Neural network approach for surface roughness prediction in surface grinding

Several systems are currently tested in order to obtain a feasible and safe method for automation and control of grinding process. This work aims to predict the surface roughness of the parts of SAE 1020 steel ground in a surface grinding machine. Acoustic emission and electrical power signals were acquired by a commercial data acquisition system. The former from a fixed sensor placed near the workpiece and the latter from the electric induction motor that drives the grinding wheel. Both signals were digitally processed through known statistics, which with the depth of cut composed three data sets implemented to the artificial neural networks. The neural network through its mathematical logical system interpreted the signals and successful predicted the workpiece roughness. The results from the neural networks were compared to the roughness values taken from the worpieces, showing high efficiency and applicability on monitoring and controlling the grinding process. Also, a comparison among the three data sets was carried out.

Grinding of hardened steels using optimized cooling

Grinding - the final machining process of a workpiece - requires large amounts of cutting fluids for the lubrication, cooling and removal of chips. These fluids are highly aggressive to the environment. With the technological advances of recent years, the worldwide trend is to produce increasingly sophisticated components with very strict geometric and dimensional tolerances, good surface finish, at low costs, and particularly without damaging the environment. The latter requirement can be achieved by recycling cutting fluids, which is a costly solution, or by drastically reducing the amount of cutting fluids employed in the grinding process. This alternative was investigated here by varying the plunge velocity in the plunge cylindrical grinding of ABNT D6 steel, rationalizing the application of two cutting fluids and using a superabrasive CBN (cubic boron nitride) grinding wheel with vitrified binder to evaluate the output parameters of tangential cutting force, acoustic emission, roughness, roundness, tool wear, residual stress and surface integrity, using scanning electron microscopy (SEM) to examine the test specimens. The performance of the cutting fluid, grinding wheel and plunge velocity were analyzed to identify the best machining conditions which allowed for a reduction of the cutting fluid volume, reducing the machining time without impairing the geometric and dimensional parameters, and the surface finish and integrity of the machined components.

Influence of grinding on the roundness, residual stresses and microstructure of VC131 steel analysed by varying the type of cutting fluid

This paper by R. E. Catai, E. C. Bianchi, P. R de Águia and M. C. Alves reports on the results of an analysis made of roundness errors, residual stresses, and SEM micrographs of VC131 steel. The analysis involved workpieces ground with two types of cutting fluid: synthetic cutting fluid and emulsive oil. In this study, the cutting parameters were kept constant while the type of cutting fluid was varied. The amount of cutting fluid injected in the process was also varied, aiming to identify the ideal amount required to obtain good results without causing structural damage to the workpiece. The SEM analyses of roundness errors and residual stresses revealed that, of the two cutting fluids, emulsive oil provided better tensions due to its greater lubricating power.

Monitoring the dressing operation in the grinding process

This work was based on a methodology of development and experimentation, and involved monitoring the dressing operation by processing the acoustic emission and electric power signals to detect the optimal dressing moment. Dressing tests were performed in a surface grinding machine with an aluminium grinding wheel. Dressing analysis software was developed and used to process the signals collected earlier in order to analyse not only the dressing parameters but also the software's ability to indicate the instant when the dressing operation could be concluded. Parameters used in the study of burn in grinding were implemented in order to ascertain if they would also prove efficient in monitoring dressing. A comparative study revealed that some parameters are capable of monitoring the dressing operation. It was possible to verify the parameters effectiveness that today are utilised in burning to monitor dressing as well as to create new parameters for monitoring this operation. Copyright © 2009, Inderscience Publishers.

Anfis applied to the prediction of surface roughness in grinding of advanced ceramics

This paper introduces a methodology for predicting the surface roughness of advanced ceramics using Adaptive Neuro-Fuzzy Inference System (ANFIS). To this end, a grinding machine was used, equipped with an acoustic emission sensor and a power transducer connected to the electric motor rotating the diamond grinding wheel. The alumina workpieces used in this work were pressed and sintered into rectangular bars. Acoustic emission and cutting power signals were collected during the tests and digitally processed to calculate the mean, standard deviation, and two other statistical data. These statistics, as well the root mean square of the acoustic emission and cutting power signals were used as input data for ANFIS. The output values of surface roughness (measured during the tests) were implemented for training and validation of the model. The results indicated that an ANFIS network is an excellent tool when applied to predict the surface roughness of ceramic workpieces in the grinding process.

Utilization of teflon and aluminum oxide for wheel cleaning in Minimum Quantity Lubrication (MQL) grinding

Researches concerning cooling-lubrication optimization in grinding have been conducted to contribute to a more sustainable process. An alternative to flood coolant is minimum quantity lubrication (MQL), which spray oil droplets in a compressed air jet. However, problems related to wheel cleaning were reported, due to wheel loading by a mixture of chips and oil, resulting in worsening of surface quality. This work aims to evaluate the viability of Teflon and aluminum oxide for wheel cleaning, compared to MQL without cleaning and MQL with cleaning by compressed air, through the following output variables: surface roughness, roundness, wheel wear, grinding power and acoustic emission. Vickers microhardness measurements and optical microscopy were also carried out. The results showed that both materials were efficient in cleaning the wheel, compared to MQL without cleaning, but not as satisfactory as compressed air. Much work is to be done in order to select the right material for wheel cleaning.

Utilization of Minimum Quantity Lubrication (MQL) with Water in CBN Grinding of Steel

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Evaluation of different methods of cooling-lubrication in cylindrical grinding of advanced ceramic dip

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Effect of grinding with diamond-disc and -bur on the mechanical behavior of a Y-TZP ceramic

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Neural tool condition estimation in the grinding of advanced ceramics

Ceramic parts are increasingly replacing metal parts due to their excellent physical, chemical and mechanical properties, however they also make them difficult to manufacture by traditional machining methods. The developments carried out in this work are used to estimate tool wear during the grinding of advanced ceramics. The learning process was fed with data collected from a surface grinding machine with tangential diamond wheel and alumina ceramic test specimens, in three cutting configurations: with depths of cut of 120 mu m, 70 mu m and 20 mu m. The grinding wheel speed was 35m/s and the table speed 2.3m/s. Four neural models were evaluated, namely: Multilayer Perceptron, Radial Basis Function, Generalized Regression Neural Networks and the Adaptive Neuro-Fuzzy Inference System. The models'performance evaluation routines were executed automatically, testing all the possible combinations of inputs, number of neurons, number of layers, and spreading. The computational results reveal that the neural models were highly successful in estimating tool wear, since the errors were lower than 4%.

Grinding process monitoring based on electromechanical impedance measurements

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Tool condition monitoring of aluminum oxide grinding wheel in dressing operation using acoustic emission and neural networks

The grinding operation gives workpieces their final finish, minimizing surface roughness through the interaction between the abrasive grains of a tool (grinding wheel) and the workpiece. However, excessive grinding wheel wear due to friction renders the tool unsuitable for further use, thus requiring the dressing operation to remove and/or sharpen the cutting edges of the worn grains to render them reusable. The purpose of this study was to monitor the dressing operation using the acoustic emission (AE) signal and statistics derived from this signal, classifying the grinding wheel as sharp or dull by means of artificial neural networks. An aluminum oxide wheel installed on a surface grinding machine, a signal acquisition system, and a single-point dresser were used in the experiments. Tests were performed varying overlap ratios and dressing depths. The root mean square values and two additional statistics were calculated based on the raw AE data. A multilayer perceptron neural network was used with the Levenberg-Marquardt learning algorithm, whose inputs were the aforementioned statistics. The results indicate that this method was successful in classifying the conditions of the grinding wheel in the dressing process, identifying the tool as "sharp''(with cutting capacity) or "dull''(with loss of cutting capacity), thus reducing the time and cost of the operation and minimizing excessive removal of abrasive material from the grinding wheel.

Grinding of AISI 4340 steel with interrupted cutting by aluminum oxide grinding wheel

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Evaluation of neural models applied to the estimation of tool wear in the grinding of advanced ceramics

Conselho Nacional de Desenvolvimento Cientifico e Tecnológico (CNPq)

Ultra-precision face grinding with constant pressure, lapping kinematics, and SiC grinding wheels dressed with overlap factor

Several machining processes have been created and improved in order to achieve the best results ever accomplished in hard and difficult to machine materials. Some of these abrasive manufacturing processes emerging on the science frontier can be defined as ultra-precision grinding. For finishing flat surfaces, researchers have been putting together the main advantages of traditional abrasive processes such as face grinding with constant pressure, fixed abrasives for two-body removal mechanism, total contact of the part with the tool, and lapping kinematics as well as some specific operations to keep grinding wheel sharpness and form. In the present work, both U d-lap grinding process and its machine tool were studied aiming nanometric finishing on flat metallic surfaces. Such hypothesis was investigated on AISI 420 stainless steel workpieces U d-lap ground with different values of overlap factor on dressing (Ud=1, 3, and 5) and grit sizes of conventional grinding wheels (silicon carbide (SiC)=#800, #600, and #300) applying a new machine tool especially designed and built for such finishing. The best results, obtained after 10 min of machining, were average surface roughness (Ra) of 1.92 nm, 1.19-μm flatness deviation of 25.4-mm-diameter workpieces, and mirrored surface finishing. Given the surface quality achieved, the U d-lap grinding process can be included among the ultra-precision abrasive processes and, depending on the application, the chaining steps of grinding, lapping, and polishing can be replaced by the proposed abrasive process.