WO2021255784A1 - 装置診断装置、装置診断方法、プラズマ処理装置および半導体装置製造システム - Google Patents

装置診断装置、装置診断方法、プラズマ処理装置および半導体装置製造システム Download PDF

Info

Publication number
WO2021255784A1
WO2021255784A1 PCT/JP2020/023386 JP2020023386W WO2021255784A1 WO 2021255784 A1 WO2021255784 A1 WO 2021255784A1 JP 2020023386 W JP2020023386 W JP 2020023386W WO 2021255784 A1 WO2021255784 A1 WO 2021255784A1
Authority
WO
WIPO (PCT)
Prior art keywords
maintenance
plasma processing
work
diagnostic
processing device
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2020/023386
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
祥太 梅田
誠浩 角屋
義人 釜地
研二 玉置
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hitachi High Tech Corp
Original Assignee
Hitachi High Tech Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hitachi High Tech Corp filed Critical Hitachi High Tech Corp
Priority to PCT/JP2020/023386 priority Critical patent/WO2021255784A1/ja
Priority to CN202511740576.6A priority patent/CN121563475A/zh
Priority to KR1020217016709A priority patent/KR102648654B1/ko
Priority to JP2021526327A priority patent/JPWO2021255784A1/ja
Priority to US17/431,516 priority patent/US12387921B2/en
Priority to CN202080007081.1A priority patent/CN114096972A/zh
Priority to TW110121443A priority patent/TWI780764B/zh
Publication of WO2021255784A1 publication Critical patent/WO2021255784A1/ja
Anticipated expiration legal-status Critical
Priority to JP2023095156A priority patent/JP7716442B2/ja
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/20—Administration of product repair or maintenance
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01J—ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS
    • H01J37/00—Discharge tubes with provision for introducing objects or material to be exposed to the discharge, e.g. for the purpose of examination or processing thereof
    • H01J37/32—Gas-filled discharge tubes
    • H01J37/32917—Plasma diagnostics
    • H01J37/32926—Software, data control or modelling
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
    • G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01J—ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS
    • H01J37/00—Discharge tubes with provision for introducing objects or material to be exposed to the discharge, e.g. for the purpose of examination or processing thereof
    • H01J37/32—Gas-filled discharge tubes
    • H01J37/32431—Constructional details of the reactor
    • H01J37/32798—Further details of plasma apparatus not provided for in groups H01J37/3244 - H01J37/32788; special provisions for cleaning or maintenance of the apparatus
    • H01J37/3288—Maintenance
    • H—ELECTRICITY
    • H01—ELECTRIC ELEMENTS
    • H01J—ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS
    • H01J37/00—Discharge tubes with provision for introducing objects or material to be exposed to the discharge, e.g. for the purpose of examination or processing thereof
    • H01J37/32—Gas-filled discharge tubes
    • H01J37/32917—Plasma diagnostics
    • H01J37/32935—Monitoring and controlling tubes by information coming from the object and/or discharge
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/80—Management or planning

Definitions

  • the present invention relates to an apparatus diagnostic method and an apparatus diagnostic apparatus of a plasma processing apparatus for processing a semiconductor wafer by plasma.
  • the plasma processing device is a device that performs plasma processing to turn a substance into plasma and remove the substance on the wafer by the action of the substance in order to form a fine shape on the wafer of the semiconductor.
  • maintenance planned maintenance
  • a maintenance plan established in advance based on the number of wafers to be processed.
  • unplanned maintenance work may occur due to deterioration of parts due to aging and accumulation of reaction by-products depending on the method of use.
  • the device diagnostic device estimates the degree of deterioration from the deviation from the normal state using the sensor values sequentially acquired from multiple state sensors attached to the device, and sets the threshold value. It is common to issue an alarm in comparison.
  • Patent Document 1 "The anomaly detection device removes noise from the summary value by applying statistical modeling to the summary value that summarizes the observation values. It estimates the state and generates a predicted value that predicts the summary value one period ahead based on the estimation. The abnormality detection device detects the presence or absence of an abnormality in the monitored device based on the predicted value. " ..
  • Patent Document 2 classifies the phenomenon pattern based on "work keywords included in maintenance history information". The method of "creating a classification standard for” and “creating a diagnostic model for estimating the work keyword presented to the maintenance worker based on the classified phenomenon pattern and the work keyword" is described.
  • Patent Document 3 describes a method of calculating the maintenance cost in the representative maintenance method by setting the failure probability in advance.
  • Patent Document 1 describes a method of detecting the presence or absence of an abnormality in a device and issuing an alarm. However, there is no mention of providing information on how to specifically revise the maintenance plan after issuing an alarm.
  • the present invention provides an apparatus diagnostic apparatus that presents a maintenance plan that takes into consideration maintenance costs such as an apparatus operating rate and maintenance work costs in addition to the deterioration degree estimation result using sensor values.
  • maintenance costs such as an apparatus operating rate and maintenance work costs in addition to the deterioration degree estimation result using sensor values.
  • the first point is to estimate the actual maintenance cost for each part and the work related to the part from the maintenance history consisting of free descriptions. From the viewpoint of recording man-hours, etc., the maintenance history is often a free description. From such unstructured records, it is necessary to identify the combination of parts and work to be maintained and estimate the actual maintenance cost.
  • Patent Document 2 describes a method of extracting a word representing work from a maintenance history as a keyword and assigning importance to the word.
  • Patent Document 2 describes a method of extracting a word representing work from a maintenance history as a keyword and assigning importance to the word.
  • the second point is to calculate the maintenance cost when unplanned maintenance is incorporated into the planned maintenance at multiple points in time using the actual maintenance cost (hereinafter referred to as the maintenance cost at the time of planned incorporation), and the optimum maintenance from the viewpoint of the maintenance cost.
  • the maintenance cost at the time of planned incorporation the actual maintenance cost
  • the optimum maintenance from the viewpoint of the maintenance cost Present a plan amendment.
  • the plasma processing device is a vacuum device, and it takes time to start up and down the device. Therefore, the operating rate may decrease if the maintenance is performed immediately after the alarm is issued. Therefore, the goal is to anticipate the occurrence of unplanned maintenance in advance and incorporate additional work into the planned maintenance that has been set up in advance.
  • Patent Document 2 describes a method of classifying a phenomenon pattern based on a sensor value and presenting a work keyword to a maintenance worker.
  • Patent Document 3 describes a method of calculating the maintenance cost in the representative maintenance method by setting the failure probability in advance, but since the etching apparatus has a long start-up time, an alarm is issued from the apparatus monitor. Immediately after that, if the device is stopped only for maintenance corresponding to this alarm, there is a problem that the device operation is lowered.
  • the present invention solves the above-mentioned problems of the prior art, predicts the occurrence of unplanned maintenance that may occur in the plasma processing apparatus in advance, and requires maintenance by a user such as a maintenance planner or a maintenance worker. It is an object of the present invention to provide an apparatus diagnostic method and an apparatus diagnostic apparatus of a plasma processing apparatus capable of immediately determining a work and a time point in which the work should be incorporated into planned maintenance from the viewpoint of priority maintenance cost.
  • the present invention is based on the probability that unplanned maintenance work of the plasma processing device will occur in the device diagnostic device for diagnosing the device state of the plasma processing device and the maintenance cost related to the maintenance work.
  • the maintenance plan for the plasma processing equipment planned in advance was revised.
  • the probability is characterized in that it is obtained based on the degree of deterioration of the plasma processing apparatus estimated based on the monitored apparatus state of the plasma processing apparatus.
  • the device diagnostic device in the plasma processing device provided with the device diagnostic device for diagnosing the device state, has a probability and maintenance that an unplanned maintenance work of the own device occurs.
  • the maintenance plan of the plasma processing device planned in advance based on the maintenance cost related to the work is modified, and the probability is based on the degree of deterioration of the own device estimated based on the monitored device state of the own device. It is characterized by being sought after.
  • the device diagnostic process is the plasma process. It has a step of modifying the maintenance plan of the plasma processing apparatus planned in advance based on the probability that unplanned maintenance work of the apparatus occurs and the maintenance cost related to the maintenance work, and the probability is the monitor of the plasma processing apparatus. It is characterized in that it is obtained based on the degree of deterioration of the plasma processing apparatus estimated based on the device state.
  • the probability that unplanned maintenance work of the plasma processing device occurs and the maintenance related to the maintenance work is modified, and the probability is obtained based on the deterioration degree of the plasma processing apparatus estimated based on the monitored apparatus state of the plasma processing apparatus. It is characterized by being able to be.
  • the occurrence of unplanned maintenance that may occur is predicted in advance, and a user such as a maintenance planner or a maintenance worker plans necessary maintenance work and the work at what time. It has become possible to immediately determine whether to incorporate it into maintenance from the viewpoint of priority maintenance cost. Issues, configurations and effects other than those described above will be clarified by the description of the following embodiments.
  • the present invention estimates and estimates maintenance costs when additional work (unplanned maintenance work not included in the original maintenance plan) is incorporated into the maintenance plan based on sensor data, maintenance history, and the initial maintenance plan. It is an object of the present invention to provide an apparatus diagnostic method and an apparatus diagnostic apparatus of a plasma processing apparatus that output a revision plan of a maintenance plan so as to minimize the maintenance cost.
  • a device diagnosis method and a device diagnosis that output as a maintenance plan amendment an additional work that minimizes the estimated maintenance cost at a plurality of planned maintenance points from the sensor data and maintenance history of the device group and the maintenance plan. Provide the device.
  • the maintenance work which is a combination of each part and the work performed by each maintenance ID is specified from the maintenance history consisting of the free description of the plasma processing device, and the maintenance is performed based on the maintenance cost information such as the device operation rate.
  • the actual maintenance cost for each work is calculated, the degree of deterioration of each part is estimated using the control values such as the sensor value and the number of sample processes sequentially acquired by the plasma processing device, and the plasma processing device group when each maintenance work occurs.
  • the probability of maintenance work occurrence until reaching a certain degree of deterioration is estimated, and at the time of device diagnosis, the transition of the degree of deterioration is predicted from the sequentially estimated degree of deterioration, and the actual maintenance cost and the maintenance are described.
  • the maintenance cost when the additional maintenance work is incorporated into the planned maintenance at a plurality of time points is calculated and presented.
  • the device diagnostic device has the following three configurations.
  • FIG. 1 shows the configuration of the device diagnostic device 100 according to this embodiment.
  • the apparatus diagnostic apparatus 100 according to this embodiment is connected to the apparatus group 1 composed of each plasma processing apparatus 11 via a communication line 150.
  • the device diagnostic device 100 includes an execution unit 2, an analysis unit 3, and a CPU (central processing unit) 4, which are connected by an internal bus 5.
  • the device diagnostic device 100 may be connected to an external control device or storage device via the communication line 150.
  • each plasma processing apparatus 11 constituting the apparatus group 1 generates plasma 12 to process the sample 13 according to the set processing conditions.
  • the plasma processing device 11 is equipped with a state sensor group 14 (for example, a temperature sensor or a pressure sensor), and has a sensor value (for example) during processing of the sample 13 with the plasma 12 or during idling when the generation of the plasma 12 is stopped. , Temperature and pressure) can be acquired as time-series data.
  • Examples of the plasma processing apparatus 11 constituting the apparatus group 1 include a plasma etching apparatus and the like.
  • the apparatus diagnostic apparatus 100 includes an execution unit 2 that receives a sensor signal from a state sensor group 14 mounted on each plasma processing apparatus 11 of the apparatus group 1 and executes processing, and plasma processing.
  • An analysis unit 3 that performs analysis on the device 11 and a CPU 4 that controls the operation of the execution unit 2 and the analysis unit 3 are provided, and they are connected by an internal bus 5.
  • the device diagnostic device 100 is connected to each plasma processing device 11 through a communication line 150, and the execution unit 2 acquires data from the state sensor group 14 from each plasma processing device 11 via the communication line 150. ..
  • the execution unit 2 has a storage unit 20, a deterioration degree estimation unit 21, and a maintenance cost calculation unit 22 at the time of planned incorporation. Further, the storage unit 20 includes a sensor value storage unit 200, a control value storage unit 210, a deterioration degree storage unit 220, and a maintenance cost storage unit 230 at the time of planned incorporation.
  • the analysis unit 3 has a storage unit 30, a maintenance work occurrence probability estimation unit 31, an actual maintenance cost calculation unit 32, an input unit 33, and a display unit 34. Further, the storage unit 30 includes a maintenance history storage unit 300, a maintenance work dictionary storage unit 310, a maintenance plan storage unit 320, and a performance maintenance cost storage unit 330.
  • the sensor value storage unit 200 in the storage unit 20 of the execution unit 2 stores the sensor value (measured value) acquired from the state sensor group 14 of the plasma processing device 11 via the communication line 150.
  • FIG. 2 is a diagram showing an example of the processing data 201 stored in the sensor value storage unit 200 in a tabular format.
  • the measured value of the sensor value 202 is stored as time series data 203 for each sensor constituting the state sensor group 14 mounted on the plasma processing device 11.
  • the processing step ID: 204 is attached and stored for each set processing step.
  • information specifying the processing such as the wafer ID: 206 and the processing condition ID: 205 is stored in association with each other.
  • the control value storage unit 210 is used to determine the processing date and time when the sample 13 is processed by the plasma processing device 11, the processing conditions of the sample 13 by the plasma processing device 11, the input power for generating the plasma 12, the processing time by the plasma 12, and the processing. Control values such as pressure, temperature of sample 13 being processed, etc.), number of processed samples 13 and the like are stored.
  • the deterioration degree estimation unit 21 uses a deterioration degree estimation model that has been learned and constructed in advance for each component to be monitored by each plasma processing device 11, and inputs the sensor value 202 sequentially acquired from the sensor value storage unit 200 as an input. Deterioration degree estimation The deterioration degree of each component corresponding to the model ID is estimated and output.
  • FIG. 3 shows an example of the data 221 stored in the deterioration degree storage unit 220 in a tabular format.
  • the data 221 stored in the deterioration degree storage unit 220 includes the deterioration degree 222 of the output for each deterioration degree estimation model ID, information specifying the processing (time series data 223, wafer ID: 226, processing condition ID: 225, processing). Step ID: 224) and the like.
  • the maintenance cost calculation unit 22 at the time of planned incorporation in FIG. 1 determines the deterioration of each component corresponding to each future deterioration degree estimation model ID from the transition of the deterioration degree 222 up to the present time in the data 221 stored in the deterioration degree storage unit 220. Predict the transition of degree 222, estimate the occurrence probability of unplanned maintenance work at the time of future planned maintenance based on the output of the maintenance work occurrence probability estimation unit 31, and use the information of the actual maintenance cost storage unit 330 in the future. Calculate the expected maintenance cost (expected value of maintenance cost) when unplanned maintenance work is incorporated as additional work in the planned maintenance of. The calculation result is stored in the maintenance cost storage unit 230 at the time of planning incorporation.
  • the maintenance history storage unit 300 in the storage unit 30 of the analysis unit 3 has each work ID 302 (one planned maintenance or unplanned maintenance).
  • the work content 307 is stored in a free description.
  • the device ID 303, the date and time 304, the non-operating time 305, the work classification 306, etc. are also stored in order to be used when calculating the actual maintenance cost.
  • the maintenance work dictionary storage unit 310 stores information for extracting parts and work keywords when specifying a combination of parts and work from the work contents of the maintenance history in the actual maintenance cost calculation unit 32.
  • the maintenance plan storage unit 320 stores the time (date and time, number of wafers processed, etc.) and work contents set in advance by the maintenance plan planner.
  • the maintenance work occurrence probability estimation unit 31 acquires the deterioration degree at the time of each maintenance work occurrence from the deterioration degree of each plasma processing device 11 of the device group 1 stored in the deterioration degree storage unit 220, and obtains the acquired deterioration degree. Use to estimate the maintenance work occurrence probability density according to the deterioration degree, perform integration processing on the deterioration degree, and calculate the probability that unplanned maintenance work will occur before reaching a certain deterioration degree (cumulative maintenance work occurrence probability). do.
  • the actual maintenance cost calculation unit 32 specifies a combination of parts and work from the work contents stored in the maintenance history storage unit 300 by using the information of the maintenance work dictionary storage unit 310. Further, by associating maintenance cost information such as the device operating rate with each combination, the actual maintenance cost of each combination is calculated and stored in the actual maintenance cost storage unit 330.
  • the input unit 33 is an input device such as a mouse or a keyboard that accepts information input by a user's operation.
  • the display unit 34 is, for example, a display, a printer, or the like, and is output from the information stored in the storage unit 20 of the execution unit 2 or the storage unit 30 of the analysis unit 3 or from the maintenance cost calculation unit 22 at the time of planned incorporation of the execution unit 2. It is a device that graphically outputs information to the user based on the final maintenance plan revision plan.
  • the actual maintenance cost calculation unit 32 performs actual maintenance. Calculate the cost (S510).
  • the maintenance work occurrence probability estimation unit 31 performs an estimation process of the maintenance work occurrence probability of unplanned maintenance (S520).
  • the maintenance cost calculation unit 22 at the time of planning embedding performs a calculation process of the maintenance cost at the time of planning embedding using the data of the actual maintenance cost calculated in S510 and the maintenance work occurrence probability obtained in S520 (S530).
  • the maintenance plan amendment plan is output to the display unit 34 (S540). The details of each step will be described below.
  • a maintenance work dictionary that defines the names of parts and work is created in advance based on the knowledge of the device, and is stored in the maintenance work dictionary storage unit 310 (S511).
  • the maintenance work dictionary 311 for parts shown in FIG. 7 each part ID 312, the part name 314 corresponding to the part name 313, and the name group 315 are specified.
  • the keywords described in the name group 315 stored in the maintenance work dictionary storage unit 310 are extracted as the parts described in the part name 314.
  • the name group 315 is made into a regular expression (S512).
  • Common word fluctuations include the presence or absence of spaces, singular and compound forms, and flexion.
  • keywords even if there is such fluctuation, for example, in the case of "o ring” made of an elastic member with a circular cross section for sealing the connection part of the vacuum device, "o [-] rings?” Etc. It is described by a regular expression as follows. Regular expressions for such standard language fluctuations can be easily automated.
  • the maintenance history for the specified period is acquired from the maintenance history storage unit 300 (S513), and the work contents of the maintenance history are divided into sentences (S514). From each sentence, a keyword matching the regular expression described in the name group is extracted and associated with the part name or part name to which the name group belongs (S515).
  • tags are added to the words and phrases in the sentence (S516).
  • a part tag is attached to a word or phrase extracted as a part
  • a work tag is attached to a word or phrase extracted as a work
  • a tag indicating a part of speech is attached to other words.
  • the specified tag order is not limited to a specific tag order as long as the combination of parts and work is correctly specified.
  • work content such as "..replace o ring and pump A ..”
  • part tags ⁇ CMP>
  • work tags ⁇ WORK>
  • And are tagged with a coordinated connective tag ( ⁇ AND>)
  • ⁇ WORK> ⁇ AND> * ⁇ WORK>
  • ⁇ CMP> ⁇ AND> * ⁇ CMP>
  • the actual maintenance cost calculated as described above may change when the period is free, so it will be updated regularly or at any time.
  • the deterioration degree estimation unit 21 sequentially acquires the sensor values during processing or idling of the sample 13 by the plasma processing device 11 from the sensor value storage unit 200 by using the deterioration degree estimation model of each registered component, and deteriorates. The degree is estimated and output to the deterioration degree storage unit 220.
  • the deterioration degree estimation model may use a method suitable for estimating the deterioration of each component, and is not limited to a specific method.
  • the parameters of the normal distribution are learned using the sensor values for a certain period immediately after parts replacement when learning the deterioration degree estimation model, and when the deterioration degree estimation is performed,
  • the degree of deterioration may be estimated using the Kullback-Leibler distance with the distribution at the time of learning and the log-likelihood as an index.
  • the degree of deterioration may be estimated by a method that can handle non-normal distributions such as the k-nearest neighbor method. Further, in order to reduce the observation noise, a value obtained by calculating a statistic such as an average value for each processing step with respect to the sensor value may be used as an input.
  • FIG. 8 shows an example of the processing of the maintenance work occurrence probability estimation unit 31 when estimating the maintenance work occurrence probability.
  • the processing flow chart shown in FIG. 8 corresponds to the above-mentioned step of estimating the degree of deterioration, and the above-mentioned deterioration degree estimation model is learned in advance of this step.
  • the degree of deterioration of the target component of the plasma processing device 11 is acquired from the degree of deterioration storage unit 220 (S521). Further, the date and time when the maintenance work content related to the target component is generated is acquired from the maintenance history storage unit 300 (S522). Further, the degree of deterioration at the time when the maintenance work occurs is extracted using the acquired data (S523). Next, the distribution of the extracted degree of deterioration at the time of maintenance work occurrence (maintenance work occurrence probability density according to the degree of deterioration) is estimated (S524).
  • Graph 900 in FIG. 9 shows an example of the probability density distribution 901 estimated from the deterioration degree distribution 902 when maintenance work occurs.
  • the horizontal axis of the graph of FIG. 9 shows the degree of deterioration, and the vertical axis shows the probability density.
  • the distribution estimation method is not limited to a specific method, but for example, a Markov chain Monte Carlo method (MCMC) or a kernel density estimation method may be used.
  • MCMC Markov chain Monte Carlo method
  • kernel density estimation method may be used.
  • the maintenance work occurrence probability density estimated in S524 is integrated with respect to the deterioration degree, and the cumulative maintenance work occurrence probability (probability that maintenance work occurs before reaching a certain deterioration degree) is calculated (S525).
  • the degree of deterioration of the target component of the plasma processing apparatus 11 from the time of maintenance work to the time of calculation is acquired from the degree of deterioration storage unit 220 (S531). Further, the future transition of the deterioration degree is predicted from the transition of the deterioration degree up to the calculation time (S532). At this time, the confidence interval of the forecast is also calculated.
  • the present prediction method is not particularly limited, but for example, an autoregressive model which is a time series prediction method may be used.
  • the date and time of future planned maintenance of the target plasma processing device 11 and the work contents are acquired from the maintenance plan storage unit 320 (S533). Further, from the predicted value of the degree of deterioration at the time of future planned maintenance, its confidence interval, and the cumulative maintenance work occurrence probability calculated by the maintenance work occurrence probability estimation unit 31, future planned maintenance as shown in graph 110 of FIG.
  • the estimated value 1101 of the maintenance work occurrence probability at the time point (in the graph 1100 of FIG. 11, the time point of the date and time t1, t2, t3) and the confidence interval 1102 thereof are calculated (S534).
  • the actual maintenance cost related to the maintenance work of interest is acquired from the actual maintenance cost storage unit 330 (S535). Further, the expected maintenance cost and its confidence interval at each planned maintenance time point are calculated from the estimated value of the maintenance work occurrence probability calculated in S534 and its confidence interval, and the actual maintenance cost acquired in S535 (S536).
  • the expected value of the maintenance cost is (probability that maintenance work will occur by t1) ⁇ (unplanned maintenance). It can be calculated by (actual maintenance cost when performing planned maintenance) + (probability that maintenance work does not occur by t1) x (actual maintenance cost when planned maintenance is performed).
  • the calculated result is stored in the maintenance cost storage unit 230 at the time of planning incorporation.
  • the expected maintenance cost and the confidence interval 233 when each maintenance work 232 is incorporated at each planned maintenance time point are stored. ..
  • the example shown in FIG. 12 shows an example in which the operating time is selected as the maintenance cost type 234.
  • FIG. 13 shows an example of the display screen 341 of the maintenance plan amendment plan.
  • the recommended additional work 345 at each planned maintenance date and time 344 is displayed in a list so that the selected maintenance cost is minimized.
  • the user can immediately determine the necessary unplanned maintenance work that was not included in the original maintenance plan and at what point in time the planned maintenance should be incorporated from the viewpoint of the priority maintenance cost. Can be done.
  • the device diagnostic device for diagnosing the device state of the plasma processing device receives the output of the sensor for monitoring the device state of the plasma processing device mounted on the plasma processing device and plasma.
  • the deterioration degree estimation unit that estimates the deterioration degree of the processing equipment, and the initial maintenance plan of the plasma processing equipment until the plasma processing equipment reaches a certain deterioration degree based on the deterioration degree of the plasma processing equipment estimated by this deterioration degree estimation unit.
  • Estimated by the maintenance work occurrence probability estimation unit that calculates the probability that unplanned maintenance work that is not included in the above, the actual maintenance cost calculation unit that calculates the actual maintenance cost of the plasma processing device, and the maintenance work occurrence probability estimation unit.
  • Initial maintenance plan for plasma processing equipment that incorporates unplanned maintenance work based on the probability that unplanned maintenance work will occur for the plasma processing equipment and the actual maintenance cost of the plasma processing equipment calculated by the actual maintenance cost calculation unit. It was configured with a maintenance cost calculation unit at the time of planning incorporation that outputs a revised maintenance plan revision plan.
  • each maintenance in the maintenance history of the plasma processing device is performed by the actual maintenance cost calculation unit of the device diagnosis device. Specify the parts and combinations of work, calculate the actual maintenance cost such as the equipment operation rate of the plasma processing equipment for each maintenance work, and output the sensor that monitors the equipment status of the plasma processing equipment installed in the plasma processing equipment.
  • the maintenance work occurrence probability estimation unit of the equipment diagnostic device estimates the maintenance work occurrence probability of unplanned maintenance work of the plasma processing device from the deterioration degree of the plasma processing device obtained by receiving Calculation of maintenance cost at the time of planning installation of equipment diagnostic equipment based on the probability of maintenance work occurrence and actual maintenance cost of plasma processing equipment calculated by the actual maintenance cost calculation unit
  • the department creates a maintenance plan revision plan that corrects the initial maintenance plan of the plasma processing device by incorporating unplanned maintenance work, and outputs the maintenance plan revision plan created by the maintenance cost calculation section when incorporating the plan into the device diagnostic device. I tried to output from the part.
  • the occurrence of unplanned maintenance that may occur in the plasma processing apparatus 11 is predicted in advance, and at what point in time a user such as a maintenance planner or a maintenance worker performs necessary maintenance work and the work. It is possible to immediately determine whether to incorporate it into planned maintenance from the viewpoint of priority maintenance cost.
  • the recommended additional work 345 at each planned maintenance date and time 344 is displayed in a list so that the selected maintenance cost is minimized.
  • this embodiment is not limited to this, and the selected maintenance is not limited to this.
  • a plurality of recommended additional work 345s at each planned maintenance date and time 344 so that the cost becomes the second or third smallest may be displayed in a list so that the recommended additional work 345 can be selected from the plurality of recommended additional work 345s.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Plasma & Fusion (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Manufacturing & Machinery (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Plasma Technology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Mechanical Treatment Of Semiconductor (AREA)
  • Testing Of Individual Semiconductor Devices (AREA)
  • Internal Circuitry In Semiconductor Integrated Circuit Devices (AREA)
PCT/JP2020/023386 2020-06-15 2020-06-15 装置診断装置、装置診断方法、プラズマ処理装置および半導体装置製造システム Ceased WO2021255784A1 (ja)

Priority Applications (8)

Application Number Priority Date Filing Date Title
PCT/JP2020/023386 WO2021255784A1 (ja) 2020-06-15 2020-06-15 装置診断装置、装置診断方法、プラズマ処理装置および半導体装置製造システム
CN202511740576.6A CN121563475A (zh) 2020-06-15 2020-06-15 装置诊断装置、装置诊断方法、等离子处理装置以及半导体装置制造系统
KR1020217016709A KR102648654B1 (ko) 2020-06-15 2020-06-15 장치 진단 장치, 장치 진단 방법, 플라스마 처리 장치 및 반도체 장치 제조 시스템
JP2021526327A JPWO2021255784A1 (https=) 2020-06-15 2020-06-15
US17/431,516 US12387921B2 (en) 2020-06-15 2020-06-15 Apparatus diagnostic apparatus, apparatus diagnostic method, plasma processing apparatus and semiconductor device manufacturing system
CN202080007081.1A CN114096972A (zh) 2020-06-15 2020-06-15 装置诊断装置、装置诊断方法、等离子处理装置以及半导体装置制造系统
TW110121443A TWI780764B (zh) 2020-06-15 2021-06-11 裝置診斷裝置、裝置診斷方法、電漿處理裝置及半導體裝置製造系統
JP2023095156A JP7716442B2 (ja) 2020-06-15 2023-06-09 装置診断装置、装置診断方法、プラズマ処理装置および半導体装置製造システム

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/023386 WO2021255784A1 (ja) 2020-06-15 2020-06-15 装置診断装置、装置診断方法、プラズマ処理装置および半導体装置製造システム

Publications (1)

Publication Number Publication Date
WO2021255784A1 true WO2021255784A1 (ja) 2021-12-23

Family

ID=79178432

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/023386 Ceased WO2021255784A1 (ja) 2020-06-15 2020-06-15 装置診断装置、装置診断方法、プラズマ処理装置および半導体装置製造システム

Country Status (6)

Country Link
US (1) US12387921B2 (https=)
JP (2) JPWO2021255784A1 (https=)
KR (1) KR102648654B1 (https=)
CN (2) CN114096972A (https=)
TW (1) TWI780764B (https=)
WO (1) WO2021255784A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023175661A1 (ja) * 2022-03-14 2023-09-21 株式会社日立ハイテク 診断装置、半導体製造装置システム、半導体装置製造システムおよび診断方法

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7311817B2 (ja) * 2021-06-16 2023-07-20 ダイキン工業株式会社 制御装置、及び制御システム
KR102800655B1 (ko) * 2022-02-25 2025-04-29 주식회사 테크위즈 환경안전관리 적용 장치에 대한 고장열화 예지보전 시스템 및 그 방법
US20230280736A1 (en) * 2022-03-02 2023-09-07 Applied Materials, Inc. Comprehensive analysis module for determining processing equipment performance
JP7564334B2 (ja) * 2022-03-24 2024-10-08 株式会社日立ハイテク 装置診断システム、装置診断装置、半導体装置製造システムおよび装置診断方法
KR20240131986A (ko) * 2023-02-21 2024-09-02 주식회사 히타치하이테크 이상 검출 장치 및 이상 검출 방법

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009124677A (ja) * 2007-11-15 2009-06-04 Toshiba Corp 保守計画システム、および保守計画方法
JP2009199596A (ja) * 2008-02-19 2009-09-03 Toshiba Corp 保守計画システム、保守計画方法及び画像形成装置
JP2015148867A (ja) * 2014-02-05 2015-08-20 株式会社日立パワーソリューションズ 情報処理装置、診断方法、およびプログラム
JP2016057730A (ja) * 2014-09-08 2016-04-21 新日鐵住金株式会社 製鋼工場における操業スケジュール作成方法および作成装置
JP2018036939A (ja) * 2016-09-01 2018-03-08 日立Ｇｅニュークリア・エナジー株式会社 プラント監視装置及びプラント監視方法
WO2018079778A1 (ja) * 2016-10-31 2018-05-03 日本電気株式会社 生産管理装置、方法、プログラム
JP2020034585A (ja) * 2018-08-27 2020-03-05 コニカミノルタ株式会社 画像形成装置、画像形成システム、およびメンテナンス支援システム

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2004019396A1 (ja) * 2002-08-13 2004-03-04 Tokyo Electron Limited プラズマ処理方法及びプラズマ処理装置
JP2004334457A (ja) 2003-05-07 2004-11-25 Mitsubishi Electric Corp 点検計画作成装置及び点検計画作成方法
JP2005286206A (ja) * 2004-03-30 2005-10-13 Hitachi High-Technologies Corp 半導体製造装置およびその監視・解析支援方法
US7152011B2 (en) * 2004-08-25 2006-12-19 Lam Research Corporation Smart component-based management techniques in a substrate processing system
JP4776590B2 (ja) 2007-06-19 2011-09-21 株式会社日立製作所 保守管理支援装置およびその表示方法、保守管理支援システム
US20090132321A1 (en) 2007-11-15 2009-05-21 Kabushiki Kaisha Toshiba Maintenance planning system and maintenance planning method
US7586100B2 (en) * 2008-02-12 2009-09-08 Varian Semiconductor Equipment Associates, Inc. Closed loop control and process optimization in plasma doping processes using a time of flight ion detector
US8022718B2 (en) * 2008-02-29 2011-09-20 Lam Research Corporation Method for inspecting electrostatic chucks with Kelvin probe analysis
JP4977064B2 (ja) * 2008-03-12 2012-07-18 株式会社東芝 保守計画支援システム
US9831111B2 (en) * 2014-02-12 2017-11-28 Applied Materials, Inc. Apparatus and method for measurement of the thermal performance of an electrostatic wafer chuck
JP6418791B2 (ja) 2014-05-29 2018-11-07 株式会社日立製作所 冷却装置の異常検知システム
JP2016057736A (ja) * 2014-09-08 2016-04-21 富士ゼロックス株式会社 情報処理装置、及びプログラム。
WO2016125248A1 (ja) 2015-02-03 2016-08-11 株式会社日立製作所 保守支援システム、保守支援方法、及び、保守支援プログラム
JP6723669B2 (ja) * 2016-09-27 2020-07-15 東京エレクトロン株式会社 異常検知プログラム、異常検知方法および異常検知装置
US11702748B2 (en) * 2017-03-03 2023-07-18 Lam Research Corporation Wafer level uniformity control in remote plasma film deposition
JP6926008B2 (ja) * 2018-01-31 2021-08-25 株式会社日立製作所 保守計画装置、及び保守計画方法
SG11202009105YA (en) 2018-03-20 2020-10-29 Tokyo Electron Ltd Self-aware and correcting heterogenous platform incorporating integrated semiconductor processing modules and method for using same
CN109019211B (zh) * 2018-08-02 2020-10-20 深圳爱梯物联网控股有限公司 一种电梯维修保养作业辅助装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009124677A (ja) * 2007-11-15 2009-06-04 Toshiba Corp 保守計画システム、および保守計画方法
JP2009199596A (ja) * 2008-02-19 2009-09-03 Toshiba Corp 保守計画システム、保守計画方法及び画像形成装置
JP2015148867A (ja) * 2014-02-05 2015-08-20 株式会社日立パワーソリューションズ 情報処理装置、診断方法、およびプログラム
JP2016057730A (ja) * 2014-09-08 2016-04-21 新日鐵住金株式会社 製鋼工場における操業スケジュール作成方法および作成装置
JP2018036939A (ja) * 2016-09-01 2018-03-08 日立Ｇｅニュークリア・エナジー株式会社 プラント監視装置及びプラント監視方法
WO2018079778A1 (ja) * 2016-10-31 2018-05-03 日本電気株式会社 生産管理装置、方法、プログラム
JP2020034585A (ja) * 2018-08-27 2020-03-05 コニカミノルタ株式会社 画像形成装置、画像形成システム、およびメンテナンス支援システム

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023175661A1 (ja) * 2022-03-14 2023-09-21 株式会社日立ハイテク 診断装置、半導体製造装置システム、半導体装置製造システムおよび診断方法
JPWO2023175661A1 (https=) * 2022-03-14 2023-09-21
JP7471513B2 (ja) 2022-03-14 2024-04-19 株式会社日立ハイテク 診断装置、半導体製造装置システム、半導体装置製造システムおよび診断方法
TWI849766B (zh) * 2022-03-14 2024-07-21 日商日立全球先端科技股份有限公司 診斷裝置、半導體製造裝置系統、半導體裝置製造系統及診斷方法
US20240321608A1 (en) * 2022-03-14 2024-09-26 Hitachi High-Tech Corporation Diagnostic device, semiconductor manufacturing equipment system, semiconductor equipment manufacturing system, and diagnostic method

Also Published As

Publication number Publication date
JPWO2021255784A1 (https=) 2021-12-23
CN121563475A (zh) 2026-02-24
KR102648654B1 (ko) 2024-03-19
JP7716442B2 (ja) 2025-07-31
KR20210157392A (ko) 2021-12-28
JP2023105229A (ja) 2023-07-28
TW202201591A (zh) 2022-01-01
TWI780764B (zh) 2022-10-11
US20220399182A1 (en) 2022-12-15
US12387921B2 (en) 2025-08-12
CN114096972A (zh) 2022-02-25

Similar Documents

Publication Publication Date Title
WO2021255784A1 (ja) 装置診断装置、装置診断方法、プラズマ処理装置および半導体装置製造システム
CN115244482B (zh) 用于维护优化的混合风险模型和用于执行此类方法的系统
US20190318288A1 (en) Computer Systems And Methods For Performing Root Cause Analysis And Building A Predictive Model For Rare Event Occurrences In Plant-Wide Operations
US11796992B2 (en) Condition-based method for malfunction prediction
JP5129725B2 (ja) 装置異常診断方法及びシステム
CN108780315B (zh) 用于优化旋转设备的诊断的方法和装置
WO2011086805A1 (ja) 異常検知方法及び異常検知システム
US20200159197A1 (en) Manufacturing condition specifying system and method
JP5413240B2 (ja) イベント予測システムおよびイベント予測方法、ならびにコンピュータ・プログラム
US12001180B2 (en) Condition-based method for malfunction prediction
JP7188470B2 (ja) 分析方法、分析プログラムおよび情報処理装置
EP4136515B1 (en) Method, apparatus and computer program product for monitoring of industrial devices
CN115699045A (zh) 用于执行资产的预测健康分析的方法和计算系统
KR102328842B1 (ko) 설비 관리 방법 및 이를 실행하는 장치
JP6697980B2 (ja) 設備点検順位設定装置及び設備点検順位設定方法
JP4862446B2 (ja) 障害原因推定システム、方法、及び、プログラム
Bouzidi et al. Deep learning for a customised head-mounted fault display system for the maintenance of wind turbines
US11954615B2 (en) Model management for non-stationary systems
Yang et al. APU FMEA validation and its application to fault identification
Han et al. Development of Autonomous Failure Maintenance System for Semiconductor Manufacturing
KR20210034846A (ko) 가스터빈 예열시간 예측 시스템
Rodriguez et al. Integrating IoT and Modelling for Predictive Maintenance in Industry 4.0
Medon A Framework for a Predictive Manitenance Tool Articulated with a Manufacturing Execution System
CN121436381A (zh) 设备生产数据处理方法和系统
Suzuki et al. An Online Anomaly Detection System Supporting Batch-Process Operator Decision-Making

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2021526327

Country of ref document: JP

Kind code of ref document: A

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20940894

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20940894

Country of ref document: EP

Kind code of ref document: A1

WWG Wipo information: grant in national office

Ref document number: 17431516

Country of ref document: US