WO2021065843A1 - 保守装置、保守方法、および、保守プログラム - Google Patents
保守装置、保守方法、および、保守プログラム Download PDFInfo
- Publication number
- WO2021065843A1 WO2021065843A1 PCT/JP2020/036748 JP2020036748W WO2021065843A1 WO 2021065843 A1 WO2021065843 A1 WO 2021065843A1 JP 2020036748 W JP2020036748 W JP 2020036748W WO 2021065843 A1 WO2021065843 A1 WO 2021065843A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- jig
- test
- maintenance
- test results
- maintenance device
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/28—Testing of electronic circuits, e.g. by signal tracer
- G01R31/2851—Testing of integrated circuits [IC]
- G01R31/2886—Features relating to contacting the IC under test, e.g. probe heads; chucks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R3/00—Apparatus or processes specially adapted for the manufacture or maintenance of measuring instruments, e.g. of probe tips
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/001—Measuring interference from external sources to, or emission from, the device under test, e.g. EMC, EMI, EMP or ESD testing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/26—Testing of individual semiconductor devices
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/26—Testing of individual semiconductor devices
- G01R31/2601—Apparatus or methods therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/28—Testing of electronic circuits, e.g. by signal tracer
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/28—Testing of electronic circuits, e.g. by signal tracer
- G01R31/2851—Testing of integrated circuits [IC]
- G01R31/2893—Handling, conveying or loading, e.g. belts, boats, vacuum fingers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Definitions
- the present invention relates to a maintenance device, a maintenance method, and a maintenance program.
- the condition of the jig deteriorates as the test is repeated. Therefore, conventionally, the jig has been regularly maintained at a predetermined timing.
- the maintenance device may include an acquisition unit that acquires a plurality of test results for each jig when a plurality of different devices to be measured are sequentially tested via a plurality of jigs.
- the maintenance device may include a calculation unit that calculates fluctuations in the test results for each jig using a plurality of test results.
- the maintenance device may include a determination unit that determines the maintenance timing of the jig based on the fluctuation of the test result.
- the determination unit may compare the fluctuation of the test result with the fluctuation in the normal state, calculate the difference, and determine the maintenance timing based on the difference.
- the fluctuation in the normal state may be the average of the fluctuation of the test results for a plurality of jigs in the normal state.
- the decision unit may decide to maintain the jig when the difference exceeds a predetermined threshold value.
- the predetermined threshold value may be determined by machine learning.
- the decision unit may calculate the difference by machine learning.
- the difference may be the Mahalanobis distance.
- the maintenance device may further include a learning unit that learns the covariance matrix used to calculate the Mahalanobis distance using a plurality of test results acquired in the normal state.
- the maintenance device further includes a model generation unit that generates a model that detects deviations with respect to fluctuations in the normal state by machine learning based on fluctuations in test results, and a determination unit calculates differences based on the output of the model. Good.
- the calculation unit may analyze a plurality of test results in a predetermined period while sequentially changing the starting point of the period, and calculate the fluctuation of the test results.
- the calculation unit may calculate the fluctuation of the fail rate in a plurality of test results.
- the fail rate may be a total fail rate indicating that at least one item in a plurality of test items has failed.
- the fail rate may be a partial fail rate indicating that a specific item in a plurality of test items has failed.
- the determination unit may determine the jig cleaning time as the maintenance timing.
- the determination unit may further determine the cleaning content of the jig.
- the determination unit may determine the cleaning content of the jig based on the fluctuation of the test result for each item in a plurality of test items.
- a maintenance method may include acquiring a plurality of test results for each jig in the case where a plurality of devices to be measured are sequentially tested through a plurality of jigs.
- the maintenance method may include calculating fluctuations in the test results for each jig using a plurality of test results.
- the maintenance method may include determining the maintenance timing of the jig based on the fluctuation of the test result.
- a maintenance program may be run by the computer.
- the maintenance program may function as an acquisition unit that acquires a plurality of test results for each jig when the computer sequentially tests a plurality of different devices to be measured via a plurality of jigs.
- the maintenance program may allow the computer to function as a calculation unit that calculates fluctuations in the test results for each jig using a plurality of test results.
- the maintenance program may allow the computer to act as a determinant to determine the maintenance timing of the jig based on fluctuations in test results.
- the maintenance device 200 according to this embodiment is shown together with the measurement system 10. An example of the details of the probe card 140 according to this embodiment is shown. An example of the case where the probe card 140 according to the present embodiment is brought into contact with the measurement target 20 is shown. An example of the flow in which the maintenance device 200 according to the present embodiment determines the maintenance timing of the jig 148 is shown. The variation of the test result and the Mahalanobis distance for each jig 148 calculated by the maintenance device 200 according to the present embodiment are shown. The maintenance device 200 according to the modified example of this embodiment is shown. An example of a computer 2200 in which a plurality of aspects of the present invention may be embodied in whole or in part is shown.
- FIG. 1 shows the maintenance device 200 according to the present embodiment together with the measurement system 10.
- the maintenance device 200 according to the present embodiment is, for example, a test carried out on a wafer in which a plurality of electronic devices such as semiconductors and Micro Electro Mechanical Systems (MEMS) are formed, and a bare chip obtained by dicing the wafer into individual pieces.
- MEMS Micro Electro Mechanical Systems
- it may be applied to various tests carried out in the measurement system 10, such as a test carried out at the same time for a plurality of tests or a test carried out for a plurality of packages containing chips at the same time. That is, the maintenance device 200 may be applied to tests performed in both the so-called pre-process and post-process.
- the maintenance device 200 is applied to a wafer test in which a wafer on which a plurality of devices 30 to be measured (for example, chips) are formed as a measurement target 20 is tested by using a tester. This case will be described.
- the test device 100 tests the measurement target 20.
- the test device 100 may be, for example, a device test device such as a system LSI tester, an analog tester, a logic tester, or a memory tester.
- the test device 100 gives various test signals to the measurement target 20 via a jig, and acquires response signals from the measurement target 20.
- the test device 100 includes a tester main body 110, a test head 120, a performance board 130, a probe card 140, and a prober 150.
- the tester main body 110 is the main body of the test device 100 and controls various tests.
- the tester main body 110 may have a function of outputting the test results obtained by various tests to the maintenance device 200 according to the present embodiment via wired or wireless.
- the test head 120 is connected to the tester main body 110 via a cable, and is configured to be driveable between a test position for testing the measurement target 20 and a retracted position.
- the test head 120 transmits a test signal to the measurement target 20 at the test position based on the control by the tester main body 110, receives a response signal from the measurement target 20, and sends it to the tester main body 110. Relay.
- the performance board 130 is detachably attached to the test head 120 and is electrically connected to the test head 120.
- the probe card 140 is detachably attached to the performance board 130 and is electrically connected to the performance board 130.
- the probe card 140 has a substrate 142, a probe housing 144, and a plurality of probe needles 146, and the plurality of probe needles 146 are brought into contact with a plurality of electrode pads in the measurement target 20 to make electrical contact. That is, the probe card 140 functions as an interface unit that connects the test function of the test device 100 and the measurement target 20 when the test device 100 tests the measurement target 20.
- the probe card 140 may be, for example, one using a vertical probe type probe needle or one using a cantilever type probe needle. Further, the probe card 140 may be appropriately modified in configuration according to the type of the measurement target 20. For example, when the maintenance device 200 is intended for a test in a subsequent process, the probe card 140 may have a socket or the like. Details of the probe card 140 will be described later.
- the substrate 142 may be, for example, a printed circuit board or the like.
- a probe housing 144 is provided on one surface of the substrate 142. Further, a plurality of connection pads (not shown) for connecting to the performance board 130 are provided on the other surface of the board 142.
- the probe housing 144 holds a plurality of probe needles 146 inside so that the tips of the respective needles are exposed.
- Each of the plurality of probe needles 146 has one end exposed to the outside of the probe housing 144 and the other end electrically to a connection pad provided on the other surface of the substrate 142 via the inside of the probe housing 144 and the substrate 142. It is connected.
- the plurality of probe needles 146 correspond to each of the plurality of electrode pads in the device 30 to be measured (four in the present embodiment) among the devices 30 to be measured formed in the measurement target 20. It is arranged.
- a group of probe needles 146 corresponding to each of the plurality of electrode pads in one device 30 to be measured form one probe unit.
- the jig 148 may be such a probe unit as an example. Therefore, the probe card 140 may have a plurality of jigs 148 corresponding to some of the devices to be measured 30 among the plurality of devices to be measured 30.
- each of the plurality of jigs 148 may be composed of functionally separated areas provided on one component (for example, one probe card 140). Alternatively, each of the plurality of jigs 148 may be composed of one independent component.
- the prober 150 conveys the measurement target 20 and places it on the stage, and aligns the measurement target 20 with the probe card 140. Further, the prober 150 has a cleaning unit (not shown) for cleaning a plurality of probe needles 146 in the jig 148.
- the test device 100 is electrically connected to the device to be measured 30 via the jig 148, the test device 100 is touched by the probe needle 146 so as to scratch the surface of the electrode pad in the device 30 to be measured, that is, to overdrive. Go down and make contact. At this time, oxides, dust, etc. on the electrode pad adhere to the needle tip of the probe needle 146.
- the test apparatus 100 cleans the probe needle 146 by providing a cleaning unit on the prober 150 and sharpening the tip by touching down the needle tip of the probe needle 146 so as to overdrive on the cleaning unit, for example. Removes deposits on the needle tip.
- the maintenance device 200 acquires and analyzes a plurality of test results when the test device 100 sequentially tests a plurality of different devices to be measured 30 via a plurality of jigs 148 in the measurement system 10. Then, the test apparatus 100 determines the maintenance timing of the jig 148 using the analyzed information.
- the maintenance device 200 may be a computer such as a PC (personal computer), a tablet computer, a smartphone, a workstation, a server computer, or a general-purpose computer, or may be a computer system to which a plurality of computers are connected. Such a computer system is also a computer in a broad sense. Further, the maintenance device 200 may be implemented by one or more virtual computer environments that can be executed in the computer.
- the maintenance device 200 may be a dedicated computer designed for maintenance of the jig 148, or may be dedicated hardware realized by a dedicated circuit.
- the maintenance device 200 may be a Web server connected to the Internet. In this case, the user accesses the maintenance device 200 on the cloud from various environments that can connect to the Internet to provide various services. Can receive.
- the maintenance device 200 may be configured as a single device connected to the measurement system 10 directly or via a network such as Local Area Network (LAN), or may be configured integrally with the measurement system 10 and is a measurement system. It may be realized as a part of 10 functional blocks.
- LAN Local Area Network
- the maintenance device 200 does not have to be connected to the measurement system 10, and the measurement system 10 does not have to be connected. It may be configured as a device independent of.
- the maintenance device 200 includes an input unit 210, an acquisition unit 220, a learning unit 230, a calculation unit 240, a determination unit 250, and an output unit 260. It should be noted that these blocks indicate functional blocks and do not necessarily match the actual device configuration. That is, just because it is shown as one block does not have to consist of only one device. Also, just because each is shown as a separate block does not mean that each is composed of different devices.
- the input unit 210 is an interface unit for inputting a plurality of test results.
- the input unit 210 is connected to, for example, the tester main body 110 of the test device 100 directly or via a network, and receives inputs of a plurality of test results tested by the test device 100.
- the input unit 210 may be a user interface that receives direct input from the user via a keyboard, a mouse, or the like, or is a device interface for connecting a USB memory, a disk drive, or the like to the maintenance device 200.
- input of a plurality of test results tested by the test apparatus 100 may be accepted through these interfaces.
- the acquisition unit 220 is connected to the input unit 210, and in the measurement system 10, a plurality of test results when the test apparatus 100 sequentially tests a plurality of different devices under test 30 via a plurality of jigs 148 are obtained. , Obtained for each jig 148. Then, the acquisition unit 220 supplies the plurality of test results acquired in the normal state to the learning unit 230. Further, the acquisition unit 220 supplies a plurality of test results acquired in the operating state to the calculation unit 240. The details of the test by the test apparatus 100 will be described later.
- the learning unit 230 determines the fluctuation in the normal state by using the plurality of test results acquired in the normal state.
- the variation in the normal state may be the average of the variation in the test results for the plurality of jigs 148 in the normal state.
- the learning unit 230 learns the covariance matrix used for calculating the Mahalanobis distance by using the plurality of test results acquired in the normal state. This will also be described later.
- the learning unit 230 supplies the variation and covariance matrix in the normal state to the determination unit 250.
- the calculation unit 240 uses a plurality of test results acquired in the operating state to calculate fluctuations in the test results for each jig 148.
- the calculation unit 240 supplies the fluctuation of the test result for each jig 148 to the determination unit 250.
- the determination unit 250 determines the maintenance timing of the jig 148 based on the fluctuation of the test result for each jig 148. At this time, the determination unit 250 may compare the fluctuation of the test result with the fluctuation in the normal state, calculate the difference, and determine the maintenance timing of the jig 148 based on the difference. The determination unit 250 supplies the maintenance timing of the jig 148 to the output unit 260.
- the output unit 260 outputs the maintenance timing of the jig 148 determined by the determination unit 250. At this time, the output unit 260 may display and output the maintenance timing on a monitor or the like, output audio by a speaker or the like, or output data to various memory devices or the like.
- FIG. 2 shows an example of details of the probe card 140 according to the present embodiment.
- a side view of the probe card 140 is shown on this figure. Further, a back view of the probe card 140 is shown below this figure.
- the plurality of probe needles 146 are arranged corresponding to each of the plurality of electrode pads in some of the devices to be measured 30 among the devices 30 to be measured formed on the measurement target 20. Then, a plurality of probe needles 146 corresponding to each of the plurality of electrode pads in one device 30 form a group (probe unit) in a substantially square or rectangular shape, for example, and form one jig 148. doing.
- the probe card 140 has four jigs 148a to 148ar arranged in a square shape, two in the X direction and two in the Y direction, is shown as an example.
- the test apparatus 100 can simultaneously test (measure) several (four in this embodiment) devices under test by contacting the probe card 140 with the measurement target 20.
- the number and arrangement of jigs 148 included in the probe card 140 are not limited to this.
- the probe card 140 may have more or less jigs 148 than four. Further, the probe card 140 may have a plurality of jigs 148 arranged in a shape different from a square such as a straight line.
- FIG. 3 shows an example in which the probe card 140 according to the present embodiment is brought into contact with the measurement target 20.
- a plurality of devices 30 to be measured are formed on the measurement target 20.
- the unique device to be measured 30 is described separately, it is referred to as the device to be measured 30 (x, y) by using the coordinate x in the X direction and the coordinate y in the Y direction.
- the test device 100 tests up to four devices under measurement 30 at the same time using, for example, the probe card 140 shown in FIG. That is, the test apparatus 100 aligns the probe card 140 and the measurement target 20 with the prober 150, and touches down the probe card 140 to the measurement target 20 (first time). Then, the test apparatus 100 includes the device 30 (3,1) to be measured via the jig 148a, the device 30 (4,1) to be measured via the jig 148b, and the device 30 to be measured (4,1) via the jig 148c. The device 30 (4,2) to be measured is simultaneously tested via the jigs 148d and 3,2).
- the test apparatus 100 uses the test result a1 of the device 30 (3,1) to be measured, the test result b1 of the device 30 (4,1) to be measured, and the test result of the device 30 (3,2) to be measured.
- the test result d1 of c1 and the device 30 (4, 2) to be measured is acquired.
- the device 30 (3, 1) to be measured is not actually formed on the measurement target 20. Therefore, the test apparatus 100 acquires the test result as no result for the test result a1 of the device 30 (3, 1) to be measured.
- the test apparatus 100 may acquire the test result as no result for the test result in the region where the device to be measured 30 does not exist.
- the test apparatus 100 changes the relative position between the probe card 140 and the measurement target 20 by the prober 150, and touches down the probe card 140 to the measurement target 20 again (second time). Then, the test apparatus 100 includes the device 30 (5, 1) to be measured via the jig 148a, the device 30 (6, 1) to be measured via the jig 148b, and the device 30 to be measured (6, 1) via the jig 148c. 5, 2) and the device 30 (6, 2) to be measured are simultaneously tested via the jig 148d. In this way, the test apparatus 100 uses the test result a2 of the device 30 (5,1) to be measured, the test result b2 of the device 30 (6,1) to be measured, and the test result of the device 30 (5,2) to be measured. c2 and the test result d2 of the device to be measured 30 (6, 2) are acquired.
- the test apparatus 100 changes the relative position between the probe card 140 and the measurement target 20 by the prober 150, and touches down the probe card 140 to the measurement target 20 again (third time). Then, the test apparatus 100 includes the device 30 (7, 1) to be measured via the jig 148a, the device 30 (8, 1) to be measured via the jig 148b, and the device 30 (measurement 30) via the jig 148c. 7,2) and the device 30 (8,2) to be measured are simultaneously tested via the jig 148d. In this way, the test apparatus 100 uses the test result a3 of the device 30 (7,1) to be measured, the test result b3 of the device 30 (8,1) to be measured, and the test result of the device 30 (7,2) to be measured. The test result d3 of c3 and the device 30 (8, 2) to be measured is acquired.
- the test apparatus 100 sequentially tests a plurality of different devices to be measured 30 via a plurality of jigs 148. Then, the test apparatus 100 acquires a plurality of test results obtained by testing the plurality of devices 30 to be measured, and stores the plurality of test results in association with information indicating through which jig each of the plurality of test results was tested.
- the test device 100 may output the plurality of test results stored in this way to the maintenance device 200 via wire or wireless.
- the maintenance device 200 analyzes the plurality of test results obtained in this way to determine the maintenance timing of the jig 148.
- FIG. 4 shows an example of a flow in which the maintenance device 200 according to the present embodiment determines the maintenance timing of the jig 148.
- the maintenance device 200 acquires a plurality of test results in a normal state.
- the plurality of test results in the normal state may be, for example, a plurality of test results in which a plurality of different devices to be measured 30 are sequentially tested via a plurality of normal jigs 148.
- the test apparatus 100 uses a probe card 140 that has been cleaned or has not been used, and one measurement target 20 (for example, one wafer) is used through a plurality of jigs 148 in the probe card 140.
- a plurality of test results obtained by sequentially testing all the devices 30 to be measured formed on the wafer may be, for example, the first (first) wafer when mass production of a new type of wafer is started.
- the test apparatus 100 may clean the probe card 140 again in the middle of the test of the one measurement target 20 in order to acquire a plurality of test results in a normal state.
- the input unit 210 receives the input of the plurality of test results in the normal state acquired in this way, and supplies the input to the acquisition unit 220.
- the acquisition unit 220 is sequentially tested through a plurality of test results a1 to a32 and the normal jig 148b, which are sequentially tested via the normal (cleaned or unused) jig 148a.
- Each d32 is acquired.
- each of the plurality of test results indicates, as an example, whether the test performed on the device to be measured 30 has passed, failed, or no test result.
- the test apparatus 100 tests a plurality of test items corresponding to a plurality of categories, such as an open short test, a DC test, a function test, an FM test, and a USB test, on each of the devices 30 to be measured. Therefore, for each of the plurality of test results, for example, all of the plurality of test items performed on each of the devices to be measured 30 have passed (P: total pass), or at least one item has failed (F: total). It may indicate either (fail) or no test result (N / A).
- the acquisition unit 220 has a plurality of test results b1 to b32 tested via the normal jig 148b, a plurality of test results c1 to c32 tested via the normal jig 148c, and a normal one.
- a plurality of test results d1 to d32 tested via the jig 148d are acquired.
- the acquisition unit 220 supplies a plurality of test results in a normal state to the learning unit 230.
- the test apparatus 100 determines the variation in the normal state.
- the variation in the normal state may be the average of the variation in the test results for the plurality of jigs 148 in the normal state.
- the learning unit 230 analyzes a plurality of test results in a predetermined period among a plurality of test results acquired in the normal state while sequentially changing the start point of the period to change the normal state. decide.
- the learning unit 230 shall use a plurality of test results in 20 touchdown periods as a plurality of test results in a predetermined period.
- the total fail rate u2 in the above is calculated by the same method as described above.
- the fail rate u3 is calculated.
- the learning unit 230 determines, for example, the fluctuation u (u1, u2, u3, ..., Un) in the normal state by sequentially changing the start point of the period.
- the learning unit 230 supplies the determined fluctuation u in the normal state to the determination unit 250.
- the maintenance device 200 calculates the covariance matrix.
- the learning unit 230 learns the covariance matrix used to calculate the Mahalanobis distance using a plurality of test results acquired in the normal state.
- the Mahalanobis distance for a group of values represented by a multivariable vector x such that the mean vector is u and the covariance matrix is ⁇ is defined as: More specifically, the Mahalanobis distance quantitatively indicates how far a certain data is from the average, and indicates the distance from the data group considering the degree of dispersion of the data in each direction. Therefore, when the multivariable vector x matches the mean vector u, the Mahalanobis distance becomes 0, and when the multivariable vector x does not match the mean vector u, the Mahalanobis distance becomes greater than 0.
- the learning unit 230 calculates the covariance, which is the average value of the products of the deviations from the mean between each variable, and learns the covariance matrix ⁇ , which is a matrix in which the covariances are arranged. Then, the learning unit 230 supplies the learned covariance matrix ⁇ to the determination unit 250.
- the maintenance device 200 acquires a plurality of test results in the operating state for each jig.
- the acquisition unit 220 acquires a plurality of test results for each jig 148 when a plurality of different devices to be measured 30 are sequentially tested via a plurality of jigs 148 in an operating state. That is, in the operating state, the acquisition unit 220 has a plurality of test results a1 to a32 sequentially tested via the jig 148a, a plurality of test results b1 to b32 sequentially tested via the jig 148b, and the jig 148c.
- a plurality of test results c1 to c32 sequentially tested via the jig 148d and a plurality of test results d1 to d32 sequentially tested via the jig 148d are obtained, respectively.
- each of the plurality of test results as in the case of the plurality of test results in the normal state, all of the plurality of test items performed on each of the devices to be measured 30 have passed (total pass), or at least one.
- the item may indicate either a fail (total fail) or no test result.
- the acquisition unit 220 sequentially acquires a plurality of test results in the operating state and supplies them to the calculation unit 240.
- the maintenance device 200 calculates the fluctuation of the test result in the operating state for each jig 148.
- the calculation unit 240 calculates the fluctuation of the test result for each jig 148 by using a plurality of test results acquired in the operating state.
- the calculation unit 240 may analyze a plurality of test results in a predetermined period while sequentially changing the start point of the period, and calculate the fluctuation of the test results, similarly to the learning unit 230.
- the maintenance device 200 calculates the fluctuation of the test result based on the test result in a certain period instead of accumulating the test result, so that the fluctuation of the test result can be calculated with high sensitivity.
- the calculation unit 240 may calculate the fluctuation of the fail rate in a plurality of test results at this time.
- the fail rate may be a total fail rate indicating that at least one item in the plurality of test items has failed.
- the maintenance device 200 calculates the fluctuation of the test result using a relatively simple index of whether the test has passed or failed, so that the calculation load of the fluctuation of the test result can be reduced.
- the calculation unit 240 uses the same method to determine the variation xb (xb1, xb2, xb3, ..., Xbn) of the test result for the jig 148b, the variation xc (xc1, xc2, xc3, ...) Of the test result for the jig 148c. , Xcn), and the variation xd (xd1, xd2, xd3, ..., Xdn) of the test result for the jig 148d are calculated, respectively. In this way, the calculation unit 240 calculates the variation x of the test result for each jig 148 using the plurality of test results in the operating state. The calculation unit 240 supplies the calculated variation x (xa, xb, xc, xd) of the test result for each jig 148 to the determination unit 250.
- the maintenance device 200 calculates the difference from the fluctuation u in the normal state.
- the determination unit 250 may compare the variation x of the test result for each jig 148 with the variation u in the normal state to calculate the difference, and determine the maintenance timing of the jig 148 based on the difference.
- the difference may be the Mahalanobis distance.
- the determination unit 250 uses the variation x (xa, xb, xc, xd) of the test result for each jig 148 calculated in step 450 as the multivariable vector x as the average vector u.
- the variation u (u1, u2, u3, ..., Un) in the normal state calculated in step 420 is substituted, and the Mahalanobis distance is calculated using the inverse matrix of the covariance matrix ⁇ learned in step 430.
- the maintenance device 200 determines whether or not the difference calculated in step 460 exceeds the threshold value. For example, the determination unit 250 determines whether or not the Mahalanobis distance calculated in step 460 exceeds a predetermined threshold value. Then, when it is determined that the Mahalanobis distance does not exceed the threshold value, the determination unit 250 determines that it is not necessary to maintain the jig 148 and proceeds to the process in step 490. On the other hand, when it is determined that the Mahalanobis distance exceeds the threshold value, the determination unit 250 determines that the jig 148 needs to be maintained and proceeds to step 480.
- the determination unit 250 may determine that it is time to maintain the jig 148 when the Mahalanobis distance exceeds the threshold value a predetermined number of times. In this way, the determination unit 250 determines the maintenance timing of the jig 148 based on the variation x of the test result for each jig 148.
- the determination unit 250 may determine the cleaning time of the jig 148 as the maintenance timing. However, it is not limited to this. As the maintenance timing, the determination unit 250 may determine a maintenance timing different from the cleaning timing, such as a replacement timing of the jig 148.
- step 480 the maintenance device 200 maintains the jig 148.
- the maintenance device 200 may perform cleaning of the jig 148 as maintenance of the jig 148.
- the maintenance device 200 advances the process to step 490.
- step 490 the maintenance device 200 determines whether or not the test of the measurement target 20 is completed. When it is determined that the test of the measurement target 20 is completed, the maintenance device 200 ends the process. On the other hand, when it is determined that the test of the measurement target 20 is not completed, the maintenance device 200 returns the process to step 440 and repeats the analysis while sequentially changing the start point of the period.
- FIG. 5 shows the variation of the test result for each jig 148 calculated by the maintenance device 200 according to the present embodiment and the Mahalanobis distance.
- the horizontal axis indicates the start point position m.
- the vertical axis represents the total fail rate [%]. Therefore, this figure shows the fluctuation of the test result (total fail rate) for each jig 148 when the start point position m is sequentially changed.
- the vertical axis indicates the Mahalanobis distance. Therefore, the lower part of this figure shows the Mahalanobis distance calculated based on the fluctuation of the test result for each jig when the start point position m is sequentially changed.
- the maintenance device 200 calculates the variation of the test result for each of the plurality of jigs 148. That is, when the number of jigs 148 is four, the maintenance device 200 calculates the fluctuations of the four test results. However, the maintenance device 200 calculates the Mahalanobis distance based on the fluctuation of the test result for each of the plurality of jigs 148, and determines the maintenance timing of the jig 148 based on the Mahalanobis distance. As described above, since the maintenance device 200 determines the maintenance timing of the jig 148 based on only one index such as the Mahalanobis distance, the maintenance timing of the jig 148 can be determined relatively easily.
- the defective device 30 to be measured is evenly generated in the measurement target 20. Further, the plurality of jigs 148 in the probe card 140 are suddenly soiled with a small probability. Therefore, when a plurality of devices to be measured, which are different from each other, are sequentially tested by the plurality of jigs 148, the probability that the plurality of test results will fail at the same time is very small.
- the maintenance device 200 utilizes such an actual condition, and determines the maintenance timing of the jig 148 based on the fluctuation of the test result for each jig 148. Generally, cleaning of the jig 148 is performed by touching down the jig on the file and overdriving it.
- the life of the probe card 140 is roughly determined by the number of times cleaning is performed.
- the jig 148 is cleaned according to a cycle determined in advance by an empirical rule, a preliminary test, or the like.
- regular maintenance of the jig 148 may be excessive or inadequate in testing the device 30 under test. For example, if the jig 148 is over-maintained, the life of the probe card 140 may be shortened more than necessary. Further, when the maintenance of the jig 148 is insufficient, the yield decreases as the contact resistance of the probe needle 146 increases.
- the maintenance timing of the jig 148 can be determined on-demand based on the fluctuation of the test result for each jig 148, so that the jig 148 can be used.
- the timing of maintenance can be optimized.
- the life of the probe card 140 can be extended while suppressing a decrease in yield.
- the maintenance device 200 may maintain the jig 148 on demand, for example, in addition to regularly maintaining the jig 148 as in the conventional case. That is, the maintenance device 200 may maintain the jig 148 by combining regular maintenance and on-demand maintenance.
- the maintenance device 200 determines the fluctuation in the normal state and learns the covariance matrix based on the test result of the first wafer when mass production of a new type of wafer is started.
- the case is shown as an example. However, it is not limited to this.
- the maintenance device 200 determines the variation in the normal state based on the test result of the first wafer and learns the covariance matrix, and then in the operating state, the yield is higher than that of the first wafer.
- the variation in the normal state and the covariance matrix may be updated based on the test result.
- the maintenance device 200 determines the fluctuation in the normal state and learns the covariance matrix based on the test results of one measurement target 20 (one wafer). Although shown, it is not limited to this.
- the maintenance device 200 may determine the variation in the normal state and learn the covariance matrix based on the statistics (for example, average) of the test results of the plurality of measurement objects 20.
- the maintenance device 200 learns the covariance matrix and uses the Mahalanobis distance as the difference between the fluctuation of the test result for each jig 148 and the fluctuation in the normal state is shown as an example. , Not limited to this.
- the maintenance device 200 inputs a plurality of test results in a normal state as teacher data into a learning model such as a neural network, and calculates the difference between the fluctuation of the test result for each jig 148 and the fluctuation in the output of the learning model. Based on this, the maintenance timing of the jig 148 may be determined.
- the maintenance device 200 may use the Euclidean distance instead of the Mahalanobis distance as the difference.
- the determination unit 250 may calculate the sum of each component as a difference by subtracting the fluctuation u in the normal state from the fluctuation x of the test result and taking an absolute value for each component, for example.
- the determination unit 250 uses the Mahalanobis distance as an example of calculating the difference by machine learning is shown.
- the determination unit 250 may calculate the difference by another machine learning algorithm.
- FIG. 6 shows a maintenance device 200 according to a modified example of the present embodiment.
- members having the same functions and configurations as those in FIG. 1 are designated by the same reference numerals, and the description thereof will be omitted except for the following differences.
- the maintenance device 200 according to this modification includes a model generation unit 610 instead of the learning unit 230.
- the model generation unit 610 generates a model for detecting the deviation with respect to the fluctuation u in the normal state by machine learning based on the fluctuation x of the test result.
- the model generation unit 610 may generate a model by an unsupervised anomaly detection algorithm.
- the model generation unit 610 uses a plurality of test results acquired during the learning period as learning data to calculate the characteristics of the statistical distribution of fluctuation u in the normal state. Then, the model generation unit 610 generates a model so as to detect a deviation with respect to the change u in the normal state when the variation x of the test result is input to the model based on the characteristics of the calculated statistical distribution.
- the model generation unit 610 since the model generation unit 610 generates the model by unsupervised learning, the work of annotation for creating the teacher data can be omitted, and the model can be generated more easily. However, it is not limited to this.
- the model generation unit 610 may generate a model by various learning algorithms such as a supervised learning algorithm, a semi-supervised learning algorithm, and a reinforcement learning algorithm.
- the model generation unit 610 supplies the generated model to the determination unit 250.
- the determination unit 250 calculates the difference based on the output of the model supplied from the model generation unit 610. For example, the determination unit 250 inputs the variation x of the test result for each jig 148 calculated by the calculation unit 240 into the model generated by the model generation unit 610, and calculates the output of the model as a difference.
- the maintenance device 200 according to this modification calculates the difference based on the output of the model generated by machine learning.
- the maintenance timing of the jig 148 can be determined by various machine learning algorithms.
- the determination unit 250 determines to maintain the jig 148 when the calculated difference exceeds a predetermined threshold value.
- the predetermined threshold value may be a fixed value preset by the worker based on an empirical rule, but is not limited to this.
- the predetermined threshold value may be determined by machine learning.
- the maintenance device 200 may learn the threshold value for determining the maintenance timing of the jig 148 by machine learning. In this case, the maintenance device 200 acquires actual data indicating that the jig 148 has been maintained, for example, data indicating what kind of cleaning was performed at what timing.
- the maintenance device 200 learns the relationship between the difference and the maintenance result by using the difference data calculated by the determination unit 250 and the actual result data as learning data. As a result, the maintenance device 200 determines by machine learning how much the difference should be before the maintenance of the jig 148 is performed, that is, the threshold value for determining the maintenance timing. As a result, according to the maintenance device 200, the threshold value for determining the maintenance timing can be set to the optimum value based on the actual results without human intervention.
- the fail rate used as the test result is the total fail rate indicating that at least one item (also referred to as a bin or a category) in a plurality of test items has failed is shown as an example. It is not limited to this.
- the fail rate may be a partial fail rate indicating that a specific item in a plurality of test items has failed. That is, the maintenance device 200 may use as a test result a partial fail rate indicating that a specific item has failed, regardless of whether or not other items in the plurality of test items have failed. Here, such a specific item may be one or a plurality. When there are a plurality of specific items, the maintenance device 200 may use the logical sum of the test results for each item as a partial fail rate. As described above, according to the maintenance device 200, either the total fail rate or the partial fail rate can be used as the test result, and various cases can be flexibly dealt with.
- the determination unit 250 may further determine the cleaning content of the jig 148.
- the cleaning content of the jig 148 There are various types of cleaning of the jig 148, such as cleaning with a brush, cleaning with a polishing sheet, and cleaning with a cleaning wafer.
- cleaning completed inside the device as described above, there is also cleaning outside the device such as removing the probe card and cleaning with another device.
- the determination unit 250 may determine the optimum cleaning content from among such a plurality of types of cleaning.
- the determination unit 250 may determine the cleaning content of the jig 148 based on the fluctuation of the test result for each item in the plurality of test items. For example, if the difference in the variation of the fail rate in the open short test exceeds a predetermined threshold value, it is highly possible that the needle tip is dirty, so the determination unit 250 is cleaned with a polishing sheet. May be decided to carry out. Similarly, if the fluctuation of the fail rate in the leak test (part of the DC test) exceeds a predetermined threshold, it is highly likely that a short circuit between the pins is the cause, so the determination unit 250 , It may be decided to carry out cleaning with a brush. As a result, the maintenance device 200 can determine the optimum cleaning content depending on which test item causes the jig 148 to be cleaned.
- a plurality of test results are acquired with the first (first) wafer when mass production of a new type of wafer is started as a measurement target.
- the case is shown as an example.
- the quality of the wafer itself also differs from wafer to wafer, and each wafer may have unique characteristics. Such unique characteristics are unlikely to vary widely within one lot, but variations can be significant between lots. Therefore, each time the lot to be measured is switched, the maintenance device 200 may acquire a plurality of test results in a normal state with the leading wafer of the lot as the measurement target via the normal jig 148.
- the maintenance device 200 may update the fluctuation u in the normal state, which is the reference of the difference, every time the lot is switched. As a result, the maintenance device 200 can determine whether the cause of the large difference is on the jig 148 side or the wafer side.
- Various embodiments of the present invention may be described with reference to flowcharts and block diagrams, wherein the block is (1) a stage of the process in which the operation is performed or (2) a device responsible for performing the operation. May represent a section of. Specific stages and sections are implemented by dedicated circuits, programmable circuits supplied with computer-readable instructions stored on a computer-readable medium, and / or processors supplied with computer-readable instructions stored on a computer-readable medium. You can.
- Dedicated circuits may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits.
- Programmable circuits are memory elements such as logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logical operations, flip-flops, registers, field programmable gate arrays (FPGA), programmable logic arrays (PLA), etc. May include reconfigurable hardware circuits, including, etc.
- the computer-readable medium may include any tangible device capable of storing instructions executed by the appropriate device, so that the computer-readable medium having the instructions stored therein is specified in a flowchart or block diagram. It will be equipped with a product that contains instructions that can be executed to create a means for performing the operation. Examples of computer-readable media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, and the like.
- Computer-readable media include floppy® disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), Electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray (RTM) disc, memory stick, integrated A circuit card or the like may be included.
- RAM random access memory
- ROM read-only memory
- EPROM or flash memory erasable programmable read-only memory
- EEPROM Electrically erasable programmable read-only memory
- SRAM static random access memory
- CD-ROM compact disc read-only memory
- DVD digital versatile disc
- RTM Blu-ray
- Computer-readable instructions are assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or object-oriented programming such as Smalltalk, JAVA®, C ++, etc. Contains either source code or object code written in any combination of one or more programming languages, including languages and traditional procedural programming languages such as the "C" programming language or similar programming languages. Good.
- Computer-readable instructions are applied to a general-purpose computer, a special purpose computer, or the processor or programmable circuit of another programmable data processing device, either locally or in a wide area network (WAN) such as the local area network (LAN), the Internet, etc. ) May be executed to create a means for performing the operation specified in the flowchart or block diagram.
- WAN wide area network
- LAN local area network
- Internet etc.
- processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers and the like.
- FIG. 7 shows an example of a computer 2200 in which a plurality of aspects of the present invention may be embodied in whole or in part.
- the program installed on the computer 2200 can cause the computer 2200 to function as an operation associated with the device according to an embodiment of the present invention or as one or more sections of the device, or the operation or the one or more. Sections can be run and / or the computer 2200 can be run a process according to an embodiment of the invention or a stage of such process.
- Such a program may be run by the CPU 2212 to cause the computer 2200 to perform certain operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.
- the computer 2200 includes a CPU 2212, a RAM 2214, a graphic controller 2216, and a display device 2218, which are connected to each other by a host controller 2210.
- the computer 2200 also includes input / output units such as a communication interface 2222, a hard disk drive 2224, a DVD-ROM drive 2226, and an IC card drive, which are connected to the host controller 2210 via the input / output controller 2220.
- input / output units such as a communication interface 2222, a hard disk drive 2224, a DVD-ROM drive 2226, and an IC card drive, which are connected to the host controller 2210 via the input / output controller 2220.
- the computer also includes legacy input / output units such as the ROM 2230 and keyboard 2242, which are connected to the input / output controller 2220 via an input / output chip 2240.
- the CPU 2212 operates according to the programs stored in the ROM 2230 and the RAM 2214, thereby controlling each unit.
- the graphic controller 2216 acquires the image data generated by the CPU 2212 in a frame buffer or the like provided in the RAM 2214 or itself so that the image data is displayed on the display device 2218.
- the communication interface 2222 communicates with other electronic devices via the network.
- the hard disk drive 2224 stores programs and data used by the CPU 2212 in the computer 2200.
- the DVD-ROM drive 2226 reads the program or data from the DVD-ROM 2201 and provides the program or data to the hard disk drive 2224 via the RAM 2214.
- the IC card drive reads programs and data from the IC card and / or writes programs and data to the IC card.
- the ROM 2230 stores a boot program or the like executed by the computer 2200 at the time of activation and / or a program depending on the hardware of the computer 2200.
- the input / output chip 2240 may also connect various input / output units to the input / output controller 2220 via a parallel port, serial port, keyboard port, mouse port, and the like.
- the program is provided by a computer-readable medium such as a DVD-ROM 2201 or an IC card.
- the program is read from a computer-readable medium, installed on a hard disk drive 2224, RAM 2214, or ROM 2230, which is also an example of a computer-readable medium, and executed by the CPU 2212.
- the information processing described in these programs is read by the computer 2200 and provides a link between the program and the various types of hardware resources described above.
- the device or method may be configured by implementing manipulation or processing of information in accordance with the use of computer 2200.
- the CPU 2212 executes a communication program loaded in the RAM 2214, and performs communication processing on the communication interface 2222 based on the processing described in the communication program. You may order.
- the communication interface 2222 reads and reads transmission data stored in a transmission buffer processing area provided in a recording medium such as a RAM 2214, a hard disk drive 2224, a DVD-ROM 2201, or an IC card. The data is transmitted to the network, or the received data received from the network is written to the reception buffer processing area or the like provided on the recording medium.
- the CPU 2212 causes the RAM 2214 to read all or necessary parts of a file or database stored in an external recording medium such as a hard disk drive 2224, a DVD-ROM drive 2226 (DVD-ROM2201), or an IC card. Various types of processing may be performed on the data on the RAM 2214. The CPU 2212 then writes back the processed data to an external recording medium.
- an external recording medium such as a hard disk drive 2224, a DVD-ROM drive 2226 (DVD-ROM2201), or an IC card.
- Various types of processing may be performed on the data on the RAM 2214.
- the CPU 2212 then writes back the processed data to an external recording medium.
- the CPU 2212 describes various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, and information retrieval described in various parts of the present disclosure with respect to the data read from the RAM 2214. Various types of processing may be performed, including / replacement, etc., and the results are written back to RAM 2214. Further, the CPU 2212 may search for information in a file, a database, or the like in the recording medium. For example, when a plurality of entries each having an attribute value of the first attribute associated with the attribute value of the second attribute are stored in the recording medium, the CPU 2212 specifies the attribute value of the first attribute. Search for an entry that matches the condition from the plurality of entries, read the attribute value of the second attribute stored in the entry, and associate it with the first attribute that satisfies the predetermined condition. The attribute value of the second attribute obtained may be acquired.
- the program or software module described above may be stored on a computer 2200 or on a computer-readable medium near the computer 2200.
- a recording medium such as a hard disk or RAM provided within a dedicated communication network or a server system connected to the Internet can be used as a computer-readable medium, thereby providing the program to the computer 2200 over the network. To do.
- Measurement system 20 Measurement target 30 Measured device 100 Test device 110 Tester body 120 Test head 130 Performance board 140 Probe card 142 Board 144 Probe housing 146 Probe needle 148 Jig 150 Prober 200 Maintenance device 210 Input unit 220 Acquisition unit 230 Learning unit 240 Calculation unit 250 Decision unit 260 Output unit 610 Model generation unit 2200 Computer 2201 DVD-ROM 2210 Host controller 2212 CPU 2214 RAM 2216 Graphic controller 2218 Display device 2220 I / O controller 2222 Communication interface 2224 Hard disk drive 2226 DVD-ROM drive 2230 ROM 2240 Input / Output Chip 2242 Keyboard
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Computer Hardware Design (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Electromagnetism (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Testing Or Measuring Of Semiconductors Or The Like (AREA)
Abstract
Description
20 測定対象
30 被測定デバイス
100 試験装置
110 テスタ本体
120 テストヘッド
130 パフォーマンスボード
140 プローブカード
142 基板
144 プローブハウジング
146 プローブニードル
148 治具
150 プローバ
200 保守装置
210 入力部
220 取得部
230 学習部
240 算出部
250 決定部
260 出力部
610 モデル生成部
2200 コンピュータ
2201 DVD-ROM
2210 ホストコントローラ
2212 CPU
2214 RAM
2216 グラフィックコントローラ
2218 ディスプレイデバイス
2220 入/出力コントローラ
2222 通信インターフェイス
2224 ハードディスクドライブ
2226 DVD-ROMドライブ
2230 ROM
2240 入/出力チップ
2242 キーボード
Claims (18)
- 複数の治具を介してそれぞれ異なる複数の被測定デバイスを順次試験した場合における複数の試験結果を、治具ごとに取得する取得部と、
前記複数の試験結果を用いて、試験結果の変動を前記治具ごとに算出する算出部と、
前記試験結果の変動に基づいて、前記治具の保守タイミングを決定する決定部と、
を備える
保守装置。 - 前記決定部は、前記試験結果の変動を正常状態における変動と比較して差分を算出し、前記差分に基づいて、前記保守タイミングを決定する、請求項1に記載の保守装置。
- 前記正常状態における変動は、正常状態における前記複数の治具についての試験結果の変動の平均である、請求項2に記載の保守装置。
- 前記決定部は、前記差分が予め定められたしきい値を超えた場合に、前記治具を保守すると決定する、請求項2または3に記載の保守装置。
- 前記予め定められたしきい値は、機械学習により決定されたものである、請求項4に記載の保守装置。
- 前記決定部は、機械学習により前記差分を算出する、請求項2から5のいずれか一項に記載の保守装置。
- 前記差分は、マハラノビス距離である、請求項6に記載の保守装置。
- 正常状態において取得された複数の試験結果を用いて、前記マハラノビス距離を算出するために用いられる共分散行列を学習する学習部を更に備える、請求項7に記載の保守装置。
- 前記試験結果の変動に基づいて、正常状態における変動に対するずれを検出するモデルを機械学習により生成するモデル生成部を更に備え、
前記決定部は、前記モデルの出力に基づいて前記差分を算出する、請求項6に記載の保守装置。 - 前記算出部は、予め定められた期間における前記複数の試験結果を、前記期間の始点を順次変更しながら分析して、前記試験結果の変動を算出する、請求項1から9のいずれか一項に記載の保守装置。
- 前記算出部は、前記複数の試験結果におけるフェイル率の変動を算出する、請求項1から10のいずれか一項に記載の保守装置。
- 前記フェイル率は、複数の試験項目における少なくとも1つの項目がフェイルしたことを示すトータルフェイル率である、請求項11に記載の保守装置。
- 前記フェイル率は、複数の試験項目における特定の項目がフェイルしたことを示す部分的なフェイル率である、請求項11に記載の保守装置。
- 前記決定部は、前記保守タイミングとして、前記治具のクリーニング時期を決定する、請求項1から13のいずれか一項に記載の保守装置。
- 前記決定部は、更に、前記治具のクリーニング内容を決定する、請求項14に記載の保守装置。
- 前記決定部は、複数の試験項目における項目ごとの前記試験結果の変動に基づいて、前記治具のクリーニング内容を決定する、請求項15に記載の保守装置。
- 複数の治具を介してそれぞれ異なる複数の被測定デバイスを順次試験した場合における複数の試験結果を、治具ごとに取得することと、
前記複数の試験結果を用いて、試験結果の変動を前記治具ごとに算出することと、
前記試験結果の変動に基づいて、前記治具の保守タイミングを決定することと、
を備える
保守方法。 - コンピュータにより実行されて、前記コンピュータを、
複数の治具を介してそれぞれ異なる複数の被測定デバイスを順次試験した場合における複数の試験結果を、治具ごとに取得する取得部と、
前記複数の試験結果を用いて、試験結果の変動を前記治具ごとに算出する算出部と、
前記試験結果の変動に基づいて、前記治具の保守タイミングを決定する決定部と、
して機能させる保守プログラム。
Priority Applications (5)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202080068241.3A CN114502968A (zh) | 2019-09-30 | 2020-09-28 | 维护装置、维护方法及维护程序 |
JP2021551274A JP7245924B2 (ja) | 2019-09-30 | 2020-09-28 | 保守装置、保守方法、および、保守プログラム |
DE112020004662.1T DE112020004662T5 (de) | 2019-09-30 | 2020-09-28 | Wartungsgerät, Wartungsverfahren und Wartungsprogramm |
KR1020227014360A KR20220074918A (ko) | 2019-09-30 | 2020-09-28 | 보수 장치, 보수 방법 및 보수 프로그램 |
US17/686,443 US12014335B2 (en) | 2019-09-30 | 2022-03-04 | Maintenance apparatus, maintenance method, and recording medium having recorded thereon maintenance program |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2019-178444 | 2019-09-30 | ||
JP2019178444 | 2019-09-30 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/686,443 Continuation US12014335B2 (en) | 2019-09-30 | 2022-03-04 | Maintenance apparatus, maintenance method, and recording medium having recorded thereon maintenance program |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021065843A1 true WO2021065843A1 (ja) | 2021-04-08 |
Family
ID=75338039
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2020/023294 WO2021065086A1 (ja) | 2019-09-30 | 2020-06-12 | 保守装置、保守方法、および、保守プログラム |
PCT/JP2020/036748 WO2021065843A1 (ja) | 2019-09-30 | 2020-09-28 | 保守装置、保守方法、および、保守プログラム |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2020/023294 WO2021065086A1 (ja) | 2019-09-30 | 2020-06-12 | 保守装置、保守方法、および、保守プログラム |
Country Status (7)
Country | Link |
---|---|
US (1) | US12014335B2 (ja) |
JP (1) | JP7245924B2 (ja) |
KR (1) | KR20220074918A (ja) |
CN (1) | CN114502968A (ja) |
DE (1) | DE112020004662T5 (ja) |
TW (2) | TW202115413A (ja) |
WO (2) | WO2021065086A1 (ja) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001326258A (ja) * | 2000-05-17 | 2001-11-22 | Tokyo Seimitsu Co Ltd | プローブカードの触針のクリーニング方法 |
JP2003098226A (ja) * | 2001-09-25 | 2003-04-03 | Fuji Xerox Co Ltd | プリント基板故障判定方法 |
JP2003282654A (ja) * | 2002-03-20 | 2003-10-03 | Hitachi Ltd | 半導体装置の製造方法 |
JP2005175154A (ja) * | 2003-12-10 | 2005-06-30 | Matsushita Electric Ind Co Ltd | プローブカードの針先クリーニング方法,半導体装置のウエハ検査装置,データ記録媒体 |
JP2006105924A (ja) * | 2004-10-08 | 2006-04-20 | Renesas Technology Corp | 接触抵抗特性解析方法 |
WO2007105387A1 (ja) * | 2006-03-10 | 2007-09-20 | Matsushita Electric Industrial Co., Ltd. | 半導体検査システム |
JP2007248200A (ja) * | 2006-03-15 | 2007-09-27 | Nec Electronics Corp | 半導体試験装置の保守システムおよび保守方法 |
US20110148446A1 (en) * | 2009-12-22 | 2011-06-23 | Suto Anthony J | Capacitive opens testing in low signal environments |
JP2011179342A (ja) * | 2010-02-26 | 2011-09-15 | Morita Mfg Co Ltd | エアモータ及び医療用ハンドピース |
JP2011258651A (ja) * | 2010-06-07 | 2011-12-22 | Mitsubishi Electric Corp | 試験装置、試験方法、そのコンピュータ・プログラムおよびそのプログラムを記録した記録媒体 |
US20130300429A1 (en) * | 2012-05-09 | 2013-11-14 | Schneider Electric USA, Inc. | Diagnostic Receptacle For Electric Vehicle Supply Equipment |
WO2018139144A1 (ja) * | 2017-01-25 | 2018-08-02 | Ntn株式会社 | 状態監視方法および状態監視装置 |
Family Cites Families (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH1054858A (ja) * | 1996-08-09 | 1998-02-24 | Sumitomo Wiring Syst Ltd | 検査装置及び検査方法 |
JP3349455B2 (ja) | 1998-09-30 | 2002-11-25 | 宮崎沖電気株式会社 | 半導体製造装置のための管理方法および管理システム |
JP4326641B2 (ja) * | 1999-11-05 | 2009-09-09 | 富士機械製造株式会社 | 装着装置,装着精度検出治具セットおよび装着精度検出方法 |
JP2002174674A (ja) * | 2000-12-05 | 2002-06-21 | Advantest Corp | 半導体試験装置及びその予防保守方法 |
US6594599B1 (en) * | 2001-05-09 | 2003-07-15 | Alcatel | System, work station and method for testing a product and generating a statistical model that predicts the processibility of making like products |
US7129733B2 (en) * | 2003-12-02 | 2006-10-31 | Intel Corporation | Dynamic overdrive compensation test system and method |
CN100549705C (zh) * | 2004-05-25 | 2009-10-14 | 株式会社村田制作所 | 测量误差校正方法和电子部件特性测量装置 |
US7511508B2 (en) * | 2004-06-28 | 2009-03-31 | Advantest Corporation | Fixture characteristic measuring device, method, program, recording medium, network analyzer, and semiconductor test device |
KR100982343B1 (ko) * | 2007-06-11 | 2010-09-15 | 주식회사 쎄믹스 | 웨이퍼 프로버의 스테이지 오차 측정 및 보정 장치 |
JP5004027B2 (ja) * | 2008-04-22 | 2012-08-22 | 富士電機株式会社 | インプリント方法およびその装置 |
JP4802259B2 (ja) * | 2009-03-23 | 2011-10-26 | 株式会社東芝 | テスト装置、テスト方法および補正電圧算出装置 |
JP5691193B2 (ja) * | 2010-02-26 | 2015-04-01 | 富士通セミコンダクター株式会社 | コンタクタ、半導体装置の試験装置、及び半導体装置の製造方法 |
US8838408B2 (en) * | 2010-11-11 | 2014-09-16 | Optimal Plus Ltd | Misalignment indication decision system and method |
DE102013211038B3 (de) | 2013-06-13 | 2014-10-16 | Siemens Aktiengesellschaft | Bereitstellen einer Information über einen Alterungszustand eines Halbleiterbauelements |
JP6026362B2 (ja) * | 2013-07-09 | 2016-11-16 | 東京エレクトロン株式会社 | 基板処理システム、基板処理システムの制御方法、及び記憶媒体 |
JP6252106B2 (ja) * | 2013-10-31 | 2017-12-27 | 日本電産リード株式会社 | 接触子のメンテナンス方法及び検査装置 |
US10357863B2 (en) * | 2016-04-19 | 2019-07-23 | Okuma Corporation | Error identification method of machine tool and error identification system of the same |
JP6981113B2 (ja) * | 2017-09-05 | 2021-12-15 | オムロン株式会社 | 情報処理装置および情報処理方法 |
JP2020012685A (ja) * | 2018-07-13 | 2020-01-23 | 日本電産リード株式会社 | プローブ、検査治具、及び検査装置 |
-
2020
- 2020-06-04 TW TW109118760A patent/TW202115413A/zh unknown
- 2020-06-12 WO PCT/JP2020/023294 patent/WO2021065086A1/ja active Application Filing
- 2020-09-28 JP JP2021551274A patent/JP7245924B2/ja active Active
- 2020-09-28 KR KR1020227014360A patent/KR20220074918A/ko unknown
- 2020-09-28 TW TW109133635A patent/TW202115414A/zh unknown
- 2020-09-28 CN CN202080068241.3A patent/CN114502968A/zh active Pending
- 2020-09-28 DE DE112020004662.1T patent/DE112020004662T5/de active Pending
- 2020-09-28 WO PCT/JP2020/036748 patent/WO2021065843A1/ja active Application Filing
-
2022
- 2022-03-04 US US17/686,443 patent/US12014335B2/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2001326258A (ja) * | 2000-05-17 | 2001-11-22 | Tokyo Seimitsu Co Ltd | プローブカードの触針のクリーニング方法 |
JP2003098226A (ja) * | 2001-09-25 | 2003-04-03 | Fuji Xerox Co Ltd | プリント基板故障判定方法 |
JP2003282654A (ja) * | 2002-03-20 | 2003-10-03 | Hitachi Ltd | 半導体装置の製造方法 |
JP2005175154A (ja) * | 2003-12-10 | 2005-06-30 | Matsushita Electric Ind Co Ltd | プローブカードの針先クリーニング方法,半導体装置のウエハ検査装置,データ記録媒体 |
JP2006105924A (ja) * | 2004-10-08 | 2006-04-20 | Renesas Technology Corp | 接触抵抗特性解析方法 |
WO2007105387A1 (ja) * | 2006-03-10 | 2007-09-20 | Matsushita Electric Industrial Co., Ltd. | 半導体検査システム |
JP2007248200A (ja) * | 2006-03-15 | 2007-09-27 | Nec Electronics Corp | 半導体試験装置の保守システムおよび保守方法 |
US20110148446A1 (en) * | 2009-12-22 | 2011-06-23 | Suto Anthony J | Capacitive opens testing in low signal environments |
JP2011179342A (ja) * | 2010-02-26 | 2011-09-15 | Morita Mfg Co Ltd | エアモータ及び医療用ハンドピース |
JP2011258651A (ja) * | 2010-06-07 | 2011-12-22 | Mitsubishi Electric Corp | 試験装置、試験方法、そのコンピュータ・プログラムおよびそのプログラムを記録した記録媒体 |
US20130300429A1 (en) * | 2012-05-09 | 2013-11-14 | Schneider Electric USA, Inc. | Diagnostic Receptacle For Electric Vehicle Supply Equipment |
WO2018139144A1 (ja) * | 2017-01-25 | 2018-08-02 | Ntn株式会社 | 状態監視方法および状態監視装置 |
Also Published As
Publication number | Publication date |
---|---|
JPWO2021065843A1 (ja) | 2021-04-08 |
US20220188776A1 (en) | 2022-06-16 |
JP7245924B2 (ja) | 2023-03-24 |
WO2021065086A1 (ja) | 2021-04-08 |
CN114502968A (zh) | 2022-05-13 |
KR20220074918A (ko) | 2022-06-03 |
US12014335B2 (en) | 2024-06-18 |
DE112020004662T5 (de) | 2022-06-15 |
TW202115414A (zh) | 2021-04-16 |
TW202115413A (zh) | 2021-04-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20170153958A1 (en) | Detecting degraded core performance in multicore processors | |
CN108292380B (zh) | 要因分析装置、要因分析方法以及记录介质 | |
EP3767399A1 (en) | Control device, control system, control method, and control program | |
WO2021065843A1 (ja) | 保守装置、保守方法、および、保守プログラム | |
JP7406017B2 (ja) | 解析装置、解析方法および解析プログラム | |
WO2021181863A1 (ja) | 判定装置、試験システム、判定方法および判定プログラム | |
CN107943642B (zh) | 一种电容式触摸感应装置的性能测试方法 | |
KR102581229B1 (ko) | 해석 장치, 해석 방법 및 해석 프로그램 | |
JP7181753B2 (ja) | 解析装置、解析方法および解析プログラム | |
JP7439467B2 (ja) | 情報処理装置、情報処理システム、モデルの学習方法 | |
JP7423898B2 (ja) | 情報処理装置、判定装置、モデルの学習方法 | |
US20220082511A1 (en) | Wafer defect tracing method and apparatus, electronic device and computer readable medium | |
JP2009134518A (ja) | 試験プログラムの検証方法及びその検証システム | |
CN115135358A (zh) | 使用机器学习的自动传感器追踪验证 | |
JP2019090626A (ja) | 基板自動解析システム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20871335 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2021551274 Country of ref document: JP Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 20227014360 Country of ref document: KR Kind code of ref document: A |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 20871335 Country of ref document: EP Kind code of ref document: A1 |