Methods, devices, equipment, storage media and systems for controlling the parameters of polishing pads.

Abstract

This invention relates to the field of integrated circuit technology and discloses a method, apparatus, device, storage medium, and system for parameter control of a polishing pad. The parameter control method for the polishing pad includes: acquiring a sensor's acquisition signal; wherein the acquisition signal is used to characterize the polishing feature parameters of the polishing pad; inputting the acquisition signal into a trained measurement signal analysis model for signal analysis and processing to obtain the polishing feature parameters of the polishing pad; wherein the polishing feature parameters include at least one of surface roughness, trench depth, and thickness, and the measurement signal analysis model is used to analyze the correspondence between the acquisition signal and the polishing feature parameters; adjusting the parameters of the polishing pad based on the polishing feature parameters, which can make the surface roughness of the polishing pad consistent and the grinding amount in local areas of the wafer surface the same during the wafer polishing process, thereby improving the overall process yield.

Description

Technical Field

[0001] This invention relates to the field of integrated circuit technology, and specifically to a method, apparatus, device, storage medium, and system for controlling the parameters of a polishing pad. Background Technology

[0002] With the continuous progress and development of the semiconductor industry, chemical mechanical polishing (CMP) has become an important part of the entire semiconductor process, especially in the chip manufacturing stage. During chip manufacturing, there are extremely high requirements for the surface flatness and surface roughness of wafers. These two requirements directly affect product quality and even the production capacity of higher-end process chips. Traditional chemical mechanical polishing (CMP) uses the interaction between a polishing head, polishing pad, polishing slurry, and polishing tool to grind the wafer surface, thereby controlling the surface roughness and flatness of the wafer to meet the production needs of high-end process chips and the higher requirements for wafer surface quality.

[0003] Furthermore, as chip linewidths become increasingly narrower, the uniformity of wafer surface thickness after polishing in CMP processes becomes increasingly critical. This uniformity is closely related to the characteristics of the polishing pads. However, the polishing pads also experience wear during CMP mass production, leading to a failure to meet the required uniformity of wafer surface thickness (uniformity refers to the difference between the maximum and minimum thickness of a single wafer). Traditional CMP polishing methods address this by manually setting trimming conditions before polishing begins and then polishing the pads during the process. However, these settings are susceptible to human error, easily resulting in severe wear in localized areas of the polishing pad and inconsistent surface roughness. This can lead to insufficient or excessive polishing in certain areas of the wafer surface, necessitating rework or wafer rejection. Consequently, unstable wafer polishing rates occur during mass production, reducing overall process yield. Summary of the Invention

[0004] In view of this, the present invention provides a chemical mechanical polishing method to solve the problem of poor wafer surface quality caused by manually setting polishing pad dressing conditions in related technologies.

[0005] In a first aspect, the present invention provides a parameter control method for a polishing pad, the method comprising: acquiring a sensor acquisition signal; wherein the acquisition signal is used to characterize the polishing feature parameters of the polishing pad; inputting the acquisition signal into a trained measurement signal analysis model for signal analysis processing to obtain the polishing feature parameters of the polishing pad; wherein the polishing feature parameters include at least one of surface roughness, groove depth, and thickness, and the measurement signal analysis model is used to analyze the correspondence between the acquisition signal and the polishing feature parameters; and adjusting the parameters of the polishing pad based on the polishing feature parameters.

[0006] In one optional implementation, adjusting the parameters of the polishing pad based on the polishing characteristic parameters includes: acquiring the signal acquisition time of the acquired signal; determining the polishing cycle information of the acquired signal based on the signal acquisition time; extracting the actual influence parameter from the polishing characteristic parameters based on the polishing cycle information; wherein the actual influence parameter is used to determine the adjustment range of the polishing pad parameters; and adjusting the polishing pad parameters based on the actual influence parameter.

[0007] In one optional implementation, the polishing cycle information includes early polishing, middle polishing, and late polishing according to polishing time. Based on the polishing cycle information, actual influencing parameters are extracted from the polishing feature parameters, including: if the polishing cycle information is early polishing or late polishing, all categories of parameters in the polishing feature parameters are used as actual influencing parameters; if the polishing cycle information is middle polishing, at least one category of parameters in the polishing feature parameters are extracted as actual influencing parameters.

[0008] In one optional implementation, adjusting the parameters of the polishing pad based on the actual influence parameters includes: obtaining the historical influence parameters corresponding to the actual influence parameters; calculating the degree of difference between the actual influence parameters and the historical influence parameters; and adjusting the parameters of the polishing pad based on the degree of difference; wherein the degree of difference is positively correlated with the parameters of the polishing pad.

[0009] In one optional implementation, adjusting the parameters of the polishing pad based on the degree of difference includes: obtaining category information of the actual influencing parameters; when the category information indicates that the actual influencing parameters can be divided into multiple categories, obtaining the degree of difference of each category of influencing parameters as a weight parameter; determining the adjustment weight of each actual influencing parameter when adjusting the parameters of the polishing pad based on the weight parameter; and adjusting the parameters of the polishing pad based on the adjustment weight and the actual influencing parameters.

[0010] In one optional implementation, the process of constructing a measurement signal analysis model includes: acquiring historical acquisition signals of the sensor and corresponding historical polishing feature parameters; training a neural network model based on the historical acquisition signals and historical polishing feature parameters; during the training process, using the neural network model to learn the correspondence between historical acquisition signals and historical polishing feature parameters to obtain the measurement signal analysis model.

[0011] Secondly, the present invention provides a parameter control device for a polishing pad, the parameter control device comprising: an acquisition module for acquiring a sensor acquisition signal; wherein the sensor is used to detect characteristic parameters of the polishing pad; an analysis module for inputting the acquisition signal into a measurement signal analysis model for signal analysis and processing to obtain polishing characteristic parameters of the polishing pad; wherein the polishing characteristic parameters include at least one of surface roughness, groove depth, and thickness; and an adjustment module for adjusting the parameters of the polishing pad based on the polishing characteristic parameters.

[0012] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the parameter control method for the polishing pad described in the first aspect or any corresponding embodiment thereof.

[0013] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the parameter control method for a polishing pad according to the first aspect or any corresponding embodiment thereof.

[0014] Fifthly, the present invention provides a parameter control system for a polishing pad, comprising: a polishing device, a polishing pad, a sensor, and a controller; the polishing device includes a transmission mechanism and a polishing mechanism; one end of the transmission mechanism is connected to the polishing mechanism, the polishing mechanism includes a rotating rod and a grinding wheel, one end of the grinding wheel is connected to the transmission mechanism, and the grinding wheel, under the enable of the transmission mechanism, polishes and trims the polishing pad with the rotation axis of the rotating rod as the polishing center; the grinding wheel includes a metal substrate and a plurality of grinding wheel diamonds; the geometric center of the metal substrate coincides with the rotation axis of the rotating rod, and the grinding wheel diamonds have a regular octahedral structure; the sensor is disposed on one side of the polishing device, with the detection end of the sensor facing the polishing pad, to detect the characteristic parameters of the polishing pad and transmit the characteristic parameters to the controller; the controller acquires the acquisition signal from the sensor; inputs the acquisition signal into a trained measurement signal analysis model for signal analysis and processing to obtain the polishing characteristic parameters of the polishing pad; and adjusts the parameters of the polishing pad based on the polishing characteristic parameters.

[0015] This invention provides a method, apparatus, device, storage medium, and system for parameter control of a polishing pad. The parameter control method includes: acquiring a sensor's acquisition signal; wherein the acquisition signal is used to characterize the polishing feature parameters of the polishing pad; inputting the acquisition signal into a trained measurement signal analysis model for signal analysis processing to obtain the polishing feature parameters of the polishing pad; wherein the polishing feature parameters include at least one of surface roughness, trench depth, and thickness, and the measurement signal analysis model is used to analyze the correspondence between the acquisition signal and the polishing feature parameters; adjusting the parameters of the polishing pad based on the polishing feature parameters; by implementing the parameter control method for the polishing pad provided in this embodiment, the surface roughness of the polishing pad can be made consistent during wafer polishing, and the amount of grinding in local areas of the wafer surface can be the same, thereby improving the overall process yield. Attached Figure Description

[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating a method for controlling the parameters of a polishing pad according to an embodiment of the present invention.

[0018] Figure 2 This is a flowchart illustrating another parameter control method for a polishing pad according to an embodiment of the present invention;

[0019] Figure 3 This is a structural block diagram of a parameter control device for a polishing pad according to an embodiment of the present invention;

[0020] Figure 4 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention;

[0021] Figure 5 This is a structural diagram of a parameter control system according to an embodiment of the present invention;

[0022] Figure 6 This is a schematic diagram of the structure of a grinding wheel according to an embodiment of the present invention;

[0023] Figure 7A This is a structural diagram of diamond grinding wheels in related technologies;

[0024] Figure 7B This is a structural diagram of a grinding wheel according to an embodiment of the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] In traditional CMP processes, the degree of wafer surface planarization is mainly controlled by changing the pressure of the polishing head and the area of ​​the air pressure distribution in the polishing head. For example, it can be achieved by controlling the pressure of the polishing head to X inch and the area of ​​the air pressure distribution in the polishing head to Y Zone head a; where X and Y are positive integers.

[0027] During the grinding process, the surface roughness of the polishing pad will also change. Particles in the polishing liquid will remain in the pores of the polishing pad. The grinder can change the surface roughness of the polishing pad and remove the by-products left after grinding.

[0028] In related technologies, the finishing conditions are typically manually set to control the parameters of the polishing pad by pre-determining the characteristic parameters of the polishing pad or the polisher, such as surface roughness, thickness, and / or trench depth. This method does not affect the surface roughness of the polishing pad during the polishing process. However, the characteristic parameters of the polishing pad directly affect the surface quality of the wafer grinding.

[0029] However, the settings parameters of the above-mentioned method are affected by human judgment, which can easily cause severe wear in some areas of the polishing pad and inconsistent surface roughness. This can lead to insufficient or excessive polishing in some areas of the wafer surface. In this case, the abnormal wafers can only be reworked or discarded, resulting in unstable wafer polishing rates during mass production and reducing the overall process yield.

[0030] Therefore, the problem of poor wafer surface quality caused by manually setting the polishing pad dressing conditions in related technologies exists.

[0031] Based on this, according to an embodiment of the present invention, a method for controlling the parameters of a polishing pad is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0032] This embodiment provides a method for controlling the parameters of a polishing pad. Figure 1This is a flowchart of a parameter control method for a polishing pad according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0033] Step S101: Acquire the sensor's acquisition signal; wherein the acquisition signal is used to characterize the polishing feature parameters of the polishing pad.

[0034] During wafer polishing, the wafer contacts the polishing pad via a polishing head. The relative movement between the wafer and the polishing pad achieves the polishing of the wafer. Simultaneously, the polisher carries a grinding wheel with several diamonds on it. These diamonds contact the polishing pad, and the relative movement between the diamonds and the polishing pad via the grinding wheel further polishes the pad. In this embodiment, a sensor is used to collect the polishing characteristic parameters of the polishing pad. Exemplarily, the sensor's detection end is positioned towards the polishing pad and can be positioned opposite the grinding wheel to collect the polishing characteristic parameters of the polishing pad in real time during the polishing process as the grinding wheel moves.

[0035] Specifically, the sensor performs round-robin data acquisition with a preset acquisition duration. To avoid sensor acquisition errors, multiple different monitoring positions can be set on the polishing pad during each round of acquisition, and the sensor's acquisition signal is acquired at each monitoring position. During each round of acquisition, multiple acquisition signals from the sensor are acquired, and error analysis is performed on the multiple acquisition signals. Acquisition signals with actual errors greater than the preset error are eliminated, and the more accurate acquisition signals are retained for subsequent processing.

[0036] For example, the preset collection duration can be 0.5h, 1h, 1.5h...Nh, where N is a real number greater than zero.

[0037] For example, the sensor can be a photoelectric sensor.

[0038] Step S102: The acquired signal is input into the trained measurement signal analysis model for signal analysis and processing to obtain the polishing characteristic parameters of the polishing pad; wherein, the polishing characteristic parameters include at least one of surface roughness, groove depth and thickness, and the measurement signal analysis model is used to analyze the correspondence between the acquired signal and the polishing characteristic parameters.

[0039] In this embodiment, the acquired signal is a digital-analog signal acquired by a sensor. In order to convert the digital-analog signal into polishing feature parameters of the polishing pad that can be processed, the acquired signal is input into a trained measurement signal analysis model for signal analysis and processing to obtain polishing feature parameters. The polishing feature parameters include at least one of surface roughness, groove depth and thickness. The measurement signal analysis model is used to analyze the correspondence between the acquired signal and the polishing feature parameters.

[0040] For example, after acquiring the collected signal, the measurement signal analysis model processes the collected signal and converts it into parameters representing the surface roughness, groove depth, and thickness of the polishing pad; for example, surface roughness Anm, groove depth B micrometers, and thickness C centimeters; where A, B, and C are all real numbers greater than or equal to zero.

[0041] For example, the measurement signal analysis model can be a machine learning model or a deep learning model; in this embodiment, the measurement signal analysis model is a machine learning model, specifically, a neural network model; after training, the neural network model can output corresponding polishing feature parameters based on the input acquisition signal.

[0042] Step S103: Adjust the parameters of the polishing pad based on the polishing feature parameters.

[0043] During the polishing process, the polishing characteristic parameters are typically related to the pressure applied by the grinding wheel and the penetration depth of the diamond on the grinding wheel surface into the polishing pad. Specifically, the greater the pressure applied to the polisher, the greater the penetration depth of the polisher, the greater the variation in the thickness and groove depth of the polishing pad, and the greater the variation in the surface roughness of the polishing pad. Conversely, the smaller the pressure applied to the polisher, the smaller the penetration depth of the polisher, the smaller the variation in the thickness and groove depth of the polishing pad, and the smaller the variation in the surface roughness of the polishing pad. Therefore, in this embodiment, adjusting the parameters of the polishing pad based on the polishing characteristic parameters can specifically involve adjusting the pressure applied by the grinding wheel based on the polishing characteristic parameters to change the polishing intensity of the grinding wheel on the polishing pad, thereby making the surface roughness of the polishing pad uniform and the polishing amount in local areas of the wafer surface the same, solving the problem of poor wafer surface quality caused by manually setting the polishing pad dressing conditions in related technologies.

[0044] By implementing the parameter control method for the polishing pad provided in this embodiment, the sensor's acquisition signal is obtained, and the acquisition signal is input into a trained measurement signal analysis model for signal analysis and processing to obtain the polishing characteristic parameters of the polishing pad. Based on the polishing characteristic parameters, the parameters of the polishing pad are adjusted, which can make the surface roughness of the polishing pad consistent and the grinding amount in local areas of the wafer surface the same during the wafer polishing process, thereby improving the overall process yield.

[0045] This embodiment provides a method for controlling the parameters of a polishing pad. Figure 2 This is a flowchart of another parameter control method for a polishing pad according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0046] Step S201: Acquire the sensor's data acquisition signal. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0047] Step S202 involves inputting the acquired signal into a trained measurement signal analysis model for signal analysis and processing to obtain the polishing characteristic parameters of the polishing pad. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0048] Step S203: Adjust the parameters of the polishing pad based on the polishing feature parameters.

[0049] The inventors discovered that the polishing process can be divided into early polishing, mid-polishing, and late polishing according to time. Throughout the polishing process, the thickness, groove depth, and surface roughness of the polishing pad continuously change. In the early polishing stage, the changing trends of each polishing characteristic parameter are different. After reaching the preset early polishing time, the process enters the mid-polishing stage, where the polishing characteristic parameters of the polishing pad maintain a linear change curve. After reaching the preset mid-polishing time, the process enters the late polishing stage, where the changing trends of the polishing characteristic parameters of the polishing pad tend to be different. Therefore, to consider the changing trends of each polishing characteristic parameter over time, this application allows for the selection of different polishing characteristic parameters based on the signal acquisition time of the acquired signal to adjust the parameters of the polishing pad.

[0050] Based on this, specifically, step S203 above includes:

[0051] Step S2031: Obtain the signal acquisition time of the acquired signal.

[0052] In this embodiment, the signal acquisition time of the current acquired signal is recorded each time a signal is acquired through the sensor; when the acquired signal is input into the trained measurement signal analysis model for signal analysis and processing, the signal acquisition time corresponding to each measurement signal is assigned to the corresponding analysis result.

[0053] Step S2032: Determine the polishing cycle information of the acquired signal based on the signal acquisition time.

[0054] In this embodiment, the polishing start time is recorded at the beginning of polishing. After the signal acquisition time of the acquired signal is obtained, the actual polishing duration is obtained by subtracting the signal acquisition time from the polishing start time. The actual polishing duration is then compared with a preset early polishing duration and a preset mid-polishing duration. If the actual polishing duration is less than the preset early polishing duration, the polishing cycle in which the acquired signal is located is confirmed to be the early polishing stage. If the actual polishing duration is greater than the preset early polishing duration but less than the preset mid-polishing duration, the polishing cycle in which the acquired signal is located is confirmed to be the mid-polishing stage. If the actual polishing duration is greater than the preset mid-polishing duration, the polishing cycle in which the acquired signal is located is confirmed to be the late polishing stage.

[0055] Step S2033: Extract the actual influencing parameters from the polishing feature parameters based on the polishing cycle information.

[0056] Throughout the polishing process, the thickness of the polishing pad, the depth of the grooves, and the surface roughness will continuously decrease; however, the changing trends of each polishing characteristic parameter in different polishing cycles can be either the same or different. Therefore, in this embodiment, the actual influencing parameters are extracted from the polishing characteristic parameters based on the polishing cycle information.

[0057] Throughout the polishing process, the thickness, groove depth, and surface roughness of the polishing pad will continuously change. In the early polishing stage, the changing trends of the various polishing characteristic parameters of the polishing pad are not related. Therefore, in the early polishing stage, all polishing characteristic parameters of the polishing pad, including thickness, groove depth, and surface roughness, are taken as the actual influencing parameters.

[0058] During the intermediate polishing stage, the various grinding characteristic parameters of the polishing pad maintain a linear variation curve; therefore, during the intermediate polishing stage, at least one of the polishing pad thickness, groove depth, and surface roughness is extracted from the grinding characteristic parameters as the actual influencing parameter.

[0059] In the late polishing stage, the changing trends of the various polishing characteristic parameters of the polishing pad are not related, and the polishing characteristic parameters of the polishing pad tend to be different; therefore, in the late polishing stage, all polishing characteristic parameters of the polishing pad thickness, groove depth and surface roughness are taken as actual influencing parameters.

[0060] Based on this, in some optional implementations, step S2023 includes:

[0061] Step a1: If the polishing cycle information is early polishing or late polishing, all categories of parameters in the polishing feature parameters are used as actual influencing parameters.

[0062] Step a2: If the polishing cycle information is in the middle of the polishing process, extract parameters of at least one category of the polishing feature parameters as actual influencing parameters.

[0063] Step S2034: Adjust the parameters of the polishing pad based on the actual influencing parameters.

[0064] Specifically, adjusting the polishing pad parameters based on actual influence parameters can be achieved by adjusting the polishing pad parameters according to the difference between the currently obtained actual influence parameters and historical influence parameters; based on this, step S2024 includes:

[0065] Step b1: Obtain the historical impact parameters corresponding to the actual impact parameters.

[0066] For example, the historical impact parameter can be determined by the historical acquisition signal of the sensor; specifically, the historical acquisition signal can be the impact parameter obtained from the historical acquisition signal of the previous round of acquisition; for example, the historical impact parameter can be the grinding characteristic parameter obtained according to the analysis model of the acquisition signal and measurement signal during the previous round of signal acquisition.

[0067] For example, the historical influence parameter can also be the historical output result of the control sensor to perform multiple signal acquisitions before polishing, based on the historical output of the acquisition and measurement signal analysis model.

[0068] Step b2: Calculate the degree of difference between the actual impact parameters and the historical impact parameters.

[0069] For example, the degree of difference can be the difference between the actual impact and the historical impact parameters.

[0070] Step b3: Adjust the parameters of the polishing pad based on the degree of difference; wherein the degree of difference is positively correlated with the parameters of the polishing pad.

[0071] In this embodiment, when the difference is large, it indicates that the polishing pad is worn more during the polishing process. In this case, the pressure value on the grinder is increased to allow the grinder to penetrate deeper, thereby increasing the grinding of the polishing pad and adjusting the parameters of the polishing pad. When the difference is small, it indicates that the polishing pad is worn less during the polishing process. In this case, the pressure value on the grinder is decreased to allow the grinder to penetrate less, thereby reducing the grinding of the polishing pad and adjusting the parameters of the polishing pad.

[0072] In the process of adjusting the parameters of the polishing pad based on the degree of difference, there are scenarios where multiple types of actual influencing parameters are used for adjustment; for this scenario, step b3 specifically includes:

[0073] Obtain the category information of the actual influencing parameters; when the category information indicates that the actual influencing parameters can be divided into multiple categories, obtain the degree of difference of each category of influencing parameters as a weight parameter; determine the adjustment weight of each actual influencing parameter when adjusting the parameters of the polishing pad based on the weight parameter; adjust the parameters of the polishing pad based on the adjustment weight and the actual influencing parameters.

[0074] In this embodiment, when the category information indicates that the actual impact parameters can be divided into multiple categories, it indicates that the scenario is where multiple categories of actual impact parameters are used for adjustment.

[0075] In this scenario, the degree of difference of each type of influence parameter is obtained as a weight parameter. Specifically, the degree of difference can be obtained by accumulating the historical influence parameters collected in each round; for example, the weight parameter can be the slope of the curve fitted by the historical influence parameters collected in each round.

[0076] Furthermore, the adjustment weights of each actual influencing parameter when adjusting the parameters of the polishing pad are determined based on the weight parameters. This can be achieved by summing the adjustment weights of each actual influencing parameter to 1, and by making the adjustment weight of each actual influencing parameter proportional to its corresponding weight parameter.

[0077] In some optional implementations, the process of constructing a measurement signal analysis model includes: acquiring historical acquisition signals of the sensor and corresponding historical polishing feature parameters; training a neural network model based on the historical acquisition signals and historical polishing feature parameters; during the training process, using the neural network model to learn the correspondence between historical acquisition signals and historical polishing feature parameters to obtain the measurement signal analysis model.

[0078] In some alternative implementations, the method for controlling the parameters of the polishing pad further includes:

[0079] Using a preset wear acquisition time as the period, the actual size value of the diamond is determined based on the acquired signal; the degree of wear of the diamond is determined based on the actual size value.

[0080] In this embodiment, the correspondence between the diamond size value and the sensor's acquired signal value can be predetermined to obtain the correspondence between the diamond size and the acquired signal value. Before the grinding begins, the sensor is controlled to acquire data multiple times, and the initial size information of the diamond is obtained according to the acquired signals. During the grinding process, the actual size value of the diamond is determined according to the acquired signals with a preset wear acquisition time as the cycle. The actual size value is subtracted from the initial size information to obtain the degree of wear of the diamond.

[0081] For example, the preset wear acquisition time can be 0.5h, 1h, 1.5h...Nh, etc., where N is a real number greater than zero; for example, the preset wear acquisition time can be 5h.

[0082] This embodiment also provides a parameter control device for a polishing pad, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0083] This embodiment provides a parameter control device for a polishing pad, such as... Figure 3 As shown, it includes:

[0084] The acquisition module 301 is used to acquire the sensor's collected signals.

[0085] The analysis module 302 is used to input the acquired signal into the measurement signal analysis model for signal analysis and processing to obtain the polishing characteristic parameters of the polishing pad.

[0086] The adjustment module 303 is used to adjust the parameters of the polishing pad based on the grinding feature parameters.

[0087] In some alternative implementations, the adjustment module 302 includes:

[0088] The time acquisition unit is used to acquire the signal acquisition time of the acquired signal.

[0089] The information determination unit is used to determine the polishing cycle information of the acquired signal based on the signal acquisition time.

[0090] The influence parameter extraction unit is used to extract the actual influence parameters from the polishing feature parameters based on the polishing cycle information.

[0091] The adjustment unit is used to adjust the parameters of the polishing pad based on the actual influencing parameters.

[0092] In some optional implementations, the extraction unit includes:

[0093] The first extraction subunit is used to take all categories of parameters in the polishing feature parameters as actual influencing parameters when the polishing cycle information is in the early or late stage of polishing.

[0094] The second extraction subunit is used to extract parameters of at least one category of the polishing feature parameters as actual influence parameters when the polishing cycle information is in the middle of the polishing process.

[0095] In some optional implementations, the adjustment unit includes:

[0096] The impact parameter acquisition subunit is used to obtain the historical impact parameters corresponding to the actual impact parameters.

[0097] The calculation sub-unit is used to calculate the degree of difference between the actual impact parameters and the historical impact parameters.

[0098] The adjustment subunit is used to adjust the parameters of the polishing pad based on the degree of difference; wherein the degree of difference is positively correlated with the parameters of the polishing pad.

[0099] In some optional implementations, the adjustment subunit obtains category information of the actual influencing parameters; when the category information indicates that the actual influencing parameters can be divided into multiple categories, the degree of difference of each category of influencing parameters is obtained as a weight parameter; and the adjustment weight of each actual influencing parameter is determined based on the weight parameter when adjusting the parameters of the polishing pad.

[0100] In some optional embodiments, the parameter control device for the polishing pad further includes: a measurement analysis model construction module, which includes:

[0101] The historical parameter acquisition unit is used to acquire the historical acquisition signals of the sensor and the corresponding historical grinding characteristic parameters.

[0102] The model training unit is used to train the neural network model based on historical acquisition signals and historical polishing feature parameters. During the training process, the neural network model learns the correspondence between historical acquisition signals and historical polishing feature parameters to obtain the measurement signal analysis model.

[0103] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0104] In this embodiment, the parameter control device for the polishing pad is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0105] This invention also provides a computer device having the above-described features. Figure 3 The parameter control device for the polishing pad shown.

[0106] Please see Figure 4 , Figure 4 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 4 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 4 Take a processor 10 as an example.

[0107] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0108] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0109] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0110] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0111] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0112] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0113] This invention also provides a parameter control system for a polishing pad. Figure 5 This is a structural diagram of a parameter control system according to an embodiment of the present invention, such as... Figure 5 As shown, the parameter control system includes: a grinding device 51, a polishing pad 52, a sensor 53, and a controller 54;

[0114] The polishing device 51 includes a transmission mechanism 511 and a polishing mechanism 512. One end of the transmission mechanism 511 is connected to the polishing mechanism 512. The polishing mechanism 512 includes a rotating rod 5121 and a grinding wheel 5122. One end of the grinding wheel 5122 is connected to the transmission mechanism 511. Under the enable of the transmission mechanism 511, the grinding wheel 5122 polishes and trims the polishing pad 52 with the rotation axis of the rotating rod 5121 as the polishing center.

[0115] The untreated diamond grinding wheels in the related technology are irregularly shaped. During the grinding process, the diamond tip height on the grinding wheel surface is inconsistent, resulting in a high rate of decrease in the cutting efficiency of the dresser, affecting its service life. At the same time, it will cause differences in the surface roughness of different areas of the polishing pad, which will have an adverse effect on the CMP process. Furthermore, it will cause differences in the accuracy of the data when monitoring the polishing pad.

[0116] To solve this problem, Figure 6 This is a schematic diagram of the structure of a grinding wheel according to an embodiment of the present invention. Figure 7A This is a structural diagram of the diamond grinding wheel in related technologies. Figure 7B This is a structural diagram of a grinding wheel according to an embodiment of the present invention, such as... Figure 6 , Figure 7A and Figure 7B As shown, the grinding wheel 5122 includes a metal substrate 61 and a plurality of grinding wheel diamonds 62; the geometric center of the metal substrate 61 coincides with the rotation axis of the rotating rod 5121.

[0117] like Figure 7A As shown, the untreated diamond grinding wheel has an irregular shape. During the grinding process, due to the inconsistent height of the diamond tip on the grinding wheel surface, on the one hand, the cutting efficiency of the dresser decreases significantly, affecting its service life; on the other hand, it also causes differences in surface roughness in different areas of the polishing pad, which has an adverse effect on the CMP process; and on the other hand, it affects the accuracy of monitoring the grinding characteristic parameters of the polishing pad.

[0118] In this invention, the diamond 62 in the grinding wheel is... Figure 7BThe octahedral structure shown ensures that the grinding wheel can maintain a consistent depth of penetration into the polishing pad during CMP polishing, effectively improving the uneven surface roughness of the polishing pad. Furthermore, the consistent penetration depth allows for more precise monitoring of the wear level of the polishing pad, avoiding the impact of inconsistent diamond wheel sizes on measurement results.

[0119] Sensor 53 is disposed on one side of the polishing device, with the detection end of sensor 53 facing the polishing pad 52, in order to detect the characteristic parameters of polishing pad 52 and transmit the characteristic parameters to the controller;

[0120] The controller 54 acquires the collected signals from the sensor 53; inputs the collected signals into a trained measurement signal analysis model for signal analysis and processing to obtain the polishing characteristic parameters of the polishing pad 52; and adjusts the parameters of the polishing pad 52 based on the polishing characteristic parameters. For details of the process, please refer to the specific descriptions in any of the above embodiments, which will not be repeated here.

[0121] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for controlling the parameters of a polishing pad, characterized in that, The parameter control method for the polishing pad includes: Acquire the sensor's acquisition signal; wherein the acquisition signal is used to characterize the polishing feature parameters of the polishing pad; The acquired signal is input into a trained measurement signal analysis model for signal analysis and processing to obtain the polishing characteristic parameters of the polishing pad; wherein, the polishing characteristic parameters include at least one of surface roughness, groove depth and thickness, and the measurement signal analysis model is used to analyze the correspondence between the acquired signal and the polishing characteristic parameters; The parameters of the polishing pad are adjusted based on the aforementioned polishing characteristic parameters; The adjustment of the parameters of the polishing pad based on the polishing characteristic parameters includes: Obtain the signal acquisition time of the acquired signal; The polishing cycle information of the acquired signal is determined based on the signal acquisition time; Based on the polishing cycle information, actual influencing parameters are extracted from the polishing feature parameters; wherein, the actual influencing parameters are used to determine the adjustment range of the polishing pad parameters; The parameters of the polishing pad are adjusted based on the actual influencing parameters. The polishing cycle information includes early polishing, middle polishing, and late polishing according to polishing time. The extraction of actual influencing parameters from the polishing characteristic parameters based on the polishing cycle information includes: If the polishing cycle information is early polishing or late polishing, all categories of parameters in the polishing characteristic parameters will be used as the actual influencing parameters. If the polishing cycle information is in the middle of the polishing process, extract parameters of at least one category of the polishing feature parameters as the actual influencing parameters; The adjustment of the polishing pad parameters based on the actual influence parameters includes: Obtain the historical impact parameters corresponding to the actual impact parameters; Calculate the degree of difference between the actual impact parameters and the historical impact parameters; The parameters of the polishing pad are adjusted based on the degree of difference; wherein the degree of difference is positively correlated with the parameters of the polishing pad. The adjustment of the parameters of the polishing pad based on the degree of difference includes: Obtain the category information of the actual impact parameters; When the category information indicates that the actual impact parameter can be divided into multiple categories, the degree of difference of the impact parameter in each category is obtained as a weight parameter; The adjustment weights of each actual influencing parameter are determined based on the weight parameters when adjusting the parameters of the polishing pad. The parameters of the polishing pad are adjusted based on the adjusted weights and the actual influence parameters.

2. The parameter control method for the polishing pad according to claim 1, characterized in that, The process of constructing the measurement signal analysis model includes: Acquire the historical acquisition signals of the sensor and the corresponding historical polishing feature parameters; The neural network model is trained based on the historical acquisition signals and the historical polishing feature parameters. During the training process, the neural network model learns the correspondence between the historical acquisition signals and the historical polishing feature parameters to obtain the measurement signal analysis model.

3. A parameter control device for a polishing pad, characterized in that, The parameter control device for the polishing pad includes: An acquisition module is used to acquire the collected signals from the sensor; wherein the sensor is used to detect the characteristic parameters of the polishing pad; The analysis module is used to input the acquired signal into the measurement signal analysis model for signal analysis and processing to obtain the polishing characteristic parameters of the polishing pad; wherein, the polishing characteristic parameters include at least one of surface roughness, groove depth and thickness; An adjustment module is used to adjust the parameters of the polishing pad based on the grinding characteristic parameters; The adjustment of the parameters of the polishing pad based on the polishing characteristic parameters includes: Obtain the signal acquisition time of the acquired signal; The polishing cycle information of the acquired signal is determined based on the signal acquisition time; Based on the polishing cycle information, actual influencing parameters are extracted from the polishing feature parameters; wherein, the actual influencing parameters are used to determine the adjustment range of the polishing pad parameters; The parameters of the polishing pad are adjusted based on the actual influencing parameters. The polishing cycle information includes early polishing, middle polishing, and late polishing according to polishing time. The extraction of actual influencing parameters from the polishing characteristic parameters based on the polishing cycle information includes: If the polishing cycle information is early polishing or late polishing, all categories of parameters in the polishing characteristic parameters will be used as the actual influencing parameters. If the polishing cycle information is in the middle of the polishing process, extract parameters of at least one category of the polishing feature parameters as the actual influencing parameters; The adjustment of the polishing pad parameters based on the actual influence parameters includes: Obtain the historical impact parameters corresponding to the actual impact parameters; Calculate the degree of difference between the actual impact parameters and the historical impact parameters; The parameters of the polishing pad are adjusted based on the degree of difference; wherein the degree of difference is positively correlated with the parameters of the polishing pad. The adjustment of the parameters of the polishing pad based on the degree of difference includes: Obtain the category information of the actual impact parameters; When the category information indicates that the actual impact parameter can be divided into multiple categories, the degree of difference of the impact parameter in each category is obtained as a weight parameter; The adjustment weights of each actual influencing parameter are determined based on the weight parameters when adjusting the parameters of the polishing pad. The parameters of the polishing pad are adjusted based on the adjusted weights and the actual influence parameters.

4. A computer device, characterized in that, include: The device includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the parameter control method for the polishing pad according to claim 1 or 2.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to execute the parameter control method for the polishing pad according to claim 1 or 2.

6. A parameter control system for a polishing pad, characterized in that, The parameter control system includes: a grinding device, a polishing pad, a sensor, and a controller; The polishing device includes a transmission mechanism and a polishing mechanism; one end of the transmission mechanism is connected to the polishing mechanism, and the polishing mechanism includes a rotating rod and a grinding wheel. One end of the grinding wheel is connected to the transmission mechanism. Under the enable of the transmission mechanism, the grinding wheel polishes and trims the polishing pad with the rotation axis of the rotating rod as the polishing center. The grinding wheel includes a metal substrate and a plurality of grinding wheel diamonds; the geometric center of the metal substrate coincides with the rotation axis of the rotating rod, and the grinding wheel diamonds have a regular octahedral structure; The sensor is disposed on one side of the polishing device, with the detection end of the sensor facing the polishing pad, so as to detect the characteristic parameters of the polishing pad and transmit the characteristic parameters to the controller; The controller acquires the sensor's collected signals; inputs the collected signals into a trained measurement signal analysis model for signal analysis and processing to obtain the polishing characteristic parameters of the polishing pad; and adjusts the parameters of the polishing pad based on the polishing characteristic parameters. The adjustment of the parameters of the polishing pad based on the polishing characteristic parameters includes: Obtain the signal acquisition time of the acquired signal; The polishing cycle information of the acquired signal is determined based on the signal acquisition time; Based on the polishing cycle information, actual influencing parameters are extracted from the polishing feature parameters; wherein, the actual influencing parameters are used to determine the adjustment range of the polishing pad parameters; The parameters of the polishing pad are adjusted based on the actual influencing parameters. The polishing cycle information includes early polishing, middle polishing, and late polishing according to polishing time. The extraction of actual influencing parameters from the polishing characteristic parameters based on the polishing cycle information includes: If the polishing cycle information is early polishing or late polishing, all categories of parameters in the polishing characteristic parameters will be used as the actual influencing parameters. If the polishing cycle information is in the middle of the polishing process, extract parameters of at least one category of the polishing feature parameters as the actual influencing parameters; The adjustment of the polishing pad parameters based on the actual influence parameters includes: Obtain the historical impact parameters corresponding to the actual impact parameters; Calculate the degree of difference between the actual impact parameters and the historical impact parameters; The parameters of the polishing pad are adjusted based on the degree of difference; wherein the degree of difference is positively correlated with the parameters of the polishing pad. The adjustment of the parameters of the polishing pad based on the degree of difference includes: Obtain the category information of the actual impact parameters; When the category information indicates that the actual impact parameter can be divided into multiple categories, the degree of difference of the impact parameter in each category is obtained as a weight parameter; The adjustment weights of each actual influencing parameter are determined based on the weight parameters when adjusting the parameters of the polishing pad. The parameters of the polishing pad are adjusted based on the adjusted weights and the actual influence parameters.

Images