CN114253168A - Machine monitoring system and machine monitoring method - Google Patents
Machine monitoring system and machine monitoring method Download PDFInfo
- Publication number
- CN114253168A CN114253168A CN202110068002.4A CN202110068002A CN114253168A CN 114253168 A CN114253168 A CN 114253168A CN 202110068002 A CN202110068002 A CN 202110068002A CN 114253168 A CN114253168 A CN 114253168A
- Authority
- CN
- China
- Prior art keywords
- parameter
- detection information
- abnormal
- machines
- machine
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012544 monitoring process Methods 0.000 title claims abstract description 46
- 238000001514 detection method Methods 0.000 claims abstract description 143
- 230000002159 abnormal effect Effects 0.000 claims abstract description 104
- 238000012545 processing Methods 0.000 claims abstract description 74
- 238000004458 analytical method Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 abstract description 19
- 230000000875 corresponding effect Effects 0.000 description 89
- 239000011159 matrix material Substances 0.000 description 9
- 238000010606 normalization Methods 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 238000000556 factor analysis Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000012847 principal component analysis method Methods 0.000 description 2
- APTZNLHMIGJTEW-UHFFFAOYSA-N pyraflufen-ethyl Chemical compound C1=C(Cl)C(OCC(=O)OCC)=CC(C=2C(=C(OC(F)F)N(C)N=2)Cl)=C1F APTZNLHMIGJTEW-UHFFFAOYSA-N 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000002759 z-score normalization Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0428—Safety, monitoring
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24024—Safety, surveillance
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a machine monitoring system and a machine monitoring method. The detection device detects the plurality of machines to generate a plurality of detection information corresponding to the plurality of machines; the data processing device is connected with the detection device and is used for: receiving a plurality of detection information, and selecting at least one abnormal machine from a plurality of machines according to the plurality of detection information; calculating a plurality of parameter values corresponding to a plurality of first detection information in a plurality of detection information, wherein the plurality of first detection information correspond to at least one abnormal machine; and selecting at least one abnormal detection information from the first detection information according to the parameter values so as to correct at least one abnormal machine by utilizing the at least one abnormal detection information. Therefore, the problem of process parameter drift of the machine can be effectively solved.
Description
Technical Field
The invention relates to a machine monitoring system and a machine monitoring method.
Background
The production schedule of the current factory tends to be complex and highly uncertain, which results in the need to adjust the process parameters of the tool sites in real time in response to the production status during the production process. For example, in a wafer manufacturing process, the stability of the tool is correlated with the wafer yield, so it is necessary to monitor the process parameters of the tool producing the wafer in real time. Generally, in the production and complex manufacturing process of many products, it is often necessary to compare one by one the differences between the process parameters of each machine in the same process depending on the manpower to detect the abnormal factors. Therefore, if there is a machine with a drift in process parameters, the abnormal factors need to be removed as soon as possible, and if necessary, the machine may need to be stopped for improvement, thereby avoiding damage and rejection of a large amount of products. Therefore, how to solve the problem of process parameter drift in real time is a problem to be solved urgently in the field.
Disclosure of Invention
The invention aims to provide a machine monitoring system which can effectively solve the problem of the drift of process parameters of a machine.
The invention provides a machine monitoring system, which comprises a detection device and a data processing device. The detection device detects the plurality of machines to generate a plurality of detection information corresponding to the plurality of machines; the data processing device is connected with the detection device and is used for: receiving a plurality of detection information, and selecting at least one abnormal machine from a plurality of machines according to the plurality of detection information; calculating a plurality of parameter values corresponding to a plurality of first detection information in a plurality of detection information, wherein the plurality of first detection information correspond to at least one abnormal machine; and selecting at least one abnormal detection information from the first detection information according to the parameter values so as to correct at least one abnormal machine by utilizing the at least one abnormal detection information.
In one embodiment, the detection information corresponds to parameter classes, and the data processing apparatus is further configured to: generating a plurality of candidate coordinates corresponding to a plurality of machines according to a plurality of detection information and a plurality of weight values corresponding to a plurality of parameter categories; and selecting at least one abnormal machine from the plurality of machines by an outlier analysis method according to the plurality of candidate coordinates.
In one embodiment, the data processing apparatus is further configured to: the detection information is normalized to generate a plurality of normalized parameters, and a plurality of candidate coordinates corresponding to the machines are generated according to the normalized parameters and a plurality of weight values corresponding to the parameter types.
In one embodiment, the data processing apparatus is further configured to: and selecting at least one outlier coordinate from the candidate coordinates by using an outlier analysis method according to the candidate coordinates, so as to select at least one abnormal machine corresponding to the at least one outlier coordinate from the machines.
In one embodiment, the data processing apparatus is further configured to: calculating a plurality of parameter values according to the plurality of weight values and the plurality of first detection information, and calculating a plurality of total parameter values corresponding to a plurality of parameter categories according to the plurality of parameter values; calculating the parameter sum of the total parameter values to calculate a plurality of total parameter proportion values corresponding to the parameter classes according to the parameter sum and the total parameter values; sorting the plurality of total parameter proportion values to generate total parameter proportion value sorting information; and selecting at least one abnormal parameter category from the plurality of parameter categories according to the total parameter proportion value sorting information so as to select at least one abnormal detection information corresponding to the at least one abnormal parameter category from the plurality of first detection information.
The invention provides a machine monitoring method. The method comprises the following steps: generating a plurality of candidate coordinates corresponding to the plurality of machines according to a plurality of detection information of the plurality of machines, so as to select at least one abnormal machine from the plurality of machines according to the plurality of candidate coordinates; calculating a plurality of parameter values corresponding to a plurality of pieces of first detection information from the plurality of pieces of first detection information, wherein the plurality of pieces of first detection information correspond to at least one abnormal machine; and selecting at least one abnormal detection information from the first detection information according to the contribution values so as to correct at least one abnormal machine by utilizing the at least one abnormal detection information.
In one embodiment, the detecting information corresponds to parameter types, and the generating candidate coordinates corresponding to the machines according to the detecting information includes: generating a plurality of candidate coordinates corresponding to a plurality of machines according to a plurality of detection information and a plurality of weight values corresponding to a plurality of parameter categories; and selecting at least one abnormal machine from the plurality of machines by an outlier analysis method according to the plurality of candidate coordinates.
In an embodiment, the step of generating a plurality of candidate coordinates corresponding to a plurality of tools according to a plurality of weight values corresponding to a plurality of detection information and a plurality of parameter types includes: the detection information is normalized to generate a plurality of normalized parameters, and a plurality of candidate coordinates corresponding to the machines are generated according to the normalized parameters and a plurality of weight values corresponding to the parameter types.
In one embodiment, the step of selecting at least one abnormal tool from the plurality of tools by an outlier analysis method according to the candidate coordinates comprises: and selecting at least one outlier coordinate from the candidate coordinates by using an outlier analysis method according to the candidate coordinates, so as to select at least one abnormal machine corresponding to the at least one outlier coordinate from the machines.
In one embodiment, the step of calculating a plurality of parameter values corresponding to a plurality of first detection information from the plurality of first detection information includes: and calculating a plurality of parameter values according to the plurality of weight values and the plurality of first detection information. The step of selecting at least one abnormal machine from the plurality of machines by an outlier analysis method according to the plurality of candidate coordinates comprises the following steps: calculating a plurality of total parameter values corresponding to a plurality of parameter types according to the plurality of parameter values; calculating the parameter sum of the total parameter values to calculate a plurality of total parameter proportion values corresponding to the parameter classes according to the parameter sum and the total parameter values; sorting the plurality of total parameter proportion values to generate total parameter proportion value sorting information; and selecting at least one abnormal parameter category from the plurality of parameter categories according to the total parameter proportion value sorting information so as to select at least one abnormal detection information corresponding to the at least one abnormal parameter category from the plurality of first detection information.
Based on the above, the machine monitoring system provided by the invention can detect the machines with abnormal states in real time, detect which abnormal factors cause the abnormal states of the machines according to the machines with the abnormal states, and further correct the machines according to the abnormal factors causing the abnormal states of the machines, so as to solve the problem of process parameter drift.
Drawings
FIG. 1 is a block diagram of a tool monitoring system according to an embodiment of the invention.
Fig. 2 is a flow chart of a machine monitoring method according to some exemplary embodiments of the invention.
FIG. 3 is a flow chart of a machine monitoring method according to further exemplary embodiments of the present invention.
Fig. 4 is a schematic diagram of a cohort profile according to some exemplary embodiments of the invention.
Description of the main reference numerals:
100-machine monitoring system, 110-detection device, 120-data processing device, 130(1) -130 (N) -machines, S201-S205, S301-S3017-steps, gp 1-gp 2-group.
Detailed Description
FIG. 1 is a block diagram of a tool monitoring system 100 according to an embodiment of the invention. Referring to FIG. 1, a tool monitoring system 100 may be used to monitor tools of various processes. In this embodiment, in order to make the present invention more understandable, the monitoring of the plurality of tools 130(1) to 130(N) is taken as an example, where N may be any positive integer, and the tools 130(1) to 130(N) may be tools of any number of processes, and there is no particular limitation on N and the number of processes.
Furthermore, the tool monitoring system 100 may comprise a detection device 110 and a data processing device 120. The detection device 110 can detect the machines 130(1) to 130(N) in real time to generate a plurality of detection information corresponding to the machines 130(1) to 130 (N).
In some embodiments, the data processing device 120 includes, for example, a storage device (not shown) and a processor (not shown). The storage device may be any type of Random Access Memory (RAM), read-only memory (ROM), flash memory (flash memory), hard disk, the like, or any combination thereof. The Processor may be, for example, a Central Processing Unit (CPU), or other programmable general purpose or special purpose Microprocessor (Microprocessor), Digital Signal Processor (DSP), programmable controller, Application Specific Integrated Circuit (ASIC), or the like, or any combination thereof. In the embodiment, the processor may load the computer program from the storage device to execute the machine monitoring method according to the embodiment of the invention.
In some embodiments, the data processing device 120 may be a central processing device disposed near or remote from the tool, and the central processing device may further be used to store various historical inspection information detected by the inspection device 110 in the past.
In some embodiments, the detecting device 110 may include a plurality of sensors (not shown) disposed on the machines 130(1) to 130(N), and may detect various parameter types periodically or non-periodically of the machines 130(1) to 130(N) through the plurality of sensors to generate a plurality of detecting information, wherein the parameter types may be measured parameters such as temperature, pressure, and gas flow, and the plurality of detecting information may be detected values of the various parameter types detected from the machines 130(1) to 130(N) (for example, two detecting information detected by the machines 130(1) are measured values of temperature and measured values of pressure, respectively). In some embodiments, the plurality of sensors may include temperature sensors, pressure sensors, and gas flow sensors for various parameters described above.
In other embodiments, the detection device 110 may detect a plurality of detection information from the various sensor detection tools 130(1) -130 (N) via a failure detection and classification system (not shown), wherein each detection information is failure detection and classification system data.
Furthermore, the data processing device 120 can be communicatively connected to the detection device 110. For the above communication connection method, the data processing device 120 may be connected to the detecting device 110 in a wired or wireless manner, and is not particularly limited.
For the wired mode, the data processing apparatus 120 may be a Universal Serial Bus (USB), an RS232, a universal asynchronous receiver/transmitter (UART), an internal integrated circuit (I2C), a Serial Peripheral Interface (SPI), a display port (display port), a thunderbolt port (thunderbolt), or a Local Area Network (LAN) interface for wired communication connection, which is not particularly limited. For the wireless mode, the data processing device 120 may utilize a wireless fidelity (Wi-Fi) module, a Radio Frequency Identification (RFID) module, a bluetooth module, an infrared module, a near-field communication (NFC) module, or a device-to-device (D2D) module to perform wireless communication connection, and is not limited in particular.
Fig. 2 is a flow chart of a machine monitoring method according to some exemplary embodiments of the invention. Referring to fig. 1 and fig. 2, the method of the present embodiment is applied to the equipment monitoring system 100 of fig. 1, and the detailed steps of the equipment monitoring method of the present embodiment are described below in conjunction with the operation relationship between the devices in the equipment monitoring system 100.
First, in step S201, the data processing apparatus 120 may receive a plurality of detection information of the tools 130(1) to 130(N) from the detection apparatus 110, and select at least one abnormal tool from the tools 130(1) to 130(N) according to the plurality of detection information. In other words, the detecting device 110 can detect each tool to generate detecting information of each tool, and transmit the detecting information to the data processing device 120. The data processing device 120 may perform data analysis on the plurality of detection information received from the detection device 110 to select at least one abnormal machine from the machines 130(1) to 130(N) according to the obtained analysis result.
In some embodiments, in the data analysis, the detection information may correspond to a plurality of parameter types, and the data processing apparatus 120 may generate a plurality of candidate coordinates corresponding to the plurality of tools according to a plurality of weight values (weight values) corresponding to the detection information and the parameter types, and perform an outliers analysis (outliers analysis) method according to the candidate coordinates. Thereby, the data processing apparatus 120 may select at least one abnormal machine from the plurality of machines.
In a further embodiment, the data processing apparatus 120 may further normalize (normalize) the detection information to generate normalized parameters, and generate candidate coordinates corresponding to the tools according to the normalized parameters and weight values corresponding to the parameter classes.
In detail, since the parameters of each parameter category have different value ranges, the parameters of each parameter category need to be normalized to facilitate the subsequent value calculation. Therefore, the data processing apparatus 120 needs to normalize the detected information to generate the normalized parameters, wherein the normalization method may be t-normalization (normalization), min-max normalization (min-max normalization), or Z-score normalization (Z-score normalization).
In this way, the data processing apparatus 120 may generate a plurality of candidate coordinates corresponding to a plurality of machines by using a Principal Component Analysis (PCA) method according to the plurality of normalized parameters and the plurality of weighted values corresponding to the plurality of parameter types.
Further, for example, in the principal component analysis method using multi-dimensional normalization parameters to generate two-dimensional coordinates, the data processing apparatus 120 may generate a covariant matrix (covariant matrix) according to the normalization parameters, and decompose the covariant matrix into a plurality of eigenvalues (eigen values) and a plurality of eigenvectors (eigen vectors). The data processing apparatus 120 may select two largest eigenvalues from the eigenvalues, and generate a projection matrix (project matrix) by using eigenvectors corresponding to the two eigenvalues to extract the first two columns of elements of the projection matrix as a weight matrix, wherein a plurality of rows of the weight matrix respectively correspond to weight values corresponding to a plurality of parameter categories (for example, a first parameter category corresponds to two elements of a first row of the weight matrix). Thus, the data processing apparatus 120 may generate a plurality of candidate coordinates corresponding to the plurality of tools by using the plurality of normalized parameters and the plurality of weighted values corresponding to the plurality of parameter categories, wherein the plurality of candidate coordinates are coordinates corresponding to the plurality of tools in the two-dimensional coordinate plane.
For example, taking p parameter classes as examples (p is any positive integer), the two-dimensional candidate coordinates (PC 1) of the machine 130(1)1,PC21) The following were used:
PC11＝α11x11+α12x12+α13x13+…α1px1p………(1)
PC21＝α21x11+α22x12+α23x13+…α2px2p………(2)
wherein alpha is11And alpha21Is the weight value corresponding to the 1 st parameter class, and x11Normalized parameter value of the detected information corresponding to the 1 st parameter class detected by the 1 st machine, and alpha12And alpha22Is the weight value corresponding to the 2 nd parameter class, and x12The normalized parameter values are the detection information corresponding to the 2 nd parameter class detected by the 1 st machine. By analogy, α13～α1pAnd alpha23～α2pIs the weight value corresponding to other parameter categories, and x13～x1pAnd the normalized parameter values of the detection information corresponding to other parameter types.
By analogy, the two-dimensional candidate coordinates (PC 1) of the machines 130(2) -130 (N)2,PC22)～(PC1N,PC2N) Can be calculated in the same manner as described above.
In some embodiments, the data processing apparatus 120 may further select at least one outlier coordinate from the plurality of candidate coordinates by using the above-mentioned outlier analysis method according to the plurality of candidate coordinates, so as to select at least one abnormal tool corresponding to the at least one outlier coordinate from the plurality of tools.
In a further embodiment, the data processing apparatus 120 may determine candidate coordinates corresponding to machines of the same process as a same group to generate at least one group, and calculate center coordinates of each group by using a plurality of candidate coordinates (e.g., calculate coordinates corresponding to a geometric center of the candidate coordinates of each group), so as to calculate a distance value between the candidate coordinates corresponding to each machine and the center coordinates of the group corresponding thereto. Therefore, the data processing device 120 can determine whether the distance value corresponding to each machine is not less than a preset distance threshold, where the preset distance threshold may be a value preset by a user or a value obtained after multiple abnormal removal of machines. When the data processing device 120 determines that the distance value corresponding to a specific machine is not less than the preset distance threshold, the data processing device 120 may determine the specific machine as an abnormal machine.
In other embodiments, when the data processing apparatus 120 determines candidate coordinates corresponding to machines of the same process as a same group to generate at least one group, the data processing apparatus 120 may also analyze an average value of each group by using a two-factor variance analysis method, and select at least one outlier coordinate from a plurality of candidate coordinates according to the average value of each group, so as to select at least one outlier machine corresponding to the at least one outlier coordinate from the plurality of machines.
In other embodiments, when the data processing apparatus 120 determines candidate coordinates corresponding to machines of the same process as the same group to generate at least one group, the data processing apparatus 120 may also select at least one outlier from the candidate coordinates by using a K-mean (K-mean) algorithm, a noise-based density clustering (dbs) method, a hierarchical clustering (hierarchical clustering), a spectral clustering (spectral clustering) algorithm, a gaussian mixture (gaussian mixtures) method, and other outlier analysis methods according to the candidate coordinates to select at least one outlier corresponding to the at least one outlier from the plurality of machines.
Next, in step S203, the data processing apparatus 120 may calculate a plurality of parameter values corresponding to a plurality of first detection information in a plurality of detection information, wherein the plurality of first detection information corresponds to at least one abnormal tool. In other words, the data processing apparatus 120 may select a plurality of first detection information corresponding to at least one abnormal machine from the plurality of detection information (i.e., the detection information detected from each abnormal machine), and calculate a plurality of parameter values corresponding to the plurality of first detection information.
In some embodiments, the data processing apparatus 120 may calculate a plurality of parameter values according to the plurality of weight values and the plurality of first detection information. In detail, the data processing apparatus 120 may obtain all the first detection information corresponding to one of the parameter categories, and multiply the first detection information and the weight value corresponding to the parameter category to generate a plurality of weight values corresponding to the first detection information. Therefore, the data processing device 120 can perform absolute value operations on the weighted values to generate a plurality of parameter values corresponding to the first detection information. By analogy, the data processing device 120 may obtain a plurality of first detection information corresponding to each of the other parameter types in the same manner to calculate a plurality of parameter values corresponding to the first detection information.
For example, in the following example, the machines 130(1) to 130(n) are taken as abnormal machines (n is any positive integer), and the parameter value of the 1 st parameter type corresponding to the machine 130(1) is abs (α)11x11) And the parameter value of the 1 st parameter type corresponding to the machine 130(2) is abs (α)11x21). By analogy, the parameter value of the 1 st parameter type corresponding to the machine 130(n) is abs (α)11xn1)。
Based on the above, the parameter values of the parameter types corresponding to the abnormal machines can be calculated in the same manner as described above.
Finally, in step S205, the data processing apparatus 120 may select at least one abnormal detection information from the plurality of first detection information according to the plurality of parameter values, so as to correct at least one abnormal machine by using the at least one abnormal detection information. In other words, the data processing apparatus 120 may determine which abnormal first detection information exists in the plurality of first detection information according to the plurality of parameter values, so as to use the abnormal first detection information as the abnormal detection information. Therefore, the data processing device 120 can determine which parameter types belong to the abnormal factors according to the abnormal detection information, and correct all abnormal machines according to the abnormal factors.
In some embodiments, the data processing apparatus 120 may calculate a plurality of total parameter values corresponding to a plurality of parameter categories according to the plurality of parameter values, and calculate a parameter sum of the plurality of total parameter values, so as to calculate a plurality of total parameter ratio values corresponding to the plurality of parameter categories according to the parameter sum and the plurality of total parameter values. Therefore, the data processing device 120 can sort the plurality of total parameter ratio values to generate the total parameter ratio value sorting information. In this way, the data processing apparatus 120 may select at least one abnormal parameter type from the plurality of parameter types according to the total parameter ratio value sorting information, so as to select at least one abnormal detection information corresponding to the at least one abnormal parameter type from the plurality of first detection information.
Specifically, when the data processing apparatus 120 calculates a plurality of parameter values corresponding to a plurality of first detection information, the data processing apparatus 120 may sum all the parameter values corresponding to each parameter type to generate a total parameter value corresponding to each parameter type, and sum all the parameter values corresponding to the plurality of parameter types to generate a parameter sum corresponding to all the parameter types. Therefore, the data processing apparatus 120 may use the total parameter value corresponding to each parameter type as a numerator and use the parameter sum as a denominator to calculate the total parameter ratio value corresponding to each parameter type.
For example, following the previous example, the total parameter value of the 1 st parameter class is
And the total parameter value of the 2 nd parameter class is
By analogy, the total parameter value of the p-th parameter class is
And the total parameter ratio value of the 1 st parameter class is
And 2 nd parameter classA parameter proportional value of
By analogy, the total parameter proportion value of the p parameter class is
Based on the above method, the data processing apparatus 120 may sequence the total parameter ratio values corresponding to the parameter categories, and select a preset number of total parameter ratio values from the sequenced total parameter ratio values, where the preset number may be a value preset by a user or a value obtained after multiple abnormal exclusions of the machine.
In this way, the data processing apparatus 120 may select at least one abnormal detection information corresponding to the selected total parameter ratio value from the plurality of first detection information (for example, the machines 130(1) to 130(3) are abnormal machines and the temperature parameter and the pressure parameter in the detection information detected by the machines 130(1) to 130(3) are abnormal detection information).
In some embodiments, the tool monitoring system 100 may further include a display device (not shown) for displaying a warning message to notify the user, wherein the warning message includes the at least one abnormal tool and the at least one abnormal detection message. In another embodiment, the machine monitoring system 100 may further transmit the warning message to a monitoring device (not shown) used by the user to notify the user in real time.
In some embodiments, the user may adjust the process parameters of at least one abnormal apparatus of the apparatuses 130(1) to 130(N) according to the at least one abnormality detection information to correct the at least one abnormal apparatus.
Through the above steps, the machine monitoring system 100 of the embodiment of the invention may perform the above abnormal factor analysis on various kinds of detection information of the machines obtained from the detection device 110 (i.e., detect which detection information is abnormal among the various kinds of detection information) in real time to determine which machines among the machines 130(1) to 130(N) are abnormal machines and determine which detection information detected by the abnormal machines is abnormal detection information. In this way, the user can correct the abnormal tools in the tools 130(1) to 130(N) through the tool monitoring system 100.
FIG. 3 is a flow chart of a machine monitoring method according to further exemplary embodiments of the present invention. Referring to fig. 1 and fig. 3, the method of the present embodiment is also applicable to the equipment monitoring system 100 of fig. 1, and the detailed steps of the equipment monitoring method of the present embodiment are described below in conjunction with the operation relationship between the devices in the equipment monitoring system 100.
First, in step S301, the data processing apparatus 120 may collect a plurality of candidate inspection information of the tools 130(1) to 130(N) from the inspection apparatus 110.
Next, in step S303, the data processing device 120 may select a plurality of detection information from a plurality of candidate detection information according to a plurality of preset parameter categories. It should be noted that the preset parameter categories may be parameter categories that often cause an abnormal state of the tool in the past, and the parameter categories that often cause an abnormal state of the tool in the past may be parameter categories that are recognized by the data processing apparatus 120 through deep learning (deep learning) of the detection information detected in the past.
Then, in step S305, the data processing apparatus 120 normalizes the detected information to generate normalized parameters.
Next, in step S307, the data processing apparatus 120 may perform feature reduction on the normalized parameters to generate candidate coordinates corresponding to the stages 130(1) to 130 (N).
Next, in step S309, the data processing device 120 may generate a cohort distribution map according to the candidate coordinates.
For example, fig. 4 is a schematic diagram of a cohort profile according to some exemplary embodiments of the invention. Referring to fig. 4, each coordinate indicated in the cluster map is a two-dimensional candidate coordinate (PC1, PC2) corresponding to each tool.
Next, referring back to fig. 1 and fig. 3, in step S3011, the data processing device 120 may perform an outlier analysis on the histogram to determine whether there is at least one outlier in the candidate coordinates. If there is not at least one outlier, the process proceeds to step S3013. If there is at least one outlier coordinate, the process proceeds to step S3015.
In some embodiments, the data processing apparatus 120 may determine candidate coordinates corresponding to tools of the same process as a same group to generate at least one group, and calculate center coordinates of each group using a plurality of candidate coordinates (e.g., calculate coordinates corresponding to a geometric center of the candidate coordinates of each group), so as to calculate a distance value between the candidate coordinates corresponding to each tool and the center coordinates of its corresponding group. Therefore, the data processing device 120 can determine whether the distance value corresponding to each candidate coordinate is not less than a preset distance threshold. When the data processing device 120 determines that the distance value corresponding to a specific candidate coordinate is not less than the preset distance threshold, the data processing device 120 may determine the specific candidate coordinate as an outlier coordinate.
For example, referring to fig. 4, the outlier analysis method can determine that the cluster distribution map has clusters gp 1-gp 2 and determine which candidate coordinates of the tool are outlier coordinates. Therefore, the distance value between the candidate coordinates and the center of the corresponding group is not smaller than the preset distance threshold value, and whether at least one outlier coordinate exists or not is judged.
Referring back to fig. 1 and 3, in step S3013, the data processing apparatus 120 stops monitoring the machines 130(1) to 130 (N). In step S3015, the data processing device 120 may perform an anomaly factor analysis on a plurality of first detection information corresponding to at least one outlier coordinate to select at least one anomaly detection information from the plurality of first detection information.
Finally, in step S3017, the data processing device 120 may correct at least one abnormal apparatus corresponding to at least one outlier coordinate according to the at least one abnormal detection information.
In summary, the tool monitoring system provided by the present invention can determine which tools are abnormal tools from a plurality of tools by combining the principal component analysis method and the outlier analysis method. In addition, for these abnormal machines, the machine monitoring system provided by the invention further provides an abnormal factor analysis method for judging the parameter types affecting the machines. Therefore, the user can monitor and correct the abnormal machines according to the parameter types influencing the machines.
Although the present invention has been described with reference to the above embodiments, it should be understood that various changes and modifications can be made therein by those skilled in the art without departing from the spirit and scope of the invention.
Claims (10)
1. A machine monitoring system, comprising:
the detection device is used for detecting a plurality of machines to generate a plurality of detection information corresponding to the machines;
the data processing device is connected with the detection device and is used for:
receiving the detection information, and selecting at least one abnormal machine from the machines according to the detection information;
calculating a plurality of parameter values corresponding to a plurality of first detection information in the plurality of detection information, wherein the plurality of first detection information correspond to the at least one abnormal machine; and
and selecting at least one abnormal detection information from the first detection information according to the parameter values so as to correct the at least one abnormal machine by using the at least one abnormal detection information.
2. The machine monitoring system of claim 1, wherein the detection information corresponds to parameter classes, and the data processing device is further configured to:
generating a plurality of candidate coordinates corresponding to the plurality of machines according to the plurality of detection information and a plurality of weight values corresponding to the plurality of parameter categories; and
selecting the at least one abnormal machine from the plurality of machines by an outlier analysis method according to the candidate coordinates.
3. The machine monitoring system of claim 2, wherein the data processing device is further configured to:
the detection information is normalized to generate a plurality of normalized parameters, and the candidate coordinates corresponding to the machines are generated according to the normalized parameters and the weight values corresponding to the parameter types.
4. The machine monitoring system of claim 2, wherein the data processing device is further configured to:
and selecting at least one outlier coordinate from the candidate coordinates by utilizing the outlier analysis method according to the candidate coordinates, so as to select the at least one abnormal machine corresponding to the at least one outlier coordinate from the machines.
5. The machine monitoring system of claim 2, wherein the data processing device is further configured to:
calculating the plurality of parameter values according to the plurality of weighted values and the plurality of first detection information, and calculating a plurality of total parameter values corresponding to the plurality of parameter types according to the plurality of parameter values;
calculating a parameter sum of the total parameter values to calculate total parameter proportion values corresponding to the parameter classes according to the parameter sum and the total parameter values;
sorting the plurality of total parameter proportion values to generate total parameter proportion value sorting information; and
selecting at least one abnormal parameter category from the plurality of parameter categories according to the total parameter proportion value sorting information, so as to select the at least one abnormal detection information corresponding to the at least one abnormal parameter category from the plurality of first detection information.
6. A method for monitoring a machine, comprising:
generating a plurality of candidate coordinates corresponding to a plurality of machines according to a plurality of detection information of the plurality of machines, so as to select at least one abnormal machine from the plurality of machines according to the plurality of candidate coordinates;
calculating a plurality of parameter values corresponding to a plurality of first detection information from the plurality of first detection information, wherein the plurality of first detection information corresponds to the at least one abnormal machine; and
and selecting at least one abnormal detection information from the first detection information according to the contribution values so as to correct the at least one abnormal machine by using the at least one abnormal detection information.
7. The apparatus monitoring method as claimed in claim 6, wherein the detection information corresponds to parameter classes, and the step of generating candidate coordinates corresponding to the plurality of apparatuses according to the detection information to select the at least one abnormal apparatus from the plurality of apparatuses according to the candidate coordinates comprises:
generating the candidate coordinates corresponding to the machines according to the detection information and the weight values corresponding to the parameter classes; and
selecting the at least one abnormal machine from the plurality of machines by an outlier analysis method according to the candidate coordinates.
8. The apparatus monitoring method as claimed in claim 7, wherein the step of generating the candidate coordinates corresponding to the plurality of apparatuses according to the weight values corresponding to the parameter types and the detection information comprises:
the detection information is normalized to generate a plurality of normalized parameters, and the candidate coordinates corresponding to the machines are generated according to the normalized parameters and the weight values corresponding to the parameter types.
9. The machine monitoring method of claim 7, wherein selecting the at least one abnormal machine from the plurality of machines by the outlier analysis method based on the candidate coordinates comprises:
and selecting at least one outlier coordinate from the candidate coordinates by utilizing the outlier analysis method according to the candidate coordinates, so as to select the at least one abnormal machine corresponding to the at least one outlier coordinate from the machines.
10. The machine monitoring method as claimed in claim 7, wherein the step of calculating the parameter values corresponding to the first detection information from the first detection information comprises:
calculating the plurality of parameter values according to the plurality of weighted values and the plurality of first detection information,
wherein the step of selecting the at least one abnormal tool from the plurality of tools by the outlier analysis method according to the candidate coordinates comprises:
calculating a plurality of total parameter values corresponding to the plurality of parameter types according to the plurality of parameter values;
calculating a parameter sum of the total parameter values to calculate total parameter proportional values corresponding to the parameter classes according to the parameter sum and the total parameter values;
sorting the plurality of total parameter proportion values to generate total parameter proportion value sorting information; and
selecting at least one abnormal parameter category from the plurality of parameter categories according to the total parameter proportion value sorting information, so as to select the at least one abnormal detection information corresponding to the at least one abnormal parameter category from the plurality of first detection information.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| TW109132788A TWI770614B (en) | 2020-09-22 | 2020-09-22 | System for monitoring machines and method for monitoring machines |
| TW109132788 | 2020-09-22 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114253168A true CN114253168A (en) | 2022-03-29 |
Family
ID=80790856
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110068002.4A Pending CN114253168A (en) | 2020-09-22 | 2021-01-19 | Machine monitoring system and machine monitoring method |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114253168A (en) |
| TW (1) | TWI770614B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115460109A (en) * | 2022-11-11 | 2022-12-09 | 广州粤芯半导体技术有限公司 | Connection state detection method and device, computer equipment and readable storage medium |
| CN117410215A (en) * | 2023-12-15 | 2024-01-16 | 合肥晶合集成电路股份有限公司 | Method for determining machine parameters, control method, control system and device thereof |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI770614B (en) * | 2020-09-22 | 2022-07-11 | 南亞科技股份有限公司 | System for monitoring machines and method for monitoring machines |
| CN116629707B (en) * | 2023-07-20 | 2023-10-20 | 合肥喆塔科技有限公司 | FDC traceability analysis method based on distributed parallel computing and storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10242610A1 (en) * | 2001-12-14 | 2003-07-10 | Agilent Technologies Inc | Solder joint defects confirming method for circuit board assemblies, involves analyzing printed circuit board surface views to determine surface slope, and adjusting distance between circuit board and sensor |
| US20070010951A1 (en) * | 2005-06-30 | 2007-01-11 | Woo David C | Automated quality control method and system for genetic analysis |
| JP2009133843A (en) * | 2007-11-02 | 2009-06-18 | Nippon Steel Corp | Apparatus, method and program for analyzing distribution pattern of surface defect |
| US20160116892A1 (en) * | 2014-10-22 | 2016-04-28 | Industrial Technology Research Institute | Method and system of cause analysis and correction for manufacturing data |
| CN106095655A (en) * | 2016-05-31 | 2016-11-09 | 北京蓝海讯通科技股份有限公司 | A kind of method for detecting abnormality, application and monitoring device |
| CN106409711A (en) * | 2016-09-12 | 2017-02-15 | 佛山市南海区广工大数控装备协同创新研究院 | Solar silicon wafer defect detecting system and method |
| CN107402547A (en) * | 2017-08-29 | 2017-11-28 | 北京易沃特科技有限公司 | Unit exception detection method and system based on the point analysis that peels off |
| CN107765884A (en) * | 2016-08-22 | 2018-03-06 | 北京搜狗科技发展有限公司 | A kind of slide input method, device and electronic equipment |
| CN109067725A (en) * | 2018-07-24 | 2018-12-21 | 成都亚信网络安全产业技术研究院有限公司 | Network flow abnormal detecting method and device |
| CN111007750A (en) * | 2018-10-08 | 2020-04-14 | 上海洁鹿环保科技有限公司 | Oil-water separation system data processing method and device and storage medium |
| CN111243743A (en) * | 2020-01-17 | 2020-06-05 | 深圳前海微众银行股份有限公司 | Data processing method, device, equipment and computer readable storage medium |
| TW202213250A (en) * | 2020-09-22 | 2022-04-01 | 南亞科技股份有限公司 | System for monitoring machines and method for monitoring machines |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5077770B2 (en) * | 2006-03-07 | 2012-11-21 | 株式会社ニコン | Device manufacturing method, device manufacturing system, and measurement / inspection apparatus |
| US8607169B2 (en) * | 2011-12-28 | 2013-12-10 | Elitetech Technology Co., Ltd. | Intelligent defect diagnosis method |
| US10678225B2 (en) * | 2013-03-04 | 2020-06-09 | Fisher-Rosemount Systems, Inc. | Data analytic services for distributed industrial performance monitoring |
| TWI643071B (en) * | 2017-10-18 | 2018-12-01 | 銘祥科技實業股份有限公司 | Artificial intelligence sensing device calibration system and calibration method |
| US10311833B1 (en) * | 2018-03-27 | 2019-06-04 | Seiko Epson Corporation | Head-mounted display device and method of operating a display apparatus tracking an object |
| CN110942520B (en) * | 2019-11-27 | 2022-06-28 | 中南大学 | Auxiliary positioning method, device and system for operation equipment and storage medium |
-
2020
- 2020-09-22 TW TW109132788A patent/TWI770614B/en active
-
2021
- 2021-01-19 CN CN202110068002.4A patent/CN114253168A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE10242610A1 (en) * | 2001-12-14 | 2003-07-10 | Agilent Technologies Inc | Solder joint defects confirming method for circuit board assemblies, involves analyzing printed circuit board surface views to determine surface slope, and adjusting distance between circuit board and sensor |
| US20070010951A1 (en) * | 2005-06-30 | 2007-01-11 | Woo David C | Automated quality control method and system for genetic analysis |
| JP2009133843A (en) * | 2007-11-02 | 2009-06-18 | Nippon Steel Corp | Apparatus, method and program for analyzing distribution pattern of surface defect |
| US20160116892A1 (en) * | 2014-10-22 | 2016-04-28 | Industrial Technology Research Institute | Method and system of cause analysis and correction for manufacturing data |
| CN106095655A (en) * | 2016-05-31 | 2016-11-09 | 北京蓝海讯通科技股份有限公司 | A kind of method for detecting abnormality, application and monitoring device |
| CN107765884A (en) * | 2016-08-22 | 2018-03-06 | 北京搜狗科技发展有限公司 | A kind of slide input method, device and electronic equipment |
| CN106409711A (en) * | 2016-09-12 | 2017-02-15 | 佛山市南海区广工大数控装备协同创新研究院 | Solar silicon wafer defect detecting system and method |
| CN107402547A (en) * | 2017-08-29 | 2017-11-28 | 北京易沃特科技有限公司 | Unit exception detection method and system based on the point analysis that peels off |
| CN109067725A (en) * | 2018-07-24 | 2018-12-21 | 成都亚信网络安全产业技术研究院有限公司 | Network flow abnormal detecting method and device |
| CN111007750A (en) * | 2018-10-08 | 2020-04-14 | 上海洁鹿环保科技有限公司 | Oil-water separation system data processing method and device and storage medium |
| CN111243743A (en) * | 2020-01-17 | 2020-06-05 | 深圳前海微众银行股份有限公司 | Data processing method, device, equipment and computer readable storage medium |
| TW202213250A (en) * | 2020-09-22 | 2022-04-01 | 南亞科技股份有限公司 | System for monitoring machines and method for monitoring machines |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115460109A (en) * | 2022-11-11 | 2022-12-09 | 广州粤芯半导体技术有限公司 | Connection state detection method and device, computer equipment and readable storage medium |
| CN117410215A (en) * | 2023-12-15 | 2024-01-16 | 合肥晶合集成电路股份有限公司 | Method for determining machine parameters, control method, control system and device thereof |
| CN117410215B (en) * | 2023-12-15 | 2024-04-09 | 合肥晶合集成电路股份有限公司 | Method for determining machine parameters, control method, control system and device thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| TWI770614B (en) | 2022-07-11 |
| TW202213250A (en) | 2022-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114253168A (en) | Machine monitoring system and machine monitoring method | |
| Fan et al. | Data-driven approach for fault detection and diagnostic in semiconductor manufacturing | |
| US20220146462A1 (en) | Method for predicting remaining life of numerical control machine tool | |
| US10261496B2 (en) | Production system | |
| US9165843B2 (en) | Systems and methods of automatically detecting failure patterns for semiconductor wafer fabrication processes | |
| He et al. | Fault detection using the k-nearest neighbor rule for semiconductor manufacturing processes | |
| KR100839071B1 (en) | A system and method for monitoring conditions of a processing tool | |
| WO2019082407A1 (en) | Abnormality detection system and abnormality detection method | |
| TW200908186A (en) | Metrics independent and recipe independent fault classes | |
| JP2012532425A (en) | Automatic detection and classification of faults in plasma processing systems and methods | |
| US9910430B2 (en) | K-nearest neighbor-based method and system to provide multi-variate analysis on tool process data | |
| CN116825169B (en) | Abnormal memory chip detection method based on test equipment | |
| CN111652518A (en) | Method and apparatus for analyzing process data and computer readable medium | |
| KR20010033059A (en) | Process for monitoring processing plants | |
| CN110910021A (en) | Method for monitoring online defects based on support vector machine | |
| Yu et al. | Using minimum quantization error chart for the monitoring of process states in multivariate manufacturing processes | |
| TWI639908B (en) | Method for detecting and diagnosing an abnormal process | |
| US20170343999A1 (en) | Semiconductor device search and classification | |
| JP2019003238A (en) | Abnormality detection device and abnormality detection system | |
| TWI804745B (en) | Manufacturing measurement system | |
| CN113157666A (en) | Method and device for establishing wafer yield problem database | |
| EP3623965A1 (en) | Fabricated data detection method | |
| JP6785715B2 (en) | Normal / abnormal discrimination device, normal / abnormal discrimination method, and normal / abnormal discrimination system | |
| US20180107202A1 (en) | System and method for detecting fault events | |
| US12007428B2 (en) | Systems and methods for multidimensional dynamic part average testing |
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 |