System and method for analyzing maintenance work of semiconductor manufacturing equipment.

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

Technical Field

[0004]

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

Background Art

[0002] Semiconductor manufacturing equipment has a more complex structure compared to general manufacturing equipment and the like. In addition, semiconductor manufacturing equipment has a great impact on the yield of the semiconductor devices themselves manufactured thereby. Therefore, when performing maintenance work such as inspection, maintenance, and preservation of semiconductor manufacturing equipment, a lot of knowledge and skills are required for the operator. And, in order to reduce the burden on the operator performing the maintenance work of semiconductor manufacturing equipment, many technologies have been developed.

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

[0004] <0000Patent Document 2 addresses the challenge of visually providing workers with information they require or information that should 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 displays support information related to maintenance in real time on a head-mounted display (HMD) 30 worn by a worker during maintenance work on the substrate processing apparatus. To achieve this, it acquires video footage of a predetermined part of the substrate processing apparatus to be maintained through a camera on the HMD 30, estimates support information related to the predetermined part included in the acquired video from information stored in a database, visualizes the estimated support information, and displays the created image on the HMD 30, thereby allowing the worker to visually confirm the support information." [Prior art documents] [Patent Documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2019-016759 [Patent Document 2] Japanese Patent Publication No. 2014-164482 [Overview of the Initiative] [Problems that the invention aims to solve]

[0006] The success or failure of maintenance work on semiconductor manufacturing equipment can sometimes be determined during the semiconductor manufacturing process after the maintenance, such as by the amount of foreign matter generated, which may necessitate redoing the maintenance work. One reason for this is that the movements of every single finger of the worker performing the maintenance work are not fully defined. Specifically, work actions such as gaze, hand position and movement, and work posture during maintenance work are left to the judgment and experience of each worker, and it is predicted that the large individual differences due to the skill level of the workers will affect the success or failure of the maintenance work. However, because the correlation between individual differences among workers and the success or failure of maintenance work, such as the presence or absence of leaks, the amount of foreign matter, and the process performance / yield after maintenance work, has not been sufficiently matched, the causes of maintenance work failures have not been clearly identified, and feedback to workers and identification of tasks and parts that are prone to maintenance failures have been insufficient. Patent documents 1 and 2 also do not adequately address these points. Therefore, the present invention aims to provide a technology that can present more useful information to maintenance workers. [Means for solving the problem]

[0007] 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 in maintenance work on components constituting at least a part of the chamber of a semiconductor manufacturing apparatus, and comprises an information acquisition unit that acquires work information including motion information indicating the movements of the 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 difference between a standard maintenance work and the maintenance work performed by the worker, wherein the work information includes information indicating the position and movement of the fingers as the motion information, and the information analysis unit analyzes the angular velocity from the information of the position and movement of the fingers of distribution, the average corner speed, the corner speed of ratio and the angular velocity This method analyzes the aforementioned work actions using information that indicates at least one aspect of the distribution's distortion as an evaluation index. [Effects of the Invention]

[0008] According to the present invention, it becomes possible to present more useful information to maintenance workers. Other issues, configurations, and effects not mentioned above will be clarified by the description of the embodiments for carrying out the invention below. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 shows a case where the maintenance work analysis system according to the embodiment is utilized. [Figure 2] Figure 2 shows an example of the configuration of a maintenance work analysis system. [Figure 3] Figure 3 shows an example of the configuration of the measurement system. [Figure 4] Figure 4 shows a process that links maintenance work with the movements of the workers. [Figure 5] Figure 5 shows the information used in the analysis by the Information Analysis Department. [Figure 6] Figure 6 shows an example of the analysis of work actions performed in the Information Analysis Department. [Figure 7] Figure 7 shows an example of the visualization results displayed in the output section. [Figure 8] Figure 8 is a flowchart showing the analysis process performed in the maintenance work analysis system. [Modes for carrying out the invention]

[0010] Embodiments of the present invention will be described below with reference to the drawings. However, the present invention is not limited to these embodiments. Furthermore, in the drawings, identical parts are denoted by the same reference numerals.

[0011] (Examples of applications of maintenance work analysis systems) Figure 1 shows a case where the maintenance work analysis system according to the embodiment is utilized. Figure 1 shows the relationship between the maintenance work analysis system 1, the measurement system 2, the maintenance work DB (database) 3, and the evaluation system 4.

[0012] The maintenance work analysis system 1 is a system that analyzes the work operations in the maintenance work of 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 performs processing and inspection of semiconductor devices, and includes, for example, process equipment such as plasma processing equipment, inspection equipment, assembly equipment, and the like.

[0013] The evaluation index acquisition function 11 is a function that acquires evaluation indexes to be analyzed for maintenance work. Examples of evaluation indexes include, for example, the work time related to maintenance work, the work process performed as maintenance work, and the contact amount (time, range, etc.) of an operator with a certain part (site) of the semiconductor manufacturing equipment. The contact amount (for example, when cleaning work is included, the cleaning amount (the time for cleaning, the range of cleaning)) ) There are also the movement amount of the operator's perspective, the work amount and trajectory that are displacements of the operator's body parts (hands, arms, elbows, etc.). The evaluation index acquisition function 11 is acquired from the measurement system 2 that measures the movements of the operator during maintenance work.

[0014] The visualization interface function 12 is a function that presents the analysis and evaluation of maintenance work to the operator and the user of the maintenance work analysis system 1. In the following description, the case of output that mainly focuses on visualization and stimulates vision will be described, but the present disclosure is not limited thereto. As a method of output to the operator and the user, it may include those that appeal to non-visual means such as voice. feelings It may also include those that appeal to non-visual means such as voice.

[0015] Analysis function 13 performs analysis on evaluation indicators. The analysis method involves comparing the evaluation indicators extracted during maintenance work with the data that serves as the standard for the work. Various methods of comparison are possible. For example, since maintenance work DB3 stores information indicating the movements of workers during maintenance work, data that serves as the set value or target value of the data in maintenance work DB3 is extracted as data indicating the evaluation standard, and compared with the extracted evaluation indicators. Evaluation system 4 also includes semiconductor measuring devices and semiconductor measurement devices. Evaluation system 4 acquires data indicating the operating state of semiconductor manufacturing equipment and measurement data of semiconductor devices after the semiconductor manufacturing equipment has been operated. In some cases, the data acquired from evaluation system 4 may indicate an inappropriate state, suggesting that the maintenance work was unsuccessful. In such cases, it is possible to determine the process and the location of the semiconductor manufacturing equipment parts that affected the outcome of the maintenance work through the analysis of the evaluation indicators.

[0016] (Configuration of the maintenance work analysis system) Figure 2 shows 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 memory unit 14 stores work information and result information. The work information includes motion information indicating the movements of the worker performing the maintenance work. The result information includes information regarding the success or failure of the worker's maintenance work.

[0018] Work information is acquired by the measurement system 2. The measurement system 2 acquires information indicating the worker's movements from various sensors such as cameras installed in the environment where maintenance work is performed, as well as from 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.

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

[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 worker's work actions from the work information. The information visualization unit 18 outputs the difference between the standard maintenance work and the maintenance work performed by the worker. In addition, the information visualization unit 18 performs visualizations such as numerical display, graphing, and video to show the results of the analysis performed by the information analysis unit 17.

[0021] The output unit 19 outputs the visualization 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 connected to a display, a mobile device such as a smartphone, or an HMD (Head Mounted Display). Furthermore, if the output unit 19 is an HMD, it is possible to overlay and display AR content on actual semiconductor manufacturing equipment.

[0022] The maintenance work analysis system 1 may be composed of hardware such as computers and servers, or it may be composed of cloud services, etc.

[0023] (Measurement system configuration) Figure 3 shows an example of the configuration of measurement system 2. Figure 3 shows an example of a system for measuring the movements of workers performing maintenance work on semiconductor manufacturing equipment.

[0024] Chamber 20 is one of the components that make up the semiconductor manufacturing equipment. Worker 21 is working with their arm extended into chamber 20 and looking inside the chamber 20. Imaging devices 22 and 23 are installed in the work environment where maintenance work is performed. Imaging device 22 captures the entire figure of worker 21 in its field of view. Imaging device 23 captures the chamber 20 and the hands of worker 21 in its field of view. 3D cameras (RGB-D sensors) can be used as imaging devices 22 and 23.

[0025] A head-mounted display (HMD) 25 is installed on the head of worker 21. The HMD 25 is equipped with an RGB-D sensor, a head position / orientation sensor (e.g., a tracking sensor), and a gaze sensor, which detect the worker 21's head and line of sight. In addition, an imaging device 25 installed on the worker 21's head can detect the worker 21's line of sight.

[0026] The worker 21 is equipped with a glove-shaped sensor 26 that estimates hand movements, for example, from the pressure distribution on the palm. Information from the imaging devices 22, 23, 25, HMD 24, and sensor 26 is collected by the measurement PC 27.

[0027] Using the sensors described above, motion information indicating the movements of worker 21 is collected. For example, information indicating worker 21's line of sight is acquired by imaging devices 22 and 25. Information indicating worker 21's head position and head movement (amount of change) is acquired by imaging device 22 and HMD 24. Information indicating worker 21's finger position and finger movement (amount of change) is acquired by imaging device 23 and sensor 26. Information indicating worker 21's working posture is acquired by imaging device 22. The motion information is acquired by the measurement PC 27 and stored in the storage unit 14 as work information. Furthermore, motion information acquired from skilled workers (hereinafter also referred to as "skilled workers") can be used as set values ​​or target values ​​when performing work analysis and is also stored in the maintenance work DB 3. Skilled worker work adopted as set values ​​or target values ​​is, for example, maintenance work that is free of leaks or foreign matter residue and has a yield that exceeds the required value (=successful work), and is work with an extremely short working time.

[0028] The measurement system 2 is not limited to the case described above. For example, if the worker 21 and the semiconductor manufacturing equipment can be imaged by at least one 3D camera, motion information can be acquired. In addition, sensors other than the imaging device and tracking sensor may be used.

[0029] (Processing of maintenance work analysis) Referring to Figures 4 to 8, the processes performed in the maintenance work analysis system will be explained.

[0030] (Classification of maintenance work processes) Figure 4 shows a process that associates maintenance work with the movements of the worker. Figure 4(a) shows an example of classification information 171 that classifies maintenance work by process. Maintenance work A includes the process of installing the first part, cleaning the first part, installing the second part, tightening the screws on the second part, installing the third part, cleaning the third part, and tightening the screws on the third part. The information analysis unit 17 has classification information 171 in advance that shows the relationship between maintenance work and the processes included in maintenance work.

[0031] Figure 4(b) shows an example of linking information 172 that links the work object, which is the target of maintenance work, with the movements of the worker. The information analysis unit 17 acquires the linking information 172 in Figure 4(b) in addition to the classification information 171 in Figure 4(a) and performs classification. In the linking information, if the worker's left and right arms move in parallel to a certain object (not limited to the work object), it is classified as an attachment process for a certain object. Also, if the fingers move in parallel and one arm is fixed, and the work object includes screws and bolts or tools such as wrenches, it is classified as a fastening process. Furthermore, if one of the worker's arms moves in a circular motion within a predetermined range, and the target includes a plate-shaped member or a ring-shaped member, it is classified as a cleaning operation.

[0032] Figure 4(c) shows an example of the relationship between imaging data and maintenance work processes. Imaging data can be acquired from any of the imaging devices 22, 23, 25, or HMD24. The data may also be a combination of data acquired from these imaging devices.

[0033] The information analysis unit 17 analyzes using motion information and associates the image data with the target of the maintenance work. For example, if it detects that the viewpoint and fingers are located within the range including the first part for a predetermined period of time, it determines that the target area is the first part. Among the image data, Scene 1 (from work start time hhmi1 to work completion time hhmi2) and Scene 2 (from work start time hhmi3 to work completion time hhmi2) are analyzed. complete Time hhmi4) was determined to be an operation on the first component. Here, although work is being done on the first part in both Scene 1 and Scene 2, it is not possible to determine the difference in the work itself. At this point, the information analysis unit 17 extracts the differences in motion information between Scene 1 and Scene 2 while referring to the linked information 172. The information analysis unit 17 identifies the difference in the amount of movement of the worker's arm. of It is possible to extract and classify the scenes, distinguishing them as follows: Scene 1 is the installation process of the first part, Scene 2 is the cleaning process of the first part, and so on.

[0034] Furthermore, in Scene 3, the work target is the second component, and in Scene 4, the work target is the first screw. The information analysis unit 17 can refer to the linked information 172 and the sequence of processes, etc., and classify Scene 3 as the installation process for the second component, and Scene 4 as the screw tightening process for the second component. Furthermore, in scenes 5 and 6, the work target is the third component. Also, in scene 7, the work target is the second screw. The information analysis unit 17 can refer to the linked information 172 and information such as the sequence of processes and classify the scenes as follows: scene 5 is the installation process of the third component, scene 6 is the cleaning process of the third component, and scene 7 is the screw tightening process of the third component.

[0035] In this way, imaging data can be analyzed using motion information to correlate maintenance work processes and the locations of the work being performed. Such correlations can be made using a classifier, or by the user of the maintenance work analysis system 1 by creating annotation data.

[0036] Furthermore, the information analysis unit 17 analyzes work movements using at least one piece of motion information as an evaluation index. In addition, the information analysis unit 17 analyzes work movements by presenting evaluation indexes specific to the work object. Note that work movements refer to movements (actions) related to maintenance work (or processes included in maintenance work). When motion information is used as an evaluation index, it is possible to use so-called primary information of movement, such as the position and amount of change of the viewpoint, and the position and amount of change of the arm. Also, when using the linked information 172 shown in Figure 4(b), evaluation indexes specific to the work object can be used, such as the installation speed of a certain object, the tightening speed of screws, the area of ​​the area that was wiped, and the time spent wiping. These evaluation indexes can be derived from primary information, for example. For example, regarding wiping work, it may be determined that it is desirable to wipe in one direction without going back and forth. When using the wiping direction as an evaluation index in this way, 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 imaging data and processes, it becomes possible to use the time required to perform each process as an evaluation metric. In addition to tasks where workers directly touch semiconductor manufacturing equipment, evaluation indicators can also include the timing and frequency of changing gloves, the timing and frequency of changing cleaning cloths, and the timing and frequency of applying cleaning solution. Such evaluation indicators can be extracted, for example, by performing image processing such as object detection on imaging data acquired by an imaging device.

[0037] The above description illustrates an example of a process that associates maintenance work with the actions of the worker, and this disclosure is not limited to this process.

[0038] (Analysis of maintenance work and process success / failure) Figure 5 shows the information used for analysis by the Information Analysis Unit. Figure 5(a) shows an example of measurement data acquired by the Evaluation System 4. The measurement data 41 is the result of measurements during the process performed in the semiconductor manufacturing equipment and the evaluation 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 on the success or failure of the operator's maintenance work. The measurement data 41 includes at least one of the following as information on the success or failure of the maintenance work: presence or absence of leaks, amount of foreign matter, and process performance / yield after maintenance. This will be explained in detail below.

[0039] The "Leak" item indicates the presence or absence of leaks based on the results of leak checks performed during the process and measurements of the achieved vacuum level. The "Foreign Matter Amount" item is determined based on the results of measuring the gas composition inside the semiconductor manufacturing equipment and 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 the semiconductor after the process.

[0040] The "Leak" item was judged as having no leaks, as the achieved vacuum level of aaaa[Pa] was within the normal range and no abnormalities were detected during the leak check. The "Foreign Matter Amount" item was judged as abnormal because SUS was detected on the surface of the semiconductor. The "Process Performance" item was judged as normal, as the evaluation result was deemed acceptable. The "Yield" item was calculated to be 89%, which is judged as normal.

[0041] Figure 5(b) shows an example of process history information 141 performed in semiconductor manufacturing equipment. Figure 5(c) shows... half This figure shows an example of pre-information 142 indicating the content of maintenance work performed in a conductor manufacturing apparatus. History information 141 and pre-information 142 are stored in the storage unit 14 as part of the work information. In addition, history information 141 and pre-information 142 are common to semiconductor manufacturing apparatus and are associated with measurement data 41 (result information).

[0042] Process history information 141 includes information on the materials used and the manufacturing method. The materials used are shown as a Si substrate, F-based gas, and Ar gas. The manufacturing method is shown as plasma etching. If multiple processes are performed, the history information 141 may also include the materials and manufacturing methods of the other processes. Furthermore, materials other than the substrate and gas type may be included, and the manufacturing method may be primarily... Essential Other manufacturing conditions may be included. Furthermore, the pre-information 142 includes information indicating the maintenance work performed on the semiconductor manufacturing equipment before the process was carried out and the workers who performed it. Maintenance work A was performed by worker XX. If multiple maintenance tasks were performed, it may also include information indicating other maintenance tasks.

[0043] (Analysis of work movements) The information analysis unit 17 combines the worker's work information and result information to analyze the factors behind the result information. The information analysis unit 17 also analyzes work movements using historical information and prior information. From the measurement data 41, the information analysis unit 17 determines that SUS was detected on the substrate and that an abnormality occurred regarding the item "amount of foreign matter". In addition, the historical information 141 included in the work information reveals that no process using SUS was performed. According to the prior information 142, it is revealed that maintenance work A was 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 and not the process, and analyzes the work movements of worker XX performing maintenance work A.

[0044] Figure 6 shows an example of the analysis of work movements performed by the information analysis unit 17. Figure 6(a) shows the work time for each process included in maintenance work A. The horizontal axis shows the processes included in maintenance work A separately. The vertical axis shows the work time. Here, the information analysis unit 17 also uses movement information of maintenance work A performed by a skilled worker from the maintenance work DB3 and compares it with the work movements of worker XX. In the figure, the dotted line graph shows the work time of the skilled worker, and the shaded line graph shows the work time of worker XX.

[0045] The Information Analysis Department focuses on specific tasks within the work area that are particularly relevant to the success or failure of maintenance work, and analyzes the work movements. The specific task is wiping, and the trajectory and speed of the worker's body parts during the wiping work are analyzed. The Information Analysis Department 17 compares the work of a skilled worker with the work of worker XX. For example, the Information Analysis Department 17 extracts processes where the deviation from the work time of the skilled worker is greater than a predetermined value, based on pre-set criteria. Here, it is found that there is a significant difference in the work time for the wiping process of the third component. The Information Analysis Department 17 focuses on the third component of the chamber, which is the work area.

[0046] Figure 6(b) shows 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 skilled worker, and the dashed line represents the case of the second skilled worker. Since the solid line is far from the dotted and dashed lines, it can be seen that the trajectory of worker XX's head is shown at a distance from the third part. Also, as shown in region R1, the position of worker XX's head is fluctuating where there is no change in the case of a skilled worker. This indicates that the speed of head movement is large.

[0047] The information analysis unit 17 analyzes that one of the factors for detecting the foreign object was that the head was separated from the third part during the cleaning 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 work information (measurement data 41, history information 141, prior information 142, movement information of skilled workers, etc.). However, the method of analysis is not limited to those described above. Other tasks may be extracted as specific tasks. In addition, analysis may be performed on body parts other than the head.

[0049] (Visualization of analysis results) The information visualization unit 18 outputs information about the work and parts that may be contributing factors when the result information indicates failure. Based on the analysis results of the information analysis unit 17, the information visualization unit 18 visualizes the cleaning process of the third part as a potentially contributing work factor and the third part as a potentially contributing part to notify the worker and user, and sends the visualization results to the output unit 19.

[0050] Figure 7 shows an example of the visualization results shown in the output unit 19. The display unit 191 of the output unit 19 includes information about the work and parts. The work column 192 shows the work process that caused the result information. The process column 193 shows the part that caused the result. The work column 192 shows maintenance work A, and the process column 193 shows the cleaning process of the third part.

[0051] Furthermore, feedback section 194 explains the analyzed factors to the worker and provides advice for improving the work. Feedback section 194 includes text indicating that the head was detached from the third part and urging workers to be more careful to increase the likelihood of noticing foreign objects during the work.

[0052] Furthermore, the visualization area 195 includes a display for providing visual feedback to the worker or user. Here, a scene is shown from the imaging data that includes a worker 21 performing a cleaning process and a chamber 20. In addition, the head 196 and third part 197 of the worker 21 are highlighted.

[0053] Although the visualization method has been explained, this disclosure is not limited to this. Rena For example, the difference between the work of a skilled worker and the work of an ordinary worker could be scored to evaluate the quality of the ordinary worker's work. Alternatively, the display unit 191 may be displayed on an HMD. It is also possible to accumulate analysis results of a particular worker, extract work trends, and notify the worker in real time of potential body parts or components that could cause failure during work.

[0054] (Processing procedure) Figure 8 is a flowchart showing the analysis process performed in the maintenance work analysis system 1.

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

[0056] Next, the information analysis unit 17 refers to the imaging 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 are any abnormalities in the result information of the process performed in the semiconductor manufacturing equipment (step S3). If there are abnormalities (Yes in step S3), the information analysis unit 17 combines the worker's work information and the result information to analyze the factors of the work result (step S5). In the factor analysis, the worker's work information and the expert's work information are compared. Furthermore, the analysis focuses on specific maintenance tasks that are judged to be highly related to the factors. 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 outputs information indicating the factors and tasks, referring to the analysis results (step S6). The information visualization unit 18 sends the visualized results to the output unit 19 for notification to the workers and users. The output unit 19 outputs the visualization results (step S7).

[0059] Furthermore, if no abnormalities are indicated in the result information (No in step S3), the information visualization unit 18 may perform an analysis based on predetermined evaluation indicators and then notify the worker that there are no abnormalities. It is also possible to store the work information as expert work in the storage unit 14 and use it for analysis.

[0060] (Effects / Actions) According to this disclosure, by providing feedback on the differences between standard maintenance work (skilled worker work) and the maintenance work of each worker, and by quantitatively and objectively identifying tasks and parts that are prone to failure, the causes of maintenance failures can be investigated. Since factor analysis is performed even on the work movements of parts of the worker's body such as gaze, fingers, and posture, even inexperienced workers can achieve a quality of work equivalent to that of skilled workers. Thus, this disclosure makes it possible to provide more useful information to maintenance workers.

[0061] Although embodiments of the present invention have been described above, the present invention is not limited to the embodiments described above, and various modifications are possible without departing from the spirit of the present invention.

[0062] The following describes, but is not limited to, embodiments that may constitute the present invention. (Aspect 1) A maintenance work analysis system for analyzing work movements in maintenance work for semiconductor manufacturing equipment, An information acquisition unit that acquires work information including motion information showing the movements of the worker performing the aforementioned maintenance work, An information analysis unit analyzes the worker's work movements from the aforementioned work information, A maintenance work analysis system characterized by having an information visualization unit that outputs the difference between standard maintenance work and the maintenance work performed by the worker. (Aspect 2) In the maintenance work analysis system described in Embodiment 1, The information acquisition unit acquires result information including information regarding the success or failure of the worker's maintenance work. The information analysis unit combines the worker's work information and the result information to analyze the factors of the result information, The aforementioned information visualization unit is characterized by outputting information about tasks and parts that may be contributing factors when the result information indicates failure, as part of a maintenance work analysis system. (Aspect 3) In the maintenance work analysis system described in Embodiment 1 or 2, The aforementioned work information includes historical information of the processes performed in the semiconductor manufacturing equipment and prior information indicating the content of maintenance work. The aforementioned information analysis unit is characterized by analyzing the work operations using the historical information and the prior information, and is a maintenance work analysis system. (Aspect 4) In the maintenance work analysis system described in any one of embodiments 1 to 3, The aforementioned work information includes, as movement information, information indicating at least one of the following: gaze, head position and movement, hand and finger position and movement, and work posture. The aforementioned information analysis unit is a maintenance work analysis system characterized by analyzing the work movements using at least one piece of the motion information as an evaluation index. (Aspect 5) In the maintenance work analysis system described in any one of embodiments 1 to 4, Information regarding the success or failure of the aforementioned maintenance work is, A maintenance work analysis system characterized by including at least one of the following: presence or absence of leaks, amount of foreign matter, and process performance / yield after maintenance. (Aspect 6) In the maintenance work analysis system described in any one of embodiments 1 to 5, The aforementioned information analysis unit, By acquiring linked information that links the work object, which is the target of the maintenance work, with the movements of the worker, A maintenance work analysis system characterized by presenting evaluation indicators specific to the work object and analyzing the work operations accordingly. (Aspect 7) In the maintenance work analysis system described in any one of embodiments 1 to 6, The aforementioned information analysis unit, A maintenance work analysis system characterized by focusing on specific tasks among the aforementioned work targets that are particularly relevant to the success or failure of maintenance work, and analyzing the work movements. (Pattern 8) In the maintenance work analysis system described in any one of embodiments 1 to 7, The aforementioned specific task is a wiping operation. A maintenance work analysis system characterized by analyzing the trajectory and speed of the body parts of the worker during the cleaning work. (Aspect 9) A maintenance work analysis method for analyzing work movements in maintenance work for semiconductor manufacturing equipment, An information acquisition step to acquire work information including motion information showing the movements of the worker performing the aforementioned maintenance work, An information analysis step that analyzes the worker's work actions from the aforementioned work information, A maintenance work analysis method characterized by having an information visualization step that outputs the difference between a standard maintenance work and the maintenance work performed by the worker. [Explanation of Symbols]

[0063] 1. Maintenance work analysis system, 2. Measurement system, 3. Maintenance work database, 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 Imaging device, 23 Imaging device, 25 Imaging device, 26 Sensor, 41 Measurement data, 141 History information, 142 Prior 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 on components constituting at least a part of the chamber of a semiconductor manufacturing apparatus, An information acquisition unit that acquires work information including motion information showing the movements of the worker performing the aforementioned maintenance work, An information analysis unit analyzes the worker's work movements from the aforementioned work information, It has an information visualization unit that outputs the difference between standard maintenance work and the maintenance work performed by the said worker, A maintenance work analysis system characterized in that the work information includes information indicating the position and movement of fingers as the movement information, and the information analysis unit analyzes the work motion using information indicating at least one of the distribution of angular velocity, the average angular velocity, the ratio of the angular velocity, and the distortion of the distribution of the angular velocity as evaluation indicators from the information of the position and movement of fingers.

2. In the maintenance work analysis system described in claim 1, The maintenance work analysis system is characterized in that the information visualization unit outputs information about the work and parts that may be contributing factors when the result information indicating the result of the operation of the semiconductor manufacturing equipment after the maintenance work indicates a failure.

3. In the maintenance work analysis system described in claim 1, The aforementioned work information includes historical information including the conditions of the process performed in the semiconductor manufacturing equipment prior to the maintenance work, and prior information indicating the content of the maintenance work. The aforementioned information analysis unit is characterized by analyzing the work operations using the historical information and the prior information, and is a maintenance work analysis system.

4. In the maintenance work analysis system described in claim 1, The aforementioned work information includes, as movement information, information indicating at least one of the following: line of sight, head position and movement, and work posture. The aforementioned information analysis unit is a maintenance work analysis system characterized by analyzing the work movements using at least one piece of the motion information as an evaluation index.

5. In the maintenance work analysis system described in claim 2, Information regarding the success or failure of the aforementioned maintenance work is, A maintenance work analysis system characterized by including at least one of the following: presence or absence of leaks, amount of foreign matter, and process performance / yield after maintenance.

6. In the maintenance work analysis system described in claim 1, The aforementioned information analysis unit, By acquiring linked information that links the work object, which is the target of the maintenance work, with the movements of the worker, A maintenance work analysis system characterized by presenting evaluation indicators specific to the work object and analyzing the work operations accordingly.

7. In the maintenance work analysis system according to claim 6, The aforementioned information analysis unit, A maintenance work analysis system characterized by focusing on specific tasks among the aforementioned work targets that are particularly relevant to the success or failure of maintenance work, and analyzing the work movements.

8. In the maintenance work analysis system described in claim 7, The aforementioned specific task is a wiping operation. A maintenance work analysis system characterized by analyzing the trajectory and speed of the body parts of the worker during the cleaning work.

9. A maintenance work analysis method for analyzing work movements in maintenance work on components constituting at least a part of the chamber of a semiconductor manufacturing apparatus, An information acquisition step to acquire work information including motion information showing the movements of the worker performing the aforementioned maintenance work, An information analysis step that analyzes the worker's work actions from the aforementioned work information, It includes an information visualization step that outputs the difference between standard maintenance work and the maintenance work performed by the worker, A maintenance work analysis method characterized in that the work information includes information indicating the position and movement of fingers as the movement information, and in the information analysis step, the work movement is analyzed using information indicating at least one of the distribution of angular velocity, the average angular velocity, the ratio of the angular velocity, and the distortion of the distribution of the angular velocity as evaluation indicators from the information of the position and movement of fingers.

Images