Leading Russian aluminium maker RUSAL has deployed a neural network to monitor the quality of aluminium ingots produced at the Irkutsk Aluminium Smelter. The new system automatically checks the surface quality of small aluminium ingots during production, before the ingots are packed for shipment to customers. Surface defects on each aluminium ingot are detected on the casting conveyor using a video monitoring system and special-purpose software. The neural network detects various types of defects, such as cracks, bumps, and foreign inclusions. All the information concerning the defects is saved and displayed as an analytical diagram, with data available regarding the number of each type of defect per day and the number of ingots that did not pass quality assurance per shift. Employees can tweak the parameters based on which ingots are found to be defective by choosing the type of defect and its size as per the specification for the product.The video monitoring system will be integrated with the existing automated production process control system and used on the casting line. Whenever a defect is found, the ingot is labelled as defective by a laser, and is then removed from the conveyor.The plan is for the new aluminium ingot quality assurance system to be used at the Company's other aluminium smelters. RUSAL has consistently been automating its production processes. Thus, the deployment of robotics systems at several of the Company's aluminium smelters has completely automated the task of stacking finished aluminium ingots onto pallets. The Company's production sites are now also adopting an automated video monitoring system to detect the accidental loss of hermetic sealing in the reduction cells.
Leading Russian aluminium maker RUSAL has deployed a neural network to monitor the quality of aluminium ingots produced at the Irkutsk Aluminium Smelter. The new system automatically checks the surface quality of small aluminium ingots during production, before the ingots are packed for shipment to customers. Surface defects on each aluminium ingot are detected on the casting conveyor using a video monitoring system and special-purpose software. The neural network detects various types of defects, such as cracks, bumps, and foreign inclusions. All the information concerning the defects is saved and displayed as an analytical diagram, with data available regarding the number of each type of defect per day and the number of ingots that did not pass quality assurance per shift. Employees can tweak the parameters based on which ingots are found to be defective by choosing the type of defect and its size as per the specification for the product.The video monitoring system will be integrated with the existing automated production process control system and used on the casting line. Whenever a defect is found, the ingot is labelled as defective by a laser, and is then removed from the conveyor.The plan is for the new aluminium ingot quality assurance system to be used at the Company's other aluminium smelters. RUSAL has consistently been automating its production processes. Thus, the deployment of robotics systems at several of the Company's aluminium smelters has completely automated the task of stacking finished aluminium ingots onto pallets. The Company's production sites are now also adopting an automated video monitoring system to detect the accidental loss of hermetic sealing in the reduction cells.
