Methods and systems for workpiece quality control

A system for providing a trained function and for performing a workpiece quality control, said system comprising:

• a first training interface, implemented by one or more processors, configured to receive a plurality of training machining datasets, wherein different training machining datasets are representative of different workpieces having an acceptable quality based on prior tests;
• a training computation apparatus, implemented by one or more processors, configured to
• transform the plurality of the training machining datasets into a time-frequency domain to generate a plurality of training time-frequency domain datasets,
• train, based on the plurality of training time-frequency domain datasets, a function based on an autoencoder, which comprises an input layer, an output layer and a hidden layer,
• provide the training time-frequency domain datasets for the input layer and for the output layer;
• a second training interface, implemented by one or more processors, configured to provide the trained function as a trained autoencoder function;
• and
• performing the workpiece quality control based on the trained autoencoder function, comprising:
• a first interface, implemented by one or more processors, receiving a machining dataset based on time-series CNC machining data, wherein the machining dataset is representative for a quality of a workpiece,
• a computation apparatus, implemented by one or more processors, configured to
• transform the machining dataset into a time-frequency domain to generate a time-frequency domain dataset,
• apply the trained autoencoder function to the time-frequency domain dataset and generate data in the hidden layer,
• analyze the quality of the workpiece based on the data generated in the hidden layer of the trained autoencoder function, and
• a second interface, implemented by one or more processors, providing results of the analysis of the quality of the workpiece, wherein the autoencoder is a variational autoencoder with a specified statistical distribution for the hidden layer, and wherein the analyzing the quality of the workpiece comprises comparing the data generated in the hidden layer of the variational autoencoder with the specified statistical distribution.