Maintenance work analysis system and maintenance work analysis method for semiconductor manufacturing apparatus

Abstract

The purpose of the present invention is to provide a technology whereby beneficial information can be presented by a worker of maintenance work. One of the maintenance work analysis systems according to the present invention is a maintenance work analysis system that analyzes a work operation in a maintenance work of a semiconductor manufacturing apparatus, and is provided with: an information acquisition unit that acquires work information including activity information indicating an activity of a worker who performs the maintenance work; an information analysis unit that analyzes a work action of the worker on the basis of the work information; and an information visualization unit that outputs the difference between the maintenance work as a reference and the maintenance work performed by the operator.

Description

Technical Field

[0001] The present invention relates to a maintenance operation analysis system and a maintenance operation analysis method for a semiconductor manufacturing device. Background Art

[0002] Semiconductor manufacturing equipment has a complex structure compared to general manufacturing equipment. In addition, semiconductor manufacturing equipment has a great influence on the yield of the semiconductor device itself manufactured thereby. Therefore, when performing maintenance (maintenance) operations such as inspection, refurbishment, and repair of semiconductor manufacturing equipment, operators are required to have more knowledge and skills. In addition, many technologies have been developed to reduce the burden on operators who perform maintenance operations on semiconductor manufacturing equipment.

[0003] Patent Document 1 aims to provide a technology capable of shortening the maintenance time of an apparatus, and discloses the following as a user interface and a maintenance guidance method.

[0004] "The user interface 52 has an operation screen that displays given information about the device and is used for given operations, and an operation unit that performs operations on the operation screen. The user interface 52 has a maintenance mode for performing maintenance on the device through the operation screen. In the maintenance mode, a maintenance screen 101 corresponding to a given maintenance item among a plurality of maintenance items in which maintenance operations are stored in the storage unit 53 is displayed on the operation screen. The maintenance screen 101 displays the content of the maintenance of the maintenance item as a screen 101 for each step based on the information in the storage unit 53. In each screen 101 of the step, a description 105 of the step and an image 106 representing the maintenance part are displayed."

[0005] Patent document 2 is aimed at visually providing the operator with the information requested by the operator and the information that the operator wants to know, and discloses the following as a support information display method, a maintenance support method for a substrate processing device, a support information display control device, a substrate processing system, and a program. "In order to display the support information related to the maintenance in real time on the head mounted display HMD30 equipped by the operator during the maintenance work of the substrate processing device performed by the operator, the display control device 40 of the substrate processing system 100A acquires an image of a given part to be maintained in the substrate processing device through a camera provided by the HMD30, infers the support information related to the given part included in the acquired image from the information accumulated in the database, visualizes the inferred support information, and displays the created image on the HMD30, thereby allowing the operator to visually recognize the support information."

[0006] Prior Art Literature

[0007] Patent Literature

[0008] Patent Document 1: Japanese Patent Application Publication No. 2019-016759

[0009] Patent Document 2: Japanese Patent Application Publication No. 2014-164482 Summary of the invention

[0010] -Problems to be solved by the invention-

[0011] The success or failure of the maintenance work of the semiconductor manufacturing device is sometimes determined by the amount of foreign matter generated in the semiconductor manufacturing process after the maintenance work, and sometimes the maintenance work needs to be repeated. As a reason for this, it is impossible to completely regulate the movements of all fingers of the operator performing the maintenance work.

[0012] Specifically, the work actions such as line of sight, finger position / movement, and work posture during maintenance work are determined by the judgment and experience of each worker, and it is predicted that the large individual differences caused by the worker's proficiency etc. will affect the success of the maintenance work.

[0013] However, since it is impossible to fully compare the individual differences among operators and the correlation between the success or failure of maintenance operations, such as the presence or absence of leakage, the amount of foreign matter, and the process performance / yield after maintenance operations, the reasons for the failure of maintenance operations are unclear, and feedback to operators, operations that are prone to maintenance failure, and screening of parts are insufficient.

[0014] Patent Documents 1 and 2 do not fully study these aspects either.

[0015] Therefore, an object of the present invention is to provide a technology that can present useful information to a worker performing maintenance work.

[0016] -Methods for solving problems-

[0017] In order to solve the above-mentioned problems, one of the representative maintenance work analysis systems of the present invention is a maintenance work analysis system for analyzing work actions in the maintenance work of a semiconductor manufacturing device, comprising: an information acquisition unit, which acquires work information including activity information representing the activities of an operator performing the maintenance work; an information analysis unit, which analyzes the work actions of the operator based on the work information; and an information visualization unit, which outputs the difference between the maintenance work serving as a benchmark and the maintenance work performed by the operator.

[0018] -Effects of the Invention-

[0019] According to the present invention, useful information can be presented to a worker performing maintenance work.

[0020] Problems, structures, and effects other than those described above will become apparent from the following description of the embodiments for carrying out the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a diagram showing a situation in which the maintenance work analysis system according to the embodiment is utilized.

[0022] Figure 2 It is a diagram showing an example of the configuration of a maintenance work analysis system.

[0023] Figure 3 This is a diagram showing an example of the configuration of a measurement system.

[0024] Figure 4 This is a diagram showing a process of associating maintenance work with worker activities.

[0025] Figure 5 This is a diagram showing information used for analysis by the information analysis unit.

[0026] Figure 6 This is a diagram showing an example of analysis of a work action performed in the information analysis unit.

[0027] Figure 7 This is a diagram showing an example of a visualization result displayed in the output unit.

[0028] Figure 8 Detailed Description of the Invention This is a flowchart showing the analysis process performed in the maintenance work analysis system. DETAILED DESCRIPTION

[0029] Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings. In addition, the present invention is not limited to the embodiment. In addition, in the description of the accompanying drawings, the same reference numerals are attached to the same parts.

[0030] (Application example of maintenance work analysis system)

[0031] Figure 1 It is a diagram showing a situation in which the maintenance work analysis system according to the embodiment is utilized. Figure 1 The relationship among the maintenance work analysis system 1, the measurement system 2, the maintenance work DB (database) 3, and the evaluation system 4 is shown.

[0032] The maintenance work analysis system 1 is a system for analyzing work actions in the maintenance work of a semiconductor manufacturing device. The maintenance work analysis system 1 has an evaluation index acquisition function 11, a visualization interface function 12, and an analysis function 13. In addition, the semiconductor manufacturing device is a device that performs processing and inspection of semiconductor devices, for example, including process devices such as plasma processing devices, inspection devices, assembly devices, etc.

[0033] The evaluation index acquisition function 11 is a function for acquiring evaluation indexes to be analyzed as maintenance work. Examples of evaluation indexes include operation time involved in maintenance work, operation steps performed as maintenance work, the amount of contact (time, range, etc.) between the operator and a certain part (part) of the semiconductor manufacturing device, i.e., the contact amount (for example, in the case of wiping work, the wiping amount (wiping time, wiping range), the movement amount of the operator's viewpoint, the displacement of the operator's body part (hand, arm, elbow, etc.), i.e., the operation amount and trajectory, etc. The evaluation index acquisition function 11 is acquired from the measurement system 2 that measures the operator's activities during maintenance work.

[0034] The visualization interface function 12 is a function for providing the analysis and evaluation of the maintenance work to the operator and the user of the maintenance work analysis system 1. In the following description, the output that stimulates vision is mainly focused on visualization, but the present disclosure is not limited to this. As the output method for the operator and the user, it can also include a method other than visual appeal, such as sound.

[0035] The analysis function 13 analyzes the evaluation index. As a method of analysis, the evaluation index extracted from the maintenance operation is compared with the data that serves as the benchmark for the operation. Various methods can be used as the comparison method. For example, since information representing the activities of the operator in the maintenance operation is stored in the maintenance operation DB3, data set as the set value or target value of the data in the maintenance operation DB3 is extracted as data representing the evaluation benchmark and compared with the extracted evaluation index. In addition, the evaluation system 4 includes a semiconductor measuring device and a semiconductor measuring device. The evaluation system 4 obtains data representing the operating state of the semiconductor manufacturing device and measurement data of the semiconductor device after the semiconductor manufacturing device is operated. Sometimes the data obtained from the evaluation system 4 indicates an inappropriate state, and it can be inferred that the maintenance operation is unsuccessful. In this case, in the process of analyzing the evaluation index, it is also possible to determine the process that affects the result of the maintenance operation and the location of the components of the semiconductor manufacturing device.

[0036] (Structure of the maintenance work analysis system)

[0037] Figure 2 1 is a diagram showing an example of the configuration of the maintenance work analysis system 1. The maintenance work analysis system 1 includes a storage unit 14, a calculation unit 15, and an output unit 19.

[0038] The storage unit 14 stores operation information and result information. The operation information includes activity information indicating the activity of the operator who performs the maintenance operation. In addition, the result information includes information on the success or failure of the operator's maintenance operation.

[0039] The work information is acquired in the measurement system 2. The measurement system 2 acquires information indicating the worker's activity from various sensors such as cameras installed in the environment where the maintenance work is performed and positioning sensors installed on the worker's body, and sends the acquired information to the storage unit 14. The measurement system 2 will be described later.

[0040] The result information is obtained in the evaluation system 4. The evaluation system 4 includes a semiconductor measuring device and a semiconductor measuring device. The result information is data obtained by operating the semiconductor manufacturing device and measurement data related to the semiconductor manufactured by the semiconductor manufacturing device. For example, the following information is included: the result of the leak inspection of the semiconductor manufacturing device; the result of the foreign matter detection determined by the measurement of the vacuum degree reached and the measurement of the gas composition in the semiconductor manufacturing device; the result of the foreign matter detection attached to the semiconductor; the evaluation result of the contour shape of the semiconductor after the manufacturing process; the process performance as the evaluation result of the electrical characteristics, and the yield of the semiconductor after the manufacturing process. In addition, the result information may also include information such as the temperature, gas flow rate, pressure, frequency, RF power, etc. in the processing device during the operation of the semiconductor manufacturing device.

[0041] The computing unit 15 includes an information acquisition unit 16, an information analysis unit 17, and an information visualization unit 18. The information acquisition unit 16 acquires the operation information from the storage unit 14. The information analysis unit 17 analyzes the operation action of the operator based on the operation information. The information visualization unit 18 outputs the difference between the maintenance operation that serves as the reference and the maintenance operation performed by the operator. In addition, the information visualization unit 18 also performs visualization such as numerical display, graphing, and imaging to show the results of the analysis performed by the information analysis unit 17.

[0042] The output unit 19 outputs the visualized information output from the information visualization unit 18 to the operator of the maintenance work and the user of the maintenance work analysis system 1. The output unit 19 can be applied to a display, a portable terminal such as a smartphone, or an HMD (Head Mounted Display). In addition, when the output unit 19 is an HMD, AR content can also be displayed superimposed on an actual semiconductor manufacturing device.

[0043] In addition, the maintenance work analysis system 1 may be constituted by hardware such as a computer and a server, or may be constituted by a cloud service or the like.

[0044] (Structure of measurement system)

[0045] Figure 3 FIG. 2 is a diagram showing an example of the structure of the measurement system 2. Figure 3 , an example of a system for measuring the activity of an operator who performs maintenance work on a semiconductor manufacturing apparatus is shown.

[0046] The chamber 20 is one of the components constituting the semiconductor manufacturing apparatus. The operator 21 extends his arm into the chamber 20 and performs the operation while looking into the inside of the chamber 20. In the operation environment where the maintenance operation is performed, cameras 22 and 23 are provided. The camera 22 takes pictures so that the entire image of the operator 21 is within the field of view. In addition, the camera 23 takes pictures so that the chamber 20 and the hand of the operator 21 are within the field of view. As the cameras 22 and 23, a 3D camera (RGB-D sensor) can be used.

[0047] The HMD 25 is provided on the head of the operator 21. The HMD 25 is provided with an RGB-D sensor, a head position / orientation sensor (e.g., a tracking sensor), and a viewpoint sensor to detect the head and line of sight of the operator 21. In addition, the camera 25 provided on the head of the operator 21 can detect the line of sight of the operator 21.

[0048] A glove-shaped sensor 26 for estimating the movement of the hand based on the pressure distribution of the palm is provided on the hand of the operator 21. Information from the imaging devices 22, 23, 25, HMD 24, and sensor 26 is collected in a measurement PC 27.

[0049] Using the above-mentioned sensors, activity information indicating the activity of the operator 21 is collected. For example, information indicating the line of sight of the operator 21 is obtained by the cameras 22 and 25. Information indicating the position of the head of the operator 21 and the movement of the head (variation) is obtained by the camera 22 and the HMD 24. Information indicating the position of the fingers of the operator 21 and the movement of the fingers (variation) is obtained by the camera 23 and the sensor 26. Information indicating the working posture of the operator 21 is obtained by the camera 22. The activity information is obtained by the measurement PC 27 and stored in the storage unit 14 as work information. In addition, the activity information obtained from a skilled operator (hereinafter also referred to as a "skilled operator") can be used as a set value or a target value when performing work analysis, and is also stored in the maintenance work DB 3. The skilled operator work used as the set value or the target value is, for example, a maintenance work (= a successful work) with no leakage, foreign matter remaining, and a yield exceeding the required value, and is a work with an infinitely short work time.

[0050] The measurement system 2 is not limited to the above-described case. For example, as long as the operator 21 and the semiconductor manufacturing device can be photographed by at least one 3D camera, the activity information can be obtained. In addition, sensors other than the imaging device and the tracking sensor may also be used.

[0051] (Processing of maintenance work analysis)

[0052] Reference Figures 4 to 8 , the processing performed in the maintenance work analysis system is explained.

[0053] (Classification of maintenance work processes)

[0054] Figure 4 This is a diagram showing a process of associating maintenance work with worker activities. Figure 4 (a) is a diagram showing an example of classification information 171 for classifying maintenance work for each process. Maintenance work A includes a first component mounting process, a first component wiping process, a second component mounting process, a second component screwing process, a third component mounting process, a third component wiping process, and a third component screwing process. The information analysis unit 17 has in advance classification information 171 showing the relationship between maintenance work and the processes included in the maintenance work.

[0055] Figure 4 (b) is a diagram showing an example of the associated information 172 that associates the work object, which is the object of the maintenance work, with the activity of the operator. Figure 4 In addition to the classification information 171 of (a), Figure 4 According to the associated information 172 of (b), the operation is classified. In the associated information, when the left and right arms of the operator move in parallel toward an object (not limited to the operation object), it is classified as an installation process of an object. In addition, when the fingers move in parallel and one arm is fixed, and the operation object includes tools such as screws and bolts or wrenches, it is classified as a fastening process. In addition, when one arm of the operator moves in a circle within a given range and the object includes a plate-like component or an annular component, it is classified as a wiping operation.

[0056] Figure 4 (c) is a diagram showing an example of the relationship between the image data and the maintenance work process. The image data can be obtained from any one of the image pickup devices 22, 23, 25, and HMD 24. The data obtained from these image pickup devices may be combined.

[0057] The information analysis unit 17 uses the activity information for analysis and associates the video data with the work object of the maintenance work. For example, when it is detected that the viewpoint and the finger are within the range including the first component for a given period, it is determined that the object part is the first component. In a certain video data, it is determined that scene 1 (from the work start time hhmi1 to the work completion time hhmi2) and scene 2 (from the work start time hhmi3 to the work start time hhmi4) are operations on the first component.

[0058] Here, although the first component is operated in scene 1 and scene 2, the difference in the operation cannot be determined. Here, the information analysis unit 17 extracts the difference in the activity information between scene 1 and scene 2 while referring to the associated information 172. The information analysis unit 17 can extract the difference in the amount of movement of the operator's arm, and classify scene 1 as the installation process of the first component and scene 2 as the wiping process of the first component, thereby performing classification.

[0059] The work object of scene 3 is the second component, and the work object of scene 4 is the first screw. The information analysis unit 17 refers to the related information 172 and the order of the processes, and can classify scene 3 as the second component installation process and scene 4 as the second component screw tightening process.

[0060] In addition, the operation object of scene 5 and scene 6 is the third component. In addition, the operation object of scene 7 is the second screw. The information analysis unit 17 refers to the related information 172 and the order of the process information, and can classify scene 5 as the installation process of the third component, scene 6 as the wiping process of the third component, and scene 7 as the screw tightening process of the third component.

[0061] In this way, the image data can be analyzed using the activity information to associate the maintenance work process with the work target. Such association can also be performed using a classifier or by the user of the maintenance work analysis system 1 as annotation data.

[0062] In addition, the information analysis unit 17 uses at least one of the activity information as an evaluation index to analyze the operation action. In addition, the information analysis unit 17 analyzes the operation action by prompting a unique evaluation index of the operation object. In addition, the operation action refers to an activity (action) related to the maintenance operation (or the process included in the maintenance operation). When the activity information is used as an evaluation index, for example, the so-called primary information of the activity such as the position and change amount of the viewpoint, the position and change amount of the arm can be used. In addition, when using Figure 4 In the case of the associated information 172 shown in (b), for example, evaluation indicators specific to the work object, such as the installation speed of a certain object, the tightening speed of a screw, the area of ​​the wiped area, and the time for which the wiping was performed, can be used. These evaluation indicators can be derived from one-time information, for example. For example, with respect to a wiping operation, it is sometimes determined that it is preferable to wipe in one direction without reciprocating. In the case of using the wiping direction as an evaluation indicator in this way, the angular velocity distribution and its average velocity, velocity ratio, distribution deformation, etc. can be calculated and evaluated based on the movement trajectory of the hand, thereby deriving the wiping direction. In addition, by classifying the camera data and the process, the operation time spent on the process can also be used as an evaluation indicator.

[0063] In addition to the work in which the operator directly contacts the semiconductor manufacturing equipment, the timing and frequency of changing gloves, the timing and frequency of changing the cloth used for wiping, the timing and frequency of applying the cleaning liquid, etc. can also be used as evaluation indicators. Such evaluation indicators can be extracted by performing image processing such as object detection on the image data obtained by the imaging device.

[0064] In addition, the above description shows an example of a process of associating a maintenance work with an operator's action, and the present disclosure is not limited to this process.

[0065] (Analysis of maintenance work and process success)

[0066] Figure 5 This is a diagram showing information used for analysis by the information analysis unit. Figure 5 (a) is a diagram showing an example of measurement data obtained in the evaluation system 4. The measurement data 41 is the measurement during the process performed in the semiconductor manufacturing device and the evaluation result of the semiconductor device after the process. The measurement data 41 is stored in the storage unit 14 of the maintenance work analysis system 1 as result information including information related to the success of the maintenance work of the operator. The measurement data 41 includes at least one of the presence or absence of leakage, the amount of foreign matter, and the process performance / yield after maintenance as information related to the success of the maintenance work. The following is a specific description.

[0067] The item "leakage" indicates the presence or absence of leakage based on the results of the leak inspection performed during the process and the measurement of the vacuum degree achieved. The item "amount of foreign matter" is determined based on the measurement of the gas composition in the semiconductor manufacturing equipment and the results of the foreign matter detection attached to the semiconductor. The item "process performance" is determined based on the evaluation results of the contour shape of the semiconductor and the evaluation results of the electrical characteristics. The item "yield rate" is determined based on the yield rate of the semiconductor after the process.

[0068] The item "leakage" reached a normal value of vacuum degree aaaa [Pa], and no abnormality was detected by the leak test. Therefore, it was judged as no leakage. Regarding the item "amount of foreign matter", SUS was detected on the surface of the semiconductor, so it was judged as abnormal. The evaluation result of the item "process performance" was OK, which was judged as normal. The item "yield rate" was calculated as 89%, which was judged as normal.

[0069] Figure 5 (b) is a diagram showing an example of the history information 141 of the process performed in the semiconductor manufacturing device. Figure 5(c) is a diagram showing an example of advance information 142 indicating the content of the maintenance work performed in the conductor manufacturing device. The history information 141 and the advance information 142 are stored in the storage unit 14 as part of the work information. In addition, the history information 141 and the advance information 142 are common to semiconductor manufacturing devices and are also associated with the measurement data 41 (result information).

[0070] The process history record information 141 is information including the materials used and the manufacturing method. As the materials used, Si substrate, F-based gas, and Ar gas are shown. In addition, plasma etching is shown as the manufacturing method. In the case where multiple processes are performed, the history record information 141 may also include materials and manufacturing methods of other processes. In addition, as materials, materials other than substrates and gas types may be included, and as manufacturing methods, the manufacturing conditions of the host may also be included.

[0071] In addition, the prior information 142 includes information indicating maintenance work performed on the semiconductor manufacturing apparatus before the process and the operator thereof. Maintenance work A is performed by operator XX. When a plurality of maintenance work is performed, information indicating other maintenance work may also be included.

[0072] (Analysis of work actions)

[0073] The information analysis unit 17 combines the operator's operation information and result information to analyze the cause of the result information. In addition, the information analysis unit 17 uses the historical record information and the prior information to analyze the operation action. The information analysis unit 17 detects SUS on the substrate based on the measurement data 41, and determines that an abnormality has occurred with respect to the item "foreign matter amount". In addition, in the historical record information 141 included in the operation information, it is determined that no process using SUS is performed. According to the prior information 142, it is determined that the operator XX performed maintenance operation A on the semiconductor manufacturing device. The information analysis unit 17 determines that the cause of foreign matter detection is not the process but the maintenance operation A, and analyzes the operation action of the operator XX who performs the maintenance operation A.

[0074] Figure 6 This is a diagram showing an example of analysis of a work action performed by the information analysis unit 17 . Figure 6 (a) is a graph showing the operation time of each process included in the maintenance operation A. The horizontal axis shows the processes included in the maintenance operation A. The vertical axis shows the operation time. Here, the information analysis unit 17 also uses the activity information of the maintenance operation A performed by the skilled person from the maintenance operation DB3 and compares it with the operation action of the operator XX. In the figure, the dotted line graph shows the operation time of the skilled person, and the oblique line graph shows the operation time of the operator XX.

[0075] The information analysis unit analyzes the operation motion by focusing on the operation that is particularly related to the success or failure of the maintenance operation, i.e., the specific operation, among the operation objects. The specific operation is the wiping operation, and the trajectory and speed of the body part of the operator in the wiping operation are analyzed. The information analysis unit 17 compares the operation of the skilled worker with the operation of the operator XX. The information analysis unit 17 extracts the process whose operation time deviation from the operation of the skilled worker is greater than a given value based on a pre-set benchmark, for example. Here, it is determined that there is a large difference in the operation time of the wiping process of the third component. The information analysis unit 17 focuses on the third component of the chamber as the operation object.

[0076] Figure 6 (b) is a graph showing the distance between the third component and the operator's head. The vertical axis represents the distance between the third component and the operator's head, and the horizontal axis represents time. Here, the solid line represents the case of operator XX, the dotted line represents the case of the first skilled person, and the dashed line represents the case of the second skilled person. Since the solid line is separated from the dotted line and the dashed line, it can be seen that the trajectory of the operator XX's head is shown at a position away from the third component. In addition, as shown in area R1, in the case of a skilled person, there is no change in the position of the operator XX's head, but the position of the operator XX's head changes. It means that the moving speed of the head is relatively large.

[0077] The information analysis unit 17 analyzes the separation of the head and the third member as one of the factors for detecting foreign matter during the wiping step of the third member. The result of the analysis performed by the information analysis unit 17 is sent to the information visualization unit 18.

[0078] In this way, the information analysis unit 17 uses the operation information (measurement data 41, history information 141, prior information 142, activity information of skilled workers' operations, etc.) to analyze the maintenance operation of the operator XX. In addition, the analysis method is not limited to the objects described above. Sometimes other operations are extracted as specific operations. In addition, as a part of the body, parts other than the head can also be analyzed.

[0079] (Visualization of analysis results)

[0080] When the result information indicates failure, the information visualization unit 18 outputs information related to the operation and component that may be the cause. Based on the analysis result of the information analysis unit 17, the information visualization unit 18 visualizes the wiping process of the third component as the operation that may be the cause and notifies the operator and the user that the third component is the component that may be the cause, and sends the visualization result, i.e., the visualization result, to the output unit 19.

[0081] Figure 71 is a diagram showing an example of a visualization result displayed in the output unit 19. The display unit 191 of the output unit 19 includes information related to the operation and the component. The operation column 192 shows the operation process that is the cause of the result information. The process column 193 shows the component that is the cause. The operation column 192 shows the maintenance operation A, and the process column 193 shows the wiping process of the third component.

[0082] In addition, the feedback column 194 explains the factors analyzed for the operator and shows suggestions for improving the work. The feedback column 194 shows a text urging the operator to pay attention, so as to keep the head away from the third component and increase the possibility of noticing the foreign object during the work.

[0083] The visualization area 195 includes a display for providing visual feedback to the operator or user. Here, a scene including the operator 21 and the chamber 20 performing the wiping process is shown based on the image data. The head 196 of the operator 21 and the third member 197 are highlighted.

[0084] In addition, although the visualization method has been described, the present disclosure is not limited thereto. For example, the difference between the work of a skilled person and the work of an operator may be scored to evaluate the quality of the work of the operator.

[0085] The display unit 191 may be displayed on the HMD. It is also possible to accumulate analysis results of a certain worker to extract the tendency of work, and notify in real time of the parts and components of the body that may become a factor of failure when the work is being performed.

[0086] (Processing steps)

[0087] Figure 8 Detailed Description of the Invention This is a flowchart showing the analysis process performed in the maintenance work analysis system.

[0088] The information acquisition unit 16 acquires operation information of maintenance work performed in the semiconductor manufacturing apparatus (step S1). The operation information includes movement information of the operator and image data acquired by the image pickup device.

[0089] Next, the information analysis unit 17 refers to the image data and classifies the operator's actions for each process (step S2). The information analysis unit 17 also refers to classification information 171 which is information on the classification of the maintenance work for each process, the operator's actions, and association information 172 for specifying the process from the work object.

[0090] Next, the information analysis unit 17 detects whether there is an abnormality in the result information of the process performed in the semiconductor manufacturing device (step S3). If there is an abnormality (yes in step S3), the information analysis unit 17 combines the operation information of the operator with the result information to analyze the factors of the operation results (step S5). In the analysis of the factors, the operation information of the operator is compared with the information of the operation of the skilled worker. In addition, the analysis is performed with an eye on the specific operation that is judged to be highly related to the factors in the maintenance operation. The results of the analysis performed in the information analysis unit 17 are sent to the information visualization unit 18.

[0091] Next, the information visualization unit 18 refers to the analysis result and outputs information indicating the factors and the work (step S6). The information visualization unit 18 sends the visualization result to the output unit 19 for notification to the operator and the user. The output unit 19 outputs the visualization result (step S7).

[0092] In addition, when the result information does not indicate an abnormality (No in step S3), the information visualization unit 18 can also notify the operator that there is no abnormality based on the analysis based on the given evaluation index. In addition, the operation information can also be stored in the storage unit 14 as a skilled worker's operation for analysis.

[0093] (Function / Effect)

[0094] According to the present disclosure, the difference between the maintenance work (work of a skilled worker) and the maintenance work of each operator is fed back, or the work and parts that are prone to failure in the maintenance work are quantitatively and objectively extracted, so that the cause of the maintenance work failure can be found. Since the work movements of the operator's body parts such as sight, fingers, and posture are analyzed, even an inexperienced operator can achieve the same work quality as that of a skilled operator.

[0095] As described above, according to the present disclosure, useful information can be presented to a worker performing maintenance work.

[0096] As mentioned above, although embodiment of this invention was described, this invention is not limited to the said embodiment, Various changes can be made within the range which does not deviate from the summary of this invention.

[0097] The following aspects may be aspects of the present invention, but the present invention is not limited thereto.

[0098] (Method 1)

[0099] A maintenance operation analysis system analyzes operation actions in maintenance operations of a semiconductor manufacturing device, the maintenance operation analysis system being characterized in that it comprises: an information acquisition unit that acquires operation information including activity information representing the activities of an operator performing the maintenance operation; an information analysis unit that analyzes the operation actions of the operator based on the operation information; and an information visualization unit that outputs the difference between a maintenance operation serving as a benchmark and the maintenance operation performed by the operator.

[0100] (Method 2)

[0101] A maintenance operation analysis system according to method 1, wherein the information acquisition unit acquires result information including information related to the success or failure of the maintenance operation performed by the operator, the information analysis unit combines the operation information of the operator and the result information to analyze the causes of the result information, and the information visualization unit outputs information related to the operation and parts that may be the causes when the result information indicates failure.

[0102] (Method 3)

[0103] According to the maintenance operation analysis system described in method 1 or 2, the operation information includes historical record information of the process performed in the semiconductor manufacturing device and prior information indicating the content of the maintenance operation, and the information analysis unit uses the historical record information and the prior information to analyze the operation action.

[0104] (Method 4)

[0105] A maintenance work analysis system according to any one of methods 1 to 3, wherein the work information includes at least one information representing line of sight, head position / movement, finger position / movement, and work posture as the activity information, and the information analysis unit uses at least one information in the activity information as an evaluation indicator to analyze the work action.

[0106] (Method 5)

[0107] The maintenance work analysis system according to any one of aspects 1 to 4, wherein the information related to the success or failure of the maintenance work includes at least one of the presence or absence of leakage, the amount of foreign matter, and the process performance / yield after maintenance.

[0108] (Method 6)

[0109] A maintenance work analysis system according to any one of methods 1 to 5, wherein the information analysis unit obtains association information that associates an object for performing the maintenance work, i.e., a work object, with an activity of the operator, and analyzes the work action by providing a unique evaluation index through the work object.

[0110] (Method 7)

[0111] The maintenance work analysis system according to any one of aspects 1 to 6, wherein the information analysis unit analyzes the work motion by focusing on a specific work that is particularly related to the success or failure of the maintenance work among the work objects.

[0112] (Method 8)

[0113] The maintenance work analysis system according to any one of aspects 1 to 7, wherein the specific work is a wiping work, and a trajectory and a speed of a body part of the worker during the wiping work are analyzed.

[0114] (Method 9)

[0115] A maintenance operation analysis method analyzes operation actions in the maintenance operation of a semiconductor manufacturing device, and the maintenance operation analysis method is characterized in that it has the following steps: an information acquisition step, acquiring operation information including activity information representing the activities of an operator performing the maintenance operation; an information analysis step, analyzing the operation actions of the operator based on the operation information; and an information visualization step, outputting the difference between a maintenance operation serving as a benchmark and the maintenance operation performed by the operator.

[0116] -Description of Reference Numerals-

[0117] 1: Maintenance work analysis system, 2: Measurement system, 3: Maintenance work DB, 4: Evaluation system, 11: Acquisition function, 12: Visualization interface function, 13: Analysis function, 14: Storage unit, 15: Calculation unit, 16: Information acquisition unit, 17: Information analysis unit, 18: Information visualization unit, 19: Output unit, 20: Chamber, 21: Operator, 22: Camera device, 23: Camera device, 25: Camera device, 26: Sensor, 41: Measurement data, 141: History information, 142: Prior information, 171: Classification information, 172: Related information, 191: Display unit, 192: Work column, 193: Process column, 194: Feedback column, 195: Visualization area, 196: Head, 197: Third component.

Claims

1. A maintenance work analysis system for analyzing operation actions in maintenance work of a semiconductor manufacturing device, wherein the maintenance work analysis system is characterized by: an information acquisition unit that acquires operation information including activity information indicating an activity of an operator who performs the maintenance operation; an information analysis unit that analyzes the operator's work action based on the work information; and The information visualization unit outputs a difference between a maintenance operation serving as a reference and the maintenance operation performed by the operator.

2. The maintenance work analysis system according to claim 1, wherein: The information acquisition unit acquires result information including information related to success or failure of the maintenance work by the operator. The information analysis unit combines the operation information of the operator and the result information to analyze factors of the result information. The information visualization unit outputs information on a work and a component that may be a cause when the result information indicates a failure.

3. The maintenance work analysis system according to claim 1, wherein: The operation information includes history information of processes performed in the semiconductor manufacturing apparatus and advance information indicating the content of maintenance operations. The information analysis unit analyzes the work action using the history information and the prior information.

4. The maintenance work analysis system according to claim 1, wherein: The work information includes, as the activity information, at least one of information indicating a line of sight, a head position / movement, a finger position / movement, and a work posture. The information analysis unit analyzes the work action using at least one piece of information in the activity information as an evaluation index.

5. The maintenance work analysis system according to claim 2, wherein: The information related to the success or failure of the maintenance work includes at least one of the presence or absence of leakage, the amount of foreign matter, and the process performance / yield after maintenance.

6. The maintenance work analysis system according to claim 1, wherein: The information analysis unit acquires association information associating a work object, which is a subject for performing the maintenance work, with an activity of the worker, and analyzes the work action by presenting a unique evaluation index with the work object.

7. The maintenance work analysis system according to claim 6, wherein: The information analysis unit analyzes the work motion by focusing on a specific work that is particularly related to the success or failure of a maintenance work among the work objects.

8. The maintenance work analysis system according to claim 7, wherein: The specific operation is a wiping operation, The trajectory and speed of the body part of the operator during the wiping operation are analyzed.

9. A maintenance work analysis method for analyzing operation actions in maintenance work of a semiconductor manufacturing device, wherein the maintenance work analysis method comprises the following steps: an information acquisition step of acquiring operation information including activity information indicating an activity of an operator performing the maintenance operation; An information analysis step of analyzing the operator's operation according to the operation information; as well as The information visualization step outputs a difference between the maintenance work serving as a reference and the maintenance work performed by the operator.

Images