FPGA-Embedded Anomaly Detection System for Milling Process

Abstract

The main goal of this work is to design a supervising controller able to detect an anomaly in the milling process and implement the soultion in Field Programmable Gate Array (FPGA) chip. Executing this task, the controller continuously monitors the vibration signal coming from the acceleration sensor, installed on the milling machine, and striving to isolate new vibration patterns which are different from typical patterns recorded for the correct milling process. The detection method relies on determining selected signal features in the frequency domain and applying an auto-associative neural network (AANN) for novelty detection. It has been shown that by exercising the frequency spectrum of the vibration signal, extracting specific features of the signal's spectrum, and using an auto-associative neural network, it is possible to detect anomalies in a milling process with relatively high efficiency. The accuracy, sensitivity, specificity, precision, and false alarm rate are equal to 94.3, 100, 91.2, 88.9, and 8.8 percent. All necessary calculations can be accomplished by the developed single-chip FPGA embedded supervising controller. The controller allows high-speed calculations under low power consumption. It characterizes high reliability and low price compared to typically encountered solutions.

Anomaly Detection in Industrial Machinery Using IoT Devices and Machine Learning: A Systematic Mapping

“…Other metrics employed in binary classification include Matthews Correlation Coefficient (MCC), frequently used metric for unbalanced classes, which combines true positive, true negative, false positive, and false negative rates to evaluate overall model quality, used in 3 studies [92], [100], [122]; False alarm rate, also known as FPR, which quantifies the proportion of negatives mistakenly classified as positives, also used in 3 studies [32], [33], [109]; and Kappa, which measures the level of agreement between observers or classifiers in a classification problem, present in 2 studies [53], [100].…”

“…[30]- [33] In the category of milling and cutting tools, numerous studies concentrate on assessing the effects of wear and tear on their surfaces. These studies are particularly relevant for machinery such as Computer Numerical Control (CNC) routers, milling machines, lathes, and hot rolling mills, which frequently handle heavy-duty tasks involving cutting metal, ceramics, and other hard materials.…”

“…Out of the 84 examined papers, 24 relied on a single type of sensor for detecting AD. Ten of these studies exclusively used vibration sensors [33], [43], [47], [49]- [59]. Seven studies depended solely on noise sensors [39]- [42], [60]- [63].…”

Very High Accuracy Hyperbolic Tangent Function Implementation in FPGAs

“…The impact of the activation function accuracy has also been examined for the auto-associative neural network performing novelty detection in the milling process [25]. Another auto-associative neural network has also been developed and examined for the cold forging process [23].…”

FPGA-Based Methodology for Detecting Positional Accuracy Degradation in Industrial Robots

“…Furthermore, works have also been developed on manufacturing equipment such as computer numerical control machines (CNC); for example, Ref. [31] proposes an anomaly detection system in the milling process based on FPGA. The extraction of features in the frequency domain of machine vibration signals is performed using discrete Fourier transform (DFT), and this information is used to enter an auto-associative neural network (AANN) for anomaly detection, reporting satisfactory results offline.…”