Machine learning is driving the rapid move towards “Industry 4.0” in manufacturing, particularly with regard to anomaly detection.
Modern factories employ sensors in every aspect of the manufacturing process. The data from these sensors, coupled with additional data such as return rates/warranty claims and materials testing, can reduce failure rates for products as well as machinery. This improves product quality (and customer satisfaction) and reduces downtime, both of which can have significant impacts on a company's bottom line.
Automated machine learning (AutoML) is particularly well suited to the task of identifying anomalies, or outliers, in large datasets. But the process is often a long, drawn out one that can be very tedious. Auger’s AutoML tool greatly reduces the time spent in selecting algorithms and tuning hyperparameters by automating the process and trying every available algorithm and hyperparameter combination. This process generates a leaderboard showing the best combinations from which an ensemble is created, combining the best attributes of the leading algorithms and hyperparameter options.
Additionally, Auger employs a “warm start” process to algorithm/hyperparameter selection, generating more accurate results in less time.