Moving average load estimator. Load is estimated as the mean of the last window_size samples. Noise can be added using the following optional configuration parameters:
--+
-
base_std: standard deviation of noise
std_slope: Increase in std with time (e.g., 0.1 = increase of 0.1 in std per second)
t0: Starting time for calculation of std
std of applied noise is defined as base_std + std_slope (t-t0). By default no noise is added
Create a new Session in prog_server
model (str) – The model to use for this session (e.g., batt)
host (str, optional) – Host address for PaaS Service. Defaults to ‘127.0.0.1’
port (int, optional) – Port for PaaS Service. Defaults to 5000.
model_cfg (dict, optional) – Configuration for ProgModel.
x0 (dict, optional) – Initial state for ProgModel.
load_est (str, optional) – Load estimator to use.
load_est_cfg (dict, optional) – Configuration for load estimator.
state_est (str, optional) – State Estimator to use (e.g., ParticleFilter). Class name for state estimator in progpy.state_estimators
state_est_cfg (dict, optional) – Configuration for state estimator.
pred (str, optional) – Prediction algorithm to use (e.g., MonteCarlo). Class name for prediction algorithm in progpy.predictors
pred_cfg (dict, optional) – Configuration for prediction algorithm.
model (str) – The model to use for this session (e.g., batt)
host (str, optional) – Host address for PaaS Service. Defaults to ‘127.0.0.1’
port (int, optional) – Port for PaaS Service. Defaults to 5000.
model_cfg (dict, optional) – Configuration for ProgModel.
x0 (dict, optional) – Initial state for ProgModel.
load_est (str, optional) – Load estimator to use.
load_est_cfg (dict, optional) – Configuration for load estimator.
state_est (str, optional) – State Estimator to use (e.g., ParticleFilter). Class name for state estimator in progpy.state_estimators
state_est_cfg (dict, optional) – Configuration for state estimator.
pred (str, optional) – Prediction algorithm to use (e.g., MonteCarlo). Class name for prediction algorithm in progpy.predictors
pred_cfg (dict, optional) – Configuration for prediction algorithm.
Get the model output
+Get the predicted output
+See also: get_prediction_status
@@ -504,7 +546,7 @@Status of prediction
If the session has been initialized
Set the future loading profile profile.
host (str, optional) – Server host. Defaults to ‘127.0.0.1’.
port (int, optional) – Server port. Defaults to 5000.
debug (bool, optional) – If the server is started in debug mode
host (str, optional) – Server host. Defaults to ‘127.0.0.1’.
port (int, optional) – Server port. Defaults to 8555.
debug (bool, optional) – If the server is started in debug mode
Start the server (not blocking).
Stop the server.
+timeout (float, optional) – Timeout in seconds for starting the service
+Bases: progpy.prognostics_model.PrognosticsModel
New in version 1.5.0.
@@ -337,24 +337,43 @@models (list[PrognosticsModel] or list[tuple[str, PrognosticsModel]]) –
A list of PrognosticsModels to be combined into a single model. +
models (list[PrognosticsModel or function] or list[tuple[str, PrognosticsModel or function]]) –
A list of PrognosticsModels to be combined into a single model. Provided in one of two forms:
A list of PrognosticsModels. The name of each model will be the class name. A number will be added for duplicates
A list of tuples where the first element is the model name and the second element is the model
A list of PrognosticsModels or functions. The name of each model will be the class name for models or ‘function’ for functions. A number will be added for duplicates
A list of tuples where the first element is the model/function name and the second element is the model/function
Note: Order provided will be the order that models are executed
connections (list[tuple[str, str]], optional) – A list of tuples where the first element is the name of the output, state, or performance metrics of one model and the second element is the name of the input of another model. +
connections (list[tuple[str, str]], optional) – A list of tuples where the first element is the name of the output, state, or performance metrics of one model or function return and the second element is the name of the input of another model or argument of a function. The first element of the tuple must be of the form “model_name.output_name”, “model_name.state_name”, or “model_name.performance_metric_key”. The second element of the tuple must be of the form “model_name.input_name”. For example, if you have two models, “Batt1” and “Batt2”, and you want to connect the output of “Batt1” to the input of “Batt2”, you would use the following connection: (“Batt1.output”, “Batt2.input”)
outputs (list[str]) – Model outputs in format “model_name.output_name”. Must be subset of all outputs from models. If not provided, all outputs will be included.
+outputs (list[str]) – Model outputs in format “model_name.output_name”. Must be subset of all outputs from models. If not provided, all outputs will be included.
Example
+>>> m = SomeModel()
+>>> m2 = SomeOtherModel()
+>>> def kelvin_to_celcius(temp_in_kelvin):
+>>> return temp_in_kelvin - 273.15
+>>> connections = [
+>>> ('m1.temp', 'kelvin_to_celcius.temp_in_kelvin')
+>>> ('kelvin_to_celcius.return', 'm2.temp')
+>>> ]
+>>> m_composite = CompositeModel(
+>>> (('m1', m), ('kelvin_to_celcius', kelvin_to_celcius), ('m2', m2)), # models
+>>> connections=connections
+>>> )
+Note
+Model parameters can be set and accessed using the ‘[model].[param]’ format. For example, for composite model m, m[‘foo.bar’] would set the parameter ‘bar’ for the model ‘foo’.
+dt (float) – Time step
dt (float) – Time step
x0 (StateContainer) – Initial state of the system
times (list[list]) – list of input data for use in data. Each element is the times for a single run of size (n_times)
inputs (list[np.array]) – list of input data for use in data. Each element is the inputs for a single run of size (n_times, n_inputs)
outputs (list[np.array]) – list of output data for use in data. Each element is the outputs for a single run of size (n_times, n_outputs)
states (list[np.array], optional) – list of state data for use in data. Each element is the states for a single run of size (n_times, n_states)
event_states (list[np.array], optional) – list of event state data for use in data. Each element is the event states for a single run of size (n_times, n_event_states)
times (list[list]) – list of input data for use in data. Each element is the times for a single run of size (n_times)
inputs (list[np.array]) – list of input data for use in data. Each element is the inputs for a single run of size (n_times, n_inputs)
outputs (list[np.array]) – list of output data for use in data. Each element is the outputs for a single run of size (n_times, n_outputs)
states (list[np.array], optional) – list of state data for use in data. Each element is the states for a single run of size (n_times, n_states)
event_states (list[np.array], optional) – list of event state data for use in data. Each element is the event states for a single run of size (n_times, n_event_states)
trim_data_to (float, optional) –
Fraction (0-1) of data resulting from progpy.PrognosticsModel.simulate_to_threshold() used to train DMD surrogate model
+
trim_data_to (float, optional) –
Fraction (0-1) of data resulting from progpy.PrognosticsModel.simulate_to_threshold() used to train DMD surrogate model
e.g. if trim_data_to = 0.7 and the simulated data spans from t=0 to 100, the surrogate model is trained on the data from t=0 to 70
Note: To trim data to a set time, use the ‘horizon’ parameter
stability_tol (float, optional) – Value that determines the tolerance for DMD matrix stability
training_noise (float, optional) – Noise added to the training data sampled from a standard normal distribution with standard deviation of training_noise. Adding noise to the training data results in a slight perturbation that removes any linear dependencies among the data
stability_tol (float, optional) – Value that determines the tolerance for DMD matrix stability
training_noise (float, optional) – Noise added to the training data sampled from a standard normal distribution with standard deviation of training_noise. Adding noise to the training data results in a slight perturbation that removes any linear dependencies among the data
m (PrognosticsModel) – Model to generate data from
load_functions (list[function]) – Each index is a callable loading function of (t, x = None) -> z used to predict future load at a given time (t) and state (x)
load_functions (list[function]) – Each index is a callable loading function of (t, x = None) -> z used to predict future load at a given time (t) and state (x)
add_dt (bool) – If the timestep should be added as an input
+add_dt (bool) – If the timestep should be added as an input
Addditional configuration parameters from progpy.PrognosticsModel.simulate_to_threshold(). These can be an array (of same length as load_functions) of config for each individual sim, or one value to apply to all
@@ -547,6 +547,17 @@
Most users will use the LSTMStateTransitionModel.from_data() method to create a model, but the model can be created by passing in a model directly into the constructor. The LSTM model in this method maps from [u_t-n+1, z_t-n, …, u_t, z_t-1] to z_t. Past input are stored in the model internal state. Actual calculation of output is performed when LSTMStateTransitionModel.output() is called. When using in simulation that may not be until the simulation results are accessed.
Note
+ProgPy must be installed with [datadriven] option to use LSTM model. either
+pip3 install progpy[datadriven]
+or (if using local version)
+pip3 install ‘.[datadriven]’
+Note
+Tensorflow’s inteface has proved to be caprecious
+inputs (list[np.array]) – list of input data for use in data. Each element is the inputs for a single run of size (n_times, n_inputs)
outputs (list[np.array]) – list of output data for use in data. Each element is the outputs for a single run of size (n_times, n_outputs)
event_states (list[np.array], optional) – list of event state data for use in data. Each element is the event state for a single run of size (n_times, n_events)
t_met (list[np.array], optional) – list of threshold met data for use in data. Each element is if the threshold has been met for a single run of size (n_times, n_events)
inputs (list[np.array]) – list of input data for use in data. Each element is the inputs for a single run of size (n_times, n_inputs)
outputs (list[np.array]) – list of output data for use in data. Each element is the outputs for a single run of size (n_times, n_outputs)
event_states (list[np.array], optional) – list of event state data for use in data. Each element is the event state for a single run of size (n_times, n_events)
t_met (list[np.array], optional) – list of threshold met data for use in data. Each element is if the threshold has been met for a single run of size (n_times, n_events)
window (int) – Number of historical points used in the model. I.e, if window is 3, the model will map from [t-3, t-2, t-1] to t
input_keys (list[str]) – List of keys to use to identify input. If not supplied u[#] will be used to idenfiy inputs
output_keys (list[str]) – List of keys to use to identify output. If not supplied z[#] will be used to idenfiy outputs
event_keys (list[str]) – List of keys to use to identify events for event state and threshold met. If not supplied event[#] will be used to identify events
validation_percentage (float) – Percentage of data to use for validation, between 0-1
epochs (int) – Number of epochs (i.e., iterations) to train the model. More epochs means better results (to a point), but more time to train. Note: large numbers of epochs may result in overfitting.
layers (int) – Number of LSTM layers to use. More layers can represent more complex systems, but are less efficient. Note: 2 layers is typically enough for most complex systems. Default: 1
units (int or list[int]) – number of units (i.e., dimensionality of output state) used in each lstm layer. Using a scalar value will use the same number of units for each layer.
activation (str or list[str]) – Activation function to use for each layer
dropout (float) – Dropout rate to be applied. Dropout helps avoid overfitting
normalize (bool) – If the data should be normalized. This is recommended for most cases.
early_stopping (bool) – If early stopping is desired. Default is True
early_stop.cfg (dict) – Configuration to pass into early stopping callback (if enabled). See keras documentation (https://keras.io/api/callbacks/early_stopping) for options. E.g., {‘patience’: 5}
workers (int) – Number of workers to use when training. One worker indicates no multiprocessing
window (int) – Number of historical points used in the model. I.e, if window is 3, the model will map from [t-3, t-2, t-1] to t
input_keys (list[str]) – List of keys to use to identify input. If not supplied u[#] will be used to idenfiy inputs
output_keys (list[str]) – List of keys to use to identify output. If not supplied z[#] will be used to idenfiy outputs
event_keys (list[str]) – List of keys to use to identify events for event state and threshold met. If not supplied event[#] will be used to identify events
validation_percentage (float) – Percentage of data to use for validation, between 0-1
epochs (int) – Number of epochs (i.e., iterations) to train the model. More epochs means better results (to a point), but more time to train. Note: large numbers of epochs may result in overfitting.
layers (int) – Number of LSTM layers to use. More layers can represent more complex systems, but are less efficient. Note: 2 layers is typically enough for most complex systems. Default: 1
units (int or list[int]) – number of units (i.e., dimensionality of output state) used in each lstm layer. Using a scalar value will use the same number of units for each layer.
activation (str or list[str]) – Activation function to use for each layer
dropout (float) – Dropout rate to be applied. Dropout helps avoid overfitting
normalize (bool) – If the data should be normalized. This is recommended for most cases.
early_stopping (bool) – If early stopping is desired. Default is True
early_stop.cfg (dict) – Configuration to pass into early stopping callback (if enabled). See keras documentation (https://keras.io/api/callbacks/early_stopping) for options. E.g., {‘patience’: 5}
Create a Data Model from an existing PrognosticsModel (i.e., a surrogate model). Generates data through simulation with supplied load functions. Then calls from_data() to generate the model.
m (PrognosticsModel) – Model to generate data from
load_functions (list[function]) – Each index is a callable loading function of (t, x = None) -> z used to predict future load at a given time (t) and state (x)
load_functions (list[function]) – Each index is a callable loading function of (t, x = None) -> z used to predict future load at a given time (t) and state (x)
add_dt (bool) – If the timestep should be added as an input
+add_dt (bool) – If the timestep should be added as an input
Addditional configuration parameters from progpy.PrognosticsModel.simulate_to_threshold(). These can be an array (of same length as load_functions) of config for each individual sim, or one value to apply to all
@@ -669,12 +679,12 @@
event_keys (list[str], optional) – List of event keys for the events. If not provided, will be generated as e0, e1, e2, etc.
+event_keys (list[str], optional) – List of event keys for the events. If not provided, will be generated as e0, e1, e2, etc.
times (list[float]) – list of times data for use in data. Each element is the time such that inputs[i] is the inputs at time[i]
times (list[float]) – list of times data for use in data. Each element is the time such that inputs[i] is the inputs at time[i]
inputs (np.array) – list of input data for use in data. Each eelement is the inputs for a single run of size (n_samples, n_inputs*n_times)
time_of_event (np.array) – Array of time of event data for use in data. Each element is the time of event for a single run of size (n_samples, n_events)
J (chaospy.Distribution, optional) – Joint distribution to sample from. Must include distribution for each timepoint for each input [u0_t0, u0_t1, …, u1_t0, …]. If not included, input_dists must be provided
input_dists (list[chaospy.Distribution], optional) – List of chaospy distributions for each input for each timepoint
order (int, optional) – Order of the polynomial chaos expansion
input_dists (list[chaospy.Distribution], optional) – List of chaospy distributions for each input for each timepoint
order (int, optional) – Order of the polynomial chaos expansion
m (Model) – Model to create PolynomialChaosExpansion from
x (StateContainer) – Initial state to use for simulation
input_dists (dict[key, chaospy.Distribution]) –
” +
input_dists (dict[key, chaospy.Distribution]) –
” List of chaospy distributions for each input
times (list[float]) – List of coordinates along the time axis used to estimate the expansion coefficients (collocation points).
times (list[float]) – List of coordinates along the time axis used to estimate the expansion coefficients (collocation points).
N (int, optional) – Number of samples to use for training
dt (float, optional) – Time step to use for simulation
order (int, optional) – Order of the polynomial chaos expansion
N (int, optional) – Number of samples to use for training
dt (float, optional) – Time step to use for simulation
order (int, optional) – Order of the polynomial chaos expansion
Bases: progpy.prognostics_model.PrognosticsModel, abc.ABC
Bases: progpy.prognostics_model.PrognosticsModel, abc.ABC
New in version 1.4.0.
Calculate Error between simulated and observed data using selected Error Calculation Method