For Battery R&D

Beijing DP Technology Co., Ltd., based on the new paradigm of AI for Science, uses material micro-properties parameters to predict the properties of particles and further simulates the performance at the electrode and cell scale. By employing machine learning modeling to predict the impact of processing technology on the performance of electrodes and cells. We are committed to working with battery industry partners to address the challenges in battery research and development through collaboration and tool development, designing batteries more accurately and reliably.

Request a demoarrow

Develop and design around the battery lifecycle

Develop materials by understanding structure-property relationships
Optimize battery formulations and processes by understanding mechanisms
Design cells by understanding cell models
Electrode materials
Electrolyte
Characterization and processes
Cells
Solutions
Case Studies
Using the DeePMD method and DPA interatomic potential pre-trained models to predict key properties of the fully doped space in cathode materials and solid-state electrolytes, the results are close to experimental tests, and the efficiency is at least 1000 times faster than mainstream methods.
Cathode Material and Solid-State Electrolyte Doping Property Prediction APP, interactively screens materials at the ten-thousand level, and shortens the new material development cycle to one-third of the original duration.
Preview
Empowering Customers
Collaborate with customers to solve R&D challenges
Apps in Piloteye boost customer R&D efficiency
Utilize R&D data to train models and predict battery properties;
Combine data-driven pretrained models with principle-driven multi-scale algorithms;
End-to-End APPs across scenarios, capturing expert insights;
User-friendly interaction for accessible and efficient battery R&D
Preview

Partners