Automatic detection of thermal damage in grinding process by artificial neural network

Esse trabalho tem por objetivo o desenvolvimento de um sistema inteligente para detecção da queima no processo de retificação tangencial plana através da utilização de uma rede neural perceptron multi camadas, treinada para generalizar o processo e, conseqüentemente, obter o limiar de queima. em geral, a ocorrência da queima no processo de retificação pode ser detectada pelos parâmetros DPO e FKS. Porém esses parâmetros não são eficientes nas condições de usinagem usadas nesse trabalho. Os sinais de emissão acústica e potência elétrica do motor de acionamento do rebolo são variáveis de entrada e a variável de saída é a ocorrência da queima. No trabalho experimental, foram empregados um tipo de aço (ABNT 1045 temperado) e um tipo de rebolo denominado TARGA, modelo ART 3TG80.3 NVHB.

Application of the Minimum Quantity Lubrication (MQL) Technique in the Plunge Cylindrical Grinding Operation

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

Production grinding burn detection using acoustic emission and electric power signals

This work uses a monitoring system based on a PC platform, where the acoustic emission and electric power signals generated during the grinding process are used to investigate superficial burning occurrence in a surface grinding operation using two types of steel, three grinding conditions and an Al203 vitrified grinding wheel. Acoustic emission signals on the workpiece and grinding power were measured during a surface plunge operation until the grinding burn happened. From the results the standard deviation of the acoustic emission signal and the maximum electric power were calculated for each grinding pass. The proposed DPO parameter is the product between the power level and acoustic emission standard deviation. The results show that both signals can be used for burning detection, and the parameter DPO is the best indicator for the burning studied in this work. This can be explained by the high dispersion of the acoustic emission RMS level associated to the high power consumption when the grinding wheel lose its sharpness.

Advanced ceramics: Evaluation of the mechanism of stock removal and ground surface quality

The aim of this work is to evaluate the mechanism of stock removal and the ground surface quality of advanced ceramics machined by a surface grinding process using diamond grinding wheels. The analysis of the grinding performance was done regarding the cutting surface wear behavior of the grinding wheel for ceramic workpieces. The ground surface was evaluated using Scanning Electron Microscopy (SEM). As a result it can be said that the mechanism of material removal in the grinding of ceramic is largely one of brittle fracture. The increase of the hmax can reduce the tangential force required by the process. Although, it results in an increase in the surface damage, reducing the mechanical properties of the ground component.

In-process thermal damage detection in grinding with monitoring via Internet

This work aims the development of a dedicated system for detection of burning in surface grinding process, where the process will constantly be monitored through the acoustic emission and electric power of the induction motor drive. Acquired by an analog-digital converter, algorithms process the signals and a control signal is generated to inform the operator or interrupt the process in case of burning occurrence. Moreover, the system makes possible the process monitoring via Internet. Additionally, a comparative study between parameters DPO and FKS is carried through. In the experimental work one type of. steel (ABNT-1020 annealed) and one type of grinding wheel referred to as TARGA, model ART 3TG80.3 NVHB, were employed.

Control of thermal damage in grinding by digital signal processing of raw acoustic emission

Grinding process is usually the last finishing process of a precision component in the manufacturing industries. This process is utilized for manufacturing parts of different materials, so it demands results such as low roughness, dimensional and shape error control, optimum tool-life, with minimum cost and time. Damages on the parts are very expensive since the previous processes and the grinding itself are useless when the part is damaged in this stage. This work aims to investigate the efficiency of digital signal processing tools of acoustic emission signals in order to detect thermal damages in grinding process. To accomplish such a goal, an experimental work was carried out for 15 runs in a surface grinding machine operating with an aluminum oxide grinding wheel and ABNT 1045 e VC131 steels. The acoustic emission signals were acquired from a fixed sensor placed on the workpiece holder. A high sampling rate acquisition system at 2.5 MHz was used to collect the raw acoustic emission instead of root mean square value usually employed. In each test AE data was analyzed off-line, with results compared to inspection of each workpiece for burn and other metallurgical anomaly. A number of statistical signal processing tools have been evaluated.

Finishing of flat parts led by lapping kinematics on abrasive disc dressed in agreement with overlap factors

This paper discusses the investigation of an abrasive process for finishing flat workpieces, based on the combination of important grinding and lapping characteristics. Instead of loose abrasive grains between the workpiece and the lapping plate, a resinoid grinding wheel of hot-pressed silicon carbide is placed on the plate of a device resembling a lapping machine. The resin bond grinding wheel is dressed with a single-point diamond. In addition to keeping the plate flat, dressing also plays the role of interfering in the behavior of the process by varying the overlap factor (Ud). It was found that the studied process simplify the set-up and can be controlled more easily than in lapping, whose is a painstaking process. The surface roughness and flatness deviation proved comparable to those of lapping, or even finer than it, with the additional advantage of a less contaminated workpiece surface with a shiny appearance. The process was also monitored by acoustic emission (AE), which indicates to be a promissing and suitable technique for use in this process. Copyright © 2008 by ASME.

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.

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)

Operator's manual : grinding machine, cylinder head (Cedar Rapids Engineering model 860), FSN 4910-889-2051.

"February 1969."

Operator's manual : grinding kit, valve seat, electric 35 degree angle type concentric drive, 1/4 horsepower, AC/DC, single phase, 115-volt, 14000 RPM rated no load speed (K.O. Lee Company model P300BB) (4910-060-9983) and (K.O. Lee Company model P300BB-M2) (4910-473-6437).

"February 1965."

Operator's manual : grinding kit, valve seat, electric, 35 degree angle, concentric drive, driver, AC/DC, 115-volt, 7,500 RPM rated no load speed (Albertson and Company model 1712-M) (4910-060-9983).

"June 1965."

Operator's manual : grinding machine, machine tool attachment, internal and external grinding, 5" maximum external diameter wheel, 1/4" minimum internal diameter wheel, 4,600 to 42,400 rpm spindle speed, 1/2 hp, AC/DC, 115 V, 60-C, single phase (Dumore series 5) ...

"October 1967."