WO2022255030A1 - プローバ制御装置、プローバ制御方法、及びプローバ - Google Patents
プローバ制御装置、プローバ制御方法、及びプローバ Download PDFInfo
- Publication number
- WO2022255030A1 WO2022255030A1 PCT/JP2022/019630 JP2022019630W WO2022255030A1 WO 2022255030 A1 WO2022255030 A1 WO 2022255030A1 JP 2022019630 W JP2022019630 W JP 2022019630W WO 2022255030 A1 WO2022255030 A1 WO 2022255030A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- input data
- unit
- probe
- prediction
- prober
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 239000000523 sample Substances 0.000 claims abstract description 208
- 239000004065 semiconductor Substances 0.000 claims abstract description 79
- 238000010801 machine learning Methods 0.000 claims abstract description 27
- 230000008569 process Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 abstract description 2
- 238000005259 measurement Methods 0.000 description 23
- 238000009529 body temperature measurement Methods 0.000 description 20
- 238000012360 testing method Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 11
- 230000007246 mechanism Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 8
- 238000006073 displacement reaction Methods 0.000 description 7
- 238000004140 cleaning Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 230000000052 comparative effect Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003028 elevating effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R1/00—Details of instruments or arrangements of the types included in groups G01R5/00 - G01R13/00 and G01R31/00
- G01R1/02—General constructional details
- G01R1/06—Measuring leads; Measuring probes
- G01R1/067—Measuring probes
- G01R1/073—Multiple probes
- G01R1/07307—Multiple probes with individual probe elements, e.g. needles, cantilever beams or bump contacts, fixed in relation to each other, e.g. bed of nails fixture or probe card
-
- 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
- G01R31/2891—Features relating to contacting the IC under test, e.g. probe heads; chucks related to sensing or controlling of force, position, temperature
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R1/00—Details of instruments or arrangements of the types included in groups G01R5/00 - G01R13/00 and G01R31/00
- G01R1/02—General constructional details
- G01R1/06—Measuring leads; Measuring probes
- G01R1/067—Measuring probes
- G01R1/06711—Probe needles; Cantilever beams; "Bump" contacts; Replaceable probe pins
- G01R1/06733—Geometry aspects
- G01R1/0675—Needle-like
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R1/00—Details of instruments or arrangements of the types included in groups G01R5/00 - G01R13/00 and G01R31/00
- G01R1/02—General constructional details
- G01R1/06—Measuring leads; Measuring probes
- G01R1/067—Measuring probes
- G01R1/073—Multiple probes
- G01R1/07307—Multiple probes with individual probe elements, e.g. needles, cantilever beams or bump contacts, fixed in relation to each other, e.g. bed of nails fixture or probe card
- G01R1/07314—Multiple probes with individual probe elements, e.g. needles, cantilever beams or bump contacts, fixed in relation to each other, e.g. bed of nails fixture or probe card the body of the probe being perpendicular to test object, e.g. bed of nails or probe with bump contacts on a rigid support
-
- 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
- G01R31/28—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]
- G01R31/2886—Features relating to contacting the IC under test, e.g. probe heads; chucks
- G01R31/2887—Features relating to contacting the IC under test, e.g. probe heads; chucks involving moving the probe head or the IC under test; docking stations
-
- 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
- G01R31/2889—Interfaces, e.g. between probe and tester
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L21/00—Processes or apparatus adapted for the manufacture or treatment of semiconductor or solid state devices or of parts thereof
- H01L21/67—Apparatus specially adapted for handling semiconductor or electric solid state devices during manufacture or treatment thereof; Apparatus specially adapted for handling wafers during manufacture or treatment of semiconductor or electric solid state devices or components ; Apparatus not specifically provided for elsewhere
- H01L21/67005—Apparatus not specifically provided for elsewhere
- H01L21/67242—Apparatus for monitoring, sorting or marking
- H01L21/67248—Temperature monitoring
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L21/00—Processes or apparatus adapted for the manufacture or treatment of semiconductor or solid state devices or of parts thereof
- H01L21/67—Apparatus specially adapted for handling semiconductor or electric solid state devices during manufacture or treatment thereof; Apparatus specially adapted for handling wafers during manufacture or treatment of semiconductor or electric solid state devices or components ; Apparatus not specifically provided for elsewhere
- H01L21/683—Apparatus specially adapted for handling semiconductor or electric solid state devices during manufacture or treatment thereof; Apparatus specially adapted for handling wafers during manufacture or treatment of semiconductor or electric solid state devices or components ; Apparatus not specifically provided for elsewhere for supporting or gripping
- H01L21/687—Apparatus specially adapted for handling semiconductor or electric solid state devices during manufacture or treatment thereof; Apparatus specially adapted for handling wafers during manufacture or treatment of semiconductor or electric solid state devices or components ; Apparatus not specifically provided for elsewhere for supporting or gripping using mechanical means, e.g. chucks, clamps or pinches
- H01L21/68707—Apparatus specially adapted for handling semiconductor or electric solid state devices during manufacture or treatment thereof; Apparatus specially adapted for handling wafers during manufacture or treatment of semiconductor or electric solid state devices or components ; Apparatus not specifically provided for elsewhere for supporting or gripping using mechanical means, e.g. chucks, clamps or pinches the wafers being placed on a robot blade, or gripped by a gripper for conveyance
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01L—SEMICONDUCTOR DEVICES NOT COVERED BY CLASS H10
- H01L22/00—Testing or measuring during manufacture or treatment; Reliability measurements, i.e. testing of parts without further processing to modify the parts as such; Structural arrangements therefor
Definitions
- the present invention relates to a prober control device, a prober control method, and a prober for a prober used to inspect electrical characteristics of semiconductor chips formed on a wafer.
- a plurality of semiconductor chips having the same electrical element circuit are formed on the surface of the wafer.
- Each semiconductor chip is inspected for electrical characteristics by a wafer test system before being individually cut by a dicer.
- This wafer test system includes a prober and a tester (see Patent Documents 1 to 4).
- the prober With the wafer held on the wafer chuck, the prober causes the probe needles to electrically contact the electrode pads of the semiconductor chip by relatively moving the probe card having the probe needles and the wafer chuck.
- the tester supplies various test signals to the semiconductor chip through terminals connected to probe needles, and receives and analyzes the signals output from the semiconductor chip to determine whether the semiconductor chip operates normally. Testing.
- the wafer chuck of the prober is provided with a temperature control unit such as a heater mechanism, a chiller mechanism, or a heat pump mechanism, and the wafer held on the wafer chuck is heated or cooled by the temperature control unit. .
- a temperature control unit such as a heater mechanism, a chiller mechanism, or a heat pump mechanism
- each part of the prober other than the wafer chuck gradually changes so as to approach the temperature of the wafer chuck. Therefore, each part deforms due to thermal expansion due to heating or contraction due to cooling, and the relative position between the probe needle and the semiconductor chip changes along with this deformation. As a result, when the probe needle and the wafer are moved relative to each other in order to inspect the semiconductor chip, a probing error may occur in which the probe needle does not properly contact the semiconductor chip.
- Patent Document 1 a temperature sensor is attached to a probe card having probe needles, and based on the measurement result of this temperature sensor, a prober corrects the height position of the wafer chuck when the probe needles and the semiconductor chip are brought into contact. is disclosed.
- the prober described in Patent Document 1 the relationship between the temperature of the probe card and the amount of displacement in the height direction of the probe needle is obtained in advance, so that the amount of correction of the height position of the wafer chuck is calculated based on the measurement result of the temperature sensor. can be asked for.
- Patent Document 2 discloses a prober in which temperature sensors are provided on a probe card and an X-direction moving stage, and the probe needles are brought into contact with a semiconductor chip while the temperature of a predetermined portion of the prober is stable based on the measurement results of the temperature sensors. It is According to the prober described in Patent Document 2, the preheating time for preheating the wafer, the probe card, and the like can be shortened.
- Patent Document 3 temperature sensors are attached to a wafer chuck, a card holder that holds a probe card, and a head stage that holds the card holder, respectively.
- a prober for correcting for is disclosed.
- the prober disclosed in Patent Document 3 the relationship between each temperature of the wafer chuck and card holder and the position of the probe needle is obtained in advance, thereby generating a predictive model showing the positional change of the probe needle accompanying each temperature change.
- the prober of Patent Document 3 can correct the contact position between the probe needle and the semiconductor chip by referring to the prediction model based on the temperature measurement result of each temperature sensor.
- Patent Document 4 the temperature of both the probe card and the card holder is measured, and based on the temperature measurement results of both, the relationship between the temperature of both and the position of the tip of the probe needle displaced by thermal deformation of both is predicted.
- a prober is disclosed that predicts the tip position of a probe needle with reference to a model. According to the prober described in Patent Document 4, the probe needle can be efficiently and stably brought into contact with the semiconductor chip.
- the drift of the temperature sensor may occur over a long period of time, or the temperature may fluctuate in places where the temperature is not measured inside the prober. If there is a displacement of the tip position of the probe needle, there is a possibility that the predicted value and the actually measured value of the tip position of the probe needle will deviate from each other.
- the present invention has been made in view of such circumstances, and an object thereof is to provide a prober control device, a prober control method, and a prober capable of more accurately predicting the tip position of the probe needle.
- a prober control device for achieving the object of the present invention comprises a wafer chuck holding a wafer on which a plurality of semiconductor chips are formed, a probe card having probe needles, and a probe card holding the outer circumference of the probe card.
- an input data acquisition unit that acquires input data including temperature data of at least one of the card holder, and prediction that the input data is input and the tip position of the probe needle is output based on the input data acquired by the input data acquisition unit
- a prediction unit that predicts the tip position of the probe needle using a model, input data that was used as teacher data for machine learning of the prediction model before the prediction by the prediction unit, and input data that was acquired by the input data acquisition unit. and a decision unit that decides whether or not to execute the prediction by the prediction unit based on.
- this prober control device before the prediction by the prediction unit, it is possible to determine whether or not the prediction model used for this prediction can accurately predict the tip position of the probe needle based on the current input data. can.
- the determination unit calculates a difference between the input data acquired by the input data acquisition unit and the input data used as the teacher data for each parameter of the input data. , calculating the square root of the sum of squares of the differences for each parameter, and based on whether at least one of the square roots of the sum of squares of the differences for each parameter is within a predetermined range, the prediction unit and a process of determining whether or not prediction can be executed.
- a needle position acquisition unit that acquires the tip position of the probe needle when the determination unit determines no, and the input data and the needle position acquired by the input data acquisition unit.
- a re-learning unit for re-learning the prediction model using teacher data including the tip position of the probe needle acquired by the unit, and the needle position acquisition unit and the re-learning unit until the decision unit determines that it is possible.
- the input data acquisition unit and the determination unit operate repeatedly. This makes it possible to accurately predict the tip position of the probe needle.
- the re-learning section excludes the oldest input data and the tip position of the probe needle corresponding to the input data from the teacher data, and then, the predictive model is generated based on the teacher data. perform re-learning. As a result, the influence of the drift of the input data acquisition section (temperature sensor) can be reduced.
- the prediction unit predicts the tip position of the probe needle, and relative movement is performed based on the tip position of the probe needle predicted by the prediction unit.
- a movement control unit that controls the unit to bring the probe needle into contact with the semiconductor chip.
- the input data acquisition unit includes the temperature data, the chip size of the semiconductor chip, the position of the wafer, and the first data used to detect the semiconductor chip as the input data.
- Alignment data including at least one of the positional relationship between the camera and the second camera used for detecting the probe needle is acquired.
- a prober for achieving the object of the present invention comprises a wafer chuck that holds a wafer on which a plurality of semiconductor chips are formed, a probe card that has probe needles, and a probe card that holds the outer periphery of the probe card and attaches the probe card to the wafer. It comprises a card holder to face each other, a relative movement section for relatively moving the wafer chuck with respect to the probe needles, and the prober control device described above.
- a prober control method for achieving the object of the present invention includes a wafer chuck that holds a wafer on which a plurality of semiconductor chips are formed, a probe card that has probe needles, and a probe card that holds the outer circumference of the probe card.
- a probe card comprising: a probe card comprising: a card holder facing a wafer; and an input data acquisition step of acquiring input data including temperature data of at least one of the card holder, and prediction that the input data is input and the tip position of the probe needle is output based on the input data acquired in the input data acquisition step Prediction step of predicting the tip position of the probe needle using the model, input data used as teacher data for machine learning of the prediction model before the prediction step, and input data obtained in the input data acquisition step and a decision step of deciding whether or not to execute the prediction step based on the prediction step.
- the present invention can more accurately predict the tip position of the probe needle.
- FIG. 1 is a schematic diagram of a prober used in a wafer test system for testing electrical characteristics of a plurality of semiconductor chips formed on a wafer;
- FIG. 3 is an external perspective view of a prober;
- FIG. 4 is a top view of a wafer held on a wafer chuck;
- FIG. 4 is an explanatory diagram showing an example of temperature measurement points of a card holder and a probe card by temperature sensors;
- 3 is a functional block diagram showing functions of a control unit of the prober;
- 4 is an explanatory diagram showing an example of teacher data used for machine learning of a prediction model by a prediction model generation unit; 4 is a flow chart showing the flow of a method for bringing a probe needle into contact with a semiconductor chip by a prober; Graph (see symbol VIIIA) showing the predicted value and the actual measurement of the tip position of the probe needle, and the predicted value and the actual measurement of the tip position of the probe needle, in a comparative example in which the determination by the determination unit and re-learning of the prediction model are not performed. 8B is a graph (see symbol VIIIB) showing a difference value from a value. In this embodiment, a graph showing the predicted value and the measured value of the tip position of the probe needle (see symbol IXA) and a graph showing the difference value between the predicted value and the measured value of the tip position of the probe needle (see symbol IXB ).
- FIG. 1 is a schematic diagram of a prober 10 used in a wafer test system for testing electrical characteristics of a plurality of semiconductor chips 9 (see FIG. 3) formed on a wafer W.
- FIG. 2 is an external perspective view of the prober 10.
- the prober 10 includes a base 12, a Y stage 13, a Y moving section 14, an X stage 15, an X moving section 16, a Z ⁇ stage 17, and a Z ⁇ moving section 18. , wafer chuck 20, column 23 (see FIG. 2), head stage 24 (see FIG. 2), card holder 25, probe card 26, wafer alignment camera 29, upper/lower stage 30, needle alignment A camera 31, a cleaning plate 32, and a temperature sensor 34 are provided.
- the external configuration of the prober 10 is not limited to the examples shown in FIGS. 1 and 2, and can be changed as appropriate.
- a Y-stage 13 is supported on the upper surface of the base 12 so as to be movable in the Y-axis direction via a Y-moving section 14 .
- the Y movement unit 14 includes, for example, a guide rail provided on the upper surface of the base 12 and parallel to the Y axis, a slider provided on the lower surface of the Y stage 13 and engaged with the guide rail, and moving the Y stage 13 in the Y axis direction. and an actuator, such as a motor, for moving the The Y moving unit 14 moves the Y stage 13 on the base 12 in the Y-axis direction.
- An X-stage 15 is supported on the upper surface of the Y-stage 13 so as to be movable in the X-axis direction via an X-moving section 16 .
- the X moving unit 16 includes, for example, a guide rail provided on the upper surface of the Y stage 13 and parallel to the X axis, a slider provided on the lower surface of the X stage 15 and engaged with the guide rail, and moving the X stage 15 along the X axis. and an actuator, such as a motor, for moving in a direction. This X moving unit 16 moves the X stage 15 on the Y stage 13 in the X axis direction.
- a Z ⁇ stage 17 and a vertical stage 30 are provided on the upper surface of the X stage 15 .
- a Z ⁇ moving unit 18 is provided on the Z ⁇ stage 17 .
- a wafer chuck 20 is held on the upper surface of the Z ⁇ stage 17 via a Z ⁇ moving unit 18 .
- the Z ⁇ moving unit 18 has, for example, an elevating mechanism that moves the Z ⁇ stage 17 in the Z-axis direction (vertical direction) and a rotation mechanism that rotates the Z ⁇ stage 17 around the Z-axis. Therefore, the Z ⁇ moving unit 18 moves the wafer chuck 20 held on the upper surface of the Z ⁇ stage 17 in the Z-axis direction and rotates it around the Z-axis.
- a wafer W is held on the upper surface of the wafer chuck 20 by various holding methods such as vacuum suction. Further, the wafer chuck 20 is provided with a temperature adjustment section 20a for adjusting the temperature of the wafer W. As shown in FIG. A known mechanism such as a heater mechanism, a chiller mechanism, or a heat pump mechanism is used as the temperature adjustment unit 20a. The temperature adjuster 20 a adjusts the temperature of the wafer W held by the wafer chuck 20 .
- the wafer chuck 20 is movably supported in the XYZ axis directions via the Y stage 13, the Y moving section 14, the X stage 15, the X moving section 16, the Z ⁇ stage 17, and the Z ⁇ moving section 18. Both are rotatably supported around the Z axis. As a result, the wafer W held by the wafer chuck 20 and the probe needles 35, which will be described later, can be moved relative to each other. That is, the Y stage 13 and Y moving section 14, the X stage 15 and X moving section 16, and the Z ⁇ stage 17 and Z ⁇ moving section 18 function as relative moving sections of the present invention.
- FIG. 3 is a top view of the wafer W held by the wafer chuck 20.
- the wafer W has a plurality of semiconductor chips 9 formed thereon.
- Each semiconductor chip 9 is formed with a plurality of electrode pads 9a.
- the column 23 is provided on the upper surface of the base 12, above the Y stage 13, the X stage 15, and the Z ⁇ stage 17 (hereinafter simply referred to as stages 13, 15, and 17). In position, it supports the headstage 24 . As a result, the head stage 24 is fixed on the base 12 via the struts 23 .
- a card holder 25 is held in the center of the head stage 24 .
- a holding hole 25a for holding the outer periphery of the probe card 26 is formed in the card holder 25, and the probe card 26 is held in this holding hole 25a. As a result, the probe card 26 is held at a position facing the wafer W via the head stage 24 and card holder 25 .
- the probe card 26 has probe needles 35 arranged according to the arrangement of the electrode pads 9a of the semiconductor chip 9 to be inspected. These card holder 25 and probe card 26 are replaced according to the type of semiconductor chip 9 .
- the probe card 26 is provided with connection terminals (not shown) electrically connected to the probe needles 35, and a tester (not shown) is connected to these connection terminals.
- the tester supplies various test signals to the electrode pads 9a of the semiconductor chip 9 via the connection terminals of the probe card 26 and the probe needles 35, and receives and analyzes the signals output from the electrode pads 9a to test the semiconductor. Test whether the chip 9 works normally. Since the configuration of the tester and the test method are well-known technologies, detailed description thereof will be omitted.
- the wafer alignment camera 29 corresponds to the first camera of the present invention, and photographs the semiconductor chip 9 on the wafer W held by the wafer chuck 20 . Based on the captured image captured by the wafer alignment camera 29, the positions of the electrode pads 9a of the semiconductor chip 9 to be inspected can be detected.
- the installation position and structure of the wafer alignment camera 29 are not particularly limited, in the present embodiment, as disclosed in Japanese Patent Application Laid-Open No. 2003-303865, the wafer alignment camera 29 and the needle alignment camera 31, which will be described later. An installation position and structure (spot light irradiation optical system) capable of measuring the relative distance are adopted.
- a needle positioning camera 31 and a cleaning plate 32 are provided on the upper and lower stages 30 at positions substantially facing the head stage 24 and the like.
- the vertical stage 30 also has an elevation mechanism (not shown) that is movable in the Z-axis direction, so that the positions of the needle positioning camera 31 and the cleaning plate 32 in the Z-axis direction can be adjusted.
- the needle positioning camera 31 and the cleaning plate 32 are movably supported in the XYZ axis directions via the Y stage 13 and Y moving section 14, the X stage 15 and X moving section 16, and the vertical stage 30. It is Thereby, the needle positioning camera 31, the cleaning plate 32, and the probe needle 35 can be moved relative to each other.
- the needle positioning camera 31 corresponds to the second camera of the present invention, and photographs the probe needles 35 of the probe card 26 . Based on the captured image of the probe needle 35 captured by the needle positioning camera 31, the position of the probe needle 35 can be detected. Specifically, the XY coordinates of the tip position of the probe needle 35 are detected from the position coordinates of the needle positioning camera 31 , and the Z coordinate of the tip position of the probe needle 35 is detected from the focus position of the needle positioning camera 31 .
- each stage 13, 15, 17 is driven each time the probe card 26 is replaced or each time a predetermined number of semiconductor chips 9 are inspected.
- the probe needle 35 is photographed by the needle positioning camera 31. Based on the image captured by the needle positioning camera 31, the tip position of the probe needle 35 is detected as described above.
- the stages 13, 15, and 17 are driven to relatively move the wafer alignment camera 29 to the photographing position of the wafer W, and then the wafer alignment is performed.
- the semiconductor chip 9 on the wafer W is photographed by the camera 29 . Based on the photographed image of the wafer alignment camera 29, the positions of the electrode pads 9a of the semiconductor chip 9 to be inspected are detected.
- the stages 13, 15 and 17 are driven to electrically contact the probe needles 35 with the electrode pads 9a of the semiconductor chip 9 to be tested first.
- the semiconductor chip 9 to be tested first is tested by a tester (not shown). Thereafter, the remaining semiconductor chips 9 to be inspected are similarly inspected.
- a specific method for inspecting the semiconductor chip 9 is a well-known technique, so a detailed description is omitted here (see, for example, Patent Document 4).
- the temperature sensors 34 are provided at positions facing the lower surfaces of the card holder 25 and the probe card 26, for example, the side surfaces of the Z ⁇ stage 17 and the upper and lower stages 30, respectively. Therefore, each temperature sensor 34 is held by each stage 13, 15, 17, 30 so as to be relatively movable with respect to the card holder 25 and the probe card 26.
- FIG. 1 A block diagram illustrating an exemplary computing environment in accordance with the present disclosure.
- the temperature sensor 34 is, for example, a non-contact temperature sensor using a radiant energy detection method, and measures the temperature of the card holder 25 and the probe card 26 without contact.
- the card holder 25 and the probe card 26 are thermally deformed under the influence of the temperature of the wafer chuck 20, and the position of the tip of the probe needle 35 is displaced with this thermal deformation. Therefore, by measuring the temperatures of the card holder 25 and the probe card 26 with the temperature sensor 34, the tip position [displacement (displacement direction, displacement amount)] of the probe needle 35 can be predicted (see Patent Document 4 above). .
- FIG. 4 is an explanatory diagram showing an example of temperature measurement points of the card holder 25 and the probe card 26 by the temperature sensor 34.
- FIG. 4 illustration of the probe needle 35 is omitted.
- the temperature sensor 34 has a plurality of temperature measurement points P1 to P5 inside the probe card 26 and a Temperatures are measured at a plurality of locations including a plurality of temperature measurement points P6 to P13. Note that the temperature measurement points P1 to P13 in FIG. 4 are examples, and their positions and numbers may be changed as appropriate.
- the temperature sensor 34 measures the temperature of each of the temperature measurement points P1 to P13 under the control of the control section 40 (see FIG. 5), which will be described later, and outputs temperature data, which is the result of the temperature measurement, to the control section 40. It should be noted that when measuring temperatures at the respective temperature measuring points P1 to P13, the temperature sensor 34 is placed at a position where the temperatures at the respective temperature measuring points P1 to P13 can be measured. The stages 13 , 15 , 17 and 30 are driven, that is, the temperature sensor 34 is moved relative to the card holder 25 and probe card 26 . This enables fixed-point measurement of the temperature at each of the temperature measurement points P1 to P13.
- FIG. 5 is a functional block diagram showing functions of the controller 40 of the prober 10. As shown in FIG. 5 shows only the function related to the contact control between the probe needle 35 and the wafer W (the electrode pad 9a of the semiconductor chip 9) among the functions of the control unit 40, and the other functions are known techniques. Therefore, illustration is omitted.
- control section 40 corresponds to the prober control device of the present invention, and controls each section of the prober 10 in an integrated manner.
- the control unit 40 may be built in the main body of the prober 10, or may be provided separately from the main body.
- the control unit 40 is composed of an arithmetic device such as a personal computer, for example, and includes an arithmetic circuit composed of various processors, memories, and the like.
- processors include CPU (Central Processing Unit), GPU (Graphics Processing Unit), ASIC (Application Specific Integrated Circuit), and programmable logic devices [e.g. SPLD (Simple Programmable Logic Devices), CPLD (Complex Programmable Logic Device), and FPGA (Field Programmable Gate Arrays)].
- Various functions of the control unit 40 may be realized by one processor, or may be realized by a plurality of processors of the same type or different types.
- control unit 40 is connected to the above-described wafer alignment camera 29, needle alignment camera 31, temperature sensor 34, etc. via various communication interfaces (not shown), as well as alignment data measurement.
- a unit 38 and a storage unit 39 are connected.
- the alignment data measuring unit 38 measures alignment data by controlling the wafer alignment camera 29, the needle alignment camera 31, and the like.
- the alignment data is data used for predicting the tip position (displacement) of the probe needle 35 together with the temperature data described above.
- This alignment data includes, for example, the three-dimensional chip size of the semiconductor chip 9 to be inspected, the three-dimensional position of the wafer W, and the three-dimensional relative distance between the wafer alignment camera 29 and the needle alignment camera 31. (hereinafter abbreviated as camera relative distance).
- the camera relative distance indicates the positional relationship between the wafer alignment camera 29 and the needle alignment camera 31 .
- the alignment data measurement unit 38 measures the chip size (expansion amount) of the semiconductor chip 9 based on the captured image of the wafer W (semiconductor chip 9 ) captured by the wafer alignment camera 29 . Further, the alignment data measuring unit 38 measures the position of the wafer W based on the photographed image of the specific pattern (not shown) of the semiconductor chip 9 photographed by the wafer alignment camera 29 . Further, as disclosed in Japanese Patent Application Laid-Open No. 2003-303865, the alignment data measurement unit 38 includes a wafer alignment camera 29, a needle alignment camera 31, and an optical system (not shown) for irradiating spot light. and to measure the relative camera distance. The alignment data measurement unit 38 then outputs alignment data including the chip size of the semiconductor chip 9 , the position of the wafer W, and the camera relative distance to the control unit 40 .
- the storage unit 39 stores a control program (not shown) for operating the control unit 40, test results of the semiconductor chip 9 by the prober 10, and teacher data 56 (training data) used for machine learning of the prediction model 47 described later. data) is stored.
- control unit 40 executes a control program (not shown) read out from the storage unit 39 to obtain an input data acquisition unit 42, a needle position acquisition unit 44, a prediction unit 46 , a prediction model generation unit 48 , a determination unit 50 , and a movement control unit 52 .
- the input data acquisition unit 42 Before the contact control for bringing the probe needle 35 into contact with the semiconductor chip 9 to be inspected (hereinafter simply referred to as "before contact control"), and before generating and re-learning the prediction model 47 described later, the input data acquisition unit 42: The temperature measurement of each temperature measurement point P1 to P13 by the temperature sensor 34 and the alignment data measurement by the alignment data measurement unit 38 are executed. Thereby, the input data acquisition unit 42 acquires input data including the temperature data of the temperature measurement points P1 to P13 from the temperature sensor 34 and the alignment data from the alignment data measurement unit 38 at each timing described above. do.
- the input data acquisition unit 42 outputs the input data acquired before the contact control to the prediction unit 46 and the determination unit 50 described later, and outputs the input data acquired before the prediction model 47 is generated and before re-learning. Output to the model generation unit 48 .
- the needle position acquisition unit 44 captures images of the probe needles 35 with the needle positioning camera 31 after the replacement of the probe card 26, after inspection of a predetermined number of semiconductor chips 9, and before generation and re-learning of a prediction model 47, which will be described later. is executed to obtain a photographed image of the probe needle 35 from the needle positioning camera 31, and the tip position of the probe needle 35 is obtained based on this photographed image.
- the needle position acquisition unit 44 outputs the tip position of the probe needle 35 acquired before generation of the prediction model 47 and before re-learning to the prediction model generation unit 48 described later, and acquires the tip position after the replacement of the probe card 26 or the like.
- the tip position of the probe needle 35 is output to the movement control section 52 which will be described later.
- the prediction unit 46 predicts the tip position of the probe needle 35 before contact control and when the determination unit 50 (to be described later) determines that the prediction unit 46 can execute prediction. Specifically, the prediction unit 46 refers to a prediction model 47 generated in advance, which will be described later, based on the input data (the temperature data of the temperature measurement points P1 to P13 and the alignment data) acquired by the input data acquisition unit 42. The tip position of the probe needle 35 is predicted, and the prediction result of the tip position is output to the movement control section 52 . The tip position of the probe needle 35 predicted by the prediction model 47 also includes a variation amount (correction amount) from the tip position of the probe needle 35 acquired by the needle position acquisition unit 44 .
- the prediction model 47 is a trained model generated by machine learning (supervised learning) using a multiple regression model (multiple regression formula, multiple regression analysis) by the prediction model generation unit 48, which will be described later.
- the prediction model 47 receives a plurality of input data (temperature data of the temperature measurement points P1 to P13 and alignment data) as explanatory variables, and outputs a predicted value of the tip position of the probe needle 35 as an objective variable.
- the prediction model generation unit 48 generates the prediction model 47 before inspecting the semiconductor chips 9 of the product wafer W.
- the predictive model generation unit 48 generates teacher data 56 (input data, alignment data, and the tip of the probe needle 35) using a product wafer W or the same wafer W for testing (for predictive model creation). position).
- FIG. 6 is an explanatory diagram showing an example of teacher data 56 used for machine learning of the prediction model 47 by the prediction model generation unit 48.
- FIG. 6 illustrates only the alignment data in one of the XYZ directions (the Y direction in this case) and the tip position of the probe needle 35 in one direction.
- the prediction model generation unit 48 controls the temperature sensor 34, the alignment data measurement unit 38, the movement control unit 52 described later, and the like to measure input data (each temperature measurement of temperature at measurement points P1 to P13, measurement of alignment data) are executed for a predetermined time. As a result, temperature data T1-T13 are obtained for each of the temperature measurement points P1-P13. Also, as alignment data, the chip size D1 of the semiconductor chip 9 (amount of change from the start of the lot), the wafer position D2 of the wafer W (amount of change from the start of the lot), and the relative camera distance D3 (the amount of change from the start of the lot). variation) is obtained.
- the predictive model generation unit 48 controls the needle positioning camera 31, the needle position acquisition unit 44, the movement control unit 52 described later, etc. in accordance with the measurement timing of the input data described above, and determines the tip position of the probe needle 35. Let the measurement run. As a result, the tip position Y[ ⁇ ] ( ⁇ is an arbitrary natural number) of the probe needle 35 for each measurement timing of the input data is obtained.
- the prediction model generation unit 48 acquires a plurality of teacher data 56 including input data and the tip position Y[ ⁇ ] of the probe needle 35 corresponding to the input data.
- the minimum number of teacher data 56 required for machine learning of the prediction model 47 may be obtained.
- one wafer W is used to acquire the teacher data 56 .
- the predictive model generation unit 48 generates a weighted model based on a plurality of teacher data 56, that is, the input data (T1 to T13, D1 to D3) as explanatory variables and the tip position Y [ ⁇ ] of the probe needle 35 as an objective variable.
- a prediction model 47 for predicting the tip position of the probe needle 35 is generated from input data by machine learning using a regression model.
- a specific method of generating the predictive model 47 that is, a machine learning algorithm using a multiple regression model is a known technique, so a specific description thereof will be omitted here. Thereby, the prediction unit 46 can predict the current tip position of the probe needle 35 from the current input data.
- the machine learning algorithm for generating the prediction model 47 is not limited to the multiple regression model, and a known machine learning algorithm such as a convolutional neural network (CNN) may be used.
- CNN convolutional neural network
- the predictive model generation unit 48 causes the storage unit 39 to store teacher data 56 (input data only) used for machine learning of the predictive model 47 .
- the teacher data 56 stored in the storage unit 39 is used by the determination unit 50, which will be described later, to determine whether or not the prediction unit 46 can execute prediction.
- the prediction model generation unit 48 operates after the prediction model 47 is generated and when the determination unit 50, which will be described later, determines that the prediction unit 46 should not perform prediction. , the prediction model 47 is re-learned.
- the determination unit 50 operates before contact control (before prediction by the prediction unit 46), and determines current (latest) input data acquired by the input data acquisition unit 42 and teacher data in the storage unit 39. 56 and the input data of 56 to determine whether or not to execute prediction by the prediction unit 46 (simply referred to as prediction enable/disable determination).
- this prediction model 47 has already performed machine learning with the teacher data 56 corresponding to the current input data. It is a learned state that has been completed. Therefore, when the prediction unit 46 predicts the tip position of the probe needle 35 using the prediction model 47 based on the current input data, the tip position of the probe needle 35 can be accurately predicted.
- this prediction model 47 is in an unlearned state in which machine learning has not been performed with the teacher data 56 corresponding to the current input data. Therefore, even if the prediction unit 46 predicts the tip position of the probe needle 35 using the unlearned prediction model 47, the tip position of the probe needle 35 cannot be predicted accurately.
- the determination unit 50 compares the current input data with the input data of the teacher data 56 in the storage unit 39 to determine whether the prediction model 47 has been trained or has not been trained with respect to the current input data. Prediction propriety determination is performed by determining whether or not.
- the determination unit 50 calculates the difference between the current input data and the input data of the teacher data 56 for each input data parameter (temperature data T1 to T13, chip size D1, wafer position D2, camera relative distance D3). do. Next, the determination unit 50 calculates the square root of the sum of squares of the differences for each parameter, and predicts based on whether at least one of the square roots of the sum of squares for each parameter is within a certain range (below the threshold). It is determined whether the model 47 is in the learned state or in the unlearned state.
- the determination method (determination method) by the determination unit 50 will be specifically described below. In order to avoid complicating the explanation, the explanation will be made assuming that the input data consists only of the temperature data T1 to T13.
- the learned input data (explanatory variable) is expressed by the following formula [Equation 1]. Further, the learned tip position Y[ ⁇ ] (objective variable) of the probe needle 35 is expressed by the following [Equation 2].
- a function obtained by a machine learning algorithm using a multiple regression model, that is, a prediction model 47 is expressed by the following [Equation 3].
- the prediction unit 46 described above based on the current input data X[T], which is the explanatory variable, uses the prediction model 47 represented by the formula [Equation 3] to calculate the tip position of the probe needle 35, which is the objective variable. Predict Y[T].
- the determination unit 50 determines that the prediction model 47 is in an unlearned state, and denies execution of prediction by the prediction model 47. and decide.
- the predictive model generating unit 48 receives the determination result from the determining unit 50 and functions as the re-learning unit of the present invention, thereby re-learning the predictive model 47 .
- the prediction model generation unit 48 controls the needle position acquisition unit 44, a movement control unit 52 described later, and the like, and obtains an objective variable corresponding to the current input data X[T]. A tip position Y[T] of a certain probe needle 35 is acquired. At this time, the predictive model generation unit 48 may control the temperature sensor 34, the alignment data measurement unit 38, the movement control unit 52, and the like to re-measure the input data.
- the predictive model generator 48 adds the current input data X[T] and the tip position Y[T] of the probe needle 35 to the teacher data 56 in the storage unit 39 to create new teacher data 56. do.
- the prediction model generation unit 48 converts the teacher data 56 in the storage unit 39 ( It is preferable to exclude the oldest data (X[1], Y[1]) from explanatory variables, objective variables).
- the prediction model generation unit 48 generates the teacher data 56 stored in the storage unit 39, that is, the input data (explanatory variables) shown in the above [Equation 6] and the probe needle shown in the above [Equation 7]. Based on the tip position (objective variable) of 35, machine learning is performed using a multiple regression model, and the prediction model 47 is re-learned. As a result, a new prediction model 47 (function) is obtained as shown in the following [Equation 8].
- the input data acquisition unit 42 acquires the input data, and then the determination unit 50 determines whether prediction is possible.
- the tip of the probe needle 35 is repeatedly operated by the needle position acquisition unit 44, the prediction model generation unit 48, the input data acquisition unit 42, and the determination unit 50 until the determination unit 50 determines that the prediction is possible. Acquisition of the position, updating of the teacher data 56 in the storage unit 39, re-learning of the prediction model 47, acquisition of the input data, and determination of prediction propriety are repeatedly executed. Thereby, the prediction unit 46 can always predict the tip position of the probe needle 35 using the learned prediction model 47 .
- the movement control unit 52 drives the stages 13, 15, and 17 via the Y moving unit 14, the X moving unit 16, and the Z ⁇ moving unit 18.
- the movement control unit 52 obtains the positions of the semiconductor chips 9 (electrode pads 9 a ) to be inspected on the wafer W held by the wafer chuck 20 based on the photographed image input from the wafer alignment camera 29 .
- the movement control unit 52 also acquires the tip position of the probe needle 35 (value measured when the probe card 26 is replaced, etc.) from the needle position acquisition unit 44 .
- the movement control unit 52 drives the stages 13, 15, and 17 to move the wafer W relative to the probe needles 35, thereby moving the probe needles 35 over the wafer W.
- the semiconductor chips 9 to be inspected are brought into contact with each other in order.
- the movement control unit 52 drives the stages 13, 15, and 17 based on the prediction result of the tip position of the probe needle 35 by the prediction unit 46, and moves the semiconductor chip 9 for each semiconductor chip 9 to be inspected.
- the contact position of the probe needle 35 with respect to is corrected.
- the probe needle 35 can be moved to the inspection target at each contact position after correction corresponding to the tip position after this displacement. It can be brought into contact with the semiconductor chip 9 .
- FIG. 7 is a flow chart showing the flow of the method of contacting the probe needle 35 to the semiconductor chip 9 by the prober 10 having the above configuration, which corresponds to the prober control method of the present invention.
- the prediction model 47 is generated in advance, and the teaching data 56 used for the machine learning is stored in the storage unit 39, and the tip position of the probe needle 35 is also acquired by the needle position acquiring unit 44. I will explain as a thing.
- the movement control unit 52 determines the position of the semiconductor chip 9 (electrode pad 9a) to be inspected based on the captured image captured by the wafer alignment camera 29 .
- the input data acquisition unit 42 causes the temperature sensor 34 to measure temperatures at the temperature measurement points P1 to P13 and the alignment data measurement unit 38 to measure alignment data.
- the input data acquisition unit 42 acquires the current input data including the temperature data of the temperature measurement points P1 to P13 and the alignment data (step S1, which corresponds to the input data acquisition step of the present invention).
- the determination unit 50 operates to compare the current input data acquired by the input data acquisition unit 42 and the input data of the teacher data 56 in the storage unit 39 for prediction.
- the predictive model 47 determines whether the current input data is in a learned state or in an unlearned state.
- the prediction model generation unit 48 controls the needle position acquisition unit 44, the movement control unit 52, etc., to correspond to the current input data.
- the tip position of the probe needle 35 is obtained (step S4). At this time, the input data may be reacquired.
- the prediction model generation unit 48 stores the current input data and the tip position of the probe needle 35 with respect to the teacher data 56 in the storage unit 39 as shown in the above [Equation 6] and [Equation 7]. By adding Y and excluding the oldest data, the teacher data 56 is updated (step S5). Then, the prediction model generation unit 48 re-learns the prediction model 47 based on the new teacher data 56 in the storage unit 39 to generate a new prediction model 47 (step S6).
- the input data acquisition unit 42 acquires the input data again (step S2), and the determination unit 50 determines whether prediction is possible based on this input data (step S3). Thereafter, the processes of steps S4 to S6, steps S1, and S2 are repeated until the determination unit 50 determines that prediction is possible.
- the prediction unit 46 refers to the prediction model 47 based on the most recent input data acquired in step S1 to determine the tip position of the probe needle 35. is predicted (step S7, which corresponds to the prediction step of the present invention). The prediction unit 46 then outputs the prediction result of the tip position of the probe needle 35 to the movement control unit 52 .
- the movement control unit 52 moves the stages 13, 15, and 17 based on the prediction result of the tip position of the probe needle 35 input from the prediction unit 46 and the previously determined position of the semiconductor chip 9 to be inspected.
- the probe needle 35 is brought into contact with the semiconductor chip 9 to be inspected (step S8). After this contact, the semiconductor chip 9 is tested by a tester (not shown) (step S9).
- step S1 to step S7 may be repeatedly executed each time a predetermined number of semiconductor chips 9 are inspected or each time a predetermined time elapses.
- the determination unit 50 compares the current input data acquired before contact control with the input data of the teacher data 56 to determine whether prediction is possible. When it is determined, the tip position of the probe needle 35 can be predicted more accurately than before by re-learning the prediction model 47 .
- FIG. 8 is a graph (see symbol VIIIA) showing the predicted value PV and the measured value MV of the tip position of the probe needle 35 in a comparative example in which the determination by the determination unit 50 and the re-learning of the prediction model 47 are not performed, and the probe 8 is a graph (see symbol VIIIB) showing a difference value between the predicted value PV and the measured value MV of the tip position of the needle 35;
- FIG. 9 is a graph (see symbol IXA) showing the predicted value PV and the measured value MV of the tip position of the probe needle 35, and the predicted value PV and the measured value MV of the tip position of the probe needle 35 in this embodiment. is a graph (see symbol IXB) showing the difference value of .
- the graphs of FIGS. 8 and 9 show predicted values of the tip position of the probe needle 35 in any one of the XYZ directions (the Y direction in this case) when the temperature of the wafer chuck 20 is set to 200°. It shows temporal changes in PV and measured values MV, and temporal changes in their difference values. WA in FIGS. 8 and 9 indicates a machine learning range in which machine learning is performed.
- the drift of the temperature sensor 34 occurs, or the position of the tip of the probe needle 35 is displaced due to the temperature fluctuation in the portion of the prober 10 where the temperature is not measured. , it was confirmed that there is a deviation between the predicted value PV and the measured value MV of the tip position of the probe needle 35 after the machine learning range WA, and the difference value gradually increases.
- the determination of the prediction availability by the determination unit 50 and the re-learning of the prediction model 47 are performed to predict the tip position of the probe needle 35. It was confirmed that the value PV and the actual measurement value MV were almost the same, and the difference value was reduced. As a result, in the present embodiment, drift of the temperature sensor 34 may occur, or the tip position of the probe needle 35 may be displaced due to temperature fluctuations at locations in the prober 10 where the temperature is not measured. However, by re-learning the prediction model 47, the tip position of the probe needle can be predicted more accurately.
- the prediction model generator 48 both generates and relearns the prediction model 47, but the generation of the prediction model 47 may be performed by the manufacturer of the prober 10, another prober 10, or the like.
- the control unit 40 instead of the prediction model generation unit 48, the control unit 40 may be provided with a re-learning unit that only re-learns the prediction model 47.
- the determination unit 50 uses the above [Equation 5] to determine whether prediction is possible, but this determination method is not particularly limited. For example, for each parameter of the input data, it is determined whether or not the current input data is included between the maximum and minimum values of the input data of the teacher data 56 (hereinafter referred to as the maximum and minimum range), and all parameters A prediction yes/no decision may be made based on whether the current input data is within the maximum/minimum range in .
- the temperature data of the card holder 25 and the probe card 26 and the alignment data are measured as the input data in the above embodiment, only the temperature data may be measured. Further, in the above embodiment, the temperature data of both the card holder 25 and the probe card 26 are measured as input data, but the temperature data of at least one of the card holder 25 and the probe card 26 may be measured. Furthermore, in the above embodiment, the chip size of the semiconductor chip 9, the position of the wafer W, and the relative distance to the camera are measured as alignment data, but at least one of these may be measured.
- non-contact temperature sensor 34 is used in the above embodiment, a contact temperature sensor 34 may be used.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Microelectronics & Electronic Packaging (AREA)
- Computer Hardware Design (AREA)
- General Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Manufacturing & Machinery (AREA)
- Condensed Matter Physics & Semiconductors (AREA)
- Software Systems (AREA)
- Robotics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Testing Or Measuring Of Semiconductors Or The Like (AREA)
- Tests Of Electronic Circuits (AREA)
Abstract
Description
図1は、ウェーハWに形成された複数の半導体チップ9(図3参照)の電気的特性を検査するウェーハテストシステムに用いられるプローバ10の概略図である。図2はプローバ10の外観斜視図である。
図5は、プローバ10の制御部40の機能を示す機能ブロック図である。なお、図5では、制御部40の各機能の中でプローブ針35とウェーハW(半導体チップ9の電極パッド9a)との接触制御に係る機能のみを図示し、他の機能については公知技術であるため図示を省略している。
図7は、本発明のプローバ制御方法に相当する、上記構成のプローバ10による半導体チップ9へのプローブ針35の接触方法の流れを示すフローチャートである。なお、予測モデル47が予め生成されており且つその機械学習に用いられた教師データ56が記憶部39に記憶され、さらに針位置取得部44によるプローブ針35の先端位置の取得も行われているものとして説明を行う。
以上のように本実施形態では、決定部50が、接触制御前に取得された現在の入力データと教師データ56の入力データとを比較して予測可否決定を行い、この決定部50が否と決定した場合には予測モデル47の再学習を実行することで、プローブ針35の先端位置を従来よりも正確に予測することができる。
上記実施形態では、予測モデル生成部48が予測モデル47の生成及び再学習の両方を行っているが、予測モデル47の生成はプローバ10の製造メーカ或いは別のプローバ10等で行ってもよい。この場合には、予測モデル生成部48の代わりに予測モデル47の再学習のみを行う再学習部を制御部40に設けてもよい。
9a 電極パッド
10 プローバ
12 ベース
13 Yステージ
14 Y移動部
15 Xステージ
16 X移動部
17 Zθステージ
18 Zθ移動部
20 ウェーハチャック
20a 温度調整部
23 支柱
24 ヘッドステージ
25 カードホルダ
25a 保持穴
26 プローブカード
29 ウェーハ位置合わせカメラ
30 上下ステージ
31 針位置合わせカメラ
32 クリーニング板
34 温度センサ
35 プローブ針
38 アライメントデータ測定部
39 記憶部
40 制御部
42 入力データ取得部
44 針位置取得部
46 予測部
47 予測モデル
48 予測モデル生成部
50 決定部
52 移動制御部
56 教師データ
D ユークリッド距離
D1 チップサイズ
D2 ウェーハ位置
D3 カメラ相対距離
Dth 閾値
MV 実測値
P1~P13 温度測定ポイント
PV 予測値
T1~T13 温度データ
W ウェーハ
WA 機械学習範囲
Claims (8)
- 複数の半導体チップが形成されたウェーハを保持するウェーハチャックと、プローブ針を有するプローブカードと、前記プローブカードの外周を保持して、前記プローブカードを前記ウェーハに対向させるカードホルダと、前記ウェーハチャックを前記プローブ針に対して相対移動させる相対移動部と、を備えるプローバの前記相対移動部を駆動して前記プローブ針を前記半導体チップに接触させるプローバ制御装置において、
前記プローブカード及び前記カードホルダの少なくとも一方の温度データを含む入力データを取得する入力データ取得部と、
前記入力データ取得部が取得した前記入力データに基づき、前記入力データを入力とし且つ前記プローブ針の先端位置を出力とする予測モデルを用いて、前記プローブ針の先端位置を予測する予測部と、
前記予測部の予測前に、前記予測モデルの機械学習に教師データとして用いられた前記入力データと、前記入力データ取得部が取得した前記入力データとに基づき、前記予測部による予測の実行の可否を決定する決定部と、
を備えるプローバ制御装置。 - 前記決定部は、
前記入力データのパラメータごとに、前記入力データ取得部が取得した前記入力データと前記教師データとして用いられた前記入力データとの差分を演算する処理と、
前記パラメータごとに前記差分の二乗和平方根を演算して、前記パラメータごとの前記差分の二乗和平方根の中で、予め定められた一定範囲内になるものが少なくとも1つあるか否かに基づき、前記予測部による予測の実行の可否を判定する処理と、
を行う請求項1に記載のプローバ制御装置。 - 前記決定部が否と決定した場合に、
前記プローブ針の先端位置を取得する針位置取得部と、
前記入力データ取得部が取得した前記入力データと前記針位置取得部が取得した前記プローブ針の先端位置とを加えた前記教師データを用いて、前記予測モデルを再学習させる再学習部と、
を備え、
前記決定部が可と決定するまで、前記針位置取得部と前記再学習部と前記入力データ取得部と前記決定部とが繰り返し作動する請求項1又は2に記載のプローバ制御装置。 - 前記再学習部が、前記教師データの中から最も古い前記入力データ及び前記入力データに対応する前記プローブ針の先端位置を除外してから、前記教師データに基づき前記予測モデルの再学習を実行する請求項3に記載のプローバ制御装置。
- 前記決定部が可と決定した場合に、前記予測部が前記プローブ針の先端位置を予測し、
前記予測部が予測した前記プローブ針の先端位置に基づき、前記相対移動部を制御して、前記半導体チップに前記プローブ針を接触させる移動制御部を備える請求項1から4のいずれか1項に記載のプローバ制御装置。 - 前記入力データ取得部が、前記入力データとして、前記温度データの他に、前記半導体チップのチップサイズと、前記ウェーハの位置と、前記半導体チップの検出に用いられる第1カメラ及び前記プローブ針の検出に用いられる第2カメラの位置関係と、の少なくともいずれか1つを含むアライメントデータを取得する請求項1から5のいずれか1項に記載のプローバ制御装置。
- 複数の半導体チップが形成されたウェーハを保持するウェーハチャックと、
プローブ針を有するプローブカードと、
前記プローブカードの外周を保持して、前記プローブカードを前記ウェーハに対向させるカードホルダと、
前記ウェーハチャックを前記プローブ針に対して相対移動させる相対移動部と、
請求項1から6のいずれか1項に記載のプローバ制御装置と、
を備えるプローバ。 - 複数の半導体チップが形成されたウェーハを保持するウェーハチャックと、プローブ針を有するプローブカードと、前記プローブカードの外周を保持して、前記プローブカードを前記ウェーハに対向させるカードホルダと、前記ウェーハチャックを前記プローブ針に対して相対移動させる相対移動部と、を備えるプローバの前記相対移動部を駆動して前記プローブ針を前記半導体チップに接触させるプローバ制御方法において、
前記プローブカード及び前記カードホルダの少なくとも一方の温度データを含む入力データを取得する入力データ取得ステップと、
前記入力データ取得ステップで取得した前記入力データに基づき、前記入力データを入力とし且つ前記プローブ針の先端位置を出力とする予測モデルを用いて、前記プローブ針の先端位置を予測する予測ステップと、
前記予測ステップの前に、前記予測モデルの機械学習に教師データとして用いられた前記入力データと、前記入力データ取得ステップで取得した前記入力データとに基づき、前記予測ステップの実行の可否を決定する決定ステップと、
を有するプローバ制御方法。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020237041608A KR20230170802A (ko) | 2021-06-04 | 2022-05-09 | 프로버 제어 장치, 프로버 제어 방법, 및 프로버 |
CN202280039695.7A CN117425953A (zh) | 2021-06-04 | 2022-05-09 | 探测器控制装置、探测器控制方法以及探测器 |
US18/527,013 US12007413B2 (en) | 2021-06-04 | 2023-12-01 | Prober controlling device, prober controlling method, and prober |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2021-094056 | 2021-06-04 | ||
JP2021094056A JP2022186039A (ja) | 2021-06-04 | 2021-06-04 | プローバ制御装置、プローバ制御方法、及びプローバ |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US18/527,013 Continuation US12007413B2 (en) | 2021-06-04 | 2023-12-01 | Prober controlling device, prober controlling method, and prober |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022255030A1 true WO2022255030A1 (ja) | 2022-12-08 |
Family
ID=84324243
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2022/019630 WO2022255030A1 (ja) | 2021-06-04 | 2022-05-09 | プローバ制御装置、プローバ制御方法、及びプローバ |
Country Status (6)
Country | Link |
---|---|
US (1) | US12007413B2 (ja) |
JP (1) | JP2022186039A (ja) |
KR (1) | KR20230170802A (ja) |
CN (1) | CN117425953A (ja) |
TW (1) | TWI834180B (ja) |
WO (1) | WO2022255030A1 (ja) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116504664A (zh) * | 2023-06-28 | 2023-07-28 | 东莞市兆恒机械有限公司 | 一种晶圆检测方法、检测装置及检测*** |
CN116500426A (zh) * | 2023-06-28 | 2023-07-28 | 东莞市兆恒机械有限公司 | 一种半导体检测设备高温测试标定的方法 |
JP7467824B1 (ja) | 2022-12-06 | 2024-04-16 | 株式会社東京精密 | 温度制御装置、温度制御方法、プログラム、プローバ及び学習モデル生成方法 |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7422340B1 (ja) | 2022-11-21 | 2024-01-26 | パナソニックIpマネジメント株式会社 | 文字認識装置、文字認識方法 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0192630A (ja) * | 1987-10-02 | 1989-04-11 | Nippon Steel Corp | 放射温度計用変換器 |
JP2007311389A (ja) * | 2006-05-16 | 2007-11-29 | Tokyo Seimitsu Co Ltd | プローバ及びプローブ接触方法 |
JP2009524050A (ja) * | 2006-01-18 | 2009-06-25 | エレクトログラス・インコーポレーテッド | 動的なプローブ調節の方法及び装置 |
US20150192616A1 (en) * | 2012-06-13 | 2015-07-09 | Taiwan Semiconductor Manufacturing Company, Ltd. | Method of Test Probe Alignment Control |
JP2018117095A (ja) * | 2017-01-20 | 2018-07-26 | 株式会社東京精密 | プローバ及びプローブ針の接触方法 |
WO2019008726A1 (ja) * | 2017-07-06 | 2019-01-10 | オリンパス株式会社 | 管状挿入装置 |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2005228788A (ja) | 2004-02-10 | 2005-08-25 | Seiko Epson Corp | ウエーハとプローブカードとの位置合わせ方法、プローブ検査方法及びプローブ検査装置 |
JP4589710B2 (ja) | 2004-12-13 | 2010-12-01 | 株式会社日本マイクロニクス | プローバ |
JP4744382B2 (ja) * | 2006-07-20 | 2011-08-10 | 株式会社東京精密 | プローバ及びプローブ接触方法 |
CN101996856A (zh) * | 2009-08-26 | 2011-03-30 | 中芯国际集成电路制造(上海)有限公司 | 晶圆可接受测试的实时监控方法 |
JP6462296B2 (ja) * | 2014-09-30 | 2019-01-30 | 東京エレクトロン株式会社 | 位置精度検査方法、位置精度検査装置及び位置検査ユニット |
JP6959831B2 (ja) * | 2017-08-31 | 2021-11-05 | 株式会社日立製作所 | 計算機、処理の制御パラメータの決定方法、代用試料、計測システム、及び計測方法 |
KR102132785B1 (ko) | 2017-08-31 | 2020-07-13 | 가부시끼가이샤 히다치 세이사꾸쇼 | 계산기, 처리의 제어 파라미터의 결정 방법, 대용 시료, 계측 시스템, 및 계측 방법 |
JP7090517B2 (ja) | 2018-09-20 | 2022-06-24 | 東京エレクトロン株式会社 | 検査装置及び検査方法 |
US11499992B2 (en) | 2018-11-27 | 2022-11-15 | Tokyo Electron Limited | Inspection system |
JP7175171B2 (ja) * | 2018-12-12 | 2022-11-18 | 東京エレクトロン株式会社 | プローブカード管理システムおよびプローブカード管理方法 |
CN112735967A (zh) * | 2020-12-29 | 2021-04-30 | 上海集成电路研发中心有限公司 | 晶圆变温测试的测试方法 |
-
2021
- 2021-06-04 JP JP2021094056A patent/JP2022186039A/ja active Pending
-
2022
- 2022-05-09 CN CN202280039695.7A patent/CN117425953A/zh active Pending
- 2022-05-09 KR KR1020237041608A patent/KR20230170802A/ko not_active Application Discontinuation
- 2022-05-09 WO PCT/JP2022/019630 patent/WO2022255030A1/ja active Application Filing
- 2022-06-01 TW TW111120393A patent/TWI834180B/zh active
-
2023
- 2023-12-01 US US18/527,013 patent/US12007413B2/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0192630A (ja) * | 1987-10-02 | 1989-04-11 | Nippon Steel Corp | 放射温度計用変換器 |
JP2009524050A (ja) * | 2006-01-18 | 2009-06-25 | エレクトログラス・インコーポレーテッド | 動的なプローブ調節の方法及び装置 |
JP2007311389A (ja) * | 2006-05-16 | 2007-11-29 | Tokyo Seimitsu Co Ltd | プローバ及びプローブ接触方法 |
US20150192616A1 (en) * | 2012-06-13 | 2015-07-09 | Taiwan Semiconductor Manufacturing Company, Ltd. | Method of Test Probe Alignment Control |
JP2018117095A (ja) * | 2017-01-20 | 2018-07-26 | 株式会社東京精密 | プローバ及びプローブ針の接触方法 |
WO2019008726A1 (ja) * | 2017-07-06 | 2019-01-10 | オリンパス株式会社 | 管状挿入装置 |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7467824B1 (ja) | 2022-12-06 | 2024-04-16 | 株式会社東京精密 | 温度制御装置、温度制御方法、プログラム、プローバ及び学習モデル生成方法 |
WO2024122320A1 (ja) * | 2022-12-06 | 2024-06-13 | 株式会社東京精密 | 温度制御装置、温度制御方法、プログラム、プローバ及び学習モデル生成方法 |
CN116504664A (zh) * | 2023-06-28 | 2023-07-28 | 东莞市兆恒机械有限公司 | 一种晶圆检测方法、检测装置及检测*** |
CN116500426A (zh) * | 2023-06-28 | 2023-07-28 | 东莞市兆恒机械有限公司 | 一种半导体检测设备高温测试标定的方法 |
CN116500426B (zh) * | 2023-06-28 | 2023-09-05 | 东莞市兆恒机械有限公司 | 一种半导体检测设备高温测试标定的方法 |
Also Published As
Publication number | Publication date |
---|---|
TW202303791A (zh) | 2023-01-16 |
CN117425953A (zh) | 2024-01-19 |
US12007413B2 (en) | 2024-06-11 |
KR20230170802A (ko) | 2023-12-19 |
US20240094254A1 (en) | 2024-03-21 |
TWI834180B (zh) | 2024-03-01 |
JP2022186039A (ja) | 2022-12-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2022255030A1 (ja) | プローバ制御装置、プローバ制御方法、及びプローバ | |
US7405584B2 (en) | Prober and probe contact method | |
TWI431288B (zh) | 探測機及用於探測機之定位方法、設備及其電腦可讀取媒體 | |
JP6821910B2 (ja) | プローバ及びプローブ針の接触方法 | |
US9383732B2 (en) | Method and system for adaptively controlling a laser-based material processing process and method and system for qualifying same | |
KR100858153B1 (ko) | 프로버 및 탐침 접촉 방법 | |
US8654190B2 (en) | Imaging position correction method, imaging method, and substrate imaging apparatus | |
JP6221200B2 (ja) | プローバ | |
CN108662992B (zh) | 表面量测方法及表面量测*** | |
JP2019032290A (ja) | 走査型プローブ顕微鏡のドリフト補正方法及びドリフト補正機能を備えた走査型プローブ顕微鏡 | |
JP4557848B2 (ja) | 形状測定方法および形状測定装置 | |
JP2006186130A (ja) | 半導体検査装置 | |
JP7467824B1 (ja) | 温度制御装置、温度制御方法、プログラム、プローバ及び学習モデル生成方法 | |
JP2022096153A (ja) | 電子デバイスの検査装置及び検査方法 | |
JP7004935B2 (ja) | プローバ及びプローブ針の接触方法 | |
WO2024070678A1 (ja) | 検査方法、検査装置及びプログラム | |
JP2008166648A (ja) | 半導体集積回路の検査装置 | |
JP2008147276A (ja) | プローブカード、半導体ウエハの検査装置および半導体ウエハの検査方法 | |
JP2008010473A (ja) | ウエハプロービング装置及びウエハプロービング方法 |
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: 22815785 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 20237041608 Country of ref document: KR Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202280039695.7 Country of ref document: CN Ref document number: 1020237041608 Country of ref document: KR |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 22815785 Country of ref document: EP Kind code of ref document: A1 |