Intelligent Monitoring and Treatment System of Heavy Metal Contaminated Soil Based on Artificial Bee Colony Algorithm and Edge Computing Nanotechnology

Abstract The CGABC algorithm improves the convergence speed of the algorithm by crossing the solution generated by the neighborhood search of bees with the current global optimal solution. By selecting reasonable cross-operation coefficients to balance the algorithm's global optimization ability and local search ability, and adding random interference terms to increase population diversity. By optimizing the test function, it was verified that the performance of the CGABC algorithm is superior to the ABC algorithm and GABC algorithm. In the context of environmental remediation, particularly in the treatment of heavy metal-contaminated soil, optimizing treatment methods through advanced computational algorithms has become increasingly critical. This paper introduces an intelligent monitoring and treatment system based on the Artificial Bee Colony (ABC) algorithm, incorporating edge computing and nanotechnology for the remediation of heavy metal-contaminated soils. To improve the efficiency and effectiveness of the system, we propose two enhanced algorithms: the Cooperative Global Artificial Bee Colony (CGABC) and Chaotic Tabu Search Artificial Bee Colony (CTABC) algorithms. Magnetic core iron trioxide was prepared by co-precipitation method, with an average particle size of 10–15 nm. Magnetic mesoporous nanoparticles Fe 3 O 4 and SiO 2 with uniform particle size and good dispersion were prepared using the Stober method. The specific surface area before calcination was 305.8 m 2 /g, and the pore size was 2.5 nm. The average particle size after calcination was around 200 nm. EDTA ferric oxide and silica were obtained by modification with N triacetate sodium salt. Fourier transform infrared spectroscopy showed successful EDTA modification with a specific surface area.