In the automotive/parts industry, the quality inspection of the gluing/sealing process is crucial. DaoAI 3D robot vision of WeLinkirt provides an efficient and accurate inspection and correction solution for this process.
User scenario: A leading automotive parts supplier. Its gluing/sealing process on the production line involves important automotive parts such as engine cylinder heads. During the gluing process, it is necessary to detect the width, height, and continuity of the glue to ensure that the gluing quality meets the product requirements. The detection object is the sealing rubber strip on the engine cylinder head.
Pain points: Under the traditional detection method, the miss-detection rate was relatively high, reaching about 3%, which caused some unqualified products to flow into the subsequent processes. At the same time, the false-alarm rate was also about 5%, increasing the unnecessary re-inspection workload. In addition, just as an automatic charging robot needs precise positioning and operation, the gluing robot also needs to precisely control the gluing path. However, the traditional method is difficult to achieve real-time path correction, which affects the gluing quality and production efficiency.
Technical principle
DaoAI 3D robot vision uses a self-developed 3D camera for imaging. Its principle is based on the structured light technology. By projecting a specific light pattern onto the surface of the detection object, the camera captures the deformation information of the reflected light and calculates the three-dimensional coordinates of the object surface using the triangulation principle, thus realizing high-precision three-dimensional shape reconstruction. In terms of 6D pose estimation, a deep-learning algorithm is used to analyze the collected 3D data to identify the position and pose of the object. This algorithm can learn the features and geometric information of the object, and can accurately estimate the pose even in a complex environment. For gluing detection, by analyzing the reconstructed 3D data, parameters such as the width and height of the glue can be accurately measured, and the continuity of the glue can be judged. Since the 3D data contains rich surface information, it can detect gluing defects more comprehensively and accurately.
- Structured light technology: Project a specific light pattern and calculate 3D coordinates through the deformation of the reflected light.
- Deep - learning 6D pose estimation: Learn object features and geometric information to accurately estimate the pose.
- 3D data gluing analysis: Accurately measure gluing parameters and judge continuity.
WeLinkirt solution and product
The core solution is DaoAI 3D robot vision. During the detection process, the self-developed 3D camera collects the 3D data of the glue on the engine cylinder head in real-time. The 6D pose estimation algorithm accurately positions the cylinder head to ensure the accuracy of the detection. The system can analyze the gluing data in real-time to determine whether there are defects such as too narrow width, insufficient height, or interrupted gluing. When a defect is detected, through the brain-eye - body closed-loop mechanism, the information is promptly fed back to the gluing robot to achieve real-time correction of the gluing path and ensure the consistency of the gluing quality. At the same time, it can be paired with the DaoAI AI AOI software system, using its positive-sample/few-sample learning function to quickly program new gluing processes and reduce the change-over time.
DaoAI 3D robot vision provides a reliable guarantee for the automotive parts gluing process with its high-precision detection and real-time correction capabilities.
Quantitative results: By applying DaoAI 3D robot vision, the detection rate of gluing defects has been increased to 98%, the miss-detection rate has been reduced to <2%, and the false-alarm rate has been reduced to 1%, effectively reducing the unnecessary re-inspection workload. At the same time, the change-over time has been shortened from the original 20min to 5min, greatly improving the production efficiency and meeting the production needs of different models of parts.
FAQ
What gluing defects can DaoAI 3D robot vision detect?
DaoAI 3D robot vision can detect defects such as too narrow glue width, insufficient height, and interrupted gluing. It collects 3D data through a self-developed 3D camera and accurately analyzes the gluing situation, with a detection rate of 98%.
How much can the change-over time be shortened after using this product?
Paired with the DaoAI AI AOI software system and using its positive-sample/few-sample learning function, the change-over time can be shortened from the original 20min to 5min, improving production efficiency.
How does this product achieve gluing path correction?
Through the brain-eye - body closed-loop mechanism, when a gluing defect is detected, the system promptly feeds back the information to the gluing robot to achieve real-time correction of the gluing path and ensure the consistency of the gluing quality.