Attorney Docket No 44020306WO01; 05542-1520WO1 CARRIER HEAD ACOUSTIC MONITORING WITH SENSOR IN PLATEN FIELD OF THE DISCLOSURE [0001] The disclosure relates to chemical mechanical polishing, and more specifically to determination of polishing parameters from acoustic signals received during chemical mechanical polishing. BACKGROUND [0002] An integrated circuit is typically formed on a substrate by the sequential deposition of conductive, semiconductive, or insulative layers on a silicon wafer. 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. A conductive filler layer, for example, can be deposited on a patterned insulative layer to fill the trenches or holes in the insulative layer. After planarization, the portions of the conductive layer remaining between the raised pattern of the insulative layer form vias, plugs, and lines that provide conductive paths between thin film circuits on the substrate. For other applications, such as oxide polishing, the filler layer is planarized until a predetermined thickness is left over the non-planar surface. In addition, planarization of the substrate surface is usually required for photolithography. [0003] Chemical mechanical polishing (CMP) is one accepted method of planarization. This planarization method typically requires that the substrate be mounted on a carrier or polishing head. The exposed surface of the substrate is typically placed against a rotating polishing pad. The carrier head provides a controllable load on the substrate to push it against the polishing pad. An abrasive polishing slurry is typically supplied to the surface of the polishing pad. SUMMARY [0004] Disclosed herein is a chemical mechanical polishing apparatus including a carrier head to hold a substrate against a polishing pad. Relative motion is generated between the polishing pad and the carrier head to polish the exposed face of the substrate. The apparatus includes an in-situ acoustic monitoring system which receives acoustic signals from the substrate and carrier head. The acoustic monitoring system generates corresponding electronic signals which are transmitted to a controller. The controller receives the electronic signals and generates a value for a carrier head status parameter based on the electronic Attorney Docket No 44020306WO01; 05542-1520WO1 signals. The controller is configured to change one or more polishing parameters, or generate an alert, based on the carrier head status parameter. [0005] In one aspect, a chemical mechanical polishing apparatus has a platen to support a polishing pad, the platen having a recess, a carrier head to hold a surface of a substrate against the polishing pad and comprising a retaining ring to retain the substrate below the carrier head, a motor to generate relative motion between the platen and the carrier head so as to polish the substrate, an in-situ acoustic monitoring system comprising an acoustic sensor arranged in the recess that receives acoustic energy from friction between the substrate and the polishing pad and from friction between the retaining ring and the polishing pad, and a controller configured to generate a value for a carrier head status parameter based on received acoustic signals from the in-situ acoustic monitoring system, and change or polishing parameter or generate an alert based on the carrier head status parameter. [0006] In another aspect, a method of polishing includes holding a substrate against a polishing surface of a polishing pad with a carrier head, generating relative motion between the substrate and polishing pad such that an in-situ acoustic monitoring system passes beneath the carrier head, monitoring the carrier head with an in-situ acoustic monitoring system oriented beneath the polishing pad to generate a signal comprising a sequence of segments, identifying a first segment from the sequence of segments corresponding to the sensor being beneath a first portion of the carrier head, identifying a second segment from the sequence of segments corresponding to the sensor being beneath a second portion of the carrier head, determining a difference between the first segment and the second segment, and changing a polishing parameter or generating an alert based on the determined difference. [0007] The details of one or more embodiments are set forth in the accompanying drawings and the description below. Other features and advantages will be apparent from the description and drawings, and from the claims. DESCRIPTION OF DRAWINGS [0008] FIG.1 is a schematic side view of a polishing system including an in-situ acoustic monitoring system. [0009] FIG.2 is a schematic top-view illustration of a substrate being polishing on a polishing pad and an example path the acoustic sensor follows during a polishing operation and an example acoustic signal generated while the sensor moves on the example path. [0010] FIG.3 is an illustration of an example acoustic signal and segments corresponding to different portions of the ring assembly or substrate. 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 [0011] FIG.4 is a flow chart diagram of an example method of a polishing process. [0012] FIG.5 is a system diagram of an example computing system. [0013] In the figures, like references indicate like elements. DETAILED DESCRIPTION [0014] One problem in CMP is verification that the polishing system is operating with the desired control parameters, e.g., desired rotation rates or chamber pressures. Ideally the appropriate physical components, e.g., motors or pressure regulators, are simply caused by a controller to operate according to a recipe with the desired control parameter values. However, in practice the actual values, e.g., actual rotation rates or chamber pressures, can vary from the desired values due to transient effects or system faults. [0015] However, if acoustic signals are correlated to a control parameter, e.g., chamber pressure or rotation rate, then a control parameter value determined from the acoustic signal can serve as a validation or fault detection for another control parameter sensor, e.g., a pressure sensor or motor encoder, can render the other sensors unnecessary. [0016] Yet another problem in CMP is determining “system health.” A failure during polishing, e.g., wafer slippage from the carrier head, failure to chuck or dechuck the substrate, stiction between membranes in the carrier head, unexpected lateral motion of the substrate or carrier head, etc., can result in direct damage to the substrate being polished and require extensive down-time for system maintenance. Conventionally, such failures are detected only after they occur. For example, visual inspection or a camera might detect that the substrate has slipped from beneath the carrier, or a change in the polishing rate may indicate a fault. [0017] However, if acoustic signals are correlated to an impending fault condition, it would be possible to diagnose problems so that corrective action can be taken before the failure occurs. [0018] Yet another problem in CMP is the creation of air bubbles between the substrate and flexible membrane during a chamber pressure ramping operation. In operation, the pressure in each of the pressurizable chambers is increased by zone according to a recipe, which can be stored in the controller. If an error in the pressure ramping process occurs, air bubbles can be entrained between the substrate and the flexible membrane. These air bubbles change the profile of pressure applied to the substrate and decrease wafer uniformity. There is no real time technique to identify a pressure ramping process which resulted in an air bubble between the membrane and wafer. 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 [0019] However, if acoustic signals are correlated to an improper pressure ramp process, it would be possible to determine the presence of an air bubble, or the improper pressure ramp process, so that corrective action can be taken before the air bubble affects the polishing of the substrate. [0020] Yet another problem in CMP is improper gimbal mechanism lubrication. In general, the gimbal mechanism is lubricated, e.g., greased, to reduce friction between the moving components when a force is applied to the carrier head which causes gimbaling, e.g., due to the carrier head riding over a polishing pad of non-uniform thickness.. If the flexible gimbal mechanism is improperly lubricated, the force needed to cause gimbaling is increased and can result undesirable polishing outcomes, direct damage to the substrate, and increased maintenance of the polishing system. [0021] However, if acoustic signals are monitored over time, it would be possible to determine improper greasing of the gimbal mechanism so that corrective action can be taken before damage to the gimbal mechanism occurs or the substrate is damaged during polishing. [0022] A polishing process generates acoustic energy as the substrate and the retaining ring of the carrier head interact with the polishing layer of the polishing pad, based on at least the frictional contact between two surfaces. The acoustic energy can be received by an acoustic sensor and processed to generate a series of acoustic measurements, i.e., an acoustic signal. [0023] Segmenting the acoustic signal according to which surfaces of the ring assembly or the substrate are generating the acoustic information facilitates detection of bubbles or other polishing parameters, e.g., a pressure or a gimbaling position, that are in error. Detection of such errors increases system reliability and reduces system faults and failed polishing operations. [0024] The techniques described herein can address any one, or more than one, of these problems, independently or in conjunction. [0025] FIG.1 illustrates an example of a polishing station of a chemical mechanical polishing system 20. The polishing system 20 includes a rotatable disk-shaped platen 24 on which a polishing pad 30 is situated. The platen 24 is operable to rotate about an axis 25. For example, a motor 26 can turn a drive shaft 28 to rotate the platen 24. The polishing pad 30 can be a two-layer polishing pad with an outer polishing layer 32 and a softer backing layer 34. A polishing surface of the polishing layer 32 can includes grooves 35, e.g., for slurry transport. [0026] The polishing system 20 can include a supply port or a combined supply-rinse arm 36 to dispense a polishing liquid 38, such as an abrasive slurry, onto the polishing pad 30. 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 The polishing system 20 can also include a pad conditioner apparatus 40 with a conditioning disk 42 to maintain the surface roughness of the polishing pad 30. The conditioning disk 42 can be positioned at the end of an arm 44 that can swing so as to sweep the disk 42 radially across the polishing pad 30. [0027] A carrier head 70 is operable to hold a substrate 10 against the polishing pad 30. The carrier head 70 is suspended from a support structure 50, e.g., a carousel or a track, and is connected by a drive shaft 54 to a carrier head rotation motor 56 so that the carrier head can rotate about an axis 58. Optionally, the carrier head 70 can oscillate laterally, e.g., on sliders on the carousel, by movement along the track, or by rotational oscillation of the carousel itself. [0028] The carrier head 70 includes a housing 72, a substrate backing assembly 74 which includes a base 76 and a flexible membrane 78 that defines a plurality of pressurizable chambers 80, a gimbal mechanism 82 (which may be considered part of the assembly 74), a loading chamber 84, a retaining ring 100, and an actuator 122. [0029] The housing 72 can generally be circular in shape and can be connected to the drive shaft 54 to rotate therewith during polishing. There may be passages (not illustrated) extending through the housing 72 for pneumatic control of the carrier head 70. The substrate backing assembly 74 is a vertically movable assembly located beneath the housing 72. The gimbal mechanism 82 permits the base 76 to gimbal relative to the housing 72 while preventing lateral motion of the base 76 relative to the housing 72. The loading chamber 84 is located between the housing 72 and the base 76 to apply a load, i.e., a downward pressure or weight, to the base 76 and thus to the substrate backing assembly. The vertical position of the substrate backing assembly 74 relative to a polishing pad is also controlled by the loading chamber 84. The lower surface of the flexible membrane 78 provides a mounting surface for a substrate 10. [0030] During installation or removal of the substrate 10 from the carrier head 70, the polishing system 20 commands the carrier head 70 to change the air pressure within the pressurizable chambers 80 according to a recipe to ‘chuck’ (e.g., install) or ‘dechuck’ (e.g., uninstall) the substrate 10 to the carrier head 70. In general, the flexible membrane 78 includes concentric pressurizable chambers 80 in which each of the chambers 80 are individually pressurizable. To chuck the substrate 10 to the carrier head 70, the pressure is increased sequentially from the central chamber concentrically outward to increasingly distal chambers. To dechuck the substrate 10 from the carrier head 70, the pressure is decreased in 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 the pressurizable chambers 80 sequentially from the outermost concentric chamber to the central chamber. [0031] The sequential pressurization of a chuck process drives air entrained between the substrate 10 and the pressurizable chambers 80 outward until the substrate 10 is held by vacuum to the flexible membrane 78. Conversely, the dechuck process sequentially decreases pressure between the pressurizable chambers 80 and the substrate 10, from the outermost chamber inwardly, such that air intrudes between the flexible membrane 78 and the substrate 10 until the substrate 10 is no longer held by vacuum to the flexible membrane 78. [0032] The polishing system 20 includes at least one in-situ acoustic monitoring system 160. The in-situ acoustic monitoring system 160 includes one or more acoustic sensors 162 arranged below a side of the substrate 10 closer to the polishing pad 30. Each acoustic sensor can be installed at a location on the platen 24. In particular, the in-situ acoustic monitoring system can be configured to sense acoustic energy, e.g., acoustic emissions caused by stress in the polishing pad, substrate or retaining ring. In general, this acoustic energy is in the form of compressive waves transmitted through the material (as opposed to bulk motion). [0033] The acoustic sensor 162 is positioned in a recess 164 in the platen 24 and is positioned to receive acoustic energy through the polishing pad 30, e.g., through an acoustic window 118 in the polishing pad 30. The acoustic sensor 162 can be connected by circuitry 168 to a power supply and/or other signal processing electronics 166 through a rotary coupling, e.g., a mercury slip ring. The signal processing electronics 166 can be connected in turn to the controller 190. [0034] The in-situ acoustic monitoring system 160 can be a passive acoustic monitoring system. The passive acoustic signals monitored by the acoustic sensor 162 can be in 50 kHz to 1 MHz range, e.g., 200 to 400 kHz, or 200 KHz to 1 MHz. For example, for monitoring of polishing of inter-layer dielectric (ILD) in a shallow trench isolation (STI), a frequency range of 225 kHz to 350 kHz can be monitored. As another example, passive mode frequencies of interest range from 500 kHz to 900 kHz. [0035] The portion of the backing layer 34 directly above the acoustic sensor 162 can include an acoustic window 118. The acoustic window 118 has a lower acoustic attenuation coefficient than the surrounding backing layer 34. The material of the acoustic window 118 has a sufficiently low acoustic attenuation coefficient, e.g., to provide a signal satisfactory for acoustic monitoring. In general, the acoustic attenuation coefficient should be as low as 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 possible (i.e., no absorption), e.g., an acoustic attenuation coefficient lower than 2 to provide a signal satisfactory for acoustic monitoring. [0036] In some implementations, the acoustic window 118 is formed of a different material than the backing layer 34. This permits the backing layer 34 to be composed of a wider range of materials to meet the needs of the CMP operation. The acoustic window 118 can be composed of a non-porous material, e.g., a solid body. For example, the acoustic material can be a polymer, e.g., a polyurethane. [0037] The acoustic window 118 can be wider than the acoustic sensor 162, e.g., as shown in FIG.1, or the two can be of substantially equal width (e.g., within 10%). Where the acoustic window 118 is narrower than the acoustic sensor 162, the sensor can also abut the bottom of the backing layer 34. [0038] The acoustic sensor 162 is a contact acoustic sensor 162 having a surface connected to (e.g., in direct contact with, or having just an adhesive layer) a portion of the backing layer 34 and/or the acoustic window 118. For example, the acoustic sensor 162 can be an electromagnetic acoustic transducer or piezoelectric acoustic transducer. A piezoelectric sensor can include a rigid contact plate, e.g., of stainless steel or the like, which is placed into contact with the body to be monitored, and a piezoelectric assembly, e.g., a piezoelectric layer sandwiched between two electrodes, on the backside of the contact plate. [0039] The acoustic sensor 162 can be secured to a portion of the backing layer 34 and/or to the acoustic window 118 by an adhesive layer. The adhesive layer increases the contact area between the acoustic sensor 162 and the backing layer 34 and/or acoustic window 118, reduces undesirable motion in the acoustic sensor 162 during polishing operations, and can reduce the presence of gas pockets between the acoustic sensor 162 and the backing layer 34. However, in some implementations, the acoustic sensor 162 contacts the acoustic window 118 directly. [0040] The acoustic window 118 extends through the backing layer 34 such that one surface, e.g., an upper surface, contacts a lower surface of the polishing layer 32. The opposing surface, e.g., a bottom surface, can be coplanar with a lower surface of the backing layer 34. [0041] The acoustic window 118 can be composed of a non-porous material. In general, non-porous materials transmit acoustic energy with reduced noise and dispersion compared to porous materials. The acoustic window 118 material can have a compressibility within a range of the compressibility of the surrounding matrix material 204 that reduces the effect of the acoustic window 118 on the polishing characteristics of the polishing layer 32. The 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 acoustic window 118 can be composed of one or more of polyurethane, polyacrylate, polyethylene, or another polymer that has a sufficiently low acoustic impedance coefficient. The acoustic window 118 is shown extending through the total thickness of the backing layer 34. The acoustic sensor 162 extends through an aperture in the platen 24 to contact the underside of the window 118. [0042] In some implementations and as shown in FIG.1, the acoustic window 118 extends through the thickness of the pad 30. As shown in FIG.2C, the acoustic window 118 extends through both the polishing layer 32 and the backing layer 34. Here, the acoustic window 118 has a lower acoustic impedance than the surrounding polishing layer 32 and backing layer 34. The acoustic window 118 is positioned such that the top surface of the acoustic window 118 is coplanar with the polishing surface 112a, and the bottom surface of the acoustic window is coplanar with the lower surface of the backing layer 34, e.g., lower surface 114b, that contacts the platen 24. The acoustic sensor 162 contacts the exposed surface of the acoustic window 118 and receives the transmitted acoustic energy. [0043] The acoustic window 118 is formed of a different material than the polishing layer 32. This permits the backing layer 34 to be composed of a wider range of materials to meet the needs of the CMP operation. In some implementations the acoustic transmission of both the polishing layer 32 and the backing layer 34 are sufficiently high that an acoustic window is not required. In this case, the acoustic sensor 162 can be placed in direct contact with a lower surface of the backing layer 34. [0044] Referring now to FIG.2, an overhead view of the platen 24, and supported polishing pad 30, are shown with the substrate 10 being confined by the retaining ring 100. During a polishing operation, relative motion between the pad 30 and substrate 10 is generated by rotation of the platen 24, rotation, or linear motion, of the carrier head 70 pressing on the substrate 10, or a combination. The sensor 162 (and window 118 if present) is shown and as the platen 24 and supported pad 30 rotate in a direction 124, the sensor 162 follows a path 102 with respect to the reference frame of FIG.2. As the sensor 162 follows the path 102 during the polishing operation, the sensor 162 travels beneath separate portions of the ring assembly 100 and the substrate 10, e.g., when the path 102 intersects a portion of the substrate 10 or a portion of the retaining ring 100. [0045] The acoustic sensor 162 is in contact with the window 118 and generates acoustic data during the polishing operation. The acoustic sensor 162 generates a series of acoustic measurements as the sensor travels along the path 102. This series includes measurements from when the sensor 162 (or window 118) is not beneath or in contact with the retaining ring 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 100 or the substrate 10. The data generated prior to the sensor 162 passes below the retaining ring 100 is termed "leading off wafer data", e.g., prior to and including entering path portion 106. An example path portion in which leading off-wafer data is collected is shown as path portion 110. [0046] As the sensor 162 passes beneath the carrier head 70, retaining ring 100, or substrate 10, the acoustic sensor 162 measures acoustic energy generated by contact between the carrier head 70, retaining ring 100, or substrate 10 and the polishing pad 30 and window 118. Path portions 104 and 108 correspond to the sensor 162 being beneath two portions of the retaining ring 100, and path portion 106 correspond to the sensor 162 being beneath the substrate 10. Data generated when the sensor 162 is beneath the substrate 10, e.g., path portion 106, is termed “on wafer data.” Due to attenuation as the acoustic energy travels through the polishing pad 30 and window 118, the acoustic energy that reaches the sensor 162 is primarily caused by the friction between the polishing pad 30 (including the window 118) and the particular component that is directly above the sensor 162, e.g., the retaining ring 100 or substrate 10. Information regarding a component can be obtained by analyzing the path portion of the signal corresponding to the component. [0047] Data generated subsequent to the sensor 162 passing below the second portion of the retaining ring 100, e.g., exiting path portion 108, is termed “trailing off-wafer data.” An example path portion in which trailing off-wafer data is collected is shown as path portion 112. [0048] The controller 190 of the acoustic monitoring system 160 receives the acoustic data from the acoustic sensor 162. In some implementations, the controller displays the measured acoustic signal on a display, e.g., a computer monitor. [0049] Referring now to FIGS.2 and 3, an exemplary acoustic signal 300 is shown. The acoustic monitoring system 160 processes the acoustic signal 300 and subdivides the acoustic signal 300 into segments corresponding to the sensor 162 being beneath the carrier head 70, e.g., beneath the ring assembly 100, or the substrate 10. The acoustic monitoring system 160 subdivides the acoustic signal 300 into segments according to the position of the measurement, i.e., the position of the sensor, e.g., as determined from the angular position of the platen. In some implementations, different segments of the signal can be differentiated based on the average amplitude of the acoustic signal 300. The sequence of segments is a time-dependent series corresponding with acoustic data generated sequentially by the acoustic sensor 162 over a time period. 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 [0050] In some implementations, the acoustic monitoring system 160 performs signal processing on the acoustic data generated by the acoustic sensor 162 to filter, e.g., de-noise, the acoustic data before communicating the acoustic data to the controller 190. The filtering can be a low-pass filter or running window average to smooth the measured signal from the sensor 162. In some examples, the acoustic monitoring system 160 generates an average value for the measured signal within each segment. [0051] In the example of FIG.3, the acoustic signal 300 includes off-wafer segment 322 corresponding with “leading off-wafer data;” segments 324 and 332 corresponding with the window 118 being beneath the retaining ring 100, e.g., data collected over path portions 106 and 108; segment 326 corresponding with the window 118 being beneath the carrier head 70 and not in contact with the ring assembly 100 or the substrate 10; on-wafer segment 328 corresponding with the window 118 being beneath the substrate 10, e.g., “on wafer data;” and off-wafer segment 334 corresponding with “trailing off-wafer data.” During a polishing operation, friction drives the substrate 10 against the trailing inner surface of the retaining ring 100 such that on-wafer segment 328 is adjacent the carrier head section 332 in the acoustic signal 300. In some examples, the segment 326 may not appear in the acoustic signal 300 received by the acoustic monitoring system 160. In general, the gap between the substrate 10 and the ring assembly 100 on the leading side of the path 102 can be 2 mm to 3 mm, which may be smaller than the sensor 162 and therefore effectively undetectable, e.g., indiscriminate, from the rest of the acoustic signal 300. [0052] The acoustic monitoring system 160 communicates the acoustic signal 300 to the controller 190. The controller 190 processes the received acoustic signal 300 to compare a value of a characteristic of the signal 300 to a predetermined threshold value or to determine changes in the characteristic of the signal 300. Examples of a characteristic of the signal include an average amplitude of the segment of the signal, the maximum or minimum amplitude within the segment of the signal, the intensity at some frequency in the frequency spectrum of segment of the signal, the total power in some bandwidth range of the frequency spectrum of segment of the signal, a frequency weighted average power, or the location (frequency) of a peak or valley in the frequency spectrum of segment of the signal. In some implementations, the controller 190 determines alternative data parameters, such as a derivative, an average, a frequency weighted average power, an integral, a standard deviation, or a variance of the acoustic signal 300, of one or more of the segments of the acoustic signal 300. 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 [0053] As an example, the controller 190 determines a difference between the values for the characteristic for one or more segments of the acoustic signal 300, such as a difference between on-wafer segment 328 and off-wafer segment 322 and/or 334, a difference between leading carrier head segment 324 and trailing carrier head segment 332, or a difference between on-wafer segment 328 and carrier head segments 324 and/or 332. The controller 190 may also determine differences in the values for the characteristic of the acoustic signal 300 over time, such as between consecutive rotations of the platen, differences between two or more substrates 10, or differences in the acoustic signal 300 over an operational time period of the polishing system 20 (e.g., weeks, or months). [0054] In some implementations, the controller 190 compares values of the characteristic of the acoustic signal 300 to one or more threshold values. For example, the controller 190 compares the maximum value (e.g., the maximum amplitude) of one or more segments of the acoustic signal 300 to a respective maximum threshold value. [0055] In general, the acoustic monitoring system 160 determines the presence of defects, incorrect or undesirable polishing parameters, or a combination, from the acoustic signal 300 by comparing one or more segments of the acoustic signal 300 with another segment, by comparing the acoustic signal 300 to historical acoustic signals generated with different substrates, or both. If a difference between the values for the characteristic for the two segments of the acoustic signal exceeds a threshold value, one of the problems may be indicated. A bubble may exist if the on-wafer signal power is significantly lower than expected or there is a significant dip in the signal power not associated with an equivalent reduction in expected pressure being applied to the wafer in that region of the signal. The gimbal position may be out of line if the difference between the leading and trailing edge ring signal power (324 and 332) fall outside of a characterized acceptable range. [0056] The controller 190 generates a value for a carrier head status parameter based on one or more segments of the received acoustic signal 300. Examples of a carrier head status parameter include a pressure in one or more pressurizable chambers 80, or a gimbal position of the gimbal mechanism 82 (e.g., a height, or an angular deflection). The controller 190 compares the carrier head status value to a threshold status value stored in the controller 190. The controller 190 can generate an alert or change an operational value of the polishing system 20 responsive to the carrier head status value exceeding the corresponding threshold status value. [0057] In an example, the controller 190 determines a difference in average amplitude between the leading carrier head segment 324 and trailing carrier head segment 332. Such an 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 amplitude difference can be indicative of an improper pressure in one or more chambers 80 which can results in an improper gimbaling of the carrier head 70. The controller 190 can generate an alert responsive to the determination. [0058] The controller 190 can determine a difference in average amplitude between the leading carrier head segment 324 and trailing carrier head segment 332 over multiple substrate 10 polishing operations. Determination that the amplitude difference exceeds a threshold value, or variations in the averaged amplitude, can be indicative of improper lubrication of the gimbal mechanism 82. The controller 190 generates an alert responsive to the determination indicating service is due on the gimbal mechanism 82. [0059] In another example, the controller 190 determines a variation in the segments 326 or 330, or the on-wafer segment 328. The variation can be calculated as the standard deviation of the signal over the respective segment, or as a difference between maximum and minimum values over the respective segment. The variation can be compared to a stored variation threshold value. In some examples, a high variation, i.e., exceeding the threshold, in the on- wafer segment 328 can be indicative of the presence of a gas bubble between the substrate 10 and the polishing layer 32. Gas bubbles reduce polishing effectiveness by reducing the contact area of the substrate 10 with the polishing layer 32. Detecting gas bubbles facilitates adjustment of one or more polishing parameters to remove the bubble which improves within-wafer polishing. The controller 190 can generate an alert responsive to the determination of the presence of a gas bubble, terminate the polishing process, or both. [0060] In some implementations, the controller 190 generates an alert responsive to the received acoustic signal 300, e.g., to one or more of the segments 322-324 in the signal 300. Examples of the alert can include an audio, or visual alert displayed on a user device. Additional or alternative examples of the alert can include a notification transmitted to a networked device connected to the polishing system 20. [0061] FIG.4 is a flow chart diagram depicting a method of polishing 400 to change a polishing parameter or generate an alert responsive to detected differences in segments of an acoustic signal 300. [0062] The substrate 10 is held against the polishing layer 32 (step 402) of a polishing pad 30 supported by the platen 24, e.g., pressed by pressurizable chambers 80 of the carrier head 70. The substrate 10 is retained beneath the carrier head 70 by a retaining ring 100 which contacts the polishing layer 32 during the polishing operation. [0063] Relative motion is generated between the substrate 10 and the polishing layer 32 (step 404). For example, the polishing system 20 can generate at least a portion of the 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 relative motion by operating the motor 26 to cause the platen 24 to rotate about an axis 25. Additionally or alternatively, the polishing system 20 generates a portion of the relative motion by operating the carrier head rotation motor 56 to cause the carrier head 70 to rotate. In some implementations, the polishing system 20 includes a linear actuator to cause motion of the drive shaft 54 along the support structure 50 which generates a portion of the relative motion between the substrate 10 and the polishing layer 32. Polishing liquid 38 is added to the polishing layer 32 from the supply - rinse arm 36 to enhance the polishing of the substrate 10 surface which contacts the polishing layer 32. [0064] An in-situ acoustic monitoring system 160 (step 406) monitors the carrier head 70 during the polishing operation. The acoustic monitoring system 160 includes the acoustic sensor 162 arranged within the platen 24, for example, within a recess 164 of the platen 24. The acoustic sensor 162 contacts a portion of the polishing pad 30, such as a surface of the backing layer 34. In some implementations, the acoustic sensor 162 contacts a surface of the polishing layer 32. Additionally or alternatively, the polishing layer 32 and/or the backing layer 34 include the acoustic window 118 which the acoustic sensor 162 contacts. [0065] As the acoustic sensor 162 sweeps beneath the carrier head 70 along the path 102, the acoustic sensor 162 receives acoustic energy corresponding to the contact between the retaining ring 100, or the substrate 10, and the polishing layer 32. The acoustic energy is received by the acoustic monitoring system 160, which generates an acoustic signal 300 which is communicated to the controller 190. [0066] The controller 190 receives the acoustic signal 300 and generates a value of a carrier head status parameter based on the received acoustic signal 300 (step 408). The controller 190 can generate the value of the carrier head status parameter by dividing up the received acoustic signal 300 into a sequence of segments, and determining differences between the segments. Alternatively or in addition, the controller 190 generate the value of the carrier head status parameter by determining a difference between different acoustic signals 300 received from different substrates 10. Generating the value can include the following steps 410-414. [0067] The acoustic signal 300 is divided into a sequence of segments, e.g., segments 322- 334, by the controller 190 or by the acoustic monitoring system 160. Determining a difference between segments includes the controller 190 identifying a first segment from the sequence of segments 322-334 (step 410) corresponding to the sensor 162 being beneath a portion of the carrier head 70, or the substrate 10. The segments 322-334 have acoustic parameter values, such as an amplitude value or a variation value. The amplitude/variation 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 values for each of the segments 322-334 is compared against respective thresholds for acoustic signals received from the carrier head 70, the ring assembly 100, or the substrate 10. [0068] The controller 190 identifies a second segment from the sequence of segments 322- 334 (step 412) corresponding to the acoustic sensor 162 being beneath a second portion of the carrier head 70. The second segment corresponds to a different segment from the first segment. [0069] The controller 190 determines a difference between the selected segments (step 414). The controller 190 compares the first and second selected segments and determines a difference. In some examples, the difference that the controller 190 determines includes subtraction, weighted averaging, or performing a mathematical process on the segments and determining a difference between the outcomes of the mathematical process. [0070] The controller 190 changes a polishing parameter, generates an alert, or both, based on the determined difference (step 416). The controller 190 determines the difference between the selected segments, and determines which problem with the polishing process is associated with the difference. Each problem can be associated with a different difference, with the association stored in the controller 190. For example, the problem with the polishing pf[rocess can be a bubble caught between the ring assembly 100 or the substrate 10, and the polishing layer 32 of the pad 30. In one example, bubbles caught between the substrate 10 and the carrier head 72 may produce a difference in the on-wafer segment 328 and historical on-wafer segments stored in the controller 190 from previous polishing operations. As an alternative or additional example, the problem with the polishing process can in the gimbaling of the gimbal mechanism 82. A problem with a gimbaling may produce a difference between the average value and/or maximum value of the leading carrier head section 324 and the trailing carrier head section 332. [0071] In some implementations, the controller 190 determines a polishing parameter corresponding to the associated problem. For example, in instances in which a bubble is between the ring assembly 100 and the polishing layer 32, the controller 190 determines that a pressure value of the carrier head 70 against the polishing layer 32 is to be reduced sufficiently that the bubble exits the space between the ring assembly 100 and the polishing layer 32. [0072] In some examples, the controller 190 determines a difference between the leading carrier head segment 324 and the trailing carrier head segment 332. For example, if the controller 190 determines a difference in the amplitude of the leading carrier head segment 324 and the trailing carrier head segment 332, the controller 190 associates an error in the 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 gimbal position of the gimbal mechanism 82 exists. In one example, the controller 190 increases a pressure in the chamber 84 to alter a height of the assembly 74. In another example, the controller 190 increases a gas pressure in one or more of the pressurizable chambers 80 to indirectly alter an angular orientation of the assembly 74 relative to the housing 72. [0073] In additional or alternative examples, the controller 190 generates an alert based on the determined difference, which can include a visual, audio, textual, or command alert communicated to a user device, a networked device, or a component of the polishing system 20. [0074] FIG.5 is a block diagram of an example computer system 500. The system 500 includes a processor 510, a memory 520, a storage device 530, and one or more input/output interface devices 540. Each of the components 510, 520, 530, and 540 can be interconnected, for example, using a system bus 550. [0075] The processor 510 is capable of processing instructions for execution within the system 500. The term “execution” as used here refers to a technique in which program code causes a processor to carry out one or more processor instructions. In some implementations, the processor 510 is a single-threaded processor. In some implementations, the processor 510 is a multi-threaded processor. The processor 510 is capable of processing instructions stored in the memory 520 or on the storage device 530. The processor 510 may execute operations such as monitoring a polishing process using an acoustic monitoring system as described herein. [0076] The memory 520 stores information within the system 500. In some implementations, the memory 520 is a computer-readable medium. In some implementations, the memory 520 is a volatile memory unit. In some implementations, the memory 520 is a non-volatile memory unit. [0077] The storage device 530 is capable of providing mass storage for the system 500. In some implementations, the storage device 530 is a non-transitory computer-readable medium. In various different implementations, the storage device 530 can include, for example, a hard disk device, an optical disk device, a solid-state drive, a flash drive, magnetic tape, or some other large capacity storage device. In some implementations, the storage device 530 may be a cloud storage device, e.g., a logical storage device including one or more physical storage devices distributed on a network and accessed using a network. [0078] The input/output interface devices 540 provide input/output operations for the system 500. In some implementations, the input/output interface devices 540 can include one 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 or more of a network interface devices, e.g., an Ethernet interface, a serial communication device, e.g., an RS-232 interface, and/or a wireless interface device, e.g., an 802.11 interface, a 3G wireless modem, a 4G wireless modem, etc. A network interface device allows the system 500 to communicate, for example, transmit and receive data. In some implementations, the input/output device can include driver devices configured to receive input data and send output data to other input/output devices, e.g., keyboard, printer and display devices. In some implementations, mobile computing devices, mobile communication devices, and other devices can be used. [0079] Software can be realized by instructions that upon execution cause one or more processing devices to carry out the processes and functions described above, for example, monitoring a polishing process using an acoustic monitoring system as described herein. Such instructions can include, for example, interpreted instructions such as script instructions, or executable code, or other instructions stored in a computer readable medium. [0080] In some examples, the system 500 is contained within a single integrated circuit package. A system500 of this kind, in which both a processor 510 and one or more other components are contained within a single integrated circuit package and/or fabricated as a single integrated circuit, is sometimes called a microcontroller. In some implementations, the integrated circuit package includes pins that correspond to input/output ports, e.g., that can be used to communicate signals to and from one or more of the input/output interface devices 540. [0081] Although an example processing system has been described in FIG.5, implementations of the subject matter and the functional operations described above can be implemented in other types of digital electronic circuitry, or in computer software, firmware, or hardware, including the structures disclosed in this specification and their structural equivalents, or in combinations of one or more of them. Implementations of the subject matter described in this specification, such as storing, maintaining, and displaying artifacts can be implemented as one or more computer program products, i.e., one or more modules of computer program instructions encoded on a tangible program carrier, for example a computer-readable medium, for execution by, or to control the operation of, a processing system. The computer readable medium can be a machine readable storage device, a machine readable storage substrate, a memory device, or a combination of one or more of them. [0082] The term “system” may encompass all apparatus, devices, and machines for processing data, including by way of example a programmable processor, a computer, or multiple processors or computers. A processing system can include, in addition to hardware, 1564255F Attorney Docket No 44020306WO01; 05542-1520WO1 code that creates an execution environment for the computer program in question, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, or a combination of one or more of them. [0083] A computer program (also known as a program, software, software application, script, executable logic, or code) can be written in any form of programming language, including compiled or interpreted languages, or declarative or procedural languages, and it can be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network. [0084] Computer readable media suitable for storing computer program instructions and data include all forms of non-volatile or volatile memory, media and memory devices, including by way of example semiconductor memory devices, e.g., EPROM, EEPROM, and flash memory devices; magnetic disks, e.g., internal hard disks or removable disks or magnetic tapes; magneto optical disks; and CD-ROM, DVD-ROM, and Blu-Ray disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry. Sometimes a server is a general purpose computer, and sometimes it is a custom- tailored special purpose electronic device, and sometimes it is a combination of these things. [0085] While this specification contains many details, these should not be construed as limitations on the scope of what may be claimed, but rather as descriptions of features specific to particular examples. Certain features that are described in this specification in the context of separate implementations can also be combined. Conversely, various features that are described in the context of a single implementation can also be implemented in multiple embodiments separately or in any suitable subcombination. 1564255F