A Virtual Sensor for Online Fault Detection of Multitooth-Tools

Abstract

The installation of suitable sensors close to the tool tip on milling centres is not possible in industrial environments. It is therefore necessary to design virtual sensors for these machines to perform online fault detection in many industrial tasks. This paper presents a virtual sensor for online fault detection of multitooth tools based on a Bayesian classifier. The device that performs this task applies mathematical models that function in conjunction with physical sensors. Only two experimental variables are collected from the milling centre that performs the machining operations: the electrical power consumption of the feed drive and the time required for machining each workpiece. The task of achieving reliable signals from a milling process is especially complex when multitooth tools are used, because each kind of cutting insert in the milling centre only works on each workpiece during a certain time window. Great effort has gone into designing a robust virtual sensor that can avoid re-calibration due to, e.g., maintenance operations. The virtual sensor developed as a result of this research is successfully validated under real conditions on a milling centre used for the mass production of automobile engine crankshafts. Recognition accuracy, calculated with a k-fold cross validation, had on average 0.957 of true positives and 0.986 of true negatives. Moreover, measured accuracy was 98%, which suggests that the virtual sensor correctly identifies new cases.

Estimating high precision hole diameters of aerospace alloys using artificial intelligence systems: a comparative analysis of different techniques

“…Bustillo et al [22] carried out a study using a virtual sensor for online fault detection of multi-tooth tools during milling operation of engine crankshafts based on a Bayesian model and used the electrical power consumption and the machining time as output variables. These authors reported that a 26 workpiece interval before the workpiece that is machined in real time is necessary for fault detection, against 40-70 workpiece interval observed in previous works, as well as a measured accuracy of 98 %.…”

Multisensory fusion based virtual tool wear sensing for ubiquitous manufacturing

“…To bridge the gap between direct sensing and indirect sensing, virtual sensing, as a complement to physical sensing, has emerged as a viable, noninvasive, and cost effective method to infer difficult-to-measure or expensive-to-measure parameters in dynamic systems based on computational models [22]. It has been investigated for active noise and vibration control [23], industrial process control [24], building operation optimization [25], lead-through robot programming [26], product quality of semiconductor industry [27], and tool condition monitoring [28,29].…”

“…In [28], an artificial neural network model is investigated to infer the state of insert wear from translational vibration measurements on a milling machine. Bayesian network is studied for tool breakage detection utilizing the in-process electrical power signal [29].…”

Virtual sensing for gearbox condition monitoring based on kernel factor analysis

“…It has been investigated for active noise and vibration control (Petersen et al 2008), industrial process control (Cheng et al 2004), building operation optimization (Ploennigs et al 2011), lead-through robot programming (Ragaglia et al 2016), product quality of hydrodesulfurization (HDS) (Shokri et al 2015), and tool condition monitoring (Bustillo et al 2011;Li and Tzeng 2000). Data-driven virtual sensing techniques are favorable by fusing the extracted features from noisy online measurements to infer the difficult-tomeasure parameters based on artificial intelligence models (Gelman et al 2013).…”