Transfer Learning Based Surface Roughness Prediction Integrating Tool Wear Under Variable Cutting Parameters

The monitoring of surface quality in machining is of great practical significance for the reliability and life of high-value products such as rocket, spacecraft and aircraft, particularly for their assembly interfaces of these products. Surface roughness is an important metric to evaluate the surface quality. The current research of online surface roughness prediction has the following limitations. The effect of the varying tool wear on the surface roughness is rarely considered in machining. In addition, the deteriorating trend of surface roughness and tool wear is different under variable cutting parameters. Prediction models trained under one set of cutting parameters fail when cutting parameters change. This paper proposes a surface roughness prediction method considering the varying tool wear under variable cutting parameters. A stacked autoencoder and long short-term memory network (SAE-LSTM) is designed as the basic surface roughness prediction model that uses tool wear conditions and sensor signals as the input. The transfer learning strategy is applied on SAE-LSTM such that the surface roughness online prediction under variable cutting parameters can be realized. Machining experiments for the assembly interface (Ti6Al4V material) of the aircraft’s vertical tail are conducted and the monitoring data are used to validate the proposed method. Ablations studies are carried out to evaluate the key modules of the proposed model. The experimental results show that the proposed method outperforms other models and well track the true surface roughness over time.

Wood Surface Roughness Prediction Modeling Depending on Influential Cutting Variables

Paper presents the design of experiment and determining mathematical model to calculate roughness parameter of wood planned surface. For design of experiment three different types of solid wood were taken and processed on the planner with three different displacements and three different cutting speeds. After measuring the roughness parameter Rz, experimental results were obtained on the basis of which the central composite plan of the experiment was made. Based on that, a model of roughness parameter Rz was made, which is adequate and with high accuracy. The significance of the model coefficients was determined using the R software and the results were presented using the Design Expert software.

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.

Experimental And Numerical Study On Surface Generated Mechanism of Robotic Belt Grinding Process Considering The Dynamic Deformation of Elastic Contact Wheel

In the robotic belt grinding process, the elastic contact condition between the flexible tool and the workpiece is a critical issue which extremely influences the surface quality of the manufactured part. The existing analysis of elastic removal mechanism is based on the statistic contact condition but ignoring the dynamic removal phenomenon. In this paper, we discussed the dynamic contact pressure distribution caused by the non-unique removal depth in the grinding process. Based on the analysis of the equivalent removal depth of a single grit and the trajectories of grits in manufacturing procedure, an elastic grinding surface topography model was established with the consideration of the dynamic contact condition in the removing process. Robotic belt grinding experiments were accomplished to validate the precision of this model, while the result showed that the surface roughness prediction error could be confined to 11.6%, which meant this model provided higher accuracy than the traditional predicting methods.

Experimental Investigation of Surface Roughness in Milling of DuralcanTM Composite

In today’s developing aircraft and automotive industry, extremely durable and wear-resistant materials, especially in high temperatures, are applied. Due to this practical approach, conventional materials have been superseded by composite materials. In recent years, the application of metal matrix composites has become evident in industry 4.0. A study has been performed to analyze the surface roughness of aluminum matrix composites named Duralcan® during end milling. Two roughness surface parameters have been selected: arithmetical mean roughness value Ra and mean roughness depth Rz regarding the variable cutting speed. Due to the classification of aluminum matrix composites as hard-to-cut materials concerning excessive tool wear, this paper describes the possibility of surface roughness prediction using machine learning algorithms. In order to find the best algorithm, Classification and Regression Tree (CART) and pattern recognition models based on artificial neural networks (ANN) have been compared. By following the obtained models, the experiment shows the effectiveness of roughness prediction based on verification models. Based on experimental research, the authors obtained the coefficient R2 for the CART model 0.91 and the mean square error for the model ANN 0.11.

Research on Surface Roughness Prediction Model of Ultrasonic Assisted Grinding by Response Surface Method

In this paper, through a series of grinding experiments with different machining parameters on the surface of the workpiece, the surface roughness under different machining parameters are obtained The surface roughness prediction model is constructed by the response surface method. The effects of feed rate, amplitude, and spindle speed on the surface roughness are analyzed. The results show that the surface quality of ultrasonic-assisted grinding is better than that of conventional grinding. Amplitude has the most prominent effect on the improvement of surface quality, followed by the spindle speed. The feed rate has little effect on the surface roughness. The model can predict 93.71% of the experimental results and the prediction error of the model is lower than 5%.