Grinding Wheel Condition Research Articles

Fabrication of Vitrified Bond Diamond Grinding Wheel via LCD Photopolymerization

In this paper, a liquid crystal display (LCD) photopolymerization method is proposed, and a vitrified bond diamond grinding wheel is successfully prepared. A high-performance vitrified bond was obtained by melting SiO2-B2O3-Al2O3-Na2O ceramic raw materials and used for grinding wheel preparation. LCD photopolymerization technology is characterized by high precision in shaping, fast processing speed, and superior quality, making it a promising technology for fabricating vitrified bond diamond grinding wheels. The preparation of vitrified bond slurry with high solid content and low viscosity was extensively investigated to meet the fabrication requirements. The effects of dispersant, the particle size of the vitrified bond, and solid content on the viscosity of the slurry were systematically analyzed. The vitrified bond slurry with solid content up to 65 wt.% (approximately 45.5 vol.%) was successfully prepared and met the requirements for printing. Furthermore, we explored the optimal formulation of the grinding wheel, debinding and sintering conditions, sintering temperature, grit-to-bond ratio, and the evaluation of the grinding performance of the wheel on hard and brittle materials, such as silicon carbide ceramic. Vitrified bond and abrasive slurry systems with a solid content of 65 wt.% (approximately 42.8 vol.%) were prepared. The results show that the vitrified bond diamond grinding wheel exhibits optimal comprehensive performance, with a sintering temperature of 680 °C and a grit-to-bond ratio of 4:6. The minimum surface roughness of the workpiece after grinding was 1.767 μm, the material removal rate was 5.08 mg/s, the grinding ratio was 9.78, and the friction coefficient was stabilized at about 0.5 during grinding. This paper guides the manufacturing of vitrified bond diamond grinding wheels via LCD photopolymerization.

Conditioning and monitoring of grinding wheels: A state-of-the-art review

<p>Grinding wheel condition monitoring is an important step towards the prediction of grinding wheel faulty conditions. It is beneficial to define techniques to minimize the wear of the grinding wheels and finally enhance the life of the grinding wheels. Grinding wheel condition monitoring is done by two techniques such as (i) direct and (ii) indirect. Direct monitoring employs optical sensors and computer vision techniques, and indirect monitoring is done by signal analysis such as acoustic emission (AE), vibration, cutting force, etc. Methods implemented for grinding wheel monitoring in the published research papers are reviewed. The review is compiled in five sections: (a) process parameters measurement, (b) data acquisition systems, (c) signal analysis techniques, (d) feature extraction, and (e) classification methods. In today’s era of Industry 4.0, a large amount of manufacturing data is generated in the industry. So, conventional machine learning techniques are insufficient to analyze real-time conditioning monitoring of the grinding wheels. However, deep learning techniques such as artificial neural network (ANN), convolutional neural network (CNN) have shown prediction accuracy above 99%.</p>

Online prediction of grinding wheel condition and surface roughness for the fused silica ceramic composite material based on the monitored power signal

The fused silica ceramic matrix composite (SiO2f/SiO2) is characterized as one of the most promising materials in radar radomes and wave-transparent antenna windows. However, the ceramic matrix surface is rather rough, which reduces their service life in severe environments. Although precision grinding is used to improve surface quality, it gets difficult to precisely achieve the desired surface requirement due to the SiO2f/SiO2 material hardness, brittleness, and complicated fiber structure, as well as the uncertain wheel conditions. Especially the wheel condition and its influence on surface quality are unable to quantify directly. With the fast development of IoT monitoring and cyber-physical system, online prediction using process physics signals gains more interest. Power monitoring is a convenient way to obtain valuable grinding information at a relatively lower cost, making it more popular in the industry. However, the links between grinding parameters, power signal, and wheel conditions, surface quality is unclear. A series of grinding experiments of the SiO2f/SiO2 workpiece has been designed to demonstrate how the wheel conditions are indicated using the warm-cold density chart of specific grinding energy. A novel exponential polynomial model of surface roughness associated with wheel conditions indicated by the cutting power signal has been built. Compared with the conventional prediction model, REs center, MSE, and Pearson correlation coefficient are improved significantly from −0.0213, 0.029669, and 0.8695 to 0.0022, 0.022478, and 0.8710, respectively.

Tracking changes in grinding wheel condition using reduced features of acoustic emission signals

In this paper, a universal method is proposed to accurately identify wheel state during grinding brittle materials. In contrast with conventional methods relying on adequate repetitive experimental data under the same process conditions, only history acoustic emission (AE) data in the same life cycle of a grinding wheel are needed for current wheel state identification. During grinding process, AE spectra samples are acquired sequentially on a series of nodes with equal interval. Samples on each node are categorized into the same class of wheel state. In the theoretical part, AE spectrum is proved to be suitable for feature representation of the degradation of wheel condition. Linear discriminant analysis is used to project AE spectra samples into a two-dimensional feature space, and the changes of the projection gives a clue to the evolution of wheel state. Two types of commonly used diamond wheels for optical surface grinding, which are straight wheel and cup wheel, were used to verify the general applicability of the method. The experiments were carried out on different machine tools and the two wheels also possessed different degradation process, yet for all of them, the evolution of wheel state can be accurately identified. It was proved that the proposed method can adaptively trace wear stage change of diamond grinding wheel.

Study of the Use of Piezoelectric Diaphragm as a Low-Cost Alternative to the Acoustic Emission Sensor in Dressing Operation of Aluminum Oxide Wheels

Acoustic emission (AE) sensors have been widely used for tool condition monitoring in the grinding process. Recently, the piezoelectric diaphragm (piezoelectric buzzer) was introduced as a low-cost alternative for the same purpose. In this context, the present research work aims to study the efficiency of the piezoelectric diaphragm as a viable substitute to AE sensors in monitoring the dressing of structurally distinct aluminum oxide grinding wheels. Dressing tests were conducted using two industrial wheels, which were subjected to various dressing conditions. The signals generated by the AE and piezoelectric diaphragm sensors were collected simultaneously and subsequently analyzed in both time and frequency domains. The most relevant features related to the dressing were extracted through the following metrics: energy criterion, Pearson correlation coefficient, power spectral density (PSD), fast Fourier transform (FFT), and magnitude-squared coherence (MSC). Correlation greater than 80% was found between the piezoelectric diaphragm and AE sensor signals for determining the actual grinding wheel condition, which indicates the piezoelectric diaphragm as a viable alternative to the commercial AE sensors in dressing operation monitoring.

Machine Learning Models for Predicting Grinding Wheel Conditions Using Acoustic Emission Features

Machine Learning Models for Predicting Grinding Wheel Conditions Using Acoustic Emission Features

Diamond Grinding Wheel Condition Monitoring Based on Acoustic Emission Signals.

Acoustic emission (AE) phenomenon has a direct relationship with the interaction of tool and material which makes AE the most sensitive one among various process variables. However, its prominent sensitivity also means the characteristics of random and board band. Feature representation is a difficult problem for AE-based monitoring and determines the accuracy of monitoring system. It is knottier for the situation of using diamond wheel grinding optical components, not only because of the complexity of grinding process but also the high requirement on surface and subsurface quality. This paper is dedicated to AE-based condition monitoring of diamond wheel during grinding brittle materials and feature representation is paid more attention. AE signal of brittle-regime grinding is modeled as a superposition of a series of burst-type AE events. Theory analysis manifested that original time waveform and frequency spectrum are all suitable for feature representation. Considering the convolution form of b-AE in time domain, a convolutional neural network with original time waveform of AE signals as the input is built for multi-class classification of wheel state. Detailed state division in a wheel’s whole life cycle is realized and the accuracy is over 90%. Different from the overlapping in time domain, AE components of different crack mechanisms are probably separated in frequency domain. From this point of view, AE spectrums are more suitable for feature extraction than the original time waveform. In addition, the time sequence of AE samples is essential for the evaluation of wheel’s life elapse and making use of sequential information is just the idea behind recurrent neural network (RNN). Therefore, long short-term memory (LSTM), a special kind of RNN, is used to build a regression prediction model of wheel state with AE spectrums as the model input and satisfactory prediction accuracy is acquired on the test set.

AE signature analysis using continuous and discrete wavelet transforms to predict grinding wheel conditions

In this study, experiments were conducted in a surface grinding operation to acquire and analyze the AE signature to establish a statistical correlation between Acoustic Emission features extracted in wavelet domain with grinding wheel conditions. Grinding wear plot was established to identify the grinding wheel conditions by monitoring the wear in the abrasive grinding wheel and workpiece. Continuous and Discrete Wavelet transforms were carried out to extract the wavelet coefficients. Decision Tree based statistical models were built using discrete and continuous wavelet coefficients. The performance of J48 Decision tree and Classification and Regression Decision Tree (CART) are compared using the classification accuracy and kappa statistics measures. In discrete wavelet transforms, wavelet coefficients are extracted using four mother wavelets namely Haar, Daubechies, Symlet, and Coiflet. In Continuous Wavelet Transforms, the Morlet wavelet is used to extract the 1D wavelet coefficients using 2D scalograms.

An efficient short-time Fourier transform algorithm for grinding wheel condition monitoring through acoustic emission

Indirect methods to monitor the surface integrity of grinding wheels by acoustic emission (AE) have been proposed, aiming to ensure their optimal performance. However, the time-frequency analysis of the content of these signals has not been addressed in the literature. AE signal analysis performed only in the frequency domain makes it impossible to locate faults on the grinding wheel surface during the dressing operation and examine the behavior of the frequencies contained in these signals over time. In this regard, the time-frequency analysis of AE signals during dressing through STFT (short-time Fourier transform) can contribute toward the proposal of new monitoring methodologies, thus reflecting the optimization of the grinding process. This paper proposes an algorithm based on the Kaiser window to adjust the STFT parameters to ensure an appropriate balance between time-frequency resolutions. Besides, this algorithm is used to investigate the characteristic frequencies in the aluminum oxide grinding wheel in dressing operation. The results indicate that the spectral content of the AE signals during dressing follows a uniform behavior, but their amplitude changes depending on the characteristics of topography and sharpness of the grinding wheel cutting edges.

Grinding Wheel Loading Evaluation by Using Acoustic Emission Signals and Digital Image Processing.

In the manufacturing industry, grinding is used as a major process for machining difficult-to-cut materials. Grinding is the most complicated and precise machining process. For grinding machines, continuous generating gear grinding machines are widely used to machine gears which are essential machine elements. However, due to its complicated process, it is very difficult to design a reliable measurement method to identify the grinding wheel loading phenomena during the grinding process. Therefore, this paper proposes a measurement method to identify the grinding wheel loading phenomenon in the grinding process for continuous generating gear grinding machines. In the proposed approach, an acoustic emission (AE) sensor was embedded to monitor the grinding wheel conditions; an offline digital image processing technique was used to determine the loading areas over the surface of Al2O3 grinding wheels; and surface roughness of the ground workpiece was measured to quantify its machining quality. Then these three data were analyzed to find their correlation. The experimental results have shown that there are two stages of grinding in the grinding process and the proposed measurement method can provide a quantitative grinding wheel loading evaluation from the AE signals online.

Cubic boron nitride wheel topography effects on phase transformation of maraging C250 steel and grinding surface quality

It is likely for the interaction between the cubic boron nitride grains on the working surface of grinding wheels and maraging C250 steel workpiece to cause phase transformation, thus reducing the material removal rates and affecting the quality of the workpiece surface generated during grinding. Up to now, there remain few studies focusing on the relationship between grinding wheel topography and phase transformation. In this study, an analysis was conducted of the effects that the topography of cubic boron nitride grinding wheel has on the distribution of phase transformation and the surface quality of maraging steel during grinding. The phase transformation diffraction curve was plotted based on the results of X-ray diffraction (XRD) analysis, and then, it was compared with the known data under different grinding wheel conditions. The topography of the cubic boron nitride grinding wheel was characterized using 3D digital microscope analysis, and the dynamic abrasive grit density coefficient λd for micro-grinding was proposed to clarify the effect of relevant parameters on phase transformation. The surface quality of grinding wheel and workpiece after grinding was analyzed, while the combination of different grinding wheel topography parameters and the process optimization scheme were proposed to achieve the optimal effect of grinding.

Grinding wheel condition prediction with discrete hidden Markov model using acoustic emission signature

Tool Condition Monitoring (TCM) is a vital activity to monitor and maintain the quality of products manufactured in any machining process without any manual intervention. Hidden Markov Models (HMM) are developed in this study for predicting grinding wheel conditions in the auto-feed surface grinding process using Acoustic Emission (AE) signatures captured during the grinding operation. A correlation between AE features and tool conditions are established using Baum-Welch and Viterbi algorithms. HMMs proposed in this study are integrated with the K-means clustering algorithm. The clustered data are represented as an integer sequence and are divided into three tool states such as ‘sharp’, ‘intermediate’ and ‘worn out’. HMM, models are created for each state of the grinding wheel. The performances of the HMMs are evaluated using log-likelihood measure. It is observed that HMM models build with AE–RMS feature are predicting the grinding wheel conditions with good accuracy.

An Intelligent System for Grinding Wheel Condition Monitoring Based on Machining Sound and Deep Learning

Immediate monitoring of the conditions of the grinding wheel during the grinding process is important because it directly affects the surface accuracy of the workpiece. Because the variation in machining sound during the grinding process is very important for the field operator to judge whether the grinding wheel is worn or not, this study applies artificial intelligence technology to attempt to learn the experiences of auditory recognition of experienced operators. Therefore, we propose an intelligent system based on machining sound and deep learning to recognize the grinding wheel condition. This study uses a microphone embedded in the grinding machine to collect audio signals during the grinding process, and extracts the most discriminated feature from spectrum analysis. The features will be input the designed CNNs architecture to create a training model based on deep learning for distinguishing different conditions of the grinding wheel. Experimental results show that the proposed system can achieve an accuracy of 97.44%, a precision of 98.26% and a recall of 96.59% from 820 testing samples.

Real-time Grinding Wheel Condition Monitoring Using Linear Imaging Sensor

Grinding is a widely used process in precision finishing of machined part surfaces. Grinding wheels, the key component of the grinding process, consist of a mixture of abrasive grains and bonding materials with or without a metal core. During the grinding process, the grits are either removed or broken on the wheel surface due to multiple mechanisms. Such tool wear on grinding wheel determines the quality of the ground surface as well as the part dimension accuracy and machining efficiency. This work presents a new method to monitor the health status of the grinding wheel using linear Charge-coupled Device (CCD) sensor, which captures one-dimensional grayscale images of the grinding wheel surface. The statistical features were extracted from the sensor data to estimate the present tool wear. Compared to general camera imaging method, the proposed approach is able to achieve high speed sampling with the CCD sensor to scan across the width of wheel in milliseconds, which enables the method a potential solution for monitoring the wheel condition in real-time. The method was tested by capturing surface images of a silicon carbide wheel on a commercial grinding machine. Statistical features such as standard deviation, kurtosis, and entropy were extracted from the grayscale color intensity of the image data and compared to the measured wheel life represented by the counted grinding cycles. The statistical features were fused by an Artificial Neural Network (ANN) model to estimate the life of the grinding wheel. Experimental results show a good match between the estimated and true wheel life with an average error less than 5%.

An intelligent monitoring system of grinding wheel wear based on two-stage feature selection and Long Short-Term Memory network

Grinding wheel condition is considered as the key factor affecting grinding performance, and therefore, accurate monitoring of wheel wear is necessary to prevent the deterioration of part quality. An intelligent wheel wear monitoring system is introduced in this article to realize processing of grinding signal, extraction of signal features, selection of optimal feature subset, and prediction of wheel wear. Physical information generated during the grinding of C-250 maraging steel is collected by a dynamometer, accelerometer, and acoustic emission sensor, and a large quantity of features in time domain and frequency domain are extracted from the processed grinding signals. To reduce feature redundancy and increase relevancy of feature to wheel wear, a two-stage feature selection approach combining filter and wrapper framework is proposed. The filter preselects individual features by minimum Redundancy Maximum Relevance method, while the wrapper evaluates different feature subsets by the model performance. A deep learning network structure named Long Short-Term Memory network is adopted to develop the wheel wear monitoring model and is compared with a conventional machine learning algorithm, Random Forest. The results have shown that the two-stage feature selection method is able to provide the globally optimal feature subset for the model. Long Short-Term Memory model achieves an R2 of 0.994 and a root-mean-square error of 0.240 with four features, while Random Forest model obtains an R2 of 0.980 and a root-mean-square error of 0.463 with seven features, which indicates that Long Short-Term Memory model is capable of predicting wheel wear more accurately even with less features.

Analysis of chip shape distribution using image processing technology to estimate wearing condition of gear grinding wheel

The chip shape distribution changes due to grinding wheel wear in surface and cylindrical grinding. However, in gear grinding, the relationship between wear and distribution has not been clarified. To investigate the relationship, in this study, we collected chips from repeated gear grindings. For rough grinding, wherein the cutting quantity is large, the gear surface became rougher with each repetition. Analysis of images of individual chips revealed unexpected change in the chip shape distribution even when the number of grinding processes increased. The surface property of work pieces was determined more dominant by finishing grinding than rough grinding.

A pneumatic sensor for grinding wheel condition monitoring

This paper presents the proof-of-concept of a pneumatic sensor for monitoring the performance of grinding wheels. The system concurrently considers the static and dynamic components of the back pressure signal, which refer to the position and topography of the functional wheel surface, respectively. Auxiliary experiments and numerical simulations are presented to demonstrate that the dynamic back pressure variations do indeed correspond to wheel topographic features. The performance of the sensor is evaluated with respect to wheel dressing, progressive wheel wear and grinding burn. The monitoring capability of the sensor is confirmed to be not compromised by the application of a flood coolant.

An Intelligent Grinding Wheel Wear Monitoring System Based on Acoustic Emission

Acoustic emission (AE) signals can provide tool condition that is critical to effective process control. However, how to process the data and extract useful information are challenging tasks. This paper presented an intelligent grinding wheel wear monitoring system which was embedded in a surface grinding machine. An AE sensor was used to collect the grinding signals. The grinding wheel wear condition features were extracted by a proposed novel method based on statistics analysis of the average wavelet decomposition coefficient. The detailed signal characteristics during different wear condition are described. A BP neural network was used to classify the conditions of the grinding wheel wear. The inputs of the neural network were the three extracted features, and the outputs were three different states of grinding wheel condition, namely primary wear, intermediate wear and serious wear. The intelligent monitoring system was evaluated through grinding experiments. The results indicate that the effectiveness of the proposed method for extracting features of AE signals and developed intelligent grinding wheel wear monitoring system are satisfied.

Focus on Carbide-Tipped Circular Saws when Cutting Stainless Steel and Special Alloys

Circular saw blades are used exclusively for cut-off work, ranging from small manual feed operations, up to very large power fed saws commonly used for sectioning stock as it comes from a rolling mill or other manufacturing processes for long products. The teeth profile, as well as the tooth configuration are of fundamental importance for the blade performances; through a combination of blade rigidity and grinding wheel condition a good quality surface finish is attained for tools of commercial standard. The materials used for the production of circular saw blades are ranging from high speed steel to cemented carbides. In particular, cemented carbides, being characterized by high hardness and strength, are used in applications where materials with high wear resistance and toughness are required. The main constituents of cemented carbides are tungsten carbide and cobalt. Tungsten carbide imparts the alloys the necessary strength and wear resistance, whereas cobalt contributes to the toughness and ductility of the alloys. The WC-Co alloys are tailored for specific applications by the proper choice of tungsten carbide grain size and the cobalt content. The grain size of the tungsten carbide in WC-Co varies from about 40 µm to around 0.3 µm, the cobalt content from 3 to 30 wt%. The coarse grained hardmetals are mainly used in mining applications, the smallest grain size being about 3 µm and the minimum cobalt content 6 wt%. The grain size of tungsten carbide in the metal cutting industry, as well as for universal applications lies in the range of 1-2 µm. However, with the advent of near net shape manufacturing and thin walled components, the use of submicron carbide is growing, since their high compressive strength and abrasive wear resistance can be used to produce tools with a sharp cutting edge and a large positive rake angle.In this invited paper, a general overview on the actual trends in the choice of the best material when cutting special alloys will be presented and discussed. Based on the recent and past literature some examples of their up-to-date application, such as circular saws used to cut stainless steels and some high strength alloys, are talk over.

Improving Grindability of Inconel 600 Using Alumina Wheel through Pneumatic Barrier Assisted Fluid Application

A Stiff Air Layer, Formed around a Rotating Grinding Wheel, Tends to Restrict Grinding Fluid Penetrate Deep inside the Grinding Zone. for this, much Fluid Is Wasted, and Thermal Defects in Grinding May Not Be Controlled. in the Present Experimental Work, a Flood Cooling System with Pneumatic Barrier Is Used for Delivering Grinding Fluid. the Pneumatic Barrier Breaks the Stiff Air Layer, and Therefore, Grinding Fluid Reaches Grinding Zone. an Exotic Nickel Base Alloy, Inconel 600, Is Taken for Surface Grinding Experiments Using an Infeed of 30 µm under Different Environmental Conditions. the Effect of Different Experimental Conditions Is Investigated in Respect of Grinding Force, Chip Formation, Surface Quality and Wheel Condition. the Experimental Result Shows that Grinding Forces and Wheel Wear Are Remarkably Reduced, and Favourable Chips and Good Surface Quality Are Obtained with the Use of Flood Cooling along with Pneumatic Barrier Setup Compared to other Environmental Conditions.