Abstract: A new algorithm for adjustment model with some nonnegative constrained parameters is suggested. In this algorithm, nonnegative constrained least-square problems are first transformed to convex quadratic programming problems, and then the programming problems are solved for the optimal solutions. The are necessary and sufficient conditions on the solvability for optimization solution are given, consequently the general form of least-squares estimation in adjustment model is given, as well as algorithm that are simple and easy to understand. A comparative calculation on a simulation example indicates that this algorithm can be applied to adjustment computation in the practical measurement.