Identification of causes of defects arising in the welding process

Goals

Determination of the causes of defects arising in the process of welding the roof with the rest of the body components

Indication of a set of parameters that are directly or indirectly related to the occurrence of particular body defects

Results

Identification of the extent of individual environmental conditions relating to the occurrence of quality problems

Challenge

The challenge was to find the causes of defects during the welding process, identify operating parameters for which defects account for less than 10% of all samples, and minimize quality problems by optimizing the closed-loop control process.

If defects account for too large a fraction of all components, the following problems arise: manual removal of defects, additional human resources, delays in production. Properly conducted root cause analysis will not only eliminate the problem, but also reduce the number of defects.

Solution

Due to the occurrence of many types of defects, in the first step of the analysis it was decided to analyze two types. A clustering method was used, where the analyzed parameter is the frequency of defect occurrence depending on the process parameters. Such information made it possible to estimate the optimal values of each parameter in order to minimize the number of failures that occur.

CASE 1 / statistical analysis of data

Example of statistical analysis of the results of the analyzed data, from which it was possible to determine:

- The types of defects that occur most frequently. Then, for the most frequently occurring defects, conduct an analysis based on clustering.
- Determine the optimal operating parameters to minimize the number of defects to a set level
- Areas of optimal start-up parameters for the process for which the fraction of defects is at an acceptable level
- The determined parameters depended on the ambient temperature - a decrease in defects was observed with a change of season
- Interpretation of the results requires further technical consultation and calibration with other types of defects

Benefits

Based on a detailed analysis of the problem posed, it turned out that the causes of the defect were very complex. The results of the project made it possible to identify incomplete information on sets of parameters/conditions at which the incidence of defect is significantly lower/higher than the average in the entire sample. The results made it possible to determine the optimal parameter area for the processes of individual machines, in which the probability of weld failure was negligible. This selection of parameters eliminated poor weld quality.

A chance to completely avoid quality problems in the welding process

Determination of the optimal parameter area for the processes of individual machines in which the probability of weld failure was negligible

Indication of incomplete information on parameter sets/conditions

About company

ReliaSol is a company established in response to the growing need to increase the efficiency of machines and installations in industry.

We provide software and services that accelerate the digital transformation process. The applications we create combine real data from machines, sensors, event reports and automate drawing conclusions. The result of their work is data visualization, event prediction and monitoring of the optimal operating range of machines and entire production lines.

We will be happy to answer your questions

Reliability Solutions Sp. z o. o.
ul. Królewska 57, 30-081 Kraków, Polska