Interplaten notch finder for detecting edge defects

Abstract

A polishing station, includes a platen, a carrier head, a sensor assembly, and a controller. The carrier head includes a membrane, a retaining ring disposed around a first membrane surface. The retaining ring and first membrane surface define an edge region of the carrier head. The sensor assembly is disposed radially outward of the platen. The carrier head is configured to translate the edge region over the sensor assembly. The sensor assembly includes a body, a fluid channel disposed through the body, and a sensor disposed in the bod. The sensor includes an orientation aligned with an outlet of the fluid channel and is configured to detect a signal. The controller is in communication with the sensor and the carrier head. The controller is configured to identify a characteristic of the carrier head based on the signal and determine a state of the carrier head based on the characteristic.

Description

PATENTAttorney Docket No.: 44025033W001INTERPLATEN NOTCH FINDER FOR DETECTING EDGE DEFECTSBACKGROUNDField

[0001] The present disclosure relates to chemical mechanical polishing (CMP), and more specifically to detecting an orientation of a substrate during a CMP process.Description of the Related Art

[0002] An integrated circuit is typically formed on a substrate by the sequential deposition of conductive, semiconductive, and / or insulative layers on a semiconductor substrate. A variety of fabrication processes require planarization of a layer on the substrate. For example, one fabrication step involves depositing a filler layer over a non-planar surface and planarizing the filler layer. For certain applications, the filler layer is planarized until the top surface of a patterned layer is exposed. For example, a metal layer can be deposited on a patterned insulative layer to fill trenches and holes in the insulative layer. After planarization, the remaining portions of the metal in the trenches and holes of the patterned layer form vias, plugs, and lines to provide conductive paths between integrated circuits (ICs) on the substrate. As another example, a dielectric layer can be deposited over a patterned conductive layer, and then planarized to enable subsequent photolithographic steps.

[0003] Chemical mechanical polishing (CMP) is one accepted method of planarization. This planarization method typically requires that the substrate be mounted on a carrier head. The exposed surface of the substrate, the surface with the layer deposition, is typically placed against a rotating polishing pad. The carrier head provides a controllable load on the substrate to urge it against the polishing pad. A polishing slurry with abrasive particles is typically supplied to the surface of the polishing pad and spreads in between the substrate and the polishing pad. The polishing pad and the carrier head each rotate at a constant rotational speed and the abrasive slurry removes material from one or more of the layers.

[0004] Conventional CMP operations, however, cannot determine the rotational orientation of the substrate relative to the carrier head, eccentricity of a substrate or the carrier head, defects at an edge of a substrate, or other information while the substrate is being polished. Thus, issues may go undetected during polishing.PATENTAttorney Docket No.: 44025033W001Therefore, there is a need in the art to determine and detect issues with the substrate and / or carrier head in-situ to improve the analysis of a CMP process.SUMMARY

[0005] Embodiments described herein generally relate to systems and methods used for apparatus, system, and methods for in-line post polish cleaning of substrates, such as semiconductor substrates. More particularly, embodiments herein provide for systems and methods using cleaning modules and a cleaning tank to allow for more efficient substrate cleaning.

[0006] In an embodiment, a polishing station, includes a platen, a carrier head, a sensor assembly, and a controller. The carrier head includes a membrane, a retaining ring disposed around a first membrane surface. The retaining ring and first membrane surface define an edge region of the carrier head. The sensor assembly is disposed radially outward of the platen. The carrier head is configured to translate the edge region over the sensor assembly. The sensor assembly includes a body, a fluid channel disposed through the body, and a sensor disposed in the bod. The sensor includes an orientation aligned with an outlet of the fluid channel and is configured to detect a signal. The controller is in communication with the sensor and the carrier head. The controller is configured to identify a characteristic of the carrier head based on the signal and determine a state of the carrier head based on the characteristic.

[0007] In another embodiment, a method of monitoring a carrier head, includes translating an edge region of a carrier head over a sensor assembly, detecting a signal with the sensor assembly, and determining, with a controller, a characteristic of the carrier head based on the signal. The characteristic includes at least one of a substrate orientation, a substrate presence, a carrier head runout, a concentricity of the substrate relative to a retaining ring, or a life of the retaining ring.

[0008] In another embodiment, a method of monitoring a carrier head includes translating an edge region of a carrier head over a sensor assembly, directing a light beam towards an edge of a substrate as the substrate rotates over the sensor assembly, detecting a signal with the sensor assembly, and determining, with a controller, a characteristic of the carrier head based on a waveform of the signal. The edge includes a reference element. The characteristic includes at least one of aPATENTAttorney Docket No.: 44025033W001 presence of the substrate within the carrier head, a carrier head runout, a substrate issue, a substrate edge condition, a substrate type, a device pattern, a concentricity of the substrate relative to a retaining ring, a contaminant presence, or a retaining ring life.BRIEF DESCRIPTION OF THE DRAWINGS

[0009] So that the manner in which the above recited features of the present disclosure can be understood in detail, a more particular description of the disclosure, briefly summarized above, may be had by reference to embodiments, some of which are illustrated in the appended drawings. It is to be noted, however, that the appended drawings illustrate only exemplary embodiments of the disclosure and are therefore not to be considered limiting of its scope, as the disclosure may admit to other equally effective embodiments.

[0010] Figure 1 depicts a schematic top view of an exemplary chemical mechanical polishing (CMP) system according to one or more embodiments described herein.

[0011] Figure 2 depicts a schematic sectional view of an exemplary polishing station of the CMP system from Figure 1 according to one or more embodiments described herein.

[0012] Figures 3A and 3B illustrate top views of a platen with a carrier head and a substrate disposed thereon according to one or more embodiments described herein.

[0013] Figure 4 is a flow diagram of a method of monitoring a carrier head during operation according to one or more embodiments described herein.

[0014] Figure 5 is a flow diagram of a method of monitoring a carrier head during operation according to one or more embodiments described herein.

[0015] Figure 6 illustrates a waveform formed by a corresponding signal according to one or more embodiments described herein.

[0016] Figure 7 illustrates a waveform formed by a corresponding signal according to one or more embodiments described herein.PATENTAttorney Docket No.: 44025033W001

[0017] Figure 8 illustrates a waveform formed by a corresponding signal according to one or more embodiments described herein.

[0018] Figure 9 illustrates a waveform formed by a corresponding signal according to one or more embodiments described herein.

[0019] Figure 10 illustrates a waveform formed by a corresponding signal according to one or more embodiments described herein.

[0020] Figure 11 illustrates a waveform formed by a corresponding signal according to one or more embodiments described herein.

[0021] To facilitate understanding, identical reference numerals have been used, where possible, to designate identical elements that are common to the figures. It is contemplated that elements and features of one embodiment may be beneficially incorporated in other embodiments without further recitation.DETAILED DESCRIPTION

[0022] An apparatus and methods for determining the characteristics of a carrier head and a substrate in real time during polishing are disclosed herein. The characteristics are used to improve the evaluation of chemical mechanical polishing (CMP) processes, such as by allowing for a determination of the rotational speed of a substrate during polishing, determining if there is an concentricity issue and other potential issues within the carrier head that can be addressed, thereby reducing excursions, reducing tool downtime, and increasing throughput.

[0023] Early detection of issues within a carrier head enhance throughput by preventing damage to substrates. Embodiments of the present disclosure provide examples of a sensor assembly that detects a signal from light reflected from an edge region of the carrier head before and after polishing operations. A waveform is generated based on the detected signal and compared to other stored waveforms that correlate to various characteristics. Comparing the generated waveform to the stored waveforms can indicate an eccentricity issue with the carrier head or the edge ring, a concentricity issue with a substrate within the carrier head, a remaining service life of the edge ring, a chipped or damaged substrate, or any combination thereof.PATENTAttorney Docket No.: 44025033W001Comparing the generated waveform to the stored waveforms also enables identification of a device on the substrate, a substrate identifier, a substrate material, a presence of a substrate in the carrier head or any combination thereof.

[0024] Figure 1 is a top plan view illustrating one embodiment of a CMP system 100. The CMP system 100 includes a factory interface module 102, a cleaner 104, a polishing module 106, and a controller 190. A substrate 115, such as a silicon wafer with one or more layers deposited thereon, is processed within the CMP system 100 to polish a front surface of the substrate 115.

[0025] A wet robot 108 is provided to transfer the substrates 115 between the factory interface module 102 and the polishing module 106. The wet robot 108 may also be configured to transfer the substrates 115 between the polishing module 106 and the cleaner 104. The factory interface module 102 includes a dry robot 110 which is configured to transfer the substrates 115 between one or more cassettes 114, one or more transfer platforms 116, one or more metrology stations 117, and one or more pre-aligner stations 118 of the factory interface 102. Substrates 115 are loaded into the CMP system 100 via the cassettes 114. In one embodiment depicted in Figure 1 , four substrate storage cassettes 114 are shown. The dry robot 110 within the factory interface 102 has sufficient range of motion to facilitate transfer between the four cassettes 114 and the one or more transfer platforms 116. Optionally, the dry robot 110 may be mounted on a rail or track 112 to position the robot 110 laterally within the factory interface module 102. The dry robot 110 additionally is configured to receive the substrates 115 from the cleaner 104 and return the clean polished substrates to the substrate storage cassettes 114.

[0026] Figure 1 shows an exemplary polishing module 106 that includes a plurality of polishing stations 124 on which the substrates 115 are polished while being retained in a carrier head 210 (e.g., polishing head). Each polishing station 124 includes a conditioning assembly 132, a first fluid delivery arm 134 and a second fluid delivery arm 160. While the polishing module 106 is shown having three polishing stations 124, the polishing module 106 may have more than three polishing stations 124. For example, the polishing module 106 may have a two pairs of polishing stations 124, each pair of stations 124 processing a substrate 115 independently ofPATENTAttorney Docket No.: 44025033W001 the other pair. The polishing stations 124 are sized to interface with one or more carrier heads 210 to facilitate polishing the substrate 115. The carrier heads 210 are coupled to a carriage (not shown) that is mounted to an overhead track 128 that is shown in phantom in Figure 1. The overhead track 128 allows the carriage to be selectively positioned around the polishing module 106 which facilitates positioning of the carrier heads 210 selectively over the polishing stations 124 and a load cup 122. In the embodiment depicted in Figure 1 , the overhead track 128 has a circular configuration which allows the carriages retaining the carrier heads 210 to be selectively and independently rotated over and / or clear of the load cups 122 and the polishing stations 124. Additionally, the overhead tracks 128 facilitate the carriage sweeping the rotating carrier heads 210 relative to a polishing station 124 during polishing. The polishing stations 124 will be described in greater detail in relation to Figure 2.

[0027] Each polishing station 124 includes a polishing pad 204 having a polishing surface (e.g., a polishing surface 204A in Figure 2) capable of polishing a substrate 115. The polishing pad 204 is supported on a platen (e.g., a platen 202 in Figure 2) which rotates the polishing pad 204 during processing. Different polishing pads 204 may be used at different polishing stations 124 to control the material removal of the substrate 115.

[0028] Each polishing station 124 may include the conditioning assembly 132. In one embodiment, the conditioning assembly 132 may comprise a pad conditioning assembly 140 which dresses the polishing surface of the polishing pad 204 by removing polishing debris and opening the pores of the polishing pad 204 by use of a pad condition disk 133 coupled to a condition disk arm 135.

[0029] Each polishing station 124 includes the first fluid delivery arm 134. The first fluid delivery arm 134 may deliver a first fluid to the polishing pad 204, such as a slurry. The first fluid disperses over the polishing surface 204A of the polishing pad 204 to facilitate polishing. The first fluid may be one or more fluids to interact with the front surface of the substrate 115 during polishing. The one or more first fluids may be delivered to the first fluid delivery arm 134 from a fluid source 182. The one or more first fluids may be a polishing fluid and / or a relatively high pressure stream of a cleanerPATENTAttorney Docket No.: 44025033W001 fluid, e.g., deionized water. One example of a first fluid can include a polishing fluid that includes, but is not limited to one or more surfactants, one or more chelating agents, one or more oxidizers, one or more corrosion inhibitors, one or more polar solvents, and deionized water. The composition may also further include one or more pH adjusting agents and / or abrasive particles. Abrasive particles which may be used in CMP compositions include, but are not limited to, alumina (AI2O3), silica (SiC>2), titania (TiC ), or ceria (CeO2) particles, or any other abrasives known in the art and used in conventional CMP compositions.

[0030] The second fluid delivery arm 160 may comprise a second arm 162 to selectively deliver a second fluid at a radial position on the polishing surface 204A of the pad 204 that will be rotated underneath the substrate 115 being polished on the pad 204. The second fluid may be repeatedly delivered, such as by pulsing, to target a targeted area on the front surface of the substrate 115 during polishing.

[0031] The second fluid may be one or more fluids, such a polishing fluid, various chemical components, and / or deionized water. The various chemical components can include, but are not limited to one or more surfactants, one or more chelating agents, one or more oxidizers, one or more corrosion inhibitors, one or more polar solvents, and one or more pH adjusting agents. Each polishing station 124 shown in Figure 1 includes the second fluid delivery arm 160. In some embodiments, only one of the polishing stations 124 includes the second fluid delivery arm 160, such as the second polishing station 124.

[0032] At least one load cup 122, such as the two load cups 122 shown in Figure 1 , is near the lower right corner of the polishing module 106 between the polishing stations 124 closest to the wet robot 108. The load cups 122 may serve multiple functions, including washing the carrier head 210, receiving the substrate 115 from the wet robot 108, washing the substrate 115, and loading the substrate 115 into the carrier heads (e.g., a carrier head 210 in Figure 2).

[0033] In certain embodiments, the factory interface module 102 can also include the pre-aligner 118 to position the substrate 115 in a known and desirable rotational orientation. The pre-alignment of the substrate 115 to a desired rotational orientation allows the substrate 115 to be transferred to the load cup 122 having a knownPATENTAttorney Docket No.: 44025033W001 rotational orientation. Thus, the carrier head 210 is able to retrieve the substrate 115 at a known rotational orientation relative to the carrier head 210. For example, the pre-aligner 118 may include a reference mark detection system, such as an optical interrupter sensor (not shown), to sense when the reference mark is at a specific angular position.

[0034] In certain embodiments, the substrate 115 is placed in the metrology station 117 by the dry robot 110 prior to placing the substrate 115 on the transfer platform 116. For example, the dry robot 110 may transfer the substrate 115 from the prealigner 118 to the metrology station 117. The metrology station 117 is used to measures various aspects of the substrate 115. The metrology station 117 may use an optical, eddy current, resistive, or other sensors to measure the substrate 115. For example, the metrology station 117 may measure a thickness of the upper layer on the patterned surface of the substrate 115. The controller 190 receives the measurements which may be used to facilitate processing the substrate 115 within the CMP system 100. The dry robot 110 may transfer the substrate 115 to the transfer platform 116 after the substrate 115 is measured in the metrology station 117.

[0035] The wet robot 108 is configured to transfer the substrate 115 from the transfer platform 116 to one of the load cups 122. A rinsed-clean carrier head 210 is moved above the load cup 122 with the unpolished substrate 115. The unpolished substrate 115 is thereafter chucked to the carrier head 210, which then moves to a position above the pad 204 of a polishing station 124 to begin the CMP process.

[0036] The controller 190 controls aspects of the CMP system 100 during a CMP process (e.g., polishing process, polishing operation, polishing). In certain embodiments, the controller 190 is one or more programmable digital computers executing digital control software. The controller 190 can include a CPU (e.g., processor) 191 situated near the polishing apparatus, e.g., a programmable computer, such as a personal computer. The controller can include a memory 192 and support circuits 193. The controller 190 can, for example, coordinate rotation of the polishing pad 204 and the carrier head 210, as well as the position of the carrier head 210 along a sweep path, to perform the desired CMP process and to facilitate monitoring for the endpoint of the CMP process. Additionally, the controller 190 canPATENTAttorney Docket No.: 44025033W001 generate waveforms from substrates in current production and compare those generated waveforms against waveforms stored in the memory 192. The CMP process system 100 is powered by power source 180, such as an electric power source configured to supply electric power to the components of the CMP process system 100.

[0037] The platen 202 and the carrier head 210 each have a rotation sensor such as an encoder, to determine their rotational position during the CMP operation. As shown in Figure 1 , a platen encoder 195, a first head encoder 196, and a second head encoder 197 are integrated into the controller 190. The platen encoder 195 is configured to determine the rotational (e.g., angular) orientation of the platen 202 and the pad 204. The first head encoder 196 is configured to determine the rotational orientation of each carrier head 210. The second head encoder 197 is configured to determine the location of each carrier head 210 above the polishing pad. Thus, the controller 190 is able to determine and track the rotational orientation of the carrier head 210 with respect to the platen 202 during the CMP process. In some embodiments, each carrier head 210 has its own dedicated first and second head encoders 196, 197. In further embodiments, the controller 190 may calculate a rotation rate of the carrier head 210 and / or platen 202 and polishing pad 204 using the encoder and an internal timing element.

[0038] The controller 190 is in communication with a sensor assembly 250 (Figure 2) and the carrier head 210. The controller 190 is configured to identify a characteristic of the carrier head based on a signal and determine a state of the carrier head 210 based on the characteristic. This is discussed in more detail below.

[0039] The controller 190 can control the rotational rate of the carrier head 210, the platen 202, and the position of the carrier head 210 along a sweep path. Additionally, the controller 190 can control the rotational rate of the platen 202 and the movement of the carrier head 210 along the sweep path on and off the platen 202. In some embodiments, the controller 190 can control the rotational speed and position of the carrier head 210 and the rotational speed of the pad 204 relative to each other.

[0040] The substrate 115 may be polished in one or more of the polishing stations 124. For example, a carrier head 210 may retrieve an unpolished substrate 115 fromPATENTAttorney Docket No.: 44025033W001 a load cup 122. The carrier head 210 and substrate 115 chucked thereto are then moved to a first polishing station 124, such as the polishing station 124 in the upper right corner of the polishing module 106 closest to the cleaner 104. The substrate 115 is then subjected to a CMP polishing operation on the first polishing station 124, such as removing a first layer formed on the substrate 115. Once the substrate 115 is done polishing in the first polishing station 124, then the carrier head 210 moves the substrate 115 to a second polishing station 124 (e.g., the polishing station 124 in the upper left corner of the polishing module 106) for additional CMP polishing. For example, the second polishing station 124 may polish the surface of the substrate 115 to form trench lines of a desired height. In some embodiments, the carrier head 210 and substrate 115 may optionally be transferred from the second polishing station 124 to a third polishing station 124 (e.g., the polishing station 124 in the lower left corner of the polishing module 106) to subject the substrate 115 to additional polishing.

[0041] After polishing, the carrier head 210 moves the polished substrate 115 chucked thereto above a load cup 122 where the polished substrate 115 is thereafter placed into the load cup 122. The wet robot 108 transports the polished substrate 115 from the load cup 122 to a cleaning chamber in the cleaner 104, where slurry residues and other contaminants that have accumulated on the surface of the substrate 115 during polishing are removed. In the embodiment depicted in Figure 1 , the cleaner 104 includes two pre-clean modules 144, two megasonic cleaner modules 146, two brush box modules 148, two spray jet modules 150, and two dryers 152. The dry robot 110 then removes the substrate 115 from the cleaner 104. In some embodiments, the dry robot 110 transfers the substrate 115 to the metrology station 117 to be measured again. Finally, the dry robot 110 returns the substrate 115 to one of the cassettes 114.

[0042] Figure 2 illustrates a schematic cross-sectional view of a polishing station 124 of the CMP system 100 of Figure 1. As shown, the polishing station 124 further includes a sensor assembly 250. A substrate 115 disposed in the carrier head 210 is shown engaged with the polishing surface 204A of the pad 204 that is coupled to the platen 202. The platen 202 and polishing pad 204 rotate about a platen axis 205. While shown as the carrier head 210 pressing the substrate 115 against the pad 204,PATENTAttorney Docket No.: 44025033W001 the carrier head 210 can also hold the substrate away from the polishing surface 204A and over the sensor assembly 250.

[0043] The carrier head 210 is disposed facing the platen 202 and the polishing pad 204 and is configured to impose different pressures against a backside surface of a substrate 115 that is disposed between the carrier head 210 and the polishing pad 204.

[0044] The carrier head 210 includes a membrane 212 and a retaining ring 218 disposed around the membrane 212. The membrane 212 includes a first membrane surface 213. The first membrane surface 213 contacts the substrate 115. The retaining ring 218 and first membrane surface 213 define an edge region 215 of the carrier head 210. The edge region 215 is the radially outward region of the carrier head 210 where the membrane 212 is proximate the retaining ring 218.

[0045] As illustrated the carrier head 210 has translated to the edge of the platen 202 and the edge region 215 hangs out over and is aligned with the sensor assembly 250. The edge region 215 hangs out over an outer most radial surface of the pad 204 and / or platen 202 so the sensor assembly 250 can analyze the edge region 215 to determine characteristics of the carrier head 210 and substrate 115.

[0046] The sensor assembly 250 is disposed radially outward of the platen 202 and pad 204. The sensor assembly 250 includes a body 251 , a fluid channel 253 disposed through the body 251 , and a sensor 255. The body 251 includes an inlet 257 and an outlet 259. The fluid channel 253 fluidly couples the inlet 257 and the outlet 259. The sensor assembly 250 is configured to direct a sensor fluid through the inlet 257, through the fluid channel 253, out the outlet 259 and towards the edge region 215 of the carrier head 210.

[0047] The sensor 255 is disposed in the body 251 and has an orientation aligned with the outlet 259 of the fluid channel 253. The sensor 255 is configured to transmit and detect a signal 263. The sensor 255 of the sensor assembly 250 is in electrical communication with the controller 190, so the controller 190 can determine a characteristic of the carrier head 210 and place the carrier head in a state. In some embodiments, the sensor 255 is an optical sensor that transmits a 4 millimeterPATENTAttorney Docket No.: 44025033W001 diameter photonic signal through a water column formed between the sensor assembly 250 and the carrier head 210 by liquid leaving the fluid channel 253.

[0048] In some embodiments, the sensor 255 directs an optical signal to one or more of the edge region 215, the substrate 115, a substrate edge 265, the first membrane surface 213, a process surface 266 of the substrate 115, or the retaining ring 218. The sensor 255 detects characteristics of the carrier head 210 and the substrate 115 disposed therein as the carrier head 210 translates over the sensor assembly 250.

[0049] While the sensor assembly 250 is shown as an optical sensor, the sensor assembly 250 may be any other suitable sensor capable of monitoring changes in the carrier head 210 and the substrate 115 during the CMP process. For example, the sensor assembly 250 may be an eddy current sensor, laser displacement sensor, or an inductive current sensor.

[0050] The carrier head 210 translates the substrate 115 over the polishing surface 204A of the polishing pad 204. The retaining ring 218 surrounds the substrate 115 and holds the substrate 115 within the carrier head 210 during a polishing operation. The carrier head 210 rotates about a carrier head axis 216 while the flexible membrane 212 urges the substrate 115 against the polishing surface 204A of the polishing pad 204. The carrier head 210 rotates at about 20 rotations per minute (RPM) to about 30 RPM, for example, about 25 RPM. During polishing, a downforce urges the retaining ring 218 against the polishing pad 204 to improve the polishing process uniformity and prevent the substrate 115 from slipping out from under the carrier head 210. In certain embodiments, the carrier head 210 includes a shaft 211 which has an axis that is collinear with carrier head axis 216.

[0051] The fluid channel 261 of the sensor assembly 250 is coupled to a fluid source 267 and the outlet 259 of the fluid channel 261 is directed towards the carrier head 210. The outlet 259 of the fluid channel is oriented about parallel to the platen axis 205.PATENTAttorney Docket No.: 44025033W001

[0052] In some embodiments, the sensor assembly 250 includes a window 269. The window 269 is disposed between the sensor 255 and the fluid channel 261 and allows the signal 263 to pass there through.

[0053] The outlet of 259 the fluid channel 261 is disposed proximate the polishing surface 204A of the pad 204. For example, the carrier head 210 translates from a first position over the platen 202 to a second position, as illustrated in Figure 2, where the edge region 215 extends outward of a radial edge 271 of the platen 202 and pad 204. The carrier head 210 can translate over the sensor assembly 250 before a polishing operation, during a polishing operation, after a polishing operation, or any combination thereof. As fluid leaves the outlet 259, the signal 263 is able to translate through the fluid as the signal 263 travels to and from the sensor 255. In some embodiments, the fluid is liquid water, for example, deionized water. The signal 263 reflects from at least one or more of the substrate 115, the substrate edge 265, the first membrane surface 213, the retaining ring 218 or any combination thereof. The sensor 255 detects an intensity of the reflected signal and communicates that intensity to the controller 190 (Figure 1 ).

[0054] Figures 3A and 3B illustrate schematic top views of the platen 202, the polishing pad 204, the carrier head 210, and the substrate 115 disposed therein according to one or more embodiments described herein.

[0055] The substrate 115 typically has a reference element 301 , such as a notch, flat edge, or other type of feature that can be used to identify crystalline orientations of the substrate 115 and note a rotational orientation of the substrate 115 relative to the carrier head axis 216 (Figure 2). The reference element 301 is disposed on the substrate edge 265.

[0056] The signal 263 reflects from the substrate 115 and the intensity of the signal 263 changes when the reference element 301 passes over the signal. The sensor assembly 250 (Figure 2) is configured to detect the reference element 301 disposed on the edge 265 of the substrate 115.

[0057] The controller 190 (Figure 1 ) uses the signal 263 to determine a characteristic of the carrier head 210 and place the carrier head 210 in a state. ForPATENTAttorney Docket No.: 44025033W001 example, the controller 190 is further configured to identify a concentricity C1 of the substrate 115 within the carrier head 210. The concentricity C1 includes the concentricity of the carrier head 210 and the concentricity of the substrate 115 relative to the retaining ring 218.

[0058] As shown in Figure 3A, the substrate 115 is concentric with the carrier head 210 and the retaining ring 218 so the controller 190 determines the carrier head 210 has a concentric characteristic and places the carrier head 210 in an operational state. In some embodiments, the controller 190 determines the carrier head 210 has a concentric characteristic based on a signal from the retaining ring 218 without the need for a substrate 115 and places the carrier head 210 in an operational state. In contrast, as shown in Figure 3B, the substrate 115 is not concentric with the carrier head 210 or retaining ring 218. The controller 190 determines the carrier head 210 has a non-concentric characteristic and places the carrier head 210 in an error state.

[0059] In addition to the signal 263 being directed at the substrate edge 265, the carrier head 210 can translate any one of the retaining ring 218, the process surface 266, or the first membrane surface 213 (Figure 2) over the signal 263. The controller 190 (Figure 1 ) is also able to utilize the intensity of the reflected signal 263 to determine other characteristics. For example, other characteristics include one or more of a substrate presence, a carrier head runout, a substrate issue, a substrate type, a device pattern, a contaminant presence, or a life of the retaining ring.

[0060] Figure 4 is a flow diagram of a method 400 of monitoring a carrier head during operation according to one or more embodiments described herein.

[0061] At operation 401 , the carrier head 210 translates the edge region 215 over the sensor assembly 250 similar to the illustration in Figure 2. Translating the edge region 215 over the sensor assembly 250 enables the sensor assembly to analyze one or more surfaces within the edge region 215. For example, the sensor assembly 250 is able to analyze the substrate 115, the substrate edge 265, the first membrane surface 213, the process surface 266 of the substrate 115, the retaining ring 218, or a combination thereof.PATENTAttorney Docket No.: 44025033W001

[0062] At operation 403, the sensor assembly 250 transmits and detects the signal 263 after reflection from a surface in the edge region 215. The signal 263 is detected while the substrate 115 is rotated by the carrier head 210. A liquid flows from the outlet 259 of the sensor assembly 250 and is directed towards the carrier head 210, thereby allowing the signal 263 to be detected through the liquid. The liquid prevents diffraction and deflection of the signal 263 by liquid droplets, particles, or debris as the signal 263 is transmitted between the sensor 255 and the edge region 215. In some embodiments, detecting the signal 263 includes directing light from the sensor assembly 250 toward the carrier head 210 and detecting the signal 263 in the form of reflected light, as the light reflects from a surface of the edge region 215 of the carrier head 210.

[0063] At operation 405, the controller 190 determines a characteristic of the carrier head 210 based on the signal 263. The characteristic of the carrier head 210 includes at least one of a substrate 115 presence, a carrier head 210 runout, a concentricity of the substrate 115 relative to the retaining ring 218, or a life of the retaining ring 218. In some embodiments, the controller 190 creates a waveform based on the signal 263 detected by the sensor 255. The waveform is based on the measured intensity of the signal 263. Exemplary waveforms are described below in reference to Figures 6-11 .

[0064] The substrate presence characteristic is whether the substrate 115 is disposed within the carrier head 210. The carrier head runout characteristic is when the carrier head 210 has an eccentricity outside of a predetermined threshold. In some embodiments, the carrier head 210 eccentricity is outside of the eccentricity threshold when a determined precession of the substrate 115 is 3 millimeters or greater. When the signal 263 is directed towards the retaining ring 218, variances in the waveform enable the controller 190 to indicate the carrier head 210 has an eccentricity outside of the predetermined threshold. For example, the threshold for carrier head 210 eccentricity is about 1.5 millimeters or less when the retaining ring 218 has an inner diameter of about 301 millimeters. In another example, the threshold for carrier head 210 eccentricity is about 3.5 millimeters or less when the retaining ring 218 has an inner diameter of about 305 millimeters. In some embodiments, the carrier head 210 eccentricity threshold will be the eccentricity of the retaining ring 218PATENTAttorney Docket No.: 44025033W001 relative to the head carrier axis 216 such that the threshold is about 0.5 millimeters or less. In some embodiments, the total eccentricity is the eccentricity of the substrate 115 and the eccentricity of the retaining ring 218 relative to the carrier head axis 216. The concentricity of the substrate relative to a retaining ring characteristic is when the substrate 115 is not concentric with the carrier head axis 216. For example, the substrate 115 has translated due to precession outside of an acceptable threshold. The life of the retaining ring characteristic is when the controller 190 determines that waveform from the signal 263 directed towards the retaining ring 218 is similar to a stored waveform that indicates retaining ring 218 life is outside of a predetermined threshold. The retaining ring 218 life is determined as a function of groove depth. For example, the retaining ring 218 life is determined by the reduction in groove depth as the depth approaches a 2 millimeter threshold.

[0065] In some embodiments, the method 400 can also include using the controller 190 to determine a carrier head 210 state. For example, the controller 190 can place the carrier head 210 in an operational state when a characteristic of the carrier head 210 is within a predetermined threshold and the controller 190 can place the carrier head 210 in an error state when a characteristic of the carrier head 210 is outside of a predetermined threshold as described herein. For example, the controller 190 can place the carrier head 210 in an error state when the eccentricity of the carrier head 210 is 0.5 millimeters or greater. The controller 190 can instruct the carrier head 210 to perform a polishing operation or diagnostic operation when the carrier head state is in the operational state. The controller 190 can also instruct the carrier head 210 to perform a notification operation when the carrier head state is the error state. In some embodiments, the error state includes one or more of the carrier head 210 runout is outside of a carrier head runout threshold, the concentricity of the substrate relative to a retaining ring is outside of a concentricity threshold, or the retaining ring 218 is outside of a retaining ring life threshold. For example, the error state includes the retaining ring 218 has been reduced by 1 millimeter or more due to wear.

[0066] Figure 5 is a flow diagram of a method 500 of monitoring the carrier head 210 during operation according to one or more embodiments described herein.PATENTAttorney Docket No.: 44025033W001

[0067] At operation 501 , the carrier head 210 translates the edge region 215 over the sensor assembly 250 similar to the illustration in Figure 2. Translating the edge region 215 over the sensor assembly 250 enables the sensor assembly to analyze one or more surfaces within the edge region 215. For example, the sensor assembly 250 is able to analyze the substrate 115, the substrate edge 265, the first membrane surface 213, the process surface 266 of the substrate 115, the retaining ring 218, or a combination thereof.

[0068] At operation 503, the sensor assembly 250 directs a light beam towards the substrate edge 265 of the substrate 115 as the substrate 115 rotates over the sensor assembly 250. The substrate edge 265 edge includes a reference element 301 .

[0069] At operation 505, the sensor assembly 250 detects the signal 263 while the carrier head 210 is rotated.

[0070] At operation 507, the controller 190 determines a characteristic of the carrier head 210 based on a waveform formed from a measured intensity of the detected signal 263. The waveform formed from the measured intensity of the signal 263 is compared to stored waveform profiles to determine in-real time using filtering algorithms, a characteristic of the carrier head 210. The characteristic includes a presence of the substrate within the carrier head, a carrier head runout, a substrate issue, a substrate edge condition, a substrate type, a device pattern, a concentricity of the substrate relative to a retaining ring, a contaminant presence, or a retaining ring life. In some embodiments, the waveforms generated by the controller 190 are saved onto the memory 192 of the controller 190 as stored data sets which can form a plurality of stored data sets to determine other characteristics of the carrier head 210. The stored data sets can be used for relative or absolute comparisons to infer carrier head characteristics.

[0071] Each stored data set includes a first waveform, a carrier head rotation rate, a carrier head applied force, and a second waveform. In some embodiments, the first waveform corresponds to a waveform generated before a polishing operation and the second waveform corresponds to a waveform generated after the polishing operation. In some embodiments, the data set is stored with the plurality of stored waveforms.PATENTAttorney Docket No.: 44025033W001

[0072] In some embodiments, the method 500 also includes using the controller 190 to determine a carrier head state before, during, after or any combination thereof relative to a polishing operation. When the carrier head 210 is in an operational state, the controller 190 instructs the carrier head 210 to perform a polishing operation. When the carrier head 210 is in an eccentric state, the controller 190 determines a compensation factor for movement of the carrier head 210 prior to perform the polishing operation. When the carrier head 210 is in an error state, the controller 190 performs a notification operation.

[0073] In some embodiments, the controller 190 may put the carrier head 210 in an error state if the substrate edge condition is damaged, the controller 190 determines the substrate 115 is not present in the carrier head 210, the controller 190 determines an error in the substrate type, the controller 190 determines an error in the device pattern of devices disposed on the substrate 115, the controller 190 determines an error in the contaminant presence, or the controller 190 determines the retaining ring 218 life is outside of a retaining ring life threshold. The stored waveforms enable the controller 190 to compare generated waveforms to stored waveforms to determine if an error state is required. Exemplary waveforms are described below in reference to Figures 6-11 .

[0074] In some embodiments, the controller 190 is a model training component having a comparative machine learning model that is trained to generate virtual waveforms based on a signal from the sensor 255 and compare the generated waveforms with stored waveforms. The controller 190 creates additional stored waveforms based on the generated waveforms for use with the training model and for carrier head and substrate analysis with the comparative model.

[0075] The machine learning model may be trained through a supervised learning process. Supervised learning techniques generally involve providing training inputs to a machine learning model, such as a neural network. The machine learning model processes the training inputs and outputs predictions based on the training inputs. The predictions are compared to the known labels associated with the training inputs to determine the accuracy of the machine learning model, and parameters of the machine learning model are iteratively adjusted until one or more conditions are met.PATENTAttorney Docket No.: 44025033W001For instance, the one or more conditions may relate to an objective function (e.g., a cost function or loss function) for optimizing one or more variables (e.g., model accuracy). In some embodiments, the conditions may relate to whether the outputs produced by the machine learning model based on the training inputs match the known labels associated with the training inputs or whether a measure of error between training iterations is not decreasing or not decreasing more than a threshold amount. The conditions may also include whether a training iteration limit has been reached. Parameters adjusted during training may include, for example, hyperparameters, values related to numbers of iterations, weights, functions used by nodes to calculate scores, and / or the like. In some embodiments, validation and testing are also performed for a machine learning model, such as based on validation data and test data, as is known in the art.

[0076] The supervised learning process for the machine learning model used to generate the virtual waveforms may comprise providing one or more features of the empirical model and a scan signal taken in real-time during a CMP process to the machine learning model as input. Based on these inputs, the machine learning model may be used to predict scan signals for various possible sensor paths across the surfaces of the edge region 215. For example, the machine learning model may be provided with a waveform from the empirical model and a corresponding sensor signal from the empirical model. The machine learning model may then be used to predict a signal for another path, and the predicted signal may be compared to a signal that corresponds to that path according to the empirical model. Parameters of the machine learning model (e.g., weights) may be iteratively adjusted based on a variance between the predicted signal and the empirical model signal associated with that path. The process may be repeated for different paths across the surface of the substrate. In some embodiments, the supervised learning process may comprise using the machine learning model to predict a characteristic of the carrier head. The characteristic may be an orientation of a substrate, a remaining service life of a retaining ring, a substrate material, a substrate edge issue, a residue on the substrate, a device pattern, a identifier pattern, a missing reference element, or any combination thereof. The machine learning model may predict the characteristic based on a signal and / or waveform, and one or more parameters of the machine learning model may bePATENTAttorney Docket No.: 44025033W001 adjusted based on variances between the predicted waveform and the waveform that the empirical model indicates is associated with the signal. As an example, a predicted orientation may comprise a predicted three dimensional map that has a particular orientation. Thus, in some embodiments, the machine learning model may be used to predict an orientation based on a real-time sensor scan.

[0077] Once trained, the machine learning model may be used to generate a virtual model comprising potential waveforms for different surfaces of the edge region 215 of the substrate 115. The machine learning model may be provided with schematic waveforms as input. The schematic waveforms may comprise data relating to features of the surface of the substrate 115 as input. For example, a waveform as described below in reference to Figures 6-11 may comprise a two dimensional graph. Since the machine learning model has been trained to predict scan signals for different paths across a particular surface of the edge region 215 based on feature data corresponding to the particular substrate, the machine learning model may be used to predict the potential waveform for the substrate 115 based on stored waveforms. The potential waveform may comprise signals for the various surfaces of the edge region 215 a sensor may detect.

[0078] In other embodiments, the virtual model may comprise an empirical model generated by scanning the substrate 115 along the various possible paths. As discussed above, an empirical model may be created by obtaining direct measurements of the features of the substrate 115. Thus, the path that the sensor 255 takes across the surfaces of the edge region 215 may be determined by comparing a real-time sensor waveform to the virtual model waveform to find a closest match. The virtual model signal that is the closest match may correspond to the path taken by the sensor 255. Creating an empirical model for the layout of each substrate to be polished (e.g., the layout shown in schematic diagram) may require more time and resources than using a machine learning model to create the virtual model, as discussed above.

[0079] Once the virtual model is generated for the substrate 115, the virtual model may be used to determine the characteristic of the carrier head 210 in real time during CMP processing. To determine the characteristic of the substrate, a signal obtainedPATENTAttorney Docket No.: 44025033W001 in real time from the sensor 255 may be compared to one or more waveforms of the virtual model. A waveform of the virtual model that is most similar to the real-time signal may be identified. For example, this identification may be performed based on correlating the peaks and / or valleys of the waveform. The virtual model waveform that most closely matches the real-time waveform may be identified as a match. The realtime characteristic of the carrier head 210 may then be determined to be the characteristic associated with the identified virtual model waveform. For example, the identified virtual model waveform was generated based on a particular path that a sensor takes across the surfaces of the edge region 215; if the real-time waveform matches the virtual model waveform, then this may mean that the real-time path matches the particular path used to generate the virtual model waveform. When the signal a sensor detects from across the surfaces within the edge region 215 is known, the characteristic of the carrier head 210 may also be known because the location of the sensor is known. The graph in Figure 6 illustrates an example of a real signal obtained from the sensor 255 or a signal from a virtual model that was identified as most similar to the real signal.

[0080] For example, the precession of the substrate 115 and the rotational velocity of the substrate 115 may be determined based on the determined rotational orientation. For example, an encoder such as the platen encoder 195 may track the rotational orientation of the platen 202. The substrate 115 precession may be calculated based on comparing the platen 202 orientation to the substrate 115 orientation. For example, the difference between the orientations may be identified as the precession. The rotational velocity of the substrate 115 may then be calculated based on the precession. For example, a platen encoder may track the rotational velocity of the platen 202. The rotational velocity of the substrate 115 may be calculated to be slightly higher or slightly lower than the rotational velocity of the platen 202, depending on the direction of the precession.

[0081] Based on the determined rotational orientation and rotational velocity, one or more actions may be performed. For example, the rotational orientation may be adjusted to a target orientation. The target orientation may be an orientation required for additional substrate processing such as a continuation of the CMP process at a different polishing station. As discussed above, because the rotational orientationPATENTAttorney Docket No.: 44025033W001 may be determined before, after, and in real time during a CMP process, the substrate does not have to be removed from a polishing module to ascertain the rotational orientation of the substrate prior to polishing the substrate on a second or third polishing station. Also, determining the true rotational velocity of the substrate during CMP processing allows for improved monitoring of the CMP process.

[0082] Figures 6-11 illustrate exemplary waveform graphs formed by corresponding signals according to one or more embodiments described herein. The graph of each waveform has a horizontal axis that represents time, a left side vertical axis that represents the relative signal intensity recorded by the controller 190 based on a measured intensity of the signal 263, and the right side vertical axis represents the angular orientation of the substrate 115 and / or carrier head 210. The sinusoidal magnitude of the waveforms infers the substrate 115 and retaining ring 218 eccentricity relative to the head carrier axis 216 within the carrier head 210 and enables the controller 190 to compensate or fine-tune substrate orientation at the start of a polishing operation to control substrate precession methods.

[0083] The controller 190 allows one or more waveforms to be created by disposing the edge region 215 of the carrier head 210 over the sensor assembly 250 while rotating the carrier head 210 and / or substrate 115 and detecting an intensity of the signal 263 with the sensor assembly 250. The signal 263 forms a main line as the average signal intensity and has variations that deviate outside of a signal threshold. In some embodiments, the signal threshold is determined by using a magnitude of a signal from known physical characteristics and comparing that known signal magnitude to a measured signal magnitude. The deviations in signal intensity correspond to the signal 263 reflecting from changing surfaces. For example, when the signal 263 is oriented toward the substrate edge 265 while the carrier head 210 rotates the substrate 115, the reference element 301 passes the path of the signal 263. As the reference element 301 rotates, the signal 263 is briefly reflected off of the first membrane surface 213 instead of the substrate 115 and the controller 190 is able to form a waveform and associate the change in signal intensity within the waveform with the orientation of the substrate 115.PATENTAttorney Docket No.: 44025033W001

[0084] The controller 190 is able to generate waveforms before and / or after a polish operation that enable the controller 190 to identify and validate carrier head 210 characteristics. For example, a first waveform can be formed before a polish operation, and a second waveform can be formed after the polish operation. If the second waveform, for example, exhibits edge chipping scenarios that were not present in the first waveform, the controller 190 is able to place the carrier head 210 in an error state, create a log of the associated parameters, and flag that substrate for removal from further operation.

[0085] The waveform 600, as illustrated in Figure 6, is an example of a waveform when the sensor 255 directs the signal 263 to the retaining ring 218 or a substrate 115 is not within the carrier head 210. The waveform 600 includes a main line 601 and substrate orientation 603. The main line 601 is the detected intensity of the signal 263 when the signal 263 reflects from the surface of the retaining ring 218 that contacts the pad 204. A plurality of valleys 605 correspond to notches in the retaining ring 218 as the signal 263 reflects from the recessed notch surface and the surface of the retaining ring 218 that contacts the pad 204 (Figure 2). The controller 190 can compare the waveform 600 to other stored waveforms and determine a characteristic of how eccentric the carrier head 210 is. For example, a misaligned carrier head 210 would correspond to a carrier head wobble and the sinusoid form of the main line 601 being outside of an acceptable threshold. When outside of the threshold the controller 190 enables an error correction in lieu of stopping production completely. For example, when the controller 190 compares a waveform prior to a polishing operation, the carrier head 210 can be placed in an error state or a compensation factor can be added to the subsequent polishing operation. Further, residue within the retaining ring 218 may also be identified by noise 609 in the waveform 600. This comparison allows the controller 190 to determine carrier head runout which corresponds to the sinusoidal characteristic of the retaining ring 218 and / or the carrier head 210.

[0086] The controller 190 can also determine if the proper retaining ring 218 has been mounted to the carrier head 210. For example, the controller 190 can use the notch depth signal 607 to determine the number of grooves and / or groove depth in the retaining ring 218 to generate the waveform 600 and determine a type of retaining ring. The controller 190 is able use the comparison to determine a remaining workingPATENTAttorney Docket No.: 44025033W001 life of the retaining ring based on a corresponding notch depth signal 607. Still further, the controller 190 can also determine if the retaining ring 218 has been damaged or if slurry has built up when noise feedback 609 is detected.

[0087] The waveform 700, as illustrated in Figure 7, is an example of a waveform when a blanket substrate 115 is within the carrier head 210. The waveform 700 includes a main line 701 and substrate orientation 703. The main line 701 is the detected intensity when the signal 263 reflects from the surface of the substrate 115. The main line 701 includes a valley 705 that corresponds to the reference element 301 (Figure 3A). Variations in the main line 701 enable the controller 190 to determine and / or categorize different types of substrate materials based on their corresponding different intensity values detected by the sensor 255.

[0088] The waveform 800, as illustrated in Figure 8, is an example of a waveform when a substrate 115 has edge abnormalities. For example, the substrate edge 265 has been chipped or damaged. The waveform 800 includes a main line 801 and substrate orientation 803. The main line 801 includes a valley 805 that corresponds to the reference element 301 (Figure 3A). Noise 807 in the main line 801 enables the controller 190 to determine when a substrate 115 has edge abnormalities that correspond to the noise 807 detected by the sensor 255. For example, using the virtual models and waveforms stored in the memory 192 and described above, the controller 190 is able to identify chipping scenarios or questionable edge properties and then modify substrate handling routines to preserve substrate integrity. In some embodiments, the controller 190 is able to use the valley 805 that corresponds to the reference element 301 to determine a substrate orientation.

[0089] The waveform 900, as illustrated in Figure 9, is an example of a waveform from a patterned substrate 115. For example, a substrate with devices or a pattern disposed thereon will have a unique waveform as opposed to an unpatterned substrate. The waveform 900 includes a main line 901 and substrate orientation 903. The main line 901 includes a plurality of valleys 905 that correspond to the different patterns disposed on the substrate surface and a specific prime valley 907 that corresponds to the reference element 301 (Figure 3A). The unique waveforms of patterned substrates enable the controller 190 to determine if a substrate is in or outPATENTAttorney Docket No.: 44025033W001 of the proper sequence of process operations. For example, peaks and valleys in a substrate with devices provide a distinct pattern 909 that may be different between different pattern arrangements.

[0090] A comparison between waveforms stored in the controller 190 with waveforms corresponding to substrates in the production enables the controller 190 to identify a substrate that does not exhibit the proper waveform based on the corresponding detected signal. The improper waveform may be an indicator for issues with the substrate or an incorrect substrate. The controller 190 enables the substrate removal from production prior to an operation that would potentially reduce substrate integrity, mitigating future downstream issue.

[0091] The waveform 1000, as illustrated in Figure 10, is an example of a waveform used for substrate identification. For example, a substrate with an identification pattern disposed thereon will have a unique waveform that can be used to identify a substrate serial number for tracking and substrate orientation. The waveform 1000 includes a main line 1001 and substrate orientation 1003. The main line 1001 includes a notch valley 1005 that corresponds to the reference element 301 and a specific identifier 1007 than can be used to identify a specific substrate. In some embodiments the notch valley 1005 is the same as the specific identifier 1007. In some embodiments, a substrate edge 265 includes a specific pattern as the reference element 301 and / or specific identifier 1007. For example, the reference element 301 is a pattern, a uniquely shaped geometry, bar code or any combination thereof on the substrate 115. The reference element 301 enables the controller 190 to simultaneously identify a unique substrate and substrate orientation.

[0092] The waveform 1100, as illustrated in Figure 11 , is an example of a waveform to identify a substrate missing a reference element 301 . For example, the waveform 1100 includes a main line 1101 and substrate orientation 1103. The main line 1101 includes a false valley 1105. The false valley 1105 corresponds to a change in signal intensity from the main line 1101 that is outside of an accepted threshold for one or more of time and change in intensity. The false valley 1105 is identified as a different shape and geometry from the reference element 301 because the reference element 301 is tightly constrained through industry standards. For example, byPATENTAttorney Docket No.: 44025033W001 comparing a generated waveform with the waveform 1100, the controller 190 is able to identify a substrate that is missing a reference element 301 . In some embodiments the false valley 1105 is first false valley 1105 and the controller 190 detects a second false valley 1107. When consistent false valleys are detected, the controller 190 can determine the reference element 301 is damaged missing, undetectable, or any combination thereof.

[0093] Benefits of the present disclosure include at least in-situ and ex-situ substrate orientation detection, carrier head characteristic determination, enhanced early issue identification and remediation, and enhanced substrate identification capabilities.

[0094] It is contemplated that one or more aspects disclosed herein may be combined. As an example, one or more aspects, features, components, operations and / or properties of the sensor assembly 250; the sensor 255; the controller 190; the carrier head 210; method 400; method 500; and the waveforms 600, 700, 800, 900, 1000, and 1100 may be combined.

[0095] While the foregoing is directed to embodiments of the present disclosure, other and further embodiments of the disclosure may be devised without departing from the basic scope thereof, and the scope thereof is determined by the claims that follow.

Claims

PATENTAttorney Docket No.: 44025033W001WHAT IS CLAIMED IS:1 . A polishing station, comprising: a platen; a carrier head comprising: a membrane; an retaining ring disposed around a first membrane surface, the retaining ring and first membrane surface defining an edge region of the carrier head; a sensor assembly disposed radially outward of the platen, the carrier head configured to translate the edge region over the sensor assembly, the sensor assembly comprising: a body; a fluid channel disposed through the body; and a sensor disposed in the body, the sensor comprising an orientation aligned with an outlet of the fluid channel, the sensor configured to detect a signal; and a controller in communication with the sensor and the carrier head, wherein the controller is configured to identify a characteristic of the carrier head based on the signal and determine a state of the carrier head based on the characteristic.

2. The polishing station of claim 1 , wherein the fluid channel is coupled to a fluid source and the outlet of the fluid channel is directed towards the carrier head, the outlet of the fluid channel oriented about parallel to an axis of the platen.

3. The polishing station of claim 1 , wherein the controller is further configured to identify a concentricity of a substrate disposed within the carrier head.

4. The polishing station of claim 3, wherein the sensor assembly is configured to detect a reference element disposed on an edge of the substrate.PATENTAttorney Docket No.: 44025033W0015. The polishing station of claim 1 , wherein the outlet of the fluid channel is disposed proximate a top surface of a pad disposed on the platen.

6. The polishing station of claim 1 , wherein the characteristic of the carrier head comprises at least one of: a substrate presence; a carrier head runout; a substrate issue; a substrate type; a device pattern; a concentricity of the substrate relative to the retaining ring; a contaminant presence; or a life of the retaining ring.

7. The polishing station of claim 1 , wherein the state of the carrier head comprises: an operational state; or an error state.

8. A method of monitoring a carrier head, comprising: translating an edge region of a carrier head over a sensor assembly; detecting a signal with the sensor assembly; and determining, with a controller, a characteristic of the carrier head based on the signal, the characteristic comprising at least one of: a substrate orientation; a substrate presence; a carrier head runout; a concentricity of the substrate relative to a retaining ring; or a life of the retaining ring.

9. The method of claim 8, further comprising rotating the carrier head while detecting the signal.PATENTAttorney Docket No.: 44025033W00110. The method of claim 8, further comprising flowing a liquid from the sensor assembly to the carrier head, the signal detected through the liquid.

11. The method of claim 8, wherein translating an edge region further comprises translating the carrier head from a first position over a platen to a second position where the edge region extends outward of a radial edge of the platen.

12. The method of claim 8, wherein detecting a signal comprises: directing light from the sensor assembly toward the carrier head; and detecting the signal from the light as the light reflects from the carrier head.

13. The method of claim 8, further comprising: determining, with the controller, a carrier head state; performing a polishing operation when the carrier head state is in an operational state; and performing a notification operation when the carrier head state is an error state, the error state comprising at least one of: the carrier head runout is outside of a carrier head runout threshold; the concentricity of the substrate relative to a retaining ring is outside of a concentricity threshold; or the retaining ring is outside of a retaining ring life threshold.

14. A method of monitoring a carrier head comprising: translating an edge region of a carrier head over a sensor assembly; directing a light beam towards an edge of a substrate as the substrate rotates over the sensor assembly, the edge comprising a reference element; detecting a signal with the sensor assembly; determining, with a controller, a characteristic of the carrier head based on a waveform of the signal, the characteristic comprising at least one of: a presence of the substrate within the carrier head; a carrier head runout; a substrate issue; a substrate edge condition;PATENTAttorney Docket No.: 44025033W001 a substrate type; a device pattern; a concentricity of the substrate relative to a retaining ring; a contaminant presence; or a retaining ring life.

15. The method of claim 14, wherein detecting a signal comprises: directing light from the sensor assembly toward the carrier head; and detecting the signal from the light as the light reflects from one or more of: the retaining ring; the substrate; or a membrane of the carrier head.

16. The method of claim 14, wherein determining a characteristic of the carrier head further comprises the controller comparing the waveform to a plurality of stored data sets to determine the characteristic of the carrier head.

17. The method of claim 16, further comprising: creating a data set when the controller places the carrier head in an error state, the data set comprising: a first waveform; a carrier head rotation rate; a carrier head applied force; and a second waveform; and adding the data set to a plurality of stored waveforms.

18. The method of claim 14, wherein the waveform is related to an intensity of the signal.

19. The method of claim 14, further comprising: performing a first polishing operation before translating the edge region of the carrier head over the sensor assembly; andPATENTAttorney Docket No.: 44025033W001 performing a second polishing operation after translating the edge region of the carrier head over the sensor assembly.

20. The method of claim 14, further comprising: determining, with the controller, a carrier head state; performing a polishing operation when the carrier head state is in an operational state; determining a compensation factor when the carrier head state is in an eccentric state; and performing a notification operation when the carrier head state is an error state, the error state comprising at least one of: the substrate edge condition is damaged; the controller determines the substrate is not present in the carrier head; the controller determines an error in the substrate type; the controller determines an error in the device pattern; the controller determines an error in the contaminant presence; or the controller determines the retaining ring life is outside of a retaining ring life threshold.

Images