Surface Roughness Prediction System Research Articles

Research on surface roughness detection and prediction of ti-6Al-4v titanium alloy based on multi-feature fusion

Considering that titanium alloy is a critical aviation resource, ensuring its machining quality is of significant importance. Surface roughness remains a key parameter for surface quality inspection. This article introduces a multi-sensor titanium alloy milling monitoring system aimed at accurately monitoring surface quality during titanium alloy processing. Principal component analysis is conducted on three-dimensional milling force and vibration. We propose a multi-objective cutting parameter optimization procedure to simultaneously optimize multiple cutting parameters to improve surface roughness and tool life. Considering the high dependence of visual measurement on the light source, we strive to mitigate this limitation and improve prediction accuracy by considering one-dimensional and two-dimensional feature values. We establish a multidimensional signal feature surface roughness prediction system based on milling parameters, milling vibration, milling force, and texture image features. Using particle swarm algorithm and machine learning models, the undetermined parameters in the prediction system are obtained. The results show that the prediction accuracy of the multi-signal feature fusion surface roughness prediction system is 99.12%, with a mean square error of less than 0.01. The research can provide some theoretical guidance for the accurate monitoring of the surface quality of titanium alloy processing.

Development of Surface Roughness Prediction and Monitoring System in Milling Process

High surface quality is an important indicator for high-performance machining during the manufacturing process. The surface roughness generated in machining can be affected by cutting parameters and machining vibration. To achieve processing efficiency, monitoring surface quality within the desired range is important. This study aimed to develop a surface roughness prediction system for the milling process. The predictive model was established based on data collected from machining experiments with the response surface methodology. The surface roughness is related to independent variables, including cutting parameters and machining vibration, in terms of nonlinear functions by regression analysis and the neural network approach, respectively. To be implemented in a CNC milling machine for online application, a predictive model was introduced in the Virtual Machine Extension (VMX) intelligent software development platform. This model can acquire the cutting parameters from the controller via the Open Platform Communications Unified Architecture (OPCUA) interface as well as the vibration features from the sensory module. The system can calculate the roughness based on these data and issue alert when the predicted value exceeds the preset threshold or abnormal vibration is detected.

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 development of an ANN surface roughness prediction system of multiple materials in CNC turning

The development of an ANN surface roughness prediction system of multiple materials in CNC turning

On-Line Surface Roughness Prediction by Using a Probabilistic Approach for End-Milling

An effective and efficient methodology is proposed to predict surface roughness by online monitoring of surface quality using accelerometer signals. A probabilistic approach, Monte Carlo Simulation, was researched and developed to create an automated tool for on-line prediction of surface quality. Data from 3-axis vibration (Vx, Vy, Vz) signals were used to predict on-line surface roughness. According to an experimental design with four cutting parameters (Cutting speed (Vc), Feed per teeth (Sz), Dept of cut (Dc), Width of cut (Wc)), three-axis vibration signals were used to combine data into a probabilistic model for development of an on-line surface roughness prediction system. Once the probability model was established by using a data set consisting of 71 experiments, the model was tested for 10 different cutting conditions. The probability model shows that the results have convergence values that are close to each other, by as high as 96.37%.

Adaptive Control System to Assist the Surface Workpiece Quality when Drilling

Article deals with design of adaptive control system for drilling process of aerospace critical components. The system proposed in this paper is directed towards real the time control of surface roughness parameter Ra. Proposed model for monitoring and control consists of surface roughness prediction system and decision making subsystem. The artificial neural network was employed to calculate surface roughness parameter Ra through of process monitoring indices such as torque Mz, force Fz, power P and cutting conditions feed f, cutting speed vc. Test samples were nickel based super alloy Udimet 720 used as a basic constructional material of discs for gas turbine engines.

Surface roughness prediction based on the correlation between surface roughness and cutting vibrations in dry turning with TiN-coated carbide tools

This paper presents an approach to improving surface roughness prediction that is based on analysing cutting tool vibrations by a novel signal processing technique known as singular spectrum analysis (SSA). Each eigenvalue of the SSA decomposition of each vibration (radial, tangential, and feed vibration) and its corresponding principal component are studied and analysed to select only those eigenvalues of each vibration signal decomposition that contain valuable information for the development of a surface roughness prediction system (SRPS). Also, the influence of tool geometry and tool flank wear on the SSA decomposition of the vibrations is studied. Finally, only the information most correlated with surface quality, extracted by means of SSA of each vibration, is used to develop an SRPS. Experimental results provide conclusive support for the proposed SRPS, and justify the use of the SSA technique in the design of these systems. The ability of the SSA technique to extract only the information correlated with surface roughness of each cutting vibration and the manner in which tool geometry and tool flank wear influence the final Ra constitute the main contributions of this work.

In-process surface roughness prediction system using cutting vibrations in turning

Machining is a complex process in which many variables can affect the desired results. Among them, surface roughness is a widely used index of a machined product quality and, in most cases, is a technical requirement for mechanical products since, together with dimensional precision, it affects the functional behavior of the parts during their useful life, especially when they have to be in contact with other materials. In-process surface roughness prediction is, thus, extremely important. In this work, an in-process surface roughness estimation procedure, based on least-squares support vector machines, is proposed for turning processes. The cutting conditions (feed rate, cutting speed, and depth of cut), parameters of tool geometry (nose radius and nose angle), and features extracted from the vibration signals constitute the input information to the system. Experimental results show that the proposed system can predict surface roughness with high accuracy in a fast and reliable way.

Development of a fuzzy-nets-based surface roughness prediction system in turning operations

This paper discusses the development of a surface roughness prediction system for a turning operation, using a fuzzy-nets modeling technique. The goal is to develop and train a fuzzy-nets-based surface roughness prediction (FN-SRP) system that will predict the surface roughness of a turned workpiece using accelerometer measurements of turning parameters and vibration data. The FN-SRP system has been developed using a computer numerical control (CNC) slant-bed lathe with a carbide cutting tool. The system was trained using feed rate, spindle speed, and tangential vibration data collected during experimental runs. A series of validation runs indicate that this system has a mean accuracy of 95%.

A fuzzy-nets-based in-process surface roughness prediction system in turning operations

A Fuzzy-Nets-based in-process surface roughness prediction (FISRP) system was developed to predict surface roughness in turning operations in a real time fashion. The input variables of the FISRP system were machining parameters, such as feed rate, spindle speed, depth of cut, and machining vibration per revolution. An accelerometer was employed to gather real-time vibration signals. Two groups of data were collected for two cutter bits with nose radii of 0.016 and 0.031 inches, respectively. Fuzzy nets theory was implemented to use the experimental data in developing the system for real-time prediction. The fuzzy nets theory is a five-step learning procedure for developing a knowledge base to predict surface roughness in real time. This FISRP system was tested to have an average prediction accuracy of 95.70%.

Fuzzy-nets based approach to using an accelerometer for an in-process surface roughness prediction system in milling operations

A fuzzy-nets based in-process surface roughness prediction (FN-ISRP) system based on the fuzzy-nets training scheme has been developed for predicting the surface roughness generated in milling operations while the machining process is taking place. In addition to the consideration of cutting parameters, such asspindle speed, feed rate, and depth of cut as fuzzy-nets input variables, this paper also describes the use of vibration in the FN-ISRP system. This cutting vibration was measured using an accelerometer and a proximity sensor. Five steps of the fuzzy-nets training scheme were implemented throughout the experiments, followed by the fuzzy rule bank, which was created based on physical experimentation. After the fuzzy rule bank was established, tests were conducted in a real-time fashion to evaluate the performance. In the fuzzynets model, Ra was predicted with a 96% accuracyrate, and the system could respond to the prediction value within 0.5 seconds during the end-milling process.