Method for estimating polishing pad life and polishing apparatus

Abstract

To provide an improved technology capable of accurately estimating a service life of a polishing pad.SOLUTION: In a polishing pad service life estimation method, a workpiece W is polished by pressing the workpiece W against a polishing surface 2a of a polishing pad 2 by an elastic film forming a pressure chamber C1 provided in a polishing head 7, a pressure in the pressure chamber C1 is controlled on the basis of a measurement value of a film thickness of the workpiece W while measuring the film thickness during polishing of the workpiece W, pressure time-series data representing a change in the pressure in the pressure chamber C1 during polishing of the workpiece W is input to a learned model 42, and a service life indicator of the polishing pad 2 is output from the learned model 42.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a technique for estimating the life of a polishing pad used in a polishing apparatus for polishing workpieces such as wafers, substrates, and panels.

Background Art

[0002] Chemical mechanical polishing (hereinafter referred to as CMP) is a process of polishing a workpiece (for example, a wafer, a substrate, or a panel) by bringing the workpiece into sliding contact with a polishing pad while supplying a polishing liquid containing abrasive grains such as silica (SiO 2 ) onto the polishing pad. A polishing apparatus for performing this CMP includes a polishing table that supports a polishing pad having a polishing surface, and a polishing head for pressing the workpiece against the polishing pad.

[0003] The polishing apparatus polishes the workpiece as follows. While rotating the polishing table and the polishing pad integrally, a polishing liquid (typically slurry) is supplied to the polishing surface of the polishing pad. The polishing head presses the surface of the workpiece against the polishing surface of the polishing pad while rotating the workpiece. The workpiece is brought into sliding contact with the polishing pad in the presence of the polishing liquid. The surface of the workpiece is polished by the chemical action of the polishing liquid and the mechanical action of the abrasive grains contained in the polishing liquid and / or the polishing pad.

[0004] When polishing the workpiece, abrasive grains and polishing debris adhere to the polishing surface of the polishing pad, and the polishing performance of the polishing pad deteriorates. Therefore, in order to regenerate the polishing surface of the polishing pad, dressing of the polishing pad is performed by a dresser 50. The dresser 50 has hard abrasive grains such as diamond particles fixed to its lower surface, and the polishing surface of the polishing pad is regenerated by slightly scraping off the polishing surface of the polishing pad with this dresser 50.

[0005] The polishing pad gradually wears out as dressing is repeated. When the polishing pad wears out, the intended polishing performance cannot be obtained, so it is necessary to replace the polishing pad regularly. Therefore, when the usage time of the polishing pad exceeds a predetermined time, or when the number of workpiece pieces polished exceeds a predetermined number, the polishing pad is replaced with a new one.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0007] However, the usage time of the polishing pad and the number of workpiece pieces polished only indirectly represent the wear of the polishing pad and may not accurately reflect the wear of the polishing pad. As a result, a polishing pad that has not yet reached the end of its life may be replaced, or a polishing pad that has worn out beyond the limit of use may continue to be used. In particular, when an overly worn polishing pad is used, the target film thickness profile of the workpiece may not be achieved.

[0008] Therefore, the present invention provides an improved technique that can accurately estimate the life of a polishing pad.

Means for Solving the Problems

[0009] In one aspect, an elastic film that forms a pressure chamber provided in a polishing head presses a workpiece against a polishing surface of a polishing pad to polish the workpiece. During polishing of the workpiece, while measuring the film thickness of the workpiece, based on the measured value of the film thickness, the pressure in the pressure chamber is controlled. Pressure time-series data representing the change in the pressure during polishing of the workpiece is input into a learned model, and a life index of the polishing pad is output from the learned model, thereby providing a method for estimating the life of a polishing pad.

[0010] In one aspect, in addition to the pressure time-series data, polishing data related to polishing of the workpiece is input into the learned model. In one aspect, the polishing data includes at least one of information on the workpiece and polishing conditions of the workpiece. In one aspect, in addition to the pressure time-series data, a cut rate of the polishing pad dressed by a dresser is input into the learned model. In one aspect, the step of inputting the pressure time-series data into the learned model and outputting the life index of the polishing pad from the learned model is executed after polishing of the workpiece and before polishing the next workpiece. In one aspect, the pressure chamber is a plurality of pressure chambers. The step of controlling the pressure in the pressure chamber is a step of controlling the pressure in the plurality of pressure chambers based on the measured value of the film thickness while measuring the film thickness of the workpiece during polishing of the workpiece. The step of inputting the pressure time-series data into the learned model is a step of inputting a plurality of pressure time-series data respectively representing the changes in the pressures in the plurality of pressure chambers during polishing of the workpiece into the learned model.

[0011] In one aspect, there is provided a polishing apparatus including: a polishing head having a pressure chamber formed by an elastic film, the polishing head pressing a workpiece against a polishing surface of a polishing pad by the elastic film to polish the workpiece; a film thickness sensor for measuring the film thickness of the workpiece; a polishing control unit for controlling the pressure in the pressure chamber during polishing of the workpiece based on the measured value of the film thickness; and a pad life calculation unit for inputting pressure time-series data representing a change in the pressure during polishing of the workpiece into a learned model and outputting a life index of the polishing pad from the learned model.

[0012] In one aspect, the pad life calculation unit is configured to input, in addition to the pressure time-series data, polishing data related to polishing of the workpiece into the learned model. In one aspect, the polishing data includes at least one of information on the workpiece and polishing conditions of the workpiece. In one aspect, the polishing apparatus further includes a dresser for dressing the polishing surface of the polishing pad, and the pad life calculation unit is configured to input, in addition to the pressure time-series data, a cut rate of the polishing pad dressed by the dresser into the learned model. In one aspect, the pad life calculation unit is configured to input the pressure time-series data into the learned model and output a life index of the polishing pad from the learned model after polishing of the workpiece and before polishing the next workpiece. In one aspect, the pressure chamber is a plurality of pressure chambers, the polishing control unit is configured to control the pressure in the plurality of pressure chambers based on the measured value of the film thickness while measuring the film thickness of the workpiece during polishing of the workpiece, and the pad life calculation unit is configured to input a plurality of pressure time-series data respectively representing changes in the pressure in the plurality of pressure chambers during polishing of the workpiece into the learned model.

Advantages of the Invention

[0013] The pressure change in the pressure chamber of the polishing head during the polishing of the workpiece reflects the degree of wear of the polishing pad. Therefore, the learned model can accurately estimate the life of the polishing pad from the pressure time-series data indicating the pressure change in the pressure chamber of the polishing head.

Brief Description of the Drawings

[0014]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Embodiments for Carrying Out the Invention

[0015] Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a schematic diagram showing an embodiment of a polishing apparatus. The polishing apparatus is an apparatus for chemically mechanically polishing a wafer W, which is an example of a workpiece used in the manufacture of semiconductor devices. As shown in FIG. 1, this polishing apparatus includes a polishing table 5 that supports a polishing pad 2 having a polishing surface 2a, a polishing head 7 that presses the wafer W against the polishing surface 2a, and a polishing liquid supply nozzle 8 that supplies a polishing liquid (for example, a slurry containing abrasive grains) to the polishing surface 2a.

[0016] The polishing head 7 is configured to hold the wafer W on its lower surface. The wafer W has a film to be polished. In the following embodiments, a wafer is used as an example of the workpiece, but the workpiece is not limited to a wafer and may be a circular substrate, a rectangular substrate, a panel, etc. used in the manufacture of semiconductor devices.

[0017] The polishing apparatus further includes a support shaft 14, a polishing head swing arm 16 connected to the upper end of the support shaft 14, and a polishing head shaft 18 rotatably supported at the free end of the polishing head swing arm 16. The polishing head 7 is fixed to the lower end of the polishing head shaft 18. A polishing head rotation mechanism (not shown) including an electric motor or the like is disposed in the polishing head swing arm 16. This polishing head rotation mechanism is connected to the polishing head shaft 18 and is configured to rotate the polishing head shaft 18 and the polishing head 7 in the direction indicated by the arrow.

[0018] The polishing head shaft 18 is connected to a polishing head lifting mechanism (including a ball screw mechanism or the like) not shown. This polishing head lifting mechanism is configured to move the polishing head shaft 18 relatively up and down with respect to the polishing head swing arm 16. Due to the up and down movement of the polishing head shaft 18, the polishing head 7 can move relatively up and down with respect to the polishing head swing arm 16 and the polishing table 5 as indicated by the arrow.

[0019] The polishing apparatus further includes a table rotation motor 21 that rotates the polishing pad 2 and the polishing table 5 about their axes. The table rotation motor 21 is disposed below the polishing table 5, and the polishing table 5 is connected to the table rotation motor 21 via a table shaft 5a. The polishing table 5 and the polishing pad 2 are rotated by the table rotation motor 21 about the table shaft 5a in the direction indicated by the arrow. The polishing pad 2 is attached to the upper surface of the polishing table 5. The exposed surface of the polishing pad 2 constitutes a polishing surface 2a for polishing the wafer W.

[0020] The wafer W is polished as follows. The wafer W is held by the polishing head 7 with its surface to be polished facing downward. While rotating the polishing head 7 and the polishing table 5 respectively, a polishing liquid (for example, a slurry containing abrasive grains) is supplied from a polishing liquid supply nozzle 8 provided above the polishing table 5 onto the polishing surface 2a of the polishing pad 2. The polishing pad 2 rotates integrally with the polishing table 5 about its central axis. The polishing head 7 is moved to a predetermined height by a polishing head lifting mechanism (not shown). Further, while the polishing head 7 is maintained at the above-mentioned predetermined height, the wafer W is pressed against the polishing surface 2a of the polishing pad 2. The wafer W rotates integrally with the polishing head 7. With the polishing liquid present on the polishing surface 2a of the polishing pad 2, the wafer W is brought into sliding contact with the polishing surface 2a. The surface of the wafer W is polished by a combination of the chemical action of the polishing liquid and the mechanical action of the abrasive grains contained in the polishing liquid and / or the polishing pad 2.

[0021] The polishing apparatus includes a film thickness sensor 24 that measures the film thickness of the wafer W on the polishing surface 2a. The film thickness sensor 24 is configured to generate a measured value of the film thickness that directly or indirectly indicates the film thickness of the wafer W. This measured value of the film thickness changes according to the film thickness of the wafer W and indicates the film thickness of the wafer W. The measured value of the film thickness may be a value representing the film thickness itself of the wafer W, or may be a physical quantity or a signal value before being converted into the film thickness.

[0022] Examples of the film thickness sensor 24 include an optical film thickness sensor and an eddy current sensor. The optical film thickness sensor is configured to irradiate light onto the surface of the wafer W and determine the film thickness of the wafer W from the spectrum of the reflected light from the wafer W. The eddy current sensor is configured to induce an eddy current in the conductive film formed on the wafer W and output a signal value that changes according to the impedance of an electric circuit including the conductive film and the coil of the eddy current sensor. Known devices can be used for the optical film thickness sensor and the eddy current sensor.

[0023] The film thickness sensor 24 is installed inside the polishing table 5 and rotates integrally with the polishing table 5. More specifically, each time the polishing table 5 makes one rotation, the film thickness sensor 24 is configured to measure the film thickness at a plurality of measurement points on the wafer W while crossing the wafer W on the polishing surface 2a. In the present embodiment, the film thickness sensor 24 is arranged to measure the film thickness at a plurality of measurement points including the center of the wafer W. Therefore, the plurality of measurement points are arranged in the radial direction of the wafer W.

[0024] The polishing apparatus further includes a polishing control unit 30 that controls the pressure in the pressure chamber (described later) of the polishing head 7 during polishing of the wafer W based on the measured film thickness values obtained by the film thickness sensor 24, and inputs pressure time series data representing the pressure change in the pressure chamber of the polishing head 7 during polishing of the wafer W into the learned model 42, and a pad life calculation unit 40 that outputs an index of the life of the polishing pad from the learned model 42.

[0025] The polishing control unit 30 is composed of at least one computer. The polishing control unit 30 includes a storage device 30a storing a program for controlling the pressure in the pressure chamber of the polishing head 7 based on the measured film thickness value, and an arithmetic device 30b that executes arithmetic operations according to instructions included in the program. The storage device 30a includes a main storage device such as a random access memory (RAM), and auxiliary storage devices such as a hard disk drive (HDD) and a solid state drive (SSD). Examples of the arithmetic device 30b include a CPU (central processing unit) and a GPU (graphics processing unit). However, the specific configuration of the polishing control unit 30 is not limited to these examples.

[0026] The pad life calculation unit 40 is composed of at least one computer. The pad life calculation unit 40 includes a storage device 40a storing a learned model 42, a program for calculating the life of the polishing head 7 using the learned model 42, and a program for executing machine learning for constructing the learned model 42, and an arithmetic device 40b that executes arithmetic operations according to instructions included in these programs. The storage device 40a includes a main storage device such as a random access memory (RAM), and auxiliary storage devices such as a hard disk drive (HDD) and a solid state drive (SSD). Examples of the arithmetic device 40b include a CPU (central processing unit) and a GPU (graphics processing unit). However, the specific configuration of the pad life calculation unit 40 is not limited to these examples.

[0027] Each of the polishing control unit 30 and the pad life calculation unit 40 may be composed of a plurality of computers. For example, each of the polishing control unit 30 and the pad life calculation unit 40 may be a combination of an edge server and a cloud server.

[0028] The film thickness sensor 24 is connected to the polishing control unit 30. The measured film thickness values generated by the film thickness sensor 24 are sent to the polishing control unit 30. That is, the measured film thickness values at a plurality of measurement points on the wafer W are output from the film thickness sensor 24, sent to the polishing control unit 30, and stored in the storage device 30a. The pad life calculation unit 40 is connected to the polishing control unit 30.

[0029] The polishing apparatus includes a dresser 50 for dressing the polishing surface 2a of the polishing pad 2. This dresser 50 includes a dressing disk 51 that is in sliding contact with the polishing surface 2a of the polishing pad 2, a dresser shaft 52 to which the dressing disk 51 is connected, and a dresser swing arm 55 that rotatably supports the dresser shaft 52. The lower surface of the dressing disk 51 constitutes a dressing surface 51a, and this dressing surface 51a is composed of abrasive grains (for example, diamond particles).

[0030] The dresser shaft 52 is connected to a disk pressing mechanism (including, for example, an air cylinder) (not shown) disposed within the dresser swing arm 55. This disk pressing mechanism is configured to press the dressing surface 51a of the dressing disk 51 against the polishing surface 2a of the polishing pad 2 via the dresser shaft 52. Further, the dresser shaft 52 is connected to a disk rotation mechanism (including, for example, an electric motor) (not shown) disposed within the dresser swing arm 55. This disk rotation mechanism is configured to rotate the dressing disk 51 in the direction indicated by the arrow via the dresser shaft 52.

[0031] The dressing of the polishing surface 2a of the polishing pad 2 is performed as follows. The polishing pad 2 is rotated by a table rotation motor 21 together with the polishing table 5, and pure water is supplied to the polishing surface 2a from a pure water supply nozzle (not shown). The dressing disk 51 is rotated by a disk rotation mechanism (not shown) about the dresser shaft 52, and the dressing surface 51a of the dressing disk 51 is pressed against the polishing surface 2a by a disk pressing mechanism (not shown). With pure water present on the polishing surface 2a, the dressing disk 51 is brought into sliding contact with the polishing surface 2a. During rotation of the dressing disk 51, the dresser swing arm 55 is pivoted about the support shaft 58 to swing the dressing disk 51 in the radial direction of the polishing surface 2a. In this way, the polishing pad 2 is slightly scraped off by the dressing disk 51, and the polishing surface 2a is dressed (regenerated). The dressing of the polishing surface 2a of the polishing pad 2 is performed during polishing of the wafer W or after polishing of the wafer W.

[0032] Next, the polishing head 7 will be described. FIG. 2 is a cross-sectional view showing an embodiment of the polishing head 7. The polishing head 7 includes a head body 61 fixed to the end of a polishing head shaft 18, an elastic film 64 attached to the lower part of the head body 61, and a retainer ring 62 disposed below the head body 61. The retainer ring 62 is disposed around the elastic film 64. This retainer ring 62 is an annular structure for holding the wafer W so that the wafer W does not jump out of the polishing head 7 during polishing of the wafer W.

[0033] Four pressure chambers C1, C2, C3, C4 are provided between the elastic film 64 and the head body 61. The pressure chambers C1, C2, C3, C4 are formed by the elastic film 64 and the head body 61. The central pressure chamber C1 is circular, and the other pressure chambers C2, C3, C4 are annular. These pressure chambers C1, C2, C3, C4 are arranged concentrically.

[0034] Pressure chambers C1, C2, C3, and C4 are respectively connected to gas transfer lines F1, F2, F3, and F4. One end of the gas transfer lines F1, F2, F3, and F4 is connected to a compressed gas supply source (not shown) as a utility provided in the factory where the polishing apparatus is installed. Compressed gas such as compressed air is supplied to the pressure chambers C1, C2, C3, and C4 through the gas transfer lines F1, F2, F3, and F4 respectively. The compressed gas in the pressure chambers C1, C2, C3, and C4 presses the wafer W against the polishing surface 2a of the polishing pad 2 via the elastic membrane 64.

[0035] The gas transfer line F3 communicating with the pressure chamber C3 is connected to a vacuum line (not shown), and it is possible to form a vacuum in the pressure chamber C3. When a vacuum is formed in the pressure chamber C3, the elastic membrane 64 constituting the pressure chamber C3 is recessed upward. As a result, the polishing head 7 can hold the wafer W by the elastic membrane 64 deformed like a suction cup. In one embodiment, an opening is formed in the portion of the elastic membrane 64 that constitutes the pressure chamber C3, and the wafer W may be adsorbed and held by the polishing head 7 by forming a vacuum in the pressure chamber C3.

[0036] An annular elastic membrane 66 is disposed between the head body 61 and the retainer ring 62, and a pressure chamber C5 is formed inside the elastic membrane 66. The pressure chamber C5 is connected to the compressed gas supply source via the gas transfer line F5. Compressed gas is supplied into the pressure chamber C5 through the gas transfer line F5, and the compressed gas in the pressure chamber C5 presses the retainer ring 62 against the polishing pad 2.

[0037] The gas transfer lines F1, F2, F3, F4, and F5 extend via a rotary joint 70 attached to the polishing head shaft 18. Pressure regulators R1, R2, R3, R4, and R5 are provided in the gas transfer lines F1, F2, F3, F4, and F5 that communicate with the pressure chambers C1, C2, C3, C4, and C5, respectively. Compressed gas from a compressed gas supply source is independently supplied into the pressure chambers C1 to C5 through the pressure regulators R1 to R5. The pressure regulators R1 to R5 are configured to adjust the pressure of the compressed gas in the pressure chambers C1 to C5.

[0038] The pressure regulators R1 to R5 can independently change the internal pressures of the pressure chambers C1 to C5, whereby the pressing pressures on the corresponding four regions of the wafer W, namely, the central portion, the inner middle portion, the outer middle portion, and the edge portion, and the pressing pressure of the retainer ring 62 on the polishing pad 2 can be independently adjusted. The gas transfer lines F1, F2, F3, F4, and F5 are also each connected to an atmosphere release valve (not shown), and it is also possible to release the pressure chambers C1 to C5 to the atmosphere. In the present embodiment, the elastic membrane 64 forms four pressure chambers C1 to C4, but in one embodiment, the elastic membrane 64 may form three or less or five or more pressure chambers. Only a single pressure chamber may be provided.

[0039] Pressure regulators R1 to R5 are connected to the polishing control unit 30. The polishing control unit 30 is configured to control the pressures in the pressure chambers C1 to C5 via the pressure regulators R1 to R5 based on the measured values of the film thickness of the wafer W. More specifically, the polishing control unit 30 receives a plurality of measured values of the film thickness of the wafer W from the film thickness sensor 24 (see FIG. 1), determines the respective target pressure values of the pressure chambers C1 to C5 for achieving the target film thickness based on the plurality of measured values of the film thickness, and transmits the target pressure values to the pressure regulators R1 to R5. The pressure regulators R1 to R5 operate so that the pressures in the pressure chambers C1 to C5 are maintained at the corresponding target pressure values. Therefore, the target pressure values for the pressure chambers C1 to C5 determined by the polishing control unit 30 respectively correspond to the actual pressures in the pressure chambers C1 to C5. In one embodiment, the pressures in the pressure chambers C1 to C5 may be measured by pressure sensors.

[0040] The polishing head 7 can apply independent pressures to a plurality of regions of the wafer W. For example, the polishing head 7 can press different regions on the surface of the wafer W against the polishing surface 2a of the polishing pad 2 with different pressures. Therefore, the polishing head 7 can control the film thickness profile of the wafer W to achieve the target film thickness profile.

[0041] In one embodiment, the polishing control unit 30 calculates the respective average polishing rates of a plurality of regions on the wafer W corresponding to the pressure chambers C1 to C4 from the measured values of the film thickness of the wafer W during polishing, calculates the difference between the average polishing rate of each region and a predetermined target polishing rate, and determines the pressure values in the pressure chambers C1 to C4 so that the difference becomes small. For example, when the average polishing rate of the region corresponding to the pressure chamber C1 is lower than the target polishing rate, the pressure in the pressure chamber C1 is increased.

[0042] In other embodiments, the polishing control unit 30 calculates a plurality of average values of the film thicknesses of a plurality of regions on the wafer W corresponding to the pressure chambers C1 to C4 from the measured values of the film thickness of the wafer W during polishing, calculates the difference between the average value of the film thickness of each region and a predetermined target film thickness value that changes as polishing progresses, and determines the target pressure values in the pressure chambers C1 to C4 necessary to eliminate the difference.

[0043] The wafer W is polished under preset polishing conditions. The polishing conditions include the rotational speed of the polishing table 5, the rotational speed of the polishing head 7, the initial pressures in the pressure chambers C1 to C4 of the polishing head 7, the type and flow rate of the polishing liquid supplied to the polishing surface 2a of the polishing pad 2, and the like. If the polishing conditions are constant, the polishing rate (also referred to as the removal rate) of the same type of wafer is generally the same. However, as the polishing pad 2 wears out, the grooves formed in the polishing surface 2a become shallower, and it becomes difficult to hold the polishing liquid on the polishing surface 2a. As a result, even though the polishing conditions are the same, the polishing rate of the wafer decreases. Therefore, when the wear of the polishing pad 2 progresses, it is necessary to replace the polishing pad 2 with a new one.

[0044] The pad life calculation unit 40 shown in FIG. 1 is configured to estimate the life of the polishing pad 2 using the learned model 42. Pressure time series data representing the change in the pressure in the pressure chamber of the polishing head 7 acquired during the polishing of the wafer W is input to the learned model 42. The pad life calculation unit 40 executes calculations according to the algorithm determined by the learned model 42 and determines the life index of the polishing pad 2.

[0045] The pressure in the pressure time series data is the pressure in at least one of the pressure chambers C1 to C4 described above. In the embodiments described below, pressure time series data indicating the pressure change in the pressure chamber C1 is used. However, in other embodiments, pressure time series data indicating the pressure change in the pressure chambers C2, C3, or C4 other than the pressure chamber C1 may be input to the learned model 42. In still other embodiments, a plurality of pressure time series data indicating the changes in the pressures of a plurality of or all of the pressure chambers C1 to C4 may be input to the learned model 42.

[0046] The pressure time series data input to the learned model 42 is data indicating the change in the pressure in the pressure chamber C1 of the polishing head 7 over the polishing time when polishing one wafer. More specifically, the pressure time series data is data indicating the change in the pressure in the pressure chamber C1 from the start to the end of the polishing of one wafer. This pressure time series data can vary depending on the wear state of the polishing pad 2. That is, when the polishing pad 2 is new and there are grooves on the polishing surface 2a, the polishing liquid (e.g., slurry) supplied onto the polishing surface 2a is held in the grooves. Therefore, during the polishing of the wafer W, a sufficient amount of polishing liquid exists between the wafer W and the polishing surface 2a of the polishing pad 2. The polishing head 7 can polish the wafer W at a high polishing rate while maintaining the pressure in the pressure chamber C1 within an appropriate range.

[0047] FIG. 3 is a graph showing an example of pressure time series data indicating the time change in the pressure in the pressure chamber C1 of the polishing head 7 during the polishing of the wafer W when the polishing pad 2 is new. During the polishing of the wafer W, the pressures in the plurality of pressure chambers C1 to C4 (see FIG. 2) of the polishing head 7 change so as to eliminate the variation in the film thickness within the plane of the wafer W and so that the overall film thickness of the wafer W reaches the target film thickness. In accordance with such pressure control, as shown in FIG. 3, the pressure in the pressure chamber C1 fluctuates somewhat but generally remains within an appropriate range.

[0048] FIG. 4 is a graph showing an example of pressure time-series data indicating the change over time of the pressure in the pressure chamber C1 of the polishing head 7 during polishing of the wafer W when the polishing pad 2 is worn to some extent. As the wear of the polishing pad 2 progresses and the grooves in the polishing surface 2a become shallower, it becomes more difficult for the polishing liquid to enter the gap between the wafer W and the polishing surface 2a of the polishing pad 2. As a result, the polishing rate of the wafer W decreases. When the polishing pad 2 is further worn, as shown in FIG. 5, the pressure in the pressure chamber C1 further increases in order to increase the polishing rate.

[0049] Thus, the wear of the polishing pad 2 is reflected in the pressure time-series data indicating the change over time of the pressure in the pressure chamber C1 of the polishing head 7. Therefore, the pad life calculation unit 40 inputs the pressure time-series data acquired during polishing of the wafer W into the learned model 42 (see FIG. 1), and outputs a life index of the polishing pad 2 from the learned model 42.

[0050] The life index of the polishing pad 2 is an index indicating the degree of wear of the polishing pad 2. The operator can determine whether or not to replace the polishing pad 2 based on the life index of the polishing pad 2 calculated by the pad life calculation unit 40. For example, the life index of the polishing pad 2 is the number of wafers (workpieces) that can be polished using the polishing pad 2. In another example, the life index of the polishing pad 2 is an index indicating the ratio of the current usage time of the polishing pad 2 to the life of the polishing pad 2. In yet another example, the life index of the polishing pad 2 is a numerical value (for example, a numerical value from 1 to 10) that directly or indirectly represents the life of the polishing pad 2.

[0051] The learned model 42 is constructed by machine learning executed by the pad life calculation unit 40. The training data used for this machine learning includes training pressure time series data obtained when a large number of wafers were polished in the past using other polishing pads. The training data further includes the life index of the polishing pad, which is the correct label. Examples of machine learning include the SVR method (Support Vector Regression method), the PLS method (Partial Least Squares method), the deep learning method, the random forest method, and the decision tree method. In one example, the learned model 42 is composed of a neural network constructed by the deep learning method.

[0052] FIG. 6 is a schematic diagram showing an example of the learned model 42 constructed using deep learning. The learned model 42 has an input layer 101, a plurality of hidden layers (also referred to as intermediate layers) 102, and an output layer 103. However, the learned model 42 is not limited to the example shown in FIG. 6.

[0053] The construction of the learned model 42 using deep learning is performed as follows. The training pressure time series data is input to the input layer 101 shown in FIG. 6. When the training pressure time series data is input to the input layer 101, the model 42 outputs the life index of the polishing pad from the output layer 103. The pad life calculation unit 40 adjusts the parameters (weights, thresholds, etc.) of each node (neuron) so as to minimize the difference between the life index of the polishing pad output from the output layer 103 and the life index of the polishing pad, which is the correct label. As a result, the model is trained to output an appropriate life index of the polishing pad from the output layer 103 based on the data input to the input layer 101.

[0054] The learned model 42 is constructed by repeating the above machine learning using a plurality of training pressure time series data obtained when polishing a plurality of wafers using a plurality of polishing pads. By performing machine learning using a large number of polishing pads, the accuracy of the life index of the polishing pad 2 output from the learned model 42 can be improved. Therefore, the learned model 42 can accurately estimate the life of the polishing pad 2 from the pressure time series data indicating the pressure change in the pressure chamber C1 of the polishing head 7. The learned model 42 is stored in the storage device 40a of the pad life calculation unit 40.

[0055] The life index of the polishing pad as the correct label included in the training data is obtained as follows. Using at least one polishing pad, polish a plurality of wafers until the polishing pad reaches the end of its life. FIG. 7 is a diagram showing an example of the relationship between the number of wafers and the use time of the polishing pad when polishing a plurality of wafers until one polishing pad reaches the end of its life. In the example shown in FIG. 7, when 1000 wafers are polished, the polishing pad has reached the end of its life. The life index of the polishing pad as the correct label can be represented by the ratio of the number of wafers polished at each time point from the start of use of the polishing pad to the end of the life of the polishing pad to 1000, the number of wafers obtained by subtracting the number of wafers at each time point from 1000 (the number of wafers that can be polished), or a numerical value equivalent thereto. The life index at each time point is associated with the corresponding training pressure time series data obtained at that time point and added to the training data. The training data created in this way is stored in the storage device 40a of the pad life calculation unit 40.

[0056] FIG. 8 is a diagram showing an example of the relationship between the number of wafers and the usage time of each polishing pad when a plurality of polishing pads are used to polish a plurality of wafers until each polishing pad reaches its life. In the example shown in FIG. 8, a plurality of polishing pads are used to obtain training data for machine learning. These polishing pads have the same structure and the same material, but the life of the polishing pads may vary due to external factors such as dressing of the polishing pads. Therefore, in the example shown in FIG. 8, a plurality of polishing pads are used for polishing until they reach their life. Polishing pads A, B, and C have the same structure and the same material, but polishing pad A reaches its life when 1000 wafers are polished, polishing pad B reaches its life when 900 wafers are polished, and polishing pad C reaches its life when 1100 wafers are polished. The life index of the polishing pad, which is the correct label using each polishing pad, is obtained in the same manner as in the example of FIG. 7.

[0057] In polishing for obtaining training data, whether or not the polishing pad has reached its life may be determined, for example, by a skilled operator visually observing the grooves formed on the polishing surface of the polishing pad. In another example, the pad life calculation unit 40 or the operator may determine that the polishing pad has reached its life based on the difference between the film thickness profile of the wafer polished using the polishing pad and the target film thickness profile. For example, when the above difference exceeds a reference value, the pad life calculation unit 40 or the operator can determine that the polishing pad has reached its life. The film thickness profile may be replaced by the uniformity of the film thickness within the wafer surface. In still another example, the pad life calculation unit 40 or the operator may determine that the polishing pad has reached its life when the polishing rate of the wafer polished using the polishing pad falls below a predetermined threshold value.

[0058] In one embodiment, the pad life calculation unit 40 calculates the life index of the polishing pad 2 using the learned model 42 during the wafer polishing process. That is, the pad life calculation unit 40 inputs the pressure time series data related to the polished wafer W into the learned model 42 after polishing the wafer W and before polishing the next wafer, and outputs the life index of the polishing pad 2 from the learned model 42. If the obtained life index of the polishing pad 2 suggests the replacement time of the polishing pad 2, the polishing pad 2 is replaced with a new polishing pad before the next wafer is polished.

[0059] The pressure change in the pressure chamber C1 of the polishing head 7 during the polishing of the wafer W may also be affected by the state of the wafer W being polished and / or the polishing conditions of the wafer W. Therefore, in one embodiment, in order to calculate a more accurate life index of the polishing pad 2, the pad life calculation unit 40 may input polishing data related to the polishing of the wafer W into the learned model 42 in addition to the pressure time series data.

[0060] The polishing data includes at least one of the information of the wafer W and the polishing conditions of the wafer W. Examples of the information of the wafer W include the polishing rate of the wafer W, the polishing time of the wafer W required to reach the target film thickness, the initial film thickness and the target film thickness of the wafer W, the film thickness profile (film thickness distribution) of the wafer W after polishing, and the profile of the polishing amount of the wafer W after polishing. Examples of the polishing conditions of the wafer W include the rotation speeds of the polishing table 5 and the polishing pad 2, the rotation speed of the polishing head 7, and the flow rate of the polishing liquid supplied to the polishing pad 2.

[0061] In one embodiment, the polishing control unit 30 may perform pressure control in each pressure chamber based on film thickness measurement data during polishing (for example, by comparison with a target polishing rate or a target film thickness value) only during a part of the period during polishing. For example, during a fixed polishing condition period from the start of polishing to a predetermined time, the wafer is polished while maintaining a predetermined constant pressure in the pressure chamber, and the profile of the polishing amount (polishing amount distribution), or the average polishing amount, or the average remaining film amount, or the profile of the remaining film (remaining film distribution) obtained within the fixed polishing condition period may be included as polishing data.

[0062] The training data used for machine learning to construct the learned model 42 includes the same type of polishing data as the polishing data input to the learned model 42. That is, the training data includes, in addition to the training pressure time series data, at least one of the information of the wafer and the polishing conditions of the wafer when the training pressure time series data is acquired.

[0063] In one embodiment, the pad life calculation unit 40 is configured to input the cut rate of the polishing pad 2 dressed by the dresser 50 into the learned model 42 in addition to the pressure time series data. The cut rate of the polishing pad 2 is the thickness (amount) of the polishing pad 2 shaved off by the dresser 50 per unit time. The thickness (amount) of the polishing pad 2 shaved off by the dresser 50 is the difference between the height of the polishing surface 2a of the polishing pad 2 before dressing and the height of the polishing surface 2a of the polishing pad 2 after dressing.

[0064] The dressing disk 51 of the dresser 50 has hard abrasive grains (for example, diamond abrasive grains) on its dressing surface 51a. These abrasive grains gradually wear as the dressing of the polishing pad 2 is repeated. Therefore, the cut rate of the polishing pad 2 also gradually changes. When the cut rate of the polishing pad 2 changes, it is assumed that the state of the polishing surface 2a of the dressed polishing pad 2 also changes, which may affect the pressure time series data.

[0065] Therefore, in order to calculate a more accurate life index of the polishing pad 2, the pad life calculation unit 40 inputs the cut rate of the polishing pad 2 into the learned model 42 in addition to the pressure time series data. The training data used for machine learning to construct the learned model 42 includes, in addition to the training pressure time series data, the cut rate of the polishing pad when the training pressure time series data was acquired.

[0066] Furthermore, in one embodiment, the pad life calculation unit 40 may be configured to input, in addition to the pressure time series data, polishing data regarding the wafer W and the cut rate of the polishing pad 2 into the learned model 42. The training data used for machine learning to construct the learned model 42 includes, in addition to the training pressure time series data, the same type of polishing data as the polishing data input into the learned model 42, and the cut rate of the polishing pad when the training pressure time series data was acquired. According to this embodiment, it is expected that the pad life calculation unit 40 can calculate a more accurate life index of the polishing pad 2.

[0067] In the above-described embodiment, the polishing head has a plurality of pressure chambers C1 to C4, but it is also possible to calculate the life index of the polishing pad 2 by machine learning using the pressure time series data of a polishing head having only a single pressure chamber.

[0068] In other embodiments, the polishing control unit 30 calculates the average value of the film thicknesses of a plurality of regions on the wafer W corresponding to the pressure chambers C1 to C4 from the measured value of the film thickness of the wafer W during polishing (i.e., the current film thickness of the wafer W), calculates the difference between the average value of the film thicknesses of each region and the average value of the film thickness of the entire wafer W, and determines the pressure values in the pressure chambers C1 to C4 necessary to eliminate the difference. For example, when the average value of the film thickness of the region corresponding to the pressure chamber C1 is less than the average value of the film thickness of the entire wafer W, the polishing control unit 30 decreases the pressure value of the pressure chamber C1. In another example, when the average value of the film thickness of the region corresponding to the pressure chamber C4 is greater than the average value of the film thickness of the entire wafer W, the polishing control unit 30 increases the pressure value of the pressure chamber C4.

[0069] During machine learning and estimation of the life index, the pressure time series data of two different pressure chambers may be input into the input layer of the model. The pressure time series data of two different pressure chambers, such as the groove depth of the polishing pad, may show different behaviors due to changes in the pad state such as the groove depth of the polishing pad. For example, when the grooves of the polishing pad become shallower, the slurry supply to the center of the wafer is particularly insufficient, so the polishing rate at the center of the wafer tends to decrease. Therefore, prior to the pressure chamber on the outer periphery of the wafer, the pressure in the pressure chamber at the center of the wafer rises during polishing, and the uniformity of polishing is maintained. Thus, by inputting the pressure time series data of two different pressure chambers into the learned model, a more accurate life index can be output.

[0070] The above-described embodiments are described for the purpose of enabling a person having ordinary skill in the technical field to which the present invention pertains to practice the present invention. Various modifications of the above embodiments can be naturally made by those skilled in the art, and the technical idea of the present invention can also be applied to other embodiments. Therefore, the present invention is not limited to the described embodiments, but is to be construed in the broadest scope in accordance with the technical idea defined by the claims.

Explanation of Reference Numerals

[0071] W Wafer 2 Polishing Pad 2a Polishing Surface 5 Polishing Table 5a Table Shaft 7 Polishing Head 8 Slurry Supply Nozzle 14 Support Shaft 16 Polishing Head Swing Arm 18 Polishing Head Shaft 21 Table Rotation Motor 24 Film Thickness Sensor 30 Polishing Control Unit 40 Pad Life Calculation Unit 42 Learned Model 50 Dressing Tool 51 Dressing Disk 51a dressing surface 52 dresser shaft 55 dresser swing arm 61 head body 62 retainer ring 64 elastic membrane 66 elastic membrane 70 rotary joint C1, C2, C3, C4, C5 pressure chambers F1, F2, F3, F4, F5 gas transfer lines R1, R2, R3, R4, R5 pressure regulators

Claims

1. An elastic film that forms a pressure chamber provided in a polishing head presses a workpiece against a polishing surface of a polishing pad to polish the workpiece, during polishing of the workpiece, while measuring the film thickness of the workpiece, based on the measured value of the film thickness, controlling the pressure in the pressure chamber, inputting pressure time-series data representing the change in the pressure during polishing of the workpiece into a learned model, and outputting a life index of the polishing pad from the learned model. A method for estimating the life of a polishing pad.

2. The method for estimating the life of a polishing pad according to claim 1, wherein, in addition to the pressure time-series data, polishing data related to polishing of the workpiece is input into the learned model.

3. The method for estimating the life of a polishing pad according to claim 2, wherein the polishing data includes at least one of information on the workpiece and polishing conditions of the workpiece.

4. The method for estimating the life of a polishing pad according to claim 1, wherein, in addition to the pressure time-series data, a cut rate of the polishing pad dressed by a dresser is input into the learned model.

5. The step of inputting the pressure time-series data into the learned model and outputting a life index of the polishing pad from the learned model is performed after polishing of the workpiece and before polishing the next workpiece. The method for estimating the life of a polishing pad according to claim 1.

6. The pressure chamber is a plurality of pressure chambers, the step of controlling the pressure in the pressure chamber is a step of controlling the pressure in the plurality of pressure chambers based on the measured value of the film thickness while measuring the film thickness of the workpiece during polishing of the workpiece, the step of inputting the pressure time-series data into a learned model is a step of inputting a plurality of pressure time-series data respectively representing changes in the pressure in the plurality of pressure chambers during polishing of the workpiece into the learned model. The method for estimating the life of a polishing pad according to any one of claims 1 to 5.

7. A polishing head having a pressure chamber formed by an elastic film, the elastic film pressing a workpiece against a polishing surface of a polishing pad to polish the workpiece, a film thickness sensor for measuring the film thickness of the workpiece, a polishing control unit for controlling the pressure in the pressure chamber during polishing of the workpiece based on the measured value of the film thickness A polishing apparatus comprising a pad life calculation unit that inputs pressure time-series data representing changes in the pressure during polishing of the workpiece into a learned model and outputs a life index of the polishing pad from the learned model.

8. The polishing apparatus according to claim 7, wherein the pad life calculation unit is configured to input, in addition to the pressure time-series data, polishing data related to polishing of the workpiece into the learned model.

9. The polishing apparatus according to claim 8, wherein the polishing data includes at least one of information on the workpiece and polishing conditions of the workpiece.

10. The polishing apparatus further includes a dresser that dresses the polishing surface of the polishing pad, The polishing apparatus according to claim 7, wherein the pad life calculation unit is configured to input, in addition to the pressure time-series data, a cut rate of the polishing pad dressed by the dresser into the learned model.

11. The polishing apparatus according to claim 7, wherein the pad life calculation unit is configured to input the pressure time-series data into the learned model and output a life index of the polishing pad from the learned model after polishing the workpiece and before polishing the next workpiece.

12. The pressure chambers are a plurality of pressure chambers, The polishing control unit is configured to control the pressure in the plurality of pressure chambers based on a measured value of the film thickness while measuring the film thickness of the workpiece during polishing of the workpiece, The polishing apparatus according to any one of claims 7 to 11, wherein the pad life calculation unit is configured to input a plurality of pressure time-series data respectively representing changes in the pressure in the plurality of pressure chambers during polishing of the workpiece into a learned model.

Images