Manufacturing automation using acoustic separation neural network

A method for controlling an operation of a machine including a plurality of actuators assisting one or multiple tools to perform one or multiple tasks, wherein the method uses a processor coupled with stored instructions implementing the method, wherein the instructions, when executed by the processor carry out steps of the method, comprising:

• receiving an acoustic mixture of signals generated by a tool performing a task and by the plurality of actuators actuating the tool;
• submitting the acoustic mixture of signals into a neural network trained to separate from the acoustic mixture a signal generated by the tool performing the task from signals generated by the actuators actuating the tool to extract the signal generated by the tool performing the task from the acoustic mixture of signals;
• analyzing the extracted signal to produce a state of performance of the task;
• and
• executing a control action selected according to the state of performance of the task wherein, during the operation of the machine, multiple tools perform multiple tasks including a first tool performing a first task and a second tool performing a second task, wherein the neural network is trained to separate from the acoustic mixture a first signal generated by the first tool performing the first task and a second signal generated by the second tool performing the second task, wherein, during the operation of the system, the processor is configured to extract the first signal and the second signal from the acoustic mixture using the neural network, analyze the first signal independently from the second signal to estimate a first state of performance of the first task and a second state of performance of the second task, and execute a first control action selected according to the first state and execute a second control action selected according to the second state.

A non-transitory computer readable storage medium embodied thereon a program executable by a processor for performing a method, the method comprising:

• receiving an acoustic mixture of signals generated by a tool performing a task and by the plurality of actuators actuating the tool;
• submitting the acoustic mixture of signals into a neural network trained to separate from the acoustic mixture a signal generated by the tool performing the task from signals generated by the actuators actuating the tool to extract the signal generated by the tool performing the task from the acoustic mixture of signals;
• analyzing the extracted signal to produce a state of performance of the task;
• and
• executing a control action selected according to the state of performance of the task, wherein the neural network is trained to separate different signals from the acoustic mixture such that each separated signal belongs to only one class of signals present in the operation of the system, while the separated signals sum up to the acoustic mixture, wherein the classes of signals present in the operation of the system are identified by weak labels, each weak label specifies a class of a signal present at some point during the operation, wherein the neural network is jointly trained with a classifier configured to classify the classes of the signals identified by the weak labels, and wherein the neural network is a jointly trained with the classifier to minimize a loss function including a cross-entropy term between the weak labels and the of the separation neural network run through the classifier.