BibMon: Process Monitoring Library

BibMon (from the Portuguese Biblioteca de Monitoramento de Processos, or Process Monitoring Library) is a Python package that provides deviation-based predictive models for fault detection, soft sensing, and process condition monitoring.

Features

The resources offered by BibMon are:

• Application in online systems: a trained BibMon model can be used for online analysis with both individual samples and data windows. For each sample or window, a prediction is made, the model state is updated, and alarms are calculated.

• Compatibility, within the same architecture, of regression models (i.e., virtual sensors, containing separate X and Y data, such as RandomForest) and reconstruction models (containing only X data, such as PCA).

• Preprocessing pipelines that take into account the differences between X and Y data and between training and testing stages.

• Possibility of programming different alarm logics.

• Easy extensibility through inheritance (there is a class called GenericModel that implements all the common functionality for various models and can be used as a base for implementing new models). For details, consult the CONTRIBUTING.md file.

• Convenience functions for performing automatic offline analysis and plotting control charts.

• Real and simulated process datasets available for importing.

• Comparative tables to automate the performance analysis of different models.

• Automatic hyperparameter tuning using Optuna.

Getting started

• Installation
  • Installing from PyPI
  • Installing from conda-forge
  • Get the Source Code
• Usage
• Tutorials
  • PCA for fault detection in Tennessee Eastman Process
    • Process description
    • Importing data
    • Modeling and process monitoring
    • Analyzing the effect of preprocessing techniques
    • Final considerations
  • Regression models for soft sensing of a real process
    • Importing data
    • Modeling and process monitoring
    • Comparing models
    • Final considerations
• Scientific article

Contributing

BibMon is an open-source project driven by the community. If you would like to contribute to the project, please refer to the following contributing page.

• Contributing
  • Getting started
  • Asking questions
  • Before contributing
  • BibMon architecture
  • Implementing New Functionalities

The API Documentation

In this section you will find information about specific functions, classes, or methods.

• API Reference
  • Autoencoder
    • Autoencoder.compute_SPE_contributions()
    • Autoencoder.fit()
    • Autoencoder.hyperparameter_tuning()
    • Autoencoder.load_model()
    • Autoencoder.map_from_X()
    • Autoencoder.plot_SPE()
    • Autoencoder.plot_SPE_contributions()
    • Autoencoder.plot_predictions()
    • Autoencoder.pre_test()
    • Autoencoder.pre_train()
    • Autoencoder.predict()
    • Autoencoder.set_hyperparameters()
    • Autoencoder.test()
    • Autoencoder.train()
    • Autoencoder.train_core()
  • ESN
    • ESN.compute_SPE_contributions()
    • ESN.fit()
    • ESN.hyperparameter_tuning()
    • ESN.initweights()
    • ESN.load_model()
    • ESN.map_from_X()
    • ESN.plot_SPE()
    • ESN.plot_SPE_contributions()
    • ESN.plot_predictions()
    • ESN.pre_test()
    • ESN.pre_train()
    • ESN.predict()
    • ESN.set_hyperparameters()
    • ESN.test()
    • ESN.train()
    • ESN.train_core()
  • PCA
    • PCA.compute_SPE_contributions()
    • PCA.fit()
    • PCA.hyperparameter_tuning()
    • PCA.load_model()
    • PCA.map_from_X()
    • PCA.plot_SPE()
    • PCA.plot_SPE_contributions()
    • PCA.plot_cumulative_variance()
    • PCA.plot_predictions()
    • PCA.pre_test()
    • PCA.pre_train()
    • PCA.predict()
    • PCA.set_hyperparameters()
    • PCA.test()
    • PCA.train()
    • PCA.train_core()
  • PreProcess
    • PreProcess.add_moving_average()
    • PreProcess.apply()
    • PreProcess.apply_lag()
    • PreProcess.back_to_units()
    • PreProcess.ffill_nan()
    • PreProcess.moving_average_filter()
    • PreProcess.normalize()
    • PreProcess.process_outliers_iqr()
    • PreProcess.remove_empty_variables()
    • PreProcess.remove_frozen_variables()
    • PreProcess.remove_observations_with_nan()
    • PreProcess.replace_nan_with_values()
  • SBM
    • SBM.compute_SPE_contributions()
    • SBM.fit()
    • SBM.hyperparameter_tuning()
    • SBM.load_model()
    • SBM.map_from_X()
    • SBM.plot_SPE()
    • SBM.plot_SPE_contributions()
    • SBM.plot_predictions()
    • SBM.pre_test()
    • SBM.pre_train()
    • SBM.predict()
    • SBM.set_hyperparameters()
    • SBM.test()
    • SBM.train()
    • SBM.train_core()
  • align_dfs_by_rows()
  • comparative_table()
  • complete_analysis()
  • create_df_with_dates()
  • create_df_with_noise()
  • load_real_data()
  • load_tennessee_eastman()
  • sklearnManifold
    • sklearnManifold.clusters_visualization()
    • sklearnManifold.compute_SPE_contributions()
    • sklearnManifold.fit()
    • sklearnManifold.fit_transform()
    • sklearnManifold.hyperparameter_tuning()
    • sklearnManifold.load_model()
    • sklearnManifold.map_from_X()
    • sklearnManifold.plot_SPE()
    • sklearnManifold.plot_SPE_contributions()
    • sklearnManifold.plot_embedding()
    • sklearnManifold.plot_predictions()
    • sklearnManifold.pre_test()
    • sklearnManifold.pre_train()
    • sklearnManifold.predict()
    • sklearnManifold.set_hyperparameters()
    • sklearnManifold.test()
    • sklearnManifold.train()
    • sklearnManifold.train_core()
    • sklearnManifold.transform()
  • sklearnRegressor
    • sklearnRegressor.compute_SPE_contributions()
    • sklearnRegressor.fit()
    • sklearnRegressor.hyperparameter_tuning()
    • sklearnRegressor.load_model()
    • sklearnRegressor.map_from_X()
    • sklearnRegressor.plot_SPE()
    • sklearnRegressor.plot_SPE_contributions()
    • sklearnRegressor.plot_importances()
    • sklearnRegressor.plot_predictions()
    • sklearnRegressor.pre_test()
    • sklearnRegressor.pre_train()
    • sklearnRegressor.predict()
    • sklearnRegressor.set_hyperparameters()
    • sklearnRegressor.test()
    • sklearnRegressor.train()
    • sklearnRegressor.train_core()
    • sklearnRegressor.update_importances()
  • spearmanr_dendrogram()
  • targets_comparative_table()
  • train_val_test_split()