Abstract: The present application relates to automatic decision-making for welding. Multi-dimensional data cleaning is performed and dimensional data warehouse is established by processing, filtering and converting basic source data of welding nodes in a welding process for monocrystal pulling-up into data sets easily identified and marked and establishing respective models based thereon. Basic source data of a current welding nodes are obtained and converted into process parameters. The process parameters are compared with respective models in the dimensional data warehouse to obtain a first determination result. Data analysis is performed on the first determination result to determine whether the current welding process is abnormal to obtain a second determination result. Decision is made automatically based on the second determination result.

Abstract: The present application relates to automatic decision-making for pulling. Multi-dimensional data cleaning is performed and dimensional data warehouse is established by processing, filtering and converting basic source data of pulling nodes in a pulling process for monocrystal pulling-up into data sets easily identified and marked and establishing respective models based thereon. Basic source data of a current pulling nodes are obtained and converted into process parameters. The process parameters are compared with respective models in the dimensional data warehouse to obtain a first determination result. Data analysis is performed on the first determination result to determine whether an abnormality occurs in the current pulling process to obtain a second determination result. Decision is made automatically based on the second determination result.

Abstract: The present disclosure relates to automatic decision-making for re-feeding. Multi-dimensional data cleaning is performed and dimensional data warehouse is established by processing, filtering and converting basic source data of re-feeding nodes in a re-feeding process for monocrystal pulling-up into data sets easily identified and marked and establishing respective models based thereon. Basic source data of a current re-feeding nodes are obtained and converted into process parameters. The process parameters are compared with respective models in the dimensional data warehouse to obtain a first determination result. Data analysis is performed on the first determination result to determine whether an abnormality occurs in the current re-feeding process to obtain a second determination result. Decision is made automatically based on the second determination result.

Abstract: The invention discloses (110) dislocation-free monocrystalline silicon and its preparation and the graphite heating system used. The process for preparation is as follows: clearing furnace and tidy the heat field; loading furnace; vacuumizing and argon charging; heating raw material; crystal seeding; expanding shoulder; rotating shoulder: speeding up the speed of shoulder-expanding; equal diameter: after shoulder-rotating, stabilize the crystal growth speed; finishing: turning off the power of crucible, decreasing the drawing rate manually; turning off the furnace. The graphite heating system includes: upper insulation column, lower insulation column and hearth tray arranged from the top down to form the external shell, and the peripheral surface is a stepped structure, and the thickness of the insulation layer of the upper insulation column is 20-30 mm, the thickness of the insulation layer of the lower insulation column is 60-70 mm, and the thickness of the insulation layer of the hearth tray is 70-80 mm.