Method and apparatus for detecting a cracked lamp housing

Abstract

This specification provides a method and apparatus for detecting a lamp housing crack. For example, a method related to a process chamber having a lamp housing includes sequentially processing a plurality of substrates within the process chamber, collecting lamp housing data indicating fluid leakage within the lamp housing from a sensor operably connected to the lamp housing of the process chamber during processing of the plurality of substrates, determining from the lamp housing data whether a lamp housing crack exists, and performing at least one of issuing an alarm or stopping the processing of the process chamber in response to determining that a lamp housing crack exists.

Description

Technical Field

[0001] Embodiments of the present disclosure generally relate to methods and apparatuses for processing substrates, such as methods and apparatuses for detecting lamp housing cracks.

Background Art

[0002] It is known to use radiant heat sources for substrate processing. For example, a vacuum chamber and an atmospheric chamber can include a lamp housing having one or more lamps configured to heat one or more substrates to a relatively high temperature (e.g., for an annealing process, removal of oxidation, etc.). However, after long-term use, the lamp housing (and / or one or more lamps) can develop cracks (see FIG. 1 below). A cracked lamp housing can leak cooling water onto the quartz window through which light can radiate within and / or through the lamp tube of the lamp. As a result, the process chamber requires a relatively long unscheduled downtime and post-maintenance to replace the lamp housing, remove the water leak, and address additional failures of the lamp and / or associated components due to water ingress.

Summary of the Invention

Problems to be Solved by the Invention

[0003] Accordingly, the inventors of the present invention describe herein improved methods and apparatuses for detecting lamp housing cracks.

Means for Solving the Problems

[0004] This specification provides a method and an apparatus for detecting a lamp housing crack. In some embodiments, a method related to a process chamber having a lamp housing includes sequentially processing a plurality of substrates in the process chamber, collecting lamp housing data indicative of fluid leakage in the lamp housing from a sensor operably connected to the lamp housing of the process chamber during the processing of the plurality of substrates, determining whether a lamp housing crack exists from the lamp housing data, and performing at least one of issuing an alarm or stopping the processing of the process chamber in response to determining that a lamp housing crack exists.

[0005] In at least some embodiments, a non-transitory computer-readable storage medium has instructions stored thereon that, when executed by a process, perform a method of using a lamp housing to process substrates. The method includes sequentially processing a plurality of substrates in the process chamber, collecting lamp housing data indicative of fluid leakage in the lamp housing from a sensor operably connected to the lamp housing of the process chamber during the processing of the plurality of substrates, determining whether a lamp housing crack exists from the lamp housing data, and performing at least one of issuing an alarm or stopping the processing of the process chamber in response to determining that a lamp housing crack exists.

[0006] In at least some embodiments, an apparatus for processing a substrate comprises a process chamber configured to process the substrate using radiant heat provided by a lamp housing, a sensor operably connected to the lamp housing, and a controller. The controller sequentially processes a plurality of substrates within the process chamber and, during the processing of the plurality of substrates, collects lamp housing data indicative of a fluid leak within the lamp housing from a sensor operably connected to the lamp housing of the process chamber, determines from the lamp housing data whether a lamp housing crack exists, and is configured to perform at least one of issuing an alarm or stopping the processing of the process chamber in response to determining that a lamp housing crack exists.

[0007] Other embodiments and additional embodiments of the present disclosure are described below.

[0008] The embodiments of the present disclosure outlined above and discussed in more detail later can be understood by reference to the exemplary embodiments of the present disclosure shown in the accompanying drawings. However, the accompanying drawings show only typical embodiments of the present disclosure and, therefore, should not be regarded as limiting the scope. This is because the present disclosure may admit of other equally effective embodiments.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Best Mode for Carrying Out the Invention

[0010] For ease of understanding, where possible, the same reference numerals are used to denote identical elements common to these figures. These figures are not drawn to scale and may be simplified for clarity. Without additional elaboration, elements and features of one embodiment may be beneficially incorporated in other embodiments.

[0011] The methods and apparatuses described herein are configured to be used with a process chamber configured to process a substrate. For example, the process chamber can include one or more lamp housing sensors configured to detect lamp housing pressure, such as one or more lamp housing sensors configured to detect lamp housing pressure when used with a vacuum process chamber. In at least some embodiments, the methods and apparatuses described herein use one or more humidity sensors configured to detect relative humidity within the lamp housing, such as one or more humidity sensors configured to detect relative humidity within the lamp housing when used with an atmospheric pressure process chamber. For example, in either embodiment, the collected data from one or more lamp housing sensors or humidity sensors can be used to predict when cracks will occur / form on the lamp housing. For example, with respect to one or more lamp housing sensors, this collected data enables a user to determine lamp housing pressure changes that may correlate with early cracking. Similarly, with respect to humidity sensors, this collected data enables a user to determine lamp housing humidity changes that may correlate with early cracking. An automatic time series modeling using a window based on at least one of a moving average of the range of the collected data, which is the difference between the maximum value and the minimum value, or a standard deviation of the range of the collected data can be used to set a threshold value (e.g., failure vs. normal) of the collected data to alert the user of the detection of early cracking. The methods and apparatuses described herein can reduce, and in some cases eliminate, unscheduled downtime and the need for post-maintenance to replace the lamp housing, remove water leaks, and address additional failures of the lamp housing (and / or lamp head) and / or associated components due to water ingress.

[0012] FIG. 1 is a flow diagram of a method 100 for processing a substrate according to at least some embodiments of the present disclosure, and FIG. 2 is a tool 200 (or apparatus) that can be used to execute the method 100 according to at least some embodiments of the present disclosure.

[0013] The method 100 may be executed within the tool 200, and the tool 200 can include any suitable process chamber configured for one or more of physical vapor deposition (PVD), chemical vapor deposition (CVD), and / or atomic layer deposition (ALD), such as plasma ALD or thermal ALD (e.g., without plasma formation). Examples of processing systems that may be used to execute the methods of the present invention disclosed herein may include, but are not limited to, one or more process chambers commercially available from Applied Materials, Inc., Santa Clara, Calif., USA. Other process chambers including process chambers from other manufacturers may be suitably used in connection with the teachings provided herein.

[0014] The tool 200 can be implemented in individual process chambers that may be provided in a stand-alone configuration, or as part of a cluster tool, such as an integrated tool (tool 200) described below with respect to FIG. 2. Examples of integrated tools can include, but are not limited to, one or more process chambers commercially available from Applied Materials, Inc., Santa Clara, Calif., USA. The methods described herein may be implemented using other cluster tools with suitable process chambers coupled thereto, or in other suitable process chambers. For example, in some embodiments, the methods of the present invention discussed above may be executed within an integrated tool such that there is limited or no vacuum break between processing steps. For example, reduced vacuum break may limit or prevent contamination (e.g., oxidation) of one or more metal layers or other portions of the substrate.

[0015] The integrated tool includes a processing platform 201 (vacuum tight processing platform), a factory interface 204, and a controller 202. The processing platform 201 includes a plurality of process chambers such as 214A, 214B, 214C, and 214D operably coupled to a transfer chamber 203 (vacuum substrate transfer chamber) and process chambers 214E and 214F operably coupled to a buffer chamber 208 (vacuum substrate buffer chamber).

[0016] The factory interface 204 is operably coupled to the buffer chamber 208 by one or more load lock chambers (two load lock chambers such as 206A and 206B shown in FIG. 2). In at least some embodiments, one of the buffer chamber 208 or the transfer chamber 203 of the tool 200 can be omitted. One or more modules or channels can be provided between the buffer chamber 208 and the transfer chamber 203, and the one or more modules or channels can be configured to receive one or more substrates from the buffer chamber 208 and / or the transfer chamber 203. In at least some embodiments, modules 218A and 218B are provided between the buffer chamber 208 and the transfer chamber 203, and the modules 218A and 218B are configured to receive one or more substrates from the buffer chamber 208 and / or the transfer chamber 203 during operation, as will be described in more detail later. As described above, the modules 218A and 218B can have transparent covers.

[0017] In some embodiments, to facilitate the transfer of one or more semiconductor substrates (wafers), the factory interface 204 includes a docking station 207 and a factory interface robot 238. The docking station 207 is configured to receive one or more front opening unified pods (FOUPs). The embodiment of FIG. 2 shows four FOUPs, such as 205A, 205B, 205C, and 205D. The factory interface robot 238 is configured to transfer substrates from the factory interface 204 to the processing platform 201 through load lock chambers such as 206A and 206B. Each of the load lock chambers 206A and 206B has a first port coupled to the factory interface 204 and a second port coupled to the transfer chamber 203. The load lock chambers 206A and 206B are coupled to a pressure control system (not shown) that pumps down and vents the load lock chambers 206A and 206B to facilitate the transfer of substrates between the vacuum environment of the buffer chamber 208 and the substantially ambient (e.g., atmospheric) environment of the factory interface 204. In at least some embodiments, the buffer chamber 208 can be maintained in a substantially ambient environment. In embodiments where the buffer chamber 208 is not used, the load lock chambers 206A and 206B facilitate the transfer of substrates between the transfer chamber 203 and the factory interface 204. The buffer chamber 208 and the transfer chamber 203 each have a vacuum robot 242 disposed to transfer / receive one or more substrates. For example, the vacuum robot 242 in the buffer chamber 208 can receive / transfer the substrate 221 between the load lock chambers 206A and 206B, the process chambers 214E and 214F, and the modules 218A and 218F. Similarly, the vacuum robot 242 in the transfer chamber 203 can receive / transfer the substrate 221 between the process chambers 214A, 214B, 214C, and 214D and the modules 218A and 218F.

[0018] In some embodiments, process chambers 214A, 214B, 214C, 214D, 214E, and 214F may include at least an ALD chamber, a CVD chamber, a PVD chamber, an e-beam deposition chamber, and / or an electroless electroplating (EEP) deposition chamber. Also, in some embodiments, one or more optional service chambers (shown as 216A and 216B) may be coupled to buffer chamber 208. Service chambers 216A and 216B may be configured to perform other substrate processes, such as degassing, bonding, chemical mechanical polishing (CMP), annealing, substrate cleaning (e.g., pre-cleaning to remove oxidation), wafer sawing, etching, plasma dicing, alignment, substrate metrology, and cooling.

[0019] Controller 202 controls the operation of tool 200 using direct control of process chambers 214A, 214B, 214C, 214D, 214E and 214F and apparatus 212, or alternatively, controls the operation of tool 200 by controlling a computer (or controller) associated with process chambers 214A, 214B, 214C, 214D, 214E and 214F, apparatus 212 and tool 200. During operation, controller 202 enables data collection and feedback from the respective chambers and systems to optimize the performance of tool 200. For example, controller 202 can receive data from one or more sensors operably coupled to one or more of process chambers 214A, 214B, 214C, 214D, 214E and 214F, service chambers 216A and 216B and / or modules 218A and 218F. Controller 202 generally includes a central processing unit 230, a memory 234 and support circuitry 232. Central processing unit 230 may be any form of general-purpose computer processor that can be used in an industrial environment. Support circuitry 232 is conventionally coupled to central processing unit 230 and may include a cache, a clock circuit, an input / output subsystem, a power supply, etc. Software routines such as the processing methods described above may be stored in memory 234 (e.g., a non-transitory computer-readable storage medium) and, when executed by central processing unit 230, may transform central processing unit 230 into a special-purpose computer (e.g., controller 202). Those software routines may be stored and / or executed by a second controller (not shown) located remotely from tool 200.

[0020] Continuing to refer to FIG. 1, initially, one or more substrates, a thermal module assembly, etc. may be loaded into one or more of four FOUPs, such as 205A, 205B, 205C, and 205D (FIG. 2). For example, in at least some embodiments, the substrate 221 (wafer) can be loaded into the FOUP 205B. The substrate 221 can have a diameter of 150 mm, 200 mm, 300 mm, etc. The substrate 221 can be formed from germanium, silicon, silicon carbide, silicon oxide, etc. In at least some embodiments, the substrate 221 can have a diameter of 300 mm and can be formed from silicon. In at least some embodiments, one or more metal layers can be deposited on the substrate 221. For example, this one or more metal layers can include aluminum, cobalt, copper, nitride, titanium, tantalum, etc. In at least some embodiments, the substrate 221 can include a metal layer including cobalt and tungsten.

[0021] After being loaded, the factory interface robot 238 can transfer the substrate 221 from the factory interface 204 to the processing platform 201, for example, through the load lock chamber 206A. The vacuum robot 242 in the buffer chamber 208 can transfer the substrate 221 from the load lock chamber 206A to one or more of the process chambers 214A, 214B, 214C, 214D, 214E, and 214F, the service chambers 216A and 216B, and / or the modules 218A and 218B, and can transfer the substrate 221 from one or more of the process chambers 214A, 214B, 214C, 214D, 214E, and 214F, the service chambers 216A and 216B, and / or the modules 218A and 218B.

[0022] For example, in at least some embodiments, the vacuum robot 242 in the buffer chamber 208 can transfer the substrate 221 from the load lock chamber 206A to the service chambers 216A and 216B and / or the modules 218A and 218B, where one or more of outgassing, bonding, chemical mechanical polishing (CMP), annealing, substrate cleaning (oxide removal process), wafer dicing, etching, plasma dicing, orientation, substrate measurement, and / or cooling can be performed.

[0023] For example, as described above, the substrate 221 can be processed in one or more process chambers configured to process the substrate using the radiant heat provided by the lamp housing. For example, service chambers 216A and 216B (e.g., radiation chambers) can be configured to perform an annealing process (annealing chamber) or an oxidation removal process (oxidation chamber) each using relatively high heat. When performing such a process, service chambers 216A and 216B can include one or more sensors 300 (e.g., lamp housing sensors and / or relative humidity sensors) operably coupled to the lamp housing via one or more suitable coupling devices (e.g., bolts, clamps, etc.). For example, when service chambers 216A and 216B are configured to be used in a reduced pressure environment (e.g., annealing process), one or more sensors 300 can be configured to detect the lamp housing pressure (e.g., pressure sensor). Similarly, when service chambers 216A and 216B are configured to be used in an atmospheric pressure environment (e.g., oxidation removal process), one or more sensors 300 can be configured to detect the relative humidity within the lamp housing (e.g., relative humidity sensor). In either embodiment, the collected data from one or more sensors 300 can be used to predict when a lamp housing crack will occur / form. Due to the lamp housing crack, a coolant 304 (e.g., cooled or uncooled water from a coolant pipeline not shown) leaks from the lamp housing 302 into one or more lamp modules 306. One or more lamp modules 306 are configured to emit / radiate high heat through a lamp window 308 to process the substrate 221 (e.g., as indicated by arrow 310). The leaked coolant 304 can damage, and in some cases destroy, one or more lamp modules 306. This can cause unexpected downtime, labor hours, and potentially other related component failures.

[0024] In response, the inventor of the present invention has found that by using empirical data regarding pressure and / or relative humidity obtained during one or more annealing processes or oxidation removal processes respectively, lamp housing cracking can be determined / predicted, and damage caused by lamp housing cracking can be reduced and in some cases eliminated. The empirical data can be obtained over a long period (e.g., one week, two weeks, one month, two months, one year, two years, etc.). For example, regarding a reduced pressure environment, the inventor of the present invention has found that this collected data enables a user to determine lamp housing pressure changes that may correlate with early lamp housing cracking. Similarly, regarding an atmospheric pressure environment, the inventor of the present invention has found that this collected data enables a user to determine lamp housing humidity changes that may correlate with early housing cracking. In at least some embodiments, an automatic time series modeling using a window based on at least one of a moving average of the value range of the collected data or a standard deviation of the value range of the collected data, which is the difference between the maximum value and the minimum value, can also be used to set limit values (e.g., failure vs. normal) of the collected data to warn the user of early crack detection.

[0025] Accordingly, at 102, method 100 includes sequentially processing a plurality of substrates within a process chamber, and at 104, method 100 includes collecting lamp housing data indicative of a fluid leak (which may cause lamp housing cracking) within the lamp housing from a sensor operably connected to the lamp housing of the process chamber during processing of the plurality of substrates. For example, the automated time series modeling can include one or more of the following: a) collecting data of a plurality of substrate (wafer) runs (annealing and / or oxide removal processes), b) for each substrate run, calculating the range of that substrate run (e.g., the range can be defined as the value obtained by subtracting the minimum sensor value from the maximum sensor value obtained from one or more sensors 300), c) calculating a moving average of the ranges obtained by b), for example, based on the last X runs, d) calculating a standard deviation of the ranges obtained by the second step, for example, based on the last X runs, e) calculating a threshold value by adding the moving average obtained by step 3 to the standard deviation obtained by the fourth step, and f) calculating the range of the next substrate run and comparing the calculated range with the threshold value obtained by e).

[0026] Next, at 106, method 100 includes determining from the lamp housing data whether a lamp housing crack exists. For example, as described above, under the control of controller 202, substrate 221 can be transferred to one or both of service chambers 216A and 216B. For example, in at least some embodiments, substrate 221 can be transferred to service chamber 216A where an oxide removal process can be performed on substrate 221. Alternatively, or in addition, substrate 221 can be transferred to service chamber 216B where an annealing process can be performed on substrate 221.

[0027] In 106, method 100 can include comparing a first subset of lamp housing data (e.g., the empirical data collected during a) - e) of 102 and 104) collected while processing a first substrate of a plurality of substrates with a second subset of lamp housing data collected while processing a second substrate of the plurality of substrates (e.g., at f) of 104). In at least some embodiments, during 106, method 100 can include determining a threshold value based on a first subset of lamp housing data (e.g., obtained during e) of 104), generating a metric based on the second subset of lamp housing data, and comparing the metric to the threshold value (e.g., obtained during f) of 104).

[0028] For example, during performing an oxidation removal process, one or more sensors 300 (e.g., a relative humidity sensor) collect relative humidity data of the lamp housing 302 and transfer the relative humidity data to the controller 202. Similarly, during performing an annealing process, one or more sensors 300 (e.g., a pressure sensor) collect pressure data of the lamp housing 302 (e.g., a pressure change along the surface of the lamp housing 302) and transfer the lamp housing pressure data to the controller 202.

[0029] For example, the controller 202 can compare the collected lamp housing data with previously stored lamp housing data (e.g., the empirical data obtained by the previously executed annealing process and / or oxidation removal process between a) to e) of 102 and 104). This empirical data can be obtained over a fixed period of about one week to about two weeks, or in some embodiments less than one week or more than two weeks (e.g., one day to about two years) using time series modeling. In at least some embodiments, this period may not be fixed, and data can be collected using continuous time series modeling. In at least some embodiments, the controller 202 can be configured to perform the comparison at a predetermined time interval (e.g., a predetermined number of seconds, minutes, hours, etc.) or continuously during processing.

[0030] Next, at 108, in response to determining that there is a lamp housing crack, method 100 includes performing at least one of issuing an alarm or stopping the processing of the process chamber. For example, when performing an oxidation removal process, if the relative humidity of the lamp housing 302 becomes higher than a predetermined threshold value (for example, a humidity of about 50% to a humidity of about 60%), the controller 202 can issue an alarm and / or automatically stop the processing of the substrate. In at least some embodiments, the controller 202 can issue an alarm and the user can manually stop the processing of the substrate. In at least some embodiments, the controller 202 can be further configured to detect a time frame during which the relative humidity remains at a predetermined threshold value (for example, for the processing of at least one substrate). Similarly, when performing an annealing process, if the pressure of the lamp housing 302 becomes higher than a predetermined threshold value (for example, about 20 Torr to about 30 Torr), the controller 202 can issue an alarm and / or stop the processing of the substrate. In at least some embodiments, the controller 202 can be further configured to detect a time frame during which the pressure remains at a predetermined threshold value (for example, for at least one substrate). In at least some embodiments, for a particular substrate, the predetermined threshold values of relative humidity and pressure can be based on at least one of a moving average of the range of the collected data obtained by subtracting the minimum value from the maximum value of the collected data over a period (for example, about one week to about two weeks, or in some embodiments, a period less than one week or more than two weeks) during the respective time series modeling, or the standard deviation of the range of the collected data of the collected data.

[0031] If process chambers 214A, 214B, 214C, 214D, 214E, and 214F are configured to perform one or more of an annealing process or an oxidation removal process, method 100 including operations 102 - 108 can also be used with process chambers 214A, 214B, 214C, 214D, 214E, and 214F.

[0032] Furthermore, in some embodiments, method 100 can be based on a prediction of a machine learning process / artificial intelligence process that can predict when a lamp house crack can occur based on trends in previous pressure / humidity measurements and current pressure / humidity measurements. For example, the collected lamp data can be input into a trained machine learning model (which may be stored in memory 234, for example) that has been previously trained with old data, and the output of the trained machine learning model can be used to issue an alarm as described above. For example, in at least some embodiments, during 106, method 100 can include extracting one or more features from the time-series lamp housing data and providing the one or more features to a trained neural network configured to provide an output indicating whether a lamp housing crack is present. In at least some embodiments, the one or more features can include a value range obtained by subtracting the minimum value from the maximum value of the sensor values obtained between a) to f) in 102 and 104 as described above during substrate processing. For example, the obtained collected data can be input into a trained neural network, and the trained neural network can use a moving average and / or a standard deviation to determine a predetermined threshold (e.g., pressure / humidity), and can issue an alarm when the predetermined threshold is reached.

[0033] The above description is directed to embodiments of the present disclosure, but other and additional embodiments of the present disclosure may be devised without departing from the basic scope of the present disclosure.

Claims

1. A method associated with a process chamber having a lamp housing, the method comprising: sequentially processing a plurality of substrates within the process chamber; collecting lamp housing data indicative of fluid leakage within the lamp housing from a sensor operably connected to the lamp housing of the process chamber during processing of the plurality of substrates; determining from the lamp housing data whether a lamp housing crack exists; and performing at least one of issuing an alarm or stopping processing of the process chamber in response to determining that the lamp housing crack exists A method comprising the above steps.

2. Determining whether a lamp housing crack exists includes comparing a first subset of the lamp housing data collected while processing a first substrate of the plurality of substrates with a second subset of the lamp housing data collected while processing a second substrate of the plurality of substrates The method according to claim 1, including the above steps.

3. The comparing includes determining a threshold value based on the first subset of the lamp housing data; generating a metric based on the second subset of the lamp housing data; and comparing the metric with the threshold value The method according to any one of claims 1 or 2, including the above steps.

4. Determining whether a lamp housing crack exists includes extracting one or more features from the lamp housing data; and providing the one or more features to a trained neural network, the trained neural network providing an output indicating whether a lamp housing crack exists The method according to claim 1, including the above steps.

5. The method according to claim 4, wherein the one or more features include a value range obtained by subtracting a minimum value from a maximum value of sensor values obtained during substrate processing.

6. The method according to any one of claims 1, 2, 4 or 5, wherein the sensor is a pressure sensor configured to detect pressure along a surface of the lamp housing or a humidity sensor configured to detect relative humidity associated with the lamp housing.

7. The method according to claim 1, wherein the process chamber is a vacuum chamber.

8. The method according to claim 1, wherein the process chamber is an atmospheric chamber.

9. The method according to any one of claims 1, 2, 4, 5, 7 or 8, wherein the process chamber is at least one of an annealing chamber or an oxidation chamber.

10. A non-transitory computer-readable storage medium having instructions stored thereon that, when executed by a processor, cause a method related to a process chamber having a lamp housing to be executed, the method comprising: sequentially processing a plurality of substrates within the process chamber; collecting lamp housing data indicative of fluid leakage within the lamp housing from a sensor operably connected to the lamp housing of the process chamber during processing of the plurality of substrates; determining from the lamp housing data whether there is a lamp housing crack; and in response to determining that there is a lamp housing crack, performing at least one of issuing an alarm or stopping processing of the process chamber. A non-transitory computer-readable storage medium.

11. Determining whether there is a lamp housing crack includes: comparing a first subset of the lamp housing data collected while processing a first substrate of the plurality of substrates with a second subset of the lamp housing data collected while processing a second substrate of the plurality of substrates. The non-transitory computer-readable storage medium according to claim 10.

12. Determining a threshold value based on the first subset of the lamp housing data; generating a metric based on the second subset of the lamp housing data; comparing the metric with the threshold value. The non-transitory computer-readable storage medium according to any one of claims 10 or 11.

13. Determining whether there is a lamp housing crack includes: extracting one or more features from time-series lamp housing data; and providing the one or more features to a trained neural network, the trained neural network providing an output indicating whether there is a lamp housing crack. The non-transitory computer-readable storage medium according to claim 10.

14. The non-transitory computer-readable storage medium according to any one of claims 10, 11, or 13, wherein the one or more features include a value range obtained by subtracting a minimum value from a maximum value of sensor values obtained during substrate processing.

15. The non-transitory computer-readable storage medium according to claim 10, wherein the sensor is a pressure sensor configured to detect pressure along a surface of the lamp housing, or a humidity sensor configured to detect relative humidity associated with the lamp housing.

16. The non-transitory computer-readable storage medium according to claim 10, wherein the process chamber is a vacuum chamber.

17. The non-transitory computer-readable storage medium according to claim 10, wherein the process chamber is an atmospheric chamber.

18. The non-transitory computer-readable storage medium according to any one of claims 10, 11, 13, 15, 16, or 17, wherein the process chamber is at least one of an annealing chamber or an oxidation chamber.

19. An apparatus for processing a substrate, comprising: a process chamber configured to process the substrate using radiant heat provided by a lamp housing; a sensor operably connected to the lamp housing; a controller wherein the controller is configured to: sequentially process a plurality of substrates in the process chamber; collect lamp housing data indicating fluid leakage in the lamp housing from the sensor operably connected to the lamp housing of the process chamber during processing of the plurality of substrates; determine whether a lamp housing crack exists from the lamp housing data; perform at least one of issuing an alarm or stopping processing of the process chamber in response to determining that a lamp housing crack exists. An apparatus configured as such.

20. The process chamber according to claim 19, wherein the controller is further configured to compare a first subset of the lamp housing data collected while processing a first substrate of the plurality of substrates with a second subset of the lamp housing data collected while processing a second substrate of the plurality of substrates.

Images