3D ACI for Battery Electrode Coating: Quality Traceability and Data Closure

DaoAI's 3D ACI equipment (featuring proprietary 3D cameras + 3D morphology reconstruction/point clouds, detecting hidden solder joints/coplanarity/micron-level morphology/pores, and other 2D optical blind spot defects, with 2D-3D fusion) significantly improved the quality traceability efficiency in new energy battery electrode coating by 75% compared to inefficient manual recording and sampling inspection methods, through deep integration of 3D morphological data and AI algorithms, substantially reducing batch quality risks and recall costs.

As the core driving force of global energy transformation, new energy batteries demand highly refined manufacturing processes and stringent quality control, which directly determine battery performance, safety, and cycle life. Among many critical processes, electrode coating is often referred to as the “first hurdle” in battery manufacturing; its coating uniformity, thickness consistency, and surface defects directly impact subsequent calendering, slitting, and assembly. Traditional 2D optical inspection solutions for online full inspection of electrode coating are often limited by imaging principles, struggling to effectively identify 3D morphological defects such as tiny air bubbles beneath the coating, dark area depressions, or uneven edges, and cannot provide deep data support for quality traceability. It is in this context that DaoAI's 3D ACI equipment has provided a breakthrough solution for a leading battery manufacturer's electrode coating line. By combining high-precision 3D morphology reconstruction with 2D-3D fusion technology, it achieves precise capture of these traditional blind spot defects and establishes a comprehensive quality traceability and data closure system, improving product quality and production efficiency from the source.

Pain Points: Why This Hurdle Is Difficult to Overcome

Online full inspection of new energy battery electrode coating faces multiple challenges, leading to high rates of undetected defects with traditional inspection solutions, posing significant production risks. First, **internal coating defects are difficult to identify**: for example, tiny air bubbles, inclusions, or depressions beneath the coating. 2D images only show surface color and texture variations, making them almost powerless against these internal or depth-related defects, with undetected defect rates often exceeding 2%. Second, **edge morphology and coplanarity detection are missing**: uneven coating at the electrode edges, burrs, or abrupt thickness changes, as well as localized unevenness (coplanarity) on the coating surface—these micron-level morphological defects significantly impact battery performance but are overlooked in traditional 2D inspection, leading to increased internal resistance or localized heating in finished batteries. Third, **data silos lead to difficult traceability**: even when defects are found, traditional solutions typically only record defect types and locations, lacking deep correlation with specific coating parameters, batch numbers, time, and other production data. This makes it time-consuming and labor-intensive to trace the root cause and pinpoint abnormal processes or equipment when quality issues arise, with average traceability cycles lasting several hours or even days, severely affecting problem resolution efficiency and the accuracy of batch product recalls. This lack of data closure also hinders the greater application of industrial vision in building digital twins, making it difficult to achieve true production process optimization.

The root cause of these difficulties lies in the complexity of the electrode coating process; even minor fluctuations in parameters such as coating rheology, doctor blade pressure, and drying temperature can cause subtle morphological defects. Traditional 2D optical imaging, being a two-dimensional projection, cannot acquire depth information. For defects hidden within the coating or manifesting only as slight 3D morphological changes, such as uneven coating thickness, localized bumps, or depressions, 2D image grayscale or color variations are insufficient to provide reliable discrimination. Furthermore, the reflective properties of the electrode material itself can cause localized overexposure or underexposure, further affecting 2D image quality. With increasingly fast production cycles, manual inspection is even more inadequate, not only being inefficient and costly but also inconsistent due to subjective factors, failing to meet the stringent requirements of the new energy battery industry for high quality, high efficiency, and full traceability.

Technical Principles

The core of DaoAI's 3D ACI equipment lies in its self-developed high-speed, high-precision 3D camera and advanced 3D morphology reconstruction algorithms, deeply integrated with the DaoAI ACI OS. The equipment utilizes multi-view structured light projection technology, projecting a series of known pattern gratings onto the electrode surface, and simultaneously capturing deformed grating images from multiple cameras at different angles. DaoAI's proprietary algorithms precisely calculate the 3D coordinates of each point on the electrode surface from this deformation data, generating high-density point cloud data and high-precision 3D morphology maps. Compared to traditional laser triangulation, our multi-view structured light solution offers stronger robustness to material reflectivity and achieves sub-micron level Z-axis accuracy, effectively capturing critical morphological information such as coating thickness, flatness, and edge contours. For example, it can precisely identify and quantify deviations in micron-level coating thickness variations.

At the algorithmic level, DaoAI integrates this high-dimensional 3D data with 2D images and feeds them into the visual foundation models embedded in the DaoAI ACI OS. This model, through APDT (Positive Sample/Few-Shot Learning) technology, can quickly learn normal morphological features of products with just 1–20 good samples and accurately identify and classify abnormal morphologies. Compared to traditional rule-based AOI, DaoAI's 3D ACI equipment can not only detect hidden defects that traditional 2D solutions struggle with (such as bubbles under the coating, internal depressions) but also quantify defect depth, volume, and other parameters using 3D data, providing more objective evidence for defect severity assessment. Simultaneously, with semantic false alarm filtering, the system effectively reduces false alarm rates, alleviating the pressure of manual re-inspection. DaoAI's 3D ACI equipment establishes a complete digital twin data chain, enabling fine-grained monitoring of the electrode coating process, providing a solid data foundation for subsequent quality traceability.

Typical Application Scenarios

• **Coating Thickness and Uniformity Detection**: DaoAI's 3D ACI equipment, through 3D morphology reconstruction, can real-time measure the absolute and relative thickness differences of any point on the coating, precisely identifying local thin, thick, or uneven areas, ensuring coating thickness within an error range of ±5μm. The challenge lies in maintaining measurement accuracy and throughput on high-speed production lines.
• **Micron-Level Bubble and Depression Detection**: Traditional 2D solutions have limited ability to identify tiny bubbles or depressions within or on the coating surface. DaoAI's 3D camera can accurately capture these 3D morphological features that form tiny protrusions or indentations on the surface, accurately detecting even defects smaller than 50μm in diameter.
• **Edge Coating Morphology and Burr Detection**: Uneven coating, overflow, or tiny burrs at the electrode edges are significant factors affecting battery safety and internal resistance. DaoAI's 3D ACI equipment, by performing high-precision 3D reconstruction of edge contours, can quantify edge straightness, flatness, and identify tiny burrs with heights above 10μm.
• **Depth Analysis of Foreign Objects and Scratches**: In addition to surface foreign objects, some scratches may have a certain depth. DaoAI's ACI not only identifies these defects but also analyzes their depth and volume using 3D data, distinguishing between surface scratches and deeper damage, providing a basis for defect grading.
• **Coplanarity and Flatness Assessment**: For large-area electrodes, overall flatness and local coplanarity are crucial for subsequent calendering processes. DaoAI's 3D ACI equipment can generate full-field 3D point cloud maps to assess the overall flatness of the electrode surface and identify local bulges or wavy deformations, ensuring products meet strict geometric dimension requirements.

Case Study

A leading domestic new energy battery manufacturer faced persistent quality traceability challenges in its electrode coating process. Their existing 2D AOI system could identify some surface defects, but it had blind spots for 3D morphological defects such as bubbles under the coating or tiny depressions. Crucially, the inspection data was siloed from production line PLC (Programmable Logic Controller) data and MES (Manufacturing Execution System) data. When batch quality issues arose, engineers spent considerable time on manual troubleshooting, averaging over 4 hours per traceability event, severely impacting production efficiency and problem response speed. To address this pain point, the manufacturer introduced DaoAI's 3D ACI equipment for online full inspection of electrode coating.

The DaoAI team deployed multiple 3D ACI devices according to the specific conditions of their production line and deeply integrated the inspection data into the customer's MES system. Through the DaoAI ACI OS, every inspection result for electrode coating, including 3D morphological data, defect type, precise location, and corresponding coater parameters (such as coating speed, coating amount, baking temperature, etc.), was uploaded in real-time and linked to the product batch number. After deployment, the system not only reduced the undetected defect rate to <0.4% but, more importantly, when quality anomalies occurred, engineers could quickly retrieve complete inspection data for relevant electrodes and corresponding production process parameters within just 1 hour via the MES system, achieving precise defect localization and root cause analysis. This improvement boosted the manufacturer's defect traceability efficiency by 75%, significantly reducing troubleshooting time and effectively preventing the risk of batch product recalls due to inadequate traceability. Simultaneously, by analyzing accumulated defect data, the customer could quickly identify issues such as equipment parameter drift or raw material batch anomalies, enabling preventive maintenance and process optimization, significantly improving production yield.

“DaoAI 3D ACI is not just an inspection tool; it's a crucial component in our journey to digitize the entire production process and build a quality digital twin, transforming our quality traceability from 'finding a needle in a haystack' to 'precise localization.'”

DaoAI Solution and Products

DaoAI's solution for new energy battery electrode coating centers on the organic combination of its 3D ACI equipment and the DaoAI ACI OS. Our 3D ACI equipment integrates a self-developed high-speed, high-precision 3D camera, capable of acquiring 3D point cloud data of the electrode surface at speeds of thousands of frames per second, ensuring 100% full inspection at high production rates. Through advanced 3D morphology reconstruction algorithms, even micron-level coating thickness differences, bubbles, or depressions can be precisely captured and quantified. For deployment, DaoAI supports 100% on-premise private deployment, ensuring customer data security and compliance, with all data remaining within the factory. For model training, the DaoAI ACI OS utilizes APDT few-shot learning technology, requiring only 1–20 good samples for customers to complete automatic model programming within 5 minutes, significantly reducing line changeover and new product introduction times.

Furthermore, the DaoAI solution emphasizes data closure and traceability. Through deep integration with customer MES/SCADA systems, DaoAI's 3D ACI equipment associates the inspection results of each electrode (including 2D/3D images, defect type, location, size, and 3D morphological data) with production batch numbers, equipment parameters, and other information, forming traceable quality archives. This not only meets the customer's stringent traceability requirements but also provides rich and accurate data sources for building higher-dimensional digital twin systems. By continuously collecting and analyzing this data, customers can further optimize coating process parameters, implement predictive maintenance, and even drive the DaoAI World model for deeper production optimization and decision support. DaoAI is committed to providing customers with a full-chain intelligent vision solution, from inspection and analysis to traceability and optimization, truly realizing the intelligent upgrade of production lines.

DaoAI's 3D ACI equipment, by accurately identifying 2D optical blind spot defects, reduces the undetected defect rate in the electrode coating process to <0.4%. Simultaneously, through deep integration with production data, it achieves efficient quality traceability and data closure, improving defect traceability efficiency by 75%. This not only significantly reduces manual re-inspection workload and lowers operating costs but, more importantly, substantially enhances product quality stability and batch consistency, providing a solid guarantee for the long-term reliability of new energy batteries, ultimately translating into significant economic benefits and market competitiveness.

Full solution for this scenario: the full inspection solution for New-energy batteries · Inline Electrode Coating Inspection

This article was generated by AI. Customer cases are simulated scenarios based on real product capabilities and figures are illustrative; see product pages for official benchmarks.