A Fault Diagnosis Method of Oil-Immersed Transformer Based on Improved Harris Hawks Optimized Random Forest

Yi, Lingzhi; Jiang, Ganlin; Zhang, Guoyong; Yu, Wenxin; Guo, You; Sun, Tao

doi:10.1007/s42835-022-01036-z

Cited by 5 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the proposed RF model, three evaluation metrics such as model accuracy ( Accuracy ), F1 value, and kappa value [ 39 ] are calculated. Among them, model accuracy refers to the ratio of the number of samples correctly predicted by the model to the total number of samples, and it can be expressed as follows:

where TP denotes the number of positive samples predicted correctly, TN denotes the number of negative samples predicted correctly, FP stands for the number of samples predicted to be positive that are actually negative, and FN is the number of samples predicted to be negative that are actually positive.…”

Section: Remote Fault Diagnosis Model Based On Rfmentioning

confidence: 99%

See 1 more Smart Citation

Remote Fault Diagnosis for the Powertrain System of Fuel Cell Vehicles Based on Random Forest Optimized with a Genetic Algorithm

Quan,

Zhang,

Feng

2024

Sensors

View full text Add to dashboard Cite

To enhance the safety and reliability of fuel cell vehicles, a remote monitoring system based on 5th generation (5G) mobile networks and controller area networks (CANs) was designed, and a random forest (RF) algorithm for the fault diagnosis for eight typical malfunctions of its powertrain system was incorporated. Firstly, the information on the powertrain system was obtained through a 5G-based monitoring terminal, and the Alibaba Cloud IoT platform was utilized for data storage and remote monitoring. Secondly, a fault diagnosis model based on the RF algorithm was constructed for fault classification; its parameters were optimized with a genetic algorithm (GA), and it was applied on the Alibaba Cloud PAI platform. Finally, the performance of the proposed RF fault diagnosis model was evaluated by comparing it with three other classification models: random search conditioning, grid search conditioning, and Bayesian optimization. Results show that the model accuracy, F1 score, and kappa value of the optimized RF fault classification model are higher than the other three. The model achieves an F1 value of 97.77% in identifying multiple typical faults of the powertrain system, as validated by vehicle malfunction data. The method demonstrates the feasibility of remote monitoring and fault diagnosis for the powertrain system of fuel cell vehicles.

show abstract

Section: Remote Fault Diagnosis Model Based On Rfmentioning

confidence: 99%

“…To evaluate the proposed RF model, three evaluation metrics such as model accuracy (Accuracy), F1 value, and kappa value [39] are calculated. Among them, model accuracy refers to the ratio of the number of samples correctly predicted by the model to the total number of samples, and it can be expressed as follows:…”

Section: Model Evaluationmentioning

confidence: 99%

Remote Fault Diagnosis for the Powertrain System of Fuel Cell Vehicles Based on Random Forest Optimized with a Genetic Algorithm

Quan,

Zhang,

Feng

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Low temperatures not only affect the breakdown voltage of transformer oil but also have a significant impact on other parameters, such as electrical conductivity and relative permittivity, apart from the breakdown voltage [43][44][45]. The most direct effect is a decrease in breakdown voltage, which leads to transformer failures and potentially disastrous consequences for substations and the entire power system [46,47]. Under specific conditions, while low temperatures certainly have a significant impact on the performance of transformer oil, ultimately, the key factor is the water content in the oil.…”

Section: Introductionmentioning

confidence: 99%

Study on Power Frequency Breakdown Characteristics of Nano-TiO2 Modified Transformer Oil under Severe Cold Conditions

Qin,

Huang,

Liu

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

With 45# transformer oil as the base fluid, different concentrations of TiO2 nanomodified transformer oil were prepared via the thermal oscillation method. Nanomodified transformer oil with a concentration of 0.01 g/L was selected for evaluation via the breakdown test. Then, 0.01 g/L nanomodified transformer oil and ordinary 45# transformer oil were subjected to the variable control of different moisture contents and different temperatures, and breakdown tests under different types of electrodes were performed within the temperature range of −30 °C to 30 °C. The test results showed the following: Under severe cold conditions, the improvement effect of the breakdown voltage in different temperature ranges was different. Within the temperature range of −30 °C to −10 °C, the enhancement effect could reach 13% to 15%. Within the temperature range of −10 °C to 0 °C, the enhancement effect could reach 8% to 9%. Within the temperature range of 0 °C to 30 °C, the enhancement effect could reach 18% to 21%. Compared with the test results at high water contents, the improvement in the breakdown voltage amplitude of transformer oil by nanomaterials was more obvious at low water contents. In addition, nanomaterials could reduce the dispersion of the breakdown voltage to make the breakdown voltage more stable. Lastly, COMSOL was used to simulate the polarization process of nanoparticles under a uniform electric field and the influence of the trajectory of charged particles in the oil to further analyze the mechanism of the influence of nanoparticles in oil on the breakdown voltage of the oil gap. The simulation results showed that, when the particles were accelerated by the electric field, they moved irregularly. After adding nanoparticles, the charged particles were adsorbed by the nanoparticles when passing through the nanoparticles, which reduced the migration rate of charged particles in the oil. The breakdown voltage of the oil gap increased.

show abstract

Transformer fault acoustic identification model based on acoustic denoising and DBO-SVM

Lu,

Zhang,

et al. 2024

J. Electr. Eng. Technol.

View full text Add to dashboard Cite

A Fault Diagnosis Method of Oil-Immersed Transformer Based on Improved Harris Hawks Optimized Random Forest

Cited by 5 publications

References 12 publications

Remote Fault Diagnosis for the Powertrain System of Fuel Cell Vehicles Based on Random Forest Optimized with a Genetic Algorithm

Remote Fault Diagnosis for the Powertrain System of Fuel Cell Vehicles Based on Random Forest Optimized with a Genetic Algorithm

Study on Power Frequency Breakdown Characteristics of Nano-TiO2 Modified Transformer Oil under Severe Cold Conditions

Transformer fault acoustic identification model based on acoustic denoising and DBO-SVM

Contact Info

Product

Resources

About