Abstract
Aiming at fault diagnosis of axial piston pumps, a new fusion method based on the extreme-point symmetric mode decomposition method (ESMD) and random forests (RFs) was proposed. Firstly, the vibration signal of the axial piston pump was decomposed by ESMD to get several intrinsic mode functions (IMFs) and an adaptive global mean curve (AGMC) on the local side. Secondly, the total energy was selected as the data of feature extraction by analyzing the whole oscillation intensity of the signal. Thirdly, the data were preprocessed and the labels were set, and then, they were adopted as the training and testing set of machine learning samples. Lastly, the RFs model was created based on machine learning service (MLS) to diagnose the faults of the axial piston pump on the cloud. Using the test and verifying the data set for comparative testing, the fault diagnosis precision rates of the model are above 90.6%, the recall rates are more than 90.9%, the F1 score is higher than 90.7%, and the accuracy rate of this model reached 97.14%. A benchmark data simulation of mechanical transmission systems and an experimental data investigation of an axial piston pump are performed to manifest the superiority of the present method by comparing with classification and regression trees (CART) and support vector machine (SVM).
Highlights
Aiming at fault diagnosis of axial piston pumps, a new fusion method based on the extreme-point symmetric mode decomposition method (ESMD) and random forests (RFs) was proposed
Using the test and verifying the data set for comparative testing, the fault diagnosis precision rates of the model are above 90.6%, the recall rates are more than 90.9%, the F1 score is higher than 90.7%, and the accuracy rate of this model reached 97.14%
To integrate multiple fault diagnosis algorithms, Tang et al proposed a fault diagnosis method based on empirical mode decomposition (EMD) and envelope spectrum aiming at the difficulty in early fault diagnosis of the pump
Summary
2.1. e Principles of ESMD. e ESMD usually adopts oddeven pole symmetric modal decomposition, and the algorithm is as follows [32]: Step 1: find all the extreme points (maximum and minimum) of the original signal Z and mark them as Ei (i 1, 2, . . ., n). The resulting margin r is an optimal AGM curve It can be seen from the above steps that the ESMD method can decompose the signal into some intrinsic mode functions (IMFs) and a residual component r. E final classification result of the system adopts the simple majority voting method, and the classification decision expression is as follows: K. k 1 where H(X) represents the combined classification model; hk(X) is a single classification model; Y stands for the correct category; I(·) is the Indicator function. Entropy or Gini coefficient is often used to quantify the order degree of a set and to quantitatively evaluate the splitting attribute of each node. Where D represents all samples of the data set; pi is the proportion of sample size of category i in all samples; n is the number of data categories
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call