SVM Algorithm for Vibration Fault Diagnosis in Centrifugal Pump

Vibration failure in the pumping system is a significant issue for indus-tries that rely on the pump as a critical device which requires regular maintenance.To save energy and money,a new automated system must be developed that can detect anomalies at an early stage.This paper presents a case study of a machine learning(ML)-based computational technique for automatic fault detection in a cascade pumping system based on variable frequency drive(VFD).Since the intensity of the vibrational effect depends on which axis has the most significant effect,a three-axis accelerometer is used to measure it in the pumping system.The emphasis is on determining the vibration effect on different axes.For experiment,various ML algorithms are investigated on collected vibratory data through Matlab software in x,y,z axes and performances of the algorithms are compared based on accuracy rate,prediction speed and training time.Based on the proposed research results,the multiclass support vector machine(MSVM)is found to be the best suitable algorithm compared to other algorithms.It has been demonstrated that ML algorithms can detect faults automatically rather than conventional meth-ods.MSVM is used for the proposed work because it is less complex and pro-duces better results with a limited data set.

COMPARISON OF MODELING TECHNIQUES FOR SELECTING OPTIMIZED AND AUTOMATED PLASMA CUTTING PROCESS PARAMETERS

The advancement in technologies made the entire manufacturing system,to be operated with more efficient,flexible,user friendly,more productive and cost effective.One such a system to be focused for advancement is plasma cutting system,which has wider industrial applications.There are many researches pursuing at various area of plasma cutting technology,still the automated and optimized parameters value selection is challenging.The work is aimed to eliminate the manual mode of feeding the input parameters for cutting operation.At present,cutting parameters are fed by referring the past cut data information or with the assistance of experienced employers.The cutting process parameters selections will have direct impact on the quality of the material being cut,and life of the consumables.This paper is intended to automate the process parameters selection by developing the mathematical model with existing cutting process parameters database.In this,three different approaches,multiple regression,multiple polynomial regression and AI technique,are selected and analyzed with the mathematical relations developed between the different cutting process parameters.The accuracy and reliability of those methods are detailed.The advantage and disadvantage of those methods for optimal setting conditions are discussed.The appropriate method that can be preferred for automated and optimal settings are elucidated.Finally,the selected technique is checked for accuracy and reliability for the existing cut data.