Detección de anomalías

R2025b

Detecte anomalías en señales utilizando modelos de IA, incluidas redes de deep learning

Extraiga características de tiempo-frecuencia dispersas para detectar anomalías en datos electromagnéticos, acústicos y de vibraciones.

Funciones

deepSignalAnomalyDetector Create signal anomaly detector (Desde R2023a)

`audioDatastore`	Datastore for collection of audio files
`arrayDatastore`	Datastore for in-memory data
`signalDatastore`	Datastore for collection of signals
`imageDatastore`	Datastore for image data
`waveletScattering`	Wavelet time scattering
`signalTimeFeatureExtractor`	Streamline signal time feature extraction
`signalFrequencyFeatureExtractor`	Streamline signal frequency feature extraction
`signalTimeFrequencyFeatureExtractor`	Streamline signal time-frequency feature extraction (Desde R2024a)
`stftLayer`	Short-time Fourier transform layer
`istftLayer`	Inverse short-time Fourier transform layer (Desde R2024a)
`cwtLayer`	Continuous wavelet transform layer (Desde R2022b)
`icwtLayer`	Inverse continuous wavelet transform layer (Desde R2024b)
`modwtLayer`	Maximal overlap discrete wavelet transform layer (Desde R2022b)

Detect anomalies in acoustic data using wavelet scattering and the deepSignalAnomalyDetector object.

Use autoencoders to detect abnormal points or segments in time series data.

Use wavelet and deep learning techniques to detect and localize transverse pavement cracks.

(Deep Learning Toolbox)

Learn how to develop an alert system for predictive maintenance using wavelet scattering and deep learning.

(Deep Learning Toolbox)

Classify faults in acoustic recordings of air compressors using a wavelet scattering network paired with a recurrent neural network.

(Deep Learning Toolbox)