control.create_estimator_iosystem

control.create_estimator_iosystem(sys, QN, RN, P0=None, G=None, C=None, state_labels='xhat[{i}]', output_labels='xhat[{i}]', covariance_labels='P[{i},{j}]', sensor_labels=None)

Create an I/O system implementing a linqear quadratic estimator

This function creates an input/output system that implements a state estimator of the form

xhat[k + 1] = A x[k] + B u[k] - L (C xhat[k] - y[k]) P[k + 1] = A P A^T + F QN F^T - A P C^T Reps^{-1} C P A L = A P C^T Reps^{-1}

where Reps = RN + C P C^T. It can be called in the form

estim = ct.create_estimator_iosystem(sys, QN, RN)

where sys is the process dynamics and QN and RN are the covariance of the disturbance noise and sensor noise. The function returns the estimator estim as I/O system with a parameter correct that can be used to turn off the correction term in the estimation (for forward predictions).

Parameters

  • sys (InputOutputSystem) – The I/O system that represents the process dynamics. If no estimator is given, the output of this system should represent the full state.

  • QN (ndarray) – Process and sensor noise covariance matrices.

  • RN (ndarray) – Process and sensor noise covariance matrices.

  • P0 (ndarray, optional) – Initial covariance matrix. If not specified, defaults to the steady state covariance.

  • G (ndarray, optional) – Disturbance matrix describing how the disturbances enters the dynamics. Defaults to sys.B.

  • C (ndarray, optional) – If the system has all full states output, define the measured values to be used by the estimator. Otherwise, use the system output as the measured values.

  • {state (str or list of str, optional) – Set the name of the signals to use for the internal state, covariance, sensors, and outputs (state estimate). If a single string is specified, it should be a format string using the variable i as an index (or i and j for covariance). Otherwise, a list of strings matching the size of the respective signal should be used. Default is 'xhat[{i}]' for state and output labels, 'y[{i}]' for output labels and 'P[{i},{j}]' for covariance labels.

  • covariance (str or list of str, optional) – Set the name of the signals to use for the internal state, covariance, sensors, and outputs (state estimate). If a single string is specified, it should be a format string using the variable i as an index (or i and j for covariance). Otherwise, a list of strings matching the size of the respective signal should be used. Default is 'xhat[{i}]' for state and output labels, 'y[{i}]' for output labels and 'P[{i},{j}]' for covariance labels.

  • sensor (str or list of str, optional) – Set the name of the signals to use for the internal state, covariance, sensors, and outputs (state estimate). If a single string is specified, it should be a format string using the variable i as an index (or i and j for covariance). Otherwise, a list of strings matching the size of the respective signal should be used. Default is 'xhat[{i}]' for state and output labels, 'y[{i}]' for output labels and 'P[{i},{j}]' for covariance labels.

  • output}_labels (str or list of str, optional) – Set the name of the signals to use for the internal state, covariance, sensors, and outputs (state estimate). If a single string is specified, it should be a format string using the variable i as an index (or i and j for covariance). Otherwise, a list of strings matching the size of the respective signal should be used. Default is 'xhat[{i}]' for state and output labels, 'y[{i}]' for output labels and 'P[{i},{j}]' for covariance labels.

Returns

estim – Input/output system representing the estimator. This system takes the system input and output and generates the estimated state.

Return type

InputOutputSystem

Notes

This function can be used with the create_statefbk_iosystem() function to create a closed loop, output-feedback, state space controller:

K, _, _ = ct.lqr(sys, Q, R) est = ct.create_estimator_iosystem(sys, QN, RN, P0) ctrl, clsys = ct.create_statefbk_iosystem(sys, K, estimator=est)

The estimator can also be run on its own to process a noisy signal:

resp = ct.input_output_response(est, T, [Y, U], [X0, P0])

If desired, the correct parameter can be set to False to allow prediction with no additional sensor information:

resp = ct.input_output_response(

est, T, 0, [X0, P0], param={‘correct’: False)