Methods, systems, and non-transitory computer readable medium are described for sensor metrology data integration. A method includes receiving sets of sensor data and sets of metrology data. Each set of sensor data includes corresponding sensor values associated with producing corresponding product by manufacturing equipment and a corresponding sensor data identifier. Each set of metrology data includes corresponding metrology values associated with the corresponding product manufactured by the manufacturing equipment and a corresponding metrology data identifier. The method further includes determining common portions between each corresponding sensor data identifier and each corresponding metrology data identifier. The method further includes, for each of the sensor-metrology matches, generating a corresponding set of aggregated sensor-metrology data and storing the sets of aggregated sensor-metrology data to train a machine learning model. The trained machine learning model is capable of generating one or more outputs for performing a corrective action associated with the manufacturing equipment.

The present invention provides methods and systems for manufacturing process control of photovoltaic products. Some embodiments relate to a method for tracking wafers for photovoltaic products with respect to which production tool processed them and their position within that production tool. Some embodiments relate to measuring and characterizing the critical-to-quality parameters of the partially-finished photovoltaic products emerging from the production tool in question. Some embodiments relate to display and visualization of the measured parameters on a computer screen, such that the parameters of each production unit can be directly observed in the context of which production tools processed them, which location within a specific production tool they were located in during processing, and which batch, or in the case of continuous processing, what time, the unit(s) was/where processed.

Aspects of the disclosed technology encompass the use of a deep-learning controller for monitoring and improving a manufacturing process. In some aspects, a method of the disclosed technology includes steps for: receiving control values associated with a process station in a manufacturing process, predicting an expected value for an article of manufacture output from the process station, and determining if the deep-learning controller can control the manufacturing process based on the expected value. Systems and computer-readable media are also provided.

A computer-implemented method to control technical equipment that performs a production batch-run of a production process, the technical equipment providing data in a form of time-series from a set of data sources, the data sources being related to the technical equipment, includes: accessing a reference time-series with data from a previously performed batch-run of the production process, the reference time-series being related to a parameter for the technical equipment; and while the technical equipment performs the production batch-run: receiving a production time-series with data, identifying a sub-series of the reference time-series, and comparing the received time-series and the sub-series of the reference time-series, to provide an indication of similarity or non-similarity, in case of similarity, controlling the technical equipment during a continuation of the production batch-run, by using the parameter as control parameter.

A method includes receiving trace sensor data associated with a first manufacturing process of a processing chamber. The method further includes processing the trace sensor data using one or more trained machine learning models that generate a representation of the trace sensor data, and then generate reconstructed sensor data based on the representation of the trace sensor data. The method further includes comparing the trace sensor data to the reconstructed sensor data. The method further includes determining one or more differences between the reconstructed sensor data and the trace sensor data. The method further includes determining whether to recommend a corrective action associated with the processing chamber based on the one or more differences between the trace sensor data and the reconstructed sensor data.

A robotic electric arc welding system includes a welding torch, a welding robot configured to manipulate the welding torch during a welding operation, a robot controller operatively connected to the welding robot to control weaving movements of the welding torch along a weld seam and at a weave frequency and weave period, and a welding power supply operatively connected to the welding torch to control a welding waveform, and operatively connected to the robot controller for communication therewith. The welding power supply is configured to sample a plurality of weld parameters during a sampling period of the welding operation and form an analysis packet, and process the analysis packet to generate a weld quality score, wherein the welding power supply obtains the weave frequency or the weave period and automatically adjusts the sampling period for forming the analysis packet based on the weave frequency or the weave period.

A set of multi-mode elastic wave generating and detecting devices and field sensors are utilized in a real-time in-situ monitoring system based on the quality assessment of a specially designed article made by an additive manufacturing machine. The original invention disclosed in U.S. patent application Ser. No. 15/731,366 involves the transmission and reception of waves into a periodic test artifact while it is being built. The current invention involves the transmission and reception of multi-mode waves into a test artifact, the processing of data from narrow and wide field-of-view sensors, and correlating and relating the waveforms and sensor data while it is being built using physics-based and machine learning models. The disclosed system may initiate control and real-time corrective actions based on the properties and characteristics of the obtained waveforms and sensor data and their correlations and functional relationships.

A prediction model generator of a prediction system determines as an explanatory variable, one or more status values among status values associated with a training sample to be used for generation of a prediction model, based on an importance with respect to the training sample, determines an interval to be used for prediction by evaluating accuracy of prediction with the determined explanatory variable with an interval included in a search interval being successively varied, and determines a model parameter for defining the prediction model by evaluating plural indicators for the prediction model defined by each model parameter, with the model parameter defining the prediction model being successively varied, under a condition of the determined explanatory variable and the determined interval.

Methods and systems for reducing substrate particle scratching using machine learning are provided. A machine learning model is trained to predict process recipe settings for a substrate temperature control process to be performed for a current substrate at a manufacturing system. First training data and second training data are generated for the machine learning model. The first training data includes historical data associated with prior process recipe settings for a prior substrate temperature control process performed for a prior substrate at a prior process chamber. The second training data is associated with a historical scratch profile of one or more surfaces of the prior substrate after performance of the prior substrate temperature control process according to the prior process recipe settings. The first training data and the second training data are provided to train the machine learning model to predict which process recipe settings for the substrate temperature control process to be performed for the current substrate correspond to a target scratch profile for one or more surfaces of the current substrate.

A method for monitoring a molding process carried out in cycles includes determining at least two nearest neighbors in the form of cycle data from at least two past cycles, such that the cycle data of the at least two nearest neighbors lie nearer to the current cycle data than the cycle data which do not pertain to the at least two nearest neighbors. Only those past cycles for which quality data are contained in the data collection are used for the determination of the at least two nearest neighbors. A predictability criterion is checked to determine whether a quality variation of the quality data of the cycles of the at least two nearest neighbors is smaller than a maximum variation and/or larger than a minimum variation. If the predictability criterion is not met, a first notification that a quality and/or a quality datum of the molded part is not reliably predictable is issued.