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

2003 ◽  
Vol 56 (4) ◽  
pp. 295-300 ◽  
Author(s):  
Fábio Romano Lofrano Dotto ◽  
Paulo Roberto de Aguiar ◽  
Eduardo Carlos Bianchi ◽  
Rogério Andrade Flauzino ◽  
Gustavo de Oliveira Castelhano ◽  
...  
Keyword(s):  
Neural Network ◽  
Thermal Damage ◽  
Intelligent System ◽  
Grinding Wheel ◽  
Grinding Process ◽  
Output Variable ◽  
The Neural Network ◽  
Wheel Drive ◽  
Drive Motor ◽  
Grinding Conditions

This work aims to develop an intelligent system for detecting the workpiece burn in the surface grinding process by utilizing a multi-perceptron neural network trained to generalize the process and, in turn, obtnaing the burning threshold. In general, the burning occurrence in grinding process can be detected by the DPO and FKS parameters. However, these ones were not efficient at the grinding conditions used in this work. Acoustic emission and electric power of the grinding wheel drive motor are the input variable and the output variable is the burning occurrence to the neural network. In the experimental work was employed one type of steel (ABNT-1045 annealed) and one type of grinding wheel referred to as TARGA model ART 3TG80.3 NVHB.

An intelligent system for selection of grinding wheels

1997 ◽  
Vol 211 (8) ◽  
pp. 635-641 ◽  
Author(s):  
Y Li ◽  
B Mills ◽  
W B Rowe
Keyword(s):  
Neural Network ◽  
Intelligent System ◽  
Back Propagation ◽  
Grinding Wheel ◽  
Neural Network System ◽  
Grinding Conditions ◽  
Training Examples ◽  
Using Data ◽  
Hidden Layer ◽  
Propagation Network

This paper describes the development of a neural network system for grinding wheel selection. The system employs a back-propagation network with one hidden layer and was trained using data from reference handbooks. It is shown that a neural network is capable of learning the relationship between the wheel and the grinding process without a requirement for rules or equations. It was further found that a relatively small number of training examples allows the system to produce reliable recommendations for a much greater number of combinations of grinding conditions. The system was developed on a PC using the C++ programming language.

The Adaptive Control of Grinding Force of CNC Cam Grinder Based on Neural Network

2012 ◽  
Vol 217-219 ◽  
pp. 2051-2055
Author(s):  
Ming Li Xie ◽  
Ling Lu
Keyword(s):  
Neural Network ◽  
Adaptive Control ◽  
Control Method ◽  
Metal Removal ◽  
Removal Rate ◽  
Grinding Force ◽  
Control Measures ◽  
Numerical Control ◽  
Grinding Wheel ◽  
Grinding Process

In the process of cam grinding, the fluctuation of grinding force can lead to the abnormal wear of the grinding wheel, the decrease of the grinding surface quality and even the damage of the grinding process system. The paper took the grinding process of numerical control cam grinding machine as research subject, the grinding force mathematical model was built, the indirect test and control measures were researched and an adaptive control method based on neural network was proposed and applied to the grinding force control of the cam grinding process. At last, the controller was designed and the grinding simulation was performed with MATLAB, which proved that the system could solve the fluctuation of grinding force during the process of cam grinding and the controller was equipped with good dynamic characteristic. The results indicate that the method can realize the purpose of optimal metal removal rate and enhance the grinding quality of cams.

scholarly journals A dynamic model of cylindrical plunge grinding process for chatter phenomena investigation

2018 ◽  
Vol 148 ◽  
pp. 09004
Author(s):  
Paweł Lajmert ◽  
Małgorzata Sikora ◽  
Dariusz Ostrowski
Keyword(s):  
Degrees Of Freedom ◽  
Stability Limit ◽  
Element Model ◽  
Grinding Wheel ◽  
Grinding Process ◽  
Plunge Grinding ◽  
Chatter Vibrations ◽  
Grinding Conditions ◽  
The Stability ◽  
Improved Model

In the paper, chatter vibrations in the cylindrical plunge grinding process are investigated. An improved model of the grinding process was developed which is able to simulate self-excited vibrations due to a regenerative effect on the workpiece and the grinding wheel surface. The model includes a finite-element model of the workpiece, two degrees of freedom model of the grinding wheel headstock and a model of wheel-workpiece geometrical interferences. The model allows to studying the influence of different factors, i.e. workpiece and machine parameters as well as grinding conditions on the stability limit and a chatter vibration growth rate. At the end, simulation results are shown and compared with exemplified real grinding results.

Grinding Vibration Detection Using a Neural Network

1996 ◽  
Vol 210 (4) ◽  
pp. 349-352 ◽  
Author(s):  
X Chen ◽  
W B Rowe ◽  
Y Li ◽  
B Mills
Keyword(s):  
Neural Network ◽  
Grinding Wheel ◽  
Wheel Wear ◽  
Objective Criterion ◽  
Neural Network Approach ◽  
Wear Process ◽  
Vibration Detection ◽  
The Neural Network ◽  
Approach Method ◽  
Band Pass

The amplitude of grinding vibration increases gradually throughout the grinding wheel wear process. In the meantime the predominant vibration frequency shifts in a region close to a natural frequency of the system. The complex time-varying pattern of vibrations makes it a problem to objectively identify when the grinding vibration becomes unacceptable and when the wheel should be redressed. A neural network approach method was proposed in this paper to identify the wheel life. The signal data were pre-treated by eight-band-pass filters, which covered the whole frequency range of the grinding chatter. These pre-treated data were used as the inputs to the neural network. By training the neural network, an objective criterion can be determined for the wheel redress life.

Adaptive Grinding Process—Prevention of Thermal Damage Using OPC-UA Technique and In Situ Metrology

2017 ◽  
Vol 139 (12) ◽  
Author(s):  
Matthias Steffan ◽  
Franz Haas ◽  
Alexander Pierer ◽  
Gentzen Jens
Keyword(s):  
Thermal Damage ◽  
Control Variable ◽  
Safety Margin ◽  
Value Added ◽  
Grinding Wheel ◽  
Grinding Process ◽  
Production Chain ◽  
Process Step ◽  
Edge Zone ◽  
Control Concept

The production process grinding deals with finishing of hardened workpieces and is one of the last stages of the value-added production chain. Up to this process step, considerable costs and energy have been spent on the workpieces. In order to avoid production rejects, significant safety reserves are calculated according to the present state of the art. The authors introduce two approaches to minimize the safety margin, thus optimizing the process’ economic efficiency. Both control concepts use the feed rate override of the machining operation as regulating variable to eliminate thermal damage of the edge zone. The first control concept is developed to avoid thermal damage in cylindrical plunge grinding by controlling the cutting forces. Therefore, the industrial standard Open Platform Communications Unified Architecture (OPC-UA) is used for the communication between a proportional–integral–derivative (PID) controller and the SINUMERIK grinding machine tool control system. For noncircular workpieces, grinding conditions change over the circumference. Therefore, thermal damage cannot be ruled out at any time during the grinding process. The authors introduce a second novel control approach, which uses a micromagnetic measure that correlates with thermal damage as the main control variable. Hence, the cutting ability of the grinding wheel and thermal damage to the workpiece edge zone is quantified in the process. The result is a control concept for grinding of noncircular workpieces, which opens up fields for major efficiency enhancement. With these two approaches, grinding processes are raised on higher economic level, independently of circular and noncircular workpiece geometries.

Effects of Relative Velocity on Grinding Performances under Si Wafer Rotary Grinding

2016 ◽  
Vol 874 ◽  
pp. 395-400
Author(s):  
Jumpei Kusuyama ◽  
Takayuki Kitajima ◽  
Akinori Yui ◽  
Toshihiro Ito
Keyword(s):  
Surface Roughness ◽  
Power Consumption ◽  
Relative Velocity ◽  
Velocity Ratio ◽  
Grinding Wheel ◽  
Grinding Process ◽  
Wafer Thickness ◽  
Grinding Conditions ◽  
The Difference ◽  
Si Wafer

For the backgrinding of semiconductor devices, a rotary grinding process is indispensable for achieving the required wafer thickness. The relative velocity between the grinding wheel and the wafer is maximum at the periphery of the wafer and minimum at the center of wafer. Generally, the grinding performances are discussed in terms of the ratio of the rotational speeds of the grinding wheel and the wafer. However, it is not possible to use this ratio to determine the grinding conditions for different wafer sizes grinding as this ratio does not show the difference in relative velocity. Therefore, a new relative velocity ratio was defined in this study. Then, the Si wafer grinding was performed to investigate the effect of the surface roughness and the power consumption of the grinding wheel spindle on the relative velocity ratio.

Research on Intelligent Forecasting of Financial Market Parameter Time Series Based on Deep Learning

2021 ◽  
Vol 7 (5) ◽  
pp. 4596-4607
Author(s):  
Enyang Zhu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Deep Learning ◽  
Financial Markets ◽  
Intelligent System ◽  
System Modeling ◽  
Layer By Layer ◽  
Healthy Development ◽  
The Neural Network ◽  
Deep Integration

Objectives: Deep learning has become the most representative and potential intelligent system modeling technology in artificial intelligence. However, the complexity of financial markets goes far beyond all economic games. Methods: This paper is devoted to the feasibility and efficiency of the deep-integration neural network model as one of the main paradigms of in-depth learning in the intelligent prediction of financial time. A prediction model of stack self-coding neural network composed of bottom stack self-coding and top regression neurons is proposed. Results: Firstly, the self-encoder unsupervised learning mechanism is used to identify and learn the time series, and the layers of the neural network are learned greedy layer by layer. Then the stack self-encoder is extended to the SAEP model with supervised mechanism, and the parameters learned by SAE are used. Used to initialize the neural network, and finally use the supervised learning to fine-tune the weights. Conclusion: The research results show that the model provides effective financial planning and decision-making basis for financial forecasting, maintains the healthy development of financial markets, and maximizes the benefits of profit-making institutions.

scholarly journals Análise de Sinais de Emissao Acústica e Estatística Counts na Detecção da Alteração Microestrutural na Retificação de Aço 1045

2018 ◽  
Vol 3 (1) ◽  
pp. 414
Author(s):  
Felipe Aparecido Alexandre ◽  
Martin Antonio Aulestia Viera ◽  
Pedro Oliveira Conceição Junior ◽  
Leonardo Simões ◽  
Wenderson Nascimento Lopes ◽  
...  
Keyword(s):  
Acoustic Emission ◽  
Value Added ◽  
Grinding Wheel ◽  
Grinding Process ◽  
Frequency Bands ◽  
Finishing Process ◽  
Grinding Conditions ◽  
Grinding Machine ◽  
1045 Steel ◽  
Selection Of

Grinding is a high-precision, high-value-added finishing process as it is usually the last stage of the manufacturing chain. However, unsatisfactory results may occur, mainly due to changes in the microstructure of the ground workpiece. Such changes are caused by the high temperatures involved in the process due to the grinding conditions in which the part was subjected. In this way, the main objective of this work is the monitoring of the grinding process in order to detect changes in the signal and to relate them with damage occurred in the ground workpiece. The tests were carried out on a surface grinding machine, aluminum oxide grinding wheel and ABNT 1045 steel parts. Metallography was performed on the parts for a more further analysis of their microstructure. The recording of signals was obtained at a sample rate of 2 MHz through an acoustic emission sensor (AE). A frequency study for the selection of the best frequency bands that characterize damage occurred in the ground workpiece. The event counts statistic was applied to the filtered signal in the chosen frequency bands. The results of this work show that the grinding conditions influence the signal and, therefore, its frequency spectrum.Keywords: Manufacturing process; automation, monitoring; grinding process; acoustic emission, damage detection

scholarly journals Surface microgeometry treated with a precast textured grinding wheel

2020 ◽  
Vol 329 ◽  
pp. 03019
Author(s):  
Vladimir Gusev
Keyword(s):  
Surface Layer ◽  
Thermal Damage ◽  
Transverse Plane ◽  
Grinding Wheel ◽  
Grinding Process ◽  
Geometric Errors ◽  
Time Process ◽  
Cutting Surface ◽  
Surface Microgeometry ◽  
Textured Grinding Wheel

The article considers the formation of the geometry of internal cylindrical surfaces when grinding with a precast textured wheel, which is under the influence of the unbalances main vector and a variable cutting force caused by the discreteness of the cutting surface (texture). Under the influence of these factors, each point of the axis of the textured tool makes vibrations in the transverse plane in the form of a wavelike sinusoid consisting of two sinusoids. The Space-time process of forming the processed surface is mathematically described. It is in applying wavelike sinusoids to the workpiece, taking into account their phase shift at each revolution of the workpiece. To ensure minimal geometric errors at the maximum possible productivity of the grinding process, phase shifts φf = (0.07–0.12)π and φf = (0.88–0.93)π are recommended. The results of the study are recommended for use in the production of high-precision details, primarily from materials that are prone to thermal damage to the surface layer under the influence of high temperature in the grinding zone.

A Model of the Fluid Convective Cooling in Grinding Process

2013 ◽  
Vol 797 ◽  
pp. 299-304 ◽  
Author(s):  
Lei Zhang ◽  
Michael N. Morgan
Keyword(s):  
Heat Transfer ◽  
Convective Heat Transfer ◽  
Convective Heat ◽  
Convective Heat Transfer Coefficient ◽  
Grinding Wheel ◽  
Process Conditions ◽  
Transfer Model ◽  
Grinding Process ◽  
Fluid Properties ◽  
Grinding Conditions

The grinding process has particular interest in that contact temperatures have great significance for quality and integrity of machined surfaces. Hardened surfaces may be damaged by softening and or being stressed, being hardened or re-hardened, burned or cracked. It is important in grinding for the fluid to remove heat from the grinding contact zone to avoid thermal damage to the workpiece surface and/or sub-surface layers. The cooling effect of grinding fluid can be quantified by the convective heat transfer coefficient (CHTC) acting in the grinding zone. This paper presents values of the CHTC based on measured grinding temperatures. The paper also presents a new convective heat transfer model based on principles of applied fluid dynamics and heat transfer. Predicted values for the CHTC calculated from the model are compared with results from experiment obtained under a range of grinding conditions and with experimental data. The results demonstrate that the new CHTC model improves the accuracy of prediction and helps explain the variation in the value of CHTC under varying process conditions. Results also show that convection efficiency strongly depends on the grinding wheel speed, grinding arc length and fluid properties.

Sign in / Sign up

Export Citation Format

Share Document