Intelligent diagnosis method and system for leakage fault in hydraulic cylinder based on data driving

Abstract

The invention relates to an intelligent diagnosis method and system for a leakage fault in a hydraulic cylinder based on data driving, and the method comprises the following steps: 1, collecting the operation state data of the hydraulic cylinder of an injection molding machine through various sensors, and obtaining a fault data sample; 2, performing feature extraction on the injection pressure signal in the pressure maintaining stage; 3, establishing a fault diagnosis model, and training the fault diagnosis model; and 4, diagnosing real-time data of the operation state of the hydraulic cylinder of the injection molding machine, and enabling the fault diagnosis model to be subjected to self-updating optimization. The leakage state in the hydraulic cylinder in the actual injection process is simulated through non-destructive manual operation, a fault data sample is obtained, fault feature extraction and diagnosis model training are completed through a data mining algorithm, and remote intelligent fault diagnosis is achieved in combination with the Internet technology.

Description

technical field [0001] The invention relates to the technical field of hydraulic system faults, in particular to a data-driven intelligent diagnosis method and system for leakage faults in hydraulic cylinders. Background technique [0002] The statements herein merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] The hydraulic system has the characteristics of light weight, small size, high power, strong working stability and the ability to complete a wide range of stepless speed regulation, and is widely used in the industrial field. Among them, the hydraulic cylinder, as the executive part of the hydraulic servo system, is widely used in the realization of linear motion or rotary reciprocating motion, and its health status directly affects the entire production activities. [0004] The fault diagnosis methods of hydraulic systems are mainly divided into three types, including methods based on mathemat...

AI Technical Summary

Problems solved by technology

[0007] Although the existing technology has successfully used the data-driven method to diagnose the fault of the hydraulic cylinder, there are problems such as the difficulty in obtaining the fault data, the poor accuracy of the diagnosis model and the selection of model parameters. The present invention uses the XGBoost algorithm by simulating the leakage experiment in the hydraulic cylinder Train the diagnostic model, and finally adopt the particle swarm optimization algorithm (PSO) to find the best kernel parameter set, which solves the above problems

Images