Use of the K-Nearest Neighbour Classifier in Wear Condition Classification of a Positive Displacement Pump

Abstract

This paper presents a learning system with a K-nearest neighbour classifier to classify the wear condition of a multi-piston positive displacement pump. The first part reviews current built diagnostic methods and describes typical failures of multi-piston positive displacement pumps and their causes. Next is a description of a diagnostic experiment conducted to acquire a matrix of vibration signals from selected locations in the pump body. The measured signals were subjected to time-frequency analysis. The signal features calculated in the time and frequency domain were grouped in a table according to the wear condition of the pump. The next step was to create classification models of a pump wear condition and assess their accuracy. The selected model, which best met the set criteria for accuracy assessment, was verified with new measurement data. The article ends with a summary.

Boosted Convolutional Neural Network Algorithm for the Classification of the Bearing Fault form 1-D Raw Sensor Data

“…By utilizing HDAN, a significant improvement in diagnostics over the classical algorithms was observed. In the field of predictive maintenance, the k-nearest neighbors (k-NN) method has been found to be an effective and computationally efficient technique [31,32]. To classify features with this method, it is important to determine the similarity measure between the training and test instances.…”

A roadmap towards energy‐efficient data fusion methods in the Internet of Things

“…Supervised machine learning attempts to develop algorithms capable of producing general patterns and hypotheses by predicting the destiny of future instances using externally provided examples. 73 Supervised machine learning involves some classification algorithms, such as Naive Bayes (NB), 74 support vector machines (SVM), 75 and K-nearest neighbor (KNN), 76 as well as artificial neural network (ANN) 77 that simulates a biological learning system. Semi-supervised learning focuses on utilizing labeled and unlabeled data to execute certain learning tasks.…”

A Real-Time Distance Measurement System for a Digital Twin Using Mixed Reality Goggles

“…The use of this technology allows for more flexible process management and support for the operator of a given device. In this case, the operator is equipped with special interactive goggles which can display holograms and information for the user and be the basis for collecting information from the environment around the user [ 13 , 14 ] and transmitting information to higher-level systems [ 15 , 16 ]. This technology is potentially a great improvement and enhancement for process operator support.…”