Bridge dynamic weighing algorithm based on maximum entropy regularization

The invention provides a bridge dynamic weighing algorithm based on maximum entropy regularization. Comprising the following steps: 1, acquiring a bridge actual measurement response Mm and an influence line matrix IL when a vehicle passes through the bridge; 2, calculating an initial value A0 of the axle load by using Mm and IL, and defining an initial value ri = 1 of a regularization parameter, i representing the number of main cycles; 3, entering a sub-loop, substituting ri and A0 into an iterative formula of a nonlinear conjugate gradient method for calculation until the axle load converges, and the absolute value of the axle load difference value obtained by two times of iteration is smaller than e, namely Aik-Aik-1lt; e, assigning the axis weight Aik of the kth iteration to Ai after sub-cycle convergence; 4, substituting Ai into a Regiska formula to obtain a parameter V, and calculating a next regularization parameter ri + 1; 5, judging whether i is greater than 10 or not, if not, substituting ri = i + 1