A Predictive Controller on the FPGA by Hardware Matrix Inversion
Cheap, efficient and industrial-grade model predictive controllers are required for extending the use of model predictive control (MPC) to resource-constrained embedded computing platforms and practical industrial fields. We implement the matrix inversion on hardware to improve the computation efficiency of our previous designed MPC controller. For the specific matrices in each iteration of active set method, a simple positive definite symmetric matrix inversion algorithm is proposed, which can transform matrix inversion into iterated matrix multiplication and add operations along with fewer division operations. Its similar calculating formulas in each iteration are very suitable for block design in hardware. To avoid extra data transmission, the matrix inversion algorithm and active set method are combined through time sequence and architecture design to form an improved predictive controller on FPGA. The improved predictive controller is implemented on a FPGA-based board specially-made for the industrial sites and applied to a holding process of the injection moulding, which achieves satisfactory control performance.
Injection molding machine HTL68/JD Physical map of the FPGA-based board
Inner structure of S-ECQP (the combination of SPMI algorithm and ECQP) solver
