TWI668540B - Condition monitoring method for manufacturing tool, semiconductor manufacturing system and condition monitoring method thereof - Google Patents

Abstract

The present disclosure provides a method of monitoring the condition of a manufacturing machine. The above method includes processing a substrate in a semiconductor manufacturing machine in accordance with a plurality of operating procedures of a manufacturing process. The above method further includes measuring the actual vibration waveform from one of the semiconductor manufacturing machines in each of the operating procedures. The above method also includes comparing the actual vibration waveform measured in one of the operational procedures with an expected vibration waveform associated with one of the operational procedures. Moreover, the above method includes issuing an alert based on the comparison described above when an amplitude difference between the actual vibration waveform and the data point corresponding to the expected vibration waveform exceeds an acceptable range of values.

Description

Condition monitoring method for manufacturing machine, semiconductor manufacturing system, and condition monitoring method thereof

Embodiments of the present invention relate to a semiconductor technology, and more particularly to a semiconductor manufacturing system and a method for monitoring the condition of the manufacturing machine.

In recent years, semiconductor integrated circuits have experienced exponential growth. In the advancement of integrated circuit materials and design techniques, multiple generations of integrated circuits have been produced, each of which has smaller and more complex circuits than the previous generation. In the development of an integrated circuit, when the geometric size (ie, the smallest component or line that can be produced in the process) is reduced, the functional density (ie, the number of interconnects per wafer area) It usually increases. In general, such a reduced size process can provide the benefits of increased production efficiency and reduced manufacturing costs. However, such reduced size processes also increase the complexity of manufacturing and manufacturing integrated circuits.

The integrated circuit is produced by processing a wafer by a series of semiconductor manufacturing machines (referred to as manufacturing machines). Each manufacturing machine typically performs an integrated circuit manufacturing process on the wafer (also known as a manufacturing process) based on a predefined or predetermined process recipe. Process) or process), wherein the process program defines various parameters of the process. For example, integrated circuit fabrication typically requires multiple production and support related manufacturing machines to perform multiple passes, and integrated circuit manufacturers need to focus on monitoring the hardware and associated of each manufacturing machine. Process to confirm and maintain the stability, repeatability and yield of integrated circuit manufacturing. Such machine monitoring can be accomplished by a fault detection and classification (FDC) system that monitors the manufacturing machine during the process and identifies the occurrence of the manufacturing machine and may cause the process to deviate from the original The expected condition is wrong.

Although the current state of the art monitoring methods and systems for manufacturing machines are sufficient to achieve their goals, these methods and systems are not satisfactory in all respects.

The present disclosure provides a method of monitoring the condition of a manufacturing machine. The above method includes processing a substrate in a semiconductor manufacturing machine in accordance with a plurality of operating procedures of a manufacturing process. The above method further includes measuring the actual vibration waveform from one of the semiconductor manufacturing machines in each of the operating procedures. The above method also includes comparing the actual vibration waveform measured in one of the operational procedures with an expected vibration waveform associated with one of the operational procedures. Moreover, the above method includes issuing an alert based on the comparison described above when an amplitude difference between the actual vibration waveform and the data point corresponding to the expected vibration waveform exceeds an acceptable range of values.

The present disclosure provides a method of monitoring a condition of a semiconductor manufacturing system. The above method includes moving a transfer member within a semiconductor manufacturing facility to transport a substrate. The above method further includes measuring one of the actual vibration data when the transport member moves to each of the selected positions. The above method also includes comparing one of the selections The actual vibration data measured at a given position and the expected vibration data associated with one of the selected locations. Moreover, the above method includes issuing an alert based on the comparison described above when an amplitude difference between the actual vibration data and the expected vibration data exceeds an acceptable range of values.

The present disclosure provides a semiconductor manufacturing system including a transmitting member, a detecting device, and an error detecting and sorting system. The transfer member is configured to transport a substrate within a semiconductor manufacturing facility. The detecting device is disposed on the conveying member. The error detection and classification system is configured to receive an actual vibration data measured by the detecting device when the transmitting member moves to each selected position, and compare the actual vibration data measured at one of the selected positions and associated with the A warning is issued when one of the selected positions is expected to vibrate and an amplitude difference between the actual vibration data and the expected vibration data exceeds an acceptable value range.

1‧‧‧Semiconductor Manufacturing System

10‧‧‧Network

20‧‧‧Database

30, 30a, 30b, 30c‧‧‧ manufacturing machine

31‧‧‧Reaction chamber

311‧‧‧ top shell

312‧‧‧Bottom cover/transport member

31A‧‧‧ Opening

31B‧‧‧ openings

32‧‧‧The boat

321‧‧‧Rotating platform

322‧‧‧heater

33‧‧‧ lower chamber

34‧‧‧ Lifting mechanism

341‧‧‧ screw

342‧‧‧ nut slider

35‧‧‧ Robotic arm

40‧‧‧Detection device

41‧‧‧Base

411‧‧‧ center pillar

412‧‧‧ openings

42‧‧‧Quality

43‧‧‧ Spring

44‧‧‧Piezoelectric components

45‧‧‧ lines

46‧‧‧Shell

50‧‧‧Advanced Process Control System

60‧‧‧Error Detection and Classification System

70‧‧‧Other entities

80‧‧‧Transfer

81‧‧‧ Track

82‧‧‧suspension vehicle/transport member

83‧‧‧ wafer carrier

100‧‧‧ Condition monitoring method for manufacturing machine

101-105‧‧‧ operation

200‧‧‧ Condition monitoring method for semiconductor manufacturing systems

201-205‧‧‧ operation

S1‧‧‧ upper surface

S2‧‧‧ lower surface

P1-P4‧‧‧ Location

W‧‧‧ wafer

1 shows a block diagram of a semiconductor fabrication system in accordance with some embodiments of the present invention.

Figure 2 shows a schematic diagram of a manufacturing machine in accordance with one of the embodiments.

Figure 3 shows a schematic diagram of a detection device in accordance with some embodiments.

Figure 4 shows a simplified flow diagram of a condition monitoring method for manufacturing a machine in accordance with one of the embodiments.

5A through 5E are schematic diagrams showing a plurality of main operational procedures of a manufacturing process implemented by a manufacturing machine, in accordance with some embodiments.

6A, 6B are graphs showing the expected vibration waveform versus time for a manufacturing machine in a wafer loading procedure, and the manufacturing machine is in accordance with some embodiments. A graph of the actual vibration waveform versus time measured in the wafer loading program.

7A, 7B are graphs showing the expected vibration waveform versus time for a manufacturing machine in a wafer transfer program, and the actual vibration waveforms measured by the manufacturing machine during the wafer transfer process, in accordance with some embodiments. A chart of the relationship to time.

8A, 8B are graphs showing the expected vibration waveform versus time for a manufacturing machine in a wafer processing program, and the actual vibration waveforms measured by the manufacturing machine in the wafer processing program, in accordance with some embodiments. A chart of the relationship to time.

Figure 9 shows a top view of a portion of a semiconductor fabrication system in accordance with some embodiments.

Figure 10 shows a simplified flow diagram of a condition monitoring method for a semiconductor fabrication system in accordance with some embodiments.

The embodiments and the embodiments disclosed below are intended to illustrate or complete the various features of the present invention. The specific embodiments of the described elements and arrangements are used to simplify the description of the present invention so that the disclosure can be more thorough and complete. The scope of the disclosure is fully conveyed to those skilled in the art. Of course, the disclosure may be embodied in many different forms and is not limited to the embodiments described below.

Spatially related terms as used hereinafter, such as "below", "below", "lower", "above", "higher" and the like, are used to facilitate the description of the illustration. Between one element or feature and another element or feature(s) Relationship. In addition to the orientation depicted in the drawings, these spatially related terms are also intended to encompass different orientations of the device in use or operation. For example, the device may be turned to a different orientation (rotated 90 degrees or other orientation), and the spatially related terms used herein may also be interpreted the same. In addition, if a first feature is formed on or above a second feature in the embodiment, it may indicate that the first feature may be in direct contact with the second feature, and may also include additional features. Formed between the first feature and the second feature described above such that the first feature and the second feature are not in direct contact with each other.

The same component numbers and/or characters may be repeated in the following various embodiments, which are for the purpose of simplification and clarity, and are not intended to limit the specific relationship between the various embodiments and/or structures discussed. In addition, in the drawings, the shape or thickness of the structure may be enlarged to simplify or facilitate the marking. It is to be understood that elements not specifically shown or described may be in various forms well known to those skilled in the art.

Figure 1 shows a block diagram of a semiconductor fabrication system 1 in accordance with some embodiments of the present invention. The semiconductor manufacturing system 1 can be a virtual integrated circuit manufacturing system (or a virtual wafer manufacturing facility). The semiconductor manufacturing system 1 implements a series of semiconductor manufacturing processes to produce integrated circuit devices. For example, the semiconductor fabrication system 1 can implement a semiconductor fabrication process on a substrate (or a wafer) to create material layers, pattern features, and/or integrated circuits. The substrate includes a semiconductor substrate (or wafer), a photomask, or any other substrate material. For the sake of clarity, the semiconductor manufacturing system 1 of Fig. 1 is simplified to facilitate a better understanding of the concepts of the present invention. Others can be added to the semiconductor manufacturing system 1 Features, and in other embodiments of semiconductor manufacturing system 1, certain features described below may also be replaced or removed.

The semiconductor manufacturing system 1 includes a network 10 for enabling a plurality of entities (e.g., a database 20, a manufacturing machine 30, a detecting device 40, an advanced process control (APC) system 50, and a false detection. The fault detection and classification (FDC) system 60, and other entities 70) are capable of communicating with each other. In some embodiments, semiconductor fabrication system 1 may include more than one of the various entities described above, and further includes other entities not illustrated in the described embodiments. In the embodiment of Figure 1, the various entities of the semiconductor manufacturing system 1 interact with other entities via the network 10 to provide services to other entities and/or to other services. Network 10 can be a single network or a variety of different networks, such as an internal network, the Internet, other networks, or a combination of the above. Network 10 includes a wired communication channel, a wireless communication channel, or a combination of both.

The database 20 is used to store data associated with the semiconductor manufacturing system 1, particularly data associated with semiconductor manufacturing processes. In some embodiments, the repository 20 stores data collected from the manufacturing machine 30, the detection device 40, the advanced process control system 50, the error detection and classification system 60, other entities 70, and combinations thereof. For example, the database 20 may store information relating to the wafer characteristics of the substrate processed by the manufacturing machine 30 (for convenience of description, hereinafter only the wafer is processed), associated with the manufacturing machine The data of the process parameters for processing the wafer, the data measured by the detection device 40 and the status of the manufacturing machine 30 in the semiconductor manufacturing process, associated with the advanced process control system 50 and errors Detection and classification system 60 for the above wafer Information on characteristics, process parameters, and/or conditions of the manufacturing machine 30, and other materials associated with the semiconductor manufacturing system 1. In some embodiments, each of manufacturing machine 30, detection device 40, advanced process control system 50, error detection and classification system 60, and other entities 70 may have a corresponding database.

The manufacturing machine 30 is used to execute a semiconductor manufacturing process (referred to as a process). According to some embodiments, the manufacturing machine 30 can be a chemical vapor deposition (CVD) machine, a physical vapor deposition (PVD) machine, an etching machine, and a Thermal oxidation machine, ion implantation machine, chemical mechanical polishing (CMP) machine, rapid thermal annealing (RTA) machine, one light A photolithography machine, a diffusion machine, or other semiconductor manufacturing machine.

FIG. 2 shows a schematic diagram of a manufacturing machine 30 in accordance with some embodiments. In the embodiment of Fig. 2, the manufacturing machine 30 is a chemical vapor deposition (CVD) machine, for example, including a furnace for performing a chemical vapor deposition process. After a wafer W is placed in the manufacturing machine 30, it is subjected to a chemical vapor deposition process in a high temperature environment, and a film can be formed on the surface.

The manufacturing machine 30 includes a reaction chamber 31, a boat 32, and a lower chamber 33. The reaction chamber 31 has a top case 311 and a bottom cover 312. The top case 311 extends a height in its longitudinal axis (i.e., the Z-axis direction in the drawing). The upper end of the top case 311 is closed. The lower end of the top case 311 is open and allows the boat 32 to be moved into or out of the reaction chamber 31 for batch processing of the wafer W. The bottom cover 312 is detachably coupled to the top case 311 and is sealable The lower end of the top case 311. For example, the bottom cover 312 is driven by a lifting mechanism 34 to be movable relative to the top case 311. When the bottom cover 312 is moved to the position shown in FIG. 2 and connected to the lower end of the top case 311, the reaction chamber can be A sealed environment is established in chamber 31. Since the bottom cover 312 can be used to transfer the wafer W into the reaction chamber 31, the bottom cover 312 is also referred to as a "transport member" in the following description.

The boat 32 is disposed on the upper surface S1 of the bottom cover 312 and faces the reaction chamber 31. In the deposition process, the wafer boat 32 is used to support and hold a plurality of vertically stacked wafers W, and allows a reactive gas to flow horizontally through the surface of the wafer W to form a desired film thereon. thickness. For the sake of brevity, the gas supply and exhaust systems connected to the openings 31A, 31B on the side walls of the reaction chamber 31 are not shown in Fig. 2, nor are they shown to uniformly distribute the reaction gas in the reaction. The airflow within the chamber 31 directs the structure (e.g., a fan and/or nozzle tube). In some embodiments, the bottom of the boat 32 is coupled to a rotating platform 321 for rotating the boat 32 during the deposition process to increase the uniformity of deposition of the wafer W. The rotating platform 321 also has a heater 322 for heating the wafer W to promote film formation thereon.

The lower chamber 33 is located below the reaction chamber 31 to facilitate the operation of loading or unloading the wafer W into the wafer boat 32. In the embodiment of FIG. 2, the lifting mechanism 34 for driving the bottom cover 312 is a lead screw disposed in the lower chamber 33 to convert the rotational motion of a screw 341 into a nut slip. The linear movement of the member 342 causes the bottom cover 312 attached to the nut slider 342 to move up and down along the Z-axis direction. For the sake of brevity, the mechanism for driving the screw 341 to rotate is not shown in FIG. In some embodiments, the pump, pipeline, and/or other components included in the gas supply and exhaust system described above may also be disposed on Inside the lower chamber 33 (not shown).

Returning to Figure 1, in some embodiments, the detection device 40 is used to measure and collect information on the condition of the manufacturing machine 30 in the semiconductor manufacturing process. For example, detection device 40 can include a vibration meter for measuring vibration waveforms from manufacturing machine 30 in a semiconductor manufacturing process. This information can be used to determine if the operational status of the manufacturing machine 30 (and/or the semiconductor manufacturing process it is performing) is normal, an impending exception, or has deviated from the originally anticipated condition and must immediately cease operation.

In some embodiments, the detection device 40 is disposed on one of the movable members of the manufacturing machine 30. For example, in the embodiment of Fig. 2, the detecting device 40 is mounted on the bottom cover 312 (transport member) of the furnace tube and is movable with the bottom cover 312. The procedure for moving the bottom cover 312 will be further explained in the following paragraphs with reference to Figures 5A-5E.

In some embodiments, the detection device 40 is disposed in a location in the manufacturing machine 30 that is not directly exposed to reactive gases and high temperature environments. For example, in the embodiment of FIG. 2, the detecting device 40 can be mounted to the lower surface S2 of the bottom cover 312 and toward the lower chamber 33. In this way, the detection device 40 can be prevented from being affected by the chemical attack and high temperature in the reaction chamber 31, so as to have a long service life and stable measurement performance. However, many other variations and modifications are possible in the disclosed embodiments. For example, the detection device 40 can also be embedded in the bottom cover 312 (not exposed). Alternatively, the detecting device 40 may be mounted on the side wall of the lower chamber 33 without moving with the bottom cover 312 (transport member).

FIG. 3 shows a schematic diagram of a detection device 40 in accordance with some embodiments. In the embodiment of FIG. 3, the detecting device 40 is a piezoelectric vibration sensor. A piezoelectric vibration sensor includes a base 41, a mass 42, a spring 43, a piezoelectric element 44, and a plurality of wires 45. As shown in Fig. 3, the spring 43, the mass 42 and the piezoelectric element 44 are sequentially mounted on a center post 411 connected to the base 41 (i.e., the mass 42 is sandwiched between the spring 43 and the pressure). Between electrical components 44). An opening 412 is formed on one of the outer sides of the base 41 for coupling with a fixing member (for example, a bolt, not shown), and the detecting device 40 is fixed to the object to be tested (for example, the bottom cover 312 of the manufacturing machine 30). . One end of each line 45 is electrically connected to the piezoelectric element 44, and the other end extends to the outside of the detecting device 40, thereby deriving the measured electrical signal (for example, voltage V).

With the above configuration, when the detecting device 40 is vibrated (for example, when the vibration generated by the bottom cover 312 of the manufacturing machine 30 is transmitted to the detecting device 40), the force applied to the piezoelectric element 44 by the mass 42 changes accordingly. And the change in the force is proportional to the vibration acceleration of the measured object. Thereby, the piezoelectric effect of the piezoelectric element 44 can be further utilized to obtain a voltage value proportional to the vibration acceleration of the object to be measured. In other words, the voltage value (unit, for example, microvolt (μV)) measured by the detecting device 40 can be used to indicate the magnitude of the vibration acceleration of the object to be measured (unit is, for example, unit of gravity acceleration (G)).

In some embodiments, the detection device 40 can also include a housing 46. As shown in FIG. 3, the outer casing 46 can be coupled to the base 41 and covered with the mass 42, the spring 43, and the piezoelectric element 44 to reduce the electrical signal measured by the detecting device 40 from the external environment (for example, temperature change). The impact of ). It should be understood that in order to measure the vibration condition of the measured object, the detecting device 40 may also adopt other kinds of vibration measuring sensors (such as eddy current type, capacitive or fiber type displacement sensor, and laser type). Linear Velocity Transducer, Acceleration Sensor, or Pressure Resistive (MEMS) MEMS accelerometers are not limited to the above embodiments.

Returning to Figure 1, an Advanced Process Control (APC) system 50 is used to monitor the wafer characteristics of the wafer being processed, and can utilize on-line measurement data (e.g., the data collected by the detection device 40 described above), Process mode, and a variety of algorithms to provide dynamic fine-tuning of intermediate process targets to achieve the final product goal of the wafer. Fine-tuning of the above process targets can also be referred to as control actions, which compensate for hardware tool issues and/or process issues that may cause variations in wafer characteristics. The advanced process control system 50 can perform control actions in real time, wafer-to-wafer, batch-to-batch, or a combination thereof.

In some embodiments, advanced process control system 50 performs control actions to modify the process programs executed by manufacturing machine 30 for processing wafers. For example, the advanced process control system 50 (depending on the inspection data of the processed wafer, the process mode, and various algorithms) modifies a predetermined process sequence for each wafer being processed (especially, by the manufacturing machine 30) Process parameters such as processing time, gas flow rate, reaction chamber pressure, temperature, wafer temperature, and other process parameters) to ensure that each wafer being processed meets the final product target. In some embodiments, advanced process control system 50 (according to the data collected by detection device 40 described above) performs control actions to modify predetermined process programs executed by manufacturing machine 30 and to stop manufacturing machine 30 The operation (for example, stopping the operation of the rotating platform 321 in the reaction chamber 31 and stopping the supply of the reaction gas into the reaction chamber 31, etc.) to avoid abnormal process targets and/or wafer scrapping.

Error Detection and Classification (FDC) system 60 monitors manufacturing machines 30 process parameters implemented in a semiconductor manufacturing process (including the data collected by the detection device 40 described above), and wafer characteristics obtained by monitoring process parameters implemented by the manufacturing machine 30 in a semiconductor manufacturing process to evaluate manufacturing The condition of the machine 30 and the detection of whether an error has occurred, for example, the condition of the machine is degraded. An embodiment of monitoring the condition of the manufacturing machine 30 by the measuring device 40 will be further described in the following paragraphs.

In some embodiments, the error detection and classification system 60 implements a statistical process control (SPC) to track and analyze the condition of the manufacturing machine 30. For example, the error detection and classification system 60 can implement one or more statistical process control (SPC) charts that record the manufacturing machine 30 by plotting the statistical process control data associated with the process in a time chart. Historical process data. The statistical process control data described above includes associated process parameters (and/or wafer features) implemented by manufacturing machine 30. When the statistical process control data indicates that the process parameters are deviating from an acceptable target (in other words, when the error detection and classification system 60 detects an error or anomaly), the error detection and classification system 60 can trigger a warning. An operator of the manufacturing machine 30 is notified to suspend the operational procedures performed by the manufacturing machine 30, take another action, or a combination of the above, such that any problems with the manufacturing machine 30 can be identified and remedied.

In the embodiments described later, the error detection and classification system 60 monitors process parameters associated with the manufacturing machine 30 to monitor the condition of the manufacturing machine 30 (eg, a chemical vapor deposition (CVD) machine). More specifically, the error detection and classification system 60 can detect an error or anomaly of the manufacturing machine 30 by evaluating process parameters (e.g., a magnitude of vibration acceleration) of the manufacturing machine 30 during the manufacturing process, such as a manufacturing machine. The deterioration of one of the stages 30.

Figure 4 shows a simplified flow diagram of a condition monitoring method 100 for manufacturing a machine in accordance with one of the embodiments. For the sake of explanation, the flowchart will be described together with reference to Figs. 1 to 3 and Figs. 5 to 8. Additionally, in some other embodiments, some of the operational procedures of the subsequent manufacturing process may be replaced or cancelled. It should be understood that the following discussion of the state of the chemical vapor deposition (CVD) machine is merely an example, and the condition monitoring method 100 of the manufacturing machine can also be implemented by the semiconductor manufacturing system 1 to monitor any kind of manufacturing machine 30 and The condition of any of the modules in the machine 30 is manufactured.

As shown in FIG. 4, the condition monitoring method 100 of the manufacturing machine includes an operation 101 in which an expected vibration waveform associated with the manufacturing machine 30 is collected. In some embodiments, the measurement device 40 (eg, a vibration sensor) can be used to measure and collect from various operational procedures of the manufacturing process performed by the manufacturing machine 30 (eg, a chemical vapor deposition machine). The vibration data of the machine 30 is manufactured, and the collected vibration data is transmitted to the database 20 for storage.

5A-5E show schematic diagrams of a number of primary operational procedures for manufacturing processes implemented by manufacturing machine 30, in accordance with some embodiments. In FIG. 5A, a plurality of wafers W are loaded through a robot arm 35 to the wafer boat 32 that stays in the lower chamber 33 (hereinafter, simply referred to as a wafer loading procedure). In FIG. 5B, after the wafer boat 32 is loaded with the wafer W, the bottom cover 312 (transport member) is moved toward the top case 311 by the driving of the elevating mechanism 34, and the wafer W on the wafer boat 32 is sent. The reaction chamber 31 (hereinafter referred to as a wafer transfer program for short) is referred to. In Fig. 5C, after the bottom cover 312 is joined to the lower end of the top case 311, a sealed environment can be established in the reaction chamber 31. Then, the wafer W is subjected to a chemical vapor deposition process in the reaction chamber 31, for example, in a high temperature environment, by a reaction gas. A resist gas flows through the surface of the wafer W and forms a deposited film thereon (hereinafter, this operation procedure is a wafer processing procedure for short). In FIG. 5D, after the deposition process is finished, the bottom cover 312 is moved toward the lower chamber 33 by the driving of the lifting mechanism 34, and the wafer W on the wafer boat 32 is sent out of the reaction chamber 31 (this procedure is also Called a wafer transfer program). In FIG. 5E, the wafer W is unloaded from the wafer boat 32 through the robot arm 35 (hereinafter, simply referred to as a wafer unloading procedure).

It should be understood that the operational procedures implemented by the manufacturing machine 30 are merely illustrative for the purpose of illustration and are not intended to limit the disclosure. In some embodiments, the above described operating procedures may also be replaced or cancelled, or some other operating procedure may be added to the manufacturing process.

In some embodiments, in each of the operational procedures performed by the manufacturing machine 30, the metrology device 40 can instantly measure and collect vibrational data from the manufacturing machine 30. For example, the measuring device 40 can record the vibration data of the manufacturing machine 30 in each operating program at regular time intervals (for example, 0.5 seconds), that is, in each operating program, the measuring device 40 can measure and record more. Pen vibration data. Thereafter, the vibration data described above can be transmitted to the database 20 for storage.

In some embodiments, no errors or anomalies are found at the manufacturing machine 30 and all wafers W can be properly processed (eg, no particles or foreign matter adhere to the surface of the wafer W, or thickness, uniformity, and expected deposition of the film) In the case where the targets are all consistent, the operation 101 may be repeated a plurality of times (for example, several times or tens of times), that is, the plurality of vibrations of each operation program when the manufacturing machine 30 performs the multiple manufacturing processes by the measuring device 40 is collected. The data is transmitted to the database 20 for storage.

It should be understood that the above vibration data is stored in the database 20 Before further processing, it can be further processed. For example, a mean value of a plurality of pieces of vibration data associated with each of the operational procedures of the manufacturing process described above can be calculated by the error detection and classification system 60 and stored in the database 20. In addition, one of the plurality of pieces of vibration data associated with each operating program can also be calculated by the error detection and classification system 60 and stored in the database 20.

In this way, a big data pattern associated with the vibration condition in each operating program of the manufacturing machine 30 can be stored in the database 20, thereby obtaining an expected vibration associated with each operating program of the manufacturing machine 30. The waveform (i.e., the vibration waveform when the manufacturing machine 30 is in normal operation). For example, Figures 6A, 7A, and 8A respectively show that the manufacturing machine 30 stored in the database 20 is in a wafer loading program (Fig. 5A), a wafer transfer program (Fig. 5B), or A graph of expected vibration waveform versus time (T-charts) in a wafer processing program (Fig. 5C).

As shown in FIG. 4, the condition monitoring method 100 of the manufacturing machine further includes an operation 102 in which another batch of wafers W are processed in the manufacturing machine 30. According to some embodiments, the wafer W of this batch can be processed in accordance with the same operational procedures as disclosed in Figures 5A through 5E.

The condition monitoring method 100 of the manufacturing machine also includes an operation 103 in which the vibration data from the manufacturing machine 30 is collected using the measuring device 40 (while performing the operation 102). In some embodiments, in each of the operational procedures in which the manufacturing machine 30 implements the manufacturing process described above, the metrology device 40 again measures and collects vibrational data from the manufacturing machine 30. For example, in each of the operational procedures disclosed in FIGS. 5A to 5E, the measuring device 40 is used to instantly measure and collect the vibration from the manufacturing machine 30. The data, wherein the measuring device 40 can measure the vibration data of the manufacturing machine 30 in each operating program at regular intervals.

In some embodiments, the measurements performed by the metrology device 40 in operation 103 correspond to the measurements performed by the metrology device 40 in operation 101. For example, the point at which the measuring device 40 performs the recording in operation 103 is the same as the point at which the measuring device 40 performs the recording in operation 101 (i.e., in operations 101 and 103, the measuring device 40 can be the same and regular time). Interval to record multiple pieces of vibration data in each of the above operating procedures). Additionally or alternatively, the location of the measurement performed by measurement device 40 in operation 103 may be the same as the location of the measurement performed by measurement device 40 in operation 101. Of course, there are many other variations and modifications of the disclosed embodiments. For example, with respect to operation 101, in operation 103, measurement device 40 can record as many of the operational procedures of manufacturing machine 30 at smaller intervals. Pen vibration data.

In operation 103, the error detection and classification system 60 is also used to convert the vibration data collected by the measurement device 40 from the manufacturing machine 30 into an actual vibration waveform corresponding to one of the above operational procedures. For example, the 6B, 7B, and 8B diagrams respectively show that the manufacturing machine 30 is in a wafer loading procedure (5A) collected by the metrology device 40 and processed by the error detection and classification system 60 in accordance with some embodiments. Figure), a wafer transfer program (Fig. 5B) or a wafer processing program (Fig. 5C), one of the actual vibration waveform versus time graph (T-charts).

The condition monitoring method 100 of the manufacturing machine further includes an operation 104 in which the actual vibration waveform measured in operation 103 is collected and stored in the manufacturing flow (operation 101) previously executed by the manufacturing machine 30. The expected vibration waveforms in the library 20 are compared. In some embodiments, the actual vibration described above The comparison of the waveform to the expected vibration waveform is performed by error detection and classification system 60.

In some embodiments, prior to comparing the actual vibration waveform with the expected vibration waveform, the error detection and classification system 60 can obtain the actual vibration waveform and the expected vibration waveform in each operation program by analyzing the waveform versus time relationship graph. One of the range of amplitude differences is an acceptable range of values.

In some embodiments, the acceptable range of values for the amplitude difference described above may be one or a few standard deviations of the expected vibration waveform in each operating sequence. For example, in Figures 6A, 7A, and 8A, an upper limit control (maximum value) is set to the average of the expected vibration waveform plus one or several standard deviations, and a lower limit control (minimum value) is set to the average of the expected vibration waveforms. The value is subtracted by one or several standard deviations, and the difference between the upper and lower limit controls becomes an acceptable range of values associated with the amplitude difference of each operating procedure. Of course, there are many other variations and modifications in the disclosed embodiments. For example, the acceptable numerical range of the amplitude difference may also be a specific ratio of the maximum amplitude value of the expected vibration waveform in each operating procedure. And the ratio can be determined by the operator based on manufacturing experience or test results, and the error detection and classification system 60 is set. In addition, the acceptable range of values for the amplitude differences of the various operating procedures may be the same or different.

In operation 104, after an acceptable range of values for the amplitude difference between the actual vibration waveform and the expected vibration waveform is determined in each operating sequence, the error detection and classification system 60 measures the result in operation 103 by comparison. The actual vibration waveforms obtained are compared with the expected vibration waveforms stored in the database 20 to determine whether the amplitude difference between the corresponding data points on the two waveforms exceeds the above acceptable numerical range. If not, the condition monitoring method 100 of the manufacturing machine can repeat the above operation. 102 to 104 until all wafers W are processed. If so, the condition monitoring method 100 of the manufacturing machine continues with operation 105 to issue an alarm condition.

For example, in Figure 6B, when a portion of the data points on the actual vibration waveform measured in a wafer loading program exceeds an acceptable range of values (such as the circled portion in the figure), A component of the robot arm 35 that loads the wafer W to the wafer boat 32 may be deteriorated, so that the wafer W may not be accurately transported to a predetermined position on the boat 32, and collide with peripheral components of the boat 32, Causes abnormal vibrations.

In Figure 7B, when a portion of the data point on the actual vibration waveform measured in a wafer transfer program exceeds an acceptable value range (for example, the circled portion in the figure), it means that the bottom cover is driven. A certain component of the lifting mechanism 34 of 312 may be deteriorated (for example, the lubricant on the screw 341 is largely volatilized), and the bottom cover 312 is caused to generate abnormal vibration while moving.

In Figure 8B, when a portion of the data points on the actual vibration waveform measured in a wafer processing program exceeds an acceptable range of values (for example, the portion circled in the figure), it is associated with the deposition process. A certain hard part of the manufacturing machine 30 (for example, the rotating platform 321 includes a built-in motor or gear, a fan in the reaction chamber 31, or a pump in the lower chamber 33, etc.) or a process step (for example, a reaction chamber) The chemical reaction or the distribution of the gas flow in the chamber 31, etc. may cause a problem and abnormal vibration is formed.

Based on the above description, when the error detection and classification system 60 detects that the actual vibration waveform of the manufacturing machine 30 at a particular time in an operating procedure deviates from the expected vibration waveform (ie, an error or an abnormality is detected), It is indicated that some portion of the manufacturing machine 30 associated with this operating program may be degraded. As a result, The operation program of the manufacturing machine 30 (at the time point) and the error or abnormality associated with the relevant part of the operation program (on the position point) can be immediately found.

In addition, in order to prevent the abnormal vibration in one of the above operating procedures from causing damage to the manufacturing machine 30 or the wafer W, the error detection and classification system 60 may issue an alert to notify the operator of the manufacturing machine 30 to suspend the manufacturing machine. The operation of the station 30, taking another action, or a combination of the above, causes any problems with the manufacturing machine 30 to be promptly identified and remedied.

In some embodiments, the error detection and classification system 60 can also implement a Fast Fourier Transform to convert the actual vibration waveform from a time domain waveform to a frequency domain waveform, wherein The resulting frequency domain waveforms include data on amplitude at different frequencies. By analyzing the frequency domain waveform, the amplitude of each vibration source in the manufacturing machine 30 corresponding to different vibration frequencies can be obtained (the vibration source is, for example, a motor, a pump, or a fan, which have different vibration frequencies and amplitudes, respectively). Moreover, it can be measured by the measuring device 40 in advance, and further, it is determined which vibration source has a vibration abnormality, so that the operator can identify the problem and improve it more quickly.

Furthermore, the measuring device 40 can be used to detect errors of other different devices in the semiconductor manufacturing system 1 (for example, one of the transmitting devices 80 in FIG. 9) in addition to the error detection of the manufacturing machine 30. Or abnormal.

Figure 9 shows a top view of a portion of a semiconductor fabrication system 1 in accordance with some embodiments. The semiconductor manufacturing system 1 (for example, a semiconductor wafer fabrication facility) includes a plurality of manufacturing machines 30, 30a, 30b, 30c, and a conveyor 80. The manufacturing machines 30a, 30b, 30c and the manufacturing machine 30 (for example, the chemical vapor deposition machine described above) may be machines that perform the same or different processes. Transfer device 80 The substrate is transferred between the manufacturing machines 30, 30a, 30b, 30c, such as a wafer or a reticle (for convenience of explanation, only the substrate to be transferred is represented by a wafer hereinafter).

In the embodiment of Figure 9, the conveyor 80 includes a track 81 that is secured to the ceiling of the wafer fabrication facility and disposed above the manufacturing machines 30, 30a, 30b, 30c. The conveyor 80 also includes an overhead hoist vehicle 82 that is configured to move along the track 81 and transport the wafer between the manufacturing machines 30, 30a, 30b, 30c. More specifically, the suspended carrier 82 can grab a wafer carrier 83 in which one or more wafers are housed, and more preferably at a selected position on the track 81 (as shown in the figure P1) , P2, P3 or P4) transporting the wafer carrier cassette 83 to one of the manufacturing machines 30, 30a, 30b, 30c for wafer processing, and after wafer processing, the wafer carrier box 83 Transfer to the other of the manufacturing machines 30, 30a, 30b, 30c for another wafer processing.

In the embodiment of Fig. 9, the measuring device 40 (for example, the vibration sensor) is mounted on the suspended carrier 82 so that it can be moved along the rail 81 together with the suspended carrier 82. A plurality of selected locations within the wafer fabrication facility (eg, locations where tracks 81 are distributed). Since the suspended carrier 82 can be used to transport wafers within a wafer fabrication facility, the suspended carrier 82 is also referred to as a "transporting member" in the following description. The measuring device 40 is configured to evaluate an operating parameter (eg, a magnitude of vibration acceleration) of the transmitting device 80 during the process of transporting the wafer by the suspended carrier 82 to detect an error or abnormality of the transmitting device 80, such as transmitting The degradation condition of a portion of the device 80.

Figure 10 shows a simplified flow diagram of a condition monitoring method 200 of a semiconductor fabrication system in accordance with some embodiments. For the sake of explanation, it will be referred to the ninth The figures together describe the flow chart. It should be understood that since the condition monitoring method 200 of the semiconductor manufacturing system is similar to the operation and concept of the condition monitoring method 100 of the manufacturing machine described above, only the different technical features of the condition monitoring method 200 of the semiconductor manufacturing system will be described below.

As shown in FIG. 10, the condition monitoring method 200 of the semiconductor manufacturing system includes an operation 201 in which an expected vibration waveform associated with one of the transmission members (for example, the suspended carrier 82) in the semiconductor manufacturing system 1 is collected. In some embodiments, the vibration data from the transfer member 82 can be measured and collected by the measuring device 40 during the transfer of the wafer along the track 81 by the transfer member 82, and the collected vibration data can be transmitted to the database. 20 for storage. In some embodiments, the metrology device 40 can instantly measure and collect vibrational data from the transport member 82. For example, the measuring device 40 can record the vibration data of the transport member 82 during the movement at a regular time interval (e.g., 0.5 seconds), that is, the plurality of strokes of the transport member 82 at different selected positions on the track 81 can be measured and recorded. Vibration data. Thereafter, the vibration data described above can be transmitted to the database 20 for storage.

In some embodiments, operation 201 may be repeated multiple times without any errors or anomalies being found during transfer of the wafer by transfer member 82 (eg, no transfer of artifacts when transport member 82 moves along track 81). (for example, several times or tens of times), that is, the collecting member 82 is repeatedly used to rotate the plurality of pieces of vibration data along the track 81 by the measuring device 40, and the vibration data is transmitted to the data bank 20 for storage. .

It should be understood that the plurality of pieces of vibration data may be further calculated by the error detection and classification system 60 before being stored in the database 20 to obtain an average value and a standard deviation.

In this way, a big data pattern associated with the vibration condition when the transfer member 82 is moved to a different selected position can be stored in the database 20, thereby obtaining one expected vibration when the transfer member 82 moves along the track 81. The waveform (i.e., the vibration waveform of the transmitting member 82 in normal operation).

As shown in FIG. 10, the condition monitoring method 200 of the semiconductor manufacturing system further includes an operation 202 in which another batch of wafers are transferred by the transfer member 82 at the wafer fabrication facility. In some embodiments, the speed at which the transfer member 82 transfers the wafer in operation 202 is the same as in operation 201.

The condition monitoring method 200 of the semiconductor manufacturing system further includes an operation 203 in which the vibration data from the transfer member 82 is collected using the measurement device 40 (while performing the operation 202). In some embodiments, during the transfer of the wafer along the track 81 by the transfer member 82, the measurement device 40 is used to again measure and collect the vibrational data of the transfer member 82 at different selected locations.

In some embodiments, the measurements performed by the metrology device 40 in operation 203 correspond to the measurements performed by the metrology device 40 in operation 201. For example, the point at which the measuring device 40 performs the recording in operation 203 is the same as the point at which the measuring device 40 performs the recording in operation 201 (i.e., in operations 201 and 203, the measuring device 40 can be the same and regular time). The interval is used to record a plurality of pieces of vibration data during the movement of the conveying member 82). Additionally or alternatively, the location point at which the metrology device 40 performs the measurement in operation 203 may be the same as the location point at which the metrology device 40 performs the measurement in operation 201.

In addition, in operation 203, the vibration data collected by the measuring device 40 from the transmitting member 82 is also converted into an actual vibration waveform by the error detection and classification system 60.

The condition monitoring method 200 of the semiconductor manufacturing system further includes an operation 204 in which the actual vibration waveform measured in operation 203 is compared with the expected vibration waveform (in operation 201) stored in the database 20. In some embodiments, the comparison of the actual vibration waveform to the expected vibration waveform is performed by the error detection and classification system 60. The error detection and classification system 60 can compare the actual vibration waveform with the expected vibration waveform and determine whether the amplitude difference between the corresponding data points on the two waveforms exceeds an acceptable numerical range (may be similar to Figure 6-8). The method of implementation of the disclosure is obtained). If not, the condition monitoring method 200 of the semiconductor manufacturing system can repeat the above operations 202 to 204. If so, the condition monitoring method 200 of the semiconductor manufacturing system continues with operation 205 to issue an alert.

For example, when the error detection and classification system 60 detects that the actual vibration waveform of the transmitting member 82 at a certain point in time deviates from the expected vibration waveform (ie, the amplitude difference between the two waveforms exceeds an acceptable numerical range), That is, it indicates that some portion of the transport device 80 may be deteriorated or abnormal. For example, a relative offset may occur between the plurality of engaging portions of the track 81 to cause abnormal vibration generation.

In some embodiments, in order to prevent the abnormal vibration of the transmitting member 82 during the movement, the wafer W may be damaged, the error detection and classification system 60 may issue an alert to notify the operator to pause when an abnormality is detected. Movement of the transfer member 82, taking another action, or a combination of the above. In this way, it is possible to immediately recognize the point of the problem where the conveying device 80 has a problem (for example, the point at which the conveying member 82 is suspended or its vicinity), and it is advantageous for the problem to be quickly remedied.

Embodiments of the present invention also include a computer system that performs the various methods and systems described above, such as monitoring and evaluating the condition of manufacturing machine 30 or transfer device 80 in semiconductor manufacturing system 1. In some embodiments, the above error detection The classification and classification (FDC) system 60 includes the computer system described above to monitor the condition of the manufacturing machine 30 or the conveyor 80. In various implementations, the apparatus of the computer system includes a network communication device or a network computing device (eg, a mobile phone, capable of communicating with the network 10 (eg, an internal network or the Internet). Laptop, PC, web server). It should be understood that each of the above-described devices can be implemented as the above-described computer system for communicating with the network 10 in accordance with a mode as will be described later. In accordance with various embodiments of the present invention, the computer system (eg, a near-end computer or a networked computer system) includes a bus bar component or other communication mechanism for communicating information that connects the subsystem and components, such as a processing component ( For example, a processor, a microcontroller, a digital signal processor (DSP), other processing elements, or a combination thereof, a system memory component (eg, random access memory (RAM)), a static storage component (eg, , read only memory (ROM), a disk component (eg, a magnetic component, an optical component, other components, or a combination thereof), a network interface component (eg, a data machine, an Ethernet card) , other network interface components, or a combination thereof, a display component (eg, a cathode ray tube (CRT), a liquid crystal display (LCD), other display components, or a combination thereof), an input component (eg, a keyboard) , a cursor control element (eg, a mouse or trackball), and an image capture component (eg, an analog or digital camera). In one embodiment, the disk component includes a library of one or more disk components.

In accordance with some embodiments of the present invention, the computer system described above, by the processor, executes one or more sequences of one or more instructions stored in the system memory element to perform a particular operation. In some embodiments, media (eg, static storage elements or disk components) can be read from other computers, Instructions read into system memory components. In other embodiments, hardware circuit loops may be used in place of (or in combination with) software instructions to implement the present invention. In accordance with various embodiments of the present invention, a logic is loaded onto a computer readable medium, which is any medium that participates in providing instructions to a processing element for execution. This media can take many forms, including but not limited to: non-volatile media and volatile media. In one embodiment, the computer readable medium is non-transitory. In various implementations, the non-volatile media includes optical or magnetic disks, such as disk components, while the volatile media includes dynamic memory, such as system memory components. In one embodiment, the information and information about the execution of the instructions are transmitted to the computer system via a transmission medium, such as in the form of sound waves or light waves, including those generated in radio wave and infrared data communication. In accordance with various embodiments of the present invention, a transmission medium includes a coaxial cable, a copper wire, and an optical fiber, including an electrical wire including a busbar.

Some general forms of computer readable media include, for example, a floppy disk, a flexible disk, a hard disk, a magnetic tape, any other magnetic media, a CD-ROM, Any other optical media, punch cards, paper tape, any other physical medium with puncturing patterns, random access memory (RAM), programmable read-only memory (PROM), Can erase programmable read-only memory (EPROM), flash erasable programmable read-only memory (FLASH-EPROM), any other memory or disk cartridge, carrier wave, or Any other media that the computer can read. In accordance with various embodiments of the present invention, the computer system described above executes a sequence of instructions to implement the invention. According to other various embodiments of the present invention, various computer systems, such as computer systems, are coupled by communication lines (eg, like LAN, WLAN, PTSN, and/or Or a variety of other wired or wireless networks (including telecommunications, wireless, and cellular networks) and execute sequences of instructions to implement the present invention in conjunction with other systems. According to various embodiments of the present invention, the computer system transmits and receives messages, data, information, and instructions through a communication connection and a communication interface, including one or more programs (in other words, application code). The processing component can execute the received code and/or the code stored in the disk component or some other non-volatile storage component for execution.

Where applicable, various embodiments of the invention may be implemented using hardware, software, or a combination of hardware and software. Moreover, where applicable, the various hardware components and/or software components described above are incorporated into a composite component including software, hardware, or both without departing from the spirit of the present disclosure. Where applicable, the various hardware components and/or software components described above are divided into secondary components including software, hardware, or both without departing from the scope of the present disclosure. In addition, where applicable, it is to be understood that the software components can be implemented as hardware components and vice versa. In accordance with the present disclosure, software (such as computer code and/or material) can be stored on one or more computer readable media. It should also be understood that the above software may use one or more general purpose or special purpose computers and/or computer systems, networked and/or unconnected. Where applicable, the order of the various steps described above can be changed, incorporated in a composite step, and/or separately as a sub-step to provide the functionality described herein.

In summary, the disclosed embodiments have the advantage of utilizing an instant measurement of vibration to detect errors or anomalies in various manufacturing machines, devices, or transfer members in a semiconductor manufacturing system. The measured actual vibration waveform can be compared with the expected vibration waveform measured under the same conditions, so it can be more accurate Determine whether an abnormal condition has occurred. When an abnormal condition occurs, the error detection and classification system can immediately respond and notify the maintenance personnel to properly handle it, thereby reducing or avoiding damage to the manufacturing machine or other supporting device for processing the semiconductor substrate, and reducing wafer scrapping. .

According to some embodiments, a condition monitoring method for a manufacturing machine is provided. The above method includes processing a substrate in a semiconductor manufacturing machine in accordance with a plurality of operating procedures of a manufacturing process. The above method further includes measuring the actual vibration waveform from one of the semiconductor manufacturing machines in each of the operating procedures. The above method also includes comparing the actual vibration waveform measured in one of the operational procedures with an expected vibration waveform associated with one of the operational procedures. Moreover, the above method includes issuing an alert based on the comparison described above when an amplitude difference between the actual vibration waveform and the data point corresponding to the expected vibration waveform exceeds an acceptable range of values.

According to some embodiments, the condition monitoring method of the manufacturing machine further includes suspending operation of the semiconductor manufacturing machine based on the alert.

According to some embodiments, the condition monitoring method of the manufacturing machine further includes collecting a plurality of pieces of vibration data from the semiconductor manufacturing machine in each of the operational procedures of the pre-executed manufacturing process. In addition, the condition monitoring method of the manufacturing machine includes storing the vibration data in a database, wherein the expected vibration waveform is obtained from the database.

According to some embodiments, the condition monitoring method of the manufacturing machine further includes converting the actual vibration waveform from a time domain waveform to a frequency domain waveform. Further, the method for monitoring the condition of the manufacturing machine includes obtaining the amplitude of each of the vibration sources in the semiconductor manufacturing machine corresponding to the different vibration frequencies based on the frequency domain waveform, and further determining which vibration source has a vibration abnormality.

According to some embodiments, a semiconductor fabrication machine includes a reaction chamber having a top case and a bottom cover. The bottom cover is configured to carry the substrate in the above operating procedure and is movable relative to the top case. The actual vibration waveform is measured by a detecting device provided on the bottom cover.

According to some embodiments, a condition monitoring method of a semiconductor manufacturing system is provided. The above method includes moving a transfer member within a semiconductor manufacturing facility to transport a substrate. The above method further includes measuring one of the actual vibration data when the transport member moves to each of the selected positions. The method further includes comparing the actual vibration data measured at one of the selected locations and the expected vibration data associated with one of the selected locations. Moreover, the above method includes issuing an alert based on the comparison described above when an amplitude difference between the actual vibration data and the expected vibration data exceeds an acceptable range of values.

According to some embodiments, the condition monitoring method of the semiconductor manufacturing system further includes suspending movement of the transfer member based on the alert.

According to some embodiments, the transfer member is a suspended carrier configured to move along a track and transfer the substrate between the selected locations. The actual vibration waveform is measured by a detecting device provided on the conveying member.

According to some embodiments, the transfer member is a semiconductor manufacturing machine for carrying one of the bottom covers of the substrate, configured to feed the substrate into and out of a reaction chamber of the semiconductor manufacturing machine. The actual vibration waveform is measured by a detecting device provided on the conveying member.

In accordance with some embodiments, a semiconductor fabrication system is provided that includes a transfer member, a detection device, and an error detection and classification system. The transfer member is configured to transport a substrate within a semiconductor manufacturing facility. The detecting device is set at On the transfer member. The error detection and classification system is configured to receive an actual vibration data measured by the detecting device when the transmitting member moves to each selected position, and compare the actual vibration data measured at one of the selected positions and associated with the A warning is issued when one of the selected positions is expected to vibrate and an amplitude difference between the actual vibration data and the expected vibration data exceeds an acceptable value range.

The embodiments and their advantages are described in detail above, and it is understood that various changes, substitutions and modifications may be made in the present disclosure without departing from the spirit and scope of the disclosure. Further, the scope of the present application is not intended to be limited to the specific embodiments of the process, the machine, the manufacture, the material composition, the tool, the method and the steps described in the specification. It will be readily apparent to those skilled in the art from this disclosure that, in accordance with the present disclosure, substantially the same functions or implementations as those of the corresponding embodiments described herein may be utilized. The resulting process, machine, manufacturing, material composition, tool, method or procedure. Therefore, the scope of the appended claims is intended to cover such processes, machines, manufacture, compositions of matter, tools, methods or steps. In addition, each patent application scope constitutes a separate embodiment, and combinations of different application patent scopes and embodiments are within the scope of the disclosure.

Claims (10)

A method for monitoring condition of a manufacturing machine, comprising: processing a substrate in a semiconductor manufacturing machine according to a plurality of operating procedures of a manufacturing process; and in each of the operating procedures, measuring an actual one from the semiconductor manufacturing machine a vibration waveform; comparing the actual vibration waveforms measured in the operational procedures with a plurality of expected vibration waveforms associated with the operational programs; and based on the comparison, one of the actual vibration waveforms A warning is issued when an amplitude difference between corresponding data points on the associated expected vibration waveform exceeds an acceptable range of values. The method for monitoring the condition of the manufacturing machine according to claim 1, further comprising: suspending operation of the semiconductor manufacturing machine based on the warning. The method for monitoring condition of a manufacturing machine according to claim 1, further comprising: collecting a plurality of pieces of vibration data from the semiconductor manufacturing machine in each operation procedure of a pre-executed manufacturing process; The vibration data is stored in a database, wherein the expected vibration waveform is obtained from the database. The method for monitoring condition of a manufacturing machine according to claim 1, further comprising: converting the actual vibration waveform from a time domain waveform to a frequency domain waveform; and obtaining the corresponding vibration frequency based on the frequency domain waveform Semiconductor manufacturing The amplitude of each vibration source in the machine is determined, and it is determined which vibration source has a vibration abnormality. The condition monitoring method of the manufacturing machine according to any one of claims 1 to 4, wherein the semiconductor manufacturing machine comprises a reaction chamber having a top case and a bottom cover, the bottom cover being configured For carrying the substrate in the operating procedures and moving relative to the top case, the actual vibration waveform is measured by a detecting device disposed on the bottom cover. A method of monitoring a condition of a semiconductor manufacturing system, comprising: moving a transfer member in a semiconductor manufacturing factory to transfer a substrate; measuring an actual vibration data when the transfer member is moved to each selected position; comparing at the selected positions The actual vibration data measured at a time and a plurality of expected vibration data associated with the selected locations; and based on the comparison, between one of the actual vibration data and the associated expected vibration data An alert is issued when an amplitude difference exceeds an acceptable range of values. The condition monitoring method of the semiconductor manufacturing system of claim 6, further comprising: suspending movement of the transmitting member based on the warning. The condition monitoring method of the semiconductor manufacturing system of claim 6, wherein the transfer member is a suspended carrier configured to move along a track and transfer the substrate between the selected positions. The actual vibration waveform is measured by a detecting device provided on the conveying member. The condition monitoring method of the semiconductor manufacturing system of claim 6, wherein the transfer member is a semiconductor manufacturing machine for carrying the a bottom cover of the substrate, and the bottom cover is configured to feed the substrate into and out of a reaction chamber of the semiconductor manufacturing machine, the actual vibration waveform is measured by a detecting device disposed on the transmitting member . A semiconductor manufacturing system comprising: a transfer member configured to transport a substrate in a semiconductor manufacturing facility; a detecting device disposed on the transfer member; and an error detection and classification system configured to receive the detection The device measures an actual vibration data of the transmission member when moving to each selected position, and compares the actual vibration data measured at the selected positions with a plurality of expected vibrations associated with the selected positions The data, and an alert is issued when an amplitude difference between one of the actual vibrational data and the associated expected vibrational data exceeds an acceptable range of values.