Multi-Sensor Data Fusion for Real-Time Surface Quality Control in Automated Machining Systems

Abstract

Multi-sensor data fusion systems entail the optimization of a wide range of parameters related to the selection of sensors, signal feature extraction methods, and predictive modeling techniques. The monitoring of automated machining systems enables the intelligent supervision of the production process by detecting malfunctions, and providing real-time information for continuous process optimization, and production line decision-making. Monitoring technologies are essential for the reduction of production times and costs, and an improvement in product quality, discarding the need for post-process quality controls. In this paper, a multi-sensor data fusion system for the real-time surface quality control based on cutting force, vibration, and acoustic emission signals was assessed. A total of four signal processing methods were analyzed: time direct analysis (TDA), power spectral density (PSD), singular spectrum analysis (SSA), and wavelet packet transform (WPT). Owing to the nonlinear and stochastic nature of the process, two predictive modeling techniques, multiple regression and artificial neural networks, were evaluated to correlate signal parametric characterization with surface quality. The results showed a high correlation of surface finish with cutting force and vibration signals. The signal processing methods based on signal decomposition in a combined time and frequency domain (SSA and WPT) exhibited better signal feature extraction, detecting excitation frequency ranges correlated to surface finish. The artificial neural network model obtained the highest predictive power, with better behavior for the whole data range. The proposed on-line multi-sensor data fusion provided significant improvements for in-process quality control, with excellent predictive power, reliability, and response times.

Deep Learning for Industrial Computer Vision Quality Control in the Printing Industry 4.0

“…In fact, there is great potential for other industries to increase the ability of machines to recognize their own state through intelligent sensors capable of sensing the specific needs of customers and responding flexibly and accordingly. This would improve the level of automation and increase product quality and customization while increasing related value stream performance [16,17,18].…”

Intelligent Control of Bulk Tobacco Curing Schedule Using LS-SVM- and ANFIS-Based Multi-Sensor Data Fusion Approaches

“…As a result of the high performance of the multi-sensor data fusion method on the noise elimination to the process control application [25], it was chosen in order to analyze the control process of a bulk tobacco curing schedule in this study. The multi-sensor data fusion method has been widely used in various research areas [17,26,27,28,29,30,31]. In the field of artificial sensors’ applications, which are highly related to the present study, a feature level fusion with principal component analysis (PCA) feature selection method and several pattern analysis techniques, such as ANN, linear discriminant analysis (LDA), partial least square (PLS), and support vector machine (SVM), have been mostly used for food authentication and the on-line monitoring of food fermentation processes [30,32,33,34].…”

Abrasive Feature Related Acoustic Emission in Grinding

“…An online monitoring system for machining processes could have remarkable impacts on a CNC machine tools system in reducing manufacturing cost and time in the product inspections, and avoiding the need for postprocess quality control [1] [2]. Online monitoring techniques allow the real time evaluation of crucial aspects of the machining processes, such as tool condition [3] [4], chatter [5], surface finish [6] [7], chip formation [8], surface damage [9] [10], and so on. In order to provide effective information with online monitoring techniques, the selection of adequate sensors, signal processing methods together with predictive techniques should be optimised according to the specific parameters under analysis.…”

“…A broad range of sensors have been used in machining process monitoring, including dynamometers, accelerometers and acoustic emission sensors [2]. For online process monitoring, different signal processing methods in time domain and frequency domain have been applied, i.e., time direct analysis (TDA) [6], singular spectrum analysis (SSA) [11], Fourier transform [6], and wavelet transform [12], and so on. Considering correlating features of the parameters under study, several predictive techniques have been applied in many researches, i.e., the multivariate regression [13], the artificial neural networks [6] and the support vector machines (SVM) [4].…”