93.;
8. Mba, D. and Hall L. D. The transmission of acoustic emission across large-scale turbine rotors. NDT&E International, vol. 35 (8), 2002, 529-539.;
9. Hall, L. D. and Mba, D. Diagnosis of continuous rotor-stator rubbing in large scale turbine units using acoustic emissions. Ultrasonics, vol. 41 (9), 2004, 765-783.;
10. Hall, L. D. and Mba, D. Acoustic emissions diagnosis of rotor-stator rubs using the KS statistic. Mechanical Systems and Signal Processing, vol 18 (4), 2004, 849868.;
11. Zuluaga-Giraldo, C., Mba, D. and Smart, M. Acoustic emission during run-up and rundown of a power generation turbine. Tribology International, vol. 37 (5), 2004, 415-422.;
12. Muthuraman, S., Twiddle, J., Singh, M., Connolly, N., "Condition monitoring of SSE gas turbines using artificial neural networks. Insight Non-Destructive Test", Condition Monitoring, 54: 436-439, (2012).;
13. Gas Turbine Performance Monitoring and Operation Challenges: A Review. GU J Sci 36(1): 154-171 (2023)
