Research on Multi-dimensional Health Evaluation Method for Complex Machinery: -- Taking Fracturing Pump as an Example

Yunlu Zhang; Chuan Wang; Huawei Wang

doi:10.62051/ijmee.v7n3.12

Authors

Yunlu Zhang
Chuan Wang
Huawei Wang

DOI:

https://doi.org/10.62051/ijmee.v7n3.12

Keywords:

Fracturing Pump, Multi-Dimensional Health State Assessment, Mahalanobis Distance, Generalized Regression Neural Network (GRNN), Markov Model Introduction

Abstract

This paper focuses on the multi-dimensional health state assessment of complex mechanical equipment, using a fracturing pump as a case study. It proposes a comprehensive assessment framework that integrates the analysis of multiple data dimensions, including real-time operational data, vibration data, and historical maintenance data. A health baseline is constructed by obtaining residual data of the equipment in a healthy state using a Generalized Regression Neural Network (GRNN) and extracting time-frequency domain features. The health assessment model for the vibration data dimension is built by calculating and normalizing the Mahalanobis Distance between the vibration data to be assessed and the health baseline. An equipment operational state evaluation model based on multiple characteristic parameters is established, using these parameters as failure criteria, to quantitatively characterize the Health Index from the real-time operational data dimension. Based on reliability theory, a multi-state transition probability for the main components of the equipment is obtained using a Markov model. The probability is mapped to the Health Index using a weighted average method for defuzzification, thereby constructing a health assessment model for the historical maintenance data dimension. Finally, the health state of the equipment is graded and comprehensively evaluated. This method can provide theoretical support for the preventive maintenance and health management of equipment, while also offering a reference for the intelligent operation and maintenance of complex mechanical equipment.

References

[1] Wang, J., Zhang, H., Li, X., et al. A generalized regression neural network based health assessment approach for rotating machinery. Mechanical Systems and Signal Processing. 2020, Vol. 128, p. 1-15.

[2] Chen, Y., Liu, B., Yang, K., et al. Fault detection and diagnosis based on improved Mahalanobis distance and wavelet analysis. Journal of Sound and Vibration. 2019, Vol. 438, p. 266-280.

[3] Smith, P., Johnson, M., Williams, R., et al. Multi-sensor data fusion for equipment health monitoring using CRITIC weight method. IEEE Transactions on Instrumentation and Measurement. 2021, Vol. 70, p. 1-12.

[4] Zhang, L., Wang, K., Li, M., et al. Health assessment of centrifugal pumps using vibration analysis and reliability theory. Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering. 2022, Vol. 236(2), p. 145-156.

[5] Brown, T., Davis, S., Wilson, P., et al. A comprehensive health monitoring system for hydraulic fracturing pumps. SPE Annual Technical Conference and Exhibition. Dubai, UAE, 2021-09-21, p. 1-12.

[6] Jackson, R., Thompson, M. Advanced Reliability Engineering and Maintenance Management. Springer, 2018, p. 89-156.

[7] Anderson, K., Roberts, S. Multi-dimensional Data Fusion in Mechanical Systems. Elsevier, 2019, p. 234-289.

[8] Wilson, K.: Intelligent Health Monitoring of Complex Mechanical Systems Using Multi-source Information Fusion (PhD dissertation, University of Michigan, USA 2020). p. 45-89.

[9] Zhao, L.: Research on Health State Evaluation and Prediction Method of Rotating Machinery (Master thesis, Tsinghua University, China 2019). p. 23-67.