CN116046078A - Fault monitoring and early warning method and system for semiconductor cleaning equipment - Google Patents
Fault monitoring and early warning method and system for semiconductor cleaning equipment Download PDFInfo
- Publication number
- CN116046078A CN116046078A CN202310335566.9A CN202310335566A CN116046078A CN 116046078 A CN116046078 A CN 116046078A CN 202310335566 A CN202310335566 A CN 202310335566A CN 116046078 A CN116046078 A CN 116046078A
- Authority
- CN
- China
- Prior art keywords
- cleaning
- early warning
- monitoring
- information
- module
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 231
- 238000004140 cleaning Methods 0.000 title claims abstract description 225
- 238000000034 method Methods 0.000 title claims abstract description 49
- 239000004065 semiconductor Substances 0.000 title claims abstract description 42
- 239000007788 liquid Substances 0.000 claims abstract description 156
- 239000000126 substance Substances 0.000 claims abstract description 100
- 238000004458 analytical method Methods 0.000 claims abstract description 99
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 99
- 230000005540 biological transmission Effects 0.000 claims abstract description 46
- 230000004927 fusion Effects 0.000 claims abstract description 27
- 239000003814 drug Substances 0.000 claims description 89
- 230000008021 deposition Effects 0.000 claims description 15
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 238000013506 data mapping Methods 0.000 claims description 8
- 230000033764 rhythmic process Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 8
- 238000007405 data analysis Methods 0.000 abstract description 7
- 230000002159 abnormal effect Effects 0.000 description 11
- 238000013507 mapping Methods 0.000 description 9
- 238000000605 extraction Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000010276 construction Methods 0.000 description 6
- 238000012512 characterization method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 239000012535 impurity Substances 0.000 description 5
- 230000005856 abnormality Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 2
- 230000000149 penetrating effect Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 238000004090 dissolution Methods 0.000 description 1
- 238000005868 electrolysis reaction Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Cleaning Or Drying Semiconductors (AREA)
Abstract
The invention provides a fault monitoring and early warning method and system for semiconductor cleaning equipment, which relate to the technical field of data analysis, and are used for monitoring and acquiring mobile monitoring data of a manipulator, chemical liquid transmission data, monitoring data of a cleaning cavity and water circulation flow monitoring data, inputting a characteristic analysis module to determine cleaning operation characteristics of each part, inputting an operation characteristic prediction model to obtain a prediction result of each part, and if the early warning condition is met, executing early warning, solving the problems that in the prior art, the fault monitoring and early warning method for the semiconductor cleaning equipment is insufficient in analysis depth and completeness, fault measurement is only carried out on the monitorable data, the fault monitoring result is insufficient in precision, potential fault factors are ignored, the technical problem of influencing the operation accuracy of the equipment is solved, the analysis and prediction are carried out by extracting single component characteristics and fusion characteristics, the analysis depth and the comprehensiveness are improved, the accuracy of the analysis result is improved, the targeted early warning is carried out on different fault analysis results, and the timely effectiveness of overhaul is ensured.
Description
Technical Field
The invention relates to the technical field of data analysis, in particular to a fault monitoring and early warning method and system of semiconductor cleaning equipment.
Background
The cleaning step is an important link penetrating through the semiconductor industry chain, and directly influences the yield of finished products of integrated circuits, so that the cleaning energy efficiency is strictly controlled, and the standardized operation of semiconductor cleaning equipment is ensured. During the operation of the semiconductor cleaning apparatus, there is inevitably a malfunction operation to affect the cleaning effect. At present, integrated monitoring is mainly carried out by arranging monitoring equipment, fault evaluation is carried out based on monitoring operation states, or spot inspection is carried out on cleaning products so as to carry out cleaning live determination, and fault positioning maintenance is carried out on existing abnormal data. The current fault monitoring and early warning mode is more traditional, and has certain defects.
In the prior art, the fault monitoring and early warning method of the semiconductor cleaning equipment is insufficient in analysis depth and completeness, fault measurement is only carried out on the monitorable data, so that the fault monitoring result is insufficient in accuracy, potential fault factors are ignored, and the operation accuracy of the equipment is affected.
Disclosure of Invention
The application provides a fault monitoring and early warning method and system for semiconductor cleaning equipment, which are used for solving the technical problems that in the prior art, the analysis depth and completeness of the fault monitoring and early warning method for the semiconductor cleaning equipment are insufficient, fault measurement is only carried out on monitorable data, the accuracy of a fault monitoring result is insufficient, potential fault factors are ignored, and the operation accuracy of the equipment is affected.
In view of the above problems, the present application provides a fault monitoring and early warning method and system for a semiconductor cleaning device.
In a first aspect, the present application provides a fault monitoring and early warning method for a semiconductor cleaning apparatus, the method including:
the manipulator monitoring module is connected with manipulator monitoring equipment to acquire manipulator movement monitoring data;
the chemical liquid medicine transmission module is connected with chemical liquid medicine configuration execution equipment to obtain chemical liquid medicine transmission data;
the cleaning chamber monitoring module is connected with cleaning chamber liquid monitoring equipment to acquire monitoring data of the cleaning chamber;
the water circulation monitoring module is connected with water circulation flow monitoring equipment to obtain water circulation flow monitoring data;
taking the mobile monitoring data of the manipulator, the chemical liquid transmission data, the monitoring data of the cleaning chamber and the water circulation flow monitoring data as input variables, and inputting the input variables into a characteristic analysis module for carrying out operation characteristic analysis and fusion characteristic analysis of each part to determine the cleaning operation characteristics of each part;
inputting the cleaning operation characteristics of each part into an operation characteristic prediction model to obtain a prediction result of each part;
and when any one of the cleaning operation characteristics of each part and the predicted results of each part reaches the early warning condition, sending early warning information according to an early warning sending rule.
In a second aspect, the present application provides a fault monitoring and early warning system for a semiconductor cleaning apparatus, the system comprising:
the manipulator movement monitoring data acquisition module is used for acquiring manipulator movement monitoring data by connecting the manipulator monitoring module with manipulator monitoring equipment;
the chemical liquid medicine transmission data acquisition module is used for connecting chemical liquid medicine configuration execution equipment through the chemical liquid medicine transmission module to acquire chemical liquid medicine transmission data;
the cleaning chamber monitoring data acquisition module is used for acquiring monitoring data of the cleaning chamber through connection of the cleaning chamber monitoring module and cleaning chamber liquid monitoring equipment;
the circulating flow monitoring data acquisition module is used for connecting the circulating flow monitoring module with the water circulating flow monitoring equipment to obtain water circulating flow monitoring data;
the characteristic analysis module is used for taking the manipulator movement monitoring data, the chemical liquid medicine transmission data, the monitoring data of the cleaning chamber and the water circulation flow monitoring data as input variables, inputting the input variables into the characteristic analysis module for carrying out the operation characteristic analysis of each part and the fusion characteristic analysis of each part, and determining the cleaning operation characteristics of each part;
The feature prediction module is used for inputting the cleaning operation features of the components into an operation feature prediction model to obtain the prediction results of the components;
and the result early warning module is used for sending early warning information according to an early warning sending rule when any result of the cleaning operation characteristics of each part and the predicted result of each part reaches an early warning condition.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the fault monitoring and early warning method for the semiconductor cleaning equipment, the manipulator monitoring module is connected with the manipulator monitoring equipment to obtain the manipulator movement monitoring data; the chemical liquid medicine transmission module is connected with chemical liquid medicine configuration execution equipment to obtain chemical liquid medicine transmission data; the cleaning chamber monitoring module is connected with cleaning chamber liquid monitoring equipment to acquire monitoring data of the cleaning chamber; the method comprises the steps of connecting a water circulation monitoring module with water circulation flow monitoring equipment to obtain water circulation flow monitoring data, further inputting a feature analysis module to perform feature analysis of each part and feature analysis of fusion of each part, determining the cleaning operation feature of each part, inputting an operation feature prediction model to obtain a prediction result of each part, and sending early warning information according to an early warning sending rule when any result of the cleaning operation feature of each part and the prediction result of each part reaches an early warning condition, so that the defects of analysis depth and completeness of a fault monitoring early warning method for semiconductor cleaning equipment in the prior art are overcome, fault measurement is performed only on the monitorable data, the defect of fault monitoring result precision is caused, potential fault factors are ignored, the technical problem of influencing the operation accuracy of the equipment is solved, the analysis and the prediction are performed by extracting single component features and fusion features, the analysis depth and the comprehensiveness are improved, the accuracy of the analysis result is improved, and the timeliness of overhaul is ensured.
Drawings
Fig. 1 is a schematic flow chart of a fault monitoring and early warning method of a semiconductor cleaning device;
fig. 2 is a schematic diagram of a process for constructing a list of operation features of a manipulator in a fault monitoring and early warning method of a semiconductor cleaning device;
fig. 3 is a schematic diagram of a process for setting early warning conditions in a fault monitoring and early warning method of a semiconductor cleaning device;
fig. 4 is a schematic structural diagram of a fault monitoring and early warning system of a semiconductor cleaning device.
Reference numerals illustrate: the device comprises a manipulator mobile monitoring data acquisition module 11, a chemical liquid transmission data acquisition module 12, a cleaning chamber monitoring data acquisition module 13, a circulating flow monitoring data acquisition module 14, a characteristic analysis module 15, a characteristic prediction module 16 and a result early warning module 17.
Detailed Description
According to the fault monitoring and early warning method and system for the semiconductor cleaning equipment, the mobile monitoring data of the manipulator, the chemical liquid medicine transmission data, the monitoring data of the cleaning chamber and the water circulation flow monitoring data are monitored and acquired, the input characteristic analysis module determines the cleaning operation characteristics of each part, the input operation characteristic prediction model obtains the prediction results of each part, and when any result reaches the early warning condition, early warning information is sent, so that the technical problems that the analysis depth and the completeness of the fault monitoring and early warning method for the semiconductor cleaning equipment are insufficient, fault measurement is only carried out on the monitorable data, the accuracy of the fault monitoring result is insufficient, potential fault factors are ignored, and the operation accuracy of the equipment is affected in the prior art are solved.
Embodiment one: as shown in fig. 1, the present application provides a fault monitoring and early warning method of a semiconductor cleaning device, where the method is applied to a fault monitoring and early warning system, and the fault monitoring and early warning system includes a manipulator monitoring module, a chemical liquid transmission module, a cleaning chamber monitoring module, and a water circulation monitoring module, and the method includes:
step S100: the manipulator monitoring module is connected with manipulator monitoring equipment to acquire manipulator movement monitoring data;
specifically, the cleaning step is an important link penetrating through the semiconductor industry chain, and directly affects the yield of finished products of integrated circuits, so that the cleaning energy efficiency is strictly controlled, and the standardized operation of semiconductor cleaning equipment is ensured. The fault monitoring method of the semiconductor cleaning equipment is applied to a fault monitoring system, the system is a total control system for performing complete monitoring and early warning on the whole bit plane of the fault of the semiconductor cleaning equipment, the system comprises a mechanical arm monitoring module, a chemical liquid transmission module, a cleaning chamber monitoring module and a plurality of functional modules of a water circulation monitoring module, and suitability monitoring equipment is respectively connected with the functional modules of the cleaning chamber monitoring module and the water circulation monitoring module and corresponds to operation parts of the semiconductor cleaning equipment and is used for monitoring data acquisition so as to determine timeliness and accuracy monitoring data.
Specifically, the manipulator is for carrying out the subassembly of semiconductor product centre gripping, manipulator monitoring module is for carrying out the monitoring control and the execution module of data entry of manipulator, manipulator monitoring module with manipulator monitoring equipment is connected, manipulator monitoring equipment is for laying the monitoring equipment in manipulator operation space, can be image acquisition equipment, track monitoring equipment etc. for example, based on the manipulator monitoring equipment carries out real-time operation and gathers, will monitor data feedback to in the manipulator monitoring module, carries out monitor data statistics rule, generates manipulator removal monitor data, manipulator removal monitor data is the acquisition source data who carries out failure analysis.
Step S200: the chemical liquid medicine transmission module is connected with chemical liquid medicine configuration execution equipment to obtain chemical liquid medicine transmission data;
step S300: the cleaning chamber monitoring module is connected with cleaning chamber liquid monitoring equipment to acquire monitoring data of the cleaning chamber;
step S400: the water circulation monitoring module is connected with water circulation flow monitoring equipment to obtain water circulation flow monitoring data;
specifically, the chemical liquid is used for cleaning semiconductor products, cleaning requirements corresponding to different cleaning process nodes are different, so that chemical liquid types are different, the chemical liquid transmission module is control execution equipment for performing chemical liquid configuration monitoring, the chemical liquid transmission module is connected with the chemical liquid configuration execution equipment, the chemical liquid configuration execution equipment is monitored to obtain chemical liquid configuration flow data, the chemical liquid configuration flow data comprises raw materials, content and the like, and the chemical liquid configuration flow data is transmitted into the chemical liquid transmission module in a statistical and regular mode to obtain the chemical liquid transmission data.
Further, the cleaning cavity is an execution space for cleaning semiconductor products, the cleaning cavity monitoring module is an execution module for cleaning monitoring control, the cleaning cavity monitoring module is connected with the cleaning cavity liquid monitoring equipment, the cleaning cavity liquid monitoring equipment is used for monitoring real-time cleaning working conditions and can be multi-type sensing monitoring equipment, multi-dimensional real-time cleaning data are collected, data attribution integration is carried out based on data types, and the chemical liquid transmission data are acquired by leading the chemical liquid transmission module.
Further, the water circulation monitoring module is used for carrying out circulation flow monitoring of liquid medicine cleaning so as to carry out circulation influence analysis of liquid medicine and fusion impurities, the water circulation flow monitoring equipment is auxiliary monitoring and collecting equipment of flow data in a cleaning process, and the water circulation monitoring module is connected with the water circulation flow monitoring equipment and used for carrying out equipment monitoring control and monitoring data import statistics to acquire the water circulation flow monitoring data. The monitoring data are all part classification acquisition results of the semiconductor cleaning equipment, have aging consistency and are used as data sources to be analyzed for abnormality judgment and early warning of the semiconductor cleaning equipment.
Step S500: taking the mobile monitoring data of the manipulator, the chemical liquid transmission data, the monitoring data of the cleaning chamber and the water circulation flow monitoring data as input variables, and inputting the input variables into a characteristic analysis module for carrying out operation characteristic analysis and fusion characteristic analysis of each part to determine the cleaning operation characteristics of each part;
specifically, the manipulator movement monitoring data, the chemical liquid transmission data, the monitoring data of the cleaning chamber and the water circulation flow monitoring data are operating component monitoring data sources of the semiconductor cleaning equipment. The feature analysis module is constructed and is a self-defined feature recognition analysis functional area meeting analysis requirements, and the feature analysis module comprises a single-component operation feature analysis sub-module and a component fusion feature analysis sub-module and is used for performing feature recognition extraction analysis. The following is a feasibility construction mode: and aiming at a module analysis component, collecting sample monitoring data for analysis, carrying out manual identification analysis and feature extraction aiming at a required feature dimension, determining corresponding sample identification features, mapping and corresponding the sample monitoring data and the sample identification features, carrying out neural network training by taking the sample monitoring data and the sample identification features as construction data to complete sub-module construction, embedding a corresponding sample monitoring data identification analysis algorithm into a corresponding sub-module, integrating a plurality of sub-modules, and generating the feature analysis module, wherein the construction methods of the plurality of sub-modules are the same. Inputting the monitoring data source of the operation part into the feature analysis module to respectively perform single feature analysis and fusion feature analysis so as to improve the completeness and accuracy of a feature analysis result and generate the cleaning operation feature of each part.
Further, as shown in fig. 2, step S500 of the present application further includes:
step S510-1: extracting a manipulator movement track, a manipulator movement amplitude and working time according to the manipulator movement monitoring data;
step S520-1: extracting operation characteristics according to the movement track of the manipulator, the movement amplitude of the manipulator and the working time to obtain a manipulator operation characteristic set;
step S530-1: and carrying out alignment processing on the manipulator operation feature set based on the corresponding relation of the working time, and constructing a manipulator operation feature list.
Specifically, mapping and matching are carried out on the manipulator monitoring data and a plurality of sub-modules in the feature analysis module, the mapping and matching are transmitted to the corresponding single-component operation feature analysis sub-module, the manipulator movement monitoring data is identified and extracted based on a sub-module identification and analysis mechanism, the module identification and analysis mechanism is generated by training a sample data and sample monitoring data identification and analysis algorithm, and the execution analysis can be directly carried out. Specifically, based on the manipulator movement monitoring data, the manipulator movement track, the manipulator movement amplitude and the working time are extracted, for example, the extraction can be performed based on a data representation form. When the operation fault analysis of the manipulator is performed, for example, loosening and the like, the assessment analysis is mainly performed by moving track, time and amplitude. And based on the movement track of the manipulator, the movement amplitude of the manipulator and the working time, performing operation feature recognition extraction, such as track deviation degree, amplitude range, accumulated working time length and the like, generating a manipulator operation feature set, and taking the manipulator operation feature set as a sub-module output result. And further performing mapping of the simultaneous sequence features on the basis of the identification time of the manipulator operation feature set to generate a plurality of feature sequences, wherein the feature sequences respectively correspond to different time nodes, and the feature sequences are integrated on the basis of time sequence propulsion to generate the manipulator operation feature list. The manipulator operation characteristic list is the basis for analyzing abnormal operation of the components.
Further, step S500 of the present application further includes:
step S510-2: obtaining chemical liquid medicine components, concentration requirements and liquid medicine replenishment information according to the chemical liquid medicine transmission data, wherein the liquid medicine replenishment information comprises replenishment time and replenishment quantity;
step S520-2: performing cleaning target characteristic analysis according to the chemical liquid composition and concentration requirements, and determining liquid cleaning characteristics;
step S530-2: carrying out replenishment matching relation analysis according to the liquid medicine cleaning characteristics and the liquid medicine replenishment information to determine replenishment matching characteristics;
step S540-2: and obtaining a chemical liquid medicine operation characteristic set based on the liquid medicine cleaning characteristic and the replenishment matching characteristic.
Specifically, the chemical liquid medicine transmission data are transmitted to a corresponding single-component operation feature analysis sub-module in the feature analysis module, data analysis is carried out to determine the configuration components and the configuration content identification of the chemical liquid medicine, the chemical liquid medicine components and the concentration requirements are obtained, the liquid medicine replenishment time and the corresponding single replenishment amount are identified, and the liquid medicine replenishment information is determined. Based on the chemical liquid medicine components and the concentration requirement, carrying out refined feature extraction, and exemplarily, extracting each component feature, such as visual characterization state and the like; chemical liquid concentration measurement, such as a concentration change rate, etc., is performed as the liquid cleaning feature. And carrying out replenishment matching analysis on the liquid medicine cleaning characteristics and the liquid medicine replenishment information, determining a plurality of concentration-replenishment quantity-concentration adjustment characterization sequences for carrying out real-time replenishment situation measurement, and taking the concentration-replenishment quantity-concentration adjustment characterization sequences as the replenishment matching characteristics for carrying out chemical liquid medicine replenishment adjustment analysis, wherein if replenishment adjustment is suspected, part abnormality is indicated. Mapping and corresponding the liquid medicine cleaning characteristics and the replenishment matching characteristics to generate the chemical liquid medicine operation characteristic set. The chemical liquid medicine operation characteristic set is a data source for evaluating the abnormal operation of the equipment components.
Further, step S500 of the present application further includes:
step S510-3: extracting ultrasonic amplitude information, cleaning flow information, temperature information, liquid level information, cleaning element information and corresponding chemical liquid information according to the monitoring data of the cleaning chamber;
step S520-3: based on the cleaning flow information, establishing a cleaning chamber data mapping relation between the ultrasonic amplitude information, the temperature information, the liquid level information, the cleaning element information, the chemical liquid medicine information and the cleaning flow information;
step S530-3: acquiring ultrasonic control parameter information, analyzing the matching relation based on the ultrasonic control parameter information and the ultrasonic amplitude information, and determining the amplitude matching degree characteristic;
step S540-3: performing cleaning characteristic analysis according to the cleaning cavity data mapping relation to determine cleaning cavity characteristics;
step S550-3: and taking the amplitude matching degree characteristic and the cleaning cavity characteristic as operation characteristics of the cleaning cavity.
Specifically, the monitoring data of the cleaning chamber is input into a corresponding single-component operation characteristic analysis sub-module in the characteristic analysis module, the monitoring data of the cleaning chamber is identified and extracted, the ultrasonic amplitude information, the cleaning flow information, the temperature information, the liquid level information, the cleaning element information and the corresponding chemical liquid medicine information are obtained, the parameter data represent the live condition of the cleaning step, and the identification and the extraction can be directly carried out. And the cleaning parameter requirements corresponding to different cleaning flow nodes are different, for example, the cleaning requirements are different due to the difference of impurity contents in the early stage and the middle stage of cleaning, the cleaning flow information is used as a pushing basis, the cleaning flow information is carried out, the mapping correspondence of the ultrasonic amplitude information, the temperature information, the liquid level information, the cleaning element information and the chemical liquid medicine information is established, and the cleaning chamber data mapping relation is generated. And acquiring ultrasonic control parameter information, such as ultrasonic frequency spectrum and the like, mapping the ultrasonic control parameter information with the ultrasonic amplitude information, determining a matching result of the control parameter and the control effect, analyzing whether the control parameter and the control effect are consistent to generate the amplitude matching degree characteristic, and when the matching degree of the control parameter and the control effect is lower, indicating that the existing control deviation is larger and the adjustment and the rest are to be regulated. And carrying out cleaning characteristic analysis on the cleaning chamber data mapping relation, and determining characterization states of different cleaning periods along with the promotion of the cleaning flow information as the cleaning chamber characteristics. Integrating the amplitude matching degree characteristic with the cleaning cavity characteristic to serve as an operation characteristic of the cleaning cavity. The operation characteristic of the cleaning chamber is a data source for carrying out abnormal operation analysis on the cleaning link component.
Further, step S500 of the present application further includes:
step S510-4: extracting water circulation flow data and water circulation liquid medicine information according to the water circulation flow monitoring data;
step S520-4: and carrying out time alignment based on the water circulation flow data and the water circulation liquid medicine information, and determining the water circulation operation characteristics.
Specifically, the water circulation flow monitoring data are input into a corresponding single-component operation feature analysis sub-module in the feature analysis module, the water circulation flow data and the water circulation liquid medicine information are determined through data identification, and due to the difference of impurity fusion features, influences, such as impurity deposition and the like, on a water circulation pipeline can exist, so that normal water circulation flow is influenced, and even blockage occurs. The water circulation flow data comprise unit flow quantity, circulation rate and the like, the water circulation liquid medicine information comprises liquid medicine impurity components, content and the like in the circulation process, and the water circulation flow data and the water circulation liquid medicine information are subjected to time correspondence, namely data of a synchronous sequence node, to be used as the water circulation operation characteristics. The water circulation operation characteristic is a data source for carrying out abnormal analysis and judgment on the operation link of the water circulation.
Further, the step S500 of the present application further includes:
step S510-5: according to the operation characteristics of the cleaning chamber, analyzing the characteristic influence relation of the cleaning element and the chemical liquid medicine, and determining chemical liquid medicine conversion parameters;
step S520-5: carrying out water circulation deposition adhesion analysis according to the water circulation operation characteristics and the chemical liquid conversion parameters to determine deposition attachment characteristics;
step S530-5: and based on the deposited attachment characteristics, carrying out flow and circulation time analysis by using water circulation flow monitoring data to obtain the water circulation pipe wall attachment time sequence characteristics.
Specifically, the operation characteristics of the cleaning chamber and the water circulation operation characteristics are input into a component fusion characteristic analysis sub-module of the characteristic analysis module, characteristic influence relation analysis is performed on the cleaning element and the chemical liquid based on the operation characteristics of the cleaning chamber, the cleaning element is an execution element for cleaning treatment, various modes such as dissolution, separation, electrolysis, chemical combination and the like may exist during the cleaning treatment, corresponding generated products are different, chemical liquid components are changed, and the determined conversion components, conversion rate and the like are used as the chemical liquid conversion parameters. And determining a deposition rate and a deposition amount based on the water circulation operation characteristic and the chemical liquid conversion parameter, wherein the deposition rate and the deposition amount of the deposition attachments are correspondingly higher as the deposition attachments are characterized by lower conversion rate and lower water circulation rate. The deposit attachments are conversion component deposits generated after the cleaning treatment. Further, based on the deposited attachment feature, the water circulation flow monitoring data, namely a circulation time period, is combined, wherein in the equipment cleaning process, circulation is carried out periodically, and the attachment time under the operation of the water circulation is determined, namely a pipe wall attachment time node and a time interval of the deposited attachment under the water circulation are used as the water circulation pipe wall attachment time sequence feature.
Step S600: inputting the cleaning operation characteristics of each part into an operation characteristic prediction model to obtain a prediction result of each part;
step S700: and when any one of the cleaning operation characteristics of each part and the predicted results of each part reaches the early warning condition, sending early warning information according to an early warning sending rule.
Specifically, the operation feature prediction model is built, and the operation feature prediction model is an auxiliary analysis tool for predicting component abnormality. And building a main body framework of the operation feature prediction model, acquiring a plurality of operation feature gradient sequences by carrying out operation record data statistics of the big data semiconductor cleaning equipment, identifying abnormal characterization features, inputting the identified operation feature gradient sequences into the main body framework of the model for training, further acquiring a plurality of groups of sample data as verification data, inputting the verification data into the operation feature prediction model for model accuracy judgment, and acquiring the sample data for model training correction until the prediction accuracy of the model reaches the preset accuracy if the model output accuracy does not reach the standard. Further, the cleaning operation characteristics of each part are input into the operation characteristic prediction model, sequence nodes corresponding to the cleaning operation characteristics of each part are determined through operation characteristic matching recognition, distance measurement is conducted on the sequence nodes corresponding to the cleaning operation characteristics of each part and the identified abnormal characteristic characteristics respectively, characteristics meeting the preset distance are screened, and the part prediction results are generated, wherein the part prediction results are provided with time node identifications, real-time judgment results are additional output information, and the real-time judgment results correspond to the identified abnormal characteristic characteristics.
Setting the early warning condition, carrying out matching assessment on the cleaning operation characteristics of each component and the prediction results of each component, when any prediction result of the same component meets the early warning condition, indicating that component operation faults exist or potential component operation faults exist, and sending early warning information to carry out early warning and warning based on the early warning sending rule, wherein the early warning sending rule is a set early warning mode for carrying out component early warning, and the early warning sending rules corresponding to different fault components and different fault grades of the same component are different so as to realize special accurate early warning of the component.
Further, as shown in fig. 3, step S700 of the present application further includes:
step S710-1: obtaining a fault record set according to basic information of a manipulator, a liquid medicine throwing device, a cleaning chamber and a water circulation device of the cleaning device;
step S720-1: according to the fault record set, fault characteristic analysis of mechanical arm movement monitoring data, chemical liquid transmission data, monitoring data of a cleaning chamber and water circulation flow monitoring data is respectively carried out, and a fault characteristic set of each component is determined;
step S730-1: and setting early warning conditions based on the fault feature sets of the components.
Specifically, aiming at various fault factors in the running process of the semiconductor cleaning equipment, early warning and warning are needed to be carried out in time so as to correct and regulate in time and avoid subsequent cleaning abnormality. Specifically, a predetermined time interval, namely a time range for calling a history record, is set, and equipment operation record collection and calling are performed based on the predetermined time interval, wherein the equipment operation record collection and calling comprises the manipulator, the liquid medicine throwing equipment, the cleaning chamber and the water circulation equipment, and a fault record set is generated and provided with a time node and a fault factor identifier. Traversing the fault record set, mapping and matching the manipulator movement monitoring data, the chemical liquid medicine transmission data, the monitoring data of the cleaning chamber and the water circulation flow monitoring data, extracting fault characteristics based on the matching fault record, for example, abnormal operation caused when the water flow is smaller than a certain specific value, such as pipeline blockage, respectively analyzing and integrating, and integrating to generate the fault characteristic set of each component, including various possible fault characteristics. And aiming at the fault characteristic sets of all the components, respectively setting early warning conditions, namely triggering the operation live of abnormal early warning, for example, when the water flow is smaller than a certain specific value, exciting the early warning of the water circulation equipment so as to realize timely and effective equipment abnormal early warning.
Further, the step S700 of the present application further includes:
step S710-2: determining a fault type and a fault grade based on the early warning condition, wherein the fault type comprises component characteristic early warning and fusion characteristic early warning;
step S720-2: setting early warning types based on the part characteristic early warning and the fusion characteristic early warning respectively, wherein the early warning types comprise signal lamp early warning and warning sound early warning;
step S730-2: setting color information or sound type information of a part early warning signal according to the part information;
step S740-2: and setting the flashing frequency of the signal lamp or the sound rhythm speed according to the fault level.
Specifically, the early warning conditions corresponding to different fault factors are different, the fault type and the fault grade are determined based on the early warning conditions, the fault type comprises the component feature early warning and the fusion feature early warning, and the component feature early warning and the fusion feature early warning comprise various refinement faults. Specifically, different early warning modes are set for different faults, so that fault factor judgment can be directly carried out. Based on the component characteristic early warning and the fusion characteristic early warning, the early warning type, namely the early warning mode, can be set, signal lamp early warning can be adopted for the component characteristic early warning, and warning sound early warning can be adopted for the fusion characteristic early warning so as to distinguish. Further, refining early warning types, and setting different early warning signal color information according to different component information aiming at the component characteristic early warning; different sound type information is set for different fusion characteristic early warning so as to perform special early warning of the component and serve as distinguishing. Modulating an early warning mode aiming at fault grade synchronization, and aiming at component characteristic early warning, taking the flicker frequency of a signal lamp as a grade judgment standard, wherein the higher the frequency is, the higher the corresponding early warning grade is; aiming at fusion characteristic early warning, the sound rhythm speed is used as a grade judgment standard, the faster the speed is, the higher the corresponding early warning grade is, and fault judgment can be directly carried out based on early warning information. Preferably, the higher the early warning level, the higher the corresponding repair priority, and when multiple components exist for simultaneous early warning, the repair order is determined based on the early warning level.
Embodiment two: based on the same inventive concept as the fault monitoring and early warning method of a semiconductor cleaning apparatus in the foregoing embodiments, as shown in fig. 4, the present application provides a fault monitoring and early warning system of a semiconductor cleaning apparatus, the system including:
the manipulator movement monitoring data acquisition module 11 is used for acquiring manipulator movement monitoring data by connecting the manipulator monitoring module with manipulator monitoring equipment;
the chemical liquid medicine transmission data acquisition module 12 is used for connecting chemical liquid medicine configuration execution equipment through the chemical liquid medicine transmission module to acquire chemical liquid medicine transmission data;
the cleaning chamber monitoring data acquisition module 13 is used for acquiring monitoring data of the cleaning chamber through connection of the cleaning chamber monitoring module and cleaning chamber liquid monitoring equipment;
the circulation flow monitoring data acquisition module 14, wherein the circulation flow monitoring data acquisition module 14 is used for connecting with the water circulation flow monitoring equipment through the water circulation monitoring module to obtain water circulation flow monitoring data;
the feature analysis module 15 is configured to take the movement monitoring data of the manipulator, the chemical liquid transmission data, the monitoring data of the cleaning chamber, and the water circulation flow monitoring data as input variables, and input the input feature analysis module to perform operation feature analysis and fusion feature analysis of each component, so as to determine cleaning operation features of each component;
The feature prediction module 16 is configured to input the cleaning operation features of each component into an operation feature prediction model, so as to obtain a prediction result of each component;
and the result early-warning module 17 is used for sending early-warning information according to an early-warning sending rule when any result of the cleaning operation characteristics of each part and the predicted result of each part reaches an early-warning condition.
Further, the system further comprises:
the manipulator movement monitoring data analysis module is used for extracting a manipulator movement track, a manipulator movement amplitude and working time according to the manipulator movement monitoring data;
the manipulator operation feature extraction module is used for extracting operation features according to the manipulator movement track, the manipulator movement amplitude and the working time to obtain a manipulator operation feature set;
and the feature list construction module is used for carrying out alignment processing on the manipulator operation feature set based on the corresponding relation of the working time to construct a manipulator operation feature list.
Further, the system further comprises:
The chemical liquid medicine transmission data analysis module is used for obtaining chemical liquid medicine components, concentration requirements and liquid medicine replenishment information according to the chemical liquid medicine transmission data, wherein the liquid medicine replenishment information comprises replenishment time and replenishment quantity;
the cleaning characteristic analysis module is used for carrying out cleaning target characteristic analysis according to the chemical liquid medicine composition and concentration requirements and determining liquid medicine cleaning characteristics;
the replenishment matching characteristic determining module is used for carrying out replenishment matching relation analysis according to the liquid medicine cleaning characteristics and the liquid medicine replenishment information to determine replenishment matching characteristics;
the chemical liquid operation characteristic acquisition module is used for acquiring a chemical liquid operation characteristic set based on the liquid cleaning characteristic and the replenishment matching characteristic.
Further, the system further comprises:
the cleaning chamber monitoring data analysis module is used for extracting ultrasonic amplitude information, cleaning flow information, temperature information, liquid level information, cleaning element information and corresponding chemical liquid information according to the monitoring data of the cleaning chamber;
The mapping relation construction module is used for establishing a cleaning chamber data mapping relation of the ultrasonic amplitude information, the temperature information, the liquid level information, the cleaning element information, the chemical liquid information and the cleaning flow information based on the cleaning flow information;
the amplitude matching degree characteristic acquisition module is used for acquiring ultrasonic control parameter information, analyzing the matching relation between the ultrasonic control parameter information and the ultrasonic amplitude information and determining an amplitude matching degree characteristic;
the cleaning cavity feature determining module is used for carrying out cleaning feature analysis according to the cleaning cavity data mapping relation to determine cleaning cavity features;
and the operation characteristic determining module is used for taking the amplitude matching degree characteristic and the cleaning cavity characteristic as operation characteristics of the cleaning cavity.
Further, the system further comprises:
the water circulation flow monitoring data analysis module is used for extracting water circulation flow data and water circulation liquid medicine information according to the water circulation flow monitoring data;
And the water circulation operation characteristic determining module is used for performing time alignment based on the water circulation flow data and the water circulation liquid medicine information to determine the water circulation operation characteristic.
Further, the system further comprises:
the conversion parameter determining module is used for analyzing the characteristic influence relation of the cleaning element and the chemical liquid according to the operation characteristics of the cleaning chamber and determining the conversion parameters of the chemical liquid;
the deposition attachment feature determining module is used for carrying out water circulation deposition attachment analysis according to the water circulation operation feature and the chemical liquid conversion parameter to determine deposition attachment features;
and the adhesion time sequence feature acquisition module is used for analyzing flow and circulation time according to the deposition attachment feature and the water circulation flow monitoring data to obtain the adhesion time sequence feature of the water circulation pipe wall.
Further, the system further comprises:
the fault record set acquisition module is used for acquiring a fault record set according to basic information of a manipulator, a liquid medicine throwing device, a cleaning chamber and a water circulation device of the cleaning device;
The fault characteristic analysis module is used for respectively carrying out fault characteristic analysis on the mechanical arm movement monitoring data, the chemical liquid transmission data, the monitoring data of the cleaning chamber and the water circulation flow monitoring data according to the fault record set and determining a fault characteristic set of each component;
and the early warning condition setting module is used for setting early warning conditions based on the fault characteristic sets of the components.
Further, the system further comprises:
the fault parameter determining module is used for determining a fault type and a fault grade based on the early warning condition, wherein the fault type comprises component feature early warning and fusion feature early warning;
the early warning type setting module is used for setting early warning types based on the component characteristic early warning and the fusion characteristic early warning respectively, wherein the early warning types comprise signal lamp early warning and warning sound early warning;
the component early warning parameter setting module is used for setting color information or sound type information of the component early warning signals according to the component information;
the grade early warning parameter setting module is used for setting the flashing frequency of the signal lamp or the sound rhythm speed according to the fault grade.
Through the foregoing detailed description of a fault monitoring and early warning method of a semiconductor cleaning device, those skilled in the art can clearly know the fault monitoring and early warning method and system of a semiconductor cleaning device in this embodiment, and for the apparatus disclosed in the embodiment, the description is relatively simple because it corresponds to the method disclosed in the embodiment, and relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (9)
1. The fault monitoring and early warning method for the semiconductor cleaning equipment is characterized by being applied to a fault monitoring and early warning system, wherein the fault monitoring and early warning system comprises a manipulator monitoring module, a chemical liquid transmission module, a cleaning chamber monitoring module and a water circulation monitoring module, and the method comprises the following steps:
The manipulator monitoring module is connected with manipulator monitoring equipment to acquire manipulator movement monitoring data;
the chemical liquid medicine transmission module is connected with chemical liquid medicine configuration execution equipment to obtain chemical liquid medicine transmission data;
the cleaning chamber monitoring module is connected with cleaning chamber liquid monitoring equipment to acquire monitoring data of the cleaning chamber;
the water circulation monitoring module is connected with water circulation flow monitoring equipment to obtain water circulation flow monitoring data;
taking the mobile monitoring data of the manipulator, the chemical liquid transmission data, the monitoring data of the cleaning chamber and the water circulation flow monitoring data as input variables, and inputting the input variables into a characteristic analysis module for carrying out operation characteristic analysis and fusion characteristic analysis of each part to determine the cleaning operation characteristics of each part;
inputting the cleaning operation characteristics of each part into an operation characteristic prediction model to obtain a prediction result of each part;
and when any one of the cleaning operation characteristics of each part and the predicted results of each part reaches the early warning condition, sending early warning information according to an early warning sending rule.
2. The method of claim 1, wherein the method comprises:
extracting a manipulator movement track, a manipulator movement amplitude and working time according to the manipulator movement monitoring data;
Extracting operation characteristics according to the movement track of the manipulator, the movement amplitude of the manipulator and the working time to obtain a manipulator operation characteristic set;
and carrying out alignment processing on the manipulator operation feature set based on the corresponding relation of the working time, and constructing a manipulator operation feature list.
3. The method of claim 1, wherein the method comprises:
obtaining chemical liquid medicine components, concentration requirements and liquid medicine replenishment information according to the chemical liquid medicine transmission data, wherein the liquid medicine replenishment information comprises replenishment time and replenishment quantity;
performing cleaning target characteristic analysis according to the chemical liquid composition and concentration requirements, and determining liquid cleaning characteristics;
carrying out replenishment matching relation analysis according to the liquid medicine cleaning characteristics and the liquid medicine replenishment information to determine replenishment matching characteristics;
and obtaining a chemical liquid medicine operation characteristic set based on the liquid medicine cleaning characteristic and the replenishment matching characteristic.
4. The method of claim 1, wherein the method comprises:
extracting ultrasonic amplitude information, cleaning flow information, temperature information, liquid level information, cleaning element information and corresponding chemical liquid information according to the monitoring data of the cleaning chamber;
Based on the cleaning flow information, establishing a cleaning chamber data mapping relation between the ultrasonic amplitude information, the temperature information, the liquid level information, the cleaning element information, the chemical liquid medicine information and the cleaning flow information;
acquiring ultrasonic control parameter information, analyzing the matching relation based on the ultrasonic control parameter information and the ultrasonic amplitude information, and determining the amplitude matching degree characteristic;
performing cleaning characteristic analysis according to the cleaning cavity data mapping relation to determine cleaning cavity characteristics;
and taking the amplitude matching degree characteristic and the cleaning cavity characteristic as operation characteristics of the cleaning cavity.
5. The method of claim 4, wherein the method comprises:
extracting water circulation flow data and water circulation liquid medicine information according to the water circulation flow monitoring data;
and carrying out time alignment based on the water circulation flow data and the water circulation liquid medicine information, and determining the water circulation operation characteristics.
6. The method of claim 5, wherein the component fusion profile comprises:
according to the operation characteristics of the cleaning chamber, analyzing the characteristic influence relation of the cleaning element and the chemical liquid medicine, and determining chemical liquid medicine conversion parameters;
Carrying out water circulation deposition adhesion analysis according to the water circulation operation characteristics and the chemical liquid conversion parameters to determine deposition attachment characteristics;
and based on the deposited attachment characteristics, carrying out flow and circulation time analysis by using water circulation flow monitoring data to obtain the water circulation pipe wall attachment time sequence characteristics.
7. The method of claim 1, wherein the method further comprises:
obtaining a fault record set according to basic information of a manipulator, a liquid medicine throwing device, a cleaning chamber and a water circulation device of the cleaning device;
according to the fault record set, fault characteristic analysis of mechanical arm movement monitoring data, chemical liquid transmission data, monitoring data of a cleaning chamber and water circulation flow monitoring data is respectively carried out, and a fault characteristic set of each component is determined;
and setting early warning conditions based on the fault feature sets of the components.
8. The method of claim 7, wherein the sending the alert information according to the alert sending rules comprises:
determining a fault type and a fault grade based on the early warning condition, wherein the fault type comprises component characteristic early warning and fusion characteristic early warning;
setting early warning types based on the part characteristic early warning and the fusion characteristic early warning respectively, wherein the early warning types comprise signal lamp early warning and warning sound early warning;
Setting color information or sound type information of a part early warning signal according to the part information;
and setting the flashing frequency of the signal lamp or the sound rhythm speed according to the fault level.
9. The utility model provides a semiconductor cleaning equipment's fault monitoring early warning system, its characterized in that, the system includes manipulator monitoring module, chemical liquid transmission module, washs cavity monitoring module, hydrologic cycle monitoring module, the system includes:
the manipulator movement monitoring data acquisition module is used for acquiring manipulator movement monitoring data by connecting the manipulator monitoring module with manipulator monitoring equipment;
the chemical liquid medicine transmission data acquisition module is used for connecting chemical liquid medicine configuration execution equipment through the chemical liquid medicine transmission module to acquire chemical liquid medicine transmission data;
the cleaning chamber monitoring data acquisition module is used for acquiring monitoring data of the cleaning chamber through connection of the cleaning chamber monitoring module and cleaning chamber liquid monitoring equipment;
the circulating flow monitoring data acquisition module is used for connecting the circulating flow monitoring module with the water circulating flow monitoring equipment to obtain water circulating flow monitoring data;
The characteristic analysis module is used for taking the manipulator movement monitoring data, the chemical liquid medicine transmission data, the monitoring data of the cleaning chamber and the water circulation flow monitoring data as input variables, inputting the input variables into the characteristic analysis module for carrying out the operation characteristic analysis of each part and the fusion characteristic analysis of each part, and determining the cleaning operation characteristics of each part;
the feature prediction module is used for inputting the cleaning operation features of the components into an operation feature prediction model to obtain the prediction results of the components;
and the result early warning module is used for sending early warning information according to an early warning sending rule when any result of the cleaning operation characteristics of each part and the predicted result of each part reaches an early warning condition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310335566.9A CN116046078A (en) | 2023-03-31 | 2023-03-31 | Fault monitoring and early warning method and system for semiconductor cleaning equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310335566.9A CN116046078A (en) | 2023-03-31 | 2023-03-31 | Fault monitoring and early warning method and system for semiconductor cleaning equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116046078A true CN116046078A (en) | 2023-05-02 |
Family
ID=86133578
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310335566.9A Pending CN116046078A (en) | 2023-03-31 | 2023-03-31 | Fault monitoring and early warning method and system for semiconductor cleaning equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116046078A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117153712A (en) * | 2023-09-18 | 2023-12-01 | 苏州恩腾半导体科技有限公司 | Comprehensive monitoring system and method for inside of semiconductor cleaning equipment chamber |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1649100A (en) * | 2004-07-23 | 2005-08-03 | 王文 | System and its method for high efficiency ozone water cleaning semiconductor wafer |
| US20080289652A1 (en) * | 2004-09-28 | 2008-11-27 | Satomi Hamada | Substrate Cleaning Apparatus and Method for Determining Timing of Replacement of Cleaning Member |
| CN105810618A (en) * | 2016-05-31 | 2016-07-27 | 北京七星华创电子股份有限公司 | System and method for improving wafer transmission efficiency |
| CN106328569A (en) * | 2016-11-07 | 2017-01-11 | 北京七星华创电子股份有限公司 | Monitoring system and detection method of working condition of semiconductor cleaning equipment |
| CN110689067A (en) * | 2019-09-25 | 2020-01-14 | 上海华力集成电路制造有限公司 | Failure detection method, device and equipment for wafer and storage medium |
| CN112016676A (en) * | 2020-08-18 | 2020-12-01 | 武汉大学 | Semiconductor film process parameter optimization system predicted by neural network model |
| CN113383282A (en) * | 2019-01-31 | 2021-09-10 | 应用材料公司 | Correcting component failure in an ion implanted semiconductor manufacturing tool |
| CN113539909A (en) * | 2021-09-15 | 2021-10-22 | 深圳市信润富联数字科技有限公司 | Fault detection method and device, terminal equipment and storage medium |
| WO2022048168A1 (en) * | 2020-09-03 | 2022-03-10 | 上海上讯信息技术股份有限公司 | Training method and device for failure prediction neural network model |
| CN115148620A (en) * | 2021-03-30 | 2022-10-04 | 长鑫存储技术有限公司 | Wafer cleaning abnormity detection method and device |
-
2023
- 2023-03-31 CN CN202310335566.9A patent/CN116046078A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1649100A (en) * | 2004-07-23 | 2005-08-03 | 王文 | System and its method for high efficiency ozone water cleaning semiconductor wafer |
| US20080289652A1 (en) * | 2004-09-28 | 2008-11-27 | Satomi Hamada | Substrate Cleaning Apparatus and Method for Determining Timing of Replacement of Cleaning Member |
| CN105810618A (en) * | 2016-05-31 | 2016-07-27 | 北京七星华创电子股份有限公司 | System and method for improving wafer transmission efficiency |
| CN106328569A (en) * | 2016-11-07 | 2017-01-11 | 北京七星华创电子股份有限公司 | Monitoring system and detection method of working condition of semiconductor cleaning equipment |
| CN113383282A (en) * | 2019-01-31 | 2021-09-10 | 应用材料公司 | Correcting component failure in an ion implanted semiconductor manufacturing tool |
| CN110689067A (en) * | 2019-09-25 | 2020-01-14 | 上海华力集成电路制造有限公司 | Failure detection method, device and equipment for wafer and storage medium |
| CN112016676A (en) * | 2020-08-18 | 2020-12-01 | 武汉大学 | Semiconductor film process parameter optimization system predicted by neural network model |
| WO2022048168A1 (en) * | 2020-09-03 | 2022-03-10 | 上海上讯信息技术股份有限公司 | Training method and device for failure prediction neural network model |
| CN115148620A (en) * | 2021-03-30 | 2022-10-04 | 长鑫存储技术有限公司 | Wafer cleaning abnormity detection method and device |
| CN113539909A (en) * | 2021-09-15 | 2021-10-22 | 深圳市信润富联数字科技有限公司 | Fault detection method and device, terminal equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 张剑波等: "《清洗技术基础教程》", 中国环境科学出版社, pages: 421 - 424 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117153712A (en) * | 2023-09-18 | 2023-12-01 | 苏州恩腾半导体科技有限公司 | Comprehensive monitoring system and method for inside of semiconductor cleaning equipment chamber |
| CN117153712B (en) * | 2023-09-18 | 2024-03-29 | 苏州恩腾半导体科技有限公司 | Comprehensive monitoring system and method for inside of semiconductor cleaning equipment chamber |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647133B (en) | Rail transit equipment state detection maintenance method and system | |
| CN104390657B (en) | A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system | |
| CN117494955B (en) | Intelligent monitoring system for automatic production | |
| CN107797537A (en) | A kind of prognostic and health management method applied to automatic production line | |
| CN115643159B (en) | Equipment abnormity early warning method and system based on edge calculation | |
| CN108510221A (en) | Have the function of carrying out the inventory management system of stock control and preventive maintenance | |
| CN116046078A (en) | Fault monitoring and early warning method and system for semiconductor cleaning equipment | |
| CN104573850A (en) | Method for evaluating state of thermal power plant equipment | |
| CN111046582A (en) | Nuclear power station diesel generating set coil temperature early warning method and system | |
| CN109426225A (en) | A kind of method of quality control of tobacco cutting production | |
| CN109634233A (en) | Industrial big data intellectual analysis decision-making technique, readable storage medium storing program for executing and terminal | |
| CN115034094B (en) | Prediction method and system for operation state of metal processing machine tool | |
| CN115576284A (en) | Clothing workshop intelligent management method and system | |
| CN116991146B (en) | Control method and system of ultrasonic cleaning device | |
| CN113806969A (en) | Compressor unit health prediction method based on time domain data correlation modeling | |
| CN109614451A (en) | Industrial big data intellectual analysis decision making device | |
| CN117193222A (en) | Intelligent quality control system based on industrial Internet of things and big data and control method thereof | |
| CN117591857A (en) | Motor detection method based on deep learning | |
| CN117668501B (en) | Welding data intelligent management system and method based on automatic production | |
| CN108593622A (en) | A kind of intelligent integration optical fiber sensing system for petrochemical iy produced process and its real-time monitoring, diagnosing method | |
| CN118134116A (en) | Cable and channel state monitoring and evaluating method based on big data analysis | |
| CN115511237A (en) | Device operation condition monitoring method and system | |
| CN117216647A (en) | Predictive maintenance and fault diagnosis method and system for vehicle body welding equipment | |
| CN116611574A (en) | Remanufacturing evaluation method and system for steel structure of pipeline welding robot | |
| CN117870034B (en) | Control method, device and system for environmental parameters of clean room |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230502 |