Thermal Load Model of a Proportional Solenoid Valve Based on Random Load Conditions

Drastic changes in the random load of an electromechanical system bring about a reliability problem for the proportional solenoid valve based on a thermal effect. In order to accurately and effectively express the thermal load of a proportional solenoid valve under random load conditions and to meet the requirements of online acquisition, adaptive anomaly detection, and the missing substitution of thermal load data, a thermal load prediction model based on the Kalman filter algorithm is proposed. Taking the compound operation process of an excavator as the object and based on the field testing of an excavator and the independent testing experiment of a proportional solenoid valve in a non-installed state, a method of obtaining historical samples of the proportional solenoid valve's power and thermal load is given. The k-means clustering algorithm is used to cluster the historical samples of the power and thermal load corresponding to the working posture of a multi-tool excavator. The Grubbs criterion is used to eliminate the outliers in the clustering samples, and unbiased estimation is performed on the clustering samples to obtain the prediction model. The results show that the cross-validation of the sample data under the specific sample characteristics of the thermal load model was carried out. Compared with other methods, the prediction accuracy of the thermal load model based on the Kalman filter is higher, the adaptability is strong, and the maximum prediction deviation percentage is stable within 5%. This study has value as a reference for random cycle thermal load analyses of low-frequency electromechanical products.

Automated summary

This paper proposes a thermal load prediction model based on the Kalman filter algorithm, which can accurately predict the thermal load of a proportional solenoid valve under random load conditions. Historical samples of the solenoid valve's power and thermal load are obtained through experiments, and the k-means clustering algorithm is used to process the samples and obtain the prediction model. Experimental results show that the thermal load model based on the Kalman filter has higher prediction accuracy and adaptability, with a maximum prediction deviation of less than 5%.