In an aeronautical predictive maintenance project, the goal was to predict filter clogging based on current consumption measurements. The idea was simple: as the filter becomes clogged, the pump compensates by consuming more power. By monitoring this consumption, it should be possible to anticipate filter replacement before a failure occurs. In theory, it’s elegant. In…
For years, my go-to tool was Excel. Pivot tables, nested formulas, a bit of VBA whenever things got truly repetitive. It was tedious and fragile – one misnamed file or a moved column, and the whole thing would fall apart. But since everyone around me was doing it, I kept at it. In 2020, I…
In industry, industrial data has become a key lever for performance: predictive maintenance, process optimization, cost reduction… But in practice, many engineers find themselves facing a simple problem: 👉 Data is difficult to work with. Not because it’s complex, but because it contains errors. In this article, we’ll look at the 7 most common errors…
In many industrial companies, although data is ubiquitous, its quality is often problematic. Engineers find that the difficulty lies not in a lack of data, but in incomplete, inconsistent, or poorly structured data, which complicates analysis. Before embarking on analytical models, it is crucial to thoroughly understand the data sources and their transformations. To improve data quality, it is recommended to document the sources, standardize formats, automate data cleaning, and regularly verify data quality. This presents an opportunity for engineers to transform this data into powerful decision-making tools.
