Automating Quality Control of Technical Support
Overview
Quality control processes are essential for many companies, and the correct detection of errors lead to much lower costs and unplanned work in the future. However, one of the main pains of organizations is the cost and effort to perform quality control manually. For example, in the energy distribution sector companies spend a lot on training technicians in intervention procedures and photographic documentation of energy meters.
Challenge
All interventions in electricity meters require technicians to document the state of the meter with an image on site. They are stored in a large database which grows by thousands every day. The problem with most of these images is that they are of very poor quality or they even don’t show the necessary information.
Lisbon,
Portugal
Opportunity
To automate the quality control process for energy meters, we have developed an image classification solution based on neural networks. The main goal was the identification of bad photographs, such as smudges, the absence of a meter, or illegible meters.
Another need reported by EDP was to recognize the numerical record present on the display of energy meters. As there is no assured standardization of this type of equipment, the format, and technology (digital or analog) of the meters can vary too much depending on each case.
Impact
The model developed was able to perform photo quality control with more than 90% accuracy. In addition to the saved effort the model also contributes to reducing the time spent on this type of task, being able to analyze 300 images per minute.
90%
correctness in automatic
quality control.