WO2024034891A1

WO2024034891A1 - Process operation method and electronic device performing same method

Info

Publication number: WO2024034891A1
Application number: PCT/KR2023/010235
Authority: WO
Inventors: 박연규; 이종훈; 김성준
Original assignee: 삼성전자주식회사
Priority date: 2022-08-12
Filing date: 2023-07-18
Publication date: 2024-02-15

Abstract

Disclosed are a process operation method and an electronic device performing the method. An electronic device, according to one embodiment, comprises: a processor; and a memory electrically connected to the processor and storing instructions executable by the processor, wherein the processor may, when the instructions are executed: collect process data regarding a plurality of processes; determine, on the basis of the process data, a defective process in which a defect has occurred from among the plurality of processes; and update, on the basis of the defect, a setting value of at least one of the plurality of processes.

Description

Method of operating a process and electronic devices performing the method

The disclosure below relates to a process operation method using process data collected from a plurality of processes, and an electronic device that performs the method.

The person in charge of each process manually manages productivity or performs quality control through personal experience and analysis. When defects occur in each unit process, the defective products are first collected and an external inspection is performed, and secondly, defect analysis is performed to identify problems in the unit process and improve the process.

An electronic device according to an embodiment may include a processor and a memory that is electrically connected to the processor and stores instructions executable by the processor. The processor may collect process data regarding a plurality of processes when the instruction is executed. The processor may determine a defective process in which a defect occurs among the plurality of processes based on the process data. The processor may update the setting value of at least one of the plurality of processes based on the defect.

A process operation method according to an embodiment includes the operation of collecting process data about a plurality of processes, based on the process data, determining a defective process in which a defect occurred among the plurality of processes, based on the defect, It may include an operation of updating the setting value of at least one of a plurality of processes.

A process operation method according to an embodiment includes collecting process data about a plurality of processes, based on the process data, determining a defective process in which a defect occurred among the plurality of processes, and based on the defect, It may include an operation of updating a setting value for at least one of a process before the defective process, the defective process, and a process after the defective process, or a combination thereof. The process data may include at least one of measurement data on input sets and discharge sets for each of the plurality of processes, equipment data on equipment, and pre-stored external data, or a combination thereof.

1 is a diagram illustrating an electronic device and a plurality of processes according to an embodiment.

FIG. 2 is a diagram illustrating an operation in which an electronic device collects process data, according to an embodiment.

Figure 3 is a diagram showing the operation of an electronic device according to an embodiment.

FIG. 4 is a diagram illustrating an operation in which an electronic device determines a defect or a defective process and determines a setting value to be updated, according to an embodiment.

Figures 5a and 5b are diagrams showing distribution before and during operation according to one embodiment.

Figures 6a and 6b are diagrams showing defect trends according to one embodiment.

Figure 7 is a diagram illustrating an operation of updating the upper and lower specification limits according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the attached drawings. In the description with reference to the accompanying drawings, identical components will be assigned the same reference numerals regardless of the reference numerals, and overlapping descriptions thereof will be omitted.

As used herein, “A or B”, “at least one of A and B”, “at least one of A or B”, “A, B or C”, “at least one of A, B and C”, and “A Each of phrases such as “at least one of , B, or C” may include any one of the items listed together in the corresponding phrase, or any possible combination thereof.

FIG. 1 is a diagram illustrating an electronic device 100 and a plurality of processes 200-1, 200-2, and 200-3 according to an embodiment.

For example, the first process 200-1 may include a facility 210-1, a sensor 220-1, and a detector/measurement device 230-1. The second process 200-2 may include a facility 210-2, a sensor 220-2, and a detector/measurement device 230-2. The third process 200-3 may include a facility 210-3, a sensor 220-3, and a detector/measurement device 230-3.

For example, the plurality of processes 200-1, 200-2, and 200-3 are sequentially connected to the first process 200-1, the second process 200-2, and the third process 200-3. Processing of the input set can be performed accordingly. For example, the first process 200-1 can process the input set. The second process 200-2 may process the set discharged from the first process 200-1. The third process 200-3 may process the set discharged from the second process 200-2.

For example, a plurality of processes 200-1, 200-2, and 200-3 (e.g., the first process 200-1, the second process 200-2, and the third process 200-3, respectively) equipment (210-1, 210-2, 210-3), sensors (220-1, 220-2, 220-3), and/or detectors/measurements (230-1, 230-2, 230-3). For example, each of the plurality of processes 200-1, 200-2, and 200-3 can perform processing, measurement, inspection, measurement, etc. on the input set.

As an example, the electronic device 100 may include a memory 110 and a processor 120.

The processor 120 may control at least one other component (e.g., a hardware or software component) of the electronic device 100 connected to the processor 120 by, for example, executing software (e.g., a program) , may perform various data processing or operations. According to one embodiment, as at least part of the data processing or operation, the processor 120 stores commands or data received from other components (e.g., communication modules) in volatile memory. According to one embodiment, the processor 120 may be a main processor (e.g., a central processing unit or an application processor) or It may include a co-processor (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or in conjunction with it. For example, electronic When the device 100 includes a main processor and a auxiliary processor, the auxiliary processor may be set to use less power than the main processor or be specialized for a designated function. The auxiliary processor may be implemented separately from the main processor or as part of it. It can be.

According to one embodiment, the auxiliary processor (eg, neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. Artificial intelligence models can be created through machine learning. For example, such learning may be performed in the electronic device 100 itself on which the artificial intelligence model is performed, or may be performed through a separate server. Learning algorithms may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but It is not limited. An artificial intelligence model may include multiple artificial neural network layers. Artificial neural networks include deep neural network (DNN), convolutional neural network (CNN), recurrent neural network (RNN), restricted boltzmann machine (RBM), belief deep network (DBN), bidirectional recurrent deep neural network (BRDNN), It may be one of deep Q-networks or a combination of two or more of the above, but is not limited to the examples described above. In addition to hardware structures, artificial intelligence models may additionally or alternatively include software structures.

The memory 110 may store various data used by at least one component (eg, processor 120 or communication module) of the electronic device 100. Data may include, for example, input data or output data for software and instructions related thereto. Memory 110 may include volatile memory or non-volatile memory.

For example, the electronic device 100 may collect process data generated in a plurality of processes 200-1, 200-2, and 200-3. For example, the electronic device 100 may include a communication module for collecting process data generated in a plurality of processes 200-1, 200-2, and 200-3 through wired or wireless communication. The electronic device 100 may include an interface for collecting process data.

For example, the process data includes equipment data including the status of the equipment (210-1, 210-2, 210-3), logs, etc., and sensors measured from the sensors (220-1, 220-2, 220-3). It may include at least one of sensor data including logs and measurement data detected or measured by the detectors/measurements 230-1, 230-2, and 230-3. For example, measurement data may include test reports, results, etc. generated using detectors/measuring instruments 230-1, 230-2, and 230-3.

For example, process data may include external data input from outside. External data may include data on parts and sets input to each of the plurality of processes 200-1, 200-2, and 200-3. For example, data about parts and sets may include data about parts and sets, such as size, characteristics, test scores, test results, quality, MES, part/raw material measurements, part life management data, etc. You can.

For example, equipment data is data related to equipment, such as equipment surrounding environment data (e.g. vibration, temperature/humidity, noise, frequency, etc.), equipment operation data (e.g. operating status, operating time, failure/failure, set emissions). status, etc.), facility self-management data (e.g. number of operations, input voltage, etc.), etc.

For example, measurement data is data generated during inspection/measurement, including inspection/measurement test reports (e.g. actual measurement values, Pass/Fail results, etc.), data generated by the set during inspection/measurement (e.g. during camera testing) It may include captured images, recorded voice when testing microphone components, radio wave strength measured during RF testing, etc.).

The above process data, equipment data, and measurement data represent one example among various embodiments, and are not limited to the above example, and various data related to parts, sets, equipment, and inspection/measurement may be applied.

For example, external data is data collected other than data generated in the processes 200-1, 200-2, and 200-3, and may include data provided from parts companies and external system data. For example, data provided by parts companies includes input sets and/or parts input into the process (200-1, 200-2, 200-3), such as camera parts receipt test reports, battery voltage, cable life cycle data, etc. It may contain data related to . For example, external system data includes production plans, development stage defects and action history, data on production and processes (e.g. repair history, defect status, measurement value distribution, etc.), logistics information (e.g. inventory/balance status, warehouse) (entry/exit status, etc.) may be included.

For example, the electronic device 100 may collect at least one of preprocessed facility data, sensor data, measurement data, and external data. For example, the electronic device 100 may preprocess at least one of collected facility data, sensor data, measurement data, and external data.

For example, the electronic device 100 may preprocess process data, such as data processing, representative value calculation, and generation of learning data for learning a neural network model.

For example, the electronic device 100 may determine a defective process in which a defect occurs among a plurality of processes based on process data. For example, the electronic device 100 may identify a defect. For example, the electronic device 100 may use process data to determine whether there is a defect from the input set and/or discharge set of each of the plurality of processes 200-1, 200-2, and 200-3.

The electronic device 100 can determine the process in which a defect occurred. For example, if a defect occurs in the set discharged from the first process 200-1, the electronic device 100 may determine the first process 200-1 to be a defective process.

For example, the electronic device 100 may update the setting value of at least one process among a plurality of processes based on a defect. For example, the electronic device 100 may resolve the cause of the defect by updating the setting values of the defective process in which the defect occurred and/or processes other than the defective process.

For example, causes of defects may include equipment or equipment failure errors, operator work errors, and defects in the parts themselves.

For example, the set value may include values set regarding the operation of the equipment (210-1, 210-2, and 210-3). For example, the set value may be set as a criterion (e.g., upper specification limit and/or lower specification limit) for each process (200-1, 200-2, 200-3) to determine whether the input set and/or output set are defective. ) may include. For example, the set value may include at least one of an item, object, and time for inspection or measurement performed in at least one of the plurality of processes 200-1, 200-2, and 200-3.

The electronic device 100 may collect process data by collecting various types of data in various ways. The electronic device 100 monitors multiple processes (200-1, 200-2, 200-3) through statistical analysis and machine learning, identifies the cause of defects, and actively monitors each process through real-time simulation. It can be operated.

As an example, the electronic device 100 can generate a report. For example, the electronic device 100 may generate a report based on data regarding the determined defect and/or defective process. For example, the electronic device 100 may generate a report of analysis results, such as defect distribution trend and defect prediction results, based on process data. For example, the electronic device 100 may generate a report on the updated settings of the plurality of processes 200-1, 200-2, and 200-3, process efficiency according to the updated settings, etc. The items and forms included in the report can be set according to user settings.

FIG. 2 is a diagram illustrating an operation in which the electronic device 100 collects process data according to an embodiment.

Referring to FIG. 2, the electronic device 100 receives facility data 111, sensor data 112, and measurement data from the facility 210-1, sensor 220-2, and detector/measurement device 230-1, respectively. (113) can be collected. For example, the electronic device 100 may process equipment data 111, sensor data 112, and measurement data 113. For example, the electronic device 100 may collect preprocessed facility data 111, preprocessed sensor data 112, and preprocessed measurement data 113.

For example, the electronic device 100 configures the format of output data (e.g., text, audio, video, binary, etc.) according to the characteristics of each of the plurality of processes 200-1, 200-2, and 200-3. At least one of equipment data 111, sensor data 112, measurement data 113, and external data 114 may be preprocessed by transforming, processing, or converting.

Figure 2 is a diagram showing the operation of collecting equipment data 111, sensor data 112, and measurement data 113 from the first process 200-1. The electronic device 100 is shown in FIG. 2 from a second process (e.g., the second process 200-2 in FIG. 1) and/or a third process (e.g., the third process 200-3 in FIG. 1). Equipment data 111, sensor data 112, and measurement data 113 can be collected in substantially the same way as the described operation.

FIG. 3 is a diagram illustrating the operation of an electronic device (eg, the electronic device 100 of FIG. 1) according to an embodiment.

Referring to FIG. 3, in operation 310, the electronic device 100 according to an embodiment performs a plurality of processes (e.g., a plurality of processes 200-1, 200-2, and 200-3 in FIG. 1). Process data can be collected. For example, the electronic device 100 may store equipment data (e.g., equipment data 111 in FIG. 2), sensor data (e.g., sensor data 112 in FIG. 2), and measurement data (e.g., measurement data in FIG. 2). Process data including at least one of (113)), or a combination thereof, may be collected. For example, the electronic device 100 may store external data provided from outside (eg, external data 114 in FIG. 2).

For example, in operation 320, the electronic device 100 may determine a defective process in which a defect occurred among the plurality of processes 200-1, 200-2, and 200-3 based on process data.

For example, the electronic device 100 may input process data into a neural network model to determine defects and/or defective processes. For example, a neural network model may be learned using training data generated based on process data. For example, a neural network model may be learned according to learning data using the correlation between a plurality of processes 200-1, 200-2, and 200-3.

As an example, a neural network model may be trained to determine defects and/or defective processes using training data. As an example, a neural network model may be trained to determine the probability of defectiveness and/or the probability of defectiveness of a process using training data. For example, the electronic device 100 may determine defects and/or defective processes using a neural network model. For example, the electronic device 100 can predict defects and defective processes using a neural network model.

For example, in an RF process that measures the performance of RF-related components, set defects can be caused not only by the RF-related components but also by external variables (e.g., poor assembly, frequency interference, defective adjacent IC, etc.).

The electronic device 100 may generate learning data using process data including existing repair history and test results of the RF process. The electronic device 100 may use learning data to train a neural network model to predict a defective process in which a defect occurs. For example, when a defect occurs in the RF process, the electronic device 100 inputs the collected process data into a neural network model to determine the defective process among the plurality of processes 200-1, 200-2, and 200-3. can do.

For example, when a defect occurs in an RF process, the existing repair history may include actions for multiple processes (200-1, 200-2, and 200-3) to resolve the cause of the defect. For example, action on multiple processes 200-1, 200-2, and 200-3 may include updating the settings of multiple processes 200-1, 200-2, and 200-3. there is.

For example, in operation 330, the electronic device 100 may change the setting value of at least one process among a plurality of processes based on a defect. For example, the electronic device 100 may change the setting value to resolve the cause of the defect.

For example, the electronic device 100 may update at least one of a first set value for a defective process, a second set value for a process before a defective process, and a third set value for a process after a defective process. A plurality of processes 200-1, 200-2, and 200-3 may be performed continuously for the input set.

For example, the electronic device 100 may update the first set value of the defective process. For example, if the defective process is a CAL process, the measurement distribution of the CAL process may be distorted depending on the process performance. The electronic device 100 may update or change the setting value so that Re CAL of the CAL process progresses depending on the degree of distribution distortion.

For example, some and/or all of the plurality of processes 200-1, 200-2, and 200-3 may be correlated with each other. For example, process data collected from a plurality of processes 200-1, 200-2, and 200-3 may have a correlation.

For example, the electronic device 100 may change the second setting value for the process before the defective process. For example, the first process 200-1 may be performed in a plurality of jigs included in the equipment 210-1. For example, among sets in which defects occurred in the third process 200-3, the ratio of sets in which the first process 200-1 was performed in a specific jig in the first process 200-1 may be high. The electronic device 100 may change the setting value of the first process 200-1 in order to resolve the cause of the defect occurring in the third process 200-3. For example, the electronic device 100 may prevent a set from being processed in a specific jig in the first process 200-1 or change settings related to the operation of the equipment 210-1.

For example, the electronic device 100 may change the second set value of the process before the defective process based on the correlation between the process data of the process before the defective process and the process data of the defective process. For example, the CAL process and the RF final process performed after the CAL process may be interrelated. When a defect occurs in the RF final process, the electronic device 100 may determine the correlation between the RF final process and the CAL process before the RF final process, or the correlation between the defect occurring in the RF final process and the CAL process.

For example, the correlation between a defective process and a process before the defective process may mean the impact of the process before the defective process on the defective process in terms of occurrence of defects. For example, the correlation between a defect and a process prior to a defective process may mean the impact on the occurrence of defects in the process prior to the defective process.

For example, the electronic device 100 may determine, through correlation, the impact of at least one of the equipment, sensors, and detectors/measurements of the CAL process on the defect process in relation to the occurrence of defects. For example, the electronic device 100 may determine the influence of at least one of CAL process equipment, sensors, and detectors/measurements on the occurrence of defects through correlation.

For example, the electronic device 100 may change the third setting value related to the process after the defective process. For example, the electronic device 100 may update at least one of the items, objects, and times for inspection or measurement performed in at least one process among a plurality of processes, or a combination thereof.

For example, if the first process 200-1 is an RF CAL (RF calibration) process and the third process 200-3 is a SAR (specific absorption rate) test process, the electronic device 100 may perform the third process. In process 200-3, at least one of item, object, and time can be changed.

For example, in the process data collected in the first process 200-1, based on the measurement data 113 collected from the detector/measurement device 230-1, the items of the third process 200-3, At least one of the target and time can be changed. For example, the electronic device 100 may perform a SAR test on a set of RF CAL results corresponding to a set range. For example, the electronic device 100 may omit and/or add some of the SAR test items to a set in which the RF CAL result corresponds to a set range. For example, the electronic device 100 may shorten and/or extend the time of the SAR test for a set in which the RF CAL result corresponds to a set range.

For example, based on process data, the electronic device 100 may update at least one or a combination of items, objects, and times for inspection or measurement performed in at least one process among a plurality of processes.

For example, when testing with some test items for shipping inspection efficiency, testing can be conducted on sets with a high probability of defects. The electronic device 100 may label sets with a high probability of defects using process data collected in a previous process.

For example, the electronic device 100 may label a set with a high probability of defect based on process data collected in the first process 200-1. In the second process 200-2 and/or the third process 200-3, the electronic device 100 performs an additional test on the labeled set, performs a test including the labeled set, or performs a labeling test. You can change the test time for a given set.

For example, the electronic device 100 may use a neural network model to update at least one of an item, object, and time for inspection or measurement performed in at least one process among a plurality of processes, or a combination thereof.

For example, if the first process 200-1 is an RF CAL (RF calibration) process and the third process 200-3 is a specific absorption rate (SAR) test process, the electronic device 100 may perform the first process. Learning data can be generated using process data collected in the process 200-1 and the third process 200-3. For example, the electronic device 100 may store results according to test items of the RF CAL process in the form of a CSV file. The electronic device 100 may extract, process, and label test items that are correlated with test items of the SAR process from the results of the RF CAL process.

The neural network model can input process data collected from the RF CAL process and output a set with a high probability of defects from the SAR process. The electronic device 100 may change the setting value of the SAR process so that the items, targets, and times of the SAR process for a set with a high probability of failure are different from the items, targets, and times of the SAR process for a set with a high probability of failure. .

The electronic device 100 may be operated as a full inspection or may be operated as a selective test in each process (200-1, 200-2, and 200-3). The electronic device 100 operates the entire inspection or selective test operation of each process (200-1, 200-2, and 200-3) based on the process data, efficiently optimizes the entire process, improves productivity, and , quality can be strengthened.

In the above example, the first process (200-1), the second process (200-2), and the third process (200-3) were described as specific processes as examples, but the first process (200-1), The second process 200-2 and the third process 200-3 are not limited to the above-described example processes.

FIG. 4 is a diagram illustrating an operation in which an electronic device (e.g., the electronic device 100 of FIG. 1 ) determines a defect or a defective process and determines a setting value to be updated, according to an embodiment. For example, FIG. 4 shows an example of determining a set value when a defect occurs in the second process of FIG. 1 (eg, the second process 200-2 of FIG. 1).

Referring to FIG. 4, the electronic device 100 may determine whether a facility is defective in operation 405. For example, equipment defects include setting values for the equipment (e.g., the equipment 210-2 in FIG. 1), operation of the equipment 210-2 (eg, torque, speed, pressure, etc.), and equipment 210-2. ) may include defects related to the condition, etc.

For example, if a facility is defective in operation 405, the electronic device 100 may determine whether stopping the facility is necessary in operation 415. For example, the electronic device 100 may determine whether to stop the facility according to set facility stop conditions. For example, the facility stop condition is when more than a set number of defects (e.g. 3, 5, etc.) occur within a set time (e.g. 5 minutes, 10 minutes, etc.), or when more than a set number of defects (e.g. 3, 5, etc.) occur. etc.) If a defect occurs continuously or exceeds the conditions set based on process data (e.g., if the temperature or pressure of the equipment exceeds the set temperature or pressure, or if the detection or measurement results related to the set are not set) It can be set in various ways, such as when equipment stop conditions are exceeded, etc.)

For example, if it is determined in operation 415 that a facility stop is necessary, or if a facility stop condition is satisfied, the electronic device 100 may stop the facility 210-2 in operation 420. For example, the electronic device 100 may stop the second process 200-2. The process may be stopped until the user starts operating the second process 200-2 again or until the condition causing the defect is resolved.

For example, if it is determined in operation 415 that facility stoppage is not necessary, or if the facility stop condition is not satisfied, the electronic device 100 may determine whether to correct the facility in operation 425. For example, if equipment correction is necessary in operation 425, the electronic device 100 may update the equipment settings in operation 430. In the second process 200-2, the equipment 210-2 may operate according to the changed equipment settings.

For example, if the equipment is not defective in operation 405, the electronic device 100 may determine whether the input set is defective in operation 410. Defects in the input set may include defects in the size and characteristics of the set input to the second process 200-2, or defects in parts and raw materials input in the second process 200-2.

For example, if the input set is defective in operation 410, the electronic device 100 may determine whether to maintain the equipment in operation 435. For example, when the input set defect rate exceeds the set defect rate, the electronic device 100 may determine to stop the facility 200-2 in operation 435.

For example, if the input set is not defective in operation 410, the electronic device 100 may determine whether the equipment is defective or provide a notification signal to the user in operation 405.

The equipment stop condition set in operation 435 above may be set to be the same as the equipment stop condition in operation 415, but is not limited to this, and the equipment stop condition in operation 435 is the equipment stop condition in operation 415. It may be set differently from the conditions.

For example, if the equipment stop condition is satisfied in operation 435, the electronic device 100 may stop the equipment 200-2 in operation 440. With respect to operation 440, the description of operation 420 may be applied substantially the same.

For example, if it is determined in operation 435 that facility stoppage is not necessary or if the facility stop condition is not satisfied, the electronic device 100 may determine whether to correct the threshold in operation 445. For example, threshold correction may include changing the upper specification limit and/or lower specification limit shown in FIG. 7.

For example, if threshold correction is necessary in operation 445, the electronic device 100 may determine whether threshold correction of the defective process is necessary in operation 450. For example, if it is determined in operation 425 that facility correction is not necessary, the electronic device 100 may determine whether threshold correction is necessary in operation 445.

For example, if it is determined in operation 450 that correction of the threshold of the defective process is necessary, the electronic device 100 may update the threshold of the second process 200-2, which is the defective process, in operation 455. .

For example, if it is determined in operation 450 that threshold correction other than the defective process is necessary, the electronic device 100 performs the first process 200-1 and/or the third process other than the defective process in operation 460. The threshold value of process 200-3 can be updated.

Referring to FIGS. 5A and 5B , the electronic device 100 according to one embodiment may determine defectiveness and defective process based on the distribution of process data. For example, the electronic device 100 may use measurement data (e.g., measurement data 113 in FIG. 2) to analyze the distribution of the detected value or measured value.

The electronic device 100 performs fault diagnosis for each detector/measurement device (e.g., the detectors/measurements 230-1, 230-2, and 230-3 in FIG. 1) through distribution analysis after inspection using process data. can do. For example, the electronic device 100 may perform fault diagnosis for each IP, port, and jig of the detectors/measurements 230-1, 230-2, and 230-3.

For example, Figure 5A may show the jig distribution of the detectors/measurements 230-1, 230-2, and 230-3 before operation. For example, the distribution by jig in FIG. 5A may change like the distribution by jig of the detectors/measurements 230-1, 230-2, and 230-3 during operation in FIG. 5B.

In FIG. 5B, the electronic device 100 may determine whether jig 3 is broken according to the distribution bias tendency of jig 3 (e.g., JIG03 in FIGS. 5A and 5B). For example, if there is a tendency for distribution bias to occur across all jigs during operation, it can be determined whether the lot of the received parts is defective.

For example, the distribution trend may include the trend of measured values for each test item and the defect trend. For example, the electronic device 100 may analyze margin defects by analyzing measurement values for each test item and defect trend analysis. Differences in the degree of defects may occur depending on voltage, temperature, humidity, frequency interference, etc., and the electronic device 100 may detect equipment (e.g., equipment 210-1 of FIG. 1, 210-2, 210-3)), sensors (e.g., sensors 220-1, 220-2, 220-3 in FIG. 1), and detectors/measurements (e.g., detectors/meters 230-1 in FIG. 1). It is possible to determine whether 230-2, 230-3)) should be inspected.

For example, the electronic device 100 uses the distribution trend to detect equipment (210-1, 210-2, 210-3), sensors (220-1, 220-2, 220-3), and detectors/measurements ( 230-1, 230-2, 230-3) can determine whether there is a progressive failure or failure.

For example, the electronic device 100 uses distribution trends and/or external data (e.g., external data 114 in FIG. 2) to detect facilities 210-1, 210-2, and 210-3, sensors ( 220-1, 220-2, 220-3) and the detector/measurement device (230-1, 230-2, 230-3) can determine whether there is a progressive failure or failure and predict the occurrence of a progressive failure or failure.

For example, the electronic device 100 can determine the correlation between the life cycle (management of usage period and number of uses) and defect trends of cables used in RF processes, etc. The electronic device 100 uses equipment (210-1, 210-2, 210-3), sensors (220-1, 220-2, 220-3), and detection/detection devices based on the correlation between the life cycle and the defect trend. Progressive failure or failure of the measuring instruments 230-1, 230-2, and 230-3 can be predicted.

FIG. 6A shows a defect trend for each jig according to an embodiment, and FIG. 6B shows a defect trend according to simulation results.

For example, the electronic device 100 may simulate the expected defect occurrence trend as shown in FIG. 6B. Figure 6b shows a graph predicting the trend of defect occurrence for each jig in a specific process. The electronic device 100 includes facilities (210-1, 210-2, 210-3), sensors (220-1, 220-2, 220-3), and detectors/measurements (230-1, 230-2, 230- 3) The trend of defect occurrence can be predicted.

For example, to predict defect occurrence trends, the electronic device 100 may use a learned neural network model. For example, a neural network model can be trained with training data generated using process data. For example, process data may include repair history. Repair history may include causes of past defects, location of defects (e.g. defective equipment, defective sensors, defective detectors/measurements), and actions taken to resolve the cause of defects. A neural network model can be trained to predict defect occurrence trends using learning data generated from process data.

For example, the electronic device 100 may predict defect occurrence trends using a plurality of neural network models. For example, multiple neural network models may each be trained using different learning algorithms. The electronic device 100 can predict defect occurrence trends according to an ensemble technique using a plurality of neural network models. A plurality of neural network models can be learned using added process data at set intervals (e.g., daily, weekly, monthly, etc.).

Referring to FIG. 7, an electronic device (e.g., the electronic device 100 of FIG. 1) according to an embodiment sets an upper specification limit (USL) and/or a lower specification limit (LSL) based on a preset target production volume. , lower specification limit) can be changed. For example, upper and lower specification limits can be determined within quality control limits. The upper specification limit and lower specification limit may be called specifications or thresholds.

The upper specification limit and lower specification limit may represent standards for the electronic device 100 to judge a set as defective or good during the process. Quality control limits may refer to standards set by the user. For example, for a set that exceeds the upper standard limit or is less than the lower standard limit, the electronic device 100 may determine the set to be defective, but the set may be a set that satisfies the quality control limit.

Considering the target production volume, the electronic device 100 changes the existing upper specification limit (USL in FIG. 7) and the existing lower specification limit (LSL in FIG. 7) into a new upper specification limit (new USL in FIG. 7) and a new lower specification limit (in FIG. 7). You can change it to new LSL).

For example, the upper specification limit and lower specification limit shown in FIG. 7 apply to multiple processes (e.g., multiple processes (200-1, 200-2, 200-3) in FIG. 1) and equipment (e.g., equipment in FIG. 1). (210-1, 200-2, 200-3)), sensors (e.g., sensors (220-1, 220-2, 220-3) of FIG. 1), equipment (e.g., detector/measurement device (230) of FIG. 1 -1, 230-2, 230-3)) can be set respectively.

The electronic device 100 may determine defectiveness or a defective process by changing at least one of the upper specification limit and lower specification limit, or a combination thereof, as shown in FIG. 7 . The electronic device 100 may adjust the upper specification limit and/or lower specification limit to maximize productivity within quality control limits and satisfy a set target production amount. The electronic device 100 can actively respond to changes in the manufacturing environment and production volume by adjusting the upper specification limit and/or the lower specification limit, and can simultaneously manage productivity and quality.

The electronic device 100 described in FIGS. 1 to 7 above operates the process autonomously based on data to minimize human error and automatically corrects thresholds (e.g., upper specification limit and/or lower specification limit) in real time to improve productivity and Quality can be improved.

In addition to determining defects in the set, the electronic device 100 can determine whether there is a failure or breakdown of equipment, sensors, and detectors/measurements, and can predict progressive defects in equipment, sensors, and detectors/measurements to respond appropriately before defects occur. there is.

An electronic device (e.g., the electronic device 100 of FIG. 1) according to an embodiment is electrically connected to a processor (e.g., the processor 120 of FIG. 1) and the processor 120, and is connected to the processor 120. It may include a memory (eg, memory 110 in FIG. 1) that stores instructions executable by the memory. When the instruction is executed, the processor 120 may collect process data regarding a plurality of processes (eg, a plurality of processes 200-1, 200-2, and 200-3 in FIG. 1). The processor 120 may determine a defective process in which a defect occurs among the plurality of processes 200-1, 200-2, and 200-3 based on the process data. The processor 120 may update the setting value of at least one of the plurality of processes 200-1, 200-2, and 200-3 based on the defect.

The process data includes measurement data related to the input set and discharge set of each of the plurality of processes 200-1, 200-2, and 200-3 (e.g., measurement data 113 in FIG. 2), and equipment related to the equipment. It may include at least one of data (e.g., equipment data 111 in FIG. 2) and pre-stored external data (e.g., external data 114 in FIG. 2), or a combination thereof.

The processor 120 may update at least one of the upper specification limit and the lower specification limit based on a preset target production volume.

The processor 120 is configured to configure at least one of an item, object, and time for inspection or measurement performed in at least one of the plurality of processes 200-1, 200-2, and 200-3, or a combination thereof. can be updated.

The processor 120 may determine the defect and the defective process by inputting the process data into a neural network model. The neural network model may be trained to determine the defect and the defect process according to learning data generated from the process data.

The processor 120 may determine the defect and the defective process based on the distribution of the process data.

The processor 120 is configured to configure at least one of a first set value for the defective process, a second set value for the process before the defective process, and a third set value for the process after the defective process, or a combination thereof. can be updated.

A process operation method according to an embodiment includes collecting process data regarding a plurality of processes (200-1, 200-2, and 200-3), and determining defects that occur among the plurality of processes based on the process data. It may include an operation of determining a process and an operation of updating a setting value of at least one of the plurality of processes based on the defect.

The process data includes measurement data 113 for the input set and discharge set for each of the plurality of processes 200-1, 200-2, and 200-3, equipment data 111 for equipment, and external data stored in advance. It may include at least one of (114), or a combination thereof.

The operation of updating the set value may update at least one of the upper specification limit and the lower specification limit based on a preset target production volume.

The operation of updating the setting value includes at least one of the items, objects, and times for inspection or measurement performed in at least one of the plurality of processes (200-1, 200-2, and 200-3), or these The combination can be updated.

The operation of determining the defective process may include inputting the process data into a neural network model to determine the defect and the defective process. The neural network model may be trained to determine the defect and the defect process according to learning data generated from the process data.

The operation of determining the defective process may include determining the defect and the defective process based on the distribution of the process data.

The operation of updating the set value includes at least one of a first set value for the defective process, a second set value for the process before the defective process, and a third set value for the process after the defective process, or these The combination can be updated.

A process operation method according to an embodiment includes the operation of collecting process data regarding a plurality of processes (200-1, 200-2, and 200-3), and based on the process data, the plurality of processes (200-1, 200-2, 200-3), an operation of determining a defective process in which a defect occurred, and based on the defect, at least one of a process before the defective process, the defective process, and a process after the defective process, or these It may include an operation to update settings related to the combination. The process data includes measurement data 113 for the input set and discharge set for each of the plurality of processes 200-1, 200-2, and 200-3, equipment data 111 for equipment, and external data stored in advance. It may include at least one of (114), or a combination thereof.

The operation of updating the set value may update at least one of the upper specification limit and the lower specification limit based on a preset target production amount.

Electronic devices according to various embodiments disclosed in this document may be of various types. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to embodiments of this document are not limited to the above-described devices.

The various embodiments of this document and the terms used herein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various changes, equivalents, or replacements of the embodiments. In connection with the description of the drawings, similar reference numbers may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the above items, unless the relevant context clearly indicates otherwise. As used herein, “A or B”, “at least one of A and B”, “at least one of A or B”, “A, B or C”, “at least one of A, B and C”, and “A Each of phrases such as “at least one of , B, or C” may include any one of the items listed together in the corresponding phrase, or any possible combination thereof. Terms such as "first", "second", or "first" or "second" may be used simply to distinguish one component from another, and to refer to that component in other respects (e.g., importance or order) is not limited. One (e.g., first) component is said to be “coupled” or “connected” to another (e.g., second) component, with or without the terms “functionally” or “communicatively.” When mentioned, it means that any of the components can be connected to the other components directly (e.g. wired), wirelessly, or through a third component.

The term “module” used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and is interchangeable with terms such as logic, logic block, component, or circuit, for example. It can be used as A module may be an integrated part or a minimum unit of the parts or a part thereof that performs one or more functions. For example, according to one embodiment, the module may be implemented in the form of an application-specific integrated circuit (ASIC).

Various embodiments of this document are software (e.g., computer) including one or more instructions stored in a storage medium (e.g., internal memory or external memory) that can be read by a machine (e.g., electronic device 100). : It can be implemented as a program). For example, a processor (e.g., processor 120) of a device (e.g., electronic device 100) may call at least one command among one or more commands stored from a storage medium and execute it. This allows the device to be operated to perform at least one function according to the at least one instruction called. The one or more instructions may include code generated by a compiler or code that can be executed by an interpreter. A storage medium that can be read by a device may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' only means that the storage medium is a tangible device and does not contain signals (e.g. electromagnetic waves), and this term refers to cases where data is semi-permanently stored in the storage medium. There is no distinction between temporary storage cases.

According to one embodiment, methods according to various embodiments disclosed in this document may be included and provided in a computer program product. Computer program products are commodities and can be traded between sellers and buyers. The computer program product may be distributed in the form of a machine-readable storage medium (e.g. compact disc read only memory (CD-ROM)) or through an application store (e.g. Play StoreTM) or on two user devices (e.g. It can be distributed (e.g. downloaded or uploaded) directly between smart phones) or online. In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

According to various embodiments, each component (e.g., module or program) of the above-described components may include a single or plural entity, and some of the plurality of entities may be separately placed in other components. there is. According to various embodiments, one or more of the components or operations described above may be omitted, or one or more other components or operations may be added. Alternatively or additionally, multiple components (eg, modules or programs) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each component of the plurality of components in the same or similar manner as those performed by the corresponding component of the plurality of components prior to the integration. . According to various embodiments, operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, or omitted. Alternatively, one or more other operations may be added.

Claims

processor 120; and

A memory 110 electrically connected to the processor 120 and storing instructions executable by the processor 120.

Including,

The processor 120,

When the command is executed, process data regarding a plurality of processes (200-1; 200-2; 200-3) is collected;

Based on the process data, determine a defective process in which a defect occurs among the plurality of processes (200-1; 200-2; 200-3);

Based on the defect, updating the setting value of at least one of the plurality of processes (200-1; 200-2; 200-3),

Electronic device (100).
According to paragraph 1,

The process data is,

At least among the measurement data 112 for the input set and discharge set for each of the plurality of processes (200-1; 200-2; 200-3), equipment data 111 for equipment, and pre-stored external data 114 Containing one, or a combination thereof,

Electronic device (100).
According to any one of paragraphs 1 and 2,

The processor 120,

Based on a preset target production volume, updating at least one of the upper specification limit and the lower specification limit,

Electronic device (100).
According to any one of claims 1 to 3,

The processor 120,

Updating at least one of the items, objects, and times for inspection or measurement performed in at least one process among the plurality of processes (200-1; 200-2; 200-3), or a combination thereof,

Electronic device (100).
According to any one of claims 1 to 4,

The processor 120,

Input the process data into a neural network model to determine the defect and the defective process,

The neural network model is,

Learned to determine the defect and the defective process according to learning data generated from the process data,

Electronic device (100).
According to any one of claims 1 to 5,

The processor 120,

Based on the distribution of the process data, determining the defect and the defective process,

Electronic device (100).
According to any one of claims 1 to 6,

The processor 120,

Updating at least one of a first set value for the defective process, a second set value for the process before the defective process, and a third set value for the process after the defective process, or a combination thereof,

Electronic device (100).
An operation of collecting process data regarding a plurality of processes (200-1; 200-2; 200-3);

Based on the process data, determining a defective process in which a defect occurs among the plurality of processes (200-1; 200-2; 200-3); and

An operation of updating the setting value of at least one of the plurality of processes (200-1; 200-2; 200-3) based on the defect.

Including,

How the process operates.
According to clause 8,

The process data is,

At least among the measurement data 113 for the input set and discharge set for each of the plurality of processes (200-1; 200-2; 200-3), equipment data 111 for equipment, and pre-stored external data 114 Containing one, or a combination thereof,

How the process operates.
According to any one of paragraphs 8 and 9,

The operation of updating the setting value is,

Based on a preset target production volume, updating at least one of the upper specification limit and the lower specification limit,

How the process operates.
According to any one of claims 8 to 10,

The operation of updating the setting value is,

Updating at least one of the items, objects, and times for inspection or measurement performed in at least one process among the plurality of processes (200-1; 200-2; 200-3), or a combination thereof,

How the process operates.
According to any one of claims 8 to 11,

The operation of determining the defective process is,

Input the process data into a neural network model to determine the defect and the defective process,

The neural network model is,

Learned to determine the defect and the defective process according to learning data generated from the process data,

How the process operates.
According to any one of claims 8 to 12,

The operation of determining the defective process is,

An operation of determining the defect and the defective process based on the distribution of the process data

Including,

How the process operates.
According to any one of claims 8 to 13,

The operation of updating the setting value is,

Updating at least one of a first set value for the defective process, a second set value for the process before the defective process, and a third set value for the process after the defective process, or a combination thereof,

How the process operates.