摘要

The temperature distribution information plays an important role in various industrial applications. Owing to the advantages such as low cost and nonintrusive sensing, the acoustic tomography (AT) is considered to be a promising technique for the temperature distribution visualization, in which the reconstruction method is of great significance for real-world measurements. In contrast with available reconstruction algorithms, in this paper, a new simultaneous algebraic reconstruction technique (SART)-Gaussian process regression (GPR) method that integrates the advantages of the SART and the GPR is proposed to improve the reconstruction quality (RQ). Numerical simulations are implemented to evaluate the feasibility and effectiveness of the proposed reconstruction method, and the results validate the superiorities of the proposed method on improving the RQ and the robustness compared with other popular algorithms. Experimental results also demonstrate that the temperature distribution can be reconstructed effectively by the SART-GPR method. As a result, a useful approach is introduced for solving the AT inverse problem.