Machine Tools Anomaly Detection Through Nearly Real-Time Data Analysis

Abstract

This work presents a new methodology for machine tools anomaly detection via operational data processing. The previous methodology has been field tested on a milling-boring machine in a real production environment. This paper also describes the data acquisition process, as well as the technical architecture needed for data processing. Subsequently, a technique for operational machine data segmentation based on dynamic time warping and hierarchical clustering is introduced. The formerly mentioned data segmentation and analysis technique allows for machine tools anomaly detection thanks to comparison between near real-time machine operational information, coming from strategically positioned sensors and outcomes collected from previous production cycles. Anomaly detection techniques shown in this article could achieve significant production improvements: “zero-defect manufacturing”, boosting factory efficiency, production plans scrap minimization, improvement of product quality, and the enhancement of overall equipment productivity.

Review of fault detection techniques for predictive maintenance

“…, 2021). Hierarchical clustering works well with real-time analysis of the production process (Herranz et al. , 2019).…”

“…Gaussian mixture models are suitable in applications dealing with manufacturing (Nieves Avendano et al, 2021). Hierarchical clustering works well with real-time analysis of the production process (Herranz et al, 2019). Electrical and manufacturing industry utilises nearest neighbours (Masero et al, 2018) for anomaly classification.…”

“…The method to be modelled here assumes that it is a hidden Markov mechanism that can be used to detect imprecise or malfunctioning IoT nodes within a cloud network architecture (Wu et al, 2018). Degradation of system output from production is a stochastic process that can be represented via gamma processes (Herranz et al, 2019;Susto et al, 2018).…”

The Need for Cybersecurity in Industrial Revolution and Smart Cities

“…The development of these features has been catalyzed by advances in artificial intelligence as well as systems based on the collaboration of human and machine as resources to form a network that executes commands with an ability that is close to human intelligence [ 10 , 11 ]. With the incorporation of collaborative robots (cobots) into the manufacturing and production processes, simulation is now extensively used in operations to exploit real-time information in order to improve quality through the construction of virtual models [ 12 , 13 , 14 ]. These simulations can be made in 3D or 2D and can be used to monitor processes such as cycle times and energy consumption, which help reduce failure and wastage along the production line [ 6 , 15 ].…”

Effect of Rack and Pinion Feed Drive Control Parameters on Machine Tool Dynamics

“…Iglesias et al [20] presented a dedicated variable pitch tools for further chatter avoidance. Furthermore, Industry 4.0 has brought advantages for near real-time data analysis for detecting anomalous machine working conditions [21] or even to realize smart chatter suppression hybrid systems [22].…”