Gavril Grebenisan | University of Oradea (original) (raw)

Papers by Gavril Grebenisan

Research paper thumbnail of A Finite Element Analysis of the behaviour of 3D printing equipment in the event of a constant heat flow

Authorea (Authorea), Apr 14, 2022

Research paper thumbnail of Control system for FDA deposition using a CNC milling machine

IOP conference series, Aug 1, 2021

This paper presents the command and control part of a 3D printhead, the command and control that ... more This paper presents the command and control part of a 3D printhead, the command and control that is made by combining the PLC of a CNC milling machine with the electrical assembly of an extruded head for FDA(Fusion Deposition Adhesion) processing. The command and control part of an extruder head is presented. On the same, the paper shows how to connect to the PLC of a CNC and presents the use and operation of an extruder block for FDA machining on CNC

Research paper thumbnail of Cylindrical parts stress study based on the bottom geometry shape

Annals of the Oradea University: Fascicle Management and Technological Engineering, 2012

Research paper thumbnail of The theoretical bases and study parameters with FEA application approach on a bending tool design

IOP conference series, Sep 17, 2019

This paper presents the theoretical basis of the approach to Finite Element Analysis (FEA) techni... more This paper presents the theoretical basis of the approach to Finite Element Analysis (FEA) techniques and their application in the case of a bending request for a piece of aluminum sheet. The plate of a bending device deforms elasto-plastically under the action of the drive forces of the device, but also under the action of the reaction forces in the supports, more for a material such as aluminum and a few times less for a structural steel. If the forces acting on the device deform the carrier plate, which is in the operator's attention, in the elastic field, then there is no danger of permanent deformations occurring. Conversely, if deformation exceeds the threshold of elastic deformation, the material undergoes plastic deformation stresses, then the piece deforms plastic, with the risk of permanent deformations occurring. These deformations, in the first place, can generate production errors, or device failure, by modifying the execution rates and the games in the studied ensemble. This is precisely the purpose of this work: to prove, with the results of the FEA, that in the case of a certain material, with the same configuration of working conditions, the system can function without producing errors, obtaining qualitatively conformable parts.

Research paper thumbnail of Optimization methods of the industrial robots’ trajectory

IOP conference series, Sep 17, 2019

In this paper, we present a part of our wider research regarding modeling, simulation and optimiz... more In this paper, we present a part of our wider research regarding modeling, simulation and optimization of the trajectory of the industrial robots. After a short introduction on the importance of the industrial robots, the necessity and widely interest regarding the trajectory optimization, we present a classification of the optimization methods: numerical, computational and hybrid. Then, we make a brief presentation of the main optimization criteria approached in the last few years in several scientific papers, regarding the optimization of the industrial robots' trajectory.

Research paper thumbnail of Machines Condition Monitoring and Oil Life Remaining Forecasting through Artificial Intelligence Techniques- a Survey

Design Engineering, Oct 5, 2021

Research paper thumbnail of Modeling and building a 3D print head

IOP Conference Series: Materials Science and Engineering, 2021

The paper presents 3D modeling and the construction of a printing head for plastic, a head that w... more The paper presents 3D modeling and the construction of a printing head for plastic, a head that will be used on a CNC milling machine. The component parts were modeled with Solid Edge software, and for manufacturing the parts we use a CNC milling machine and one conventional lathe. Following the manufacture of the parts, they were mounted together. After that, the mechanical parts was connected together with the electrical components and the result is a functional head that uses fused deposition modeling (FDM) technology.

Research paper thumbnail of Validation of an algorithm for predicting the remaining useful life, for a model with linear degradation

IOP Conference Series: Materials Science and Engineering, 2020

This paper aimed to validate a working tool, component of the Predictive Maintenance Toolbox ™, p... more This paper aimed to validate a working tool, component of the Predictive Maintenance Toolbox ™, produced by Matlab (MathWorks), in the case of a procedure for monitoring the operation of mechanical systems, in order to diagnose a failure of the process and to estimate the remaining useful life (RUL). This toolbox provides toolsets, materialized in function files, for labeling data, designing condition indicators, and estimating a parameter named the remaining useful life of a machine. You can analyze and label machine data imported from local files, cloud storage, and distributed file systems. The algorithm suggested by Matlab (software owned by MathWorks) was used in detail to process part of the data set provided freely by NASA through The Prognostics Data Repository, The Prognostics Center of Excellence (PCoE) at Ames Research Center. Of the 4 data sets, only one was used for this paper. Each data set is composed of 3 working files, in text format, for training, test and algorith...

Research paper thumbnail of A brief overview of Additive Manufacturing

IOP Conference Series: Materials Science and Engineering, 2020

In this paper, a brief overview is presented, resulting from a recent literature review of some r... more In this paper, a brief overview is presented, resulting from a recent literature review of some representative books or papers regarding various research on additive manufacturing. Some basic terms are presented, in the context of founding the existence of several terminologies for some specific expressions of this subject, as well as different definitions for them materials used at that process, areas of using, problems appeared during process of manufacturing, heat treatments used, advantages and disadvantages. This research is carried out to identify a solution for controlling the parameters during the additive processing (AM) process, parameters with which to improve the quality of the parts obtained by AM

Research paper thumbnail of Experimental approach and finite element analysis of the behavior of a steel bending tool

IOP Conference Series: Materials Science and Engineering, 2019

This work contains the 3D design and finite element analysis of a manual device for assembly by b... more This work contains the 3D design and finite element analysis of a manual device for assembly by bending the sheets around an exhaust muffler. As a result of the design of the device, the requested was executed by the information provided by the mechanical designer; only when the device of bending was put into operation, some faults appeared, namely that its parts during the operation has been elastically deformed. For the construction of the elastically yielding parts, the finite element method was used to study the behavior of the tool. Following the FEA analysis, it was concluded that the dimensions and material from which those pieces had been built had to be changed. By making the new parts based on FEA calculations, they no longer elastically yield (elastic deformation less than 0.1%), so the device is accepted by the customer.

Research paper thumbnail of Parameterized optimization analysis with finite elements, using ANSYS®, of a reference point under a torque action

IOP Conference Series: Materials Science and Engineering, 2019

To determine the elastic/plastic deformation value of the part, we used Ansys R19.0 software(CAE)... more To determine the elastic/plastic deformation value of the part, we used Ansys R19.0 software(CAE), to simulate a torque moment applied to the functional area part, which provided the information set about the part behavior. The mold of the part has 4 cavities, and the part material is a polyamide. Having a requirement imposed by the customer on the drawing, we considered this finite element analysis it is necessary before start manufacturing the molding and starting injection the parts to demonstrate that the customer requirement is achievable. The results obtained from the analysis with finite elements in ANSYS R19 showed that the constructional part could not fulfill the design requirement, namely to withstand a torque of 4500Nmm the part being fixed in the hole with a diameter of 2.5 mm. After analyzing the results, the client will have to modify the current drawing based on the results obtained by us, namely to reduce the torque value from 4500Nmm to 4000.3 Nmm.

Research paper thumbnail of The implementation of an adaptive traffic light concept in regards to tram access in a complex intersection

IOP Conference Series: Materials Science and Engineering, 2019

Case study on the solution of the implementation of an adaptive traffic light concept in regards ... more Case study on the solution of the implementation of an adaptive traffic light concept in regards to tram access of in the intersection created between the Decebal Bvd-Aradului Path-Primariei Street of Oradea Municipality.Description of the proposed solution for the intersection Decebal Bvd-Aradului Path-Primariei Street

Research paper thumbnail of A multiobjective genetic algorithm optimization framework for batch plant design

Computer Aided Chemical Engineering, 2003

This paper presents a MultiObjective Genetic Algorithm (MOGA) optimization framework for batch pl... more This paper presents a MultiObjective Genetic Algorithm (MOGA) optimization framework for batch plant design. For this purpose, two MOGAs are implemented with respect to three criteria, i.e., investment cost, equipment number and a flexibility indicator based on Work In Process (the so-called WIP) computed by use of a Discrete-Event simulation model. The performances of the two procedures are studied for

Research paper thumbnail of An optimization approach by Finite Element Analysis, using Design of Experiments and Response Surfaces- a survey

IOP Conference Series: Materials Science and Engineering, 2019

The deformation of an aluminum plate, called in this paper, a support plate, which is part of a b... more The deformation of an aluminum plate, called in this paper, a support plate, which is part of a bending plastic deformation device, is studied in this paper using the Finite Elements Method, respectively design points of the design by optimization using features such as Design of Experiments and Response Surfaces. The start of the analysis was determined by a functional requirement in the design and construction of a sophisticated bending device controlled by steel plates for the production of exhausts for cars. To optimize the project, it was necessary to analyze the behavior of the active material and components of the device. The analysis of material and piece behavior, in working conditions, has been developed by addressing the facilities offered by Ansys software. Following FEA analysis, optimizing the active components of the device has provided proven results in practice through the execution and operation of the device, according to the technology required by the product des...

Research paper thumbnail of An approach of classification and parameters estimation, using neural network, for lubricant degradation diagnosis

MATEC Web of Conferences, 2018

This paper addresses a delicate problem, namely the diagnosis of the state of the oils in the ind... more This paper addresses a delicate problem, namely the diagnosis of the state of the oils in the industrial systems, namely the machine tools. Based on measurements (the data set contains over five million records), within a Machine Intelligence for Diagnosis Automation (MIDA) project funded by the National Program PN II, ERA MANUNET: NR 13081221 / 13.08.2013, several applications of MATLAB toolbars are being developed in the field of artificial intelligence, specifically using the Support Vector Machine algorithms and neural networks. The tests were carried out on several distinct situations, followed by validation and verification tests on the devices designed and developed within the project (MIDA, Monitoil).

Research paper thumbnail of A brief assessment of outliers and malfunctions detecting techniques with an application on lubricant condition monitoring

IOP Conference Series: Materials Science and Engineering, 2019

Condition monitoring and machine status classification are of great practical importance in the m... more Condition monitoring and machine status classification are of great practical importance in the manufacturing industry as it provides online updates on the state of the machine, avoiding loss of production and minimizing the probability of generating catastrophic damage to the machine. In this paper, the classification of conditions is based on the processing of information using wavelets based on the results of the monitoring and the data collected during such an action, measuring the characteristics of the lubricating oil over some time sufficient to produce a time series of results. In this paper, the classification system is tested and validated using observation sequences based on the maximum wavelet distribution obtained from the collected signals, monitoring the state of the lubricating oil, to define and diagnose singularities in time series.

Research paper thumbnail of A neural networks approach of process fault diagnosis using time series collected data through oil condition monitoring

IOP Conference Series: Materials Science and Engineering, 2019

In this paper was used the data set collected in a research project between private companies fro... more In this paper was used the data set collected in a research project between private companies from Romania and Italy, for the development of a basic approach of artificial neural network techniques, as an application in Matlab, aiming to detect the degree of degradation of oil, an automated installation, measuring online the physicochemical properties of the oil. Physical-chemical parameters measured lead to the creation of generous time series, but accessible by numerical and statistical calculation, for the application of artificial intelligence techniques. Applying neural network techniques to parameters that measure oil degradation, oxidation and humidity have generated the results of this work. The main function of monitoring the state of operation of a mechanical system, machine, or plant is to provide the almost correct diagnosis of the machine’s state and rate of change so that preventive measures can be taken at a given time.

Research paper thumbnail of Parameterized finite element analysis of a superplastic forming process, using Ansys®

MATEC Web of Conferences, 2017

A theoretical and experimental analysis was carried out, after superplastic forming, of Al-Ti-V-b... more A theoretical and experimental analysis was carried out, after superplastic forming, of Al-Ti-V-based alloy sheets, of hemispherical parts, as the start point of research. Based on the measurements i.e. the quantitative and qualitative determinations of the manufactured parts, work reports have been prepared to contain the magnitude of variations in the thickness of the parts, in cross-section, as well as references to the surface quality and the local thinning of the walls of the part. The experimental study was followed by a parameterized finite elements analysis of the process, using Ansys®, Explicit Dynamics Module, This being for examining the next step of our study, comparing the experimental results with the theoretical analysis, based on two input parameters: and discussing the results, and very necessary, the correlation between input and output parameters, mainly the influence magnitude rate of input parameters on output parameters.

Research paper thumbnail of Oil Condition Monitoring and Remaining Life Prediction using Classification Learner Technique, an AI Application

Research Developments in Science and Technology Vol. 7

Research paper thumbnail of Oil condition monitoring, an AI application study using the Classification Learner Technics

The present study uses an estimation and prediction method and characteristic techniques to predi... more The present study uses an estimation and prediction method and characteristic techniques to predict the life of the lubricating oil based on data collected directly from the mechanical or hydraulic system. The collected data is part of a complex data set with 19 lubricating oil status parameters resulting from online measurements on an experiment stand built and operated under conditions similar to those in a mechanical machining company. The data set was collected during six months, continuously validating the data in several 258646 instances for 19 operating parameters. To predict the values of the next steps of a sequence, the Classification Learner Technics has been approached by support vector machines (SVM) models. The answers obtained characterize and equate the training sequences with values changed by a step of the time, and this means that at each stage of the input sequence, the data structure learns to predict the output value at the next time step. To prevent divergence of the forecast, it was necessary to standardize the training data so that it will achieve a zero mean and unit variance. Also, the test data set has been normalized in the same way as training data.

Research paper thumbnail of A Finite Element Analysis of the behaviour of 3D printing equipment in the event of a constant heat flow

Authorea (Authorea), Apr 14, 2022

Research paper thumbnail of Control system for FDA deposition using a CNC milling machine

IOP conference series, Aug 1, 2021

This paper presents the command and control part of a 3D printhead, the command and control that ... more This paper presents the command and control part of a 3D printhead, the command and control that is made by combining the PLC of a CNC milling machine with the electrical assembly of an extruded head for FDA(Fusion Deposition Adhesion) processing. The command and control part of an extruder head is presented. On the same, the paper shows how to connect to the PLC of a CNC and presents the use and operation of an extruder block for FDA machining on CNC

Research paper thumbnail of Cylindrical parts stress study based on the bottom geometry shape

Annals of the Oradea University: Fascicle Management and Technological Engineering, 2012

Research paper thumbnail of The theoretical bases and study parameters with FEA application approach on a bending tool design

IOP conference series, Sep 17, 2019

This paper presents the theoretical basis of the approach to Finite Element Analysis (FEA) techni... more This paper presents the theoretical basis of the approach to Finite Element Analysis (FEA) techniques and their application in the case of a bending request for a piece of aluminum sheet. The plate of a bending device deforms elasto-plastically under the action of the drive forces of the device, but also under the action of the reaction forces in the supports, more for a material such as aluminum and a few times less for a structural steel. If the forces acting on the device deform the carrier plate, which is in the operator's attention, in the elastic field, then there is no danger of permanent deformations occurring. Conversely, if deformation exceeds the threshold of elastic deformation, the material undergoes plastic deformation stresses, then the piece deforms plastic, with the risk of permanent deformations occurring. These deformations, in the first place, can generate production errors, or device failure, by modifying the execution rates and the games in the studied ensemble. This is precisely the purpose of this work: to prove, with the results of the FEA, that in the case of a certain material, with the same configuration of working conditions, the system can function without producing errors, obtaining qualitatively conformable parts.

Research paper thumbnail of Optimization methods of the industrial robots’ trajectory

IOP conference series, Sep 17, 2019

In this paper, we present a part of our wider research regarding modeling, simulation and optimiz... more In this paper, we present a part of our wider research regarding modeling, simulation and optimization of the trajectory of the industrial robots. After a short introduction on the importance of the industrial robots, the necessity and widely interest regarding the trajectory optimization, we present a classification of the optimization methods: numerical, computational and hybrid. Then, we make a brief presentation of the main optimization criteria approached in the last few years in several scientific papers, regarding the optimization of the industrial robots' trajectory.

Research paper thumbnail of Machines Condition Monitoring and Oil Life Remaining Forecasting through Artificial Intelligence Techniques- a Survey

Design Engineering, Oct 5, 2021

Research paper thumbnail of Modeling and building a 3D print head

IOP Conference Series: Materials Science and Engineering, 2021

The paper presents 3D modeling and the construction of a printing head for plastic, a head that w... more The paper presents 3D modeling and the construction of a printing head for plastic, a head that will be used on a CNC milling machine. The component parts were modeled with Solid Edge software, and for manufacturing the parts we use a CNC milling machine and one conventional lathe. Following the manufacture of the parts, they were mounted together. After that, the mechanical parts was connected together with the electrical components and the result is a functional head that uses fused deposition modeling (FDM) technology.

Research paper thumbnail of Validation of an algorithm for predicting the remaining useful life, for a model with linear degradation

IOP Conference Series: Materials Science and Engineering, 2020

This paper aimed to validate a working tool, component of the Predictive Maintenance Toolbox ™, p... more This paper aimed to validate a working tool, component of the Predictive Maintenance Toolbox ™, produced by Matlab (MathWorks), in the case of a procedure for monitoring the operation of mechanical systems, in order to diagnose a failure of the process and to estimate the remaining useful life (RUL). This toolbox provides toolsets, materialized in function files, for labeling data, designing condition indicators, and estimating a parameter named the remaining useful life of a machine. You can analyze and label machine data imported from local files, cloud storage, and distributed file systems. The algorithm suggested by Matlab (software owned by MathWorks) was used in detail to process part of the data set provided freely by NASA through The Prognostics Data Repository, The Prognostics Center of Excellence (PCoE) at Ames Research Center. Of the 4 data sets, only one was used for this paper. Each data set is composed of 3 working files, in text format, for training, test and algorith...

Research paper thumbnail of A brief overview of Additive Manufacturing

IOP Conference Series: Materials Science and Engineering, 2020

In this paper, a brief overview is presented, resulting from a recent literature review of some r... more In this paper, a brief overview is presented, resulting from a recent literature review of some representative books or papers regarding various research on additive manufacturing. Some basic terms are presented, in the context of founding the existence of several terminologies for some specific expressions of this subject, as well as different definitions for them materials used at that process, areas of using, problems appeared during process of manufacturing, heat treatments used, advantages and disadvantages. This research is carried out to identify a solution for controlling the parameters during the additive processing (AM) process, parameters with which to improve the quality of the parts obtained by AM

Research paper thumbnail of Experimental approach and finite element analysis of the behavior of a steel bending tool

IOP Conference Series: Materials Science and Engineering, 2019

This work contains the 3D design and finite element analysis of a manual device for assembly by b... more This work contains the 3D design and finite element analysis of a manual device for assembly by bending the sheets around an exhaust muffler. As a result of the design of the device, the requested was executed by the information provided by the mechanical designer; only when the device of bending was put into operation, some faults appeared, namely that its parts during the operation has been elastically deformed. For the construction of the elastically yielding parts, the finite element method was used to study the behavior of the tool. Following the FEA analysis, it was concluded that the dimensions and material from which those pieces had been built had to be changed. By making the new parts based on FEA calculations, they no longer elastically yield (elastic deformation less than 0.1%), so the device is accepted by the customer.

Research paper thumbnail of Parameterized optimization analysis with finite elements, using ANSYS®, of a reference point under a torque action

IOP Conference Series: Materials Science and Engineering, 2019

To determine the elastic/plastic deformation value of the part, we used Ansys R19.0 software(CAE)... more To determine the elastic/plastic deformation value of the part, we used Ansys R19.0 software(CAE), to simulate a torque moment applied to the functional area part, which provided the information set about the part behavior. The mold of the part has 4 cavities, and the part material is a polyamide. Having a requirement imposed by the customer on the drawing, we considered this finite element analysis it is necessary before start manufacturing the molding and starting injection the parts to demonstrate that the customer requirement is achievable. The results obtained from the analysis with finite elements in ANSYS R19 showed that the constructional part could not fulfill the design requirement, namely to withstand a torque of 4500Nmm the part being fixed in the hole with a diameter of 2.5 mm. After analyzing the results, the client will have to modify the current drawing based on the results obtained by us, namely to reduce the torque value from 4500Nmm to 4000.3 Nmm.

Research paper thumbnail of The implementation of an adaptive traffic light concept in regards to tram access in a complex intersection

IOP Conference Series: Materials Science and Engineering, 2019

Case study on the solution of the implementation of an adaptive traffic light concept in regards ... more Case study on the solution of the implementation of an adaptive traffic light concept in regards to tram access of in the intersection created between the Decebal Bvd-Aradului Path-Primariei Street of Oradea Municipality.Description of the proposed solution for the intersection Decebal Bvd-Aradului Path-Primariei Street

Research paper thumbnail of A multiobjective genetic algorithm optimization framework for batch plant design

Computer Aided Chemical Engineering, 2003

This paper presents a MultiObjective Genetic Algorithm (MOGA) optimization framework for batch pl... more This paper presents a MultiObjective Genetic Algorithm (MOGA) optimization framework for batch plant design. For this purpose, two MOGAs are implemented with respect to three criteria, i.e., investment cost, equipment number and a flexibility indicator based on Work In Process (the so-called WIP) computed by use of a Discrete-Event simulation model. The performances of the two procedures are studied for

Research paper thumbnail of An optimization approach by Finite Element Analysis, using Design of Experiments and Response Surfaces- a survey

IOP Conference Series: Materials Science and Engineering, 2019

The deformation of an aluminum plate, called in this paper, a support plate, which is part of a b... more The deformation of an aluminum plate, called in this paper, a support plate, which is part of a bending plastic deformation device, is studied in this paper using the Finite Elements Method, respectively design points of the design by optimization using features such as Design of Experiments and Response Surfaces. The start of the analysis was determined by a functional requirement in the design and construction of a sophisticated bending device controlled by steel plates for the production of exhausts for cars. To optimize the project, it was necessary to analyze the behavior of the active material and components of the device. The analysis of material and piece behavior, in working conditions, has been developed by addressing the facilities offered by Ansys software. Following FEA analysis, optimizing the active components of the device has provided proven results in practice through the execution and operation of the device, according to the technology required by the product des...

Research paper thumbnail of An approach of classification and parameters estimation, using neural network, for lubricant degradation diagnosis

MATEC Web of Conferences, 2018

This paper addresses a delicate problem, namely the diagnosis of the state of the oils in the ind... more This paper addresses a delicate problem, namely the diagnosis of the state of the oils in the industrial systems, namely the machine tools. Based on measurements (the data set contains over five million records), within a Machine Intelligence for Diagnosis Automation (MIDA) project funded by the National Program PN II, ERA MANUNET: NR 13081221 / 13.08.2013, several applications of MATLAB toolbars are being developed in the field of artificial intelligence, specifically using the Support Vector Machine algorithms and neural networks. The tests were carried out on several distinct situations, followed by validation and verification tests on the devices designed and developed within the project (MIDA, Monitoil).

Research paper thumbnail of A brief assessment of outliers and malfunctions detecting techniques with an application on lubricant condition monitoring

IOP Conference Series: Materials Science and Engineering, 2019

Condition monitoring and machine status classification are of great practical importance in the m... more Condition monitoring and machine status classification are of great practical importance in the manufacturing industry as it provides online updates on the state of the machine, avoiding loss of production and minimizing the probability of generating catastrophic damage to the machine. In this paper, the classification of conditions is based on the processing of information using wavelets based on the results of the monitoring and the data collected during such an action, measuring the characteristics of the lubricating oil over some time sufficient to produce a time series of results. In this paper, the classification system is tested and validated using observation sequences based on the maximum wavelet distribution obtained from the collected signals, monitoring the state of the lubricating oil, to define and diagnose singularities in time series.

Research paper thumbnail of A neural networks approach of process fault diagnosis using time series collected data through oil condition monitoring

IOP Conference Series: Materials Science and Engineering, 2019

In this paper was used the data set collected in a research project between private companies fro... more In this paper was used the data set collected in a research project between private companies from Romania and Italy, for the development of a basic approach of artificial neural network techniques, as an application in Matlab, aiming to detect the degree of degradation of oil, an automated installation, measuring online the physicochemical properties of the oil. Physical-chemical parameters measured lead to the creation of generous time series, but accessible by numerical and statistical calculation, for the application of artificial intelligence techniques. Applying neural network techniques to parameters that measure oil degradation, oxidation and humidity have generated the results of this work. The main function of monitoring the state of operation of a mechanical system, machine, or plant is to provide the almost correct diagnosis of the machine’s state and rate of change so that preventive measures can be taken at a given time.

Research paper thumbnail of Parameterized finite element analysis of a superplastic forming process, using Ansys®

MATEC Web of Conferences, 2017

A theoretical and experimental analysis was carried out, after superplastic forming, of Al-Ti-V-b... more A theoretical and experimental analysis was carried out, after superplastic forming, of Al-Ti-V-based alloy sheets, of hemispherical parts, as the start point of research. Based on the measurements i.e. the quantitative and qualitative determinations of the manufactured parts, work reports have been prepared to contain the magnitude of variations in the thickness of the parts, in cross-section, as well as references to the surface quality and the local thinning of the walls of the part. The experimental study was followed by a parameterized finite elements analysis of the process, using Ansys®, Explicit Dynamics Module, This being for examining the next step of our study, comparing the experimental results with the theoretical analysis, based on two input parameters: and discussing the results, and very necessary, the correlation between input and output parameters, mainly the influence magnitude rate of input parameters on output parameters.

Research paper thumbnail of Oil Condition Monitoring and Remaining Life Prediction using Classification Learner Technique, an AI Application

Research Developments in Science and Technology Vol. 7

Research paper thumbnail of Oil condition monitoring, an AI application study using the Classification Learner Technics

The present study uses an estimation and prediction method and characteristic techniques to predi... more The present study uses an estimation and prediction method and characteristic techniques to predict the life of the lubricating oil based on data collected directly from the mechanical or hydraulic system. The collected data is part of a complex data set with 19 lubricating oil status parameters resulting from online measurements on an experiment stand built and operated under conditions similar to those in a mechanical machining company. The data set was collected during six months, continuously validating the data in several 258646 instances for 19 operating parameters. To predict the values of the next steps of a sequence, the Classification Learner Technics has been approached by support vector machines (SVM) models. The answers obtained characterize and equate the training sequences with values changed by a step of the time, and this means that at each stage of the input sequence, the data structure learns to predict the output value at the next time step. To prevent divergence of the forecast, it was necessary to standardize the training data so that it will achieve a zero mean and unit variance. Also, the test data set has been normalized in the same way as training data.