Element: Automatically Detecting Anomalies in Battery Test Results
Element: Automatically Detecting Anomalies in Battery Test Results
The Element Materials Technology Group uses Dataiku to detect anomalies in battery test results automatically and in near real time, claiming back 90% of technicians’ time and increasing testing throughput by up to 25%.
Share
25%
increased testing throughput
90%
of technicians’ time saved
95%
reduction in battery test result screening
Why: The Business Challenge
Laboratory teams at Element manually screen battery test results, sometimes after the data has been made available to the customer. Irregularities when conducting charge or discharge tests — such as testing equipment (cycler), unsecured connections, or misbehaving battery units due to internal faults — are unfortunately common, happening in as many as 25%-30% of cases.
Element’s customers are granted access to the test results through an online platform. Here, they have access to analytical capabilities where they can visually screen for anomalies in battery test results. While the lab will re-test units free of charge when requested by customers, this costs personnel time and uses revenue-generating cycler channels.
The team at Element therefore set out to solve this challenge with a machine learning- and statistics-based approach. With Dataiku, they are now detecting anomalies in battery test results automatically and in near real time, informing personnel to halt the tests early and therefore saving incredible amounts of technician resources.
More specifically, Element used Dataiku to build an intermediator service that screens battery test results in seconds instead of hours. The statistical test runs on streaming data, detecting signal irregularities. As soon as an issue is raised, a member of staff investigates, remediates the situation, and restarts the test if the battery unit is non-faulty. Otherwise, the unit is placed safely, waiting for its return to the customer.
In addition to benefits like reduced customer wait time, resulting in lower customer attrition, Element is also seeing tangible, quantifiable return on investment (ROI) in the form of:
Reducing battery test result screening by up to 95%, which means 90% of technician time is freed up for other high-value tasks.
Halting tests early, which is safer for staff and has increased testing throughput by up to 25%.
Incredibly, the team developed and tested their minimum viable product (MVP) in three months, reaching break even on the project within six months thanks to the tangible value from this single use case.
Heraeus: Improving the Sales Lead Pipeline With LLMs
Each of Heraeus’s 20 operating companies has its own lead identification and qualification process. See how Heraeus uses Large Language Models (LLMs) in Dataiku to support these processes, ultimately saving time and increasing sales conversion.
Western Digital leverages Dataiku’s NLP and MLOps capabilities to automate email categorization and wafer testing in manufacturing, saving 100 hours monthly and improving product quality.
Solvay uses Dataiku to monitor and improve soda ash production across 6+ plants, reducing production costs as well as energy consumption to pave the way for a sustainable business.