- System delineation
TThe intelligence system supports the quality inspection process (approve /reject products) automatically. It captures the knowledge needed in the scope of the quality check task and includes the agents (humans and robots), the sensors, and the software. This knowledge is implemented in an intelligence engine that continuously supports the decision making process, removing this burden from the humans.
The artificial vision system is an autonomous system that does not require the supervision of an operator to verify that the quality of information matches the quality of the products checked. It has been fully integrated in HORSE middleware which ensures a secure data transfer and an internal diagnostics module which ensures that the system is operating correctly for each product and each image.
- Requirements and functions
The main function offered is the automated quality inspection for the final wiper product.
Critical features of the wiper systems are recorded using high definition cameras. This is facilitated by the integrated HORSE robot which appropriately grabs the product and rotates it in front of the camera to capture pictures of the product from all angles.
In case there are issues the images are also displayed to an operator who can visually inspect for defects. The areas of the components which need additional human inspection are indicated using augmented reality.
The main function is provided by a set of cameras, lights and software technologies embedded in a black box and which is orchestrated to support the actions and tasks of a robot. This HORSE MPMS is responsible for the orchestration of all the sensors, machines, robots and humans, and ensures that there is no lack of communication between different agents in the work cell. Hence there is an accurate and automated quality inspection of the product. Alerts to the operator of troubleshooting or possible defects are created to inform when there is a product that needs human inspection. Also the system handles fake alerts or wrong behavior for the machines by adopting triggers that indicate a fake alert of wrong decision, which is then fixes by the local quality department by teaching the system and ensuring avoiding the same issue in future quality evaluations.
- System description
The main part of the BOS vision system developed in HORSE is the “Adapter”.
The Bosch (BOS) adapter operates as a bridge between the HORSE middleware (message broker) and the corresponding Bosch industrial equipment: the Visual Control systems (to which it communicates via EtherCAT), the conveyor belt (to which it communicates via PLC) and a beacon and a switch (to which it also communicates via a separate PLC). The adapter ensures the communication with three protocols – the HORSE messaging protocol, the format of the EtherCAT frames and the PLC (by exchanging XML files through TCP-IP) protocol. See the attached diagram for more information on the proposed idea:
- Demonstration scenarios
The following scenario describes a use case, which involves a conveyor belt, a robot, high definition cameras and sensors and operators sharing together the same workspace. In order to ensure the operator’s safety and avoid emergency stops, we use a situation awareness components which relies on contextual data and adapt the robot behavior accordingly.
In this scenario, the worker is assisted during the inspection of the wiper systems. The worker who was previously at the end of the production line, checking visually the final quality of the produced part and rejecting the part in case a defect is shown has been replaced by this automated system.
This with the help of a robot and the equipment mentioned above, checks the product by means of high definition cameras. Because many features has to be checked, the product itself is rotated in front of the camera (using a robot) to make sure all angles of the product are covered. When faults are identified by the visual inspection system, the human is informed to come and check the product.
The images are then displayed to an operator that can visually inspect for defects. The locations of the features where inspection has to take place are indicated using augmented reality.
- Download information
Access rights shall be granted after written request (with a separate license agreement) on a non-exclusive basis, without the right to sublicense, and in case of software, in object code. The request for access right may be made during the project or up to twelve months after the end of the project. The request will specify the intended purpose (implementation of the action necessary for exploitation of its own result) and a demonstration of the rights is needed.
Access rights shall be granted against financial compensation if needed for the exploitation of a party's own results in case of direct or indirect industrial or commercial exploitation.