Wear of the secondary of the welding gun, caused by mechanical fatigue or due to a bad parameterization of the welding points, causes an increase in quality problems such as non-existent welds or a reduced weld nugget size. In addition to quality problems, this defect causes production stoppages that affect the final cost of the manufactured part. Different studies have focused on evaluating the importance of different welding parameters, such as current, in the final quality of the welding nugget. However, few studies have focused on preventing weld command parameters from degrading or changing. This investigation seeks to determine the wear of the secondary circuit to avoid variability in the current supplied to the welding point caused by this defect and the increase in circuit resistance, especially in industrial environments. In this work, a virtual sensor is developed to estimate the resistance of the welding arm based on previous research, which has shown the possibility of detecting secondary wear by analysing the duty cycle of the power circuit. From the data of the virtual sensor, an anomaly detection method based on the Mahalanobis distance is developed. Finally, an integral system for detecting secondary wear of welding guns in real production lines is presented. This system establishes performance thresholds based on the analysis of the Mahalanobis distance distribution, allowing monitoring of the secondary circuit wear condition after each welding cycle. The results obtained show how the system can detect incipient wear in welding guns, regardless of which part of the secondary the wear occurs, improving decision-making and reducing quality problems.

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.

Electrode misalignment, produced by mechanical fatigue or bad adjustments of the welding gun, leads to an increase in expulsions, deformations and quality problems of the welding joints. Different studies have focused on evaluations of the influence of a misalignment of the electrodes and the final quality of the weld nugget. However, few studies have focused on determining a misalignment of the electrodes to avoid problems caused by this defect, especially in industrial environments. In this paper, a method for performing the condition monitoring of electrode alignment degradation was developed following previous research, which has shown the relationship between the misalignment of short-circuited electrodes and the magnetic field generated by them. This method was carried out by means of a device capable of measuring the magnetic field. Finally, an integral system for the detection of misalignments in real production lines is presented. This system set behavior thresholds based on the experimentation, allowing the condition monitoring of the alignment after each welding cycle.