A method for checking the quality of a workpiece, a surface section of the workpiece is finished with a manufacturing device. A reference signal representing a time dependent difference between an ideal tool position and a real tool position of a tool of the manufacturing device in a reference phase is determined when finishing the workpiece. A test signal representing a time dependent difference between an ideal tool position and a real tool position of a tool of the manufacturing device in an operation phase is determined when finishing the workpiece. A mean value and a standard deviation value from the reference signal is determined. Data points of the test signal are determined, where the test signal deviates from the mean value more than a defined multiple of the standard deviation value. The surface quality of the workpiece is estimated by using the determined data points.

A quality prediction model generation method for a metal material manufactured through one or more processes includes: a first collection step of collecting a manufacturing condition of each of the processes for each of predetermined areas of the metal material; a second collection step of evaluating and collecting quality of the metal material manufactured through each process for each of the predetermined areas; a storage step of storing the manufacturing condition of each process and the quality of the metal material manufactured under the manufacturing condition in association with each other for each of the predetermined areas; and a model generation step of generating a quality prediction model that predicts quality of the metal material for each of the predetermined areas based on the stored manufacturing condition for each of the predetermined areas in each process.

Anomaly detection and remedial recommendation techniques for improving the quality and yield of microelectronic products are provided. In one aspect, a method for quality and yield improvement via anomaly detection includes: collecting time series sensor data during individual steps of a semiconductor manufacturing process; calculating anomaly scores for each of the individual steps using a predictive model; and implementing changes to the semiconductor manufacturing process based on the anomaly scores. A system for quality and yield improvement via anomaly detection is also provided.

Machine learning and computer vision based systems and methods for three-dimensional (3D) printer monitoring are described herein. An example method includes receiving an image of an object during a 3D printing process; determining a printing property associated with the object based upon the image of the object; inputting the printing property associated with the object into a machine learning module; and predicting, using the machine learning module, a 3D printing error.

A robot control device that controls a robot including a driving section configured to drive an arm based on an operation command value and a first encoder section configured to output a first encoder value, the robot control device including a first command-value comparing section, a first mutual monitoring section, a second command-value comparing section, a second mutual monitoring section, and a power interrupting section. The first-command value comparing section performs comparison processing for a command value and a first encoder value and outputs a first command value comparison result. The second command-value comparing section performs comparison processing for the command value and the first encoder value and outputs a second command value comparison result. The first mutual monitoring section and the second mutual monitoring section output an interruption signal based on the first command value comparison result and the second command value comparison result.

Various systems and methods for modeling a manufacturing assembly line are disclosed herein. Some embodiments relate to operating a processor to receive cell data and line production data, determine one or more production associations between the cell data and the line production data; evaluate the one or more production associations to identify one or more critical production associations; retrieve the cell data and the line production data associated with the one or more critical production associations; and train a predictive model with the retrieved cell data and the retrieved line production data to predict the production level of the manufacturing assembly line.

A yield-rate assessment apparatus for a manufacture system including a plurality of machines, each machine participating in one or more manufacture steps of a batch of products in the manufacture system, performs for each machine: calculating a bad-piece expectation value and a quantity of potential bad pieces at each corresponding manufacture step based on a quantity of bad pieces detected after the last one of the manufacture steps is finished and an initial yield rate of the current machine; calculating a good-piece expectation value based on a quantity of good pieces detected after the last one of the manufacture steps is finished and a summation of all quantities of potential bad pieces calculated for the current machine; and assessing a yield rate according to the good-piece expectation value calculated for the current machine and a summation of the bad-piece expectation value calculated for the current machine at each corresponding step.

An abnormality monitoring method includes obtaining multiple target machine process parameters that affect a measurement value of a preset product at a first measurement point of the preset product, constructing a measurement value prediction model corresponding to the first measurement point, calculating a degree of fit of the measurement value prediction model, aggregating the degree of fit of the measurement value prediction model, the estimated value of the first measurement point, the target machine process parameters corresponding to the first measurement point, and the parameter coefficients of the target machine process parameters, repeating the above steps for each of multiple measurement points, calculating an influence degree index value of each machine, process parameter, and outputting warning information of machine process parameters that exceed a first preset influence degree index value.

The optimization support device includes a first conversion unit that converts an operating condition parameter indicating an operating condition of a process for producing a product into a state parameter indicating a state of the process, and a second conversion unit that converts the state parameter into a quality parameter indicating a quality of the product.

Methods and systems for detecting and correcting substrate process drift using machine learning are provided. Data associated with processing each of a first set of substrates at a manufacturing system according to a process recipe is provided as input to a trained machine learning model. One or more outputs are obtained from the trained machine learning model. An amount of drift of a first set of metrology measurement values for the first set of substrates from a target metrology measurement value is determined from the one or more outputs. Process recipe modification identifying one or more modifications to the process recipe is also determined. For each modification, an indication of a level of confidence that a respective modification to the process recipe satisfies a drift criterion for a second set of substrates is determined. In response to an identification of the respective modification with a level of confidence that satisfies a level of confidence criterion, the process recipe is updated based on the respective modification.