Researchers in China have improved the accuracy of detecting space junk in orbit around the earth. The goal of the project is to allow more effective plotting of safe routes for spacecraft maneuvers. The researchers say that after more than 50 years in space, there is all sorts of debris in orbit that spacecraft need to avoid for safety.
So far, some space junk identification systems have been developed, but it is hard to pinpoint small and fast space debris. The team created a set of algorithms for laser ranging telescopes that have significantly improved the rate of space debris detection. The researchers say that after improving the pointing accuracy of the telescope using a neural network, space debris with a cross-sectional area of 1 meter squared and a distance of 1,500 km can be detected.
Previous algorithms allowed the detection of debris, but the accuracy was only to a 1km level. Using the neural network and a pair of correcting algorithms has optimized the network thresholds for the recognition of space debts. This ensures the network wasn’t too sensitive and could be trained on localized areas of space.
Researchers on the project demonstrated the improved accuracy compared to three traditional methods at the Beijing Fangshan laser range telescope station. The team says that the new positioning correction algorithms proved the most accurate and was easy to operate with good real-time performance.
The observation data of 95 stars was used to solve the algorithms coefficients for each method, and the accuracy of detecting 22 other stars was assessed. Researchers plan to refine the technique further. One researcher notes that obtaining the orbit of space debris helps with the safe operation of spacecraft.