An Unsupervised Condition Monitoring System for Electrode Milling Problems in the Resistance Welding Process

Abstract

Resistance spot welding is one of the most widely used metal joining processes in the manufacturing industry, used for structural body manufacturing, railway vehicle construction, electronics manufacturing, battery manufacturing, etc. Due to its wide use, the quality of welded joints is of great importance to the manufacturing industry, as it is critical for ensuring the integrity of finished products, such as car bodies, that withstand high levels of stress. The quality of the welding is influenced both by the programming of the welding and by the good condition of the mechanical part that carries out the welding. These mechanical factors, such as electrode geometry and wear, degrade over time. As the welding points are made, the geometry and properties of the electrodes change, so they undergo a milling process to remove impurities and return them to their initial geometry. Sometimes the milling is deficient, and the electrode continues to wear, causing welding problems such as loose spots and metal spatter. This article presents a method for condition monitoring of the milling process and weld wear based on existing data in real production lines. The use of unsupervised clustering methods is proposed to perform a check by which, using current and resistance data, the electrode wear is grouped. Specifically, a method using multidimensional k-means for the condition monitoring of electrode wear is established. This research gives a real and applicable solution for reducing the quality problems caused by milling defects and electrode wear in the production lines of high-production manufacturing industries, presenting a system for sending alarms based on the behavior of welding variables.

Editorial for Special Issue: Machine Health Monitoring and Fault Diagnosis Techniques

“…The theme of this Special Issue focuses on machine health monitoring and fault diagnosis techniques, especially intelligent fault diagnosis. This Special Issue highlights 18 articles that can be divided into four categories: condition monitoring [ 1 , 2 , 3 , 4 ], degradation process prediction [ 5 , 6 , 7 , 8 ], intelligent diagnostic algorithms [ 9 , 10 , 11 , 12 , 13 , 14 , 15 ], and sensor fault detection [ 16 , 17 , 18 ]. In addition to the traditional bearing vibration signals, the research objects include the electrode signals, blade vibration signals, diesel engine vibration signals, and bearing heat signals.…”

“…In [ 4 ], a method using multidimensional k-means for the condition monitoring of electrode wear was established. With the aid of this method, the relationship between the serial time data of the resistance and the mechanical properties variation of the electrodes was described.…”

Assessing Electrode Characteristics in Continuous Resistance Spot Welding of BH 340 Steel Based on Dynamic Resistance

“…The relationship between welding process signals such as dynamic resistance and electrode displacement signals and electrode wear has recently attracted the attention of some researchers. Ibáñez et al [11] proposed a real-time monitoring method based on data collected from the actual welding production line when the spot-welding electrode wears to a certain degree and requires milling. The unsupervised clustering method is used to process and analyse the welding current and resistance data to classify the degree of electrode wear.…”