Abstract: Embodiments of the present invention provide a predictive maintenance method for a component of a production tool, in which a time series prediction (TSP) algorithm and an information criterion algorithm are adapted to build a TSP model, thereby forecasting the complicated future trend of accidental shutdown of the component of the production tool. In addition, an alarm scheme is provided for performing maintenance immediately when the component is very likely to enter a dead state, and a death related indicator (DCI) is provided for quantitatively showing the possibility of the component entering the dead state.

Abstract: An additive manufacturing (AM) system, an AM method, and an AM feature extraction method are provided. The AM system includes an AM tool, a product metrology system, an in-situ metrology system, a virtual metrology (VM) system, a compensator, a track planner, a controller, a simulator and an augmented reality (AR) device. The simulator is used to find feasible parameter ranges, while the AR device is used to support operations and maintenance of the AM tool. The product metrology system, the in-situ metrology system and the VM system are integrated to estimate the variation of material on a powder bed of the AM tool. The compensator is used for compensating the process variation by adjusting process parameters. The product metrology system is used to measure the quality of products. The in-situ metrology system is used to collect features of melt pools on the powder bed.

Abstract: A tool wear monitoring and predicting method is provided, and uses a hybrid dynamic neural network (HDNN) to build a tool wear prediction model. The tool wear prediction model adopts actual machining (cutting) conductions, sensing data detected at the current tool run of operation and the predicted tool wear value at the previous tool run of operation to predict a predicted tool wear value at the current tool run. A cyber physical agent (CPA) is adopted for simultaneously monitoring and predicting tool wear values of plural machines of the same machine type.

Abstract: An additive manufacturing (AM) system, an AM method, and an AM feature extraction method are provided. The AM system includes an AM tool, a product metrology system, an in-situ metrology system, a virtual metrology (VM) system, a compensator, a track planner, a controller, a simulator and an augmented reality (AR) device. The simulator is used to find feasible parameter ranges, while the AR device is used to support operations and maintenance of the AM tool. The product metrology system, the in-situ metrology system and the VM system are integrated to estimate the variation of material on a powder bed of the AM tool. The compensator is used for compensating the process variation by adjusting process parameters. The product metrology system is used to measure the quality of products. The in-situ metrology system is used to collect features of melt pools on the powder bed.

Abstract: An automated constructing method of cloud manufacturing service is provided for a distributed system including a virtual machine and a service manager. The method includes: obtaining a library package which is locally built, analyzing the library package to obtain key information, and generating a library information file; automatically generating a project source code file according to the library information file, and generating a web service package according to the project source code file; and deploying, by the service manager, the web service package on the virtual machine.

Abstract: Embodiments of the present disclosure provide a two-phase process for searching root causes of a yield loss in a production line. In a first phase, an interaction between two process tools, that between two parameters, or that between one process tool and one parameter that is likely to cause the yield loss is identified. In a second phase, a threshold of the parameter that is likely to cause the yield loss and is obtained from the first phase is identified. In each phase, two different algorithms can be used to generate a reliance index (RII) for gauging the reliance levels of their search results.

Abstract: A product quality prediction method for mass customization is provided. When a production system has a status change, data of sets of process parameters and actual measurement values of workpiece samples processed before the status change occurs, and data of sets of process parameters and actual measurement values of few workpiece samples processed after the status change occurs are used for build or retrain a prediction model, thereby predicting a metrology value of a next workpiece.

Abstract: In a metrology sampling method with a sampling rate decision scheme, a mean absolute percentage error (MAPE) and a maximum absolute percentage error (MaxErr) of visual metrology values of all workpieces in a set of determinative samples (DS), and various index values that can detect various status changes of a process tool (such as maintenance operation, parts changing, parameter adjustment, etc.), and/or information abnormalities of the process tool (such as abnormal process data, parameter drift/shift, abnormal metrology data, etc.) appearing in a manufacturing process are applied to develop an automated sampling decision (ASD) scheme for reducing a workpiece sampling rate while VM accuracy is still sustained.

Abstract: A baseline predictive maintenance method for a target device (TD) and a computer program product thereof are provided. Fresh samples which are generated when the target device produces workpieces just after maintenance are collected, and a new workpiece sample which is generated when the target device produces a new workpiece is collected. A plurality of modeling samples are used to build a TD baseline model in accordance with a conjecturing algorithm, wherein the modeling samples include the new workpiece sample and the fresh samples. A TD healthy baseline value for the new workpiece is computed by the TD baseline model, and a device health index (DHI), a baseline error index (BEI) and baseline individual similarity indices (ISIB) are computed, thereby achieving the goals of fault detection and classification (FDC) and predictive maintenance (PdM).

Abstract: An automated constructing method of cloud manufacturing service is provided for a distributed system including a virtual machine and a service manager. The method includes: obtaining a library package which is locally built, analyzing the library package to obtain key information, and generating a library information file; automatically generating a project source code file according to the library information file, and generating a web service package according to the project source code file; and deploying, by the service manager, the web service package on the virtual machine.

Abstract: A tool wear monitoring and predicting method is provided, and uses a hybrid dynamic neural network (HDNN) to build a tool wear prediction model. The tool wear prediction model adopts actual machining (cutting) conductions, sensing data detected at the current tool run of operation and the predicted tool wear value at the previous tool run of operation to predict a predicted tool wear value at the current tool run. A cyber physical agent (CPA) is adopted for simultaneously monitoring and predicting tool wear values of plural machines of the same machine type.

Abstract: A system and a method for machine tool maintenance and repair is provided for allowing an expert at a remote site to collaborate with an on-site personnel to maintain or repair a physical machine in a manner of combining the physical machine with a virtual reality (VR) model or an augmented reality (AR) model. Two maintenance modes are provided, which are an augmented virtual reality model guided by a standard operation procedure (referred as a SOP-AVR mode), and an augmented virtual reality model guided by an expert operation procedure (referred as an EG-AVR mode). A cyber physical agent (CPA) is adopted for simultaneously monitoring and repairing plural machines of the same machine type.

Abstract: A product quality prediction method for mass customization is provided. When a production system has a status change, data of sets of process parameters and actual measurement values of workpiece samples processed before the status change occurs, and data of sets of process parameters and actual measurement values of few workpiece samples processed after the status change occurs are used for build or retrain a prediction model, thereby predicting a metrology value of a next workpiece.

Abstract: In a metrology sampling method, various index values that can detect various status changes of a process tool (such as maintenance operation, parts changing, parameter adjustment, etc.), and/or information abnormalities of the process tool (such as abnormal process data, parameter drift/shift, abnormal metrology data, etc.) appear in a manufacturing process are applied to develop an intelligent sampling decision (ISD) scheme for reducing sampling rate while VM accuracy is still sustained. The indices includes a reliance Index (RI), a global similarity index (GSI), a process data quality index (DQIX) and a metrology data quality index (DQIy).

Abstract: A processing apparatus includes a processing unit for processing the workpiece, a processing quality prediction unit connected with the processing unit electrically, a signal interpretation unit connected with the processing quality prediction unit electrically, and a control unit connected with both the processing unit and the signal interpretation unit electrically, wherein when the processing unit is processing the workpiece, the processing quality prediction unit detects the processing signal and sends the signal to the signal interpretation unit, wherein when the signal interpretation unit interprets the processing signal, if there is abnormality in the processing signal, the signal interpretation unit will immediately notify the control unit to stop the processing unit from operating.

Abstract: A processing apparatus includes a processing quality prediction unit capable of outputting workpiece surface processing signal, a storage unit capable of storing workpiece surface processing signal, and a workpiece surface information management unit capable of interpreting workpiece surface processing signal. The workpiece surface information management unit can convert the surface processing signal into data of workpiece surface quality. The workpiece surface information management unit can be utilized to respectively interpret the surface processing signals provided by the processing quality prediction unit and to convert them into data of the roughness degree of the workpiece surface texture, so as to clearly provide information regarding the quality of the workpiece surface and completely utilize the signals detected during the processing for increasing the value added of the processing apparatus and enhancing the efficiency of use of the processing apparatus.

Abstract: A processing apparatus with vision-based measurement includes a central control unit and a workpiece transporting unit, a vision-based measurement unit, a processing quality prediction unit, and a processing unit that are respectively connected to the central control unit electrically. The workpiece transporting unit is controlled by the central control unit to transport the workpiece to the vision-based measurement unit to be measured. The data obtained by the vision-based measurement unit from measuring the workpiece is provided to the processing quality prediction unit for conducting quality prediction. The processing quality prediction unit implements a virtual processing quality prediction method to establish a quality prediction model, wherein the workpiece transporting unit is utilized to assist the processes of establishing or modifying the model.

Abstract: A processing apparatus includes a central control unit, and a processing quality prediction unit, a processing unit, and a tool compensation unit which are respectively connected with the central control unit electrically. The processing quality prediction unit implements a virtual processing quality prediction method to predict the processing quality of the workpiece, output an accurate data of quality to the central control unit, and generate tool path for the processing unit to process the workpiece. The central control unit judges the data from the processing quality prediction unit and outputs the data to the tool compensation unit to calculate tool compensation data. The tool compensation unit provides the tool compensation data to the processing quality prediction unit to form a new processing path. Then the processing unit implements the compensated processing path to process the workpiece.

Abstract: A digital marking processing apparatus includes a central control unit, and a processing quality prediction unit, a processing unit and a marking unit which are respectively connected with the central control unit electrically. The processing quality prediction unit can implement a virtual processing quality prediction method to predict the processing quality of the workpiece, output an accurate data of quality to the central control unit and generate tool path for the processing unit to process the workpiece. The central control unit is able to compile the data of quality from the processing quality in prediction unit into file information, so that the marking unit can then utilize the file information to correspondingly mark barcode or other digital pattern on the workpiece, which facilitate workpiece management and information disclosure.

Abstract: Embodiments of the present invention provide a two-phase process for searching the root causes of the yield loss in the production line 100. In a first phase, process tools and their process tool types that are likely to cause the yield loss are identified, and in a second phase, the process parameters that are likely to cause the yield loss within the process tool types found in the first phase are identified. In each phase, two different algorithms can be used to generate a reliance index (RIk) for gauge the reliance levels of their search results.