I recently upgraded to BBS 2.6.0.51, and I’ve found that it is much better at first layer defect and spaghetti detection. Also, adding bookmarks to models is much faster than the glacial pace of 2.3x–2.5.x. Also, so far, the cursor hasn’t stopped working, like in 2.5.x where I would have to quit and restart the app to get any functionality. So, I know it’s not perfect, and it has defects with other BBL printers, but as far as the X1C goes, this is a great update. Thank you BBL.
Please note: the model slicing software does not affect the quality of print defect detection. This process is performed on Bamboo servers, through which the video of the printing process is transmitted.
This is just your imagination.
The X1 series has the capability to detect failures/spaghetti based on the processing power it has. This system uses a machine-learning algorithm and all the data processing is done locally.
When the printer is used in LAN mode, the printer behaves just like when it is not connected to the internet and uses local processing to provide this feature.If the printer is not connected to the cloud, and the user improvement option is not enabled, the printer will rely only on the information it has in the latest firmware for failure detection, which might be outdated compared to the cloud-connected experience where the AI model is updated regularly. We recommend updating the firmware regularly to benefit from additional improvements that will be added over time.
This isn’t true. Even the new H2’s computing power doesn’t allow for local defect detection, let alone the computing power of the old X1. Therefore, this function only really works via the Bamboo Cloud, where the neural network is installed on powerful servers.
But it is true. I’ve been printing LAN-only for years, with the X1C blocked from the internet at the router. First-layer and spaghetti detection work very well, exactly as they did with the cloud connection.
If your newer printer lacks this ability, you have my sympathy.
The x1с has a lidar sensor that detects irregularities in the first layer. This doesn’t require AI or a neural network; it’s a very simple procedure. But detecting “spaghetti” is much more difficult.
I printed on the wonderful X1C for three years and became very familiar with all its capabilities and design.
1 Like
I can find no mention anywhere that defect detection relies on video sent to the Bambu servers. Every indication is that all defect detection is performed locally. If you have a reliable source that says detection is performed in the cloud, I would be interested in seeing it.
The P2/X1/X2/H2 printers all use a Rockchip RV1126 high-performance vision processor SoC (System-on-Chip), which incorporates a Quad-core ARM A7 processor and a built-in NPU for AI-related applications.
You are correct to say that a Studio update does not change defect detection. A firmware update theoretically may make a difference by modifying the detection algorithm used by the processor.
More information here, explaining how spaghetti detection is done locally:
1 Like