{"id":867258,"date":"2024-10-04T11:54:54","date_gmt":"2024-10-04T11:54:54","guid":{"rendered":"https:\/\/www.capgemini.com\/de-de\/?page_id=867258"},"modified":"2026-01-22T07:46:18","modified_gmt":"2026-01-22T07:46:18","slug":"data-driven-quality-prediction-in-battery-production","status":"publish","type":"page","link":"https:\/\/www.capgemini.com\/de-de\/data-driven-quality-prediction-in-battery-production\/","title":{"rendered":"Data-Driven Quality Prediction in Battery Production"},"content":{"rendered":"\n
\"\"<\/picture><\/div>
<\/div>
Engineering<\/span><\/div><\/div>
\"capgemini-engineering\"\/<\/div><\/div><\/div>

Data-Driven Quality Prediction in Battery Production \u2013 How Capgemini and ACCURE optimize the production process<\/h1><\/div>
<\/div><\/div><\/div><\/div><\/div><\/header>\n\n\n\n
\n

Intelligent Formation Diagnostics is a disruptive new approach to battery cell production, combining the power of AI with physics-based models to deliver significant improvements in quality detection, cycle time reduction, and throughput.<\/p>\n\n\n\n

What are the challenges in battery cell production?<\/h2>\n\n\n\n

Battery cell manufacturing faces a multitude of challenges, including high scrap rates, energy waste, complex supply chains, and quality assurance. The overall goal is to produce high-quality and durable cells that maintain high performance over their lifetime, while keeping production costs low. A key enabler towards this goal is early detection of faulty cells and process optimization to reduce cycle time and costs.<\/p>\n\n\n\n

As new production lines ramp up in Europe, the difficulties in creating factories with consistent quality and acceptable scarp rates become ever more evident: Even established producers struggle to replicate quality standards in new facilities. Continuing cost pressures further complicate the situation.<\/p>\n\n\n\n

Why are formation and aging necessary?<\/h2>\n\n\n\n

The battery cell manufacturing is comprised of three phases: Electrode manufacturing, cell assembly, and cell finalization. The formation and aging process are most time-consuming steps and occur during cell finalization.<\/p>\n\n\n\n

The formation process is the initial charge-discharge cycle that a battery cell undergoes after the assembly under controlled conditions. The purpose is to create a highly defined solid-electrolyte interface at the electrodes \u2013 it\u2019s the foundation of a safe, stable and reliable battery cell. This is followed by the aging process, which measures the gradual self-discharge of the battery over time and serves as a quality control.<\/p>\n\n\n\n

Why does the solution focus on formation to end-of-line testing?<\/h2>\n\n\n\n

Reducing formation and aging time significantly cuts costs and energy use, and frees up production space, thereby reducing cycle time. Scrap cells waste both energy and money, so it\u2019s important to assess cells quality as early as possible.<\/p>\n\n\n\n

ACCURE and Capgemini are addressing quality assurance and prediction with an Intelligent Formation Diagnostic solution<\/strong><\/p>\n\n\n\n

“Mastering the data-driven optimization of the production process is one of the key differentiation levers for cell manufacturer. We are constantly exploring the market and are convinced that our formation diagnostic offering with ACCURE can be a game changer for our customers\u201d, states Michael M\u00fcller, Head of Climate Tech and Sustainability at Capgemini Engineering.<\/em><\/p>\n\n\n\n

What is the solution?<\/h2>\n\n\n\n

ACCURE\u2019s analysis leverage physics-based models, AI and existing data streams that are generated during battery formation to predict their lifetime performance. The validated and patented method only require voltage, current, and temperature and therefore, can easily be integrated into any existing production process. The seamless integration of the analytical module is ensured by Capgemini.<\/p>\n\n\n\n

Advanced formation diagnostics not only allow for early scrap detection and improved cell grading and sorting, but also allow to continuously optimize formation protocols to find the optimum balance between quality and speed.<\/p>\n\n\n\n

Dr. Kai-Philipp Kairies, CEO of ACCURE Battery Intelligence says: \u201cOur Formation Diagnostics enable early detection of battery cell quality, reducing scrap, lowering production costs, decreasing warranty risk, and increasing efficiency\u2014all without additional hardware. It\u2019s a true competitive advantage in battery manufacturing.\u201d<\/em><\/p>\n\n\n\n

What are the main benefits?<\/h2>\n\n\n\n
    \n
  1. Substantial reduction of aging and EOL tests<\/li>\n\n\n\n
  2. Significantly improved quality detection<\/li>\n\n\n\n
  3. Higher throughput of battery cells<\/li>\n\n\n\n
  4. Reduced cycle time of the battery cell production process<\/li>\n\n\n\n
  5. Early detection and handling of scrap prior to the aging process<\/li>\n\n\n\n
  6. Enhanced grading and sorting<\/li>\n\n\n\n
  7. Reduced long-term warranty risks<\/li>\n<\/ol>\n\n\n\n

    What is the approach to implement the solution?<\/h2>\n\n\n\n

    Each engagement starts with a pilot project where the value of the solution is proven on real-life data and an implementation roadmap is created based on the customer\u2019s unique production and IT landscape. For a successful validation, formation and EOL test data of 500-5,000 cells has proven to be sufficient.<\/p>\n\n\n\n

    The evaluation of the production and IT landscape involves reviewing system documentation, interviewing experts, and evaluating APIs, IT security, and authentication protocols. We also evaluate databases, data flows, and data strategies to ensure efficient data management. By establishing data standards and evaluating tools, we optimize the implementation processes and enhance overall reliability and safety.<\/p>\n\n\n\n

    \"\"<\/figure>\n\n\n\n

    Results of the pilot project are summarized in a final report that includes the validation results, a cost-benefit analysis and the roll-out of the solution. After a positive decision, the solution is integrated into the customer\u2019s production process and IT landscape without disrupting operations.<\/p>\n\n\n\n

    Why are ACCURE and Capgemini the best team for this?<\/h2>\n\n\n\n

    ACCURE specializes in predictive battery analytics, providing AI-driven software solutions that monitor and optimize battery performance, safety, and lifespan across mobility and stationary applications. Their platform delivers valuable insights into battery health, predicts failures, and extends battery life. ACCURE\u2019s team, composed of engineers and scientists from top research groups and tech companies, has a deep understanding of battery cell technology. ACCURE has a strong track record of improving battery safety, performance, and longevity, successfully preventing numerous battery incidents.<\/p>\n\n\n\n

    Capgemini brings extensive experience in digitizing production, especially in battery factories. With expertise in designing and maintaining IT landscapes, we manage, clean, and analyze large datasets. Operating in over 50 countries, with a workforce of about 350,000 skilled professionals, Capgemini is a global leader in intelligent industry and consulting services, including system integration, testing, and software development for manufacturing. We offer flexible solutions, delivering support locally or through a combination of both, to meet the client needs.<\/p>\n\n\n\n


    By optimizing the formation, aging and EOL process, we enable early scrap detection, reduce costs, shorten cycle times and increase throughput. Intelligent Formation Diagnostics provides a competitive advantage by improving quality assessment through existing data streams and reducing production costs.<\/p>\n\n\n\n

    <\/p>\n\n\n\n

    We’d be happy to arrange a meeting to discuss our experience with Intelligent Formation<\/p>\n<\/div><\/div><\/div><\/div><\/div><\/section>\n\n\n\n

    Authors<\/h3><\/div><\/div>
    \n\t\t
    \n\t\t\t
    \n\t\t\t\t
    \n\t\t\t\t\t
    \n\t\t\t\t\t\t\"Michael\n\t\t\t\t\t<\/div>\n\t\t\t\t\t
    \n\t\t\t\t\t\t
    \n\t\t\t\t\t\t\t
    \n\t\t\t\t\t\t\t\t