Real time contaminants identification during composite material manufacturing via non-contact chemical sensing

A contaminant detection system comprising:

• a computer system;
• a machine learning model system trained to classify contaminants in unconsolidated composite materials using Fourier transform infrared scans of the unconsolidated composite materials;
• and
• an analyzer located in the computer system, wherein the analyzer is configured to:
• receive a Fourier transform infrared scan for a section of an unconsolidated composite material in real time as sensor data is received during manufacturing of the unconsolidated composite material by a composite material manufacturing system;
• determine whether a contaminant is present in the section of the unconsolidated composite material in real time as sensor data is received during manufacturing of the unconsolidated composite material in the composite material manufacturing system using the Fourier transform infrared scan and the machine learning model system;
• and
• perform a number of corrective actions, in response to determining that a contaminant is present in the section, including a least one of an adjustment action including adjusting parameters for out of tolerance portions of the unconsolidated composite materials and a change action,
• wherein the machine learning model system comprises one or more machine learning models including one or more of a decision tree, a support vector machine, a random forest machine learning model, a regression machine learning model, a classification machine learning model, and a Bayesian network.

A contaminant detection system comprising:

• a computer system;
• a machine learning model system trained to classify contaminants in unconsolidated composite materials using electromagnetic scans of the unconsolidated composite materials;
• and
• an analyzer located in the computer system, wherein the analyzer is configured to:
• receive an electromagnetic scan for a section of an unconsolidated composite material in real time as sensor data is received during manufacturing of the unconsolidated composite material by a composite material manufacturing system;
• determine whether a contaminant is present in the section of the unconsolidated composite material in real time as sensor data is received during manufacturing of the unconsolidated composite material by the composite material manufacturing system using the electromagnetic scan and the machine learning model system;
• and
• perform a number of corrective actions, in response to determining that a contaminant is present in the section, including a least one of an adjustment action including adjusting parameters for out of tolerance portions of the unconsolidated composite materials and a change action,
• wherein the machine learning model system comprises one or more machine learning models including one or more of a decision tree, a support vector machine, a random forest machine learning model, a regression machine learning model, a classification machine learning model, and a Bayesian network.

A method for detecting a contaminant, the method comprising:

• receiving a Fourier transform infrared scan for a section of an unconsolidated composite material in real time as sensor data is received during manufacturing of the unconsolidated composite material by a composite material manufacturing system;
• determining whether the contaminant is present in the section of the unconsolidated composite material in real time as sensor data is received during manufacturing of the unconsolidated composite material by the composite material manufacturing system using the Fourier transform infrared scan and a machine learning model system trained to classify contaminants in unconsolidated composite materials using the Fourier transform infrared scan of the unconsolidated composite materials;
• and
• performing a number of corrective actions, in response to determining that a contaminant is present in the section, including a least one of an adjustment action including adjusting parameters for out of tolerance portions of the unconsolidated composite materials and a change action,
• wherein the machine learning model system comprises one or more machine learning models including one or more of a decision tree, a support vector machine, a random forest machine learning model, a regression machine learning model, a classification machine learning model, and a Bayesian network.