Predictive control method and apparatus

Claim 2

A predictive control method for controlling a physical object, the physical object being responsive to a manipulated variable signal U n and producing a controlled variable signal X n , comprising the steps of: (1) preparing a multi-layered neural network as an identification model for said physical object; (2) receiving, at said multi-layered neural network, said controlled variable signal X n and said manipulated variable signal U n , at a sampling time, and predicting a predicted value Z n+1 for said controlled variable signal X n using said multi-layered neural network; (3) computing an error signal ΔX n+1 between said predicted value Z n+1 and a desired value d n+1 for said controlled variable signal X n ; (4) receiving said error signal ΔX n+1 at said multi-layered neural network, finding a correction amount ΔU n for said manipulated variable signal U n using back propagation within said multi-layered neural network, and correcting said manipulated variable signal U n according to said correction amount ΔU n; and (5) transmitting said corrected manipulated variable signal to said physical object and controlling said physical object according to said corrected manipulated variable signal.

Claim 3

The method according to claim 1, wherein said predicting operation of step (2) comprises the steps of: (a) setting input signals corresponding to said manipulated variable signal U n and said controlled variable signal X n ; and (b) finding said predicted value Z n+1 corresponding to an output value X n+1 for said controlled variable signal X n using forward computation within said multi-layered neural network.

Claim 4

The method according to claim 1, wherein step (3) comprises the steps of: calculating an error signal ΔX n+1 from said predicted value Z n+1 and said desired value d n+1 on the basis of the following equation ΔX.sub.n+1 =d.sub.n+1 -Z.sub.n+1 ; and finding an error function E n+1 from said error signal ΔX n+1 on the basis of the following equation E.sub.n+1 1/2(ΔX.sub.n+1).sup.T Ks(ΔX.sub.n+1) where Ks=a gain determinant.

Claim 5

The method according to claim 1, wherein step 4 comprises the steps of: finding, using back propagation, said correction amount ΔU n , on the basis of the following equation ΔU.sub.n =-(dE.sub.n+1)/(dU.sub.n) where E n+1 is an error function; and adding said correction amount ΔU n to said manipulated variable signal U n .

Claim 6

The method according to claim 1, wherein step (1) is performed by arranging said multi-layered neural network in three layers including an input layer, an intermediate layer and an output layer.

Claim 7

The method according to claim 1, wherein said predicting part of step (2), said computing part of step (3), and said finding part of step (4) are repetitively carried out over a period bounded by said sampling time.

Claim 8

A predictive control apparatus for controlling a physical object, the physical object being responsive to a manipulated variable signal U n and producing a controlled variable signal X n , comprising: a multi-layered neural network used as an identification model for said physical object; first means for receiving said controlled variable signal X n and said manipulated variable signal U n into said multi-layered neural network, at a sampling time, and for predicting a predicted value Z n+1 for said controlled variable signal X n using said multi-layered neural network; means for computing an error signal ΔX n+1 between said predicted value Z n+1 and a desired value d n+1 for said controlled variable signal X n ; second means for receiving said error signal ΔXn+1 into said multi-layered neural network, for finding a correction amount ΔU n for said manipulated variable signal U n using back propagation within said multi-layered neural network, and for correcting said manipulated variable signal U n according to said correction amount ΔU n ; and means for transmitting said corrected manipulated variable signal to said physical object and controlling said physical object in accordance with said corrected manipulated variable signal.

Claim 9

A predictive control apparatus for controlling a physical object, the physical object being responsive to a manipulated variable signal U n and producing a controlled variable signal X n , comprising: a multi-layered neural network used as an identification model for said physical object; first means for receiving said controlled variable signal X n and said manipulated variable signal U n into said multi-layered neural network, at a sampling time, and for predicting a predicted value Z n+1 for said controlled variable signal X n using said multi-layered neural network; means for computing an error signal ΔX n+1 between said predicted value Z n+1 and a desired value d n+1 for said controlled variable signal X n ; second means for receiving said error signal ΔXn+1 into said multi-layered neural network, for finding a correction amount ΔU n for said manipulated variable signal U n using back propagation within said multi-layered neural network, and for correcting said manipulated variable signal U n according to said correction amount ΔU n ; and means for transmitting said corrected manipulated variable signal to said physical object and controlling said physical object in accordance with said corrected manipulated variable signal.

Claim 10

The apparatus according to claim 7, wherein said first means comprises means for setting input signals corresponding to said manipulated variable signal U n and said controlled variable signal X n ; and means for finding said predicted value Z n+1 corresponding to an output value X n+1 for said controlled variable signal X n using forward computation within said multi-layered neural network.

Claim 11

The apparatus according to claim 7, wherein said means for computing an error signal comprises: means for calculating an error signal ΔX n+1 from said predicted value Z n+1 and said desired value d n+1 on the basis of the following equation ΔX.sub.n+1 =d.sub.n+1 -Z.sub.n+1 ; and means for finding an error function E n+1 from said error signal ΔX n+1 on the basis of the following equation E.sub.n+1 =1/2(ΔX.sub.n+1).sup.T Ks(ΔX.sub.n+1) where Ks=a gain determinant.

Claim 12

The apparatus according to claim 7, wherein said second means comprises: means for finding, using back propagation, said correction amount ΔU n , on the basis of the following equation ΔU.sub.n =-(dE.sub.n+1)/(dU.sub.n where E n+1 is an error function: and means for adding said correction amount ΔU n to said manipulated variable signal U n .

Claim 13

The apparatus according to claim 7, wherein said multi-layered neural network is comprised of a three-layered neural network having an input layer, an intermediate layer and an output layer.

Claim 14

The apparatus according to claim 7, wherein said transmitting means comprises: an integrator, coupled to said second means and having an output for supplying said manipulated variable signal U n ; and a switch, coupled to said integrator, for delivering said output of said integrator to said physical object, said switch being operable at a sampling interval.

Claim 15

The apparatus according to claim 12, wherein said output of said integrator comprises a joint angle torque, and wherein said controlled variable signal X n comprises joint angular velocities.

Claim 16

The apparatus according to claim 7, further comprising a delay circuit for delaying said controlled variable signal X n from said physical object.