The present invention reduces costs relating to generation of a model, and suppresses a decrease in the estimating accuracy of the generated model. A quality prediction system of one aspect of the present invention acquires first learning data collected in first manufacturing equipment, acquires second learning data collected in second manufacturing equipment, and in order to implement transfer learning, converts the acquired first learning data to match the second learning data, uses the converted first learning data and the second learning data to implement machine learning of a quality prediction model, uses a trained quality prediction model to specify an adjustment amount for each adjustment item of the second manufacturing equipment so that a quality index predicted for a second product satisfies a quality standard, and outputs the specified adjustment amount of each adjustment item of the second manufacturing equipment.

An online prediction method of tool-electrode consumption adapted for an electrical discharge machining (EDM) apparatus includes an experimental design; extracting electrode consumption variables from machining parameters of the electrical discharge machining (EDM) apparatus; and obtaining a correlation between the machining parameters and the electrode consumption variables through a correlation analysis to obtain a prediction model capable of predicting an effective contact area of a tool-electrode and a workpiece. In addition, a prediction method of machining accuracy is provided.

Methods, apparatus, systems, and articles of manufacture are disclosed. An example system to modify an industrial control system includes: at least one memory; programmable circuitry; and instructions to cause the programmable circuitry to: configure a device driver based on a first command, the first command to configure the device driver to initiate a device-specific communication protocol to collect input data from a publisher device coupled to the device driver; access a second command from a subscriber device, the second command to include a device identifier of the publisher device and to specify at least one of a communication mode, a device calibration configuration, or a fault detection configuration, the second command based on a product quality prediction, the product quality prediction generated using a spectral data model; and provide the second command to the device driver.

Example embodiments are disclosed of systems and methods for predicting failure probabilities of future product tests of a testing sequence based on outcomes of prior tests. Predictions are made by a machine-learning-based model (MLM) trained with a set of test-result sequence records (TRSRs) including test values and pass/fail indicators (PRIs) of completed tests. Within training epochs over the set, iterations are carried out over each TRSR. Each iteration involves sub-iterations carried out successively over test results of the TRSR. Each sub-iteration involves (i) inputting to the MLM values of a given test and those of tests earlier in the sequence while masking those later in the sequence, (ii) computing probabilities of test failures for the masked tests found later in the sequence than the given test, and (iii) applying the PFIs of test results later in the sequence than the given test as ground-truths to update parameters of the MLM.

A technique to generate predicted data for control or monitoring of a production process to improve a parameter of interest. Context data associated with operation of the production process is obtained. Metrology/testing is performed on the product of the production process, thereby obtaining performance data. A context-to-performance model is provided to generate predicted performance data based on labeling of the context data with performance data. This is an instance of semi-supervised learning. The context-to-performance model may include the learner that performs semi-supervised labeling. The context-to-performance model is modified using prediction information related to quality of the context data and/or performance data. Prediction information may include relevance information relating to relevance of the obtained context data and/or obtained performance data to the parameter of interest. The prediction information may include model uncertainty information relating to uncertainty of the predicted performance data.

A cutting machine for detecting a defect during a manufacturing process is disclosed. The cutting machine comprises a base structure having a planar surface defining a working area, a rack to support a material spool, a cutter assembly, and a material-inspection system. The rack may be positioned at an end of the base structure to facilitate unrolling of a composite material sheet from the material spool and onto the working area. The cutter assembly comprises a cutter tool to cut the composite material sheet on the working area. The cutter assembly may be configured to move relative to the working area via a two-axis gantry. The material-inspection system comprises a plurality of non-contact ultrasonic sensors to measure one or more material properties of the composite material sheet. The measured one or more material properties can be used to detect and predict defects in the composite material sheet.

A method for predicting based on the state of an industrial process at a first point in time that is described by a process snapshot record with values of a first set of variables a value of at least one process variable of the industrial process at a second, later point in time, includes mapping using a machine learning model the process snapshot record to at least one initial state record; providing the initial state record to a simulation model; simulating using the simulation model the further development of the process; obtaining from the simulation model a final state record; and determining based on the final state record the sought value of the process variable at the second point in time.

In order to realize stable quality control, provided is a quality control device (1) having an input device which receives data such as an operation condition of each device (21) to (26) in a production system (20) for producing a product; a calculation unit which assigns a value of the operation condition to a correlation formula calculated in advance and calculates a value derived from the correlation formula; and a determination unit which performs good or bad determination on a quality of a workpiece in each process, on the basis of a result calculated by the calculation unit. Further, when bad is determined as a result of the good or bad determination, the quality control device (1) calculates an appropriate value of the operation condition and sets the value to each device (21) to (26).

Statistically significant event patterns predict the timing for performing entity maintenance. Event patterns are determined based on a target variable having an undesired value for a given entity when the event pattern occurs. Event patterns are filtered based on distributions of the event patterns across multiple entities and distributions of event patterns during desired operation of the entities and undesired operation of the entities. A predictive maintenance process is established having significant event patterns as the basis for maintenance tasks.

A system, method, and computer-readable medium are disclosed for identifying sources of variation in complex manufacturing processes via a variation identification operation. In certain embodiments, the variation identification operation is performed via a variation identification system. The variation identification operation addresses special class of analytic problems, namely the estimation of variance components and related statistics from very large (big data) hierarchically nested designs of random factors. These types of data structures occur frequently across various industries, and in particular in automated and batch manufacturing where the variability in product quality as measured in final product testing should be related to batches, lots, wafers, suppliers, etc. upstream of the process.