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

Abstract

The purpose of the present invention is to provide technical features for presenting more useful information to a maintenance work worker.　The present invention provides a maintenance work analysis system for analyzing a work operation in maintenance work for a semiconductor manufacturing apparatus, the maintenance work analysis system comprising: an information acquisition unit for acquiring work information including movement information indicating the movement of a worker who performs the maintenance work; an information analysis unit for analyzing the work operation of the worker from the work information; and an information visualization unit for outputting the difference between a reference maintenance work and the maintenance work performed by the worker.

Description

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

[0001] The present invention relates to a maintenance work analysis system and a maintenance work analysis method for semiconductor manufacturing equipment.

[0002] Semiconductor manufacturing equipment has a more complex configuration than general manufacturing equipment. Furthermore, the semiconductor manufacturing equipment significantly affects the yield of the semiconductor devices manufactured by the equipment. Therefore, maintenance work, such as inspection and servicing of semiconductor manufacturing equipment, requires workers to have extensive knowledge and skills. Therefore, many technologies have been developed to reduce the burden on workers performing maintenance work on semiconductor manufacturing equipment.

[0003] Patent Document 1 aims to provide a technology that can shorten the time required for device maintenance, and discloses the following content regarding a user interface and a maintenance guidance method: "A user interface 52 having an operation screen on which predetermined information about the device is displayed and which is used for predetermined operations, and an operation unit for operating the operation screen, has a maintenance mode on the operation screen for performing device maintenance, and in the maintenance mode, a maintenance screen 101 corresponding to a predetermined maintenance item among a plurality of maintenance items for which maintenance operations are stored in a storage unit 53 is displayed on the operation screen, and the maintenance content of the maintenance item is displayed as a screen 101 for each procedure based on the information in the storage unit 53, and each screen 101 for each procedure displays an explanation 105 of the procedure and an image 106 indicating the maintenance location."

[0004] Patent Document 2 addresses the issue of visually providing workers with information they require or want to be made known to them, and discloses the following as a support information display method, a maintenance support method for a substrate processing apparatus, a support information display control device, a substrate processing system, and a program: "The display control device 40 of the substrate processing system 100A acquires an image of a predetermined portion of the substrate processing apparatus to be maintained through a camera provided in the HMD 30, in order to display support information related to maintenance in real time on a head-mounted display (HMD) 30 worn by the worker while the worker is performing maintenance on the substrate processing apparatus, estimates support information related to the predetermined portion contained in the acquired image from information stored in a database, converts the estimated support information into an image, and displays the created image on the HMD 30, thereby allowing the worker to visually recognize the support information."

[0005] JP 2019-016759 A JP 2014-164482 A

[0006] The success or failure of maintenance work on semiconductor manufacturing equipment can sometimes be determined by the presence or absence of a large amount of foreign matter during the semiconductor manufacturing process after the maintenance work, which can require the maintenance work to be redone. One reason for this is that the movements of all the fingers and fingers of the maintenance workers have not been fully specified. Specifically, work movements such as line of sight, finger position and movements, and working posture during maintenance work are left to the judgment and experience of each worker, and it is predicted that significant individual differences due to the worker's level of proficiency affect the success or failure of the maintenance work. However, because the correlation between individual differences among workers and the success or failure of the maintenance work, such as the presence or absence of leaks, the amount of foreign matter, and the process performance / yield after the maintenance work, has not been fully verified, the causes of maintenance work failures are not clearly identified, and feedback to the workers and narrowing down of tasks and components that are prone to maintenance failures are insufficient. Patent Documents 1 and 2 also do not fully address these issues. Therefore, the present invention aims to provide a technology that can present more useful information to maintenance workers.

[0007] In order to solve the above problems, one representative maintenance work analysis system of the present invention is a maintenance work analysis system that analyzes work movements during maintenance work on semiconductor manufacturing equipment, and has an information acquisition unit that acquires work information including movement information that indicates the movements of a worker performing the maintenance work, an information analysis unit that analyzes the work movements of the worker from the work information, and an information visualization unit that outputs the differences between a reference maintenance work and the maintenance work performed by the worker.

[0008] According to the present invention, it is possible to present more useful information to maintenance workers. Problems, configurations, and effects other than those described above will become apparent from the following description of the preferred embodiments of the present invention.

[0009] FIG. 1 is a diagram showing a case in which a maintenance work analysis system according to an embodiment is utilized. FIG. 2 is a diagram showing an example of the configuration of the maintenance work analysis system. FIG. 3 is a diagram showing an example of the configuration of a measurement system. FIG. 4 is a diagram showing a process of associating maintenance work with worker movements. FIG. 5 is a diagram showing information used for analysis by an information analysis unit. FIG. 6 is a diagram showing an example of analysis of work movements performed by the information analysis unit. FIG. 7 is a diagram showing an example of visualization results displayed on an output unit. FIG. 8 is a flowchart showing analysis processing performed in the maintenance work analysis system.

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. Note that the present invention is not limited to this embodiment. In addition, in the description of the drawings, the same parts are designated by the same reference numerals.

[0011] (Application example of the maintenance work analysis system) Fig. 1 is a diagram showing a case where a maintenance work analysis system according to an embodiment is utilized. Fig. 1 shows the relationship between a maintenance work analysis system 1, a measurement system 2, a maintenance work DB (database) 3, and an evaluation system 4.

[0012] The maintenance work analysis system 1 is a system for analyzing work operations during maintenance work for semiconductor manufacturing equipment. The maintenance work analysis system 1 has an evaluation index acquisition function 11, a visualization interface function 12, and an analysis function 13. Note that the semiconductor manufacturing equipment is equipment that processes and inspects semiconductor devices, and includes, for example, process equipment such as plasma processing equipment, inspection equipment, and assembly equipment.

[0013] The evaluation index acquisition function 11 is a function for acquiring evaluation indexes to be used in analyzing maintenance work. Examples of evaluation indexes include the work time related to the maintenance work, the work process performed as part of the maintenance work, the amount of contact (time, area, etc.) that the worker made with a certain part (part) of the semiconductor manufacturing equipment (for example, if wiping work is included, the amount of wiping (time spent wiping, area wiped), the amount of movement of the worker's viewpoint, and the amount of work and trajectory that are the displacement of parts of the worker's body (hands, arms, elbows, etc.). The evaluation index acquisition function 11 is acquired from the measurement system 2 that measures the movements of the worker during maintenance work.

[0014] The visualization interface function 12 is a function that presents the analysis and evaluation of the maintenance work to workers and users of the maintenance work analysis system 1. The following description focuses mainly on visualization and describes the case of output that stimulates the visual sense, but the present disclosure is not limited to this. Methods of output to workers and users may also include methods that appeal to non-visual sensations, such as audio.

[0015] The analysis function 13 analyzes the evaluation index. The analysis is performed by comparing the evaluation index extracted from the maintenance work with the data serving as the work standard. Various methods for comparison are possible. For example, since the maintenance work DB 3 stores information indicating the movements of the worker during the maintenance work, data serving as the set value or target value in the maintenance work DB 3 is extracted as data indicating the evaluation standard, and the extracted evaluation index is compared. The evaluation system 4 also includes a semiconductor metrology device and a semiconductor measuring device. The evaluation system 4 acquires data indicating the status of the semiconductor manufacturing equipment during operation and measurement data of the semiconductor equipment after the semiconductor manufacturing equipment is operated. The data acquired from the evaluation system 4 may indicate an inappropriate state, suggesting that the maintenance work was not successful. In such cases, the analysis of the evaluation index may determine the process and the location of the semiconductor manufacturing equipment components that affected the results of the maintenance work.

[0016] 2 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.

[0017] The storage unit 14 stores work information and result information. The work information includes movement information indicating the movement of a worker performing maintenance work. The result information includes information regarding the success or failure of the worker's maintenance work.

[0018] The work information is acquired by the measurement system 2. The measurement system 2 acquires information indicating the movement of the worker from various sensors such as cameras installed in the environment where the maintenance work is performed and from positioning sensors installed on the body of the worker, and sends the acquired information to the storage unit 14. The measurement system 2 will be described later.

[0019] The result information is acquired by the evaluation system 4. The evaluation system 4 includes a semiconductor metrology device and a semiconductor measurement device. The result information is data acquired by operating the semiconductor manufacturing equipment and measurement data related to the semiconductors manufactured by the semiconductor manufacturing equipment. For example, the result information includes the results of a leak check performed on the semiconductor manufacturing equipment, measurements of the ultimate vacuum, results of foreign matter detection determined by measuring the gas composition inside the semiconductor manufacturing equipment, results of foreign matter detection on the semiconductor, evaluation results of the profile shape of the semiconductor after manufacturing processing, process performance which is the evaluation results of electrical characteristics, and semiconductor yield after manufacturing processing. The result information can also include information such as the temperature, gas flow rate, pressure, frequency, and RF power inside the processing equipment of the semiconductor manufacturing equipment while it is operating.

[0020] The calculation 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 work information from the storage unit 14. The information analysis unit 17 analyzes the work actions of the worker from the work information. The information visualization unit 18 outputs the difference between the reference maintenance work and the maintenance work performed by the worker. In addition, the information visualization unit 18 visualizes the results of the analysis performed by the information analysis unit 17 by displaying numerical values, creating graphs, visualizing images, etc.

[0021] The output unit 19 outputs the visualized information output from the information visualization unit 18 to the maintenance worker and the user of the maintenance work analysis system 1. The output unit 19 can be a display, a mobile terminal such as a smartphone, or a head-mounted display (HMD). Furthermore, when the output unit 19 is an HMD, it can also display AR content superimposed on the actual semiconductor manufacturing equipment.

[0022] The maintenance work analysis system 1 may be configured by hardware such as a computer and a server, or may be configured by a cloud service or the like.

[0023] (Configuration of Measurement System) Fig. 3 is a diagram showing an example of the configuration of the measurement system 2. Fig. 3 shows an example of a system for measuring the movements of a worker performing maintenance work on semiconductor manufacturing equipment.

[0024] The chamber 20 is one of the components that make up the semiconductor manufacturing equipment. A worker 21 works by stretching his / her arm into the chamber 20 and peering into the inside of the chamber 20. Imaging devices 22 and 23 are installed in the work environment where the maintenance work is performed. The imaging device 22 captures an image of the worker 21 so that the entire image is captured within its angle of view. The imaging device 23 captures an image of the chamber 20 and the hands of the worker 21 so that the image is captured within its angle of view. 3D cameras (RGB-D sensors) can be used as the imaging devices 22 and 23.

[0025] An HMD 25 is attached to the head of the worker 21. The HMD 25 is equipped with an RGB-D sensor, a head position / orientation sensor (e.g., a tracking sensor), and a viewpoint sensor, and detects the head and line of sight of the worker 21. In addition, the imaging device 25 attached to the head of the worker 21 can detect the line of sight of the worker 21.

[0026] A glove-shaped sensor 26 that estimates hand movement from, for example, the pressure distribution of the palm of the hand is attached to the hand of the worker 21. Information from the image capture devices 22, 23, 25, HMD 24, and sensor 26 is collected in a measurement PC 27.

[0027] Using the above-described sensors, movement information indicating the movement of the worker 21 is collected. For example, information indicating the line of sight of the worker 21 is acquired by the imaging devices 22 and 25. Information indicating the head position and head movement (variation amount) of the worker 21 is acquired by the imaging device 22 and HMD 24. Information indicating the hand and finger position and finger movement (variation amount) of the worker 21 is acquired by the imaging device 23 and sensor 26. Information indicating the working posture of the worker 21 is acquired by the imaging device 22. The movement information is acquired by the measurement PC 27 and stored in the memory unit 14 as work information. In addition, the movement information acquired from a skilled worker (hereinafter also referred to as "skilled worker") 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 worker work used as a set value or a target value is, for example, maintenance work that is free of leaks or remaining foreign matter and has a yield exceeding the required value (= successful work) and has an extremely short work time.

[0028] The measurement system 2 is not limited to the above-described case. For example, as long as at least one 3D camera can capture images of the worker 21 and the semiconductor manufacturing equipment, movement information can be acquired. Sensors other than the imaging device and tracking sensor may also be used.

[0029] (Maintenance Work Analysis Processing) The processing performed in the maintenance work analysis system will be described with reference to FIGS.

[0030] (Classification of Maintenance Work Processes) Fig. 4 is a diagram showing a process for associating maintenance work with the movements of a worker. Fig. 4(a) is a diagram showing an example of classification information 171 for classifying maintenance work by process. This shows that maintenance work A includes a process of installing a first component, a process of wiping the first component, a process of installing a second component, a process of screwing the second component, a process of installing a third component, a process of wiping the third component, and a process of screwing the third component. The information analysis unit 17 thus stores in advance classification information 171 that indicates the relationship between maintenance work and the processes included in the maintenance work.

[0031] FIG. 4B is a diagram showing an example of linking information 172 linking the work object, which is the target of maintenance work, with the worker's movements. The information analysis unit 17 acquires the linking information 172 in FIG. 4B in addition to the classification information 171 in FIG. 4A and performs classification. In the linking information, if the worker's left and right arms move parallel to a certain object (not limited to the work object), the work is classified as an installation process of the object. Furthermore, if the fingers move parallel and one arm is fixed, and the work object includes tools such as screws and bolts or wrenches, the work is classified as a fastening process. Furthermore, if one of the worker's arms moves circularly within a predetermined range and the object includes a plate-shaped or ring-shaped member, the work is classified as a wiping work.

[0032] 4C is a diagram showing an example of association between imaging data and maintenance work processes. The imaging data can be acquired from any of the imaging means, i.e., the imaging devices 22, 23, 25, and the HMD 24. The imaging data may also be a combination of data acquired from these imaging means.

[0033] The information analysis unit 17 analyzes the movement information and associates the captured image data with the maintenance work target. For example, if it detects that the viewpoint and fingers are located within a range including the first part for a predetermined period of time, it determines that the target location is the first part. Among certain captured image data, scene 1 (from the work arrival time hhmi1 to the work completion time hhmi2) and scene 2 (from the work arrival time hhmi3 to the work arrival time hhmi4) are determined to be operations on the first part. Here, although work is performed on the first part in scenes 1 and 2, it is not possible to determine the differences between the work. Here, the information analysis unit 17 extracts differences in the movement information between scenes 1 and 2 while referring to the linking information 172. The information analysis unit 17 extracts differences in the amount of movement of the worker's arm and can distinguish and classify scene 1 as the first part installation process and scene 2 as the first part wiping process.

[0034] Furthermore, in scene 3, the work target is the second part, and in scene 4, the work target is the first screw. The information analysis unit 17 refers to the linking information 172 and the order of the processes, etc., and can classify scene 3 as a process for attaching the second part, and scene 4 as a process for tightening a screw for the second part. Furthermore, in scenes 5 and 6, the work target is the third part. Furthermore, in scene 7, the work target is the second screw. The information analysis unit 17 refers to the linking information 172 and information such as the order of the processes, and can classify scene 5 as a process for attaching the third part, scene 6 as a process for wiping the third part, and scene 7 as a process for tightening a screw for the third part.

[0035] In this way, the imaging data can be analyzed using the motion information to associate the maintenance work process with the work target location. Such association can be performed using a classifier, or can be performed by the user of the maintenance work analysis system 1 as annotation data.

[0036] The information analysis unit 17 also analyzes the work motions using at least one piece of movement information as an evaluation index. Additionally, the information analysis unit 17 analyzes the work motions by presenting evaluation indexes specific to the work object. The work motions refer to movements (motions) associated with the maintenance work (or the processes included in the maintenance work). When using the movement information as an evaluation index, it is possible to use so-called primary movement information, such as the viewpoint position and amount of movement, and the arm position and amount of movement. Furthermore, when using the linking information 172 shown in FIG. 4( b), it is possible to use evaluation indexes specific to the work object, such as the installation speed of an object, the screw tightening speed, the area of ​​the wiped area, and the wiping time. These evaluation indexes can be derived from, for example, the primary information. For example, in wiping work, it may be determined that wiping in one direction without reciprocating is desirable. When using the wiping direction as an evaluation index, the wiping direction can be derived by calculating and evaluating the angular velocity distribution, its average velocity, velocity ratio, distribution distortion, etc. from the hand movement trajectory. Furthermore, by classifying the imaging data and the processes, it becomes possible to use the work time required to perform a process as an evaluation index. In addition to the work in which the worker directly touches the semiconductor manufacturing equipment, it is also possible to use the timing and frequency of changing gloves, the timing and frequency of changing cloths used for wiping, the timing and frequency of applying cleaning liquid, etc. as evaluation indexes. Such evaluation indexes can be extracted, for example, by performing image processing such as object detection on the imaging data acquired by the imaging device.

[0037] The above description shows an example of a process for associating a maintenance task with a worker's action, and the present disclosure is not limited to this process.

[0038] (Analysis of Maintenance Work and Process Success or Failure) FIG. 5 is a diagram showing information used for analysis by the information analysis unit. FIG. 5(a) is a diagram showing an example of measurement data acquired by the evaluation system 4. The measurement data 41 is the measurement results during a process performed in the semiconductor manufacturing equipment and the evaluation results of the semiconductor device after the process. The measurement data 41 is stored in the memory unit 14 of the maintenance work analysis system 1 as result information including information regarding the success or failure of the maintenance work performed by the worker. The measurement data 41 includes at least one of the presence or absence of a leak, the amount of foreign matter, and the process performance / yield after maintenance as information regarding the success or failure of the maintenance work. A specific description will be given below.

[0039] The "Leak" item indicates whether or not there is a leak based on the results of leak checks performed during the process and measurements of the ultimate vacuum level. The "Amount of Foreign Matter" item is determined based on measurements of the gas composition inside the semiconductor manufacturing equipment and the results of detecting foreign matter adhering to the semiconductor. The "Process Performance" item is determined based on the evaluation results of the semiconductor profile shape and electrical characteristics. The "Yield" item is determined based on the yield of semiconductors after the process.

[0040] For the item "Leakage," the ultimate vacuum of aaaa [Pa] was a normal value, and no abnormalities were detected by the leak check. Therefore, it was determined that there was no leakage. For the item "Foreign matter amount," SUS was detected on the surface of the semiconductor, so it was determined to be abnormal. For the item "Process performance," the evaluation result was acceptable, and it was determined to be normal. For the item "Yield," it was calculated to be 89%, and it was determined to be normal.

[0041] Fig. 5(b) is a diagram showing an example of history information 141 of processes performed in semiconductor manufacturing equipment. Fig. 5(c) is a diagram showing an example of advance information 142 indicating the contents of maintenance work performed in the conductor manufacturing equipment. The history information 141 and advance information 142 are stored as part of work information in the storage unit 14. The history information 141 and advance information 142 are common to the semiconductor manufacturing equipment, and are also associated with the measurement data 41 (result information).

[0042] The process history information 141 is information including the materials used and the manufacturing method. The materials used are shown to be a Si substrate, an F-based gas, and an Ar gas. Furthermore, the manufacturing method is shown to be plasma etching. When multiple processes are performed, the history information 141 may also include the materials and manufacturing methods of other processes. Furthermore, the materials may include materials other than the substrate and gas type, and the manufacturing method may include the main manufacturing conditions. Furthermore, the prior information 142 includes information indicating the maintenance work performed on the semiconductor manufacturing equipment and the worker who performed it before the process was performed. Maintenance work A is performed by worker XX. When multiple maintenance work is performed, information indicating other maintenance work may also be included.

[0043] (Analysis of Work Actions) The information analysis unit 17 combines the worker's work information and result information to analyze the causes of the result information. The information analysis unit 17 also analyzes the work actions using history information and prior information. The information analysis unit 17 determines from the measurement data 41 that SUS has been detected on the substrate and that an abnormality has occurred in the item "foreign matter amount." Furthermore, the history information 141 included in the work information reveals that no process using SUS has been performed. The prior information 142 reveals that maintenance work A has been performed on the semiconductor manufacturing equipment by worker XX. The information analysis unit 17 determines that the cause of the foreign matter detection is maintenance work A, not the process, and analyzes the work actions of worker XX performing maintenance work A.

[0044] FIG. 6 is a diagram showing an example of the analysis of work movements performed by the information analysis unit 17. FIG. 6(a) is a diagram showing the work time for each process included in maintenance work A. The horizontal axis shows the separate processes included in maintenance work A. The vertical axis shows the work time. Here, the information analysis unit 17 also uses movement information for maintenance work A performed by an expert from the maintenance work DB 3 to compare it with the work movements of worker XX. In the figure, the dotted line graph shows the work time of the expert, and the diagonal line graph shows the work time of worker XX.

[0045] The information analysis unit analyzes the work movements, focusing on a specific task among the work objects, which is a task that is particularly related to the success or failure of the maintenance work. The specific task is a wiping task, and analyzes the trajectory and speed of the worker's body parts during the wiping task. The information analysis unit 17 compares the work of the skilled worker with the work of worker XX. For example, based on a preset standard, the information analysis unit 17 extracts processes whose deviation from the work time of the skilled worker is equal to or greater than a predetermined value. Here, it is found that there is a large difference in the work time for the wiping process of the third component. The information analysis unit 17 focuses on the third component of the chamber, which is the work object.

[0046] FIG. 6(b) is a diagram showing the distance between the third part and the worker's head. The vertical axis represents the distance between the third part and the worker's head, and the horizontal axis represents time. Here, the solid line represents the case of worker XX, the dotted line represents the case of the first expert, and the dashed line represents the case of the second expert. Since the solid line is separated from the dotted and dashed lines, it can be seen that the trajectory of worker XX's head is shown at a position that is distanced from the third part. Furthermore, as shown in region R1, while there is no fluctuation in the case of the expert, the position of worker XX's head fluctuates. This indicates that the speed of head movement is high.

[0047] The information analysis unit 17 analyzes that one of the factors that led to the detection of the foreign object was that the head was separated from the third part during the wiping process of the third part. The results of the analysis performed by the information analysis unit 17 are sent to the information visualization unit 18.

[0048] In this way, the information analysis unit 17 analyzes the maintenance work of worker XX using the work information (measurement data 41, history information 141, advance information 142, movement information of skilled worker work, etc.). Note that the method of analysis is not limited to the one described above. Other work may be extracted as the specific work. Furthermore, analysis may be performed on body parts other than the head.

[0049] (Visualization of Analysis Results) When the result information indicates a failure, the information visualization unit 18 outputs information about the operation and part that may be the cause. Based on the analysis results of the information analysis unit 17, the information visualization unit 18 visualizes the wiping process of the third part as the operation that may be the cause and the third part as the part that may be the cause to notify the worker and the user, and sends the visualization results that are the results of the visualization to the output unit 19.

[0050] 7 is a diagram showing an example of the visualization result displayed on the output unit 19. The display unit 191 of the output unit 19 includes information related to the work and the parts. The work column 192 indicates the work process that caused the result information. The process column 193 indicates the part that caused the cause. The work column 192 indicates maintenance work A, and the process column 193 indicates the wiping process for the third part.

[0051] The feedback section 194 explains the analyzed factors to the worker and provides advice for improving the work. The feedback section 194 displays a message that the worker's head was away from the third part and a message that calls for attention to increase the likelihood of noticing foreign objects while working.

[0052] The visualization area 195 also includes a display for providing visual feedback to the operator or user. Here, a scene including the operator 21 performing the wiping process and the chamber 20 is shown based on the imaging data. The head 196 of the operator 21 and the third part 197 are also displayed in an emphasized manner.

[0053] Although the visualization method has been described, the present disclosure is not limited to this. For example, the difference between the work of an expert and the work of a worker may be scored to evaluate the quality of the worker's work. The display unit 191 may also display the results on an HMD. It is also possible to accumulate the analysis results of a certain worker, extract work trends, and notify the worker of body parts or parts that may be the cause of failure when performing work in real time.

[0054] (Processing Procedure) FIG. 8 is a flowchart showing the analysis processing performed in the maintenance work analysis system 1.

[0055] The information acquisition unit 16 acquires work information on maintenance work performed on semiconductor manufacturing equipment (step S1). The work information includes information on the movement of the worker and image data acquired by the imaging device.

[0056] Next, the information analysis unit 17 refers to the image data and classifies the worker's actions by process (step S2). The information analysis unit 17 also refers to classification information 171, which is information that classifies the maintenance work by process, and linking information 172, which identifies the process from the worker's actions and the work target.

[0057] Next, the information analysis unit 17 detects whether there is an abnormality in the result information of the process performed in the semiconductor manufacturing equipment (step S3). If there is an abnormality (Yes in step S3), the information analysis unit 17 combines the worker's work information and the result information to analyze the cause of the work result (step S5). In analyzing the cause, the worker's work information is compared with the information on the skilled worker's work. Furthermore, the analysis focuses on specific maintenance work that is determined to be closely related to the cause. The results of the analysis performed by the information analysis unit 17 are sent to the information visualization unit 18.

[0058] Next, the information visualization unit 18 refers to the analysis results and outputs information indicating the causes and tasks (step S6). The information visualization unit 18 sends the visualized results to the output unit 19 to notify the workers and users. The output unit 19 outputs the visualized results (step S7).

[0059] If the result information does not indicate an abnormality (No in step S3), the information visualization unit 18 may perform an analysis based on a predetermined evaluation index and then notify the worker that no abnormality is found. Also, the work information may be stored in the storage unit 14 as an expert work and used for analysis.

[0060] (Actions and Effects) According to the present disclosure, the causes of maintenance work failures can be identified by providing feedback on the differences between the standard maintenance work (work by an expert) and each worker's maintenance work, and by quantitatively and objectively identifying tasks and parts that are prone to failure. Because factor analysis is performed on the work movements of the worker's body parts, such as line of sight, fingers, and posture, even inexperienced workers can achieve work quality equivalent to that of an expert. In this way, according to the present disclosure, it is possible to present more useful information to maintenance workers.

[0061] Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, and various modifications are possible within the scope of the gist of the present invention.

[0062] The following are embodiments that may be included in the present invention, but the present invention is not limited to these. (Aspect 1) A maintenance work analysis system for analyzing work movements in maintenance work for semiconductor manufacturing equipment, comprising: an information acquisition unit that acquires work information including movement information that indicates the movements of a worker performing the maintenance work; an information analysis unit that analyzes the work movements of the worker from the work information; and an information visualization unit that outputs differences between a reference maintenance work and the maintenance work performed by the worker. (Aspect 2) The maintenance work analysis system according to Aspect 1, wherein the information acquisition unit acquires result information including information regarding the success or failure of the maintenance work performed by the worker, the information analysis unit combines the work information of the worker with the result information to analyze factors in the result information, and the information visualization unit, when the result information indicates a failure, outputs information regarding the work and parts that may be contributing to the failure. (Aspect 3) The maintenance work analysis system according to Aspect 1 or 2, wherein the work information includes history information of processes performed in the semiconductor manufacturing equipment and prior information indicating the content of the maintenance work, and the information analysis unit analyzes the work actions using the history information and the prior information. (Aspect 4) The maintenance work analysis system according to any one of Aspects 1 to 3, wherein the work information includes, as the movement information, information indicating at least one of line of sight, head position and movement, hand and finger position and movement, and work posture, and the information analysis unit analyzes the work actions using at least one of the movement information as an evaluation index. (Aspect 5) 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 a leak, the amount of foreign matter, and process performance / yield after maintenance.(Aspect 6) The maintenance work analysis system according to any one of Aspects 1 to 5, wherein the information analysis unit acquires linking information linking a work object, which is a target for the maintenance work, with the movements of the worker, and analyzes the work movements by presenting an evaluation index specific to the work object. (Aspect 7) The maintenance work analysis system according to any one of Aspects 1 to 6, wherein the information analysis unit analyzes the work movements by focusing on a specific work among the work objects, which is work that particularly relates to the success or failure of the maintenance work. (Aspect 8) The maintenance work analysis system according to any one of Aspects 1 to 7, wherein the specific work is wiping work, and wherein the maintenance work analysis system analyzes the trajectories and speeds of body parts of the worker during the wiping work. (Aspect 9) A maintenance work analysis method for analyzing work movements during maintenance work on semiconductor manufacturing equipment, comprising: an information acquisition step for acquiring work information including movement information indicating the movements of a worker performing the maintenance work; an information analysis step for analyzing the work movements of the worker from the work information; and an information visualization step for outputting differences between a reference maintenance work and the maintenance work performed by the worker.

[0063] 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 Memory unit, 15 Calculation unit, 16 Information acquisition unit, 17 Information analysis unit, 18 Information visualization unit, 19 Output unit, 20 Chamber, 21 Worker, 22 Imaging device, 23 Imaging device, 25 Imaging device, 26 Sensor, 41 Measurement data, 141 History information, 142 Advance information, 171 Classification information, 172 Linking information, 191 Display unit, 192 Work column, 193 Process column, 194 Feedback column, 195 Visualization area, 196 Head, 197 Third part

Claims

1. A maintenance work analysis system for analyzing work movements in maintenance work for semiconductor manufacturing equipment, comprising: an information acquisition unit that acquires work information including movement information that indicates the movements of a worker performing the maintenance work; an information analysis unit that analyzes the work movements of the worker from the work information; and an information visualization unit that outputs the differences between a reference maintenance work and the maintenance work performed by the worker.

2. A maintenance work analysis system as described in claim 1, characterized in that: the information acquisition unit acquires result information including information regarding the success or failure of the maintenance work by the worker; the information analysis unit combines the work information of the worker with the result information to analyze the causes of the result information; and when the result information indicates a failure, the information visualization unit outputs information regarding the work and parts that may be the cause.

3. A maintenance work analysis system as described in claim 1, wherein the work information includes history information of processes performed in the semiconductor manufacturing equipment and advance information indicating the contents of the maintenance work, and the information analysis unit analyzes the work operations using the history information and the advance information.

4. A maintenance work analysis system as described in claim 1, wherein the work information includes, as the movement information, information indicating at least one of gaze, head position / movement, hand and finger position / movement, and work posture, and the information analysis unit analyzes the work movements using at least one of the movement information as an evaluation index.

5. A maintenance work analysis system according to claim 2, characterized in that the information relating to the success or failure of the maintenance work includes at least one of the presence or absence of a leak, the amount of foreign matter, and the process performance / yield after maintenance.

6. A maintenance work analysis system as described in claim 1, wherein the information analysis unit acquires linking information linking the work object on which the maintenance work is performed with the movements of the worker, and presents evaluation indices specific to the work object to analyze the work movements.

7. A maintenance work analysis system as described in claim 6, characterized in that the information analysis unit analyzes the work movements by focusing on specific work among the work objects, which is work that is particularly related to the success or failure of the maintenance work.

8. A maintenance work analysis system as described in claim 7, wherein the specific work is a wiping work, and the trajectory and speed of the worker's body parts during the wiping work are analyzed.

9. A maintenance work analysis method for analyzing work movements in maintenance work for semiconductor manufacturing equipment, comprising: an information acquisition step for acquiring work information including movement information indicating the movements of a worker performing the maintenance work; an information analysis step for analyzing the work movements of the worker from the work information; and an information visualization step for outputting the difference between a reference maintenance work and the maintenance work performed by the worker.

Images