Prediction model of ammonium uranyl carbonate calcination by microwave heating using incremental improved Back-Propagation neural network

The incremental improved Back-Propagation (BP) neural network prediction model was put forward, which was very useful in overcoming the problems, such as long testing cycle, high testing quantity, difficulty of optimization for process parameters, many training data probably were offered by the way of increment batch and the limitation of the system memory could make the training data infeasible, which existed in the process of calcinations for ammonium uranyl carbonate (AUC) by microwave heating. The prediction model of the nonlinear system was built, which could effectively predict the experiment of microwave calcining of AUC. The predicted results indicated that the contents of U and U4+ were increased with increasing of microwave power and irradiation time, and decreased with increasing of the material average depth.

Research highlights
► The incremental improved Back-Propagation neural network prediction model using the Levenberg–Marquardt algorithm based on optimizing theory is put forward.
► The prediction model of the nonlinear system is built, which can effectively predict the experiment of microwave calcining of ammonium uranyl carbonate (AUC).
► AUC can accept the microwave energy and microwave heating can quickly decompose AUC.
► In the experiment of microwave calcining of AUC, the contents of U and U4+ increased with increasing of microwave power and irradiation time, and decreased with increasing of the material average depth.