Monitoring Of Surface Roughness Research Articles

Microservice-based digital twin system towards smart manufacturing

Digital Twin (DT) is a promising technology that offers versatile services to enhance manufacturing intelligence. However, the agility, reliability and analysis capabilities of existing DT services are severely challenged when applied and deployed at large-scale production lines. To address the aforementioned issues, a microservice-based DT system with redundant architecture is proposed. First, a scalable microservice-based DT system compatible with standard and tailored plug-and-play DT services is constructed for DT protocol adaptation, stream processing, information and model management. Concurrently, a generic information model is proposed to represent the entire production lifecycle from design, operation, and maintenance in a structured manner. Second, an industrial multi-task DT model is introduced, leveraging the aforementioned architecture, to effectively achieve parallel monitoring of surface roughness and tool wear. Finally, industrial manufacturing cases are introduced to verify the feasibility and effectiveness of the proposed system. The results show that heterogeneous DT data are transferred and managed reliably, with a mean absolute percentage error of 1.28% for surface roughness prediction, and 85.71% accuracy in tool wear diagnosis.

The role of carbon capping and Ar pressure on SiC surface degradation during high temperature annealing

High temperature annealing (>1600°C) is commonly employed to activate dopants and recover the SiC lattice after ion implantation. Despite extensive studies monitoring surface roughness after annealing, a lack of understanding persists on how the carbon-cap (C-cap) effectively protects the SiC surface and prevents Si sublimation. This study investigates the role of the C-cap and ambient Ar pressure on SiC surface degradation. 4H-SiC wafers were implanted with 60 keV 1x1015 cm−2 Al+ at 700°C and annealed from 1650°C to 1950°C with a pyrolyzed C-cap. Transmission electron microscopy (TEM) and atomic force microscopy (AFM) were used to study the evolution of the C-cap and SiC surface. The C-cap impacted the surface degradation morphology, from step-bunching to surface pitting above 1750°C, resulting in disordered graphite that does not conform or grow uniformly at the SiC surface. This is dramatically worsened at reduced Ar pressure. No Si accumulation was observed in the C-cap or at the interface, suggesting the C-cap is not a diffusion barrier to Si sublimation under our conditions. It is proposed that when a cap is present, the limiting step for SiC degradation is related to the crystallization and diffusion of C atoms as they form graphite, more than Si sublimation.

Deep-learning-assisted online surface roughness monitoring in ultraprecision fly cutting

Deep-learning-assisted online surface roughness monitoring in ultraprecision fly cutting

Leveraging IoT in Auto Component Manufacturing to Monitor Surface Roughness and Tool Temperature

Surface finish is an important requirement in Auto Component Manufacturing that defines the quality of work piece obtained from turning operations. Thus to reduce downtime due to rejection of work piece for its surface finish a continuous monitoring of surface roughness based on its cutting parameter and vibration signal is required. Similarly it is also important to monitor the cutting tool temperature to have a longer tool life. With the emerging trend of Internet-of-Things (IoT) it has become very easy to collect the required data, storing it, analysing it and also alerting the required personnel through the mobile application, e-mail and SMS. The stored data and analysis could reveals in depth the process, which leaves a large scope for improvement of the system. The paper discusses the implementation of IoT to collect data of vibration signal and cutting tool temperature of dry turning operation, for cutting parameter like 1) spindle speed 2) feed rate and 3) depth of cut for three different material mild steel (MS), brass and aluminium (Al). A correlation was obtained to predict surface roughness and tool temperature. The system developed could give a real time monitoring of surface roughness on a smart phone that can be used as a tool for optimizing the turning process to give improved quality and increased production volume.

Leveraging IoT in Auto Component Manufacturing to Monitor Surface Roughness and Tool Temperature

Surface finish is an important requirement in Auto Component Manufacturing that defines the quality of work piece obtained from turning operations. Thus to reduce downtime due to rejection of work piece for its surface finish a continuous monitoring of surface roughness based on its cutting parameter and vibration signal is required. Similarly it is also important to monitor the cutting tool temperature to have a longer tool life. With the emerging trend of Internet-of-Things (IoT) it has become very easy to collect the required data, storing it, analysing it and also alerting the required personnel through the mobile application, e-mail and SMS. The stored data and analysis could reveals in depth the process, which leaves a large scope for improvement of the system. The paper discusses the implementation of IoT to collect data of vibration signal and cutting tool temperature of dry turning operation, for cutting parameter like 1) spindle speed 2) feed rate and 3) depth of cut for three different material mild steel (MS), brass and aluminium (Al). A correlation was obtained to predict surface roughness and tool temperature. The system developed could give a real time monitoring of surface roughness on a smart phone that can be used as a tool for optimizing the turning process to give improved quality and increased production volume.

EXPERIMENTAL STUDY AND MONITORING OF TEMPERATURE AND SURFACE ROUGHNESS AND MICRO-HARDNESS OF THE WHEEL–RAIL CONTACT IN THE DESERT REGION OF THE OUARGLA TRAMWAY

Public transport via trams has become increasingly important in daily life to meet the growing demand for economic and environmental considerations. In order to ensure the safety of the railway system and reduce service costs, it is necessary to understand the tribological behavior of the system. There are various types of damage such as fatigue, wear, and cracking that can harm the wheels and rails. To determine the wear mechanisms and identify the situations in which wear movements occur, it is crucial to monitor factors such as temperature, surface roughness, and contact micro-hardness between the wheel and the rail. The objective of this study is to analyze the tribological behavior and the impact of climatic conditions on the wheel–rail contact system in the desert area of the Ouargla tramway in Algeria. To achieve this, an intelligent sensor programmed by a microcontroller was utilized to measure the temperature of the wheel–rail contact. Additionally, a hardness tester was used to measure the micro-hardness of the rail, and a roughness tester was utilized to monitor the surface condition of the rail. The measured temperature values during the passage of the tramway varied between ambient temperature and a temperature of 450∘C. The micro-hardness values ranged from 270 Hv to 440 Hv, and the roughness values varied between 0.4[Formula: see text][Formula: see text]m and 2.7[Formula: see text][Formula: see text]m.

Model-based real-time prediction of surface roughness in fused deposition modeling with graph convolutional network-based error correction

Additively manufactured parts usually have relatively rough surface finish due to the layer-by-layer process. Extensive research has been conducted on the effect of process parameters on surface roughness as well as on real-time monitoring of surface roughness using sensor data. However, very few studies consider both process parameters and condition monitoring data to perform real-time prediction of surface roughness. To address this research gap, we introduce an augmented deep learning framework that integrates a model-based predictor with a deep learning-based error corrector to predict the surface roughness of parts fabricated via fused deposition modeling. The model-based predictor predicts surface roughness by considering the effects of process parameters on surface roughness, while the deep learning-based error corrector estimates the prediction errors between the true surface roughness and predicted surface roughness using real-time sensor data collected during additive manufacturing. To consider both correlations among features extracted from sensor signals and temporal correlations of each sensor signal, we construct multiple graphs to reveal these correlations and introduce a multi-graph convolutional network to analyze these undirected graphs. Experimental results show that the proposed framework outperforms existing data-driven methods reported in the literature.

Position-dependent milling process monitoring and surface roughness prediction for complex thin-walled blade component

Freeform surface parts, such as blades, exhibit complex structures and excellent aerodynamic performance, making them widely utilized in aerospace propulsion systems. However, monitoring and ensuring surface quality during the milling process of such components is challenging, leading to high scrap rates and unguaranteed processing efficiency. To address these issues, this paper investigated the milling process monitoring and position-dependent surface roughness prediction for the thin-walled blade with the material of Ti-6Al-4 V. The monitored blade-root acceleration signal was utilized to develop a discrete spatial vibration model based on the machining characteristics of the blade. This involved using Fourier transform and inverse techniques to combine the frequency response functions and cutting force for acceleration calculation, which was then compared to measured values to validate the model’s monitorability. Aiming at the surface roughness prediction, a predictive method for the entire machined surface was proposed, consisting of signal pre-processing, feature extraction and selection, and construction of extreme learning machine (ELM) model. Time-domain, frequency-domain, and time–frequency-domain methods were adopted for feature extraction. To enhance the generalization ability and accuracy of the predictive model, the maximal information coefficient was employed for correlation analysis, resulting in the selection of 12 features as input for the ELM-based surface roughness prediction system. Comparison of the measured and predicted surface roughness results revealed that all errors were less than 14%, with an average error of only 6.70%, demonstrating the validity and reliability of the prediction method. Notably, the proposed monitoring method does not interfere with the milling process and enables prediction of surface roughness at arbitrary positions on the entire surface during variable-parameter processing of freeform surface parts, thereby improving the quality and precision of the machined surface. The potential application of this paper lies in the final inspection of defects in industrial products and reducing the service risk of non-conforming parts.

The correlation of surface roughness and tool edge condition under sustainable cryogenic machining

This paper investigates the correlation between surface roughness of Inconel 718 and tool edge condition of ball nose inserts when milled at high speed. The cutting parameters were varied as follows; cutting speed: 120–140 m/min, feed rate: 0.15–0.25 mm/tooth, and axial depth of cut: 0.3–0.7 mm. For a sustainable machining approach, the experimental works were carried out under a smooth supply of cryogenic coolant which is a mix of liquid CO2, gas CO2, and compressed air. The experimental results revealed that the range of surface roughness obtained is from 0.114 to 0.197 µm. Along the cutting process, the tool wear patterns such as the abrasion, chipping, and the intermittent build-up-edge near the depth of cut cause the rapid increase of tool wear as well as the roughness of the machined surface with a significant correlation between them. However, the roughness was slowly reduced and became stable with the increase of notch wear. The finding could be used as a prediction reference for monitoring surface roughness and tool wear progress under cryogenic conditions. It also provides foundations for further research on machinability under this sustainable approach.

Knowledge-based neural network for surface roughness prediction of ball-end milling

Theoretical modeling for surface roughness of ball-end milling generally results in low prediction accuracy due to the lack of machining information, excessive computational costs, and uncertainty of manual adjustment parameters. Besides, data-driven methods are limited in practical applications due to the lack of theoretical support or ‘black-box problems’ of neural network. To deal with these problems as mentioned above, this paper presents a coupling model for surface roughness prediction by combining the theoretical model of surface roughness and the data-driven approach. The core process is the secondary modeling with regard to the predictive result of theoretical model, which is realized by utilizing the knowledge-based neural networks with radial basis functions (KBaNN_RBF). Firstly, a theoretical model is established for the surface roughness prediction of ball-end milling by using the tool parameters and machining parameters. The output of the theoretical model is embedded into KBaNN_RBF as a priori knowledge. Secondly, low-dimensional features are extracted from the monitoring signals and adopted as the input of KBaNN_RBF for secondary modeling. And, the network structure is optimized by utilizing particle swarm optimization (PSO). Finally, ball-end milling experiment is carried out to verify the effectiveness of the presented KBaNN_RBF. Experimental results show that KBaNN_RBF is highly effective in improving the prediction accuracy and compressing the confidence interval (CI). Moreover, the comparison results show that the effectiveness of KBaNN_RBF is far superior to the traditional methods, such as back propagation neural network (BPNN) and support vector machine (SVM). This paper provides theoretical guidance for accurate monitoring of surface roughness in real industrial settings.

Feature representation of audible sound signal in monitoring surface roughness of the grinding process

ABSTRACT This study proposes the feature representation method of audible sound (AS) signal in the grinding process. The extracted sound feature is provided as the input for the machine learning model to predict the machining surface roughness. Firstly, a sensitive EEMD-IMPE feature set is extracted from the AS signal basing on the combination of the ensemble empirical mode decomposition (EEMD) and improved multiscale permutation entropy (IMPE) methods. Then, an optimized PSO-LS-SVR predictor model is- established basing on the particle swarm optimization algorithm (PSO) and least square support vector regression (LS-SVR) to predict the surface roughness. The experiments demonstrated the consistent AS feature, which is specific to the grinding surface quality in a cutting parameter set. The results of the PSO-LS-SVR model show that the extracted EEMD-IMPE feature is used to predict the grinding surface roughness with the high prediction accuracy and can be controlled within 8% of testing data.

Online modeling and monitoring of power consumption, aerosol emissions, and surface roughness in wire cut electric discharge machining of Ti-6Al-4 V

Online modeling and monitoring of power consumption, aerosol emissions, and surface roughness in wire cut electric discharge machining of Ti-6Al-4 V

Machine learning models for surface roughness monitoring in machining operations

Machining manufacturing companies are faced with ever-increasing demands in terms of quality, product variability and cost reduction. To address these constraints, machining monitoring systems for surface integrity control are an expected solution. However, due to the harsh machining environment, the sensor options for monitoring are limited and, as a result, so is the direct information available. To address this limitation, in this work, machine learning based models are developed for continuous prediction of surface roughness in machining operations. The proposed models use as inputs cutting forces, temperature and vibration data acquired by robust sensors suitable for the machining environment.

Application of improved fireworks algorithm in grinding surface roughness online monitoring

The enclosed machining environment, the cutting fluid impact on the workpiece, the danger posed by high-speed rotation of the grinding wheel and the highly dynamic nature of the machine tool makes online monitoring surface roughness a self-evident conundrum in the grinding process. Guided by this difficulty, an online monitoring method of the grinding surface roughness based on Improved Fireworks Algorithm (IFWA) was proposed. According to the frequency spectrum analysis of grinding force signal and surface texture curve, and with the help of chi-square distribution density function, the functional relationship between grinding force signal and surface texture amplitude-frequency curve was established. Then, the Inverse Discrete Fourier Transform (IDFT) of the aforementioned mathematical function was executed to procure the mathematical relationship of the grinding force signal expressing the surface texture curve. Furthermore, the least square method was used to calibrate the profile least-square median of the surface texture curve. The calculation process of the surface texture curve to the surface roughness was then incorporated into the IFWA. Eventually, the elite retention strategy was introduced into the standard Fireworks Algorithm (FWA). An IFWA was designed to optimize the attenuation coefficient in the grinding force signal and surface texture curve function model. Taking the plane grinding of silica ceramic composites as an example, a theoretical model for online monitoring the grinding surface roughness was established based on the experimental data, and the prediction results in the accuracy of the method was the highest by comparing various algorithms. According to this model, the online monitoring of grinding roughness can be accomplished by the real-time acquisition of force signals in the grinding process.

Real-time monitoring of silica ceramic composites grinding surface roughness based on signal spectrum analysis

Aiming at the difficulty of real-time ceramic surface roughness monitoring in the automatic grinding process, a time–spatial domain spectrum analysis method was proposed based on the monitored grinding force signal and grinding surface texture curve. Discrete Fourier Transform (DFT) was employed to acquire spectral responses of grinding force and surface texture. The mean and maximum values of grinding force signal and surface texture in their amplitude-frequency curve were found to be positively correlated. The chi-square distribution model was then developed to predict the amplitude-frequency response of surface texture by monitoring force signal. Subsequently, the Inverse Discrete Fourier Transform (IDFT) was performed to obtain the surface texture curve. The mathematical function of the surface texture curve was modelled by the grinding force signal, finally. The surface roughness (Ra) could be calculated from the surface texture curve. In this work, taking the surface grinding of silica ceramic composites as an example, 75 stochastic groups of grinding experiments were designed. The results show that the real-time monitoring of silica ceramic composites grinding surface roughness could be accurately predicted by the chi-square model. The correlation coefficient between the predicted Ra and the actual one has reached 0.9821. The proposed prediction model could be valuable for the online measurement of grinding quality towards intelligent manufacturing.

Machine learning approaches for real-time monitoring and evaluation of surface roughness using a sensory milling tool

In the case of complex forming tools, the topographical properties of the component surfaces play a crucial role for the resulting quality of the formed metal sheets. To be able to process the free-form surfaces of these components, the used end-milling tools need to be long-cantilevered and slender. Today, the characterisation of the component surfaces is carried out afterwards and partly by extensive quality investigations. A 100 % inspection of the entire surface is usually not carried out. Detecting the surface properties during machining and thus making the process more efficient, a sensor integrated end-milling tool has been developed. The significant advantage of this tool is the high sensitivity due to the accelerometer installed close to the tool center point. In this paper, a machine learning approach is presented which can predict the surface roughness Ra of the component based on the acquired acceleration data from the sensory milling tool. To calculate the surface roughness Ra a convolutional neural network CNN is developed and trained using LabVIEW combined with a Python algorithm. Furthermore, results obtained from real-time investigations are presented using milling tests. In conclusion, the results are discussed, and an outlook is given showing how the CNN can be used for an active control of surface roughness in the milling process.

Comparative assessment of documentation referred to surface roughness measurement

The research relates to the field of metrological supervision, specifically to the control of surface roughness parameters. The authors analyzed the following regulatory documents: GOST R ISO 4287-2014 “Geometrical product specifications (GPS). Surface texture. Profile method. Terms, definitions and surface texture parameters”, GOST 25142-82 “Surface roughness. Terms and definitions”, GOST 2789-73 “Surface roughness. Parameters and characteristics”, GOST 9378-93 (ISO 2632-1-85, ISO 2632-2-85) “Roughness comparison specimens. General technical conditions”, GOST 27964-88 (ST SEV 6134-87, ISO 4287 / 2-84) “Measurement of roughness parameters. Terms and definitions”, GOST 19300-86 “Instruments for measurement of surface roughness by the profile method. Contact profilographs and profilometers. Types and main parameters”, GOST R 8.651-2009 ISO “State system for ensuring the uniformity of measurements. Contact (stylus) instruments for the measurement of surface roughness. Procedure of calibration”, GOST 9847-79 “Optical instruments for surface roughness parameters measuring. Basis parameters and types”, GOST R 8.700-2010 “State system for ensuring the uniformity of measurements. Method of surface roughness effective height measurements by means of scanning probe atomic force microscope”, which regulate the measured parameters of the surface roughness, instruments that measure these parameters. In the course of a comparative analysis of the values of the parameters of existing devices and the values of the parameters of devices prescribed in the standards, a summary table was formed, and the problem of controlling nanoparameters and nanocoatings was also identified. The existing instrument base for monitoring surface roughness allows measuring parameters with high accuracy and within wide limits, but the regulatory framework on the territory of the Russian Federation is outdated and does not allow the use of some modern types of instruments. In this regard, it is necessary to update the requirements of GOSTs for the modern capabilities of technology and control over roughness parameters.

Surface roughness prediction using kernel locality preserving projection and Bayesian linear regression

To further improve the prediction accuracy of surface roughness in milling process, this paper presents a new two-stage feature-fusion method by combining principal component analysis (PCA) and kernel locality preserving projection (KLPP). PCA is utilized for dimension-reduction while KLPP is utilized for dimension-increment. Vibration information of the workpiece, fixture and spindle is adopted as the monitoring signal. Firstly, the commonly-used time-domain features are extracted from the vibration signals. Then, the presented two-stage feature-fusion method is carried out for extracting more effective signal features. Besides, two types of Bayesian linear regression (BLR) model (Standard_BLR and Standard_SBLR) are utilized for model construction. Before the two-stage feature-fusion, Standard_BLR is utilized to determine the optimum dimension of PCA-based fusion features and the model parameters of KLPP. After the two-stage feature-fusion, Standard_SBLR is utilized to construct the BLR-based surface roughness predictive model. Two types of milling experiment (down milling and up milling) are carried out to show the influence of the presented two-stage feature-fusion method on the predictive performance of Standard_SBLR. Experimental results show that KLPP is highly effective in improving the prediction accuracy and compressing the confidence interval (CI) of Standard_SBLR. Moreover, the comparison results show that the effectiveness of KLPP is not inferior to kernel principal component analysis (KPCA). This paper lays the foundation for accurate monitoring of surface roughness in real industrial settings.

Analysis of the impact of defect systems in subsurface layers on the properties of solid-state materials using AMD-methods

This paper presents the results of analysis of the influence of defects of various nature on the physical properties of subsurface layers of solid-state materials. To successfully solve this urgent material science problem, it is proposed to use methods of acoustic-microscopic flaw detection (AMD-methods). During the experiments, the results of monitoring of surface roughness, studied the process of initiation and propagation of microcracks in solid materials, the influence of pitting corrosion on steel properties, we studied the behavior of powder materials with different degree of porosity.

Evaluation of dynamic responses of bridges considering traffic flow and surface roughness

The variations in the vehicle types, speeds, and passing order in the traffic flow and roughness conditions cause the dynamic effects of live loads on the bridges. In this study, a numerical calculation scheme is proposed to evaluate the bridge dynamic response under random traffic flow, considering the surface roughness condition. Traffic vehicles with a random passing order are constructed as the time history of the transient force functions assigned at each discretised deck node of the numerical model. The random effects of the vehicle types, speeds, and surface roughness are represented by the amplitude levels of the transient force functions. The validity of the calculation scheme is verified by applying it to an existing steel box-girder bridge using dynamic monitoring data, traffic data, and a finite element model. The behaviour of the calculated root mean square (RMS) of the accelerations agrees with that of the measurement data, particularly in the traffic situation with a high truck ratio. Moreover, a parametric study is conducted to investigate the effects of the traffic flow characteristics and surface roughness conditions on the bridge dynamic responses. The results demonstrate that the RMS of acceleration depends on the truck ratio and traffic flow speed; however, the maximum acceleration may be influenced by the vehicle speed and passing order, as well as the surface roughness condition. It is concluded that the calculation scheme is applicable for evaluating the dynamic responses of existing bridges with the given dynamic monitoring data, traffic flow, and surface roughness conditions.