Motor control in an electric power steering

1 . An electric power assisted steering system for a vehicle comprising:

an electric motor configured to apply an assistance torque to a part of a steering assembly so as to assist a driver of a vehicle in turning the steering wheel,

a drive circuit for the motor which selectively connects a plurality of motor phases to an electrical supply to cause current to flow in the motor phases, the amount of assistance torque applied by the motor being a function of the current flowing in the phases of the motor,

a control circuit configured to generate a control signal that is applied to the motor drive stage, the control signal indicating phase-resolved currents required in the motor phases, the control circuit comprising:

a PID controller configured to receive at an input a demand signal indicative of a required behaviour of the motor and provides, at an output the control signal that is fed to the drive stage for the motor, the controller arranged in a closed loop configuration with the motor and configured to minimise an error value comprising the difference between the demanded behaviour and the actual motor behaviour, and

a neural network including an input layer of neurons, at least one hidden layer of neurons, and an output layer,

wherein the neural network is a feedforward neural network configured to:

receives, at its input layer (i) the demand signal, (ii) the control signal output from the PID controller, the error value, and (iv) at least one environmental variable not used in the PID control loop;

compute proportiona (P gain), integral (I gain), and derivative (D gain) gain terms as respective neuron values internal to the hidden layer; and

update the proportional, integral and derivative gain terms in real time using gradient-descent backpropagation in response to each computed error signal so as to adaptively tune the controller to electrical, mechanical and operating-condition variations on the steering system.

2 . A system according to claim 1 in which the demand signal comprises a torque demand signal indicative of a torque that is required from the motor, and the measure of the motor behaviour comprises a measurement of the motor torque.

3 . A system according to claim 1 in which the demand signal input to the PID controller comprises a current demand signal Idq_set indicative of the required motor current.

4 . A system according to claim 1 in which the values of one or more of the P I and D terms used by the PID controller are set directly by the neural network in real time.

5 . A system according to claim 1 in which the neural network is configured to set the values of one or more of the P I and D terms when the electric power steering system is offline and to store the values in a look up table for use by the controller in real time.

6 . A system according to claim 1 in which the neural network is configured to determine one or more of the P I and D gain values as respective nodal values within a hidden layer of the neural network.

7 . A system according to claim 1 in which the environmental variable comprises at least one of the following:

the speed of the vehicle,

the motor rotation speed/angle for the current/torque control, and

steering torque or angle.

8 . An electric power assisted steering system for a vehicle comprising: an electric motor configured to apply an assistance torque to a part of a steering assembly so as to assist a driver of a vehicle in turning the steering wheel,

a drive circuit for the motor configured to selectively connect motor phases to an electrical supply to cause current to flow in the motor phases, the amount of assistance torque applied by the motor being a function of the current flowing in the phases of the motor,

and a control circuit configured to generate a control signal that is applied to the motor drive stage, the control circuit comprising:

a PID controller configured to receive at an input a demand signal indicative of a required behaviour of the motor and provides at an output the control signal that is fed to the drive stage for the motor, the controller arranged in a closed loop configuration with the motor and configured to minimise an error value comprising the difference between the demanded behaviour as indicated by the demand signal and the actual behaviour of the motor, and

a neural network including an input layer of neurons, at least one hidden layer of neurons, and an output layer comprising at least one output neuron,

the neural network comprising a feedforward neural network that receives at the input layer of input neurons the demand signal, the control signal output from the controller and the error value,

wherein the neural network is configured to determine one or more of the P gain, gain and D gain terms used by the PID controller,

wherein the neural network receives as an additional feedforward term at least one additional discrete environmental variable, and

wherein the neural network is configured to set the values of one or more of the P I and D terms when the electric power steering system is offline and to store the values in a look up table for use by the controller in real time.

9 . A system according to claim 8 in which the demand signal comprises a torque demand signal indicative of a torque that is required from the motor, and the measure of the motor behaviour comprises a measurement of the motor torque.

10 . A system according to claim 8 in which the demand signal input to the PID controller comprises a current demand signal Idq_set indicative of the required motor current.

11 . A system according to claim 8 in which the values of one or more of the P I and D terms used by the PID controller are set directly by the neural network in real time.

12 . A system according to claim 8 in which the neural network is configured to determine one or more of the P I and D gain values as respective nodal values within a hidden layer of the neural network.

13 . A system according to claim 8 in which the environmental variable comprises at least one of the following:

the speed of the vehicle,

the motor rotation speed/angle for the current/torque control, and

steering torque or angle.

14 . An electric power assisted steering system for a vehicle comprising:

an electric motor configured to apply an assistance torque to a part of a steering assembly so as to assist a driver of a vehicle in turning the steering wheel,

a drive circuit for the motor which selectively connects the motor phases to an electrical supply to cause current to flow in the motor phases, the amount of assistance torque applied by the motor being a function of the current flowing in the phases of the motor,

and a control circuit configured to generate a control signal that is applied to the motor drive stage, the control signal indicating the currents required in the motor phases, in which the control circuit comprises:

a PID controller configured to receive at an input a demand signal that comprises a current demand signal Idq_set indicative of the required motor current of a required behaviour of the motor and provides at an output the control signal that is fed to the drive stage for the motor, the controller arranged in a closed loop configuration with the motor and configured to minimise an error value comprising the difference between the demanded behaviour as indicated by the demand signal and the actual behaviour of the motor, and

a neural network which has including an input layer of neurons, at least one hidden layer of neurons, and an output layer comprising at least one output neuron,

in which the neural network comprises a feedforward neural network that receives at the input layer of input neurons the demand signal, the control signal output from the controller and the error value

and in which the neural network is configured to determine one or more of the P gain, I gain and D gain terms used by the PID controller,

and further in which the neural network receives as an additional feedforward term at least one additional discrete environmental variable.