To design an algorithm for detecting and diagnosing faults, you use condition indicators extracted from system data to train a decision model that can analyze test data to determine the current system state.
When designing your algorithm, you might test different fault detection and diagnosis models using different condition indicators. Thus, this step in the design process is likely iterative with the step of extracting condition indicators, as you try different indicators, different combinations of indicators, and different decision models.
For an overview of the types of models you can use, see Decision Models for Fault Detection and Diagnosis
|Train support vector machine (SVM) classifier for one-class and binary classification|
|Fit multiclass models for support vector machines or other classifiers|
|Fit k-nearest neighbor classifier|
|Fit binary linear classifier to high-dimensional data|
|Train multiclass naive Bayes model|
|Fit binary decision tree for multiclass classification|
|Fit binary Gaussian kernel classifier using random feature expansion|
|Maximum likelihood estimates|
|Create bag of decision trees|
|Estimate parameters of nonlinear ARX model|
|Estimate state-space model using time-domain or frequency-domain data|
|Estimate parameters of ARX, ARIX, AR, or ARI model|
|Estimate parameters of ARMAX, ARIMAX, ARMA, or ARIMA model using time-domain data|
|Estimate parameters of AR model or ARI model for scalar time series|
|Forecast identified model output|
|Translate parameter covariance across model transformation operations|
Use condition indicators extracted from healthy and faulty data to train classifiers or regression models for detecting and diagnosing faults.
Use a model-based approach for detection and diagnosis of different types of faults in a pumping system.
Use a model parity-equations-based approach for detection and diagnosis of faults in a pumping system.
Use a data-based modeling approach for fault detection.
Use an extended Kalman filter for online estimation of the friction of a simple DC motor. Significant changes in the estimated friction are detected and indicate a fault.
Detect abrupt changes in the behavior of a system using online estimation and automatic data segmentation techniques.
Use a Simulink model to generate faulty and healthy data, and use the data to develop a multi-class classifier to detect different combinations of faults.
Use the Diagnostic Feature Designer app to analyze and select features to diagnose faults in a triplex reciprocating pump.
Use simulation data to train a neural network than can detect faults in a chemical process.
This example shows how to perform fault diagnosis of a rolling element bearing using a deep learning approach.
Detect anomalies in industrial-machine vibration data using machine learning and deep learning.