In battery R&D, it can take several days to design experiments, half a day to analyze data, and hours to produce reports. As test conditions grow more complex, reliance on individual researcher experience increases, while repetitive manual work reduces the time available for core research.

LG CNS integrates battery cyclers with an Agentic AI–based analytics service to automate the full experiment lifecycle—design, execution, analysis, and reporting. Leveraging high-fidelity charge/discharge data captured by the cyclers, AI interprets experimental objectives in natural language, designs optimal test recipes, and autonomously orchestrates specialized analytics tools to analyze results. It also automatically generates reports, including mechanism-level interpretations supported by literature citations.

By applying Design of Experiments (DOE) and active learning, AI recommends optimal test conditions for the next phase. This helps shift R&D decision-making from experience-driven judgment to data-driven decisions.

LG CNS’s AI analytics platform can reduce data analysis time by up to 90% and, through active learning, cut the number of required experiments by 30–50% compared with traditional full factorial designs.

Formation—the most critical step in battery manufacturing—largely determines cell performance and service life.

To move beyond the limits of conventional constant-current/constant-voltage (CC-CV) formation, manufacturers need ultra-precise pulse control to optimize the solid electrolyte interphase (SEI) layer and flexibly accommodate multiple cell form factors. Minimizing energy losses during high-capacity charge/discharge cycling is also essential to improving manufacturing competitiveness.

Based on its Ultra-precise Pulse Formation technology, LG CNS delivers an integrated architecture that combines DC power distribution and an uninterruptible power supply (UPS) to improve both process quality and energy efficiency across formation operations.

Pulse charge/discharge profiles help extend cell life, while DC distribution reduces AC-DC conversion losses. In addition, an energy-circulation design recovers discharge energy and routes it to adjacent charging channels.

As the EU Battery Regulation takes effect and makes end-of-life (EOL) battery recycling mandatory, the need for safe, efficient discharge processes is growing.

However, conventional brine discharge can take more than 24 hours and generate hundreds of tons of wastewater each year. It also has clear structural limitations across environmental performance, safety, and operational efficiency, including fire and explosion risk and the need for large-scale storage and staging space.

LG CNS’s Dry Discharge technology electrically discharges EOL batteries without water, eliminating wastewater at the source and reducing discharge time to within two hours.

AI continuously learns from discharge data to optimize temperature-control profiles and discharge strategies. As more data accumulates, both equipment efficiency and safety are further enhanced.

Standardized discharge-history data also supports corporate ESG management by quantifying carbon-reduction impact.

Battery charge/discharge equipment inherently carries safety risks, including fire, explosion, and thermal runaway, because it handles high-power electricity and high-energy-density cells. At the same time, global regulatory requirements continue to tighten, including the EU Battery Regulation, carbon emissions regulations, and wastewater standards set by the Ministry of Environment.

LG CNS embeds AI-based safety control and environmental compliance capabilities across equipment operations. Real-time anomaly detection AI applied to cyclers and pulse formation processes anticipates abnormal temperature, voltage, and current patterns and triggers an automatic shutdown within 100 milliseconds. Thermal runaway prediction AI applied to dry discharge equipment monitors cell-level discharge profiles in real time.

Operational data from all equipment is consolidated through an integrated monitoring and control platform, automatically building the data history required for Battery Passport compliance and providing quantitative ESG reporting metrics based on energy consumption, energy recovery, and carbon emissions data.

Beyond add-on safety devices, LG CNS structurally raises safety and environmental performance through an AI-enabled predictive safety framework that continuously learns and is continuously enhanced, and a compliance-ready data pipeline automatically generated from equipment operations data.

LG CNS designs and manufactures the core equipment required across the entire battery value chain—from cyclers for R&D to pulse formation equipment for production, dry discharge equipment for recycling, and the supporting DC power distribution systems and uninterruptible power supplies (UPS).

Through integration with the AX platform, operational data from all equipment is collected, standardized, and analyzed in a single layer, and AI agents generate equipment-specific insights. Digital twins enable virtual simulation and predictive maintenance for equipment.

LG CNS’s differentiation lies in combining the engineering capability to build optimized equipment with the ability to make it intelligent by applying Physical AI.