An evaluation method of health condition for wind turbine based on asymmetric proximity

Zhang, Haifeng; Xiu, Bingjie; Jiang, Dongxiao; Zhuang, Guanqun; Zhang, Yifu; Li, Benxin

doi:10.3389/fenrg.2023.1111355

Cited by 2 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The probabilistic approach for components' life estimation uses statistical models, such a method has been discussed in [12,13]. The deterministic approach uses physics-based models to estimate the life based on the degradation rate of the components such as the work done in [14]. The data-driven approach uses machine learning techniques to learn the degradation patterns from the sensor data [15].…”

Section: Introductionmentioning

confidence: 99%

Wind Turbine Optimal Preventive Maintenance Scheduling Using Fibonacci Search and Genetic Algorithm

Singh

Afshari

Liang

2023

JDMD

View full text Add to dashboard Cite

Maintenance scheduling is essential and crucial for wind turbines to avoid breakdowns and reduce maintenance costs. Many maintenance models have been developed for wind turbines' maintenance planning, such as corrective, preventive and predictive maintenance. Due to communities' dependence on wind turbines for electricity needs, preventative maintenance is the most widely used method for maintenance scheduling. The downside to using this approach is that preventive maintenance is often done in fixed intervals, which is inefficient. In this paper, a more detailed maintenance plan for a 2MW wind turbine has been developed. The paper's focus is to minimize a wind turbine's maintenance cost based on a wind turbine's reliability model. This study uses a two-layer optimization framework: Fibonacci and Genetic Algorithm (GA). The first layer in the optimization method (Fibonacci) finds the optimal number of preventive maintenance required for the system. In the second layer, the optimal times for preventative maintenance and optimal components to maintain have been determined to minimize maintenance costs. The Monte Carlo simulation estimates wind turbine component failure times using their lifetime distributions from the reliability model. The estimated failure times are then used to determine the overall corrective and preventive maintenance costs during the system's lifetime. Finally, an optimal preventive maintenance schedule is proposed for a 2MW wind turbine using the presented method. The method used in this paper can be expanded to a wind farm or similar engineering systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Wind Turbine Optimal Preventive Maintenance Scheduling Using Fibonacci Search and Genetic Algorithm

Singh

Afshari

Liang

2023

JDMD

View full text Add to dashboard Cite

show abstract

“…The monitoring signals for a hydraulic turbine system can be divided into pendulum, vibration type, pressure pulsation, and temperature type signals. In order to reflect the real operation of the unit and determine the reliability of the evaluation method, this study constructed a hierarchical analysis system according to the type of monitoring signals (Zhang et al, 2023), taking Unit 4 of a power plant as an example. This hydropower unit was divided into the three layers shown in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

Hydropower unit health assessment based on a combination weighting and improved fuzzy comprehensive evaluation method

Ke,

Wang,

Xiao

et al. 2023

Front. Energy Res.

View full text Add to dashboard Cite

The health state of hydroelectric power generation units is of great significance to ensure the stability and economy of safe operation of the power grid. In order to address the challenges in existing assessment methods of the insufficient reliability of the evaluation of multi-complex systems and the inability to reflect anomalies of a single index. A state evaluation model based on combination weighting and improved fuzzy comprehensive evaluation method is accordingly proposed. First, a hierarchical analysis system is constructed based on actual monitoring indicator data from the hydropower unit. Optimal comprehensive and indicator weights are subsequently obtained for each indicator level using a combination of the improved hierarchical analysis and CRICIT method through game theory. Next, the industry guidelines and regulations are difficult to effectively determine the limit values of each index of the unit, and they do not fully take into account the actual situation of the unit itself and the huge amount of accumulated historical health data. To address this issue. The Gaussian threshold method was proposed to determine the limit values of the monitoring data for each indicator, which more accurately determines the indicator thresholds as well as their standard values. The degradation degree of the hydroelectric unit can be calculated by comparing the real-time monitoring data with these limits. Finally, the combined weights of dynamic change and the fuzzy evaluation matrix are used to obtain the state evaluation matrix reflecting the condition of the turbine. The proposed approach is validated using the actual monitoring data and operating conditions for case study hydroelectric station, The results show that the improved evaluation method has an optimal evaluation effect.

show abstract

An evaluation method of health condition for wind turbine based on asymmetric proximity

Cited by 2 publications

References 31 publications

Wind Turbine Optimal Preventive Maintenance Scheduling Using Fibonacci Search and Genetic Algorithm

Wind Turbine Optimal Preventive Maintenance Scheduling Using Fibonacci Search and Genetic Algorithm

Hydropower unit health assessment based on a combination weighting and improved fuzzy comprehensive evaluation method

Contact Info

Product

Resources

About