Roughness Prediction Model Research Articles

Development of pavement roughness regression models based on smartphone measurements

PurposeThe purpose of this paper was to study the possibility of using smartphone roughness measurements for developing pavement roughness regression models as a function of pavement age, traffic loading and traffic volume variables. Also, the effects of patching and pavement distresses on pavement roughness were investigated. The work focused on establishing pavement roughness prediction models and applying these models to pavement management systems (PMS) to help decision-makers choose the best maintenance and rehabilitation (M&R) options by using cost-effective methods.Design/methodology/approachSignal processing techniques including filtering and processing techniques were used to obtain the International Roughness Index (IRI) from raw acceleration data collected from smartphone accelerometer sensors. The obtained IRI values were inputted as a dependent variable in analytical regression models as well as several independent variables with proper transformations.FindingsAccording to the study results, several regression models were developed with a big variation in the coefficients of determination (R2). However, the best models included pavement age, accumulated traffic volume (∑TV) and construction quality factor (CQF) with R2 equal to 0.63. It was also found that the effects of pavement distresses and patching was significant at a-level < 0.05. The patching effect on pavement roughness was found higher than the effect of other pavement distresses.Practical implicationsThe presented results and methods in this paper could be used in the future predictions of pavement roughness and help the decision-makers to estimate M&R needs. The work focused on establishing IRI prediction models and applying these models to the PMS to help decision-makers choose the best M & R options.Originality/valueTo develop sound pavement roughness models, it is essential to collect roughness data using automated procedures. However, applying these procedures in developing countries faces several difficulties such as the high price and operation costs of roughness equipment and lack of technical experience. The advantage of using IRI values taken from smartphones is that the roughness evaluation survey may be expanded to cover the full road network at a cheaper cost than with automated instruments. Therefore, if the roughness survey covers more roads, the prediction model’s accuracy will be improved.

Roughness and condition prediction models for airfield pavements using digital image processing

Based on the assessment of three runways at mid-size Chilean airports, the aim of this article is twofold. First, it discusses the potential empirical relationship that may exist between two parameters traditionally used to measure pavement roughness and condition, i.e. the International Roughness Index (IRI) and Pavement Condition Index (PCI), both measured using industry-standard, semi-automated processes. Second, it proposes an automated and parsimonious methodology for estimating the IRI and PCI, based on a digital image processing algorithm that accurately determines the total amount of cracking in pavements and which essentially requires no human curation. On one hand, a direct correlation between IRI and PCI has been obtained that can be considered statistically significant. On the other hand, highly reasonable estimates for the IRI and PCI can be achieved based solely on the total cracking percentage of a unit sample. The models proposed can be used for airport pavement management purposes.

Artificial neural network-based roughness prediction models for gravel roads considering land use

Artificial neural network-based roughness prediction models for gravel roads considering land use

Roughness prediction model of milling noise-vibration-surface texture multi-dimensional feature fusion for N6 nickel metal

Roughness is one of the important indicators for judging the quality of surface processing. In order to efficiently predict the surface roughness of nickel metal during milling, in this paper we built a multivariate signal monitoring system for nickel metal processing status and used the sound level meter, the three-way vibration sensor, the industrial camera, and the roughness measuring instrument to collect noise, vibration, surface texture, and roughness during milling. The three-way vibration is reduced by principal component analysis, and the correlation of each signal is analyzed by grey relational theory. The particle swarm optimization (PSO) algorithm is used to optimize the least squares support vector machine (LSSVM), and a roughness prediction model of multi-dimensional feature fusion is established, which takes the characteristic values of noise, vibration, and workpiece surface texture as input values and roughness as the output value. The results show that the prediction accuracy of the obtained roughness model based on PSO-LSSVM is 92.54%. The research can provide a theory guide for scientific monitoring of the surface roughness of milling workpieces.

Process Optimization of Robotic Polishing for Mold Steel Based on Response Surface Method

Aimed to reduce surface roughness (Ra) and improve surface quality of mold steel, the optimizations of process parameters for robotic polishing, such as polishing pressure, feed speed and rotating speed of tool, are accomplish in this research. The optimum range of each parameter is obtained according to a single factor experiment, and the central composite design experiments on the three polishing parameters are conducted to establish a prediction model of surface roughness. Furthermore, a significance test of the prediction model is carried out through variance analysis. The optimum polishing parameters are obtained based on the analysis of response surface, and are then adopted in the polishing experiments of mold steel for validation. The experiment result of model verification indicates that the relative errors of predicted Ra ratio and actual Ra ratio are within the allowable range (maximum is 13.47%). It proves the accuracy of the roughness prediction model. Meanwhile, the experimental results of multipath polishing show that the surface roughness decreased effectively after polishing with the optimum polishing parameters. The prediction model of surface roughness and optimum polishing parameters are helpful to improve surface quality in robotic polishing for mold steel.

Prediction model for surface generation mechanism and roughness in face gear grinding

Prediction model for surface generation mechanism and roughness in face gear grinding

Online Surface Roughness Prediction for Assembly Interfaces of Vertical Tail Integrating Tool Wear under Variable Cutting Parameters.

Monitoring surface quality during machining has considerable practical significance for the performance of high-value products, particularly for their assembly interfaces. Surface roughness is the most important metric of surface quality. Currently, the research on online surface roughness prediction has several limitations. The effect of tool wear variation on surface roughness is seldom considered in machining. In addition, the deterioration trend of surface roughness and tool wear differs under variable cutting parameters. The prediction models trained under one set of cutting parameters fail when cutting parameters change. Accordingly, to timely monitor the surface quality of assembly interfaces of high-value products, this paper proposes a surface roughness prediction method that considers the tool wear variation under variable cutting parameters. In this method, a stacked autoencoder and long short-term memory network (SAE–LSTM) is designed as the fundamental surface roughness prediction model using tool wear conditions and sensor signals as inputs. The transfer learning strategy is applied to the SAE–LSTM such that the surface roughness online prediction under variable cutting parameters can be realized. Machining experiments for the assembly interface (using Ti6Al4V as material) of an aircraft’s vertical tail are conducted, and monitoring data are used to validate the proposed method. Ablation studies are implemented to evaluate the key modules of the proposed model. The experimental results show that the proposed method outperforms other models and is capable of tracking the true surface roughness with time. Specifically, the minimum values of the root mean square error and mean absolute percentage error of the prediction results after transfer learning are 0.027 μm and 1.56%, respectively.

Development of a Surface Roughness Prediction Model for Slow Tool Servo Turning Machining

To investigate the effect of slow tool servo turning process parameters on surface roughness, we es-tablished a high precision surface roughness prediction model. A guide to the selection of turning process parameters was compiled, and a turning test was conducted based on a response surface method (RSM) central composite design. ANOVA explores the influence law of process parameters on surface roughness. A RSM BP neural network model, and MEA-BP surface roughness model were established and the prediction performance of the three models was evaluated. The results show that the significant process parameters affecting surface roughness are tool radius, discrete angle, feed rate, and cutting depth in descending order; and the prediction errors of RSM, BP, and MEA-BP are 11.41%, 19.67%, and 5.54%. This suggests that the MEA-BP model has the highest prediction accura-cy with the same test data, RSM is second, whilst the single BP model struggles to capture multiple data characteristics and its prediction accuracy is poor. In addition, MEA can effectively solve the BP model falling into local optimum and improve the model prediction accuracy.

Application of statistical and soft computational techniques in machining of Nickel based supper-alloy using cryogenically treated tools for estimation of surface roughness

ABSTRACT In this paper, surface roughness prediction models are developed for turning of Inconel 718 using untreated and cryogenically treated inserts by using Dimensional Analysis, Response Surface Methodology (RSM) and Artificial Neural Network (ANN). Performance of untreated and treated tools is analysed using SEM, Energy-dispersive X-ray analysis, Vicker hardness test and electrical conductivity. For the established surface roughness models by dimensional analysis, RSM and ANN, the mean absolute errors for confirmation tests are 5.32%, 8.28% and 4.15% for untreated inserts and 4.95%, 6.01% and 4.20% for treated inserts, respectively. The effect of cutting parameters on surface roughness is analysed using the main effect plot and 3D surface plots. Based on correlation coefficient (R2 ) values, ANN modelling technique (R2 = 99.68%) is more accurate for predicting surface roughness. Thus, it can be an effective tool for analysing machining responses. The study also noted that while cutting at v= 60 m/min, f= 0.1 mm/rev and d= 0.5 mm, surface roughness and flank wear values are 0.5 µm and 0.45 µm and 0.777 mm and 0.627 mm for untreated and treated inserts, respectively. The use of treated tools resulted in 10% and 19% improvement in surface quality and tool life than the untreated tools.

Investigation on the surface roughness modeling and analysis for ultra-precision diamond turning processes constrained by the complex multisource factors

Ultra-precision machining is widely used in the manufacturing of national defense and sophisticated civil products because of its high precision, nearly no surface damage and other advantages. The surface roughness of a workpiece is the key indicator of ultraprecision machining technology, which is affected by many factors in the process of machining. However, the existing surface roughness prediction model only considers a single error factor between the tool and workpiece, lacking comprehensive consideration of multisource error factors. Therefore, based on the research of the single error factor, multisource errors that affect the surface roughness of a workpiece in machining was investigated in this paper. A prediction model of workpiece surface roughness under multisource error affecting was established to improve the accuracy of prediction models. According to the vibration model, the sensitive direction of roughness can be determined. In the axial direction, the error of each point on the surface is superimposed with the theoretical surface shape to obtain the final surface profile. The three-dimensional morphology was established and the two-dimensional topography can be obtained by intercepting the three-dimensional topography. The roughness simulation value is obtained by extracting the peak value of each point of the two-dimensional topography. A single-point diamond turning experiment is performed to verify the simulation models. The result concluded from the experiment is compared with the simulation result, showing that the error between the simulation and the experiment is less than 4%, which is of great significance to optimizing machining process parameters and improving machining precision of workpiece surfaces for ultraprecision single point diamond turning.

Study on prediction model of surface roughness of SiCp/Al composites based on Neural Network

In order to effectively meet the actual industrial production standards and improve the prediction accuracy of composite surface roughness, a prediction model of SiCp/Al composite surface roughness based on neural network is proposed. The influence parameters of surface roughness of SiCp/Al composites are analyzed from the cutting tool parameters, and the mathematical calculation of surface roughness of SiCp/Al composites is carried out. Using neural network technology, by determining various parameters of neural network, collecting and processing various data of material surface, the surface roughness prediction model of SiCp/Al composite is constructed to realize the surface roughness prediction of SiCp/Al composite. The experimental results show that the maximum error between the actual value and the predicted value of the surface roughness of composite materials from the prediction model established in this paper is only 0.013, and the average error percentage between the actual value and the predicted value is 0.705%, which can effectively improve the prediction accuracy of the surface roughness of composite materials and meet the standards of actual industrial production.

Broad Learning System Based on Binary Grey Wolf Optimization for Surface Roughness Prediction in Slot Milling

Surface roughness is considered to be one of the most significant indicators for evaluating machining quality. Manufacturing industries generally aim to achieve high product quality while considering reducing production costs and time. Therefore, an accurate and reliable surface roughness prediction model plays a key role in the production process. Recently, a broad learning system (BLS) has attracted great attention due to its outstanding performance. In order to improve the prediction accuracy of surface roughness and reduce the influence of uncertain factors, sensors are necessarily added to monitor the product processing. Consequently, the surface roughness data obtained in the actual machining process tends to have a small sample size and a high feature dimension. In addition, due to the structural characteristics of the BLS, its hidden layer neuron nodes often carry some irrelevant or redundant features during the training process, which affects the prediction performance of the model. To overcome these problems, this article proposes a novel BLS architecture for surface roughness prediction, in which binary grey wolf optimization (BGWO) is used for the selection of neurons in the hidden layer. To verify the effectiveness of the proposed method, a slot milling surface roughness experiment was performed and compared with other methods for different evaluation indicators. The results show that the proposed method provides an effective solution for surface roughness prediction.

Roughness Prediction Model Based on Neural Network

Roughness Prediction Model Based on Neural Network

Optimization of surface roughness and machining parameters for turning superalloy GH4169 under high-pressure cooling

Superalloys are important structural materials in the aerospace and petrochemical industries. Because of their excellent fatigue and oxidation resistance, superalloys are usually used predominantly in rotor and turbine components. The requirement of good surface quality and high-precision processes has been widely concerned. High-pressure cooling is a commonly used auxiliary processing technology in the metal cutting field, which can efficiently improve the quality of the processed surface. It is of great significance to study the surface roughness of GH4169 processed by cutting under high-pressure cooling conditions. First, the single-factor and orthogonal experiment methods were used. The single factors, interaction effect, and quadratic effect of cutting parameters and cooling pressure were analyzed. Then, the multiple linear regression method was adopted to establish the prediction model for surface roughness of GH4169, and the accuracy of this model was verified. Finally, according to the prediction model, the machining parameters were optimized and verified. The results indicated that the proposed model was accurate and reliable, which could be used to optimize the machining parameters. The optimal parameter combination was achieved, with the cutting speed of 154 m min−1, the feed rate of 0.10 mm/r, the cutting depth of 0.46 mm, and the cooling pressure of 52 bar. Under this parameter setting, the prediction error was 4.20%, and the surface roughness was 34.92% less than that obtained under the actually recommended machining parameters. The above results will provide theoretical guidance for the parameter optimization of cutting superalloy under high-pressure cooling conditions and quality control of the processed surface.

Development of a Deep Convolutional Neural Network for the Prediction of Pavement Roughness from 3D Images

Current roughness prediction models require extensive input data including pavement distress, climatic, and traffic data, which may be difficult to collect. In addition, these models have geographical limitations; therefore, a significant bias is expected if these models are used without recalibration. Pavement digital images can reflect both surface distresses and other surface irregularities that may affect pavement roughness conditions. In this study, convolutional neural networks (CNNs) were used to classify pavement sections into different roughness categories and to estimate International Roughness Index (IRI) values using pavement surface images. Furthermore, the effectiveness of artificial neural network (ANN) and multinomial logistic (MNL) regression models to categorize pavement sections into different roughness conditions was investigated. A pretrained CNN model was trained and validated using 850 three-dimensional (3D) pavement surface images, which were extracted from the Louisiana DOT and Development (LaDOTD) pavement management system (PMS) inventory. In addition, 1,142 test observations including IRI measurements and distress data were used to develop the ANN-based pattern recognition and MNL models. The developed CNN model outperformed the ANN and MNL models with an accuracy of 93.4% in the training stage. In addition, the CNN model predicted IRI values with a coefficient of determination (R2) of 0.985 and an average error of 5.9%.

Optimization of magnetic field assisted finishing process during nanofinishing of titanium alloy (grade-5) implant using soft computing approaches

ABSTRACT The present study explores the potential of magnetic field assisted finishing (MFAF) in precise finishing of femoral knee implant made of bio-titanium alloy at the nanometric level. The process parameters, viz. rotational speed of tool, feed rate and carbonyl iron particle (CIP) concentration of MFAF have significant influence on the final surface topography of implants and thus selection of optimal set of their values is a difficult but an important task. In the present work, central composite rotatable design of response surface methodology is considered for nanofinishing of titanium alloy based femoral knee implants. Based on the experimental results, a polynomial regression prediction model for surface roughness is established in terms of MFAF process parameters. The fuzzy logic model with the help of ANOVA analysis is employed to analyze the effect of individual and interaction of parameters on surface roughness of implants. Finally, for further optimizing the final surface roughness of knee implant and determining the best settings of MFAF parameters, an improved salp swarm algorithm (ISSA) is proposed by introducing two important enhancements in basic SSA. The results reveal that SSA and ISSA metaheuristics achieved an improvement in final surface finish of knee implant by 4.04% and 14.24%, respectively, in comparison to default experimental trials during finishing.

Roughness Modeling for Composite Pavements using Machine Learning

A large number of paved highway surfaces comprises composite pavements as a result of concrete pavement rehabilitation that uses an asphalt overlay on top of the concrete surface. Annually, billions of dollars are spent on the maintenance and rehabilitation of road networks. Roughness is one of the several indicators of road conditions used to make objective decisions related to road network management. The irregularities in the pavement surface affecting the ride quality of road users can be described by a standard roughness index defined as the International Roughness Index (IRI). Roughness prediction models can identify rehabilitation needs, analyze rehabilitation effects, and estimate future pavement conditions to implement different Maintenance and Rehabilitation (M&R) activities to extend the pavement life cycle and provide a smooth surface for road users. This study intended to develop pavement performance models to predict roughness for asphalt overlay on concrete pavement sections using the Long-Term Performance Pavement (LTPP) program database. Artificial Neural Networks (ANNs) approach was used to develop roughness prediction models. A total of 52 pavement sections with 592 data points were analyzed. Five models were developed, and the best performing model, Model 5 was found with an average square error (ASE) of 0.0023, mean absolute relative error (MARE) of 12.936, and coefficient of determination (R2) of 0.88. Model 5 utilized one output variable (IRIMean) and 14 input variables (i.e., Initial IRIMean, Age, Wet-Freeze, Wet Non-Freeze, Dry-Freeze, Dry Non-Freeze, Asphalt Thickness, Concrete Thickness, CN Code, ESAL, Annual Air Temperature, Freeze Index, Freeze-Thaw, and Precipitation). The ANN model structure utilized for Model 5 was 14-9-1 (14 inputs, 9 hidden nodes, and 1 output). Environmental impacts and traffic repetitions can cause severe damage to the pavement if timely maintenance and rehabilitation are not performed. By considering the effects of the M&R history of the pavement, it is possible to obtain realistic prediction models for future planning. Therefore, the developed ANN roughness performance models in this paper can be used as a prediction tool for IRI values and guide decision-makers to develop a better M&R plan. Local and state agencies can use available historical traffic and climatological data in the developed models to estimate the change in IRI values. Utilizing these prediction models eliminates time-consuming data collection and post-processing, and consequently, a cost reduction. This low-cost tool will improve the condition assessment and effective M&R scheduling.

Surface Roughness Analysis and Prediction with an Artificial Neural Network Model for Dry Milling of Co-Cr Biomedical Alloys.

The aim of this paper is to conduct an experimental study in order to obtain a roughness (Ra) prediction model for dry end-milling (with an AlTiCrSiN PVD-coated tool) of the Co–28Cr–6Mo and Co–20Cr–15W–10Ni biomedical alloys, a model that can contribute to more quickly obtaining the desired surface quality and shortening the manufacturing process time. An experimental plan based on the central composite design method was adopted to determine the influence of the axial depth of cut, feed per tooth and cutting speed process parameters (input variables) on the Ra surface roughness (response variable) which was recorded after machining for both alloys. To develop the prediction models, statistical techniques were used first and three prediction equations were obtained for each alloy, the best results being achieved using response surface methodology. However, for obtaining a higher accuracy of prediction, ANN models were developed with the help of an application made in LabView for roughness (Ra) prediction. The primary results of this research consist of the Co–28Cr–6Mo and Co–20Cr–15W–10Ni prediction models and the developed application. The modeling results show that the ANN model can predict the surface roughness with high accuracy for the considered Co–Cr alloys.

Optimization of magnetic composite fluid polishing process based on response surface method

ABSTRACT Currently, research on the optimization of key process parameters in the polishing process usually uses orthogonal test method, which needs a lot of experiments. In order to solve this problem, this paper proposes a parameters optimization of magnetic composite fluid polishing process based on response surface method. Firstly, roughness of the polycarbonate microfluidic chip surface polished with magnetic composite fluid was used as the optimization object, while the machining gap, spindle speed and machining time were defined as the key parameters, and experiments were designed and conducted based on response surface method. Subsequently, using the above experimental data, a prediction model for microfluidic chip surface roughness after polishing that depends on key parameters is established. After that, by the application of the prediction model, the key parameters were optimized and verified by experiments. The results indicated that by using the optimized process parameters, the minimum surface roughness of the microfluidic chip reduced from 0.5 μm to 0.0384 μm, while the maximum and minimum errors between measured and predicted results are 0.0052 μm and 0.0007 μm, respectively. The above result has proved the accuracy of the established model and the effectiveness of the proposed parameters optimization method.

Surface Roughness Analysis of H13 Steel during Electrical Discharge Machining Process Using Cu-TiC Sintered Electrode.

In electrical discharge machining (EDM), the machined surface quality can be affected by the excessive temperature generation during the machining process. To achieve a longer life of the finished part, the machined surface quality plays a key role in maintaining its overall integrity. Surface roughness is an important quality evaluation of a material’s surface that has considerable influence on mechanical performance of the material. Herein, a sintered cermet tooltip with 75% copper and 25% titanium carbide was used as tool electrode for processing H13 steel. The experiments have been performed to investigate the effects of EDM parameters on the machined surface roughness. The findings show that, as the pulse current, pulse length, and pulse interval are increased, the surface roughness tends to rise. The most significant determinant for surface roughness was found to be pulse current. A semi-empirical surface roughness model was created using the characteristics of the EDM technique. Buckingham’s theorem was used to develop a semi-empirical surface roughness prediction model. The semi-empirical model’s predictions were in good agreement with the experimental studies, and the built empirical model based on physical features of the cermet tooltip was tested using dimensional analysis.